Author name cluster

Lu Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

36 papers

2 author rows

EAAI Journal 2026 Journal Article

A multivariate long-term time-series prediction model for water quality based on Transformer architecture with spectral reconstruction optimizer

Dashe Li
Ying Li
Lu Liu
Xiaodong Ji
Haoran Xing

Predicting key water quality parameters, such as dissolved oxygen, is of considerable importance for water environment monitoring and aquaculture management. It also provides scientific support to achieve ecological protection and sustainable development. However, long-term prediction faces challenges such as difficulty in nonstationary information modeling, insufficient perception of intervariable dependency structures, and limited feature expression. This study proposes a multivariate long-term time-series prediction model based on the Transformer architecture. First, a spectral reconstruction optimizer is designed to explicitly enhance and reconstruct the intermediate frequency energy in the frequency domain to solve the information asymmetry problem caused by the dominance of low frequencies in the frequency space distribution of time series. Second, a graph-structured feature modulation mechanism is constructed to dynamically adjust variable features by integrating dual-pooling compression and graph-structured modeling operations to explore potential cross-variable synergies. Finally, dual-stream hybrid attention is used. This mechanism introduces a learnable fusion of Squared Rectified Linear unit (ReLU 2 ) and softmax-attention based on a dense–sparse dual-branch structure, considering both information retention and key dependency enhancement. This study conducted experiments on six ocean datasets for 168 time steps in the future, indicating that the proposed model outperformed seven baseline models with higher accuracy and stronger generalization ability. For example, on the BaffleCreek dataset, the mean absolute error (MAE) and root mean square error (RMSE) of the proposed model were reduced by an average of 17. 50% and 16. 45%, respectively. Similarly, on the Shandong Peninsula dataset, the reductions were 31. 29% and 31. 24% for MAE and RMSE, respectively.

AAAI Conference 2026 Conference Paper

Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection

Yihua Wang
Qi Jia
Cong Xu
Feiyu Chen
Yuhan Liu
Haotian Zhang
Liang Jin
Lu Liu

Multimodal sarcasm detection is a complex task that requires distinguishing subtle complementary signals across modalities while filtering out irrelevant information. Many advanced methods rely on learning shortcuts from datasets rather than extracting intended sarcasm-related features. However, our experiments show that shortcut learning impairs the model's generalization in real-world scenarios. Furthermore, we reveal the weaknesses of current modality fusion strategies for multimodal sarcasm detection through systematic experiments, highlighting the necessity of focusing on effective modality fusion for complex emotion recognition. To address these challenges, we construct MUStARD++R by removing shortcut signals from MUStARD++. Then, a Multimodal Conditional Information Bottleneck (MCIB) model is introduced to enable efficient multimodal fusion for sarcasm detection. Experimental results show that the MCIB achieves the best performance without relying on shortcut learning.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Explainable Depression Assessment from Face Videos by Weakly Supervised Learning

Rongfan Liao
Xiangyu Kong
Shiqing Tang
Lang He
Changzeng Fu
Weicheng Xie
Xiaofeng Liu
Lu Liu

Existing video-based automatic depression assessment (ADA) approaches frequently achieve video-level depression assessment by aggregating features or predictions of individual frames or equal-length segments within the given video. While their performances have been largely enhanced by recent advanced deep learning models, they typically fail to explicitly consider the varied importance of depression-related behavioural cues across different video segments, i.e., segments within one video may contain behaviours reflecting varying levels of depression. Underestimating segment-level variations can obscure the detection of facial behaviour cues associated with depression, thereby undermining the accuracy and interpretability of video-based depression detection systems. In this paper, we propose a novel video-based ADA approach that specifically identifies and differentiates video segments that exhibit depression-related facial behaviours across varying temporal durations, providing clear insights into how each segment contributes to the video-level depression prediction. To achieve this, a novel weakly supervised strategy is proposed to compare segment-level behaviours with video-level depression label, enabling the model to assign depression-relevant scores to multiple temporal scale video segments and attend selectively to those most indicative of depressive states. Extensive experiments on the AVEC 2013 and AVEC 2014 face video depression datasets demonstrate the effectiveness of our approach.

PDF Details DOI

AAAI Conference 2026 Conference Paper

TimeCAP: A Channel-Aware Pre-Training Framework for Multivariate Time Series Forecasting

Chuanru Ren
Yao Lu
Tianjin Huang
Haowen Zheng
Hengde Zhu
Yunyin Li
Hengxiao Li
Lu Liu

Amid recent advances for multivariate time series forecasting, self-supervised learning has emerged as a promising paradigm for deriving transferable knowledge from multi-domain data. Despite its effectiveness, existing approaches exhibit two critical limitations: (1) Underestimating the significance of multivariate dependencies in learning generalizable representations and (2) Failing to reconcile the complementary strengths of autoregressive and one-shot generative paradigms. In this work, we propose TimeCAP, a novel channel-aware pre-training framework that internalizes latent causal relationships among variables inherent in multi-domain data, and effectively transfers the acquired knowledge to downstream applications. Technically, we present a flexible channel-grouping learning approach, complemented by an adaptive meta-routing mechanism, enabling TimeCAP to parallel recognize intra-group local patterns while maintaining global coherence. Intra- and inter-group multivariate dependencies are captured through the self- and cross-attention with channel-aware mask, which strictly confine interactions among time-aligned, fine-grained multivariate tokens. To seamlessly unify two advanced generative paradigms, we propose a novel dynamic dual-head decoding and optimization strategy, empowering TimeCAP to leverage critical dependencies in the output series while avoiding cumulative errors over time. In the few-shot evaluation, TimeCAP achieves average MSE and MAE reductions of 11.8% and 6% over leading baselines, while also outperforming state-of-the-art models in full-shot and zero-shot settings by large margins.

PDF Details DOI

AIIM Journal 2026 Journal Article

Topo-UNet: A topology-aware multi-task network for pulmonary vessel segmentation

Lu Liu
Ye Yuan
Yanxin Ma
WEI SHAO
Jiahe Song
Zhe Wang
Ruoyu Wang
Wenjun Tan

The precise segmentation of pulmonary vessels is crucial for the early diagnosis and treatment of pulmonary diseases. However, vessel images are frequently compromised by high levels of noise and blurred boundaries, which complicate the extraction of vessel features. Current state-of-the-art (SOTA) methods also encounter challenges such as segmenting fine vessels, interruptions in vessel continuity, and loss of inter-layer information. To address these issues, this study proposes a topology-aware multi-task network called Topo-UNet, which integrates the Bidirectional Slice-wise ConvLSTM (BS-ConvLSTM) module and topology-aware auxiliary task to enhance the accurate capture of vessel structural features. The BS-ConvLSTM module mitigates discontinuities in vessel structures by extracting spatial continuity features. Meanwhile, the topology-aware auxiliary task employs a Gaussian function to simulate the intensity distribution within vessels, improving the network's capability to accurately identify vessel structures. Additionally, this study introduces a joint auxiliary task-based method for vessel refinement that increases the recognition rate of fine vessels while enhancing segmentation continuity. Extensive experiments were conducted on CT and CTA datasets to evaluate the performance of Topo-UNet. Comparisons with various SOTA methods across multiple metrics show that Topo-UNet demonstrates superior performance in the task of pulmonary vessel segmentation. Specifically, it achieved Dice coefficients of 90. 78% and 91. 91%, along with Intersection over Union (IoU) scores of 83. 31% and 85. 09% across two test datasets. Furthermore, the discussion section presents a grouping evaluation strategy to address the segmentation performance of vessels of varying sizes, and explores a quadratic approach for vessel refinement, enhancing the segmentation of fine vessels. The code of the proposed Topo-UNet is publicly available at https: //github. com/liu66-git/Topo-UNet.

JBHI Journal 2025 Journal Article

A Clinical Data Based Framework for Outcome Forecasting in Patients With Pneumonia

Rui Gao
Robert C. Free
Ashiq Anjum
Xiang Sun
Gerrit Woltmann
Lu Liu

Respiratory diseases are a major cause of death globally, placing a significant burden on healthcare services. Early-stage clinical decision-making is crucial for enabling personalized, prioritized treatment and more efficient allocation of healthcare resources. Clinicians can intervene proactively and develop appropriate treatment plans for patients when provided with vital information such as mortality prediction, deterioration detection, and length-of-stay prediction. To precisely predict such vitals, it is essential to leverage sequential information that is inherent in clinical variables. In this paper, we employ a unified framework for patient outcome forecasting in pneumonia patients. The proposed model utilizes clinical time-series data of varying lengths, along with static admission information, to effectively capture the sequential information of clinical variables. Additionally, we model the imbalanced distribution of mortality prediction and deterioration detection through weight constraints, and we account for the right-skewed distribution of length-of-stay data to enhance the robustness of the model. Furthermore, we develop a data splitting strategy to track dynamic changes in model performance at different timestamps, helping to bridge the gap between testing conditions and real-world scenarios. We conduct experiments on CAP-AI dataset that was obtained and collected from the University Hospitals of Leicester with the involvement of clinicians. It is based on real-world clinical data from patients admitted with pneumonia-related diagnoses. Extensive experimental results demonstrate the effectiveness and robustness of our approach whilst predicting patient outcomes in a clinical setting.

EAAI Journal 2025 Journal Article

Adaptive self-evolving extreme learning machine-based terminal sliding mode control with application in retinal vein injection

Bo Hu
Shiyu Xu
Lu Liu
Rongxin Liu
Mingzhu Sun
Xin Zhao

Retinal vein occlusion (RVO) is a serious condition that can lead to blindness. Injecting drugs into the retinal vein is a promising procedure for treating RVO. Due to the fragility of the retinal tissue, maintaining a precise drug flow rate (DFR) with a fast response is critical. Considering the unknown disturbance from piston dynamic and the drug-vein interaction, an adaptive self-evolving neural terminal sliding mode (ASNTSM) controller is proposed for DFR tracking. The integral terminal sliding surface is adopted to track the desired DFR in finite-time. The extreme learning machine (ELM) is utilized to estimate overall disturbances, and the adaptive switching gain is employed to compensate for the estimation error without requiring prior bounds. To achieve a compact ELM structure, a self-evolving mechanism is designed to implement the growth or pruning strategy of the hidden neurons. Theoretical analysis has proven that the ASNTSM controller can guarantee finite-time stability. Comparative experiments are conducted using a silicon phantom with simulated blood flow disturbances. The experimental results illustrate that the ASNTSM controller not only achieves lower transient time and average steady-state error, but also exhibits lower fluctuation and chattering effect. The self-evolving mechanism enhances the practicability of neural network in artificial intelligence-based medical engineering. Therefore, the ASNTSM controller is suitable for retinal vein injection tasks to improve surgical efficiency.

JBHI Journal 2025 Journal Article

Bidirectional Prototype-Guided Consistency Constraint for Semi-Supervised Fetal Ultrasound Image Segmentation

Chongwen Lyu
Kai Han
Lu Liu
Jun Chen
Lele Ma
Zheng Pang
Zhe Liu

Fetal ultrasound (US) image segmentation plays an important role in fetal development assessment, maternal pregnancy management, and intrauterine surgery planning. However, obtaining large-scale, accurately annotated fetal US imaging data is time-consuming and labor-intensive, posing challenges to the application of deep learning in this field. To address this challenge, we propose a semi-supervised fetal US image segmentation method based on bidirectional prototype-guided consistency constraint (BiPCC). BiPCC utilizes the prototype to bridge labeled and unlabeled data and establishes interaction between them. Specifically, the model generates pseudo-labels using prototypes from labeled data and then utilizes these pseudo-labels to generate pseudo-prototypes for segmenting the labeled data inversely, thereby achieving bidirectional consistency. Additionally, uncertainty-based cross-supervision is incorporated to provide additional supervision signals, thereby enhancing the quality of pseudo-labels. Extensive experiments on two fetal US datasets demonstrate that BiPCC outperforms state-of-the-art methods for semi-supervised fetal US segmentation. Furthermore, experimental results on two additional medical segmentation datasets exhibit BiPCC's outstanding generalization capability for diverse medical image segmentation tasks. Our proposed method offers a novel insight for semi-supervised fetal US image segmentation and holds promise for further advancing the development of intelligent healthcare.

TCS Journal 2025 Journal Article

Integer-valued martingales and cl-Turing reductions

Nan Fang
Lu Liu
Liang Yu

We prove that a sequence X is integer-valued random (IVR) if and only if for every cl-tt reduction Φ, there are only finitely many oracles that compute X via Φ. A well-known property of integer-valued supermartingales is that under any cone, there is a subcone where the values are constant. We extend this property and prove that for a special integer-valued martingale M, which starts with initial capital 1 and always bets 1 on bit “1” if possible, and for any integer-valued supermartingale f, under any cone there is a subcone such that f actually simulates M. Using this property, we prove that there exists a non-IVR sequence that is cl-computable by only countably many oracles, as a complement to the first result.

EAAI Journal 2025 Journal Article

Named entity recognition based on anchor span for manufacturing knowledge extraction

Yahui Li
Qi Sun
Chunjie Zhou
Lu Liu
Yu-Chu Tian

Named Entity Recognition (NER) serves as a fundamental component of knowledge-based intelligent manufacturing systems, enabling the transformation of unstructured text into structured semantic information. However, current NER approaches face challenges in handling multiple levels of entity nesting in knowledge extraction, especially with high information density embedded in short text. To address this issue, an Anchor Span-based NER (ASNER) approach is introduced, which combines token and span classification for accurate and efficient extraction of manufacturing knowledge. It utilizes a boundary match neural network based on the head and tail features of entities to generate the corresponding anchor span of potential entities, enabling precise and robust entity localization in diverse contexts. Subsequently, the approach extracts token spatial contextual features by using biaffine attention and convolutional neural networks, and assigns classification categories to the anchor span-filtered entity features. Experimental studies demonstrate the effectiveness of the proposed ASNER approach.

AAAI Conference 2025 Conference Paper

PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation

Hengde Zhu
Xiangyu Kong
Weicheng Xie
Xin Huang
Xilin He
Lu Liu
Linlin Shen
Wei Zhang

In dyadic human-human interactions, individuals may express multiple different facial reactions in response to the same/similar behaviours expressed by their conversational partners depending on their personalised behaviour patterns. As a result, frequently-employed reconstruction loss-based strategies lead the training of previous automatic facial reaction generation (FRG) models to not only suffer from the 'one-to-many mapping' problem, but also fail to comprehensively consider the quality of the generated facial reactions. Besides, none of them considered such personalised behaviour patterns in generating facial reactions. In this paper, we propose the first adversarial FRG model training strategy which jointly learns appropriateness and realism discriminators to provide comprehensive task-specific supervision for training the target facial reaction generators, and reformulates the 'one-to-many (facial reactions) mapping' training problem as a 'one-to-one (distribution) mapping' training task, i.e., the FRG model is trained to output a distribution representing multiple appropriate/plausible facial reaction from each input human behaviour. In addition, our approach also serves as the first offline FRG approach that considers personalised behaviour patterns in generating of target individuals' facial reactions. Experiments show that our PerReactor not only largely outperformed all existing offline solutions for generating more appropriate, diverse and realistic facial reactions, but also is the first approach that can effectively generate personalised appropriate facial reactions.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

REOBench: Benchmarking Robustness of Earth Observation Foundation Models

Xiang Li
Yong Tao
Siyuan Zhang
Siwei Liu
Zhitong Xiong
Chunbo Luo
Lu Liu
Mykola Pechenizkiy

Earth observation foundation models have shown strong generalization across multiple Earth observation tasks, but their robustness under real-world perturbations remains underexplored. To bridge this gap, we introduce REOBench, the first comprehensive benchmark for evaluating the robustness of Earth observation foundation models across six tasks and twelve types of image corruptions, including both appearance-based and geometric perturbations. To ensure realistic and fine-grained evaluation, our benchmark focuses on high-resolution optical remote sensing images, which are widely used in critical applications such as urban planning and disaster response. We conduct a systematic evaluation of a broad range of models trained using masked image modeling, contrastive learning, and vision-language pre-training paradigms. Our results reveal that (1) existing Earth observation foundation models experience significant performance degradation when exposed to input corruptions. (2) The severity of degradation varies across tasks, model architectures, backbone sizes, and types of corruption, with performance drop varying from less than 1% to over 25%. (3) Vision-language models show enhanced robustness, particularly in multimodal tasks. REOBench underscores the vulnerability of current Earth observation foundation models to real-world corruptions and provides actionable insights for developing more robust and reliable models.

EAAI Journal 2025 Journal Article

Unsupervised domain adaptation for lithology classification using dynamic entropy-based prototype learning

Hengxiao Li
Yahui Liu
Lu Liu

Lithology classification plays a crucial role in geological exploration and resource evaluation. However, the significant distribution discrepancies between source and target domains, coupled with the unavailability of source domain data, pose substantial challenges to traditional domain adaptation methods. To address these challenges, we propose an innovative framework, Unsupervised Domain Adaptive Dynamic Entropy Prototype Learning (UDADEPL), which leverages a source-free unsupervised domain adaptation strategy for lithology classification. The UDADEPL framework consists of a frozen source pre-trained model and a trainable target model, incorporating a dynamic entropy-based prototype learning matrix for reliable sample selection and centroid-based pseudo-label learning for iterative optimization. Additionally, an information maximization loss and source domain regularization loss are integrated into a curriculum learning strategy to balance feature extraction and domain adaptation. This approach enables the model to effectively handle complex lithological boundaries and class imbalances in the target domain. Extensive experiments on datasets from the Tarim Oilfield and Hugoton–Panoma field demonstrate the superiority of UDADEPL over traditional machine learning and advanced deep learning models. UDADEPL achieves superior classification accuracy, outperforming the best baseline models, especially in cross-domain adaptation and complex lithology identification.

AAAI Conference 2024 Conference Paper

A Fast Exact Solver with Theoretical Analysis for the Maximum Edge-Weighted Clique Problem

Lu Liu
Mingyu Xiao
Yi Zhou

The maximum vertex-weighted clique problem (MVWCP) and the maximum edge-weighted clique problem (MEWCP) are two natural extensions of the fundamental maximum clique problem. In this paper, we systematically study MEWCP and make the following major contributions: (1) We show that MEWCP is NP-hard even when the minimum degree of the graph is n-2, in contrast to MVWCP which is polynomial-time solvable when the minimum degree of the graph is at least n-3. This result distinguishes the complexity of the two problems for the first time. (2) To address MEWCP, we develop an efficient branch-and-bound algorithm called MEWCat with both practical and theoretical performance guarantees. In practice, MEWCat utilizes a new upper bound tighter than existing ones, which allows for more efficient pruning of branches. In theory, we prove a running-time bound of O*(1.4423^n) for MEWCat, which breaks the trivial bound of O*(2^n) in the research line of practical exact MEWCP solvers for the first time. (3) Empirically, we evaluate the performance of MEWCat on various benchmark instances. The experiments demonstrate that MEWCat outperforms state-of-the-art exact solvers significantly. For instance, on 16 DIMACS graphs that the state-of-the-art solver BBEWC fails to solve within 7200 seconds, MEWCat solves all of them with an average time of less than 1000 seconds. On real-world graphs, MEWCat achieves an average speedup of over 36x.

PDF Details DOI

EAAI Journal 2024 Journal Article

A user review data-driven supplier ranking model using aspect-based sentiment analysis and fuzzy theory

Bingli Sun
Xiao Song
Wenxin Li
Lu Liu
Guanghong Gong
Yan Zhao

Background: The supplier selection problem is a sophisticated decision-making process that involves evaluating multiple factors. While previous research has primarily focused on objective attributes, such as supplier qualifications, product quality, and price, the subjective opinions of users have often been overlooked. However, with the growing importance of user reviews and sentiment analysis in e-commerce, incorporating users’ opinions on supplier products can provide valuable insights. Purpose: This study aims to address the limitations of existing supplier selection approaches by proposing a comprehensive framework that integrates aspect-level sentiment analysis and a fuzzy multi-attribute decision model. The goal is to enhance the decision-making process by considering both objective attributes and subjective opinions. Methods: To achieve this, we develop a novel convolutional neural network (CNN) model with a gating mechanism to perform aspect-level sentiment analysis. Furthermore, we propose a fuzzy multi-attribute decision model that combines the predefined sentiment aspects with traditional evaluation criteria. The model is applied to a dataset specifically designed for automotive component supplier selection. Results: Experimental results demonstrate the superior performance of our approach compared to existing methods and datasets. A case study demonstrates the combination of aspect-level sentiment analysis and the fuzzy decision model allows for a more comprehensive evaluation of suppliers. Conclusion: By integrating aspect-level sentiment analysis and the fuzzy multi-attribute decision model, our proposed framework offers a novel perspective on supplier selection problems. The results highlight the feasibility and superiority of our approach, providing valuable insights for management in making informed decisions. This research contributes to the fields of supplier selection, sentiment analysis, and decision-making, with potential applications in various industries beyond the automotive sector.

NeurIPS Conference 2024 Conference Paper

Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and Baseline

Qi Jia
Baoyu Fan
Cong Xu
Lu Liu
Liang Jin
Guoguang Du
Zhenhua Guo
Yaqian Zhao

Existing video multi-modal sentiment analysis mainly focuses on the sentiment expression of people within the video, yet often neglects the induced sentiment of viewers while watching the videos. Induced sentiment of viewers is essential for inferring the public response to videos and has broad application in analyzing public societal sentiment, effectiveness of advertising and other areas. The micro videos and the related comments provide a rich application scenario for viewers’ induced sentiment analysis. In light of this, we introduces a novel research task, Multimodal Sentiment Analysis for Comment Response of Video Induced(MSA-CRVI), aims to infer opinions and emotions according to comments response to micro video. Meanwhile, we manually annotate a dataset named Comment Sentiment toward to Micro Video (CSMV) to support this research. It is the largest video multi-modal sentiment dataset in terms of scale and video duration to our knowledge, containing 107, 267 comments and 8, 210 micro videos with a video duration of 68. 83 hours. To infer the induced sentiment of comment should leverage the video content, we propose the Video Content-aware Comment Sentiment Analysis (VC-CSA) method as a baseline to address the challenges inherent in this new task. Extensive experiments demonstrate that our method is showing significant improvements over other established baselines. We make the dataset and source code publicly available at https: //github. com/IEIT-AGI/MSA-CRVI.

PDF Details DOI

JBHI Journal 2022 Journal Article

A Fully Deep Learning Paradigm for Pneumoconiosis Staging on Chest Radiographs

Wenjian Sun
Dongsheng Wu
Yang Luo
Lu Liu
Hongjing Zhang
Shuang Wu
Yan Zhang
Chenglong Wang

Pneumoconiosis staging has been a very challenging task, both for certified radiologists and computer-aided detection algorithms. Although deep learning has shown proven advantages in the detection of pneumoconiosis, it remains challenging in pneumoconiosis staging due to the stage ambiguity of pneumoconiosis and noisy samples caused by misdiagnosis when they are used in training deep learning models. In this article, we propose a fully deep learning pneumoconiosis staging paradigm that comprises a segmentation procedure and a staging procedure. The segmentation procedure extracts lung fields in chest radiographs through an Asymmetric Encoder-Decoder Network (AED-Net) that can mitigate the domain shift between multiple datasets. The staging procedure classifies the lung fields into four stages through our proposed deep log-normal label distribution learning and focal staging loss. The two cascaded procedures can effectively solve the problem of model overfitting caused by stage ambiguity and noisy labels of pneumoconiosis. Besides, we collect a clinical chest radiograph dataset of pneumoconiosis from the certified radiologist's diagnostic reports. The experimental results on this novel pneumoconiosis dataset confirm that the proposed deep pneumoconiosis staging paradigm achieves an Accuracy of 90. 4%, a Precision of 84. 8%, a Sensitivity of 78. 4%, a Specificity of 95. 6%, an F1-score of 80. 9% and an Area Under the Curve (AUC) of 96%. In particular, we achieve 68. 4% Precision, 76. 5% Sensitivity, 95% Specificity, 72. 2% F1-score and 89% AUC on the early pneumoconiosis ‘stage-1’.

JBHI Journal 2022 Journal Article

An Effective Semi-Supervised Approach for Liver CT Image Segmentation

Kai Han
Lu Liu
Yuqing Song
Yi Liu
Chengjian Qiu
Yangyang Tang
Qiaoying Teng
Zhe Liu

Despite the substantial progress made by deep networks in the field of medical image segmentation, they generally require sufficient pixel-level annotated data for training. The scale of training data remains to be the main bottleneck to obtain a better deep segmentation model. Semi-supervised learning is an effective approach that alleviates the dependence on labeled data. However, most existing semi-supervised image segmentation methods usually do not generate high-quality pseudo labels to expand training dataset. In this paper, we propose a deep semi-supervised approach for liver CT image segmentation by expanding pseudo-labeling algorithm under the very low annotated-data paradigm. Specifically, the output features of labeled images from the pretrained network combine with corresponding pixel-level annotations to produce class representations according to the mean operation. Then pseudo labels of unlabeled images are generated by calculating the distances between unlabeled feature vectors and each class representation. To further improve the quality of pseudo labels, we adopt a series of operations to optimize pseudo labels. A more accurate segmentation network is obtained by expanding the training dataset and adjusting the contributions between supervised and unsupervised loss. Besides, the novel random patch based on prior locations is introduced for unlabeled images in the training procedure. Extensive experiments show our method has achieved more competitive results compared with other semi-supervised methods when fewer labeled slices of LiTS dataset are available.

YNICL Journal 2022 Journal Article

Changes in brain connectivity linked to multisensory processing of pain modulation in migraine with acupuncture treatment

Lu Liu
Tian-Li Lyu
Ming-Yang Fu
Lin-Peng Wang
Ying Chen
Jia-Hui Hong
Qiu-Yi Chen
Yu-Pu Zhu

Migraine without aura (MWoA) is a major neurological disorder with unsatisfactory adherence to current medications. Acupuncture has emerged as a promising method for treating MWoA. However, the brain mechanism underlying acupuncture is yet unclear. The present study aimed to examine the effects of acupuncture in regulating brain connectivity of the key regions in pain modulation. In this study, MWoA patients were recruited and randomly assigned to 4 weeks of real or sham acupuncture. Resting-state functional magnetic resonance imaging (fMRI) data were collected before and after the treatment. A modern neuroimaging literature meta-analysis of 515 fMRI studies was conducted to identify pain modulation-related key regions as regions of interest (ROIs). Seed-to-voxel resting state-functional connectivity (rsFC) method and repeated-measures two-way analysis of variance were conducted to determine the interaction effects between the two groups and time (baseline and post-treatment). The changes in rsFC were evaluated between baseline and post-treatment in real and sham acupuncture groups, respectively. Clinical data at baseline and post-treatment were also recorded in order to determine between-group differences in clinical outcomes as well as correlations between rsFC changes and clinical effects. 40 subjects were involved in the final analysis. The current study demonstrated significant improvement in real acupuncture vs sham acupuncture on headache severity (monthly migraine days), headache impact (6-item Headache Impact Test), and health-related quality of life (Migraine-Specific Quality of Life Questionnaire). Five pain modulation-related key regions, including the right amygdala (AMYG), left insula (INS), left medial orbital superior frontal gyrus (PFCventmed), left middle occipital gyrus (MOG), and right middle cingulate cortex (MCC), were selected based on the meta-analysis on brain imaging studies. This study found that 1) after acupuncture treatment, migraine patients of the real acupuncture group showed significantly enhanced connectivity in the right AMYG/MCC-left MTG and the right MCC-right superior temporal gyrus (STG) compared to that of the sham acupuncture group; 2) negative correlations were established between clinical effects and increased rsFC in the right AMYG/MCC-left MTG; 3) baseline right AMYG-left MTG rsFC predicts monthly migraine days reduction after treatment. The current results suggested that acupuncture may concurrently regulate the rsFC of two pain modulation regions in the AMYG and MCC. MTG and STG may be the key nodes linked to multisensory processing of pain modulation in migraine with acupuncture treatment. These findings highlighted the potential of acupuncture for migraine management and the mechanisms underlying the modulation effects.

NeurIPS Conference 2022 Conference Paper

Federated Learning from Pre-Trained Models: A Contrastive Learning Approach

Yue Tan
Guodong Long
Jie Ma
Lu Liu
Tianyi Zhou
Jing Jiang

Federated Learning (FL) is a machine learning paradigm that allows decentralized clients to learn collaboratively without sharing their private data. However, excessive computation and communication demands pose challenges to current FL frameworks, especially when training large-scale models. To prevent these issues from hindering the deployment of FL systems, we propose a lightweight framework where clients jointly learn to fuse the representations generated by multiple fixed pre-trained models rather than training a large-scale model from scratch. This leads us to a more practical FL problem by considering how to capture more client-specific and class-relevant information from the pre-trained models and jointly improve each client's ability to exploit those off-the-shelf models. Here, we design a Federated Prototype-wise Contrastive Learning (FedPCL) approach which shares knowledge across clients through their class prototypes and builds client-specific representations in a prototype-wise contrastive manner. Sharing prototypes rather than learnable model parameters allows each client to fuse the representations in a personalized way while keeping the shared knowledge in a compact form for efficient communication. We perform a thorough evaluation of the proposed FedPCL in the lightweight framework, measuring and visualizing its ability to fuse various pre-trained models on popular FL datasets.

AAAI Conference 2022 Conference Paper

FedProto: Federated Prototype Learning across Heterogeneous Clients

Yue Tan
Guodong Long
Lu Liu
Tianyi Zhou
Qinghua Lu
Jing Jiang
Chengqi Zhang

Heterogeneity across clients in federated learning (FL) usually hinders the optimization convergence and generalization performance when the aggregation of clients’ knowledge occurs in the gradient space. For example, clients may differ in terms of data distribution, network latency, input/output space, and/or model architecture, which can easily lead to the misalignment of their local gradients. To improve the tolerance to heterogeneity, we propose a novel federated prototype learning (FedProto) framework in which the clients and server communicate the abstract class prototypes instead of the gradients. FedProto aggregates the local prototypes collected from different clients, and then sends the global prototypes back to all clients to regularize the training of local models. The training on each client aims to minimize the classification error on the local data while keeping the resulting local prototypes sufficiently close to the corresponding global ones. Moreover, we provide a theoretical analysis to the convergence rate of FedProto under non-convex objectives. In experiments, we propose a benchmark setting tailored for heterogeneous FL, with FedProto outperforming several recent FL approaches on multiple datasets.

YNIMG Journal 2021 Journal Article

Eating to dare - Nutrition impacts human risky decision and related brain function

Lu Liu
Sergio Oroz Artigas
Anja Ulrich
Jeremy Tardu
Peter N.C. Mohr
Britta Wilms
Berthold Koletzko
Sebastian M. Schmid

Macronutrient composition modulates plasma amino acids that are precursors of neurotransmitters and can impact brain function and decisions. Neurotransmitter serotonin has been shown to regulate not only food intake, but also economic decisions. We investigated whether an acute nutrition-manipulation inducing plasma tryptophan fluctuation affects brain function, thereby affecting risky decisions. Breakfasts differing in carbohydrate/protein ratios were offered to test changes in risky decision-making while metabolic and neural dynamics were tracked. We identified that a high-carbohydrate/protein breakfast increased plasma tryptophan/LNAA (large neutral amino acids) ratio which mapped to individual risk propensity changes. The nutrition-manipulation and tryptophan/LNAA fluctuation effects on risk propensity changes were further modulated by individual differences in body fat mass. Using fMRI, we further identified activation in the parietal lobule during risk-processing, of which activities 1) were sensitive to the tryptophan/LNAA fluctuation, 2) were modulated by individual's body fat mass, and 3) predicted the risk propensity changes in decision-making. Our results provide evidence for a personalized nutrition-driven modulation on human risky decision and its metabolic and neural mechanisms.

ICLR Conference 2021 Conference Paper

Free Lunch for Few-shot Learning: Distribution Calibration

Shuo Yang 0006
Lu Liu
Min Xu 0001

Learning from a limited number of samples is challenging since the learned model can easily become overfitted based on the biased distribution formed by only a few training examples. In this paper, we calibrate the distribution of these few-sample classes by transferring statistics from the classes with sufficient examples. Then an adequate number of examples can be sampled from the calibrated distribution to expand the inputs to the classifier. We assume every dimension in the feature representation follows a Gaussian distribution so that the mean and the variance of the distribution can borrow from that of similar classes whose statistics are better estimated with an adequate number of samples. Our method can be built on top of off-the-shelf pretrained feature extractors and classification models without extra parameters. We show that a simple logistic regression classifier trained using the features sampled from our calibrated distribution can outperform the state-of-the-art accuracy on three datasets (~5% improvement on miniImageNet compared to the next best). The visualization of these generated features demonstrates that our calibrated distribution is an accurate estimation.

NeurIPS Conference 2021 Conference Paper

Recognizing Vector Graphics without Rasterization

Xinyang Jiang
Lu Liu
Caihua Shan
Yifei Shen
Xuanyi Dong
Dongsheng Li

In this paper, we consider a different data format for images: vector graphics. In contrast to raster graphics which are widely used in image recognition, vector graphics can be scaled up or down into any resolution without aliasing or information loss, due to the analytic representation of the primitives in the document. Furthermore, vector graphics are able to give extra structural information on how low-level elements group together to form high level shapes or structures. These merits of graphic vectors have not been fully leveraged in existing methods. To explore this data format, we target on the fundamental recognition tasks: object localization and classification. We propose an efficient CNN-free pipeline that does not render the graphic into pixels (i. e. rasterization), and takes textual document of the vector graphics as input, called YOLaT (You Only Look at Text). YOLaT builds multi-graphs to model the structural and spatial information in vector graphics, and a dual-stream graph neural network is proposed to detect objects from the graph. Our experiments show that by directly operating on vector graphics, YOLaT outperforms raster-graphic based object detection baselines in terms of both average precision and efficiency. Code is available at https: //github. com/microsoft/YOLaT-VectorGraphicsRecognition.

AAAI Conference 2020 Conference Paper

Attribute Propagation Network for Graph Zero-Shot Learning

Lu Liu
Tianyi Zhou
Guodong Long
Jing Jiang
Chengqi Zhang

The goal of zero-shot learning (ZSL) is to train a model to classify samples of classes that were not seen during training. To address this challenging task, most ZSL methods relate unseen test classes to seen(training) classes via a predeﬁned set of attributes that can describe all classes in the same semantic space, so the knowledge learned on the training classes can be adapted to unseen classes. In this paper, we aim to optimize the attribute space for ZSL by training a propagation mechanism to reﬁne the semantic attributes of each class based on its neighbors and related classes on a graph of classes. We show that the propagated attributes can produce classiﬁers for zero-shot classes with signiﬁcantly improved performance in different ZSL settings. The graph of classes is usually free or very cheap to acquire such as WordNet or ImageNet classes. When the graph is not provided, given predeﬁned semantic embeddings of the classes, we can learn a mechanism to generate the graph in an end-to-end manner along with the propagation mechanism. However, this graphaided technique has not been well-explored in the literature. In this paper, we introduce the “attribute propagation network (APNet)”, which is composed of 1) a graph propagation model generating attribute vector for each class and 2) a parameterized nearest neighbor (NN) classiﬁer categorizing an image to the class with the nearest attribute vector to the image’s embedding. For better generalization over unseen classes, different from previous methods, we adopt a metalearning strategy to train the propagation mechanism and the similarity metric for the NN classiﬁer on multiple sub-graphs, each associated with a classiﬁcation task over a subset of training classes. In experiments with two zero-shot learning settings and ﬁve benchmark datasets, APNet achieves either compelling performance or new state-of-the-art results.

YNICL Journal 2020 Journal Article

Is monetary reward processing altered in drug-naïve youth with a behavioral addiction? Findings from internet gaming disorder

Yuan-Wei Yao
Lu Liu
Patrick D. Worhunsky
Sarah Lichenstein
Shan-Shan Ma
Lei Zhu
Xin-Hui Shi
Songshan Yang

Current models of addiction biology highlight altered neural responses to non-drug rewards as a central feature of addiction. However, given that drugs of abuse can directly impact reward-related dopamine circuitry, it is difficult to determine the extent to which reward processing alterations are a trait feature of individuals with addictions, or primarily a consequence of exogenous drug exposure. Examining individuals with behavioral addictions is one promising approach for disentangling neural features of addiction from the direct effects of substance exposure. The current fMRI study compared neural responses during monetary reward processing between drug naïve young adults with a behavioral addiction, internet gaming disorder (IGD; n = 22), and healthy controls (n = 27) using a monetary incentive delay task. Relative to controls, individuals with IGD exhibited blunted caudate activity associated with loss magnitude at the outcome stage, but did not differ from controls in neural activity at other stages. These findings suggest that decreased loss sensitivity might be a critical feature of IGD, whereas alterations in gain processing may be less characteristic of individuals with IGD, relative to those with substance use disorders. Therefore, classic theories of altered reward processing in substance use disorders should be translated to behavioral addictions with caution.

TIST Journal 2019 Journal Article

Energy-efficient Static Task Scheduling on VFI-based NoC-HMPSoCs for Intelligent Edge Devices in Cyber-physical Systems

Umair Ullah Tariq
Haider Ali
Lu Liu
John Panneerselvam
Xiaojun Zhai

The interlinked processing units in modern Cyber-Physical Systems (CPS) creates a large network of connected computing embedded systems. Network-on-Chip (NoC)-based Multiprocessor System-on-Chip (MPSoC) architecture is becoming a de facto computing platform for real-time applications due to its higher performance and Quality-of-Service (QoS). The number of processors has increased significantly on the multiprocessor systems in CPS; therefore, Voltage Frequency Island (VFI) has been recently adopted for effective energy management mechanism in the large-scale multiprocessor chip designs. In this article, we investigated energy-efficient and contention-aware static scheduling for tasks with precedence and deadline constraints on intelligent edge devices deploying heterogeneous VFI-based NoC-MPSoCs (VFI-NoC-HMPSoC) with DVFS-enabled processors. Unlike the existing population-based optimization algorithms, we proposed a novel population-based algorithm called ARSH-FATI that can dynamically switch between explorative and exploitative search modes at run-time. Our static scheduler ARHS-FATI collectively performs task mapping, scheduling, and voltage scaling. Consequently, its performance is superior to the existing state-of-the-art approach proposed for homogeneous VFI-based NoC-MPSoCs. We also developed a communication contention-aware Earliest Edge Consistent Deadline First (EECDF) scheduling algorithm and gradient descent--inspired voltage scaling algorithm called Energy Gradient Decent (EGD). We introduced a notion of Energy Gradient (EG) that guides EGD in its search for island voltage settings and minimize the total energy consumption. We conducted the experiments on eight real benchmarks adopted from Embedded Systems Synthesis Benchmarks (E3S). Our static scheduling approach ARSH-FATI outperformed state-of-the-art technique and achieved an average energy-efficiency of ∼24% and ∼30% over CA-TMES-Search and CA-TMES-Quick, respectively.

NeurIPS Conference 2019 Conference Paper

Learning to Propagate for Graph Meta-Learning

Lu Liu
Tianyi Zhou
Guodong Long
Jing Jiang
Chengqi Zhang

Meta-learning extracts the common knowledge from learning different tasks and uses it for unseen tasks. It can signiﬁcantly improve tasks that suffer from insufﬁcient training data, e. g. , few-shot learning. In most meta-learning methods, tasks are implicitly related by sharing parameters or optimizer. In this paper, we show that a meta-learner that explicitly relates tasks on a graph describing the relations of their output dimensions (e. g. , classes) can signiﬁcantly improve few-shot learning. The graph’s structure is usually free or cheap to obtain but has rarely been explored in previous works. We develop a novel meta-learner of this type for prototype based classiﬁcation, in which a prototype is generated for each class, such that the nearest neighbor search among the prototypes produces an accurate classiﬁcation. The meta-learner, called “Gated Propagation Network (GPN)”, learns to propagate messages between prototypes of different classes on the graph, so that learning the prototype of each class beneﬁts from the data of other related classes. In GPN, an attention mechanism aggregates messages from neighboring classes of each class, with a gate choosing between the aggregated message and the message from the class itself. We train GPN on a sequence of tasks from many-shot to few-shot generated by subgraph sampling. During training, it is able to reuse and update previously achieved prototypes from the memory in a life-long learning cycle. In experiments, under different training-test discrepancy and test task generation settings, GPN outperforms recent meta-learning methods on two benchmark datasets. Code of GPN is publicly available at: https: //github. com/liulu112601/Gated-Propagation-Net.

IJCAI Conference 2019 Conference Paper

Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph

Lu Liu
Tianyi Zhou
Guodong Long
Jing Jiang
Lina Yao
Chengqi Zhang

A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they do not fully explore weakly-supervised information, which is usually free or cheap to collect. In this paper, we show that weakly-labeled data can significantly improve the performance of meta-learning on few-shot classification. We propose prototype propagation network (PPN) trained on few-shot tasks together with data annotated by coarse-label. Given a category graph of the targeted fine-classes and some weakly-labeled coarse-classes, PPN learns an attention mechanism which propagates the prototype of one class to another on the graph, so that the K-nearest neighbor (KNN) classifier defined on the propagated prototypes results in high accuracy across different few-shot tasks. The training tasks are generated by subgraph sampling, and the training objective is obtained by accumulating the level-wise classification loss on the subgraph. On two benchmarks, PPN significantly outperforms most recent few-shot learning methods in different settings, even when they are also allowed to train on weakly-labeled data.

YNICL Journal 2019 Journal Article

The neural correlations of spatial attention and working memory deficits in adults with ADHD

Xiangsheng Luo
Jialiang Guo
Lu Liu
Xixi Zhao
Dongwei Li
Hui Li
Qihua Zhao
Yanfei Wang

Working memory impairment is a typical cognitive abnormality in patients with attention-deficit/hyperactivity disorder (ADHD) and is closely related to attention. Exploring the interaction between working memory and attention in patients with ADHD is of great significance for studying the pathological mechanism of this disease. In this study, electrophysiological markers of attention, posterior contralateral N2 (N2pc), and working memory, contralateral delay activity (CDA), were used to explore the relationship between these two cognitive abilities in patients with ADHD. EEG data were collected from adults with ADHD and age-, sex-, and IQ-matched normal controls while performing a classical visuospatial working memory task that consisted of low-load and high-load memory conditions. In different memory load conditions, the memory array elicited a smaller N2pc (220-260 ms) and a smaller CDA (400-800 ms) in adults with ADHD than in normal controls. Further analysis revealed that the reduced CDA amplitude could be significantly predicted by the earlier and reduced N2pc amplitude in adults with ADHD. Moreover, when the number of memory items increased, the increase in N2pc highly predicted the increases in CDA. Our findings illustrate the relationship between spatial working memory and attention ability in ADHD adults from the neurophysiological aspect that reduced working memory is closely related to insufficient attention ability and provide a potential physiological basis for the pathological mechanism of ADHD.

AAAI Conference 2018 Conference Paper

Attention-based Belief or Disbelief Feature Extraction for Dependency Parsing

Haoyuan Peng
Lu Liu
Yi Zhou
Junying Zhou
Xiaoqing Zheng

Existing neural dependency parsers usually encode each word in a sentence with bi-directional LSTMs, and estimate the score of an arc from the LSTM representations of the head and the modiﬁer, possibly missing relevant context information for the arc being considered. In this study, we propose a neural feature extraction method that learns to extract arcspeciﬁc features. We apply a neural network-based attention method to collect evidences for and against each possible head-modiﬁer pair, with which our model computes certainty scores of belief and disbelief, and determines the ﬁnal arc score by subtracting the score of disbelief from the one of belief. By explicitly introducing two kinds of evidences, the arc candidates can compete against each other based on more relevant information, especially for the cases where they share the same head or modiﬁer. It makes possible to better discriminate two or more competing arcs by presenting their rivals (disbelief evidence). Experiments on various datasets show that our arc-speciﬁc feature extraction mechanism signiﬁcantly improves the performance of bi-directional LSTMbased models by explicitly modeling long-distance dependencies. For both English and Chinese, the proposed model achieve a higher accuracy on dependency parsing task than most existing neural attention-based models.

AAAI Conference 2018 Conference Paper

RNN-Based Sequence-Preserved Attention for Dependency Parsing

Yi Zhou
Junying Zhou
Lu Liu
Jiangtao Feng
Haoyuan Peng
Xiaoqing Zheng

Recurrent neural networks (RNN) combined with attention mechanism has proved to be useful for various NLP tasks including machine translation, sequence labeling and syntactic parsing. The attention mechanism is usually applied by estimating the weights (or importance) of inputs and taking the weighted sum of inputs as derived features. Although such features have demonstrated their effectiveness, they may fail to capture the sequence information due to the simple weighted sum being used to produce them. The order of the words does matter to the meaning or the structure of the sentences, especially for syntactic parsing, which aims to recover the structure from a sequence of words. In this study, we propose an RNN-based attention to capture the relevant and sequence-preserved features from a sentence, and use the derived features to perform the dependency parsing. We evaluated the graph-based and transition-based parsing models enhanced with the RNN-based sequence-preserved attention on the both English PTB and Chinese CTB datasets. The experimental results show that the enhanced systems were improved with signiﬁcant increase in parsing accuracy.

YNICL Journal 2017 Journal Article

Dissociable neural processes during risky decision-making in individuals with Internet-gaming disorder

Lu Liu
Gui Xue
Marc N. Potenza
Jin-Tao Zhang
Yuan-Wei Yao
Cui-Cui Xia
Jing Lan
Shan-Shan Ma

Risk-taking is purported to be central to addictive behaviors. However, for Internet gaming disorder (IGD), a condition conceptualized as a behavioral addiction, the neural processes underlying impaired decision-making (risk evaluation and outcome processing) related to gains and losses have not been systematically investigated. Forty-one males with IGD and 27 healthy comparison (HC) male participants were recruited, and the cups task was used to identify neural processes associated with gain- and loss-related risk- and outcome-processing in IGD. During risk evaluation, the IGD group, compared to the HC participants, showed weaker modulation for experienced risk within the bilateral dorsolateral prefrontal cortex (DLPFC) (t =−4. 07; t =−3. 94; P FWE <0. 05) and inferior parietal lobule (IPL) (t =−4. 08; t =−4. 08; P FWE <0. 05) for potential losses. The modulation of the left DLPFC and bilateral IPL activation were negatively related to addiction severity within the IGD group (r =−0. 55; r =−0. 61; r =−0. 51; P FWE <0. 05). During outcome processing, the IGD group presented greater responses for the experienced reward within the ventral striatum, ventromedial prefrontal cortex, and orbitofrontal cortex (OFC) (t =5. 04, P FWE <0. 05) for potential gains, as compared to HC participants. Within the IGD group, the increased reward-related activity in the right OFC was positively associated with severity of IGD (r =0. 51, P FWE <0. 05). These results provide a neurobiological foundation for decision-making deficits in individuals with IGD and suggest an imbalance between hypersensitivity for reward and weaker risk experience and self-control for loss. The findings suggest a biological mechanism for why individuals with IGD may persist in game-seeking behavior despite negative consequences, and treatment development strategies may focus on targeting these neural pathways in this population.

YNICL Journal 2016 Journal Article

Effects of craving behavioral intervention on neural substrates of cue-induced craving in Internet gaming disorder

Jin-Tao Zhang
Yuan-Wei Yao
Marc N. Potenza
Cui-Cui Xia
Jing Lan
Lu Liu
Ling-Jiao Wang
Ben Liu

Internet gaming disorder (IGD) is characterized by high levels of craving for online gaming and related cues. Since addiction-related cues can evoke increased activation in brain areas involved in motivational and reward processing and may engender gaming behaviors or trigger relapse, ameliorating cue-induced craving may be a promising target for interventions for IGD. This study compared neural activation between 40 IGD and 19 healthy control (HC) subjects during an Internet-gaming cue-reactivity task and found that IGD subjects showed stronger activation in multiple brain areas, including the dorsal striatum, brainstem, substantia nigra, and anterior cingulate cortex, but lower activation in the posterior insula. Furthermore, twenty-three IGD subjects (CBI + group) participated in a craving behavioral intervention (CBI) group therapy, whereas the remaining 17 IGD subjects (CBI - group) did not receive any intervention, and all IGD subjects were scanned during similar time intervals. The CBI + group showed decreased IGD severity and cue-induced craving, enhanced activation in the anterior insula and decreased insular connectivity with the lingual gyrus and precuneus after receiving CBI. These findings suggest that CBI is effective in reducing craving and severity in IGD, and it may exert its effects by altering insula activation and its connectivity with regions involved in visual processing and attention bias.

EAAI Journal 2016 Journal Article

The improved grey model based on particle swarm optimization algorithm for time series prediction

Kewen Li
Lu Liu
Jiannan Zhai
Taghi M. Khoshgoftaar
Timing Li

Grey theory is one of the most common methods for solving uncertain problems using limited data and poor information, due to its high performance in time series prediction. However, the inappropriate background value and initial value are the main factors affecting prediction accuracy of the Grey Model GM(1, 1). An improved grey model based on particle swarm optimization algorithm named PGM(1, 1) is proposed for time series prediction in this paper. The development coefficient of the grey model is calculated by PGM(1, 1) based on particle swarm optimization, targeting at minimizing the average relative errors between the restored value and real value of the model to avoid the problem caused by background value optimization. In addition, the initial value of the Grey Model GM(1, 1) is optimized and a sliding window is introduced to improve both precision and adaptability. Finally, three data sets, featuring increasing trend, decreasing trend, and wide fluctuations, are used in the experiments, showing that the proposed method achieves better prediction accuracy.

AAAI Conference 2014 Conference Paper

Forecasting Potential Diabetes Complications

Yang Yang
Walter Luyten
Lu Liu
Marie-Francine Moens
Jie Tang
Juanzi Li

Diabetes complications often afflict diabetes patients seriously: over 68% of diabetes-related mortality is caused by diabetes complications. In this paper, we study the problem of automatically diagnosing diabetes complications from patients’ lab test results. The objective problem has two main challenges: 1) feature sparseness: a patient only undergoes 1. 26% lab tests on average, and 65. 5% types of lab tests are performed on samples from less than 10 patients; 2) knowledge skewness: it lacks comprehensive detailed domain knowledge of the association between diabetes complications and lab tests. To address these challenges, we propose a novel probabilistic model called Sparse Factor Graph Model (SparseFGM). SparseFGM projects sparse features onto a lower-dimensional latent space, which alleviates the problem of sparseness. SparseFGM is also able to capture the associations between complications and lab tests, which help handle the knowledge skewness. We evaluate the proposed model on a large collections of real medical records. SparseFGM outperforms (+20% by F1) baselines significantly and gives detailed associations between diabetes complications and lab tests.