Tao Liu

EAAI Journal 2026 Journal Article

A Chinese financial event knowledge graph-based retrieval-augmented generation framework for financial question answering

• Haitao Cheng
• Ke Wang
• Qi Wang
• Tao Liu
• Kai Sheng

Financial question answering in the Chinese domain presents significant challenges due to complex domain-specific terminology and the integration of heterogeneous financial research reports from multiple institutions. To address these issues, we propose a Chinese financial event knowledge graph-based retrieval-augmented generation framework. The framework constructs a structured index via semantic-aware text chunking and large language model-driven triplet extraction, incorporating a generation–verification mechanism to ensure reliable and relevant information retrieval. To mitigate vague or underspecified user queries that commonly occur in Chinese due to implicit expressions and unclear word boundaries, a reinforcement learning-based query reformulation module generates domain-specific representations, improving retrieval intent alignment. A dual-level retrieval mechanism is designed to retrieve core entities via semantic similarity and then expand event chains through knowledge graph-based neighbor expansion. Experimental results across three question types (single-hop, multi-hop, and open-ended) and four evaluation dimensions (comprehensiveness, diversity, empowerment, and overall performance) demonstrate that the proposed framework consistently outperforms baseline models, showing superior performance across various financial question answering tasks.

AAAI Conference 2026 Conference Paper

Realistic Curriculum Reinforcement Learning for Autonomous and Sustainable Marine Vessel Navigation

• Xiaocai Zhang
• Zhe Xiao
• Maohan Liang
• Tao Liu
• Haijiang Li
• Wenbin Zhang

Sustainability is becoming increasingly critical in the maritime transport, encompassing both environmental and social impacts, such as Greenhouse Gas (GHG) emissions and navigational safety. Traditional vessel navigation heavily relies on human experience, often lacking autonomy and emission awareness, and is prone to human errors that may compromise safety. In this paper, we propose a Curriculum Reinforcement Learning (CRL) framework integrated with a realistic, data-driven marine simulation environment and a machine learning-based fuel consumption prediction module. The simulation environment is constructed using real-world vessel movement data and enhanced with a Diffusion Model to simulate dynamic maritime conditions. Vessel fuel consumption is estimated using historical operational data and learning-based regression. The surrounding environment is represented as image-based inputs to capture spatial complexity. We design a lightweight, policy-based CRL agent with a comprehensive reward mechanism that considers safety, emissions, timeliness, and goal completion. This framework effectively handles complex tasks progressively while ensuring stable and efficient learning in continuous action spaces. We validate the proposed approach in a sea area of the Indian Ocean, demonstrating its efficacy in enabling sustainable and safe vessel navigation.

JBHI Journal 2026 Journal Article

Whisperization and Masked CycleGAN-Based Framework for Electrolaryngeal Speech Enhancement

• Jie Zhou
• Li Wang
• Fengji Li
• Shaochuan Zhang
• Fan Fan
• Tao Liu
• Xiaohong Chen
• Haijun Niu

Electrolarynx (EL) provides an effective approach to voice rehabilitation for patients with phonation disorder. However, due to its reliance on an external mechanical source, EL speech suffers from limited acoustic cues, leading to degraded quality and restricting the potential of subsequent modeling and enhancement. This paper proposes a novel EL speech enhancement framework that combines whisperization with Masked CycleGAN model. The whisperization step removes redundant constant excitation and mechanical noise, generating an intermediate speech form—whisper-like EL (W-EL) speech, whose acoustic and perceptual properties are closer to natural whisper. Subsequently, the Masked CycleGAN employs a frame-level masking strategy to guide the generator in reconstructing missing prosodic and linguistic features. Thus, we achieved a dual-stage enhancement of “redundancy removal” and “deficiency compensation. ” Acoustic feature analysis demonstrates that the converted W-EL speech is more similar to normal speech in terms of spectrogram, fundamental frequency (F0) values, and F0 contours, while also compensating for the missing low frequency energy below 500 Hz. Objective evaluations show significant improvements across multiple metrics. Subjective evaluations confirm that W-EL speech exhibits higher naturalness and intelligibility compared to original EL speech. Moreover, the combined “whisperization + voice conversion” framework further enhances perceptual quality. This study not only offer a novel pathway for EL speech enhancement, but also may provide valuable insights for improving other types of pathological speech.

EAAI Journal 2025 Journal Article

A multi-scale feature and cross-domain fusion network for image tampering localization

• Fan Deng
• Tao Liu
• Haibo Yu
• Ruitao Yang

As a phenomenal communication application based on artificial intelligence forms, the potential social harm of image tampering is prominent. Despite the significant research achievements attained by existing works, the current methods fall short in adequately extracting and integrating features from different frequency domains, and they exhibit limitations when confronted with tampered images that have undergone post-processing operations. To address these problems, we propose a multi-scale features and cross-domain fusion network (MFCF-Net). First, the simple linear iterative clustering algorithm is adopted to achieve growth, merging, and segmentation within the spatial domain. Second, uneven blur features are captured by introducing a Local Self-Attention Mechanism (LSAM) block and an Edge Feature Enhancement Module (EFEM). Third, a complete cross-domain fused feature is obtained by combining a Multi-Scale Feature Fusion (MSFF) and a Cross-Domain Fusion Module (CDFM), thereby enhancing the module's ability to recognize subtle changes in the tampered area. Finally, the detection and localization of tampered regions are achieved by utilizing the dual-matching algorithm for multi-scale feature matching. Extensive experiments indicate that the MFCF-Net possesses higher detection accuracy on six benchmark datasets and exhibits excellent performance when dealing with tampered images that have undergone post-processing operations.

JBHI Journal 2025 Journal Article

Addressing Multiple Challenges in Early Gait Freezing Prediction for Parkinson's Disease: A Practical Deep Learning Approach

• Wenan Wang
• Jingfeng Lin
• Xinning Le
• Yaru Li
• Tao Liu
• Lunxin Pan
• Min Li
• Dezhong Yao

Objective: Freezing of Gait (FOG) significantly impacts daily activities of Parkinson's disease (PD) patients. Despite the potential of wearable sensors in predicting FOG, challenges persist, including the brief prediction interval before FOG onset, limited generalization across patients, and the inconvenience of multiple sensors. Addressing one issue often aggravates others, making it difficult to achieve suitable concurrent solutions to all these challenges. Methods: We introduce the PhysioGait Predictive Network (PhysioGPN), a deep learning framework designed to predict FOG events in PD patients at least 2 seconds prior to onset. The model architecture incorporates four key strategies: 1) Detection of progressive motion changes using large convolutional kernels; 2) Unraveling the complexity of motion coordination and gait dynamics using multi-dimensional and multi-scale convolution; 3) Capture gait self-similarity and asymmetry with twin-tower structure; 4) Promoting cross-domain information exchange with multi-domain attention. Furthermore, we propose a framework based on knowledge distillation (KD), reducing the model's dependence on multiple sensors while maintaining prediction accuracy. Results: The model achieves an 85. 8% Area Under the Curve (AUC) in FOG prediction. When reducing the number of sensors, KD mitigates the decline in performance and increases the AUC by 5. 1%, compared to scenarios without KD. Conclusion: Our research proposes a practical solution to the challenges of FOG prediction, demonstrating the effectiveness of the KD approach for lightweight wearable sensors in rehabilitation engineering. Significance: Our findings offer valuable insights for addressing multiple challenges in the practical application of wearable devices.

IROS Conference 2025 Conference Paper

ContextCache: Task-Aware Lifecycle Management for Memory-Efficient LLM Agent Deployment

• Tao Liu
• Ping Guo
• Dong Feng
• Peng Wang

LLM-based agents have demonstrated remarkable capabilities in multi-step reasoning and task execution across domains such as robotics and autonomous systems. However, deploying these agents on resource-constrained platforms presents a fundamental challenge: minimizing latency while optimizing memory usage. Existing caching techniques (KVCache, PrefixCache, PromptCache) improve inference speed by reusing cached context but overlook LLM dependency relationships in agent workflows, leading to excessive memory usage or redundant recomputation across LLM calls. To address this, we propose ContextCache, a task-aware lifecycle management framework that optimizes context fragment caching for multi-step LLM agents. ContextCache predicts the lifespan of each context fragment and dynamically allocates and releases GPU memory accordingly. We evaluate our approach on a newly constructed dataset, covering logistics coordination, assembly tasks, and health management. Experimental results demonstrate a 15% reduction in memory usage compared to state-of-the-art caching strategies, with no loss in inference efficiency, making our approach well-suited for real-world deployment in resource-constrained environments.

YNIMG Journal 2025 Journal Article

Decoding cortical folding patterns in marmosets using machine learning and large language model

• Yue Wu
• Xuesong Gao
• Zhengliang Liu
• Pengcheng Wang
• Zihao Wu
• Yiwei Li
• Tuo Zhang
• Tianming Liu

Macroscale neuroimaging results have revealed significant differences in the structural and functional connectivity patterns of gyri and sulci in the primate cerebral cortex. Despite these findings, understanding these differences at the molecular level has remained challenging. This study leverages a comprehensive dataset of whole-brain in situ hybridization (ISH) data from marmosets, with updates continuing through 2024, to systematically analyze cortical folding patterns. Utilizing advanced machine learning algorithm and large language model (LLM), we identified genes with significant transcriptomic differences between concave (sulci) and convex (gyri) cortical patterns. Further, gene enrichment analysis, neural migration analysis, and axon guidance pathway analysis were employed to elucidate the molecular mechanisms underlying these structural and functional differences. Our findings provide new insights into the molecular basis of cortical folding, demonstrating the potential of LLM in enhancing our understanding of brain structural and functional connectivity.

ECAI Conference 2025 Conference Paper

Degree of Staleness-Aware Data Updating in Federated Learning

• Tao Liu
• Xuehe Wang

Handling data staleness remains a significant challenge in federated learning with highly time-sensitive tasks, where data is generated continuously and data staleness largely affects model performance. Although recent works attempt to optimize data staleness by determining local data update frequency or client selection strategy, none of them explore taking both data staleness and data volume into consideration. In this paper, we propose Data Updating in Federated Learning (DUFL), an incentive mechanism featuring an innovative local data update scheme manipulated by three knobs: the server’s payment, outdated data conservation rate, and clients’ fresh data collection volume, to coordinate staleness and volume of local data for best utilities. To this end, we introduce a novel metric called Degree of Staleness (DoS) to quantify data staleness and conduct a theoretic analysis illustrating the quantitative relationship between DoS and model performance. We model DUFL as a two-stage Stackelberg game with dynamic constraint, deriving the optimal local data update strategy for each client in closed-form and the approximately optimal strategy for the server. Experimental results on real-world datasets demonstrate the significant performance of our approach.

EAAI Journal 2025 Journal Article

Efficient generation of power system topology diagrams based on Graph Neural Network

• Chen Yang
• Shengyang Wu
• Tao Liu
• Yixuan He
• Jingyu Wang
• Dongyuan Shi

Power system topology diagrams illustrate the physical and spatial relationship of system nodes and are widely used as a basic tool for displaying system structure. Well-presented topology diagrams provide better situational awareness for the operators, but their efficient generation remains a challenge. Existing approaches struggle to find a balance between visual aesthetics and the generation speed of the diagram. With the rapid changes in power system topology, there is a higher demand for the rendering speed of the graph data. To satisfy both the real-time requirement and the aesthetic quality, this paper proposes an integrated framework for efficiently generating power system topology diagrams. It consists of a Graph Neural Network (GNN) model and a graph fine-tuning model. This framework can directly optimize the raw topology diagram while preserving the relative positions of nodes in the initial layout. It achieves a decent trade-off between layout quality and computational expenses, enabling the generation of aesthetically satisfactory diagrams in a short time. Due to the strong generalization ability of GNN, the proposed model can be trained on small system datasets and used for inference on large systems. Case studies verify that the proposed GNN model can optimize the aesthetic metrics of topology diagram layouts within seconds to an average value of 0. 55. Finally, it can be used in power system applications as a fundamental tool for topology diagram generation and optimization.

JBHI Journal 2025 Journal Article

Extraction of Fetal ECG by Logarithmic Hyperbolic Secant Adaptive Algorithm in Alpha-Stable Noise

• Mengjia Wang
• Deqiu Zhai
• Jiacheng Zhang
• Bo Ni
• Tao Liu

Direct fetal electrocardiogram (FECG) plays a crucial role in assessing fetal health and monitoring pregnancy conditions. Extracting high-quality FECG signals from maternal abdominal electrocardiogram (AECG) recordings remains a significant challenge due to the low amplitude of the FECG, its overlap with the maternal electrocardiogram (MECG), and the potential exposure to impulsive noise in the real world. Adaptive filtering (AF) is an essential method for FECG extraction, however, its performance tends to degrade in the presence of impulsive noise, such as instrument interference. To address this limitation, we propose a novel AF algorithm based on a nonlinear logarithmic hyperbolic secant (LHS) cost function. Alpha-stable distribution is adopted to model the realistic noises due to its high scalability. To further enhance extraction accuracy and optimize the preset parameters, we introduce a hyperbolic tangent-like transformation and develop the improved logarithmic hyperbolic secant adaptive filtering (ILHSAF) algorithm. The proposed approach leverages the approximate linear interval of the LHS function to maximize the preservation of original FECG information within the AECG. We use the synthetic dataset FECGSYN as well as two real datasets, Daisy and NI-FECG, to evaluate the performance and our methods outperform other existing AF algorithms. The ILHSAF algorithm exhibits commendable performance in R-peak detection and full-wave analysis on both real-world datasets, indicating its effective denoising capability and robustness in FECG extraction. This advancement establishes a foundation for long-term maternal and fetal monitoring using portable devices, as the proposed algorithms are capable of real-time operation.

NeurIPS Conference 2025 Conference Paper

From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging

• Tao Liu
• Dafeng Zhang
• Gengchen Li
• Shizhuo Liu
• yongqi song
• Senmao Li
• Shiqi Yang
• Boqian Li

Face aging has become a crucial task in computer vision, with applications ranging from entertainment to healthcare. However, existing methods struggle with achieving a realistic and seamless transformation across the entire lifespan, especially when handling large age gaps or extreme head poses. The core challenge lies in balancing $age\ accuracy$ and $identity\ preservation$—what we refer to as the $Age\text{-}ID\ trade\text{-}off$. Most prior methods either prioritize age transformation at the expense of identity consistency or vice versa. In this work, we address this issue by proposing a $two\text{-}pass$ face aging framework, named $Cradle2Cane$, based on few-step text-to-image (T2I) diffusion models. The first pass focuses on solving $age\ accuracy$ by introducing an adaptive noise injection ($AdaNI$) mechanism. This mechanism is guided by including prompt descriptions of age and gender for the given person as the textual condition. Also, by adjusting the noise level, we can control the strength of aging while allowing more flexibility in transforming the face. However, identity preservation is weakly ensured here to facilitate stronger age transformations. In the second pass, we enhance $identity\ preservation$ while maintaining age-specific features by conditioning the model on two identity-aware embeddings ($IDEmb$): $SVR\text{-}ArcFace$ and $Rotate\text{-}CLIP$. This pass allows for denoising the transformed image from the first pass, ensuring stronger identity preservation without compromising the aging accuracy. Both passes are $jointly\ trained\ in\ an\ end\text{-}to\text{-}end\ way\$. Extensive experiments on the CelebA-HQ test dataset, evaluated through Face++ and Qwen-VL protocols, show that our $Cradle2Cane$ outperforms existing face aging methods in age accuracy and identity consistency. Additionally, $Cradle2Cane$ demonstrates superior robustness when applied to in-the-wild human face images, where prior methods often fail. This significantly broadens its applicability to more diverse and unconstrained real-world scenarios. Code is available at https: //github. com/byliutao/Cradle2Cane.

ICRA Conference 2025 Conference Paper

GS-EVT: Cross-Modal Event Camera Tracking Based on Gaussian Splatting

• Tao Liu
• Runze Yuan
• Yi'ang Ju
• Xun Xu
• Jiaqi Yang
• Xiangting Meng
• Xavier Lagorce
• Laurent Kneip

Reliable self-localization is a foundational skill for many intelligent mobile platforms. This paper explores the use of event cameras for motion tracking thereby providing a solution with inherent robustness under difficult dynamics and illumination. In order to circumvent the challenge of event camera-based mapping, the solution is framed in a cross-modal way. It tracks a map representation that comes directly from frame-based cameras. Specifically, the proposed method operates on top of gaussian splatting, a state-of-the-art representation that permits highly efficient and realistic novel view synthesis. The key of our approach consists of a novel pose parametrization that uses a reference pose plus first order dynamics for local differential image rendering. The latter is then compared against images of integrated events in a staggered coarse-to-fine optimization scheme. As demonstrated by our results, the realistic view rendering ability of gaussian splatting leads to stable and accurate tracking across a variety of both publicly available and newly recorded data sequences.

NeurIPS Conference 2025 Conference Paper

GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation

• Tao Liu
• Chongyu Wang
• Rongjie Li
• Yingchen Yu
• Xuming He
• Song Bai

While Multimodal Large Language Models (MLLMs) have advanced GUI navigation agents, current approaches face limitations in cross-domain generalization and effective history utilization. We present a reasoning-enhanced framework that systematically integrates structured reasoning, action prediction, and history summarization. The structured reasoning component generates coherent Chain-of-Thought analyses combining progress estimation and decision reasoning, which inform both immediate action predictions and compact history summaries for future steps. Based on this framework, we train a GUI agent, GUI-Rise, through supervised fine-tuning on pseudo-labeled trajectories and reinforcement learning with Group Relative Policy Optimization (GRPO). This framework employs specialized rewards, including a history-aware objective, directly linking summary quality to subsequent action performance. Comprehensive evaluations on standard benchmarks demonstrate state-of-the-art results under identical training data conditions, with particularly strong performance in out-of-domain scenarios. These findings validate our framework's ability to maintain robust reasoning and generalization across diverse GUI navigation tasks.

EAAI Journal 2025 Journal Article

Identification of zinc stripping defects from cathode plate based on deep learning

• Tao Liu
• Yibin Liu
• Jian Chen
• Jin Gong

During hydro-zinc smelting, the cathode plates are attached by with residual zinc or discarded due to damaged insulation strips and edging strips. Such defects limit the recycling of cathode plates. Current manual observation leads to low accuracy and speed of recognition owing to perception biases. Therefore, this work applied computer vision and deep learning semantic segmentation technology to realize the defect recognition of cathode plates. Firstly, a semantic segmentation dataset on cathode plates was constructed for training and testing the model. Then a network of attention mechanism and multiscale feature fusion (AMNet) was proposed to detect the defects. In AMNet, the encoder-decoder jump connection architecture was designed to fuse low-level and high-level features. A channel attention module was incorporated to enhance focus on the channels with important information, and the newly proposed multiscale feature extraction module was used to solve the problem of target multiscale capture. Through related parameter selection experiments, the final AMNet achieved 95. 12% and 97. 73% for Mean Intersection over Union (MIoU) and mean pixel accuracy (MPA), respectively. These values are 3. 24 and 1. 74 percentage points higher than DeepLabv3+.

ICLR Conference 2025 Conference Paper

One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

• Tao Liu
• Kai Wang 0060
• Senmao Li
• Joost van de Weijer 0001
• Fahad Shahbaz Khan
• Shiqi Yang 0002
• Yaxing Wang
• Jian Yang 0003

Text-to-image generation models can create high-quality images from input prompts. However, they struggle to support the consistent generation of identity-preserving requirements for storytelling. Existing approaches to this problem typically require extensive training in large datasets or additional modifications to the original model architectures. This limits their applicability across different domains and diverse diffusion model configurations. In this paper, we first observe the inherent capability of language models, coined $\textit{context consistency}$, to comprehend identity through context with a single prompt. Drawing inspiration from the inherent $\textit{context consistency}$, we propose a novel $\textit{training-free}$ method for consistent text-to-image (T2I) generation, termed "One-Prompt-One-Story" ($\textit{1Prompt1Story}$). Our approach $\textit{1Prompt1Story}$ concatenates all prompts into a single input for T2I diffusion models, initially preserving character identities. We then refine the generation process using two novel techniques: $\textit{Singular-Value Reweighting}$ and $\textit{Identity-Preserving Cross-Attention}$, ensuring better alignment with the input description for each frame. In our experiments, we compare our method against various existing consistent T2I generation approaches to demonstrate its effectiveness, through quantitative metrics and qualitative assessments. Code is available at https://github.com/byliutao/1Prompt1Story.

JBHI Journal 2025 Journal Article

PPA Net: The Pixel Prediction Assisted Net for 3D TOF-MRA Cerebrovascular Segmentation

• Zhiqi Lee
• Tao Liu
• Haonan Zhang
• Xiang Zhang
• Xuan Li
• Yizhen Pan
• Tingting Wu
• Jierui Ding

Cerebrovascular segmentation is essential for diagnosing and treating cerebrovascular diseases. However, accurately segmenting cerebral vessels in TOF-MRA remains challenging due to significant interindividual variations in cerebrovascular morphology, low image con-trast, and class imbalance. The present study proposes an advanced deep learning model called PPA Net, consisting of VesselMRA Net and VesselConvLSTM components. Firstly, VesselMRA Net utilizes rectangular convolutional blocks to fuse multi-scale features, enhancing feature extraction per-formance. VesselMRA Net employs the attention mechanism to boost certain valuable semantic weighting, addressing segmentation challenges arising from class imbalance and low contrast. Secondly, VesselConvLSTM, a pixel-level prediction model, employs a gating mechanism to learn cerebral vessel morphology across individuals. It reduces individual differences in segmentation and restores inter-voxel correlations disrupted by data slicing, aiding VesselMRA Net in accurately segmenting cerebrovascular pixels. Lastly, integrating VesselMRA Net and VesselConv-LSTM results in a modular cerebral vessel segmentation framework, PPA Net, facilitating separate optimization of the backbone network and predicted model components. The performance of this model has been extensively validated through experimental evaluations on three publicly available datasets, obtaining significant competitiveness when compared to the state-of-the-art of the current cerebral vessel segmentation models.

AAAI Conference 2025 Conference Paper

Relation-aware Hierarchical Prompt for Open-vocabulary Scene Graph Generation

• Tao Liu
• Rongjie Li
• Chongyu Wang
• Xuming He

Open-vocabulary Scene Graph Generation (OV-SGG) overcomes the limitations of the closed-set assumption by aligning visual relationship representations with open-vocabulary textual representations. This enables the identification of novel visual relationships, making it applicable to real-world scenarios with diverse relationships. However, existing OV-SGG methods are constrained by fixed text representations, limiting diversity and accuracy in image-text alignment. To address these challenges, we propose the Relation-Aware Hierarchical Prompting (RAHP) framework, which enhances text representation by integrating subject-object and region-specific relation information. Our approach utilizes entity clustering to address the complexity of relation triplet categories, enabling the effective integration of subject-object information. Additionally, we utilize a large language model (LLM) to generate detailed region-aware prompts, capturing fine-grained visual interactions and improving alignment between visual and textual modalities. RAHP also introduces a dynamic selection mechanism within Vision-Language Models (VLMs), which adaptively selects relevant text prompts based on the visual content, reducing noise from irrelevant prompts. Extensive experiments on the Visual Genome and Open Images v6 datasets demonstrate that our framework consistently achieves state-of-the-art performance, demonstrating its effectiveness in addressing the challenges of open-vocabulary scene graph generation.

YNIMG Journal 2025 Journal Article

Structural damage-driven brain compensation among near-centenarians and centenarians without dementia

• Hui Tang
• Haichao Zhao
• Hao Liu
• Jiyang Jiang
• Nicole Kochan
• Jing Jing
• Henry Brodaty
• Wei Wen

Compensation has been proposed as a mechanism to explain how individuals in very old age remain able to maintain normal cognitive functioning. Previous studies have provided evidence on the role of increasing functional connectivity as a compensatory mechanism for age-related white matter damage. However, we lack direct investigation into how these mechanisms contribute to the preservation of cognition in the very old population. We examined a cohort of near-centenarians and centenarians without dementia (aged 95-103 years, n=44). We constructed a structural disconnection matrix based on the disruption of white matter pathways caused by white matter hyperintensities (WMHs), aiming to explore the relationship between functional connections, cognitive preservation and white matter damage. Our results revealed that structural damage can reliably explain the variations of functional connections or cognitive maintenance. Notably, we found significant correlations between the weights in the functional connectivity model and the weights in the cognition model. We observed positive correlations between models for brain disconnections and cognitive function in near-centenarians and centenarians. The strongest effects were found between attention and somatomotor network (SMN) (r=0.397, p<0.001), memory and SMN (r=0.333 p<0.001), fluency and visual network (VIS) - control network (CN) (r=0.406, p<0.001), language and VIS (r=0.309, p<0.001), visuospatial ability and VIS-default mode network (DMN) (r=0.464, p<0.001), as well as global cognition and VIS-DMN (r=0.335, p<0.001). These findings suggest that enhancement of functional connectivity may serve as a compensatory mechanism, such that it mitigates the effects of white matter damage and contributes to preserved cognitive performance in very old age.

AAAI Conference 2025 Conference Paper

VQTalker: Towards Multilingual Talking Avatars Through Facial Motion Tokenization

• Tao Liu
• Ziyang Ma
• Qi Chen
• Feilong Chen
• Shuai Fan
• Xie Chen
• Kai Yu

We present VQTalker, a Vector Quantization-based framework for multilingual talking head generation that addresses the challenges of lip synchronization and natural motion across diverse languages. Our approach is grounded in the phonetic principle that human speech comprises a finite set of distinct sound units (phonemes) and corresponding visual articulations (visemes), which often share commonalities across languages. We introduce a facial motion tokenizer based on Group Residual Finite Scalar Quantization (GRFSQ), which creates a discretized representation of facial features. This method enables comprehensive capture of facial movements while improving generalization to multiple languages, even with limited training data. Building on this quantized representation, we implement a coarse-to-fine motion generation process that progressively refines facial animations. Extensive experiments demonstrate that VQTalker achieves state-of-the-art performance in both video-driven and speech-driven scenarios, particularly in multilingual settings. Notably, our method achieves high-quality results at a resolution of 512 × 512 pixels while maintaining a lower bitrate of approximately 11 kbps. Our work opens new possibilities for cross-lingual talking face generation.

EAAI Journal 2024 Journal Article

An approach to ship target detection based on combined optimization model of dehazing and detection

• Tao Liu
• Zhao Zhang
• Zhengling Lei
• Yuchi Huo
• Shuo Wang
• Jiansen Zhao
• Jinfeng Zhang
• Xin Jin

The design of a ship detection model that can be adapted to both foggy and clear images faces significant challenges. Existing methods are either not accurate enough, or have a high amount of model parameters, making them difficult to deploy to lightweight front-ends. To address these issues, a lightweight deep learning model based on combined optimization of dehazing and detection is proposed, focusing on self-adaptive ship detection. Firstly, a self-adaptive image dehazing module is designed and placed ahead of the detection network, including a dehazing parameter predictor and an improved dehazing method. Subsequently, a lightweight-improved object detection deep learning model integrated with the dehazing module is devised to detect the ship in the foggy image. Experimental results demonstrate the effectiveness of this approach in enabling efficient and accurate ship detection under foggy conditions. Through the joint optimization of the dehazing module and the detection module, it can be seen from the experiments that our Dehazing + Detection model has the highest detection accuracy and performs well in terms of detection speed, parameter amount, and weight file size. The detection accuracy has reached 97. 1%, which is better than that of the other three dehazing + detection models.

EAAI Journal 2024 Journal Article

An interpretable precursor-driven hierarchical model for predictive aircraft safety

• Jie Yang
• Jinsong Yu
• Diyin Tang
• Zhanbao Gao
• Can Feng
• Tao Liu

Predicting high-risk anomalous events in flight is crucial for ensuring in-time aviation safety and reducing potential incidents. This paper proposes a precursor-driven hierarchical predictive model for early warnings and actionable insights before incidents occur. The model uses an unsupervised learning network to construct latent event sequences from discrete variables, guiding a weakly supervised learning network for feature extraction from continuous variables. This hierarchical fusion captures the influence of discrete control variables on continuous flight states, enhancing its prediction performance of anomalous events. Guided by event sequences, the model can detect different anomalous patterns through identified precursors, thus providing a comprehensive understanding of events with interpretation. Quantitative evaluations further support the model’s rationale in interpretation, encompassing self-explanation and post-hoc analysis. A real case study on unstable approach events, using data from enhanced flight recorders, validates the model’s effectiveness in prediction and interpretation from precursors. The study explains imminent unstable approaches and offers an in-depth analysis of error cases, providing insights for model refinement and risk analysis, contributing to ongoing improvement in aviation safety.

JBHI Journal 2024 Journal Article

Ankle Moment Estimation Based on A Novel Distributed Plantar Pressure Sensing System

• Mingyu Du
• Bowen Lv
• Bingfei Fan
• Xiaoling Li
• Junze Yu
• Fugang Yi
• Tao Liu
• Shibo Cai

Ankle moment plays an important role in human gait analysis, patients’ rehabilitation process monitoring, and the human-machine interaction control of exoskeleton robots. However, current ankle moment estimation methods mainly rely on inverse dynamics (ID) based on optical motion capture system (OMC) and force plate. These methods rely on fixed instruments in the laboratory, which are difficult to be applied to the control of exoskeleton robots. To solve this problem, this paper developed a new distributed plantar pressure system and proposed an ankle plantar flexion moment estimation method using the plantar pressure system. We integrated eight pressure sensors in each insole to collect the pressure data of the key area of the foot and then used the plantar pressure data to train four neural networks to obtain the ankle moment. The performance of the models was evaluated using normalized root mean square error (NRMSE) and cross-correlation coefficient (ρ). During experiments, eight subjects were recruited for the overground walking tests, and OMC and force plate were used as the gold standard. The results indicate that the Genetic algorithm - Gated recurrent unit estimation algorithm (GA-GRU) was the best estimation model which achieved the highest accuracy in generalized ankle moment estimation (NRMSE = 7. 23%, ρ = 0. 85) compared with the other models. The designed novel distributed plantar pressure system and the proposed method could serve as a joint moment estimation approach in wearable robot control and human motion state monitoring.

AAAI Conference 2024 Conference Paper

Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning

• Tao Liu
• Yuhang Zhang
• Zhu Feng
• Zhiqin Yang
• Chen Xu
• Dapeng Man
• Wu Yang

Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimately failing. We use a new metric to quantify the degree of this weakened backdoor effect, called attack persistence. Given that research to improve this performance has not been widely noted, we propose a Full Combination Backdoor Attack (FCBA) method. It aggregates more combined trigger information for a more complete backdoor pattern in the global model. Trained backdoored global model is more resilient to benign updates, leading to a higher attack success rate on the test set. We test on three datasets and evaluate with two models across various settings. FCBA's persistence outperforms SOTA federated learning backdoor attacks. On GTSRB, post-attack 120 rounds, our attack success rate rose over 50% from baseline. The core code of our method is available at https://github.com/PhD-TaoLiu/FCBA.

IROS Conference 2024 Conference Paper

EVIT: Event-based Visual-Inertial Tracking in Semi-Dense Maps Using Windowed Nonlinear Optimization

• Runze Yuan
• Tao Liu
• Zijia Dai
• Yi-Fan Zuo
• Laurent Kneip

Event cameras are an interesting visual exteroceptive sensor that reacts to brightness changes rather than integrating absolute image intensities. Owing to this design, the sensor exhibits strong performance in situations of challenging dynamics and illumination conditions. While event-based simultaneous tracking and mapping remains a challenging problem, a number of recent works have pointed out the sensor’s suitability for prior map-based tracking. By making use of cross-modal registration paradigms, the camera’s ego-motion can be tracked across a large spectrum of illumination and dynamics conditions on top of accurate maps that have been created a priori by more traditional sensors. The present paper follows up on a recently introduced event-based geometric semi-dense tracking paradigm, and proposes the addition of inertial signals in order to robustify the estimation. More specifically, the added signals provide strong cues for pose initialization as well as regularization during windowed, multi-frame tracking. As a result, the proposed framework achieves increased performance under challenging illumination conditions as well as a reduction of the rate at which intermediate event representations need to be registered in order to maintain stable tracking across highly dynamic sequences. Our evaluation focuses on a diverse set of real world sequences and comprises a comparison of our proposed method against a purely event-based alternative running at different rates.

NeurIPS Conference 2024 Conference Paper

Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference

• Senmao Li
• Taihang Hu
• Joost van de Weijer
• Fahad S. Khan
• Tao Liu
• Linxuan Li
• Shiqi Yang
• Yaxing Wang

One of the main drawback of diffusion models is the slow inference time for image generation. Among the most successful approaches to addressing this problem are distillation methods. However, these methods require considerable computational resources. In this paper, we take another approach to diffusion model acceleration. We conduct a comprehensive study of the UNet encoder and empirically analyze the encoder features. This provides insights regarding their changes during the inference process. In particular, we find that encoder features change minimally, whereas the decoder features exhibit substantial variations across different time-steps. This insight motivates us to omit encoder computation at certain adjacent time-steps and reuse encoder features of previous time-steps as input to the decoder in multiple time-steps. Importantly, this allows us to perform decoder computation in parallel, further accelerating the denoising process. Additionally, we introduce a prior noise injection method to improve the texture details in the generated image. Besides the standard text-to-image task, we also validate our approach on other tasks: text-to-video, personalized generation and reference-guided generation. Without utilizing any knowledge distillation technique, our approach accelerates both the Stable Diffusion (SD) and DeepFloyd-IF model sampling by 41$\%$ and 24$\%$ respectively, and DiT model sampling by 34$\%$, while maintaining high-quality generation performance. Our code will be publicly released.

YNIMG Journal 2024 Journal Article

Influence of interpersonal distance on collaborative performance in the joint Simon task—An fNIRS-based hyperscanning study

• Xiaolei Song
• Meimei Dong
• Kun Feng
• Jiaqi Li
• Xiaofei Hu
• Tao Liu

Collaboration is a critical skill in everyday life. It has been suggested that collaborative performance may be influenced by social factors such as interpersonal distance, which is defined as the perceived psychological distance between individuals. Previous literature has reported that close interpersonal distance may promote the level of self-other integration between interacting members, and in turn, enhance collaborative performance. These studies mainly focused on interdependent collaboration, which requires high levels of shared representations and self-other integration. However, little is known about the effect of interpersonal distance on independent collaboration (e.g., the joint Simon task), in which individuals perform the task independently while the final outcome is determined by the parties. To address this issue, we simultaneously measured the frontal activations of ninety-four pairs of participants using a functional near-infrared spectroscopy (fNIRS)-based hyperscanning technique while they performed a joint Simon task. Behavioral results showed that the Joint Simon Effect (JSE), defined as the RT difference between incongruent and congruent conditions indicating the level of self-other integration between collaborators, was larger in the friend group than in the stranger group. Consistently, the inter-brain neural synchronization (INS) across the dorsolateral and medial parts of the prefrontal cortex was also stronger in the friend group. In addition, INS in the left dorsolateral prefrontal cortex negatively predicted JSE only in the friend group. These results suggest that close interpersonal distance may enhance the shared mental representation among collaborators, which in turn influences their collaborative performance.

EAAI Journal 2024 Journal Article

Predicting the properties of metamaterials consisting of curved-wall triangles using ensemble neural networks with interpretability

• Shaowei Zhu
• Mingdu Wen
• Zhuo Lv
• Liming Chen
• Tao Liu
• Xianbo Hou

Machine learning has emerged as a promising tool for predicting the properties of metamaterials, owing to its substantially faster prediction speed compared to conventional methods. However, the lack of interpretability of black-box machine learning models has impeded their adoption in this field. In this work, we develop an ensemble of neural networks (NNE) for predicting the mechanical properties of metamaterials consisting of curved-wall triangles. Our method achieves high prediction accuracy for the effective Young's modulus and Poisson's ratio for most samples. The average relative errors of the NNE are less than 5% for predicting the dimensionless Young's modulus and less than 10% for predicting Poisson's ratios. Additionally, our method is orders of magnitude faster than finite element simulations. More importantly, by explaining the predictions of NNE using SHapley Additive exPlanations (SHAP), we are able to quantify the relationships between geometric features and metamaterial properties. This reveals insights into parameter couplings and nonlinear effects. New physical insights can thus be obtained and new design rules discovered through this machine learning interpretability approach. Overall, our interpretable machine learning model can accelerate the design and discovery of metamaterials while providing physical insights into the inner workings of the models.

YNIMG Journal 2024 Journal Article

Relationships between brain structure-function coupling in normal aging and cognition: A cross-ethnicity population-based study

• Chang Liu
• Jing Jing
• Jiyang Jiang
• Wei Wen
• Wanlin Zhu
• Zixiao Li
• Yuesong Pan
• Xueli Cai

Increased efforts in neuroscience seek to understand how macro-anatomical and physiological connectomes cooperatively work to generate cognitive behaviors. However, the structure-function coupling characteristics in normal aging individuals remain unclear. Here, we developed an index, the Coupling in Brain Structural connectome and Functional connectome (C-BSF) index, to quantify regional structure-function coupling in a large community-based cohort. C-BSF used diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (fMRI) data from the Polyvascular Evaluation for Cognitive Impairment and Vascular Events study (PRECISE) cohort (2007 individuals, age: 61.15 ± 6.49 years) and the Sydney Memory and Ageing Study (MAS) cohort (254 individuals, age: 83.45 ± 4.33 years). We observed that structure-function coupling was the strongest in the visual network and the weakest in the ventral attention network. We also observed that the weaker structure-function coupling was associated with increased age and worse cognitive level of the participant. Meanwhile, the structure-function coupling in the visual network was associated with the visuospatial performance and partially mediated the connections between age and the visuospatial function. This work contributes to our understanding of the underlying brain mechanisms by which aging affects cognition and also help establish early diagnosis and treatment approaches for neurological diseases in the elderly.

EAAI Journal 2023 Journal Article

Method of recognizing sleep postures based on air pressure sensor and convolutional neural network: For an air spring mattress

• Yao Chao
• Tao Liu
• Li-Ming Shen

The present study aimed to develop a sleep postures recognition system based on the hardness adjustment system for a specific air spring mattress. To the end, an air spring mattress prototype and its embedded system was manufactured. Then the supine and lateral postures were defined, and the sleep posture images generated by the relative change rate of air pressure matrix were filtered. At last, a convolutional neural network (CNN) model was proposed and analyzed by ablation experiment. Furthermore, the CNN model was compared with a CNN-SVM fusion model and a ResNet50 model to valid the performance. The results indicate that it is feasible to define sleep postures with the air pressure, and the images smoothed by a Gaussian filter contains significant features. The F1-score of the CNN model determined by the ablation experiment is 0. 981, while the F1-score values of the CNN-SVM fusion model and the ResNet50 model are 0. 932 and 0. 954, respectively. Therefore, the generalization ability of the CNN model proposed outperformed the other two. Finally, the F1-score of the SSA-CNN model optimized by Sparrow Search Algorithm (SSA) increased to 0. 992. It concludes that sleep posture recognition can be achieved using only the inherent structure of the air spring mattress without additional sensors, reducing the cost and complexity of the system. In addition, the air pressure signal can be processed by the proposed CNN model to recognize sleep postures with a high accuracy.

NeurIPS Conference 2023 Conference Paper

Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation

• Ruida Zhou
• Tao Liu
• Min Cheng
• Dileep Kalathil
• P. R. Kumar
• Chao Tian

We study robust reinforcement learning (RL) with the goal of determining a well-performing policy that is robust against model mismatch between the training simulator and the testing environment. Previous policy-based robust RL algorithms mainly focus on the tabular setting under uncertainty sets that facilitate robust policy evaluation, but are no longer tractable when the number of states scales up. To this end, we propose two novel uncertainty set formulations, one based on double sampling and the other on an integral probability metric. Both make large-scale robust RL tractable even when one only has access to a simulator. We propose a robust natural actor-critic (RNAC) approach that incorporates the new uncertainty sets and employs function approximation. We provide finite-time convergence guarantees for the proposed RNAC algorithm to the optimal robust policy within the function approximation error. Finally, we demonstrate the robust performance of the policy learned by our proposed RNAC approach in multiple MuJoCo environments and a real-world TurtleBot navigation task.

NeurIPS Conference 2023 Conference Paper

Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference

• Ran Ran
• Nuo Xu
• Tao Liu
• Wei Wang
• Gang Quan
• Wujie Wen

The marriage of Graph Convolutional Network (GCN) and Homomorphic Encryption (HE) enables the inference of graph data on the cloud with significantly enhanced client data privacy. However, the tremendous computation and memory overhead associated with HE operations challenges the practicality of HE-based GCN inference. GCN inference involves a sequence of expensive matrix-matrix multiplications, and we observe that directly applying the state-of-the-art HE-based secure matrix-matrix multiplication solutions to accelerate HE-GCN inference is far less efficient as it does not exploit the unique aggregation mechanism of two-dimension graph node-features in GCN layer computation. As a result, in this paper, we propose a novel HE-based ciphertext packing technique, i. e. , Penguin, that can take advantage of the unique computation pattern during the HE-GCN inference to significantly reduce the computation and memory overhead associated with HE operations. Specifically, Penguin employs (i) an effective two-dimension parallel packing technique for feature ciphertext with optimal graph node partitioning and graph feature interleaving, and (ii) an interleaved assembly technique that can effectively make use of the blank slots to merge ciphertexts after feature reduction and significantly reduce the costly rotation operation. We provide theoretical analysis and experimental validation to demonstrate the speedup achieved by Penguin in accelerating GCN inference using popular GCN models and datasets. Our results show that Penguin can achieve up to $\sim10\times$ speedup and around $\sim79$% reduction in computational memory overhead, significantly outperforming state-of-the-art solutions. To the best of our knowledge, this is the first work that can ensure the protection of both graph structure and features when accelerating HE-GCN inference on encrypted data. Our code is publicly available at https: //github. com/ranran0523/Penguin.

NeurIPS Conference 2023 Conference Paper

Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games

• Youbang Sun
• Tao Liu
• Ruida Zhou
• P. R. Kumar
• Shahin Shahrampour

This work studies an independent natural policy gradient (NPG) algorithm for the multi-agent reinforcement learning problem in Markov potential games. It is shown that, under mild technical assumptions and the introduction of the \textit{suboptimality gap}, the independent NPG method with an oracle providing exact policy evaluation asymptotically reaches an $\epsilon$-Nash Equilibrium (NE) within $\mathcal{O}(1/\epsilon)$ iterations. This improves upon the previous best result of $\mathcal{O}(1/\epsilon^2)$ iterations and is of the same order, $\mathcal{O}(1/\epsilon)$, that is achievable for the single-agent case. Empirical results for a synthetic potential game and a congestion game are presented to verify the theoretical bounds.

NeurIPS Conference 2022 Conference Paper

Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning

• Ruida Zhou
• Tao Liu
• Dileep Kalathil
• P. R. Kumar
• Chao Tian

We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions, which are to be jointly optimized according to given criteria such as proportional fairness (smooth concave scalarization), hard constraints (constrained MDP), and max-min trade-off. We propose an Anchor-changing Regularized Natural Policy Gradient (ARNPG) framework, which can systematically incorporate ideas from well-performing first-order methods into the design of policy optimization algorithms for multi-objective MDP problems. Theoretically, the designed algorithms based on the ARNPG framework achieve $\tilde{O}(1/T)$ global convergence with exact gradients. Empirically, the ARNPG-guided algorithms also demonstrate superior performance compared to some existing policy gradient-based approaches in both exact gradients and sample-based scenarios.

NeurIPS Conference 2022 Conference Paper

Falconn++: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Search

• Ninh Pham
• Tao Liu

We present Falconn++, a novel locality-sensitive filtering (LSF) approach for approximate nearest neighbor search on angular distance. Falconn++ can filter out potential far away points in any hash bucket before querying, which results in higher quality candidates compared to other hashing-based solutions. Theoretically, Falconn++ asymptotically achieves lower query time complexity than Falconn, an optimal locality-sensitive hashing scheme on angular distance. Empirically, Falconn++ achieves a higher recall-speed tradeoff than Falconn on many real-world data sets. Falconn++ is also competitive with HNSW, an efficient representative of graph-based solutions on high search recall regimes.

NeurIPS Conference 2022 Conference Paper

Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales

• Tao Liu
• P. R. Kumar
• Ruida Zhou
• Xi Liu

Motivated by the problem of learning with small sample sizes, this paper shows how to incorporate into support-vector machines (SVMs) those properties that have made convolutional neural networks (CNNs) successful. Particularly important is the ability to incorporate domain knowledge of invariances, e. g. , translational invariance of images. Kernels based on the \textit{maximum} similarity over a group of transformations are not generally positive definite. Perhaps it is for this reason that they have not been studied theoretically. We address this lacuna and show that positive definiteness indeed holds \textit{with high probability} for kernels based on the maximum similarity in the small training sample set regime of interest, and that they do yield the best results in that regime. We also show how additional properties such as their ability to incorporate local features at multiple spatial scales, e. g. , as done in CNNs through max pooling, and to provide the benefits of composition through the architecture of multiple layers, can also be embedded into SVMs. We verify through experiments on widely available image sets that the resulting SVMs do provide superior accuracy in comparison to well-established deep neural network benchmarks for small sample sizes.

YNICL Journal 2022 Journal Article

Predicting prognosis of primary pontine hemorrhage using CT image and deep learning

• Shuo Wang
• Feng Chen
• Mingyu Zhang
• Xiaolin Zhao
• Linghua Wen
• Wenyuan Wu
• Shina Wu
• Zhe Li

Prognosis of primary pontine hemorrhage (PPH) is important for treatment planning and patient management. However, only few clinical factors were reported to have prognostic value to PPH. Here, we propose a deep learning (DL) model that mines high-dimensional prognostic information from computed tomography (CT) images and combines clinical factors for predicting individualized prognosis of PPH. We proposed a multi-task DL model to learn high-dimensional CT features of hematoma and perihematomal areas for predicting the risk of 30-day mortality, 90-day mortality and 90-day functional outcome of PPH simultaneously. We further explored the combination of the DL model and clinical factors by building a combined model. All the models were trained in a training cohort (n = 219) and tested in an independent testing cohort (n = 35). The DL model achieved area under the curve (AUC) of 0.886, 0.886, and 0.759 in predicting 30-day mortality, 90-day mortality and 90-day functional outcome of PPH in the independent testing cohort, which improved over the previously reported new PPH score and the clinical model. When combining the DL model and clinical factors, the combined model achieved improved performance (AUC = 0.920, 0.941, and 0.894), indicating that DL model mines CT information that complements clinical factors. Through DL visualization technique, we found that the internal structure of hematoma and its expansion to perihematomal regions are important for predicting the prognosis of PPH. This DL model provides an easy-to-use way for predicting individualized prognosis of PPH by mining high-dimensional information from CT images, and showed improvement over clinical factors and present methods.

YNIMG Journal 2022 Journal Article

The role of low-frequency oscillations in three-dimensional perception with depth cues in virtual reality

• Zhili Tang
• Xiaoyu Liu
• Hongqiang Huo
• Min Tang
• Tao Liu
• Zhixin Wu
• Xiaofeng Qiao
• Duo Chen

Currently, vision-related neuroscience studies are undergoing a trend from simplified image stimuli toward more naturalistic stimuli. Virtual reality (VR), as an emerging technology for visual immersion, provides more depth cues for three-dimensional (3D) presentation than two-dimensional (2D) image. It is still unclear whether the depth cues used to create 3D visual perception modulate specific cortical activation. Here, we constructed two visual stimuli presented by stereoscopic vision in VR and graphical projection with 2D image, respectively, and used electroencephalography to examine neural oscillations and their functional connectivity during 3D perception. We find that neural oscillations are specific to delta and theta bands in stereoscopic vision and the functional connectivity in the two bands increase in cortical areas related to visual pathways. These findings indicate that low-frequency oscillations play an important role in 3D perception with depth cues.

YNIMG Journal 2021 Journal Article

A slower rate of sulcal widening in the brains of the nondemented oldest old

• Hui Tang
• Tao Liu
• Hao Liu
• Jiyang Jiang
• Jian Cheng
• Haijun Niu
• Shuyu Li
• Henry Brodaty

The relationships between aging and brain morphology have been reported in many previous structural brain studies. However, the trajectories of successful brain aging in the extremely old remain underexplored. In the limited research on the oldest old, covering individuals aged 85 years and older, there are very few studies that have focused on the cortical morphology, especially cortical sulcal features. In this paper, we measured sulcal width and depth as well as cortical thickness from T1-weighted scans of 290 nondemented community-dwelling participants aged between 76 and 103 years. We divided the participants into young old (between 76 and 84; mean = 80.35±2.44; male/female = 76/88) and oldest old (between 85 and 103; mean = 91.74±5.11; male/female = 60/66) groups. The results showed that most of the examined sulci significantly widened with increased age and that the rates of sulcal widening were lower in the oldest old. The spatial pattern of the cortical thinning partly corresponded with that of sulcal widening. Compared to females, males had significantly wider sulci, especially in the oldest old. This study builds a foundation for future investigations of neurocognitive disorders and neurodegenerative diseases in the oldest old, including centenarians.

JBHI Journal 2021 Journal Article

IMU-Based Gait Normalcy Index Calculation for Clinical Evaluation of Impaired Gait

• Lei Wang
• Yun Sun
• Qingguo Li
• Tao Liu
• Jingang Yi

Inertial measurement units (IMU) have been used for gait analysis in many clinical studies, as a more convenient, low cost and less restricted alternative to the laboratory-based motion capture systems or instrumented walkways. Spatial-temporal gait parameters such as gait cycle duration and stride length calculated from the IMUs were often used in these studies for evaluating the impaired gait. However, the spatial-temporal information provided by IMUs is limited, and sometime suffers incomplete and less effective evaluation. In this study, we develop a novel IMU-based method for clinical gait evaluation. Nine gait variables including three spatial-temporal parameters and six kinematic parameters are extracted from two shank-mounted IMUs for quantifying patient's gait deviations. Based on those parameters, an IMU-based gait normalcy index (INI) is derived to evaluate the overall gait performance. Eight inpatient subjects with gait impairments caused by n-hexane neuropathy and ten healthy subjects were recruited. The proposed gait variables and INI were examined on the inpatients at three to five time instants during the rehabilitation process until being discharged. A comparison with healthy subjects and statistical analysis for the changes of gait variables and INI demonstrated that the proposed new set of gait variables and INI can provide adequate and effective information for quantifying gait abnormalities, and help understanding the progress of gait and effectiveness of therapy during rehabilitation process.

NeurIPS Conference 2021 Conference Paper

Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs

• Tao Liu
• Ruida Zhou
• Dileep Kalathil
• Panganamala Kumar
• Chao Tian

We address the issue of safety in reinforcement learning. We pose the problem in an episodic framework of a constrained Markov decision process. Existing results have shown that it is possible to achieve a reward regret of $\tilde{\mathcal{O}}(\sqrt{K})$ while allowing an $\tilde{\mathcal{O}}(\sqrt{K})$ constraint violation in $K$ episodes. A critical question that arises is whether it is possible to keep the constraint violation even smaller. We show that when a strictly safe policy is known, then one can confine the system to zero constraint violation with arbitrarily high probability while keeping the reward regret of order $\tilde{\mathcal{O}}(\sqrt{K})$. The algorithm which does so employs the principle of optimistic pessimism in the face of uncertainty to achieve safe exploration. When no strictly safe policy is known, though one is known to exist, then it is possible to restrict the system to bounded constraint violation with arbitrarily high probability. This is shown to be realized by a primal-dual algorithm with an optimistic primal estimate and a pessimistic dual update.

AIIM Journal 2021 Journal Article

MvKFN-MDA: Multi-view Kernel Fusion Network for miRNA-disease association prediction

• Jin Li
• Tao Liu
• Jingru Wang
• Qing Li
• Chenxi Ning
• Yun Yang

Predicting the associations between microRNAs (miRNAs) and diseases is of great significance for identifying miRNAs related to human diseases. Since it is time-consuming and costly to identify the association between miRNA and disease through biological experiments, computational methods are currently used as an effective supplement to identify the potential association between disease and miRNA. This paper presents a Multi-view Kernel Fusion Network (MvKFN) based prediction method (MvKFN-MDA) to address the problem of miRNA-disease associations prediction. A novel multiple kernel fusion framework Multi-view Kernel Fusion Network (MvKFN) is first proposed to effectively fuse different views similarity kernels constructed from different data sources in a highly nonlinear way. Using MvKFNs, both different base similarity kernels for miRNA, such as sequence, functional, semantic, Gaussian profile kernels and different base similarity kernels for diseases, such as semantic, Gaussian profile kernel are nonlinearly fused into two integrated similarity kernels, one for miRNA, another for disease. Then, miRNA and disease feature representations are extracted from the miRNA and disease integrated similarity kernels respectively. These features are then fed into a neural matrix completion framework which finally outputs the association prediction scores. The parameters of MvKFN-MDA are learned based on the known miRNA-disease association matrix in a supervised end-to-end way. We compare the proposed method with other state-of-the-art methods. The AUCs of our proposed method were superior to the existing methods in both 5-FCV and LOOCV on two open experimental datasets. Furthermore, 49, 48, and 47 of the top 50 predicted miRNAs for three high-risk human diseases, namely, colon cancer, lymphoma, and kidney cancer, are verified respectively using experimental literature. Finally, 100% accuracy from the top 50 predicted miRNAs is achieved when breast cancer is used as a case study to evaluate the ability of MvKFN-MDA for predicting a new disease without any known related miRNAs.

YNIMG Journal 2021 Journal Article

Team-work, Team-brain: Exploring synchrony and team interdependence in a nine-person drumming task via multiparticipant hyperscanning and inter-brain network topology with fNIRS

• Tao Liu
• Lian Duan
• Ruina Dai
• Matthew Pelowski
• Chaozhe Zhu

Teamwork is indispensable in human societies. However, due to the complexity of studying ecologically valid synchronous team actions, requiring multiple members and a range of subjective and objective measures, the mechanism underlying the impact of synchrony on team performance is still unclear. In this paper, we simultaneously measured groups of nine-participants' (total N = 180) fronto-temporal activations during a drum beating task using functional near infrared spectroscopy (fNIRS)-based hyperscanning and multi-brain network modeling, which can assess patterns of shared neural synchrony and attention/information sharing across entire teams. Participants (1) beat randomly without considering others' drumming (random condition), (2) actively coordinated their beats with the entire group without other external cue (team-focus condition), and (3) beat together based on a metronome (shared-focus condition). Behavioral data revealed higher subjective and objective measures of drum-beat synchronization in the team-focus condition, as well as higher felt interdependence. The fNIRS data revealed that participants in the team-focus condition also showed higher interpersonal neural synchronization (INS) and higher Global Network Efficiency in their left TPJ and mPFC. Higher left TPJ Global Network Efficiency also predicted higher actual synchrony in the team-focus condition, with an effect size roughly 1.5 times that of subjective measures, but not in the metronome-enabled shared-focus condition. This result suggests that shared mental representations with high efficiency of information exchange across the entire team may be a key component of synchrony, adding to the understanding of the actual relation to team work.

IJCAI Conference 2021 Conference Paper

What If We Could Not See? Counterfactual Analysis for Egocentric Action Anticipation

• Tianyu Zhang
• Weiqing Min
• Jiahao Yang
• Tao Liu
• Shuqiang Jiang
• Yong Rui

Egocentric action anticipation aims at predicting the near future based on past observation in first-person vision. While future actions may be wrongly predicted due to the dataset bias, we present a counterfactual analysis framework for egocentric action anticipation (CA-EAA) to enhance the capacity. In the factual case, we can predict the upcoming action based on visual features and semantic labels from past observation. Imagining one counterfactual situation where no visual representation had been observed, we would obtain a counterfactual predicted action only using past semantic labels. In this way, we can reduce the side-effect caused by semantic labels via a comparison between factual and counterfactual outcomes, which moves a step towards unbiased prediction for egocentric action anticipation. We conduct experiments on two large-scale egocentric video datasets. Qualitative and quantitative results validate the effectiveness of our proposed CA-EAA.

JBHI Journal 2020 Journal Article

Spatially Aware Dense-LinkNet Based Regression Improves Fluorescent Cell Detection in Adaptive Optics Ophthalmic Images

• Jianfei Liu
• Yoo-Jean Han
• Tao Liu
• Nancy Aguilera
• Johnny Tam

Retinal pigment epithelial (RPE) cells play an important role in nourishing retinal neurosensory photoreceptor cells, and numerous blinding diseases are associated with RPE defects. Their fluorescence signature can now be visualized in the living human eye using adaptive optics (AO) imaging combined with indocyanine green (ICG), which motivates us to develop an automated RPE detection method to improve the quantitative evaluation of RPE status in patients. This paper proposes a spatially-aware, Dense-LinkNet-based regression approach to improve the detection of in vivo fluorescent cell patterns, achieving precision, recall, and F1-Score of 93. 6 $\pm$ 4. 3%, 81. 4 $\pm$ 9. 5%, and 86. 7 $\pm$ 5. 7%, respectively. These results demonstrate the utility of incorporating spatial inputs into a deep learning-based regression framework for cell detection.

YNIMG Journal 2020 Journal Article

Stronger bilateral functional connectivity of the frontoparietal control network in near-centenarians and centenarians without dementia

• Jiyang Jiang
• Tao Liu
• John D. Crawford
• Nicole A. Kochan
• Henry Brodaty
• Perminder S. Sachdev
• Wei Wen

Centenarians without dementia can be considered as a model of successful ageing and resistance against age-related cognitive decline. Is there something special about their brain functional connectivity that helps them preserve cognitive function into the 11th decade of life? In a cohort of 57 dementia-free near-centenarians and centenarians (95–103 years old) and 66 cognitively unimpaired younger participants (76–79 years old), we aimed to investigate brain functional characteristics in the extreme age range using resting-state functional MRI. Using group-level independent component analysis and dual regression, results showed group differences in the functional connectivity of seven group-level independent component (IC) templates, after accounting for sex, education years, and grey matter volume, and correcting for multiple testing at family-wise error rate of 0. 05. After Bonferroni correction for testing 30 IC templates, near-centenarians and centenarians showed stronger functional connectivity between right frontoparietal control network (FPCN) and left inferior frontal gyrus (Bonferroni-corrected p ​= ​0. 024), a core region of the left FPCN. The investigation of between-IC functional connectivity confirmed the voxel-wise result by showing stronger functional connectivity between bilateral FPCNs in near-centenarians and centenarians compared to young-old controls. In addition, near-centenarians and centenarians had weaker functional connectivity between default mode network and fronto-temporo-parietal network compared to young-old controls. In near-centenarians and centenarians, stronger functional connectivity between bilateral FPCNs was associated with better cognitive performance in the visuospatial domain. The current study highlights the key role of bilateral FPCN connectivity in the reserve capacity against age-related cognitive decline.

YNIMG Journal 2019 Journal Article

Assessing autism at its social and developmental roots: A review of Autism Spectrum Disorder studies using functional near-infrared spectroscopy

• Tao Liu
• Xingchen Liu
• Li Yi
• Chaozhe Zhu
• Patrick S. Markey
• Matthew Pelowski

We review a relatively new method for studying the developing brain in children and infants with Autism Spectrum Disorder (ASD). Despite advances in behavioral screening and brain imaging, due to paradigms that do not easily allow for testing of awake, very young, and socially-engaged children—i. e. , the social and the baby brain—the biological underpinnings of this disorder remain a mystery. We introduce an approach based on functional near-infrared spectroscopy (fNIRS), which offers a noninvasive imaging technique for studying functional activations by measuring changes in the brain's hemodynamic properties. This further enables measurement of brain activation in upright, interactive settings, while maintaining general equivalence to fMRI findings. We review the existing studies that have used fNIRS for ASD, discussing their promise, limitations, and their technical aspects, gearing this study to the researcher who may be new to this technique and highlighting potential targets for future research.

YNICL Journal 2018 Journal Article

The association of regional white matter lesions with cognition in a community-based cohort of older individuals

• Jiyang Jiang
• Matthew Paradise
• Tao Liu
• Nicola J. Armstrong
• Wanlin Zhu
• Nicole A. Kochan
• Henry Brodaty
• Perminder S. Sachdev

Emerging evidence from lesion-symptom mapping (LSM) studies suggested that regional white matter lesions (WML) on strategic white matter (WM) fiber tracts are significantly associated with specific cognitive domains, independent of global WML burden. However, previous LSM investigations were mostly carried out in disease cohorts, with little evidence from community-based older individuals, making findings difficult to generalize. Moreover, most LSM studies applied a threshold to the probabilistic atlas, leading to the loss of information and threshold-dependent findings. Furthermore, it is still unclear whether associations between regional WML and cognition are independent of global grey matter (GM) and WM volumes, which have also been linked to cognition. In the current study, we undertook a region of interest (ROI) LSM study to examine the relationship between regional WML on strategic WM tracts and cognitive performance in a large community-based cohort of older individuals (N = 461; 70–90 years). WML were extracted using a publicly available pipeline, UBO Detector (https: //cheba. unsw. edu. au/group/neuroimaging-pipeline). Mapping of WML to the Johns Hopkins University WM atlas was undertaken using an automated TOolbox for Probabilistic MApping of Lesions (TOPMAL), which we introduce here, and is implemented in UBO Detector. The results show that different patterns of brain structural volumes in the ageing brain were associated with different cognitive domains. Regional WML were associated with processing speed, executive function, and global cognition, independent of total GM, WM and WML volumes. Moreover, regional WML explained more variance in executive function, compared to total GM, WM and WML volumes. The current study highlights the importance of studying regional WML in age-related cognitive decline.

YNIMG Journal 2018 Journal Article

UBO Detector – A cluster-based, fully automated pipeline for extracting white matter hyperintensities

• Jiyang Jiang
• Tao Liu
• Wanlin Zhu
• Rebecca Koncz
• Hao Liu
• Teresa Lee
• Perminder S. Sachdev
• Wei Wen

We present ‘UBO Detector’, a cluster-based, fully automated pipeline for extracting and calculating variables for regions of white matter hyperintensities (WMH) (available for download at https: //cheba. unsw. edu. au/group/neuroimaging-pipeline). It takes T1-weighted and fluid attenuated inversion recovery (FLAIR) scans as input, and SPM12 and FSL functions are utilised for pre-processing. The candidate clusters are then generated by FMRIB's Automated Segmentation Tool (FAST). A supervised machine learning algorithm, k-nearest neighbor (k-NN), is applied to determine whether the candidate clusters are WMH or non-WMH. UBO Detector generates both image and text (volumes and the number of WMH clusters) outputs for whole brain, periventricular, deep, and lobar WMH, as well as WMH in arterial territories. The computation time for each brain is approximately 15 min. We validated the performance of UBO Detector by showing a) high segmentation (similarity index (SI) = 0. 848) and volumetric (intraclass correlation coefficient (ICC) = 0. 985) agreement between the UBO Detector-derived and manually traced WMH; b) highly correlated (r2 > 0. 9) and a steady increase of WMH volumes over time; and c) significant associations of periventricular (t = 22. 591, p < 0. 001) and deep (t = 14. 523, p < 0. 001) WMH volumes generated by UBO Detector with Fazekas rating scores. With parallel computing enabled in UBO Detector, the processing can take advantage of multi-core CPU's that are commonly available on workstations. In conclusion, UBO Detector is a reliable, efficient and fully automated WMH segmentation pipeline.

YNIMG Journal 2018 Journal Article

Variation in longitudinal trajectories of cortical sulci in normal elderly

• Xinke Shen
• Tao Liu
• Dacheng Tao
• Yubo Fan
• Jicong Zhang
• Shuyu Li
• Jiyang Jiang
• Wanlin Zhu

Sulcal morphology has been reported to change with age-related neurological diseases, but the trajectories of sulcal change in normal ageing in the elderly is still unclear. We conducted a study of sulcal morphological changes over seven years in 132 normal elderly participants aged 70–90 years at baseline, and who remained cognitively normal for the next seven years. We examined the fold opening and sulcal depth of sixteen (eight on each hemisphere) prominent sulci based on T1-weighted MRI using automated methods with visual quality control. The trajectory of each individual sulcus with respect to age was examined separately by linear mixed models. Fold opening was best modelled by cubic fits in five sulci, by quadratic models in six sulci and by linear models in five sulci, indicating an accelerated widening of a number of sulci in older age. Sulcal depth showed significant linear decline in three sulci and quadratic trend in one sulcus. Turning points of non-linear trajectories towards accelerated widening of the fold were found to be around the age between 75 and 80, indicating an accelerated atrophy of brain cortex starting in the age of late 70s. Our findings of cortical sulcal changes in normal ageing could provide a reference for studies of neurocognitive disorders, including neurodegenerative diseases, in the elderly.

AAAI Conference 2017 Conference Paper

Neural Bag-of-Ngrams

• Bofang Li
• Tao Liu
• Zhe Zhao
• Puwei Wang
• Xiaoyong Du

Bag-of-ngrams (BoN) models are commonly used for representing text. One of the main drawbacks of traditional BoN is the ignorance of n-gram’s semantics. In this paper, we introduce the concept of Neural Bag-of-ngrams (Neural-BoN), which replaces sparse one-hot n-gram representation in traditional BoN with dense and rich-semantic n-gram representations. We first propose context guided n-gram representation by adding n-grams to word embeddings model. However, the context guided learning strategy of word embeddings is likely to miss some semantics for text-level tasks. Text guided ngram representation and label guided n-gram representation are proposed to capture more semantics like topic or sentiment tendencies. Neural-BoN with the latter two n-gram representations achieve state-of-the-art results on 4 documentlevel classification datasets and 6 semantic relatedness categories. They are also on par with some sophisticated DNNs on 3 sentence-level classification datasets. Similar to traditional BoN, Neural-BoN is efficient, robust and easy to implement. We expect it to be a strong baseline and be used in more real-world applications.

YNIMG Journal 2015 Journal Article

Optimization of large-scale mouse brain connectome via joint evaluation of DTI and neuron tracing data

• Hanbo Chen
• Tao Liu
• Yu Zhao
• Tuo Zhang
• Yujie Li
• Meng Li
• Hongmiao Zhang
• Hui Kuang

Tractography based on diffusion tensor imaging (DTI) data has been used as a tool by a large number of recent studies to investigate structural connectome. Despite its great success in offering unique 3D neuroanatomy information, DTI is an indirect observation with limited resolution and accuracy and its reliability is still unclear. Thus, it is essential to answer this fundamental question: how reliable is DTI tractography in constructing large-scale connectome? To answer this question, we employed neuron tracing data of 1772 experiments on the mouse brain released by the Allen Mouse Brain Connectivity Atlas (AMCA) as the ground-truth to assess the performance of DTI tractography in inferring white matter fiber pathways and inter-regional connections. For the first time in the neuroimaging field, the performance of whole brain DTI tractography in constructing a large-scale connectome has been evaluated by comparison with tracing data. Our results suggested that only with the optimized tractography parameters and the appropriate scale of brain parcellation scheme, can DTI produce relatively reliable fiber pathways and a large-scale connectome. Meanwhile, a considerable amount of errors were also identified in optimized DTI tractography results, which we believe could be potentially alleviated by efforts in developing better DTI tractography approaches. In this scenario, our framework could serve as a reliable and quantitative test bed to identify errors in tractography results which will facilitate the development of such novel tractography algorithms and the selection of optimal parameters.

YNIMG Journal 2014 Journal Article

A longitudinal study of brain atrophy over two years in community-dwelling older individuals

• Jiyang Jiang
• Perminder Sachdev
• Darren M. Lipnicki
• Haobo Zhang
• Tao Liu
• Wanlin Zhu
• Chao Suo
• Lin Zhuang

Most previous neuroimaging studies of age-related brain structural changes in older individuals have been cross-sectional and/or restricted to clinical samples. The present study of 345 community-dwelling non-demented individuals aged 70–90years aimed to examine age-related brain volumetric changes over two years. T1-weighted magnetic resonance imaging scans were obtained at baseline and at 2-year follow-up and analyzed using the FMRIB Software Library and FreeSurfer to investigate cortical thickness and shape and volumetric changes of subcortical structures. The results showed significant atrophy across much of the cerebral cortex with bilateral transverse temporal regions shrinking the fastest. Atrophy was also found in a number of subcortical structures, including the CA1 and subiculum subfields of the hippocampus. In some regions, such as left and right entorhinal cortices, right hippocampus and right precentral area, the rate of atrophy increased with age. Our analysis also showed that rostral middle frontal regions were thicker bilaterally in older participants, which may indicate its ability to compensate for medial temporal lobe atrophy. Compared to men, women had thicker cortical regions but greater rates of cortical atrophy. Women also had smaller subcortical structures. A longer period of education was associated with greater thickness in a number of cortical regions. Our results suggest a pattern of brain atrophy with non-demented people that resembles a less extreme form of the changes associated with Alzheimer's disease (AD).

YNIMG Journal 2013 Journal Article

Limited relationships between two-year changes in sulcal morphology and other common neuroimaging indices in the elderly

• Tao Liu
• Perminder S. Sachdev
• Darren M. Lipnicki
• Jiyang Jiang
• Guangqiang Geng
• Wanlin Zhu
• Simone Reppermund
• Dacheng Tao

Measuring the geometry or morphology of sulcal folds has recently become an important approach to investigating neuroanatomy. However, relationships between cortical sulci and other brain structures are poorly understood. The present study investigates how age-related changes in sulcal width are associated with age-related changes in traditional indices of brain structure such as cortical thickness, and cortical gray matter (GM), white matter (WM), subcortical, and white matter hyperintensity (WMH) volumes. These indices and sulcal width were measured at baseline and at two-year follow up in 185 community-dwelling individuals (91 men) aged 70–89years. There were significant increases in sulcal width and WMH volume, and significant decreases in all other indices between baseline and follow-up. Sulcal widening was associated with decreases in cortical GM, subcortical and WM volumes. A further association between sulcal width and cortical thickness became non-significant when cortical GM volume was controlled for. Our findings give insights into the mechanisms responsible for cortical sulcal morphology. The relationships between sulcal morphology and other common measures suggest that it could be a more comprehensive measure for clinical classifications than traditional neuroimaging metrics, such as cortical thickness.

YNIMG Journal 2013 Journal Article

Longitudinal changes in sulcal morphology associated with late-life aging and MCI

• Tao Liu
• Perminder S. Sachdev
• Darren M. Lipnicki
• Jiyang Jiang
• Yue Cui
• Nicole A. Kochan
• Simone Reppermund
• Julian N. Trollor

The present study investigated changes in sulcal morphology associated with late-life aging and mild cognitive impairment (MCI). Participants were 219 community-dwelling 70–90year-olds from the Sydney Memory and Ageing Study; all had MRI scans and were classified as having normal cognition (NC) or MCI at each of waves 1 and 2, two years apart. Automated methods were used to calculate a global sulcal index (g-SI), widths of five prominent sulci, and regional cortical thickness. There were significant longitudinal declines in g-SI and increases in sulcal width among the entire sample, but the rate of change differed among cognitive subgroups. Participants with MCI at both waves (persisting MCI) showed accelerated sulcal widening, particularly for the superior frontal and superior temporal sulci. The sulcal morphology of participants who reverted from MCI to NC was more consistent with stable NC than persisting MCI. Overall cortical thickness decreased between waves similarly across the subgroups. While changes in sulcal morphology are characteristic of normal late-life aging, they are accelerated in individuals with MCI (in contrast to changes in cortical thickness). Sulcal measures also differentiate between persistent MCI and MCI that reverts to NC, and may thus help in predicting the prognosis of MCI patients.

YNIMG Journal 2012 Journal Article

Automated detection of amnestic mild cognitive impairment in community-dwelling elderly adults: A combined spatial atrophy and white matter alteration approach

• Yue Cui
• Wei Wen
• Darren M. Lipnicki
• Mirza Faisal Beg
• Jesse S. Jin
• Suhuai Luo
• Wanlin Zhu
• Nicole A. Kochan

Amnestic mild cognitive impairment (aMCI) is a syndrome widely considered to be prodromal Alzheimer's disease. Accurate diagnosis of aMCI would enable earlier treatment, and could thus help minimize the prevalence of Alzheimer's disease. The aim of the present study was to evaluate a magnetic resonance imaging-based automated classification schema for identifying aMCI. This was carried out in a sample of community-dwelling adults aged 70–90years old: 79 with a clinical diagnosis of aMCI and 204 who were cognitively normal. Our schema was novel in using measures of both spatial atrophy, derived from T1-weighted images, and white matter alterations, assessed with diffusion tensor imaging (DTI) tract-based spatial statistics (TBSS). Subcortical volumetric features were extracted using a FreeSurfer-initialized Large Deformation Diffeomorphic Metric Mapping (FS+LDDMM) segmentation approach, and fractional anisotropy (FA) values obtained for white matter regions of interest. Features were ranked by their ability to discriminate between aMCI and normal cognition, and a support vector machine (SVM) selected an optimal feature subset that was used to train SVM classifiers. As evaluated via 10-fold cross-validation, the classification performance characteristics achieved by our schema were: accuracy, 71. 09%; sensitivity, 51. 96%; specificity, 78. 40%; and area under the curve, 0. 7003. Additionally, we identified numerous socio-demographic, lifestyle, health and other factors potentially implicated in the misclassification of individuals by our schema and those previously used by others. Given its high level of performance, our classification schema could facilitate the early detection of aMCI in community-dwelling elderly adults.

YNIMG Journal 2012 Journal Article

Predicting the development of mild cognitive impairment: A new use of pattern recognition

• Yue Cui
• Perminder S. Sachdev
• Darren M. Lipnicki
• Jesse S. Jin
• Suhuai Luo
• Wanlin Zhu
• Nicole A. Kochan
• Simone Reppermund

While the conversion from mild cognitive impairment to Alzheimer's disease has received much recent attention, the transition from normal cognition to mild cognitive impairment is largely unexplored. The present pattern recognition study addressed this by using neuropsychological test scores and neuroimaging morphological measures to predict the later development of mild cognitive impairment in cognitively normal community-dwelling individuals aged 70–90years. A feature selection algorithm chose a subset of neuropsychological and FreeSurfer-derived morphometric features that optimally differentiated between individuals who developed mild cognitive impairment and individuals who remained cognitively normal. Support vector machines were used to train classifiers and test prediction performance, which was evaluated via 10-fold cross-validation to reduce variability. Prediction performance was greater when using a combination of neuropsychological scores and morphological measures than when using either of these alone. Results for the combined method were: accuracy 78. 51%, sensitivity 73. 33%, specificity 79. 75%, and an area under the receiver operating characteristic curve of 0. 841. Of all the features investigated, memory performance and measures of the prefrontal cortex and parietal lobe were the most discriminative. Our prediction method offers the potential to detect elderly individuals with apparently normal cognition at risk of imminent cognitive decline. Identification at this stage will facilitate the early start of interventions designed to prevent or slow the development of Alzheimer's disease and other dementias.

AAAI Conference 2011 Conference Paper

Partially Supervised Text Classification with Multi-Level Examples

• Tao Liu
• Xiaoyong Du
• Yongdong Xu
• Minghui Li
• Xiaolong Wang

Partially supervised text classification has received great research attention since it only uses positive and unlabeled examples as training data. This problem can be solved by automatically labeling some negative (and more positive) examples from unlabeled examples before training a text classifier. But it is difficult to guarantee both high quality and quantity of the new labeled examples. In this paper, a multi-level example based learning method for partially supervised text classification is proposed, which can make full use of all unlabeled examples. A heuristic method is proposed to assign possible labels to unlabeled examples and partition them into multiple levels according to their labeling confidence. A text classifier is trained on these multi-level examples using weighted support vector machines. Experiments show that the multi-level example based learning method is effective for partially supervised text classification, and outperforms the existing popular methods such as Biased-SVM, ROC-SVM, S-EM and WL.

YNIMG Journal 2011 Journal Article

The relationship between cortical sulcal variability and cognitive performance in the elderly

• Tao Liu
• Wei Wen
• Wanlin Zhu
• Nicole A. Kochan
• Julian N. Trollor
• Simone Reppermund
• Jesse S. Jin
• Suhuai Luo

The relationship between cognitive functions and brain structure has been of long-standing research interest. Most previous research has attempted to relate cognition to volumes of specific brain structures or thickness of cortical regions, with relatively few studies examining other features such as cortical surface anatomy. In this study, we examine the relationship between cortical sulcal features and cognitive function in a sample (N=316) of community-dwelling subjects aged between 70 and 90years (mean=78. 06±4. 75; male/female=130/186) who had detailed neuropsychological assessments and brain MRI scans. Using automated methods on 3D T1-weighted brain scans, we computed global sulcal indices (g-SIs) of the whole brain and average sulcal spans of five prominent sulci. The g-SI, which reflects the complexity of sulcal folds across the cerebral hemispheres, showed a significant positive correlation with performance in most cognitive domains including attention/processing speed, memory, language and executive function. Regionally, a negative correlation was found between some cognitive functions and sulcal spans, i. e. poorer cognitive performance was associated with a wider sulcal span. Of the five cognitive domains examined, the performance of processing speed was found to be correlated with the spans of most sulci, with the strongest correlation being with the superior temporal sulcus. Memory did not show a significant correlation with any individual sulcal index, after correcting for age and sex. Of the five sulci measured, the left superior temporal sulcus showed the highest sensitivity, with significant correlations with performances in all cognitive domains except memory, after controlling for age, sex, years of education and brain size. The results suggest that regionally specific sulcal morphology is associated with cognitive function in elderly individuals.

YNIMG Journal 2010 Journal Article

Negative covariation between task-related responses in alpha/beta-band activity and BOLD in human sensorimotor cortex: An EEG and fMRI study of motor imagery and movements

• Han Yuan
• Tao Liu
• Rebecca Szarkowski
• Cristina Rios
• James Ashe
• Bin He

Similar to the occipital alpha rhythm, electroencephalographic (EEG) signals in the alpha- and beta-frequency bands can be suppressed by movement or motor imagery and have thus been thought to represent the “idling state” of the sensorimotor cortex. A negative correlation between spontaneous alpha EEG and blood-oxygen-level-dependent (BOLD) signals has been reported in combined EEG and fMRI (functional Magnetic Resonance Imaging) experiments when subjects stayed at the resting state or alternated between the resting state and a task. However, the precise nature of the task-induced alpha modulation remains elusive. It was not clear whether alpha/beta rhythm suppressions may co-vary with BOLD when conducting tasks involving varying activations of the cortex. Here, we quantified the task-evoked responses of BOLD and alpha/beta-band power of EEG directly in the cortical source domain, by using source imaging technology, and examined their covariation across task conditions in a mixed block and event-related design. In this study, 13 subjects performed tasks of right-hand, right-foot or left-hand movement and motor imagery when EEG and fMRI data were separately collected. Task-induced increase of BOLD signal and decrease of EEG amplitudes in alpha and beta bands were shown to be co-localized at the somatotopic sensorimotor cortex. At the corresponding regions, the reciprocal changes of the two signals co-varied in the magnitudes across imagination and movement conditions. The spatial correspondence and negative covariation between the two measurements were further shown to exist at somatotopic brain regions associated with different body parts. These results suggest an inverse functional coupling relationship between task-induced changes of BOLD and low-frequency EEG signals.

YNIMG Journal 2010 Journal Article

The effects of age and sex on cortical sulci in the elderly

• Tao Liu
• Wei Wen
• Wanlin Zhu
• Julian Trollor
• Simone Reppermund
• John Crawford
• Jesse S. Jin
• Suhuai Luo

A large number of structural brain studies using magnetic resonance imaging (MRI) have reported age-related cortical changes and sex difference in brain morphology. Most studies have focused on cortical thickness or density, with relatively few studies of cortical sulcal features, especially in the elderly. In this paper, we report global sulcal indices (g-SIs) of both cerebral hemispheres and the average sulcal span in six prominent sulci, as observed in T1-weighted scans obtained from a large community cohort of 319 non-demented individuals aged between 70 and 90 years (mean=78. 06±4. 75; male/female=149/170), using automated methods. Our results showed that for both hemispheres, g-SIs had significant negative correlations with age in both men and women. Using an interactive effect analysis, we found that g-SIs for men declined faster with age than that for women. The widths of all six sulcal spans increased significantly with age, with largest span increase occurring in the superior frontal sulcus. Compared to women, men had significantly wider sulcal spans for all sulci that were examined. Our findings suggest that both age and sex contribute to significant cortical gyrification differences and variations in the elderly. This study establishes a reference for future studies of age-related brain changes and neurodegenerative diseases in the elderly.

ICML Conference 2003 Conference Paper

An Evaluation on Feature Selection for Text Clustering

• Tao Liu
• Shengping Liu
• Zheng Chen 0001
• Wei-Ying Ma