Min Liu

EAAI Journal 2026 Journal Article

A deep learning-based imaging classification framework for interstitial lung disease

• Hongyi Wang
• Anqi Liu
• Xiaoyan Yang
• Yifei Ni
• Jianping Wang
• Jie Du
• Yuhui Qiang
• Bingbing Xie

Rationale Interstitial lung diseases (ILD) are a diverse group of conditions, often diagnosed using high-resolution chest computed tomography (HRCT), which is susceptible to subjective biases in interpretation. Objectives This study aims to develop and validate SPAIDNet (Spatial Pattern Analysis for ILD Diagnosis using a residual neural Network), a deep learning (DL) model for the automated classification of ILD, to reduce subjective biases and improve diagnostic consistency. Methods The study included 2901 ILD patients who underwent 5213 HRCT scans across multiple centers between July 2017 and June 2023. SPAIDNet, built upon the pre-trained residual neural network with 18 layers, utilizes multi-instance learning in three centers in China. Measurements and main results The model demonstrated exceptional performance, achieving macro-average area under the receiver operating characteristic curve (AUC) of over 0. 999 in internal validation, 0. 905 in external cohort I, and 0. 870 in external cohort II for multiclass classification. SPAIDNet outperformed both a junior radiologist (AUC: 0. 737) and a senior radiologist (AUC: 0. 763). Furthermore, DL-assisted the two radiologists saw significant improvements in diagnostic accuracy, with AUCs rising to 0. 817 and 0. 787, respectively. Conclusions These results underscore SPAIDNet's potential to offer high accuracy, robustness, and generalizability in ILD diagnosis, providing a valuable tool to mitigate the subjectivity inherent in HRCT image interpretation.

JBHI Journal 2026 Journal Article

DF-DiffVSR: Deformable Field-Driven Diffusion Model for Inter-Slice Continuity Enhancement in Medical Volume Super-Resolution

• Can Wang
• Min Liu
• Qinghao Liu
• Yuehao Zhu
• Xiang Chen
• Licheng Liu
• Yaonan Wang
• Erik Meijering

Medical volumetric imaging is crucial for precise diagnosis, but limited by equipment and acquisition constraints, anisotropic resolution leads to challenges in detecting small lesions and 3D visualization. While volumetric super-resolution methods can mitigate this issue, existing techniques suffer from limited receptive fields, failing to fully exploit inter-slice correlations and resulting in compromised inter-slice continuity. To address this limitation, we propose DF-DiffVSR, a novel deformable field-enhanced diffusion model for medical volume super resolution. The proposed method integrates optical flow principles with diffusion models through a Deformable Field Extraction (DFE) module, which explicitly learns inter slice motion information to enhance structural continuity in the through-plane direction. Furthermore, we design a Multiscale Large Kernel Convolution (MLKC) module that employs striped convolutions with varying kernel sizes to expand the receptive field and capture global anatomical context. Evaluated on RPLHR-CT and IXI-T2 datasets, DF DiffVSR achieves state-of-the-art (SOTA) performance, surpassing the sub-optimal method by 0. 732 dB and 0. 214 dB in PSNR, respectively, demonstrating superior capabilities in preserving inter-slice continuity and recovering fine grained details.

AAAI Conference 2026 Conference Paper

Mono3DVG-EnSD: Enhanced Spatial-aware and Dimension-decoupled Text Encoding for Monocular 3D Visual Grounding

• Yuzhen Li
• Min Liu
• Zhaoyang Li
• Yuan Bian
• Xueping Wang
• Erbo Zhai
• Yaonan Wang

Monocular 3D Visual Grounding (Mono3DVG) is an emerging task that locates 3D objects in RGB images using text descriptions with geometric cues. However, existing methods face two key limitations. Firstly, they often over-rely on high-certainty keywords that explicitly identify the target object while neglecting critical spatial descriptions. Secondly, generalized textual features contain both 2D and 3D descriptive information, thereby capturing an additional dimension of details compared to singular 2D or 3D visual features. This characteristic leads to cross-dimensional interference when refining visual features under text guidance. To overcome these challenges, we propose Mono3DVG-EnSD, a novel framework that integrates two key components: the CLIP-Guided Lexical Certainty Adapter (CLIP-LCA) and the Dimension-Decoupled Module (D2M). The CLIP-LCA dynamically masks high-certainty keywords while retaining low-certainty implicit spatial descriptions, thereby forcing the model to develop a deeper understanding of spatial relationships in captions for object localization. Meanwhile, the D2M decouples dimension-specific (2D/3D) textual features from generalized textual features to guide corresponding visual features at same dimension, which mitigates cross-dimensional interference by ensuring dimensionally-consistent cross-modal interactions. Through comprehensive comparisons and ablation studies on the Mono3DRefer dataset, our method achieves state-of-the-art (SOTA) performance across all metrics. Notably, it improves the challenging Far(Acc@0.5) scenario by a significant +13.54%.

JBHI Journal 2026 Journal Article

Morphology Prior Enhanced Teeth Segmentation for High-Resolution Oral Scans

• Yuxian Jiang
• Xiuying Wang
• Tao Yang
• Changkai Ji
• Lanshan He
• Yusheng Liu
• Wei Wang
• Min Liu

Deep learning methods have been proposed for tooth segmentation on high-resolution intra-oral scans (IOS) that plays a crucial role in clinical dental practice. However, they generally segment teeth in a low-resolution data with a fixed receptive field and generate final segmentation by up-sampling interpolation, and neglect teeth’s morphology priors: their similar dental arch structures and significantly different curvatures in different parts of each tooth. They thus lack adaptability to different parts of each tooth, and show less accurate segmentation of boundary points between teeth and gums due to the up-sampling computation. Further, cluttered poses of IOS limit their generalization and usability of teeth location and geometric information. To address these limitations, a morphology prior enhanced teeth segmentation framework is proposed in this paper. Firstly, a robust preprocessing is introduced to align poses of different IOS by computing their dental arch orientations, thereby improving segmentation generalization and usability of IOS geometric information. Secondly, a decomposition-merging strategy is designed to avoid the up-sampling limitation, which decomposes an IOS into multiple low-resolution data and merges their segmentation outcomes into a high-resolution result. Thirdly, an innovative module integrating semantic and geometric features is proposed to adaptively select deformable receptive fields. It geometrically samples within a variable probability space to construct receptive fields with varied graph relationships for different points, facilitating adaptive segmentation of different parts of each tooth. Experimental results on 6238 IOS from four centers demonstrate that our method significantly outperforms 11 state-of-the-art methods, achieving a 6. 93% enhancement for cross-center testing.

EAAI Journal 2026 Journal Article

Physics-based and data-driven adaptive compressor optimization in gas pipeline systems under dynamic and non-isothermal conditions

• Min Liu
• Nan Dong
• Xinmin Wang
• Ling Jian

With growing demand variability and closer integration between gas and electricity systems, intraday fluctuations in non-isothermal gas transmission pipelines have become more pronounced. Accurate dynamic simulation and adaptive optimization are therefore needed to ensure efficient and secure compressor operation. This paper proposes a hierarchical simulation–optimization framework to minimize system self-consumption. The simulation layer combines a physics-based dynamic model with data-driven enhancement. Key physical parameters, including the pipeline friction factor and total heat transfer coefficient, are identified from historical field measurements, and a long short-term memory network with an attention mechanism is used to compensate residual modeling errors. The optimization layer formulates dynamic compressor operation as a sequential decision-making problem and solves it using an improved double deep Q-network that accounts for both static pipeline characteristics and time-varying operating conditions. A decoupled time-scale design separates optimization decisions from fine-grained simulation steps, preserving simulation fidelity while producing operationally feasible strategies. On a real pipeline benchmark with field measurements, the hybrid simulation model achieves an average relative error below 1%, and the proposed optimization method reduces system self-consumption by 8. 78% relative to the deep Q-network and by 12. 74% relative to the double deep Q-network.

AAAI Conference 2026 Conference Paper

R-Tuning: Wavelet-Decomposed Replay and Semantic Alignment for Continual Adaptation of Pretrained Time-Series Models

• Tianyi Yin
• Jingwei Wang
• Chenze Wang
• Han Wang
• Jiexuan Cai
• Min Liu
• Yunlong Ma
• Kun Gao

Pre-trained models have demonstrated exceptional generalization capabilities in time-series forecasting; however, adapting them to evolving data distributions remains a significant challenge. A key hurdle lies in accessing the original training data, as fine-tuning solely on new data often leads to catastrophic forgetting. To address this issue, we propose Replay Tuning (R-Tuning), a novel framework designed for the continual adaptation of pre-trained time-series models. R-Tuning constructs a unified latent space that captures both prior and current task knowledge through a frequency-aware replay strategy. Specifically, it augments model-generated samples via wavelet-based decomposition across multiple frequency bands, generating trend-preserving and fusion-enhanced variants to improve representation diversity and replay efficiency. To further reduce reliance on synthetic samples, R-Tuning introduces a latent consistency constraint that aligns new representations with the prior task space. This constraint guides joint optimization within a compact and semantically coherent latent space, ensuring robust knowledge retention and adaptation. Extensive experimental results demonstrate the superiority of R-Tuning, which reduces MAE and MSE by up to 46.9% and 46.8%, respectively, on new tasks, while preserving prior knowledge with gains of up to 5.7% and 6.0% on old tasks. Notably, under few-shot settings, R-Tuning outperforms all state-of-the-art baselines even when synthetic proxy samples account for only 5% of the new task dataset.

AAAI Conference 2026 Conference Paper

Re-architecting Personalized Federated Learning for Demanding Edge Environments

• Quyang Pan
• Sheng Sun
• Tingting Wi
• Zhiyuan Wu
• Yuwei Wang
• Min Liu
• Bo Gao
• Jingyuan Wang

Federated Edge Learning (FEL) has emerged as a promising approach for enabling edge devices to collaboratively train machine learning models while preserving data privacy. Despite its advantages, practical FEL deployment faces significant challenges related to device constraints and device-server interactions, necessitating heterogeneous, user-adaptive model training with limited and uncertain communication. While knowledge cache-driven federated learning offers a promising FEL solution for demanding edge environments, its logits-based interaction design provides poor richness of exchanged information for on-device model optimization. To tackle this issue, we introduce DistilCacheFL, a novel personalized FEL architecture that enhances the exchange of optimization insights while delivering state-of-the-art performance with efficient communication. DistilCacheFL incorporates the benefits of both dataset distillation and knowledge cache-driven federated learning by storing and organizing distilled data as knowledge in the server-side knowledge cache, allowing devices to periodically download and utilize personalized knowledge for local model optimization. Moreover, a device-centric cache sampling strategy is introduced to tailor transferred knowledge for individual devices within controlled communication bandwidth. Extensive experiments on five datasets covering image recognition, audio understanding, and mobile sensor data mining tasks demonstrate that (1) DistilCacheFL significantly outperforms state-of-the-art methods regardless of model structures, data distributions, and modalities. (2) DistilCacheFL can train splendid personalized on-device models with at least 28.6 improvement in communication efficiency.

AAAI Conference 2025 Conference Paper

Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting

• Tianyi Yin
• Jingwei Wang
• Yunlong Ma
• Han Wang
• Chenze Wang
• Yukai Zhao
• Min Liu
• Weiming Shen

Encoding time series into tokens and using language models for processing has been shown to substantially augment the models' ability to generalize to unseen tasks. However, existing language models for time series forecasting encounter several obstacles, including aliasing distortion and prolonged inference times, primarily due to the limitations of quantization processes and the computational demands of large models. This paper introduces Apollo-Forecast, a novel framework that tackles these challenges with two key innovations: the Anti-Aliasing Quantization Module (AAQM) and the Race Decoding (RD) technique. AAQM adeptly encodes sequences into tokens while mitigating high-frequency noise in the original signals, thus enhancing both signal fidelity and overall quantization efficiency. RD employs a draft model to enable parallel processing and results integration, which markedly accelerates the inference speed for long-term predictions, particularly in large-scale models. Extensive experiments on various real-world datasets show that Apollo-Forecast outperforms state-of-the-art methods by 35.41% and 18.99% in WQL and MASE metrics, respectively, in zero-shot scenarios. Furthermore, our method achieves an acceleration of 1.9X-2.7X in inference speed over the baseline methods.

ICRA Conference 2025 Conference Paper

FACET: Fast and Accurate Event-Based Eye Tracking Using Ellipse Modeling for Extended Reality

• Junyuan Ding
• Ziteng Wang
• Chang Gao 0002
• Min Liu
• Qinyu Chen

Eye tracking is a key technology for gaze-based interactions in Extended Reality (XR), but traditional frame-based systems struggle to meet XR's demands for high accuracy, low latency, and power efficiency. Event cameras offer a promising alternative due to their high temporal resolution and low power consumption. In this paper, we present FACET (Fast and Accurate Event-based Eye Tracking), an end-to-end neural network that directly outputs pupil ellipse parameters from event data, optimized for real-time XR applications. The ellipse output can be directly used in subsequent ellipse-based pupil trackers. We enhance the EV-Eye dataset by expanding annotated data and converting original mask labels to ellipse-based annotations to train the model. Besides, a novel trigonometric loss is adopted to address angle discontinuities and a fast causal event volume event representation method is put forward. On the enhanced EV-Eye test set, FACET achieves an average pupil center error of $\mathbf{0. 2 0}$ pixels and an inference time of 0. 53 ms, reducing pixel error and inference time by $1. 6 \times$ and $1. 8 \times$ compared to the prior art, EV-Eye, with $4. 4 \times$ and $11. 7 \times$ less parameters and arithmetic operations. The code is available at https://github.com/DeanJY/FACET.

ICRA Conference 2025 Conference Paper

Local Policies Enable Zero-Shot Long-Horizon Manipulation

• Murtaza Dalal
• Min Liu
• Walter Talbott
• Chen Chen 0032
• Deepak Pathak
• Jian Zhang 0050
• Ruslan Salakhutdinov

Sim2real for robotic manipulation is difficult due to the challenges of simulating complex contacts and generating realistic task distributions. To tackle the latter problem, we introduce ManipGen, which leverages a new class of policies for sim2real transfer: local policies. Locality enables a variety of appealing properties including invariances to absolute robot and object pose, skill ordering, and global scene configuration. We combine these policies with foundation models for vision, language and motion planning and demonstrate SOTA zero-shot performance of our method to Robosuite benchmark tasks in simulation (97 %). We transfer our local policies from simulation to reality and observe they can solve unseen long-horizon manipulation tasks with up to 8 stages with significant pose, object and scene configuration variation. ManipGen outperforms SOTA approaches such as SayCan, Open VLA, LLMTrajGen and VoxPoser across 50 real-world manipulation tasks by 36%, 76%, 62% and 60% respectively. Video results at mihdalal.github.io/manipgen

FLAP Journal 2025 Journal Article

Maximal Ideals and Minimal Prime Ideals on ∨-Ehoops

• Min Liu
• Hongxing Liu

In this paper, the notion of maximal ideals on Ehoops is introduced. It is proved that every proper Ehoop has at least one maximal filter. If a ∨-Ehoop A has the least element 0, then A has at least one maximal ideal and every proper ideal of A is contained in a maximal ideal of A. In addition, the concept of minimal prime ideals of A is defined. We provide two equivalent theorems for minimal prime ideals. Furthermore, the hull-kernel topology of the set of maximal ideals (maximal filters) of A is investigated. It is showed that the weak topology of the set of state-morphisms and the hull-kernel topology of the set of maximal filters are homeomorphic.

NeurIPS Conference 2025 Conference Paper

OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates

• Jinpei Guo
• Yifei Ji
• Zheng Chen
• Kai Liu
• Min Liu
• Wang Rao
• Wenbo Li
• Yong Guo

Pretrained latent diffusion models have shown strong potential for lossy image compression, owing to their powerful generative priors. Most existing diffusion-based methods reconstruct images by iteratively denoising from random noise, guided by compressed latent representations. While these approaches have achieved high reconstruction quality, their multi-step sampling process incurs substantial computational overhead. Moreover, they typically require training separate models for different compression bit-rates, leading to significant training and storage costs. To address these challenges, we propose a one-step diffusion codec across multiple bit-rates. termed OSCAR. Specifically, our method views compressed latents as noisy variants of the original latents, where the level of distortion depends on the bit-rate. This perspective allows them to be modeled as intermediate states along a diffusion trajectory. By establishing a mapping from the compression bit-rate to a pseudo diffusion timestep, we condition a single generative model to support reconstructions at multiple bit-rates. Meanwhile, we argue that the compressed latents retain rich structural information, thereby making one-step denoising feasible. Thus, OSCAR replaces iterative sampling with a single denoising pass, significantly improving inference efficiency. Extensive experiments demonstrate that OSCAR achieves superior performance in both quantitative and visual quality metrics. The code and models are available at https: //github. com/jp-guo/OSCAR/.

AAAI Conference 2025 Conference Paper

Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach

• Qingxiang Liu
• Sheng Sun
• Yuxuan Liang
• Min Liu
• Jingjing Xue

The existing federated learning (FL) methods for spatio-temporal forecasting fail to capture the inherent spatio-temporal heterogeneity, which calls for personalized FL (PFL) methods to model the spatio-temporally variant representations. While contrastive learning is promising in tackling spatio-temporal heterogeneity, the existing methods are noneffective in distinguishing positive and negative pairs and can hardly apply to PFL paradigm. To tackle this limitation, we propose a novel PFL method, named Federated dUal sEmantic aLignment-based contraStive learning (FUELS), which can adaptively align positive and negative pairs based on semantic similarity, thereby injecting precise spatio-temporal heterogeneity into the latent representation space by auxiliary contrastive tasks. From temporal perspective, a hard negative filtering module is introduced to dynamically align heterogeneous temporal representations for the supplemented intra-client contrastive task. From spatial perspective, we design lightweight-but-efficient prototypes as client-level semantic representations, based on which the server evaluates spatial similarity and yields client-customized global prototypes for the supplemented inter-client contrastive task. Extensive experiments demonstrate that FUELS outperforms state-of-the-art methods, with impressive communication cost reduction.

NeurIPS Conference 2025 Conference Paper

Searching Efficient Semantic Segmentation Architectures via Dynamic Path Selection

• Yuxi Liu
• Min Liu
• Shuai Jiang
• Yi Tang
• Yaonan Wang

Existing NAS methods for semantic segmentation typically apply uniform optimization to all candidate networks (paths) within a one-shot supernet. However, the concurrent existence of both promising and suboptimal paths often results in inefficient weight updates and gradient conflicts. This issue is particularly severe in semantic segmentation due to its complex multi-branch architectures and large search space, which further degrade the supernet's ability to accurately evaluate individual paths and identify high-quality candidates. To address this issue, we propose Dynamic Path Selection (DPS), a selective training strategy that leverages multiple performance proxies to guide path optimization. DPS follows a stage-wise paradigm, where each phase emphasizes a different objective: early stages prioritize convergence, the middle stage focuses on expressiveness, and the final stage emphasizes a balanced combination of expressiveness and generalization. At each stage, paths are selected based on these criteria, concentrating optimization efforts on promising paths, thus facilitating targeted and efficient model updates. Additionally, DPS integrates a dynamic stage scheduler and a diversity-driven exploration strategy, which jointly enable adaptive stage transitions and maintain structural diversity among selected paths. Extensive experiments demonstrate that, under the same search space, DPS can discover efficient models with strong generalization and superior performance.

FLAP Journal 2024 Journal Article

Esemihoops

• Min Liu
• Hongxing Liu

TIST Journal 2024 Journal Article

Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation

• Zhiyuan Wu
• Sheng Sun
• Yuwei Wang
• Min Liu
• Quyang Pan
• Junbo Zhang
• Zeju Li
• Qingxiang Liu

Federated learning (FL) is a privacy-preserving machine learning paradigm in which the server periodically aggregates local model parameters from cli ents without assembling their private data. Constrained communication and personalization requirements pose severe challenges to FL. Federated distillation (FD) is proposed to simultaneously address the above two problems, which exchanges knowledge between the server and clients, supporting heterogeneous local models while significantly reducing communication overhead. However, most existing FD methods require a proxy dataset, which is often unavailable in reality. A few recent proxy-data-free FD approaches can eliminate the need for additional public data, but suffer from remarkable discrepancy among local knowledge due to client-side model heterogeneity, leading to ambiguous representation on the server and inevitable accuracy degradation. To tackle this issue, we propose a proxy-data-free FD algorithm based on distributed knowledge congruence (FedDKC). FedDKC leverages well-designed refinement strategies to narrow local knowledge differences into an acceptable upper bound, so as to mitigate the negative effects of knowledge incongruence. Specifically, from perspectives of peak probability and Shannon entropy of local knowledge, we design kernel-based knowledge refinement (KKR) and searching-based knowledge refinement (SKR) respectively, and theoretically guarantee that the refined-local knowledge can satisfy an approximately-similar distribution and be regarded as congruent. Extensive experiments conducted on three common datasets demonstrate that our proposed FedDKC significantly outperforms the state-of-the-art on various heterogeneous settings while evidently improving the convergence speed.

EAAI Journal 2024 Journal Article

KD loss: Enhancing discriminability of features with kernel trick for object detection in VHR remote sensing images

• Xi Chen
• Liyue Li
• Zhihong Li
• Min Liu
• Qingli Li
• Honggang Qi
• Dongliang Ma
• Ying Wen

The classification accuracy of the object detection relies on the network's ability to learn discriminative features on very high resolution (VHR) remote sensing images. Popular optimization of the feature representation is implemented with loss functions by minimizing intra-class distance and maximizing inter-class distance in the original feature space. However, existing loss functions may be insufficient in capturing the complex nonlinear relationships inherent in the data, requiring further improvement to achieve accurate classification. To address this issue, we propose a new loss function, referred to as the kernel-based discriminative loss (KD loss), by constructing weight term using the kernel trick and applying them to re-weight the softmax cross-entropy loss. Specifically, the KD loss maps the class centers of deep features to the Hilbert space and calculates the distance between each class center using the Mercer kernel. Besides, the KD loss also employs kernel function to learn the similarity between the deep features and their corresponding class center, thereby facilitating the model in acquiring more discriminative and class-specific feature representations. Compared to existing loss functions, the KD loss improves the feature discriminability in the high-dimensional Hilbert space for the first time. Extensive experiments on the DOTA and RSOD datasets demonstrate that the KD loss can significantly improve the performance of VHR remote sensing object detection.

IROS Conference 2024 Conference Paper

SoftMAC: Differentiable Soft Body Simulation with Forecast-based Contact Model and Two-way Coupling with Articulated Rigid Bodies and Clothes

• Min Liu
• Gang Yang
• Siyuan Luo
• Lin Shao 0002

Differentiable physics simulation provides an avenue to tackle previously intractable challenges through gradient-based optimization, thereby greatly improving the efficiency of solving robotics-related problems. To apply differentiable simulation in diverse robotic manipulation scenarios, a key challenge is to integrate various materials in a unified framework. We present SoftMAC, a differentiable simulation framework that couples soft bodies with articulated rigid bodies and clothes. SoftMAC simulates soft bodies with the continuum-mechanics-based Material Point Method (MPM). We provide a novel forecast-based contact model for MPM, which effectively reduces penetration without introducing other artifacts like unnatural rebound. To couple MPM particles with deformable and non-volumetric clothes meshes, we also propose a penetration tracing algorithm that reconstructs the signed distance field in local area. Diverging from previous works, SoftMAC simulates the complete dynamics of each modality and incorporates them into a cohesive system with an explicit and differentiable coupling mechanism. The feature empowers SoftMAC to handle a broader spectrum of interactions, such as soft bodies serving as manipulators and engaging with underactuated systems. We conducted comprehensive experiments to validate the effectiveness and accuracy of the proposed differentiable pipeline in downstream robotic manipulation applications. Supplementary materials are available on our project website at https://damianliumin.github.io/SoftMAC.

EAAI Journal 2024 Journal Article

Time-segment-wise feature fusion transformer for multi-modal fault diagnosis

• Xiaohan Zhang
• Han Wang
• Chenze Wang
• Min Liu
• Gaowei Xu

Mechanical fault diagnosis is crucial to ensure the safe operations of equipment in intelligent manufacturing systems. Recently, deep learning based fault diagnosis methods have achieved remarkable advancements with monitored data from a single sensor. However, obtaining satisfactory diagnostic results based on a single sensor is often difficult because the complementary information between different sensors is ignored. Extracting comprehensive fault features from multi-modal data is a problem that remains to be solved. To address these challenges, a time-segment-wise feature fusion Transformer (FFTR) is proposed in this paper. First, the signals from various modalities as multiple channels are normalized channel-by-channel and form a multi-modal sample. Second, a time-segment-wise feature learning network is designed to transform a multi-modal sample into several fusion features through the sequential processes of sample segmentation, segment-level feature extraction and time-aligned feature fusion. Finally, a Transformer network is employed for comprehensive multi-modal feature analysis and fault classification. In addition, a joint loss function is designed to comprehensively train the end-to-end FFTR. The comparison experiment with other baseline methods is conducted on two multi-modal datasets. The experimental results show that FFTR achieves 3. 69% and 3. 93% higher diagnostic accuracy than baseline on two datasets respectively and can address real-world problems effectively.

EAAI Journal 2023 Journal Article

An online continual object detector on VHR remote sensing images with class imbalance

• Xi Chen
• Jie Jiang
• Zhiqiang Li
• Honggang Qi
• Qingli Li
• Jiapeng Liu
• Laiwen Zheng
• Min Liu

It is a great challenge for traditional offline detectors to learn from continuous data streams, remember previous tasks and adapt to new-coming tasks in dynamic environments. To meet the challenge, online continual learning has recently attracted increasing attention, while the overwhelming majority of works focus only on classification with a balanced class distribution assumption. In this paper, we propose a replay-based approach called an online continual object detector (OCOD) for very-high-resolution (VHR) remote sensing images. First, we find that rehearsal imbalance is ubiquitous, and has more important impact on experimental results than class imbalance, which is contrary to the situation of offline learning (due to the limited memory). Here, rehearsal imbalance refers to significant difference among the number of images pertaining to various classes. Second, entropy is used to measure the degree of rehearsal imbalance in the memory, and an entropy reservoir sampling (ERS) strategy is proposed to maintain rehearsal balance in the online memory. Finally, a rehearsal-balancing priority assignment network (RBPAN) is proposed to adaptively select images from the memory for a rehearsal-balancing replay procedure. The experimental results obtained on three publicly available VHR satellite images from the NWPU VHR-10, DIOR and DOTA datasets, highlight the effectiveness and practicality of developed method.

EAAI Journal 2023 Journal Article

MIANet: Multi-level temporal information aggregation in mixed-periodicity time series forecasting tasks

• Sheng Wang
• Xi Chen
• Dongliang Ma
• Chen Wang
• Yong Wang
• Honggang Qi
• Gongjian Zhou
• Qingli Li

Regular human activities generate a large number of time series with mixed periodicity that can reflect human behavior patterns and the societal working mechanism. When forecasting these time series, nonlinear neural networks often encounter some limitations, such as utilizing mixed-periodic patterns, balancing multi-level information, incorporating future vision, forecasting delays and scale insensitivity, which affect the forecasting accuracy. To address these problems, we propose the Multi-level Information Aggregation Network (MIANet), a novel neural network with four key characteristics: (i) a novel folded recurrent structure that dynamically updates the local and mini-local information at a global range in a compact manner; (ii) a new recurrent unit called Folded Convolution Aggregation Temporal Memory (FCATM) that extracts and aggregates neighbor-trends in local and mini-local data; (iii) a fusing decoder structure that promotes the sharing of forward–backward future information and adaptively adjusts relationships among adjacent points; and (iv) a new Skip-Autoregressive (SAR) linear strategy that addresses scale sensitivity issues. The SAR can be embedded as a plug-and-play component into other deep learning (DL) models. Compared with other baseline methods, MIANet obtains statistically significant improvements on six real-world datasets, as demonstrated by conducting two-sample t-tests, indicating that the MIANet can be applied to various predictive scenarios, such as road occupancy, electricity consumption, pedestrian flow and urban noise.

AAAI Conference 2023 Conference Paper

Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation

• Min Liu
• Yu Bao
• Chengqi Zhao
• Shujian Huang

Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive Transformer (NAT) achieves great success in neural machine translation tasks. However, existing knowledge distillation has side effects, such as propagating errors from the teacher to NAT students, which may limit further improvements of NAT models and are rarely discussed in existing research. In this paper, we introduce selective knowledge distillation by introducing an NAT evaluator to select NAT-friendly targets that are of high quality and easy to learn. In addition, we introduce a simple yet effective progressive distillation method to boost NAT performance. Experiment results on multiple WMT language directions and several representative NAT models show that our approach can realize a flexible trade-off between the quality and complexity of training data for NAT models, achieving strong performances. Further analysis shows that distilling only 5% of the raw translations can help an NAT outperform its counterpart trained on raw data by about 2.4 BLEU.

JBHI Journal 2023 Journal Article

TransFusionNet: Semantic and Spatial Features Fusion Framework for Liver Tumor and Vessel Segmentation Under JetsonTX2

• Xun Wang
• Xudong Zhang
• Gan Wang
• Ying Zhang
• Xin Shi
• Huanhuan Dai
• Min Liu
• Zixuan Wang

Liver cancer is one of the most common malignant diseases worldwide. Segmentation and reconstruction of liver tumors and vessels in CT images can provide convenience for physicians in preoperative planning and surgical intervention. In this paper, we introduced a TransFusionNet framework, which consists of a semantic feature extraction module, a local spatial feature extraction module, an edge feature extraction module, and a multi-scale feature fusion module to achieve fine-grained segmentation of liver tumors and vessels. In addition, we applied the transfer learning approach to pre-train using public datasets and then fine-tune the model to further improve the fitting effect. Furthermore, we proposed an intelligent quantization scheme to compress the model weights and achieved high performance inference on JetsonTX2. The TransFusionNet framework achieved mean IoU of 0. 854 in vessel segmentation task, and achieved mean IoU of 0. 927 in liver tumor segmentation task. When profiling the Computational Performance of the quantized inference, our quantized model achieved 4TFLOPs on Node with NVIDIA RTX3090 and 132GFLOPs on JetsonTX2. This unprecedented segmentation effect solves the accuracy and performance bottleneck of automated segmentation to a certain extent.

JBHI Journal 2022 Journal Article

A Deep Learning Method for Breast Cancer Classification in the Pathology Images

• Min Liu
• Lanlan Hu
• Ying Tang
• Chu Wang
• Yu He
• Chunyan Zeng
• Kun Lin
• Zhizi He

Objective: Breast cancer is the most common female cancer in the world, and it poses a huge threat to women's health. There is currently promising research concerning its early diagnosis using deep learning methodologies. However, some commonly used Convolutional Neural Network (CNN) and their variations, such as AlexNet, VGGNet, GoogleNet and so on, are prone to overfitting in breast cancer classification, due to both small-scale breast pathology image datasets and overconfident softmax-cross-entropy loss. To alleviate the overfitting issue for better classification accuracy, we propose a novel framework for breast pathology classification, called the AlexNet-BC model. The model is pre-trained using the ImageNet dataset and fine-tuned using an augmented dataset. We also devise an improved cross-entropy loss function to penalize overconfident low-entropy output distributions and make the predictions suitable for uniform distributions. The proposed approach is then validated through a series of comparative experiments on BreaKHis, IDC and UCSB datasets. The experimental results show that the proposed method outperforms the state-of-the-art methods at different magnifications. Its strong robustness and generalization capabilities make it suitable for histopathology clinical computer-aided diagnosis systems.

JBHI Journal 2022 Journal Article

An O-Shape Neural Network With Attention Modules to Detect Junctions in Biomedical Images Without Segmentation

• Yuqiang Zhang
• Min Liu
• Fuhao Yu
• Tieyong Zeng
• Yaonan Wang

Junction plays an important role in biomedical research such as retinal biometric identification, retinal image registration, eye-related disease diagnosis and neuron reconstruction. However, junction detection in original biomedical images is extremely challenging. For example, retinal images contain many tiny blood vessels with complicated structures and low contrast, which makes it challenging to detect junctions. In this paper, we propose an O-shape Network architecture with Attention modules (Attention O-Net), which includes Junction Detection Branch (JDB) and Local Enhancement Branch (LEB) to detect junctions in biomedical images without segmentation. In JDB, the heatmap indicating the probabilities of junctions is estimated and followed by choosing the positions with the local highest value as the junctions, whereas it is challenging to detect junctions when the images contain weak filament signals. Therefore, LEB is constructed to enhance the thin branch foreground and make the network pay more attention to the regions with low contrast, which is helpful to alleviate the imbalance of the foreground between thin and thick branches and to detect the junctions of the thin branch. Furthermore, attention modules are utilized to introduce the feature maps of LEB to JDB, which can establish a complementary relationship and further integrate local features and contextual information between these two branches. The proposed method achieves the highest average F1-scores of 0. 82, 0. 73 and 0. 94 in two retinal datasets and one neuron dataset, respectively. The experimental results confirm that Attention O-Net outperforms other state-of-the-art detection methods, and is helpful for retinal biometric identification.

JBHI Journal 2022 Journal Article

DeepRayburst for Automatic Shape Analysis of Tree-Like Structures in Biomedical Images

• Yi Jiang
• Weixun Chen
• Min Liu
• Yaonan Wang
• Erik Meijering

Precise quantification of tree-like structures from biomedical images, such as neuronal shape reconstruction and retinal blood vessel caliber estimation, is increasingly important in understanding normal function and pathologic processes in biology. Some handcrafted methods have been proposed for this purpose in recent years. However, they are designed only for a specific application. In this paper, we propose a shape analysis algorithm, DeepRayburst, that can be applied to many different applications based on a Multi-Feature Rayburst Sampling (MFRS) and a Dual Channel Temporal Convolutional Network (DC-TCN). Specifically, we first generate a Rayburst Sampling (RS) core containing a set of multidirectional rays. Then the MFRS is designed by extending each ray of the RS to multiple parallel rays which extract a set of feature sequences. A Gaussian kernel is then used to fuse these feature sequences and outputs one feature sequence. Furthermore, we design a DC-TCN to make the rays terminate on the surface of tree-like structures according to the fused feature sequence. Finally, by analyzing the distribution patterns of the terminated rays, the algorithm can serve multiple shape analysis applications of tree-like structures. Experiments on three different applications, including soma shape reconstruction, neuronal shape reconstruction, and vessel caliber estimation, confirm that the proposed method outperforms other state-of-the-art shape analysis methods, which demonstrate its flexibility and robustness.

JBHI Journal 2021 Journal Article

Efficient 3D Junction Detection in Biomedical Images Based on a Circular Sampling Model and Reverse Mapping

• Lan Shen
• Min Liu
• Chao Wang
• Changhao Guo
• Erik Meijering
• Yaonan Wang

Detection and localization of terminations and junctions is a key step in the morphological reconstruction of tree-like structures in images. Previously, a ray-shooting model was proposed to detect termination points automatically. In this paper, we propose an automatic method for 3D junction points detection in biomedical images, relying on a circular sampling model and a 2D-to-3D reverse mapping approach. First, the existing ray-shooting model is improved to a circular sampling model to extract the pixel intensity distribution feature across the potential branches around the point of interest. The computation cost can be reduced dramatically compared to the existing ray-shooting model. Then, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is employed to detect 2D junction points in maximum intensity projections (MIPs) of sub-volume images in a given 3D image, by determining the number of branches in the candidate junction region. Further, a 2D-to-3D reverse mapping approach is used to map these detected 2D junction points in MIPs to the 3D junction points in the original 3D images. The proposed 3D junction point detection method is implemented as a build-in tool in the Vaa3D platform. Experiments on multiple 2D images and 3D images show average precision and recall rates of 87. 11% and 88. 33% respectively. In addition, the proposed algorithm is dozens of times faster than the existing deep-learning based model. The proposed method has excellent performance in both detection precision and computation efficiency for junction detection even in large-scale biomedical images.

JBHI Journal 2021 Journal Article

Neuron Image Segmentation via Learning Deep Features and Enhancing Weak Neuronal Structures

• Bo Yang
• Weixun Chen
• Huiqiong Luo
• Yinghui Tan
• Min Liu
• Yaonan Wang

Neuron morphology reconstruction (tracing) in 3D volumetric images is critical for neuronal research. However, most existing neuron tracing methods are not applicable in challenging datasets where the neuron images are contaminated by noises or containing weak filament signals. In this paper, we present a two-stage 3D neuron segmentation approach via learning deep features and enhancing weak neuronal structures, to reduce the impact of image noise in the data and enhance the weak-signal neuronal structures. In the first stage, we train a voxel-wise multi-level fully convolutional network (FCN), which specializes in learning deep features, to obtain the 3D neuron image segmentation maps in an end-to-end manner. In the second stage, a ray-shooting model is employed to detect the discontinued segments in segmentation results of the first-stage, and the local neuron diameter of the broken point is estimated and direction of the filamentary fragment is detected by rayburst sampling algorithm. Then, a Hessian-repair model is built to repair the broken structures, by enhancing weak neuronal structures in a fibrous structure determined by the estimated local neuron diameter and the filamentary fragment direction. Experimental results demonstrate that our proposed segmentation approach achieves better segmentation performance than other state-of-the-art methods for 3D neuron segmentation. Compared with the neuron reconstruction results on the segmented images produced by other segmentation methods, the proposed approach gains 47. 83% and 34. 83% improvement in the average distance scores. The average Precision and Recall rates of the branch point detection with our proposed method are 38. 74% and 22. 53% higher than the detection results without segmentation.

AAMAS Conference 2019 Conference Paper

Attack-Resilient Connectivity Game for UAV Networks using Generative Adversarial Learning

• Bo Yang
• Min Liu

The continuous link connectivity is critical for the efficient collaboration of multiple unmanned aerial vehicles (UAVs). However, the UAV communication environments are not only harsh, but are also confronted with the threats of smart attackers, which pose great barriers in maintaining the links unblocked. In this paper, we leverage the paradigm of the Generative Adversarial Network (GAN) to formulate an attackresilient connectivity game between a pair of neighboring UAVs and an attacker. In the three-agent adversary game, the attacker acts as the generator, which attempts to generate highly approximate information as the UAVs so as to maximize its jamming capability; while the pairwise UAVs act as the discriminators, which attempt to enhance the capability of refusing the fake information (i. e. , the opponent’s attack). As the state-of-the-art GAN learning algorithms suffer from the instability dilemma (i. e. , either with the unsuccessful convergence or with the low generation/discrimination performance), we incorporate the conditional GAN with the least square objective loss function as well as the mean square error such that the attacker can improve the detection capability from UAVs’ historical activity patterns and the UAVs can accordingly adjust the connectivity strategy. We validate the effectiveness of the proposed algorithm through extensive evaluations. Results demonstrate that the proposed algorithm can improve the convergence efficiency, reduce the connection latency, and enhance the attack-resilience capability significantly.

TCS Journal 2019 Journal Article

On conditional fault tolerance of hierarchical cubic networks

• Xiang-Jun Li
• Min Liu
• Zheng Yan
• Jun-Ming Xu

This paper considers the conditional fault tolerance, h-super connectivity κ h and h-super edge-connectivity λ h of the hierarchical cubic network H C N n, an attractive alternative network to the hypercube, and shows κ h ( H C N n ) = λ h ( H C N n ) = 2 h ( n + 1 − h ) for any h with 0 ≤ h ≤ n − 1. The results imply that at least 2 h ( n + 1 − h ) vertices or edges have to be removed from H C N n to make it disconnected with no vertices of degree less than h, and generalize some known results.

YNICL Journal 2019 Journal Article

The effect of ApoE ε4 on longitudinal brain region-specific glucose metabolism in patients with mild cognitive impairment: a FDG-PET study

• Manish D. Paranjpe
• Xueqi Chen
• Min Liu
• Ishan Paranjpe
• Jeffrey P. Leal
• Rongfu Wang
• Martin G. Pomper
• Dean F. Wong

While the ApoE ε4 allele is a known risk factor for mild cognitive impairment (MCI) and Alzheimer's disease, brain region specific effects remain elusive. In this study, we investigate whether the ApoE ε4 allele exhibits brain region specific effects in longitudinal glucose uptake among patients with MCI from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Preprocessed FDG PET images, MRIs, and demographic information were downloaded from the ADNI database. An iterative reblurred Van Cittertiteration method was used for partial volume correction (PVC) on all PET images. Structural MRIs were used for PET spatial normalization and region of interest (ROI) definition in standard space. Longitudinal changes in ROI FDG standardized uptake value ratio (SUVR) relative to cerebellum in 24 ApoE ε4 carriers and 24 age-matched ApoE ε4 non-carriers were measured for up to 84-months (median 72 months, SD = 11.2 months) and compared using a generalized linear mixed effects model controlling for gender, education, baseline age, and follow-up period. Additionally, voxelwise analysis was performed by implementing a paired t-test comparing matched baseline and 72 month FDG SUVR images in ApoE carriers and non-carriers separately. Results with PVC were compared with ones from non-PVC based analysis. After applying PVC, the superior fontal, parietal, lateral temporal, medial temporal, caudate, thalamus, and post-cingulate, and amygdala regions had greater longitudinal decreases in FDG uptake in ApoE ε4 carriers with MCI compared to non-carriers with MCI. Similar forebrain and limbic clusters were found through voxelwise analysis. Compared to the PVC based analysis, fewer significant ApoE-associated regions and clusters were found in the non-PVC based PET analysis. Our findings suggest that the ApoE ε4 genotype is associated with a longitudinal decline in glucose uptake in 8 forebrain and limbic brain regions in the context of MCI. In conclusion, this 84-months longitudinal FDG PET study demonstrates a novel ApoE ε4-associated brain-region specific glucose metabolism pattern in patients with MCI. Partial volume correction improved FDG PET quantification.

IJCAI Conference 2018 Conference Paper

Keeping in Touch with Collaborative UAVs: A Deep Reinforcement Learning Approach

• Bo Yang
• Min Liu

Effective collaborations among autonomous unmanned aerial vehicles (UAVs) rely on timely information sharing. However, the time-varying flight environment and the intermittent link connectivity pose great challenges to message delivery. In this paper, we leverage the deep reinforcement learning (DRL) technique to address the UAVs' optimal links discovery and selection problem in uncertain environments. As the multi-agent learning efficiency is constrained by the high-dimensional and continuous action spaces, we slice the whole action spaces into a number of tractable fractions to achieve efficient convergences of optimal policies in continuous domains. Moreover, for the nonstationarity issue that particularly challenges the multi-agent DRL with local perceptions, we present a multi-agent mutual sampling method that jointly interacts the intra-agent and inter-agent state-action information to stabilize and expedite the training procedure. We evaluate the proposed algorithm on the UAVs' continuous network connection task. Results show that the associated UAVs can quickly select the optimal connected links, which facilitate the UAVs' teamwork significantly.

YNIMG Journal 2018 Journal Article

Preferential susceptibility of limbic cortices to microstructural damage in temporal lobe epilepsy: A quantitative T1 mapping study

• Boris C. Bernhardt
• Fatemeh Fadaie
• Reinder Vos de Wael
• Seok-Jun Hong
• Min Liu
• Marie C. Guiot
• David A. Rudko
• Andrea Bernasconi

The majority of MRI studies in temporal lobe epilepsy (TLE) have utilized morphometry to map widespread cortical alterations. Morphological markers, such as cortical thickness or grey matter density, reflect combinations of biological events largely driven by overall cortical geometry rather than intracortical tissue properties. Because of its sensitivity to intracortical myelin, quantitative measurement of longitudinal relaxation time (qT1) provides and an in vivo proxy for cortical microstructure. Here, we mapped the regional distribution of qT1 in a consecutive cohort of 24 TLE patients and 20 healthy controls. Compared to controls, patients presented with a strictly ipsilateral distribution of qT1 increases in temporopolar, parahippocampal and orbitofrontal cortices. Supervised statistical learning applied to qT1 maps could lateralize the seizure focus in 92% of patients. Intracortical profiling of qT1 along streamlines perpendicular to the cortical mantle revealed marked effects in upper levels that tapered off at the white matter interface. Findings remained robust after correction for cortical thickness and interface blurring, suggesting independence from previously reported morphological anomalies in this disorder. Mapping of qT1 along hippocampal subfield surfaces revealed marked increases in anterior portions of the ipsilateral CA1-3 and DG that were also robust against correction for atrophy. Notably, in operated patients, qualitative histopathological analysis of myelin stains in resected hippocampal specimens confirmed disrupted internal architecture and fiber organization. Both hippocampal and neocortical qT1 anomalies were more severe in patients with early disease onset. Finally, analysis of resting-state connectivity from regions of qT1 increases revealed altered intrinsic functional network embedding in patients, particularly to prefrontal networks. Analysis of qT1 suggests a preferential susceptibility of ipsilateral limbic cortices to microstructural damage, possibly related to disrupted myeloarchitecture. These alterations may reflect atypical neurodevelopment and affect the integrity of fronto-limbic functional networks.

JBHI Journal 2015 Journal Article

Stroke Parameters Identification Algorithm in Handwriting Movements Analysis by Synthesis

• Min Liu
• Xuemei Guo
• Guoli Wang

This paper presents a new approach to identify the stroke parameters in handwriting movement data understanding. A two-step analysis by synthesis paradigm is employed to facilitate the coarse-to-fine parameter identification for all strokes. One is the stroke data extraction, the other is the coarse-to-fine stroke parameter identification. The new consideration of using this two-step paradigm is that the nonnegative primitive factorization technique is incorporated to decouple the overlapped strokes from the measurement data. In comparison to the existing paradigms of using the heuristic stroke data decoupling techniques, our paradigm presented here contributes to alleviating the difficulty of local optimum traps with the well-shaped initializations in the global optimization for jointly identifying stroke parameters. Moreover, our paradigm excludes the iteration between two steps, which contributes to the enhancement of computational efficiency. Experimental results are reported to validate the proposed approach.

YNIMG Journal 2013 Journal Article

The acute phase of Wallerian degeneration: Longitudinal diffusion tensor imaging of the fornix following temporal lobe surgery

• Min Liu
• Donald W. Gross
• B. Matt Wheatley
• Luis Concha
• Christian Beaulieu

Numerous animal studies have shown the applicability of diffusion tensor imaging (DTI) to track Wallerian degeneration that occurs after injury to the neural fiber. Non-invasive biomarkers that may differentiate the early axonal breakdown and later myelin degradation have been attributed to either reduced parallel and elevated perpendicular diffusivity, respectively. While several human DTI studies have shown this potential at subacute and chronic time points, the diffusion changes that occur within the first week are unknown. Anterior temporal lobectomy (i. e. resection of hippocampus) is the standard surgical treatment of medically refractory temporal lobe epilepsy. The concomitant transection of the fimbria-fornix serves as a unique opportunity to examine the process of Wallerian degeneration since the timing is known. Six temporal lobe epilepsy patients underwent brain DTI before the surgery, three to four times within the first week post-operatively, and at one to four months following surgery. Both parallel and perpendicular diffusivities decreased markedly by a similar amount in the ipsilateral fornix within the first two days post-surgery. Approaching the end of the first week, perpendicular (but not parallel) diffusivity pseudo-recovered towards its pre-surgical value, but then increased dramatically months later. Fractional anisotropy, as a result of the combined action of the parallel and perpendicular diffusivities, stayed relatively stable within the first week and only reduced drastically at the chronic stage. DTI demonstrated acute water diffusion changes within days of transection that are not just limited to parallel diffusivity. While the chronic diffusion changes in the fornix are compatible with myelin degradation, the acute changes may reflect beading and swelling of axolemma, granular disintegration of the axonal neurofilaments, ischemia induced cytotoxic edema, and/or changes in the extra-axonal space including inflammatory changes and gliosis.

YNICL Journal 2012 Journal Article

Mesial temporal sclerosis is linked with more widespread white matter changes in temporal lobe epilepsy

• Min Liu
• Luis Concha
• Catherine Lebel
• Christian Beaulieu
• Donald W. Gross

Temporal lobe epilepsy patients with unilateral mesial temporal sclerosis (TLE + uMTS) have been demonstrated to have extensive white matter abnormalities both ipsilateral and contralateral to the seizure onset zone. However, comparatively less is known about the white matter integrity of TLE patients without MTS (non-lesional TLE, nl-TLE). The purpose of the study was to investigate the diffusion properties of thirteen major white matter tracts in patients with TLE + uMTS and nl-TLE. Diffusion tensor imaging (DTI) was performed on 23 TLE + uMTS (15 left MTS and 8 right MTS), 15 nl-TLE and 21 controls. Thirteen tracts were delineated by tractography and their diffusion parameters compared for the two TLE groups relative to controls, with left and right hemispheres combined per tract. A subgroup analysis investigated left and right MTS separately. Compared to controls, reduced anisotropy was detected in ten tracts for TLE + uMTS, but only the parahippocampal cingulum and tapetum for nl-TLE. Right MTS subgroup showed reduced anisotropy in 7 tracts bilaterally (3 limbic, 3 association, 1 projection) and 2 tracts ipsilaterally (1 association, 1 projection) and the body of the corpus callosum whereas the left MTS subgroup showed reduced anisotropy in 4 tracts bilaterally (2 limbic, 1 association, 1 projection) and 2 tracts ipsilaterally (1 limbic, 1 association). Diffusion abnormalities in tracts were observed within and beyond the temporal lobe in TLE + uMTS and were more widespread than in nl-TLE. Patients with right MTS had more extensive, bilateral abnormalities in comparison to left MTS. These findings suggest different dysfunctional networks in TLE patients with and without MTS.

ICRA Conference 2006 Conference Paper

Lagrangian Relaxation for Complex Job Shop Scheduling

• Tao Sun
• Peter B. Luh
• Min Liu

Market competition forces manufactures to schedule their resources efficiently for on-time order delivery and low inventory. However, for companies such as textile and steel-making companies, optimizing schedules is difficult because of the NP-hard nature of the problem and the complex product structures: assemblies, disassemblies and couplings across orders. To address the difficulties, this paper extends the Lagrangian relaxation approach through selectively relaxing precedence constraints. The solution oscillation is identified and alleviated by adding auxiliary penalty and by nonlinear approximation. Furthermore, the normalized surrogate subgradient method is developed to accelerate the convergence of Lagrangian multipliers to obtain good solutions in computational efficient manner. Testing results demonstrate that better schedules are obtained when solution oscillation is alleviated. The newly developed normalized method significantly improves traditional methods