Author name cluster

Pengfei Zhang

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.

24 papers

2 author rows

AAAI Conference 2026 Conference Paper

Adaptive Graph Attention Based Discrete Hashing for Incomplete Cross-modal Retrieval

Shuang Zhang
Yue Wu
Lei Shi
Huilong Jin
Feifei Kou
Pengfei Zhang
Mingying Xu
Pengtao Lv

Cross-modal hashing has emerged as a pivotal solution for efficient retrieval across diverse modalities, such as images and texts, by mapping them into compact binary hash spaces. However, in real-world scenarios, the modalities data is often missing or misaligned. Existing methods are most rely on fully paired training data and ignore missing or misaligned modalities data, resulting in the semantic inconsistencies. To address these challenges, we propose an Adaptive Graph Attention-Based Discrete Hashing (AGADH) method, which consists of three parts. First, to solve the problem of missing modalities, AGADH employs a masked completion strategy to reconstruct missing modalities. Second, to mitigate semantic misalignment, AGADH leverages a Graph Attention Network (GAT) encoder-decoder architecture with alignment module to construct features from different modalities. Additionally, to enhance the fusion performance, an adaptive fusion module dynamically adjusting the contributions of image and text modalities with learnable weighting coefficients is proposed. Extensive experiments on three benchmark datasets, MS-COCO, NUS-WIDE, and MIRFlickr-25K, demonstrating that AGADH outperforms state-of-the-art methods in both fully paired and incompletely paired scenarios, showing its robustness and effectiveness in cross-modal retrieval tasks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Efficient, Secure, Differentially Private Deep Learning in the Two-Server Model

Jun Feng
Hong Sun
Pengfei Zhang
Bocheng Ren
Shunli Zhang

Existing solutions on differentially private deep learning (DPDL) either require the assumption of a trusted data server (centralized DPDL) or suffer from poor utility (local DPDL); and hence their adoptions are hampered in real-world scenarios.We present CRYPTDP, a crypto-assisted differentially private deep learning approach in the two-server model. CRYPTDP employs two non-colluding servers to collaboratively and efficiently train differentially private deep learning over the secret shares of data owners' private data while protecting the confidentiality of the data from untrusted servers. CRYPTDP is the first approach with the best of both local DPDL and centralized DPDL models, which does not resort to trusted server like local DPDL and has the utility like centralized DPDL. In particular, we also make innovations for addressing the major challenges like poor performance and security that beset CRYPTDP: We introduce a new secure computation and differential privacy friendly activation function; we propose a novel garbled-circuits-free most significant bit extraction protocol, and using the protocol we propose an efficient and secure garbled-circuits-free protocol for activation function over secret shares. Exhaustive experiments show that CRYPTDP delivers significantly better performance than the state-of-the-art local DPDL, yields higher accuracy than the state-of-the-art centralized DPDL, and can achieve two orders of magnitude faster runtime than the state-of-the-art approach.

PDF Details DOI

AAAI Conference 2026 Conference Paper

High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers

Wenyu Liu
Tianqiang Huang
Pengfei Zhang
Zong Ke
Minghui Min
Puning Zhao

Adversarial attacks pose a major challenge to distributed learning systems, prompting the development of numerous robust learning methods. However, most existing approaches suffer from the curse of dimensionality, i.e. the error increases with the number of model parameters. In this paper, we make a progress towards high dimensional problems, under arbitrary number of Byzantine attackers. The cornerstone of our design is a direct high dimensional semi-verified mean estimation method. The idea is to identify a subspace with large variance. The components of the mean value perpendicular to this subspace are estimated using corrupted gradient vectors uploaded from worker machines, while the components within this subspace are estimated using auxiliary dataset. As a result, a combination of large corrupted dataset and small clean dataset yields significantly better performance than using them separately. We then apply this method as the aggregator for distributed learning problems. The theoretical analysis shows that compared with existing solutions, our method gets rid of sqrt{d} dependence on the dimensionality, and achieves minimax optimal statistical rates. Numerical results validate our theory as well as the effectiveness of the proposed method.

PDF Details DOI

EAAI Journal 2026 Journal Article

Hypergraph topic neural network with cross-modal fusion for latent treatment pattern recommendation

Xin Min
Wei Li
Weidong Xie
Pengfei Zhang
Chuanbiao Wen
Weiping Ding

Electronic Medical Records (EMR) provide valuable data for intelligent treatment recommendation systems. However, existing methods face challenges in modeling complex high-order relationships and integrating heterogeneous medical features effectively. Traditional topic models struggle with shallow semantic representations. Conversely, hypergraph methods lack interpretability because they insufficiently integrate textual features. This study proposes a Hypergraph Topic neural network with cross-modal fusion for treatment pattern recommendation (HGTCNRec), integrating hypergraph neural networks with topic modeling and cross-modal feature fusion. The framework integrates three key components: hypergraph neural topic modeling for capturing high-order treatment relationships, auxiliary textual feature extraction using Transformer encoders, and cross-modal fusion for heterogeneous feature integration. The hypergraph structure captures complex co-occurrence patterns among treatment behaviors through hyperedge representations. The topic modeling component discovers clinically meaningful patterns while maintaining interpretability. We propose a novel score-level cross-modal architecture that fundamentally differs from existing fusion methods through key architectural innovations. Comprehensive experiments on three real-world datasets demonstrate superior performance compared to baseline methods. Results show significant improvements in recommendation accuracy metrics and topic modeling quality measures. This method has been clinically validated by experts to offer superior interpretability and holds promise for supporting personalized treatment plans. However, its practical clinical value requires further confirmation through in-depth evaluation by clinicians and prospective studies.

Details DOI

AAAI Conference 2026 Conference Paper

MusicRec: Multi-modal Semantic-Enhanced Identifier with Collaborative Signals for Generative Recommendation

Yuqiu Zhao
Lei Shi
Yan Zhong
Feifei Kou
Pengfei Zhang
Jiwei Zhang
Mingying Xu
Yanchao Liu

Generative recommendation as a new paradigm is influencing the current development of recommender systems. It aims to assign identifiers that capture richer semantic and collaborative information to items, and subsequently predict item identifiers via autoregressive generation using Large Language Models (LLMs). Existing approaches primarily tokenize item text into codebooks with preserved semantic IDs through RQ-VAE, or separately tokenize different modality features of items. However, existing tokenization methods face two major challenges: (1) Learning decoupled multi-modal features limits the quality of the semantic representation. (2) Ignoring collaborative signals from interaction history limits the comprehensiveness of identifiers. To address these limitations, we propose a multi-modal semantic-enhanced identifier with collaborative signals for generative recommendation, named MusicRec. In MusicRec, we propose a tokenization approach based on shared-specific modal fusion, enabling the generated identifiers to preserve semantic information more comprehensively from all modalities. In addition, we incorporate collaborative signals from user interactions to guide identifier generation, preserving collaborative patterns in the semantic representation space. Extensive experiments on three public datasets demonstrate that MusicRec achieves state-of-the-art performance compared to existing baseline methods.

PDF Details DOI

AAAI Conference 2026 Conference Paper

PrivSV: Differentially Private Steering Vector for Large Language Models

Haocheng Yang
Xiang Cheng
Chenhao Sun
Pengfei Zhang
Sen Su

Steering Vector (SV) is a powerful technique for controlling Large Language Models (LLMs) by manipulating their activations without altering model weights. However, when constructed from sensitive data, SV poses significant privacy risks, as it may leak private information. Existing differential privacy (DP) techniques for constructing SV cannot be directly applied to training-based SV construction paradigms, which offer higher task performance. In this work, we present **PrivSV**, a general privacy-preserving approach for constructing SV with DP guarantees, compatible with arbitrary SV construction paradigms while maintaining high utility. In PrivSV, we propose three novel methods: a Layer-wise Noise-Resilient Reduction (LNR²) method to reduce the injected noise in high-dimensional SV; a Directional Prior Compensation (DPC) method to recover utility degraded by noise perturbation; and a Privacy-Aware Optimal Parameter Determination (POPD) method to adaptively maximize the performance of the final compensated SV. Extensive experiments on open-source LLMs of different families (i.e., LlaMa, Qwen, Mistral and Gemma) demonstrate that PrivSV outperforms several existing techniques across various privacy budgets.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Stabilizing Cross-Modal Bidirectional Attribution: Few-Shot Adversarial Prompt Tuning for Robust Vision-Language Models

Jun Feng
Shuhong Wu
Hong Sun
Pengfei Zhang
Bocheng Ren
Shunli Zhang

Large-scale pre-trained vision-language models (VLMs) like CLIP show exceptional performance and zero-shot generalization. However, their reliability may be severely undermined by a critical vulnerability to subtle adversarial perturbations. Our work reveals a critical cross-modal vulnerability: visual-only perturbations induce substantial, synchronous shifts in decision attribution maps across both image and text. This phenomenon signifies a fundamental disruption of the VLM's internal logic, as it alters both the model's perceptual focus and its decision rationale. To counter this vulnerability, we introduce Cross-modal Bidirectional Attribution guided Few-shot Adversarial Prompt Tuning (CBA-FAPT), a novel method that leverages the model's internal decision rationale as a regularizer for robust learning. Our framework's core mechanism is the alignment of a novel bidirectional attribution map. This map is a unique fusion of two components. It combines forward feature attention to capture the model's perceptual focus. It also incorporates backward decision gradients to act as a proxy for the model's decision rationale, quantifying how each feature influences the final outcome. We enforce consistency on this bidirectional map between clean and adversarial examples. This approach corrects the model's internal logic on two fronts and effectively restores its adversarial robustness. Comprehensive experiments on 11 datasets demonstrate that CBA-FAPT outperforms the state-of-the-art, establishing a superior trade-off between robust and natural accuracy.

PDF Details DOI

YNIMG Journal 2026 Journal Article

The regulations on topological organization of prefrontal-sensorimotor cortical network elicited by tonifying and reducing manipulations of acupuncture: A graph theory analysis study based on fNIRS

Jingya Cao
Yuzhu Qu
Li Chen
Tianyu Liu
Jing Guo
Zilei Tian
Chongkai Luo
Yulai Gong

This study aims to investigate the similarities and differences in the topological organization of prefrontal-sensorimotor cortical network (PFC-SMC) induced by traditional tonifying and reducing manipulations of acupuncture (TRMs), including the tonifying, reducing, and even tonifying-reducing manipulations. Thirty-five healthy participants underwent all three types of TRMs while functional near-infrared spectroscopy data were recorded. To characterize the network properties, graph-theoretical analysis was applied to calculate topological metrics at both global and nodal levels. Based on these metrics, k-means++ clustering analysis was subsequently performed to assess the representational and discriminative capacity of the derived features across different acupuncture manipulation. The results revealed that all three acupuncture manipulations perserved the typical small-world properties of the PFC-SMC network (p < 0. 05, false discovery rate [FDR] corrected). However, further comparison showed that both the even tonifying-reducing manipulation and the reducing manipulation elicited significantly higher clustering coefficient and network efficiency than the tonifying manipulation (pFDR < 0. 05). At the nodal level, the tonifying manipulation showed lower nodal betweenness centrality and nodal degree centrality than the other two acupuncture manipulations (pFDR < 0. 05). Notably, these topological properties enabled reliable differentiation among the three TRMs, as confirmed by the clustering analysis. These findings highlight that different acupuncture manipulations exert distinct modulatory effects on the brain functional network, providing visualized evidence for facilitating the understanding and clinical application of TRMs.

Details DOI

NeurIPS Conference 2025 Conference Paper

Dynamic Masking and Auxiliary Hash Learning for Enhanced Cross-Modal Retrieval

Shuang Zhang
Yue Wu
Lei Shi
Yingxue Zhang
Feifei Kou
Huilong Jin
Pengfei Zhang
Meiyu Liang

The demand for multimodal data processing drives the development of information technology. Cross-modal hash retrieval has attracted much attention because it can overcome modal differences and achieve efficient retrieval, and has shown great application potential in many practical scenarios. Existing cross-modal hashing methods have difficulties in fully capturing the semantic information of different modal data, which leads to a significant semantic gap between modalities. Moreover, these methods often ignore the importance differences of channels, and due to the limitation of a single goal, the matching effect between hash codes is also affected to a certain extent, thus facing many challenges. To address these issues, we propose a Dynamic Masking and Auxiliary Hash Learning (AHLR) method for enhanced cross-modal retrieval. By jointly leveraging the dynamic masking and auxiliary hash learning mechanisms, our approach effectively resolves the problems of channel information imbalance and insufficient key information capture, thereby significantly improving the retrieval accuracy. Specifically, we introduce a dynamic masking mechanism that automatically screens and weights the key information in images and texts during the training process, enhancing the accuracy of feature matching. We further construct an auxiliary hash layer to adaptively balance the weights of features across each channel, compensating for the deficiencies of traditional methods in key information capture and channel processing. In addition, we design a contrastive loss function to optimize the generation of hash codes and enhance their discriminative power, further improving the performance of cross-modal retrieval. Comprehensive experimental results on NUS-WIDE, MIRFlickr-25K and MS-COCO benchmark datasets show that the proposed AHLR algorithm outperforms several existing algorithms.

PDF Details

IJCAI Conference 2025 Conference Paper

EVICheck: Evidence-Driven Independent Reasoning and Combined Verification Method for Fact-Checking

Lingxiao Wang
Lei Shi
Feifei Kou
Ligu Zhu
Chen Ma
Pengfei Zhang
Mingying Xu
Zeyu Li

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) have demonstrated significant potential in automated fact-checking. However, existing methods face limitations in insufficient evidence utilization and lack of explicit verification criteria. Specifically, these approaches aggregate evidence for collective reasoning without independently analyzing each piece, hindering their ability to leverage the available information thoroughly. Additionally, they rely on simple prompts or few-shot learning for verification, which makes truthfulness judgments less reliable, especially for complex claims. To address these limitations, we propose a novel method to enhance evidence utilization and introduce explicit verification criteria, named EVICheck. Our approach independently reasons each evidence piece and synthesizes the results to enable more thorough exploration and enhance interpretability. Additionally, by incorporating fine-grained truthfulness criteria, we make the model's verification process more structured and reliable, especially when handling complex claims. Experimental results on the public RAWFC dataset demonstrate that EVICheck achieves state-of-the-art performance across all evaluation metrics. Our method demonstrates strong potential in fake news verification, significantly improving the accuracy.

PDF Details DOI

EAAI Journal 2025 Journal Article

Interactive streaming feature selection based on neighborhood rough sets

Gangqiang Zhang
Jingjing Hu
Jing Yang
Pengfei Zhang

Feature streams refer to features that arrive continuously over time without changing the number of samples. Such data is commonly encountered in various practical application scenarios. Stream feature selection is a technique designed to select relevant features from high-dimensional stream data, thereby reducing its overall size. Feature interaction plays a crucial role in influencing the results of feature selection. Most existing methods address stream feature selection primarily by focusing on irrelevance and redundancy, often overlooking the important interactions between features. Additionally, these methods typically assume that all samples and features are known, which contradicts the fundamental nature of streaming data. This study introduces an interactive feature selection approach for stream feature selection, utilizing the neighborhood rough set. First, we provide a basic explanation of multi-neighbor entropy, which measures the amount of information related to neighborhood classes. It is used to measure how the amount of information about neighborhood classes. Next, we propose a feature evaluation method based on correlation, redundancy, and interaction analysis. Finally, we elaborate on functions for feature evaluation criteria, aiming to design streaming feature selection algorithms that integrate correlation, redundancy, and interactivity. The proposed algorithm is compared with six other representative feature selection algorithms across 14 public datasets. Experimental results demonstrate the validity of our proposed solution.

Details DOI

IROS Conference 2025 Conference Paper

Jumping Mechanism Assists Takeoff for Large-Sized Flapping-Wing Robots

Zeyu Zhang
Xinde Li
Zhentong Zhang
Chengxiang Yu
Pengfei Zhang

Flapping-wing robots exhibit numerous advantages in flight performance, which mimic the natural flight of birds or insects. However, autonomous takeoff remains a significant challenge for large-sized bird-like flapping-wing robots. To address this challenge, we design a jumping mechanism based on a bow-like carbon fiber spring. This mechanism is capable of repeated self-compression and release and can be readily integrated into flapping-wing robots to assist their jumping takeoff. Then we conduct a mechanical analysis of the motion states during the jumping takeoff process. Additionally, we propose a jump-flapping coupling control method based on sensor data to ensure a seamless transition and smooth coordination between the jumping and flapping action, thus enabling a smooth takeoff. Experimental results validate the effectiveness of the proposed jumping mechanism and its collaborative control strategy. This study provides support for advancing flapping-wing robots toward autonomous multi-modal locomotion and further deepens research in this field.

Details

NeurIPS Conference 2025 Conference Paper

Multimodal 3D Genome Pre-training

Minghao Yang
Pengteng Li
Yan Liang
Qianyi Cai
Zhihang Zheng
Shichen Zhang
Pengfei Zhang
Zhi-An Huang

Deep learning techniques have driven significant progress in various analytical tasks within 3D genomics in computational biology. However, a holistic understanding of 3D genomics knowledge remains underexplored. Here, we propose MIX-HIC, the first multimodal foundation model of 3D genome that integrates both 3D genome structure and epigenomic tracks, which obtains unified and comprehensive semantics. For accurate heterogeneous semantic fusion, we design the cross-modal interaction and mapping blocks for robust unified representation, yielding the accurate aggregation of 3D genome knowledge. Besides, we introduce the first large-scale dataset comprising over 1 million pairwise samples of Hi-C contact maps and epigenomic tracks for high-quality pre-training, enabling the exploration of functional implications in 3D genomics. Extensive experiments show that MIX-HIC significantly surpasses existing state-of-the-art methods in diverse downstream tasks. This work provides a valuable resource for advancing 3D genomics research.

PDF Details

TIST Journal 2024 Journal Article

DNSRF: Deep Network-based Semi-NMF Representation Framework

Dexian Wang
Tianrui Li
Ping Deng
Zhipeng Luo
Pengfei Zhang
Keyu Liu
Wei Huang

Representation learning is an important topic in machine learning, pattern recognition, and data mining research. Among many representation learning approaches, semi-nonnegative matrix factorization (SNMF) is a frequently-used one. However, a typical problem of SNMF is that usually there is no learning rate guidance during the optimization process, which often leads to a poor representation ability. To overcome this limitation, we propose a very general representation learning framework (DNSRF) that is based on a deep neural net. Essentially, the parameters of the deep net used to construct the DNSRF algorithms are obtained by matrix element update. In combination with different activation functions, DNSRF can be implemented in various ways. In our experiments, we tested nine instances of our DNSRF framework on six benchmark datasets. In comparison with other state-of-the-art methods, the results demonstrate the superior performance of our framework, which is thus shown to have a great representation ability.

Details DOI

ICML Conference 2024 Conference Paper

Enabling Few-Shot Learning with PID Control: A Layer Adaptive Optimizer

Le Yu
Xinde Li
Pengfei Zhang
Zhentong Zhang
Fir Dunkin

Model-Agnostic Meta-Learning (MAML) and its variants have shown remarkable performance in scenarios characterized by a scarcity of labeled data during the training phase of machine learning models. Despite these successes, MAMLbased approaches encounter significant challenges when there is a substantial discrepancy in the distribution of training and testing tasks, resulting in inefficient learning and limited generalization across domains. Inspired by classical proportional-integral-derivative (PID) control theory, this study introduces a Layer-Adaptive PID (LA-PID) Optimizer, a MAML-based optimizer that employs efficient parameter optimization methods to dynamically adjust task-specific PID control gains at each layer of the network, conducting a first-principles analysis of optimal convergence conditions. A series of experiments conducted on four standard benchmark datasets demonstrate the efficacy of the LA-PID optimizer, indicating that LA-PID achieves state-oftheart performance in few-shot classification and cross-domain tasks, accomplishing these objectives with fewer training steps. Code is available on https: //github. com/yuguopin/LA-PID.

Details

IROS Conference 2024 Conference Paper

EVSMap: An Efficient Volumetric-Semantic Mapping Approach for Embedded Systems

Jiyuan Qiu
Chen Jiang
Pengfei Zhang
Haowen Wang

Despite significant progress in perception tasks such as 3D scene mapping and semantic information extraction using SLAM and deep learning, applying these techniques within computationally constrained embedded systems remains a challenge. In this work, we introduce a novel end-to-end framework for efficient and real-time volumetric-semantic mapping. We have developed a lightweight and robust RGB-D segmentation network for extracting semantic information. Through the introduction of three distinct modules—CFIM, DAPPF, and LAD—our network significantly enhances real-time performance while achieving Mean Intersection over Union (MIoU) scores comparable to state-of-the-art (SOTA) models. Our model reduces the parameters by 8 to 26 times compared to similar networks and improves inference speed by 2 to 3 times. Additionally, we improved a multi-class bayesian updating strategy by refining penalty function to reduce the memory size of the semantic map and enhance the mapping speed. Compared with other volumetric-semantic mapping approaches, our work maintains the same level of detail in semantic information representation, while increasing mapping speed by 1. 3 to 9. 6 times and reducing memory size of the map by up to 2. 6 times. Finally, we applied our work to real-world mobile robot exploration scenarios, demonstrating the efficiency of the proposed framework.

Details

EAAI Journal 2024 Journal Article

Unsupervised video forecasting with flow parsing mechanism of human visual system

Beibei Jin
Xiaohui Song
Jindong Li
Pengfei Zhang

Video forecasting aims to predict future video frames based on past observed video frames, and unlike object recognition or object classification, it does not require manual labeling of the data set. The explosive growth of Internet video data provides a huge space for its development. At present, it has become a research hotspot in the field of computer vision, and has broad application prospects in the field of automatic driving or robot navigation. However, due to the high dimensional characteristics and the complex spatial–temporal logic of video data, current methods still face the challenges of blurry and inconsistent prediction. The cognitive ability of “flow parsing mechanism” helps humans adapt to new situations systematically. Inspired by this, a deep flow parsing network for future video forecasting is proposed in this paper, which is designed to predict future scenes by parsing optical flow into rigid flow and residual flow. The rigid flow represents the scene dynamics due to observer’s ego-motion, while the residual flow corresponds to the movement of the other objects in the scene. With this procedure, the model exhibits much more comprehensive understanding over the environment and achieves top performance on competitive driving datasets, demonstrating its effectiveness and generalizability.

Details DOI

JBHI Journal 2023 Journal Article

Interactive Skin Wound Segmentation Based on Feature Augment Networks

Pengfei Zhang
Xinjian Chen
Ziting Yin
Xin Zhou
Qingxin Jiang
Weifang Zhu
Dehui Xiang
Yun Tang

Skin wound segmentation in photographs allows non-invasive analysis of wounds that supports dermatological diagnosis and treatment. In this paper, we propose a novel feature augment network (FANet) to achieve automatic segmentation of skin wounds, and design an interactive feature augment network (IFANet) to provide interactive adjustment on the automatic segmentation results. The FANet contains the edge feature augment (EFA) module and the spatial relationship feature augment (SFA) module, which can make full use of the notable edge information and the spatial relationship information be-tween the wound and the skin. The IFANet, with FANet as the backbone, takes the user interactions and the initial result as inputs, and outputs the refined segmentation result. The pro-posed networks were tested on a dataset composed of miscellaneous skin wound images, and a public foot ulcer segmentation challenge dataset. The results indicate that the FANet gives good segmentation results while the IFANet can effectively improve them based on simple marking. Comprehensive comparative experiments show that our proposed networks outperform some other existing automatic or interactive segmentation methods, respectively.

Details DOI

YNICL Journal 2022 Journal Article

Rich-club reorganization and related network disruptions are associated with the symptoms and severity in classic trigeminal neuralgia patients

Pengfei Zhang
Xinyue Wan
Kai Ai
Weihao Zheng
Guangyao Liu
Jun Wang
Wenjing Huang
Fengxian Fan

BACKGROUND: Alterations in white matter microstructure and functional activity have been demonstrated to be involved in the central nervous system mechanism of classic trigeminal neuralgia (CTN). However, the rich-club organization and related topological alterations in the CTN brain networks remain unclear. METHODS: We simultaneously collected diffusion-tensor imaging (DTI) and resting state functional magnetic resonance imaging (rs-fMRI) data from 29 patients with CTN (9 males, mean age = 54.59 years) and 34 matched healthy controls (HCs) (12 males, mean age = 54.97 years) to construct structural networks (SNs) and functional networks (FNs). Rich-club organization was determined separately based on each group's SN and different kinds of connections. For both network types, we calculated the basic connectivity properties (network density and strength) and topological properties (global/local/nodal efficiency and small worldness). Moreover, SN-FN coupling was obtained. The relationships between all those properties and clinical measures were evaluated. RESULTS: Compared to their FN, the SN of CTN patients was disrupted more severely, including its topological properties (reduced network efficiency and small-worldness), and a decrease in network density and strength was observed. Patients showed reorganization of the rich-club architecture, wherein the nodes with decreased nodal efficiency in the SN were mainly non-hub regions, and the local connections were closely related to altered global efficiency and whole brain coupling. While the cortical-subcortical connections of feeder were found to be strengthened in the SN of patients, the coupling between networks increased in all types of connections. Finally, disease severity (duration, pain intensity, and affective alterations) was negatively correlated with coupling (rich-club, feeder, and whole brain) and network strength (the rich-club of the SN and local connections of the FN). A positive correlation was only found between pain intensity and the coupling of local connections. CONCLUSIONS: The SN of patients with CTN may be more vulnerable. Accompanied by the reorganization of the rich-club, the less efficient network communication and the impaired functional dynamics were largely attributable to the dysfunction of non-hub regions. As compensation, the pain transmission pathway of feeder connections involving in pain processing and emotional regulation may strengthen. The local and feeder sub-networks may serve as potential biomarkers for diagnosis or prognosis.

Details DOI

EAAI Journal 2020 Journal Article

A novel three-way decision method in a hybrid information system with images and its application in medical diagnosis

Zhaowen Li
Pengfei Zhang
Ningxin Xie
Gangqiang Zhang
Ching-Feng Wen

Three-way decisions are effective and heuristic methods in information processing, moreover, it provides a trisecting-and-acting framework for complex problem solving. In this paper, combining with the practical application scenario, we propose a novel three-way decisions approach and apply it to medical diagnosis. First, we build an information system which is called a hybrid information system with images by considering the characteristics of the examination items of nephritis, including urinary color, urinary tuberculosis, pH, red blood cell count, urinary irritation, computed tomography, white blood cell count and so on. Second, to describe two objects of the conditional attribute set in a hybrid information system with images, we propose the hybrid distance based on Euclidean distance. Then, the tolerance relation induced by this system is constructed. In addition, considering that missing values exist in a hybrid information system with images, interval-valued numbers are used to obtain the loss function. Given different types of parameters can respond the level of the tolerance relation and the risk preference of decision makers, and the decision rules are shown in tabular forms. Finally, an illustration is showed to verify the feasibility and reasonability of the proposed method.

Details DOI

AAAI Conference 2020 Conference Paper

High Performance Depthwise and Pointwise Convolutions on Mobile Devices

Pengfei Zhang
Eric Lo
Baotong Lu

Lightweight convolutional neural networks (e. g. , MobileNets) are speciﬁcally designed to carry out inference directly on mobile devices. Among the various lightweight models, depthwise convolution (DWConv) and pointwise convolution (PWConv) are their key operations. In this paper, we observe that the existing implementations of DW- Conv and PWConv are not well utilizing the ARM processors in the mobile devices, and exhibit lots of cache misses under multi-core and poor data reuse at register level. We propose techniques to re-optimize the implementations of DWConv and PWConv based on ARM architecture. Experimental results show that our implementation can respectively achieve a speedup of up to 5. 5× and 2. 1× against TVM (Chen et al. 2018) on DWConv and PWConv.

PDF Details

IJCAI Conference 2017 Conference Paper

A Trust-based Mixture of Gaussian Processes Model for Reliable Regression in Participatory Sensing

Qikun Xiang
Jie Zhang
Ido Nevat
Pengfei Zhang

Data trustworthiness is a crucial issue in real-world participatory sensing applications. Without considering this issue, different types of worker misbehavior, especially the challenging collusion attacks, can result in biased and inaccurate estimation and decision making. We propose a novel trust-based mixture of Gaussian processes (GP) model for spatial regression to jointly detect such misbehavior and accurately estimate the spatial field. We develop a Markov chain Monte Carlo (MCMC)-based algorithm to efficiently perform Bayesian inference of the model. Experiments using two real-world datasets show the superior robustness of our model compared with existing approaches.

PDF Details

AAMAS Conference 2017 Conference Paper

A Trust-based Mixture of Gaussian Processes Model for Robust Participatory Sensing

Qikun Xiang
Jie Zhang
Ido Nevat
Pengfei Zhang

Data trustworthiness is a crucial issue in real-world participatory sensing applications. Without considering this issue, different types of worker misbehavior, especially the challenging collusion attacks, can result in biased and inaccurate estimation and decision making. In this paper, we propose a novel trust-based mixture of Gaussian processes (GP) model for spatial regression to jointly detect such misbehavior and accurately estimate the spatial field. We develop a Markov chain Monte Carlo (MCMC)-based algorithm to efficiently perform Bayesian inference of the model. Experiments using real-world dataset show the superior robustness of our model compared with existing approaches.

PDF

ICRA Conference 2009 Conference Paper

Voice coil based hopping mechanism for microrobot

Pengfei Zhang
Quan Zhou

Hopping is a very efficient locomotion method for a robot in an unconstructed environment or a complicated terrain. Small hopping robots have many interesting properties in comparison to the larger ones. However, relatively little research has been reported on hopping microrobot, while most of existing designs of hopping robots are not suitable to scale down. In this paper we propose a novel hopping mechanism that is based on the working principle of voice coil actuator. This mechanism is relatively easy to miniaturize and the hopping performance improves in a smaller scale. Two prototypes are developed based on electromagnetic simulation and an analytic model of hopping process. The first prototype has a dimension of Φ30 mm × 10 mm and a mass of 41. 59 g, with a hopping height of about 45 mm. The second one has a dimension of Φ14 mm × 6 mm and a mass of 4. 94 g, and achieves a hopping height of about 65 mm.

Details