Author name cluster

Ping 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.

33 papers

2 author rows

AAAI Conference 2026 Conference Paper

Achieving Fairness Without Harm via Selective Demographic Experts

Xuwei Tan
Yuanlong Wang
Thai-Hoang Pham
Ping Zhang
Xueru Zhang

As machine learning systems become increasingly integrated into human-centered domains such as healthcare, ensuring fairness while maintaining high predictive performance is critical. Existing bias mitigation techniques often impose a trade-off between fairness and accuracy, inadvertently degrading performance for certain demographic groups. In high-stakes domains like clinical diagnosis, such trade-offs are ethically and practically unacceptable. In this study, we propose a fairness-without-harm approach by learning distinct representations for different demographic groups and selectively applying demographic experts consisting of group-specific representations and personalized classifiers through a no-harm constrained selection. We evaluate our approach on three real-world medical datasets—covering eye disease, skin cancer, and X-ray diagnosis—as well as two face datasets. Extensive empirical results demonstrate the effectiveness of our approach in achieving fairness without harm.

PDF Details DOI

TIST Journal 2026 Journal Article

Federated Inverse Probability Treatment Weighting for Individual Treatment Effect Estimation

Changchang Yin
Hong-You Chen
Wei-Lun Chao
Ping Zhang

Individual Treatment Effect (ITE) estimation is to evaluate the causal effects of treatment strategies on some important outcomes, which is a crucial problem in healthcare. Most existing ITE estimation methods are designed for centralized settings. However, in real-world clinical scenarios, the raw data are usually not shareable among hospitals due to the potential privacy and security risks, which makes the methods not applicable. In this work, we study the ITE estimation task in a federated setting, which allows us to harness the decentralized data from multiple hospitals. Due to the unavoidable confounding bias in the collected data, a model directly learned from it would be inaccurate. One well-known solution is Inverse Probability Treatment Weighting (IPTW), which uses the conditional probability of treatment given the covariates to re-weight each training example. Applying IPTW in a federated setting, however, is non-trivial. We found that even with a well-estimated conditional probability, the local model training step using each hospital’s data alone would still suffer from confounding bias. To address this, we propose F ED -IPTW, a novel algorithm to extend IPTW into a federated setting that enforces both global (over all the data) and local (within each hospital) decorrelation between covariates and treatments. We validated our approach on the task of comparing the treatment effects of mechanical ventilation on improving survival probability for patients with breadth difficulties in the Intensive Care Unit (ICU). We conducted experiments on both synthetic and real-world eICU datasets, and the results show that F ED -IPTW outperforms state-of-the-art methods on all the metrics on factual prediction and ITE estimation tasks, paving the way for personalized treatment strategy design in mechanical ventilation usage.

Details DOI

EAAI Journal 2025 Journal Article

Automotive fuse & relay box plug-in modules assembly correctness detection system based on machine vision

ZhengWei Gong
Jun Song
Ping Zhang

The automotive fuse and relay box is vital for electrical safety and reliability, demanding stringent quality control before leaving the factory. However, existing methods face limitations such as light interference, inability to detect non-fuse plug-in modules, lack of worker-friendly interfaces, insufficient data recording features, and a lack of comparative diagnostic capabilities for detection results. To address these issues, an artificial intelligence (AI)-powered automotive fuse and relay box assembly correctness detection system based on machine vision is proposed. This system incorporates a closed image acquisition setup, advanced machine vision techniques, and My Structured Query Language (MySQL) database operations for efficient data management. A comprehensive detection rule-setting subsystem, developed with Python Qt 5 (PyQt5) graphical user interface (GUI), integrates classification detection, similarity detection, color detection, and text recognition, allowing users to easily create detection rules. Additionally, a PyQt5-based template selection subsystem further streamlines template identification for various scenarios. The detection system combines these four methods with an object detection method for real-time, accurate assembly verification. The core You Only Look Once version 11 extra-large (YOLOx) model provides fast and precise localization, while supplementary modules—Residual Neural Network with 18 layers for classification detection, Siamese network-based similarity detection, binary character recognition, and color detection—work synergistically to enhance detection robustness and accuracy. The system achieves an average detection time of 0. 141 s per module for correct assemblies and 1. 398 s for faulty assemblies. Demonstrating 99. 9 % accuracy, high adaptability, and efficient detection, the system is highly suitable for large-scale, real-world production environments.

Details DOI

EAAI Journal 2025 Journal Article

Exploring multi-label feature selection via feature and label information supplementation

Suqi Zhang
Yonghao Li
Ping Zhang
Wanfu Gao

Multi-label feature selection has garnered significant attention for its ability to identify informative features while capturing complex dependencies between labels and features. Therefore, it is essential for dealing with the high dimensionality of multi-label problems. Traditional information-theoretic-based feature selection methods ignore the dynamic nature of the relationship between label relationships and selected features with the labels while assessing candidate features. To address these limitations, we propose a novel method called Feature and Label Information Supplementation (FLIS), which integrates label information supplementation and the mechanisms of selected features with labels. In the FLIS method, we consider dynamic changes in selected features based on conditional mutual information and the mutual information among selected features, candidate features, and labels. Additionally, we distinguish label relationships that provide label information supplementation. Therefore, FLIS can dynamically evaluate the impact of different features on the label relationships. Experimental results on multiple benchmark datasets demonstrate that FLIS captures supplementary information from dynamic relationships between features and labels and significantly improves classification accuracy compared to traditional multi-label feature selection methods.

Details DOI

JBHI Journal 2025 Journal Article

FedPC: An Efficient Prototype-Based Clustered Federated Learning on Medical Imaging

Tianrun Gao
Keyan Liu
Yuning Yang
Xiaohong Liu
Ping Zhang
Guangyu Wang

Federated learning (FL) has emerged as a promising distributed paradigm that enables collaborative model training while preserving data privacy, but it suffers from performance degradation due to data heterogeneity. Although clustered federated learning (CFL) attempts to address this challenge by grouping clients with similar data distributions, existing methods are inefficient in capturing client data representations, leading to incorrect cluster identities and inferior cluster performance. To overcome these limitations, we propose an efficient prototype-based CFL framework (FedPC). Specifically, we introduce a dual-prototype strategy combining specific prototypes and generalized prototypes to capture class representations for cluster identities, along with a prototype-contrastive training mechanism that maximizes intra-cluster prototype consistency to improve cluster performance. Extensive experiments on medical imaging datasets (BloodMNIST and DermaMNIST) demonstrate that the FedPC outperforms nine state-of-the-art (SOTA) approaches, achieving average improvements of 2. 17% and 3. 47%, respectively. Furthermore, the FedPC reduces communication overhead by 3. 33 to 5. 68 times compared to SOTA methods, showcasing its efficiency in real-world FL scenarios.

Details DOI

AAAI Conference 2025 Conference Paper

GMAP: Generalized Manipulation of Articulated Objects in Robotic Using Pre-trained Model

Hongliang Zeng
Ping Zhang
Fang Li
QinPeng Yi
Tingyu Ye
Jiahua Wang

Perception and interaction with articulated objects present a unique challenge for service robots. Although recent research has emphasized understanding articulated shapes and affordance proposals, existing methods only address isolated aspects, failing to develop comprehensive strategies for robotic perception and manipulation of articulated objects. To bridge this gap, we propose GMAP, which systematically integrates the entire process from command to perception and manipulation. Specifically, we first perform precise part-level segmentation of the object and identify the geometric and kinematic parameters of articulated joints. Then, by evaluating point-level affordance proposals, we determine the interaction poses for the robot's end-effector. Finally, the robot's execution trajectory is dynamically computed by combining commands with joint parameters and interaction points. Additionally, a key innovation of GMAP is addressing the scarcity of annotated data. We designed a multi-scale point cloud feature extraction module and introduced pre-training and fine-tuning techniques, significantly enhancing the generalization capability of the perception model. Extensive experiments demonstrate that GMAP achieves state-of-the-art (SOTA) performance in both the perception and manipulation of articulated objects and adapts to real-world scenarios.

PDF Details DOI

JBHI Journal 2025 Journal Article

MHFNet: A Multimodal Hybrid-Embedding Fusion Network for Automatic Sleep Staging

Ruhan Liu
Jiajia Li
Yang Wen
Xian Huang
Bin Sheng
David Dagan Feng
Ping Zhang

Scoring sleep stages is essential for evaluating the status of sleep continuity and comprehending its structure. Despite previous attempts, automating sleep scoring remains challenging. First, most existing works did not fuse local and global temporal information. Second, the correlation for special waves in different signals is rarely used in sleep staging modeling. Third, the logic of scoring rules based on adjacent epochs is not considered in developing sleep staging models. This paper introduces a multimodal hybrid-embedding fusion network (MHFNet), which aims to tackle these challenges in automating sleep stage scoring. MHFNet comprises multi-stream Xception blocks to extract wave characteristics, a hybrid time-embedding module to combine local and global temporal information, a dual-path gate transformer to fuse and enhance attention features, and a refined output header to reconstruct sleep scoring. We perform experiments using three publicly available datasets (SleepEDF-ST, SleepEDF-SC, and SHHS). Experimental results indicate the superiority of MHFNet over baseline approaches in cross-validation. Moreover, at the individual level, MHFNet yielded an average $R^{2}$ score improvement of 9 $\%$ in the testing dataset compared to state-of-the-art models, paving the way for its applications in real-world sleep medicine.

Details DOI

AAAI Conference 2025 Conference Paper

Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm

Thai-Hoang Pham
Yuanlong Wang
Changchang Yin
Xueru Zhang
Ping Zhang

Domain adaptation (DA) tackles the issue of distribution shift by learning a model from a source domain that generalizes to a target domain. However, most existing DA methods are designed for scenarios where the source and target domain data lie within the same feature space, which limits their applicability in real-world situations. Recently, heterogeneous DA (HeDA) methods have been introduced to address the challenges posed by heterogeneous feature space between source and target domains. Despite their successes, current HeDA techniques fall short when there is a mismatch in both feature and label spaces. To address this, this paper explores a new DA scenario called open-set HeDA (OSHeDA). In OSHeDA, the model must not only handle heterogeneity in feature space but also identify samples belonging to novel classes. To tackle this challenge, we first develop a novel theoretical framework that constructs learning bounds for prediction error on target domain. Guided by this framework, we propose a new DA method called Representation Learning for OSHeDA (RL-OSHeDA). This method is designed to simultaneously transfer knowledge between heterogeneous data sources and identify novel classes. Experiments across text, image, and clinical data demonstrate the effectiveness of our algorithm.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Revisiting Semi-Supervised Learning in the Era of Foundation Models

Ping Zhang
Zheda Mai
Quang-Huy (Percy) Nguyen
Wei-Lun (Harry) Chao

Semi-supervised learning (SSL) enhances model performance by leveraging abundant unlabeled data alongside limited labeled data. As vision foundation models (VFMs) become central to modern vision applications, this paper revisits SSL in the context of these powerful pre-trained models. We conduct a systematic study on tasks where frozen VFMs underperform and reveal several key insights when fine-tuning them. First, parameter-efficient fine-tuning (PEFT) using only labeled data often surpasses traditional SSL methods---even without access to unlabeled data. Second, pseudo-labels generated by PEFT models offer valuable supervisory signals for unlabeled data, and different PEFT techniques yield complementary pseudo-labels. These findings motivate a simple yet effective SSL baseline for the VFM era: \emph{ensemble pseudo-labeling across diverse PEFT methods and VFM backbones}. Extensive experiments validate the effectiveness of this approach, offering actionable insights into SSL with VFMs and paving the way for more scalable and robust semi-supervised learning in the foundation model era.

PDF Details

TIST Journal 2025 Journal Article

SubgroupTE: Advancing Treatment Effect Estimation with Subgroup Identification

Seungyeon Lee
Ruoqi Liu
Wenyu Song
Lang Li
Ping Zhang

Precise estimation of treatment effects is crucial for accurately evaluating the intervention. While deep learning models have exhibited promising performance in learning counterfactual representations for treatment effect estimation (TEE), a major limitation in most of these models is that they often overlook the diversity of treatment effects across potential subgroups that have varying treatment effects and characteristics, treating the entire population as a homogeneous group. This limitation restricts the ability to precisely estimate treatment effects and provide targeted treatment recommendations. In this paper, we propose a novel treatment effect estimation model, named SubgroupTE, which incorporates subgroup identification in TEE. SubgroupTE identifies heterogeneous subgroups with different responses and more precisely estimates treatment effects by considering subgroup-specific treatment effects in the estimation process. In addition, we introduce an expectation–maximization (EM)-based training process that iteratively optimizes estimation and subgrouping networks to improve both estimation and subgroup identification. Comprehensive experiments on the synthetic and semi-synthetic datasets demonstrate the outstanding performance of SubgroupTE compared to the existing works for treatment effect estimation and subgrouping models. Additionally, a real-world study demonstrates the capabilities of SubgroupTE in enhancing targeted treatment recommendations for patients with opioid use disorder (OUD) by incorporating subgroup identification with treatment effect estimation.

Details DOI

NeurIPS Conference 2025 Conference Paper

The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective

Thai-Hoang Pham
Jiayuan Chen
Seungyeon Lee
Yuanlong Wang
Sayoko Moroi
Xueru Zhang
Ping Zhang

As machine learning (ML) algorithms are increasingly used in medical image analysis, concerns have emerged about their potential biases against certain social groups. Although many approaches have been proposed to ensure the fairness of ML models, most existing works focus only on medical image diagnosis tasks, such as image classification and segmentation, and overlooked prognosis scenarios, which involve predicting the likely outcome or progression of a medical condition over time. To address this gap, we introduce FairTTE, the first comprehensive framework for assessing fairness in time-to-event (TTE) prediction in medical imaging. FairTTE encompasses a diverse range of imaging modalities and TTE outcomes, integrating cutting-edge TTE prediction and fairness algorithms to enable systematic and fine-grained analysis of fairness in medical image prognosis. Leveraging causal analysis techniques, FairTTE uncovers and quantifies distinct sources of bias embedded within medical imaging datasets. Our large-scale evaluation reveals that bias is pervasive across different imaging modalities and that current fairness methods offer limited mitigation. We further demonstrate a strong association between underlying bias sources and model disparities, emphasizing the need for holistic approaches that target all forms of bias. Notably, we find that fairness becomes increasingly difficult to maintain under distribution shifts, underscoring the limitations of existing solutions and the pressing need for more robust, equitable prognostic models.

PDF Details

ECAI Conference 2025 Conference Paper

Training Robotic Self-Evolving with GRPO

Qinpeng Yi
Ping Zhang
Junwei Chen

Current embodied robots heavily depend on pre-trained models, whose capabilities are inherently constrained by the data they were originally trained on. However, truly intelligent robots are expected to improve themselves autonomously when encountering novel environments where these pre-trained models fall short. This is the capability we define as self-evolving ability. In this paper, we investigate the self-evolving capacity of robotic vision models. Specifically, we simulate this process using the R3ED dataset and propose a training framework in which a policy learns to navigate through unfamiliar environments to collect informative data that can be used to refine the vision model. Our training pipeline is built upon the GRPO algorithm and incorporates historical states into the policy design to enhance contextual awareness. Furthermore, we introduce a novel reward mechanism based on supervision discrepancy to guide effective data collection. Experimental results validate the effectiveness of our proposed reinforcement training strategy. Our work highlights the potential of designing intelligent robots that can improve themselves without the intervene of human beings. Nevertheless, we acknowledge that robotic self-evolving remains a nascent and underexplored area, with significant room for further future research and the discovery of more optimal approaches.

Details

JBHI Journal 2024 Journal Article

Dense Contrastive-Based Federated Learning for Dense Prediction Tasks on Medical Images

Yuning Yang
Xiaohong Liu
Tianrun Gao
Xiaodong Xu
Ping Zhang
Guangyu Wang

Deep learning (DL) models have achieved remarkable success in various domains. But training an accurate DL model requires large amounts of data, which can be challenging to obtain in medical settings due to privacy concerns. Recently, federated learning (FL) has emerged as a promising solution that shares local models instead of raw data. However, FL in medical settings faces challenges of client drift due to the data heterogeneity across dispersed institutions. Although there exist studies to address this challenge, they mainly focus on the classification tasks that learn global representation of an entire image. Few have been studied on the dense prediction tasks, such as object detection. In this study, we propose dense contrastive-based federated learning (DCFL) tailored for dense prediction tasks in FL settings. DCFL introduces dense contrastive learning to FL, which aligns the local optimization objectives towards the global objective by maximizing the agreement of representations between the global and local models. Moreover, to improve the performance of dense target prediction at each level, DCFL applies multi-scale contrastive representation by utilizing multi-scale representations with dense features in contrastive learning. We evaluated DCFL on a set of realistic datasets for pulmonary nodule detection. DCFL demonstrates an overall performance improvement compared with the other federated learning methods in heterogeneous settings–improving the mean average precision by 4. 13% and testing recall by 6. 07% in highly heterogeneous settings.

Details DOI

EAAI Journal 2024 Journal Article

Detection and utilization of new-type encrypted network traffic in distributed scenarios

Ping Zhang
Feng Chen
Hongyuan Yue

Encrypted Network Traffic Classification (ENTC) is a crucial task in network management. The existing ENTC schemes usually imply two hypotheses. First, adopting a centralized processing mode. Second, the number of network traffic categories is fixed. However, it is usually unreasonable to collect all network traffic to the centralized node for processing which may cause network congestion. In addition, new traffic types emerge in endlessly, and the existing models cannot classify them. This paper studies the ENTC problem in distributed scenarios, where multiple monitoring nodes coexist, and both the existing types and new types of encrypted traffic exist at the same time. These nodes cooperate to train models, which can alleviate the challenges of limited numbers and types faced by each single node. In order to solve the proposed ENTC problem, firstly, we propose a feature extraction method in the distributed scenario. Then a detection method for new type traffic and a classification method for existing type traffic are proposed. Finally, a globally consistent automatic category labeling method and classification model updating method for new types encrypted traffic are proposed. We also take Security Information and Event Management (SIEM) as an example to discuss the managerial implications.

Details DOI

NeurIPS Conference 2024 Conference Paper

Fine-Tuning is Fine, if Calibrated

Zheda Mai
Arpita Chowdhury
Ping Zhang
Cheng-Hao Tu
Hong-You Chen
Vardaan Pahuja
Tanya Berger-Wolf
Song Gao

Fine-tuning is arguably the most straightforward way to tailor a pre-trained model (e. g. , a foundation model) to downstream applications, but it also comes with the risk of losing valuable knowledge the model had learned in pre-training. For example, fine-tuning a pre-trained classifier capable of recognizing a large number of classes to master a subset of classes at hand is shown to drastically degrade the model's accuracy in the other classes it had previously learned. As such, it is hard to further use the fine-tuned model when it encounters classes beyond the fine-tuning data. In this paper, we systematically dissect the issue, aiming to answer the fundamental question, "What has been damaged in the fine-tuned model? " To our surprise, we find that the fine-tuned model neither forgets the relationship among the other classes nor degrades the features to recognize these classes. Instead, the fine-tuned model often produces more discriminative features for these other classes, even if they were missing during fine-tuning! What really hurts the accuracy is the discrepant logit scales between the fine-tuning classes and the other classes, implying that a simple post-processing calibration would bring back the pre-trained model's capability and at the same time unveil the feature improvement over all classes. We conduct an extensive empirical study to demonstrate the robustness of our findings and provide preliminary explanations underlying them, suggesting new directions for future theoretical analysis.

PDF Details DOI

AAAI Conference 2024 Conference Paper

KG-TREAT: Pre-training for Treatment Effect Estimation by Synergizing Patient Data with Knowledge Graphs

Ruoqi Liu
Lingfei Wu
Ping Zhang

Treatment effect estimation (TEE) is the task of determining the impact of various treatments on patient outcomes. Current TEE methods fall short due to reliance on limited labeled data and challenges posed by sparse and high-dimensional observational patient data. To address the challenges, we introduce a novel pre-training and fine-tuning framework, KG-TREAT, which synergizes large-scale observational patient data with biomedical knowledge graphs (KGs) to enhance TEE. Unlike previous approaches, KG-TREAT constructs dual-focus KGs and integrates a deep bi-level attention synergy method for in-depth information fusion, enabling distinct encoding of treatment-covariate and outcome-covariate relationships. KG-TREAT also incorporates two pre-training tasks to ensure a thorough grounding and contextualization of patient data and KGs. Evaluation on four downstream TEE tasks shows KG-TREAT’s superiority over existing methods, with an average improvement of 7% in Area under the ROC Curve (AUC) and 9% in Influence Function-based Precision of Estimating Heterogeneous Effects (IF-PEHE). The effectiveness of our estimated treatment effects is further affirmed by alignment with established randomized clinical trial findings.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

MARS: Multimodal Active Robotic Sensing for Articulated Characterization

Hongliang Zeng
Ping Zhang
Chengjiong Wu
Jiahua Wang
Tingyu Ye
Fang Li

Precise perception of articulated objects is vital for empowering service robots. Recent studies mainly focus on point cloud, a single-modal approach, often neglecting vital texture and lighting details and assuming ideal conditions like optimal viewpoints, unrepresentative of real-world scenarios. To address these limitations, we introduce MARS, a novel framework for articulated object characterization. It features a multi-modal fusion module utilizing multi-scale RGB features to enhance point cloud features, coupled with reinforcement learning-based active sensing for autonomous optimization of observation viewpoints. In experiments conducted with various articulated object instances from the PartNet-Mobility dataset, our method outperformed current state-of-the-art methods in joint parameter estimation accuracy. Additionally, through active sensing, MARS further reduces errors, demonstrating enhanced efficiency in handling suboptimal viewpoints. Furthermore, our method effectively generalizes to real-world articulated objects, enhancing robot interactions. Code is available at https: //github. com/robhlzeng/MARS.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Predictive Modeling with Temporal Graphical Representation on Electronic Health Records

Jiayuan Chen
Changchang Yin
Yuanlong Wang
Ping Zhang

Deep learning-based predictive models, leveraging Electronic Health Records (EHR), are receiving increasing attention in healthcare. An effective representation of a patient's EHR should hierarchically encompass both the temporal relationships between historical visits and medical events, and the inherent structural information within these elements. Existing patient representation methods can be roughly categorized into sequential representation and graphical representation. The sequential representation methods focus only on the temporal relationships among longitudinal visits. On the other hand, the graphical representation approaches, while adept at extracting the graph-structured relationships between various medical events, fall short in effectively integrate temporal information. To capture both types of information, we model a patient's EHR as a novel temporal heterogeneous graph. This graph includes historical visits nodes and medical events nodes. It propagates structured information from medical event nodes to visit nodes and utilizes time-aware visit nodes to capture changes in the patient's health status. Furthermore, we introduce a novel temporal graph transformer (TRANS) that integrates temporal edge features, global positional encoding, and local structural encoding into heterogeneous graph convolution, capturing both temporal and structural information. We validate the effectiveness of TRANS through extensive experiments on three real-world datasets. The results show that our proposed approach achieves state-of-the-art performance.

PDF Details DOI

AIIM Journal 2024 Journal Article

SSM-Net: Semi-supervised multi-task network for joint lesion segmentation and classification from pancreatic EUS images

Jiajia Li
Pingping Zhang
Xia Yang
Lei Zhu
Teng Wang
Ping Zhang
Ruhan Liu
Bin Sheng

Pancreatic cancer does not show specific symptoms, which makes the diagnosis of early stages difficult with established image-based screening methods and therefore has the worst prognosis among all cancers. Although endoscopic ultrasonography (EUS) has a key role in diagnostic algorithms for pancreatic diseases, B-mode imaging of the pancreas can be affected by confounders such as chronic pancreatitis, which can make both pancreatic lesion segmentation and classification laborious and highly specialized. To address these challenges, this work proposes a semi-supervised multi-task network (SSM-Net) to leverage unlabeled and labeled EUS images for joint pancreatic lesion classification and segmentation. Specifically, we first devise a saliency-aware representation learning module (SRLM) on a large number of unlabeled images to train a feature extraction encoder network for labeled images by computing a contrastive loss with a semantic saliency map, which is obtained by our spectral residual module (SRM). Moreover, for labeled EUS images, we devise channel attention blocks (CABs) to refine the features extracted from the pre-trained encoder on unlabeled images for segmenting lesions, and then devise a merged global attention module (MGAM) and a feature similarity loss (FSL) for obtaining a lesion classification result. We collect a large-scale EUS-based pancreas image dataset (LS-EUSPI) consisting of 9, 555 pathologically proven labeled EUS images (499 patients from four categories) and 15, 500 unlabeled EUS images. Experimental results on the LS-EUSPI dataset and a public thyroid gland lesion dataset show that our SSM-Net clearly outperforms state-of-the-art methods.

Details DOI

ICRA Conference 2023 Conference Paper

FLYOVER: A Model-Driven Method to Generate Diverse Highway Interchanges for Autonomous Vehicle Testing

Yuan Zhou 0005
Gengjie Lin
Yun Tang 0003
Kairui Yang
Wei Jing
Ping Zhang
Junbo Chen
Liang Gong

It has become a consensus that autonomous vehicles (AVs) will first be widely deployed on highways. However, the complexity of highway interchanges becomes the bottleneck for their deployment. An AV should be sufficiently tested under different highway interchanges, which is still challenging due to the lack of available datasets containing diverse highway interchanges. In this paper, we propose a model-driven method, Flyover, to generate a dataset of diverse interchanges with measurable diversity coverage. First, Flyover uses a labeled digraph to model interchange topology. Second, Flyover takes real-world interchanges as input to guarantee topology practicality and extracts different topology equivalence classes by classifying corresponding topology models. Third, for each topology class, Flyover identifies the corresponding geometrical features for the ramps and generates concrete interchanges using k-way combinatorial coverage and differential evolution. To illustrate the diversity and applicability of the generated interchange dataset, we test the built-in traffic flow control algorithm in SUMO and the fuel-optimization trajectory tracking algorithm deployed to Alibaba's autonomous trucks on the dataset. The results show that except for the geometrical difference, the interchanges are diverse in throughput and fuel consumption under the traffic flow control and trajectory tracking algorithms, respectively.

Details

TIST Journal 2022 Journal Article

Incorporation of Data-Mined Knowledge into Black-Box SVM for Interpretability

Shaohan Chen
Chuanhou Gao
Ping Zhang

The lack of interpretability often makes black-box models challenging to be applied in many practical domains. For this reason, the current work, from the black-box model input port, proposes to incorporate data-mined knowledge into the black-box soft-margin SVM model to enhance accuracy and interpretability. The concept and incorporation mechanism of data-mined knowledge are successively developed, based on which a partially interpretable soft-margin SVM ( pTsm -SVM) optimization model is designed and then solved through reformulating the optimization problem as standard quadratic programming. An algorithm for mining linear positive (negative) class knowledge from general data sets is also proposed, which generates a linear two-dimensional discriminative rule with specificity (sensitivity) equal to 1 and the highest possible sensitivity (specificity) among all two-dimensional feature spaces. The knowledge-integrated pTsm -SVM works by achieving a good trade-off among the “large margin”, “high specificity”, and “high sensitivity”. Our experimental results on eight UCI datasets demonstrate the superiority of the proposed pTsm -SVM over the standard soft-margin SVM both in terms of accuracy and interpretability.

Details DOI

JBHI Journal 2022 Journal Article

Optimization of Dry Weight Assessment in Hemodialysis Patients via Reinforcement Learning

Ziyue Yang
Yu Tian
Tianshu Zhou
Yilin Zhu
Ping Zhang
Jianghua Chen
Jingsong Li

Dry weight (DW), defined as the lowest tolerated postdialysis weight following the ultrafiltration (UF) of excess fluid volume, is essential for any dialysis prescription for hemodialysis (HD) patients. However, there is no gold standard for DW assessment, and the difficulty of its accurate assessment increases given individual variations and the dynamic changes caused by the uncertainty of patients’ condition. Therefore, the current empirical evaluation process is often crude, imprecise, experience-dependent, and energy-consuming. Here, we highlight the personalized dynamic changes in DW over time rather than the more accurate DW assessments at some point in time and formulate the DW evaluation problem into a sequential decision-making process using the Markov decision process (MDP) framework. A reinforcement learning (RL) algorithm based on a dueling double deep Q-network (Duel-DDQN) is proposed to optimize the DW assessment policy, and a multifaceted inspection is applied to assess policy effectiveness and safety. We utilize ten years of data from the Kidney Disease Center, enrolling 750 HD patients and 243, 287 dialysis sessions. Good model calibration is confirmed, and off-policy evaluation demonstrates that our policy outperforms other policies, suggesting a decrease of 7. 71% in the expected 5-year mortality rate and of 13. 44% in the incidence of intradialytic symptoms compared with those of clinicians’ strategy. The RL policy adjusts DW more frequently, responds to DW changes more actively, and observes a larger feature space. It is hoped that the proposed solution will help clinicians assess and monitor DW dynamically, making the estimation process more refined, personalized, and intelligent.

Details DOI

EAAI Journal 2021 Journal Article

A conditional-weight joint relevance metric for feature relevancy term

Ping Zhang
Wanfu Gao
Juncheng Hu
Yonghao Li

Feature selection is an important preprocessing operation in the fields of machine learning and data mining. Information theory is widely used in feature selection methods because it can measure linear and nonlinear correlations among variables. Traditional information theory-based feature selection methods intend to maximize feature relevancy while minimizing feature redundancy. However, previous feature selection methods focus on either the effect of candidate features or the effect of already-selected features on the feature relevancy. In fact, both candidate features and already-selected features offer important classification information in the design of feature relevancy term. To avoid this problem, we extract useful classification information from joint mutual information to design a novel feature relevancy term named Conditional-Weight Joint Relevance (CWJR). Based on CWJR, we propose a novel feature selection method named Feature Selection considering Conditional-Weight Joint Relevance (CWJR-FS). Additionally, to distinguish the differences between our method and previous methods, we divide information theory-based feature selection methods into two categories: linear-based feature selection methods and nonlinear-based feature selection methods. Finally, our method is compared to seven linear-based methods and four nonlinear-based methods on 19 benchmark data sets. The experimental results demonstrate that CWJR-FS outperforms the compared methods in terms of the average classification accuracy, AUC and F1 score.

Details DOI

IROS Conference 2021 Conference Paper

KB-Tree: Learnable and Continuous Monte-Carlo Tree Search for Autonomous Driving Planning

Lanxin Lei
Ruiming Luo
Renjie Zheng
Jingke Wang
Jianwei Zhang
Cong Qiu
Liulong Ma
Liyang Jin

In this paper, we present a novel learnable and continuous Monte-Carlo Tree Search method, named as KB-Tree, for motion planning in autonomous driving. The proposed method utilizes an asymptotical PUCB based on Kernel Regression (KR-AUCB) as a novel UCB variant, to improve the exploitation and exploration performance. In addition, we further optimize the sampling in continuous space by adapting Bayesian Optimization (BO) in the selection process of MCTS. Moreover, we use a customized Graph Neural Network (GNN) as our feature extractor to improve the learning performance. To the best of our knowledge, we are the first to apply the continuous MCTS method in autonomous driving. To validate our method, we conduct extensive experiments under several weakly and strongly interactive scenarios. The results show that our proposed method performs well in all tasks, and outperforms the learning-based continuous MCTS method and the state-of-the-art Reinforcement Learning (RL) baseline.

Details

NeurIPS Conference 2021 Conference Paper

Learning to Select Exogenous Events for Marked Temporal Point Process

Ping Zhang
Rishabh Iyer
Ashish Tendulkar
Gaurav Aggarwal
Abir De

Marked temporal point processes (MTPPs) have emerged as a powerful modelingtool for a wide variety of applications which are characterized using discreteevents localized in continuous time. In this context, the events are of two typesendogenous events which occur due to the influence of the previous events andexogenous events which occur due to the effect of the externalities. However, inpractice, the events do not come with endogenous or exogenous labels. To thisend, our goal in this paper is to identify the set of exogenous events from a set ofunlabelled events. To do so, we first formulate the parameter estimation problemin conjunction with exogenous event set selection problem and show that thisproblem is NP hard. Next, we prove that the underlying objective is a monotoneand \alpha-submodular set function, with respect to the candidate set of exogenousevents. Such a characterization subsequently allows us to use a stochastic greedyalgorithm which was originally proposed in~\cite{greedy}for submodular maximization. However, we show that it also admits an approximation guarantee for maximizing\alpha-submodular set function, even when the learning algorithm provides an imperfectestimates of the trained parameters. Finally, our experiments with synthetic andreal data show that our method performs better than the existing approaches builtupon superposition of endogenous and exogenous MTPPs.

PDF Details

IJCAI Conference 2018 Conference Paper

Interpretable Drug Target Prediction Using Deep Neural Representation

Kyle Yingkai Gao
Achille Fokoue
Heng Luo
Arun Iyengar
Sanjoy Dey
Ping Zhang

The identification of drug-target interactions (DTIs) is a key task in drug discovery, where drugs are chemical compounds and targets are proteins. Traditional DTI prediction methods are either time consuming (simulation-based methods) or heavily dependent on domain expertise (similarity-based and feature-based methods). In this work, we propose an end-to-end neural network model that predicts DTIs directly from low level representations. In addition to making predictions, our model provides biological interpretation using two-way attention mechanism. Instead of using simplified settings where a dataset is evaluated as a whole, we designed an evaluation dataset from BindingDB following more realistic settings where predictions of unobserved examples (proteins and drugs) have to be made. We experimentally compared our model with matrix factorization, similarity-based methods, and a previous deep learning approach. Overall, the results show that our model outperforms other approaches without requiring domain knowledge and feature engineering. In a case study, we illustrated the ability of our approach to provide biological insights to interpret the predictions.

PDF Details

AAAI Conference 2017 Conference Paper

Adverse Drug Reaction Prediction with Symbolic Latent Dirichlet Allocation

Cao Xiao
Ping Zhang
W. Chaovalitwongse
Jianying Hu
Fei Wang

Adverse drug reaction (ADR) is a major burden for patients and healthcare industry. It usually causes preventable hospitalizations and deaths, while associated with a huge amount of cost. Traditional preclinical in vitro safety proﬁling and clinical safety trials are restricted in terms of small scale, long duration, huge ﬁnancial costs and limited statistical signiﬁcance. The availability of large amounts of drug and ADR data potentially allows ADR predictions during the drugs’ early preclinical stage with data analytics methods to inform more targeted clinical safety tests. Despite their initial success, existing methods have trade-offs among interpretability, predictive power and efﬁciency. This urges us to explore methods that could have all these strengths and provide practical solutions for real world ADR predictions. We cast the ADR-drug relation structure into a three-layer hierarchical Bayesian model. We interpret each ADR as a symbolic word and apply latent Dirichlet allocation (LDA) to learn topics that may represent certain biochemical mechanism that relates ADRs with drug structures. Based on LDA, we designed an equivalent regularization term to incorporate the hierarchical ADR domain knowledge. Finally, we developed a mixed input model leveraging a fast collapsed Gibbs sampling method that the complexity of each iteration of Gibbs sampling proportional only to the number of positive ADRs. Experiments on real world data show our models achieved higher prediction accuracy and shorter running time than the state-of-the-art alternatives.

PDF Details

AAAI Conference 2017 Conference Paper

Multitask Dyadic Prediction and Its Application in Prediction of Adverse Drug-Drug Interaction

Bo Jin
Haoyu Yang
Cao Xiao
Ping Zhang
Xiaopeng Wei
Fei Wang

Adverse drug-drug interactions (DDIs) remain a leading cause of morbidity and mortality around the world. Identifying potential DDIs during the drug design process is critical in guiding targeted clinical drug safety testing. Although detection of adverse DDIs is conducted during Phase IV clinical trials, there are still a large number of new DDIs founded by accidents after the drugs were put on market. With the arrival of big data era, more and more pharmaceutical research and development data are becoming available, which provides an invaluable resource for digging insights that can potentially be leveraged in early prediction of DDIs. Many computational approaches have been proposed in recent years for DDI prediction. However, most of them focused on binary prediction (with or without DDI), despite the fact that each DDI is associated with a different type. Predicting the actual DDI type will help us better understand the DDI mechanism and identify proper ways to prevent it. In this paper, we formulate the DDI type prediction problem as a multitask dyadic regression problem, where the prediction of each speciﬁc DDI type is treated as a task. Compared with conventional matrix completion approaches which can only impute the missing entries in the DDI matrix, our approach can directly regress those dyadic relationships (DDIs) and thus can be extend to new drugs more easily. We developed an effective proximal gradient method to solve the problem. Evaluation on real world datasets is presented to demonstrate the effectiveness of the proposed approach.

PDF Details

YNICL Journal 2016 Journal Article

The development of automatic emotion regulation in an implicit emotional Go/NoGo paradigm and the association with depressive symptoms and anhedonia during adolescence

Wenhai Zhang
Qiang Ding
Ning Chen
Qing Wei
Cancan Zhao
Ping Zhang
Xiying Li
Qiang Liu

Impaired automatic emotion regulation (AER) is closely related to major depressive disorder. Our research in adults has identified two AER-related components, Go N2 and NoGo P3, in an implicit emotional Go/NoGo paradigm. However, it is unclear whether Go N2 and NoGo P3 reflect the development of AER in adolescents and the relationship of these components with subclinical depressive symptoms and trait anhedonia. We collected EEG data from 55 adolescents while they completed the implicit emotional Go/NoGo task. After the experiment, the subjects completed the Chinese version of the Temporal Experience of Pleasure Scale and the Beck Depression Inventory. Consistent with results in adults, we determined that Go N2 represents automatic top-down attention to emotions in Go trials, whereas NoGo P3 represents automatic response inhibition in NoGo trials. These AER components exhibited age-dependent improvement during adolescence. Additionally, NoGo P3 amplitudes elicited by viewing positive faces were positively correlated with trait anhedonia, whereas NoGo P3 amplitudes elicited by viewing negative faces were negatively correlated with depressive symptoms. Our observations provide further understanding of the neurodevelopmental mechanism of AER and yield new insight into dissociable impairments in AER in adolescents with major depressive disorder during positive and negative implicit processing.

Details DOI

EAAI Journal 2015 Journal Article

Research of semantic understanding on target region of interest for fuzzy image

QingE Wu
Weidong Yang
Zhiwu Chen
Ping Zhang

Image understanding can provide an accurate and rapid target identification method for some military affairs, public security, finance and other departments. How to carry out the semantic understanding of scene of fuzzy image is a problem to be solved urgently in many departments. Moreover, research on this problem is still in an initial stage at home and abroad. For fuzziness, incompleteness and scene semantic understanding on fuzzy image processing, this paper studies a variety of fuzzy signals, analyzes the uncertainties classification and their influence, constructs a three-tier processing mode framework that can eliminate fuzziness processing, repair processing, dynamic combination processing, and presents some methods and algorithms for fuzzy signal processing. Through defining the support, this paper selects target region of interest (ROI), extracts some multidimensional and effective characteristics of targets on ROI, and builds a fuzzy recognition algorithm for targets. By defining the correlative importance between targets, as well as expert knowledge or associated experimental data, this paper carries out a semantic scene understanding on ROI, and presents a semantic understanding method for fuzzy image understanding. Using the combination method of simulation and instance experiments, this paper systematically analyzes the validity of the model and algorithms. The research developed in this paper can pave a new way to improve the real-time, speed and accuracy of information processing, have an important theoretical reference and practical significance, further form the theoretic base for uncertain information processing, and also provide a new idea and way on target recognition for a variety of scenarios.

Details DOI

ICRA Conference 2007 Conference Paper

Design Tradeoffs for Electrothermal Microgrippers

Mohammad Mayyas
Ping Zhang
Woo Ho Lee
Panos S. Shiakolas
Dan O. Popa

Microgrippers based on electrothermal actuation were designed and fabricated using the deep reactive ion etching (DRIE) process with 100mum thick silicon on insulator (SOI) wafer. The design requirements are restricted to basic manipulation tasks such as pick and place, and nonprehensile manipulation. This paper explores several electrothermal end-effectors which have been fabricated for serial and parallel microassembly. The end-effectors include three main building blocks: 1) Integrated and symmetrical actuators of V and U shapes. The symmetrical expansions on Chevron and hot arms allow combination of forward translations that amplify angular motion at the tips of a gripper. 2) A joule heating element based on a resistive V-shape electrothermal actuator. In 3D microassembly, the joining of a micropart is essentially performed by providing an integrated microheater device. 3) A force or position feedback sensing block based on self-straining or electrostatic principle. The integrated sensor can be calibrated for both position and force measurements. Serial heterogeneous assembly of meso and micro-scale objects is demonstrated using a 3D microassembly station. Black-box dynamical models for microgrippers are derived using experimentally obtained data, and performance variations due to the way the microgrippers are mounted onto the robot are discussed.

Details

ICRA Conference 2007 Conference Paper

µ 3: Multiscale, Deterministic Micro-Nano Assembly System for Construction of On-Wafer Microrobots

Aditya N. Das
Ping Zhang
Woo Ho Lee
Dan O. Popa
Harry E. Stephanou

One of the major issues enduring with microscale mechanics has been to design high fidelity miniature machines capable of performing complex operations. Though achieved in some proportion through conventional in-plane and out-of-plane designs, the efficacy of such micro-electro-mechanical systems (MEMS) structures is highly limited due to complicate fabrication and inadequate robustness. On the other hand, the use of precise robots to assemble MEMS parts of comparatively simpler design to build 3D micromechanical structures has recently emerged as a viable approach. Such modular assemblies of microscale parts typically utilize minimum energy connectors that are multifunctional, e. g. , mechanical, electrical etc. The μ 3 is a 3-D microassembly station consisting of 19 DOF arranged into 3 micromanipulators, with additional microgrippers and stereo microscope vision. The platform is capable of motion resolutions of 3nm and is small enough to be used inside of a scanning electron microscope (SEM) for nano-manipulation. In this paper we discuss how systematic identification and calibration of the station, combined with appropriate part connector designs can lead to multi-degree of freedom active MEMS robots assembled on a wafer.

Details

ICRA Conference 1996 Conference Paper

A full tactile sensing suite for dextrous robot hands and use in contact force control

David Johnston
Ping Zhang
John M. Hollerbach
Stephen C. Jacobsen

A full tactile sensing suite for the finger segments and palm of the Utah/MIT dextrous hand is presented. The rubber-based sensors employ capacitance sensing and floating electrodes in the top layer, and contain local electronics for excitation, filtering, analog-to-digital conversion, and serial communication. Experimental results on static, dynamic, and spatial properties are presented. Use of the tactile sensor in contact force control is demonstrated.

Details