Author name cluster

Yifan Zhou

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.

23 papers

2 author rows

TMLR Journal 2026 Journal Article

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Guibin Zhang
Hejia Geng
Xiaohang Yu
Zhenfei Yin
Zaibin Zhang
Zelin Tan
Heng Zhou
Zhong-Zhi Li

The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous, decision-making agents embedded in complex, dynamic worlds. This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM RL with the temporally extended Partially Observable Markov Decision Processes (POMDPs) that define Agentic RL. Building on this foundation, we propose a comprehensive twofold taxonomy: one organized around core agentic capabilities, including planning, tool use, memory, reasoning, self-improvement, and perception, and the other around their applications across diverse task domains. Central to our thesis is that reinforcement learning serves as the critical mechanism for transforming these capabilities from static, heuristic modules into adaptive, robust agentic behavior. To support and accelerate future research, we consolidate the landscape of open-source environments, benchmarks, and frameworks into a practical compendium. By synthesizing over five hundred recent works, this survey charts the contours of this rapidly evolving field and highlights the opportunities and challenges that will shape the development of scalable, general-purpose AI agents.

PDF Details

IROS Conference 2025 Conference Paper

BaTCAVe: Trustworthy Explanations for Robot Behaviors

Som Sagar
Aditya Taparia
Harsh Mankodiya
Pranav Bidare
Yifan Zhou
Ransalu Senanayake

Black box neural networks are an indispensable part of modern robots. Nevertheless, deploying such high-stakes systems in real-world scenarios poses significant challenges when the stakeholders, such as engineers and legislative bodies, lack insights into the neural networks’ decision-making process. Presently, explainable AI is primarily tailored to natural language processing and computer vision, falling short in two critical aspects when applied in robots: grounding in decision-making tasks and the ability to assess trustworthiness of their explanations. In this paper, we introduce a trustworthy explainable robotics technique based on human-interpretable, high-level concepts that attribute to the decisions made by the neural network. Our proposed technique provides explanations with associated uncertainty scores for the explanation by matching neural network’s activations with human-interpretable visualizations. To validate our approach, we conducted a series of experiments with various simulated and real-world robot decision-making models, demonstrating the effectiveness of the proposed approach as a post-hoc, human-friendly robot diagnostic tool. Code: https://github.com/aditya-taparia/BaTCAVe

Details

NeurIPS Conference 2025 Conference Paper

CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing

Yifan Zhou
Tianshi Xu
Jue Hong
Ye Wu
Meng Li

Private large language model (LLM) inference based on cryptographic primitives offers a promising path towards privacy-preserving deep learning. However, existing frameworks only support dense LLMs like LLaMA-1 and struggle to scale to mixture-of-experts (MoE) architectures. The key challenge comes from securely evaluating the dynamic routing mechanism in MoE layers, which may reveal sensitive input information if not fully protected. In this paper, we propose CryptoMoE, the first framework that enables private, efficient, and accurate inference for MoE-based models. CryptoMoE balances expert loads to protect expert routing information and proposes novel protocols for secure expert dispatch and combine. CryptoMoE also develops a confidence-aware token selection strategy and a batch matrix multiplication protocol to improve accuracy and efficiency further. Extensive experiments on DeepSeekMoE-16. 4B, OLMoE-6. 9B, and QWenMoE-14. 3B show that CryptoMoE achieves $2. 8\sim3. 5\times$ end-to-end latency reduction and $3\sim6\times$ communication reduction over a dense baseline with minimum accuracy loss. We also adapt CipherPrune (ICLR'25) for MoE inference and demonstrate CryptoMoE can reduce the communication by up to $4. 3 \times$.

PDF Details

ICLR Conference 2025 Conference Paper

Empowering Users in Digital Privacy Management through Interactive LLM-Based Agents

Bolun Sun
Yifan Zhou
Haiyun Jiang

This paper presents a novel application of large language models (LLMs) to enhance user comprehension of privacy policies through an interactive dialogue agent. We demonstrate that LLMs significantly outperform traditional models in tasks like Data Practice Identification, Choice Identification, Policy Summarization, and Privacy Question Answering, setting new benchmarks in privacy policy analysis. Building on these findings, we introduce an innovative LLM-based agent that functions as an expert system for processing website privacy policies, guiding users through complex legal language without requiring them to pose specific questions. A user study with 100 participants showed that users assisted by the agent had higher comprehension levels (mean score of 2.6 out of 3 vs. 1.8 in the control group), reduced cognitive load (task difficulty ratings of 3.2 out of 10 vs. 7.8), increased confidence in managing privacy, and completed tasks in less time (5.5 minutes vs. 15.8 minutes). This work highlights the potential of LLM-based agents to transform user interaction with privacy policies, leading to more informed consent and empowering users in the digital services landscape.

Details

EAAI Journal 2025 Journal Article

Online diagnosis of weak welds in busbar laser welding based on photoelectric signals and machine learning

Leshi Shu
Yifan Zhou
Wendi Wu
Ping Jiang
Yilin Wang

Busbars are essential conductive components in power systems, laser welding is widely used for their electrical connections due to its advantages of high precision, high efficiency, and a low heat-affected zone. However, weak weld defects are prone to occur in laser welding of busbars due to factors such as laser power fluctuations, focal shift, surface contamination, and overlap gap instability. Weak weld defects can reduce joint strength, increase contact resistance, and affect the performance and safety of the equipment. This study presents a weak weld diagnosis method for laser welding of busbars driven by machine learning based on photoelectric signals. The proposed method introduces a Reference-Enhanced Signal Feature Definition method, which improves diagnostic accuracy by utilizing multi-band data segmentation and the calculation of the Reference Deviation Coefficient Feature Matrix. This feature definition method has advantages in adapting to different process conditions and improving the recognition rate of minor defects. On this basis, the random forest-based weak weld defect diagnosis model was constructed. The method not only detects the presence of weak weld defects in busbar laser welding but also diagnoses the factors inducing these defects, providing effective support for rapid identification of problem sources and targeted interventions in industrial production. Mechanistic analysis reveals that different types of weak weld defect-inducing factors exhibit significant differences in their photoelectric signal characteristics. Experimental results show that the model achieved an average detection accuracy of 99. 20 % for weak weld defects across 1427 welding joints, with an average accuracy of 98. 75 % in defect-inducing factors diagnosis.

Details DOI

NeurIPS Conference 2025 Conference Paper

Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs

Yifan Zhou
Sachin Grover
Mohamed El Mistiri
Kamalesh Kalirathinam
Pratyush Kerhalkar
Swaroop Mishra
Neelesh Kumar
Sanket Gaurav

Reinforcement Learning (RL) traditionally relies on scalar reward signals, limiting its ability to leverage the rich semantic knowledge often available in real-world tasks. In contrast, humans learn efficiently by combining numerical feedback with language, prior knowledge, and common sense. We introduce Prompted Policy Search (ProPS), a novel RL method that unifies numerical and linguistic reasoning within a single framework. Unlike prior work that augments existing RL components with language, ProPS places a large language model (LLM) at the center of the policy optimization loop—directly proposing policy updates based on both reward feedback and natural language input. We show that LLMs can perform numerical optimization in-context, and that incorporating semantic signals, such as goals, constraints, and strategy hints can lead to more informed exploration and sample-efficient learning. ProPS is evaluated across 15 Gymnasium tasks, spanning classic control, Atari games, and MuJoCo environments, and compared to seven widely-adopted RL algorithms (e. g. , PPO, SAC, TRPO). It outperforms all baselines on 8 out of 15 tasks and demonstrates substantial gains when provided with domain knowledge. These results highlight the potential of unifying semantics and numerics for transparent, generalizable, and human-aligned reinforcement learning.

PDF Details

AAAI Conference 2025 Conference Paper

Rebalancing Multi-Label Class-Incremental Learning

Kaile Du
Yifan Zhou
Fan Lyu
Yuyang Li
Junzhou Xie
Yixi Shen
Fuyuan Hu
Guangcan Liu

Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL approaches can only achieve suboptimal performance due to the oversight of the positive-negative imbalance problem, which manifests at both the label and loss levels because of the task-level partial label issue. The imbalance at the label level arises from the substantial absence of negative labels, while the imbalance at the loss level stems from the asymmetric contributions of the positive and negative loss parts to the optimization. To address the issue above, we propose a Rebalance framework for both the Loss and Label levels (RebLL), which integrates two key modules: asymmetric knowledge distillation (AKD) and online relabeling (OR). AKD is proposed to rebalance at the loss level by emphasizing the negative label learning in classification loss and down-weighting the contribution of overconfident predictions in distillation loss. OR is designed for label rebalance, which restores the original class distribution in memory by online relabeling the missing classes. Our comprehensive experiments on the PASCAL VOC and MS-COCO datasets demonstrate that this rebalancing strategy significantly improves performance, achieving new state-of-the-art results even with a vanilla CNN backbone.

PDF Details DOI

EAAI Journal 2025 Journal Article

Research on fresh supply chain risk evaluation of community group purchase based on hybrid multi-attribute decision-making method

Nian Zhang
Anling Wang
Yifan Zhou
Shuo Zheng

The community group purchase (CGP) is rapidly evolving as a novel e-commerce mode that combines modern e-commerce with community integration in China. However, the core products of CGP are mainly fresh goods, where the fresh supply chain demands higher quality, faster processing, and greater freshness compared to the traditional product supply chain. Therefore, a risk evaluation of the CGP's fresh supply chain is crucial to ensure supplier stability, logistics efficiency, and storage conditions. This study presents a comprehensive risk evaluation model of CGP's fresh supply chain to enhance risk management and maintain product and freshness. Firstly, the social network analysis (SNA) method and the grounded theory are used to extract key indicators from existing literature and textual data. Secondly, the weight of each indicator is determined from the subjective and objective dimensions by using the order relationship analysis (G1) method and the Criteria Importance Through Intercriteria Correlation (CRITIC) method, and the decision matrix is constructed by the Fermatean hesitant fuzzy set. Then, considering that decision-maker (DM) may not be in a completely rational state during the evaluation process, the regret theory is introduced to quantify the DM's regret psychology. In addition, after obtaining the relative dominance through the TOmada de Decisão Iterativa Multicritério (TODIM) method, the risk evaluation is completed by using the VIseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method. Finally, sensitivity analysis validates the model's validity and applicability. This study offers a dynamic fresh supply chain risk evaluation model for the CGP industry, contributing to stable CGP enterprise operations.

Details DOI

ICRA Conference 2025 Conference Paper

RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenes

Sicheng Yu
Chong Cheng
Yifan Zhou
Xiaojun Yang
Hao Wang 0094

3D Gaussian Splatting (3DGS) has become a popular solution in SLAM, as it can produce high-fidelity novel views. However, previous GS-based methods primarily target indoor scenes and rely on RGB-D sensors or pretrained depth estimation models, hence underperforming in outdoor scenarios. To address this issue, we propose a RGB-only gaussian splatting SLAM method for unbounded out-door scenes—OpenGS-SLAM. Technically, we first employ a pointmap regression network to generate consistent pointmaps between frames for pose estimation. Compared to commonly used depth maps, pointmaps include spatial relationships and scene geometry across multiple views, enabling robust camera pose estimation. Then, we propose integrating the estimated camera poses with 3DGS rendering as an end-to-end differentiable pipeline. Our method achieves simultaneous optimization of camera poses and 3DGS scene parameters, significantly enhancing system tracking accuracy. Specifically, we also design an adaptive scale mapper for the pointmap regression network, which provides more accurate pointmap mapping to the 3DGS map representation. Our experiments on the Waymo dataset demonstrate that OpenGS-SLAM reduces tracking error to 9. 8% of previous 3DGS methods, and achieves state-of-the-art results in novel view synthesis. Project page: https://3dagentworld.github.io/pengs-slam/.

Details

ICRA Conference 2025 Conference Paper

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement

Heni Ben Amor
Laura Graesser
Atil Iscen
David B. D'Ambrosio
Saminda Abeyruwan
Alex Bewley
Yifan Zhou
Kamalesh Kalirathinam

We demonstrate the ability of large language models (LLMs) to perform iterative self-improvement of robot policies. An important insight of this paper is that LLMs have a built-in ability to perform (stochastic) numerical optimization and that this property can be leveraged for explainable robot policy search. Based on this insight, we introduce the SAS Prompt (Summarize, Analyze, Synthesize) – a single prompt that enables iterative learning and adaptation of robot behavior by combining the LLM's ability to retrieve, reason and optimize over previous robot traces in order to synthesize new, unseen behavior. Our approach can be regarded as an early example of a new family of explainable policy search methods that are entirely implemented within an LLM. We evaluate our approach both in simulation and on a real-robot table tennis task. Project website: sites.google.com/asu.edu/sas-llm/

Details

NeurIPS Conference 2025 Conference Paper

WorldMem: Long-term Consistent World Simulation with Memory

Zeqi Xiao
Yushi Lan
Yifan Zhou
Wenqi Ouyang
Shuai Yang
Yanhong Zeng
Xingang Pan

World simulation has gained increasing popularity due to its ability to model virtual environments and predict the consequences of actions. However, the limited temporal context window often leads to failures in maintaining long-term consistency, particularly in preserving 3D spatial consistency. In this work, we present WorldMem, a framework that enhances scene generation with a memory bank consisting of memory units that store memory frames and states (e. g. , poses and timestamps). By employing state-aware memory attention that effectively extracts relevant information from these memory frames based on their states, our method is capable of accurately reconstructing previously observed scenes, even under significant viewpoint or temporal gaps. Furthermore, by incorporating timestamps into the states, our framework not only models a static world but also captures its dynamic evolution over time, enabling both perception and interaction within the simulated world. Extensive experiments in both virtual and real scenarios validate the effectiveness of our approach.

PDF Details

ICLR Conference 2024 Conference Paper

AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation

Zihao Tang
Zheqi Lv
Shengyu Zhang 0001
Yifan Zhou
Xinyu Duan
Fei Wu 0001
Kun Kuang 0001

Due to privacy or patent concerns, a growing number of large models are released without granting access to their training data, making transferring their knowledge inefficient and problematic. In response, Data-Free Knowledge Distillation (DFKD) methods have emerged as direct solutions. However, simply adopting models derived from DFKD for real-world applications suffers significant performance degradation, due to the discrepancy between teachers' training data and real-world scenarios (student domain). The degradation stems from the portions of teachers' knowledge that are not applicable to the student domain. They are specific to the teacher domain and would undermine students' performance. Hence, selectively transferring teachers' appropriate knowledge becomes the primary challenge in DFKD. In this work, we propose a simple but effective method AuG-KD. It utilizes an uncertainty-guided and sample-specific anchor to align student-domain data with the teacher domain and leverages a generative method to progressively trade off the learning process between OOD knowledge distillation and domain-specific information learning via mixup learning. Extensive experiments in 3 datasets and 8 settings demonstrate the stability and superiority of our approach.

Details

JMLR Journal 2024 Journal Article

Cluster-Adaptive Network A/B Testing: From Randomization to Estimation

Yang Liu
Yifan Zhou
Ping Li
Feifang Hu

The performance of A/B testing in both online and offline experimental settings hinges on mitigating network interference and achieving covariate balancing. These experiments often involve an observable network with identifiable clusters, and measurable cluster-level and individual-level attributes. Exploiting these inherent characteristics holds potential for refining experimental design and subsequent statistical analyses. In this article, we propose a novel cluster-adaptive network A/B testing procedure, which contains a cluster-adaptive randomization (CLAR) and a cluster-adjusted estimator (CAE) to facilitate the design of the experiment and enhance the performance of ATE estimation. The CLAR sequentially assigns clusters to minimize the Mahalanobis distance, which further leads to the balance of the cluster-level covariates and the within-cluster-averaged individual-level covariates. The cluster-adjusted estimator (CAE) is tailored to offset biases caused by network interference. The proposed procedure has the following two folds of the desirable properties. First, we show that the Malanobis distance calculated for the two levels of covariates is $O_p(m^{-1})$, where $m$ represents the number of clusters. This result justifies the simultaneous balance of the cluster-level and individual-level covariates. Under mild conditions, we derive the asymptotic normality of CAE and demonstrate the benefit of covariate balancing on improving the precision for estimating ATE. The proposed A/B testing procedure is easy to calculate, consistent, and achieves higher accuracy. Extensive numerical studies are conducted to demonstrate the finite sample property of the proposed network A/B testing procedure. [abs] [ pdf ][ bib ] &copy JMLR 2024. ( edit, beta )

PDF Details

IROS Conference 2024 Conference Paper

Diff-Control: A Stateful Diffusion-based Policy for Imitation Learning

Xiao Liu
Yifan Zhou
Fabian Clemens Weigend
Shubham D. Sonawani
Shuhei Ikemoto
Heni Ben Amor

While imitation learning provides a simple and effective framework for policy learning, acquiring consistent action during robot execution remains a challenging task. Existing approaches primarily focus on either modifying the action representation at data curation stage or altering the model itself, both of which do not fully address the scalability of consistent action generation. To overcome this limitation, we introduce the Diff-Control policy, which utilizes a diffusion-based model to learn action representation from a state-space modeling viewpoint. We demonstrate that diffusion-based policies can acquire statefulness through a Bayesian formulation facilitated by ControlNet, leading to improved robustness and success rates. Our experimental results demonstrate the significance of incorporating action statefulness in policy learning, where Diff-Control shows improved performance across various tasks. Specifically, Diff-Control achieves an average success rate of 72% and 84% on stateful and dynamic tasks, respectively. Notably, Diff-Control also shows consistent performance in the presence of perturbations, outperforming other state-of-the-art methods that falter under similar conditions. Project page: https://diff-control.github.io/

Details

ICRA Conference 2024 Conference Paper

Open X-Embodiment: Robotic Learning Datasets and RT-X Models: Open X-Embodiment Collaboration

Abby O'Neill
Abdul Rehman
Abhiram Maddukuri
Abhishek Gupta 0004
Abhishek Padalkar
Abraham Lee
Acorn Pooley
Agrim Gupta

Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x. github.io.

Details

IROS Conference 2024 Conference Paper

Rotograb: Combining Biomimetic Hands with Industrial Grippers using a Rotating Thumb

Arnaud Bersier
Matteo Leonforte
Alessio Vanetta
Sarah Lia Andrea Wotke
Andrea Nappi
Yifan Zhou
Sebastiano Oliani
Alexander M. Kübler

The development of robotic grippers and hands for automation aims to emulate human dexterity without sacrificing the efficiency of industrial grippers. This study introduces Rotograb, a tendon-actuated robotic hand featuring a novel rotating thumb. The aim is to combine the dexterity of human hands with the efficiency of industrial grippers. The rotating thumb enlarges the workspace and allows in-hand manipulation. A novel joint design minimizes movement interference and simplifies kinematics, using a cutout for tendon routing. We integrate teleoperation, using a depth camera for real-time tracking and autonomous manipulation powered by reinforcement learning with proximal policy optimization. Experimental evaluations demonstrate that Rotograb’s rotating thumb greatly improves both operational versatility and workspace. It can handle various grasping and manipulation tasks with objects from the YCB dataset, with particularly good results when rotating objects within its grasp. Rotograb represents a notable step towards bridging the capability gap between human hands and industrial grippers. The tendon-routing and thumb-rotating mechanisms allow for a new level of control and dexterity. Integrating teleoperation and autonomous learning underscores Rotograb’s adaptability and sophistication, promising substantial advancements in both robotics research and practical applications.

Details

NeurIPS Conference 2024 Conference Paper

Video Diffusion Models are Training-free Motion Interpreter and Controller

Zeqi Xiao
Yifan Zhou
Shuai Yang
Xingang Pan

Video generation primarily aims to model authentic and customized motion across frames, making understanding and controlling the motion a crucial topic. Most diffusion-based studies on video motion focus on motion customization with training-based paradigms, which, however, demands substantial training resources and necessitates retraining for diverse models. Crucially, these approaches do not explore how video diffusion models encode cross-frame motion information in their features, lacking interpretability and transparency in their effectiveness. To answer this question, this paper introduces a novel perspective to understand, localize, and manipulate motion-aware features in video diffusion models. Through analysis using Principal Component Analysis (PCA), our work discloses that robust motion-aware feature already exists in video diffusion models. We present a new MOtion FeaTure (MOFT) by eliminating content correlation information and filtering motion channels. MOFT provides a distinct set of benefits, including the ability to encode comprehensive motion information with clear interpretability, extraction without the need for training, and generalizability across diverse architectures. Leveraging MOFT, we propose a novel training-free video motion control framework. Our method demonstrates competitive performance in generating natural and faithful motion, providing architecture-agnostic insights and applicability in a variety of downstream tasks.

PDF Details DOI

IROS Conference 2023 Conference Paper

Enhancing State Estimation in Robots: A Data-Driven Approach with Differentiable Ensemble Kalman Filters

Xiao Liu
Geoffrey Clark
Joseph Campbell
Yifan Zhou
Heni Ben Amor

This paper introduces a novel state estimation framework for robots using differentiable ensemble Kalman filters (DEnKF). DEnKF is a reformulation of the traditional ensemble Kalman filter that employs stochastic neural networks to model the process noise implicitly. Our work is an extension of previous research on differentiable filters, which has provided a strong foundation for our modular and end-to-end differentiable framework. This framework enables each component of the system to function independently, leading to improved flexibility and versatility in implementation. Through a series of experiments, we demonstrate the flexibility of this model across a diverse set of real-world tracking tasks, including visual odometry and robot manipulation. Moreover, we show that our model effectively handles noisy observations, is robust in the absence of observations, and outperforms state-of-the-art differentiable filters in terms of error metrics. Specifically, we observe a significant improvement of at least 59% in translational error when using DEnKF with noisy observations. Our results underscore the potential of DEnKF in advancing state estimation for robotics. Code for DEnKF is available at https://github.com/ir-lab/DEnKF

Details

IROS Conference 2023 Conference Paper

Projecting Robot Intentions Through Visual Cues: Static vs. Dynamic Signaling

Shubham D. Sonawani
Yifan Zhou
Heni Ben Amor

Augmented and mixed-reality techniques harbor a great potential for improving human-robot collaboration. Visual signals and cues may be projected to a human partner in order to explicitly communicate robot intentions and goals. However, it is unclear what type of signals support such a process and whether signals can be combined without adding additional cognitive stress to the partner. This paper focuses on identifying the effective types of visual signals and quantify their impact through empirical evaluations. In particular, the study compares static and dynamic visual signals within a collaborative object sorting task and assesses their ability to shape human behavior. Furthermore, an information-theoretic analysis is performed to numerically quantify the degree of information transfer between visual signals and human behavior. The results of a human subject experiment show that there are significant advantages to combining multiple visual signals within a single task, i. e. , increased task efficiency and reduced cognitive load.

Details

JBHI Journal 2023 Journal Article

Trustworthy Data and AI Environments for Clinical Prediction: Application to Crisis-Risk in People With Depression

Yamiko Joseph Msosa
Arturas Grauslys
Yifan Zhou
Tao Wang
Iain Buchan
Paul Langan
Steven Foster
Michael Walker

Depression is a common mental health condition that often occurs in association with other chronic illnesses, and varies considerably in severity. Electronic Health Records (EHRs) contain rich information about a patient's medical history and can be used to train, test and maintain predictive models to support and improve patient care. This work evaluated the feasibility of implementing an environment for predicting mental health crisis among people living with depression based on both structured and unstructured EHRs. A large EHR from a mental health provider, Mersey Care, was pseudonymised and ingested into the Natural Language Processing (NLP) platform CogStack, allowing text content in binary clinical notes to be extracted. All unstructured clinical notes and summaries were semantically annotated by MedCAT and BioYODIE NLP services. Cases of crisis in patients with depression were then identified. Random forest models, gradient boosting trees, and Long Short-Term Memory (LSTM) networks, with varying feature arrangement, were trained to predict the occurrence of crisis. The results showed that all the prediction models can use a combination of structured and unstructured EHR information to predict crisis in patients with depression with good and useful accuracy. The LSTM network that was trained on a modified dataset with only 1000 most-important features from the random forest model with temporality showed the best performance with a mean AUC of 0. 901 and a standard deviation of 0. 006 using a training dataset and a mean AUC of 0. 810 and 0. 01 using a hold-out test dataset. Comparing the results from the technical evaluation with the views of psychiatrists shows that there are now opportunities to refine and integrate such prediction models into pragmatic point-of-care clinical decision support tools for supporting mental healthcare delivery.

Details DOI

EAAI Journal 2023 Journal Article

VIKOR method for Pythagorean hesitant fuzzy multi-attribute decision-making based on regret theory

Nian Zhang
Yifan Zhou
Jin Liu
Guiwu Wei

In reality, influenced by fuzzy information and irrational behavior, decision-makers are typically difficult to make decisions. Therefore, how to comprehensively express the evaluation information and accurately quantify the psychological behavior becomes a primary key to improve the efficiency of decision-making. Aiming at multi-attribute decision-making problem with completely unknown weight information and Pythagorean hesitate fuzzy evaluation value, a VIKOR method based on regret theory is proposed. Firstly, the weights are determined from two levels of alternative and attribute. Secondly, the relative closeness decision matrix is constructed by TOPSIS method. Then, the VIKOR method is used to calculate the values of group utility and individual regret based on regret perception value, which can describe the ranking of alternatives. Finally, the availability and effectiveness of this method are proved by sensitivity and comparative analysis. In conclusion, the proposed method not only considers the compromise preference under Pythagorean hesitant fuzzy environment, but also takes into account regret psychologic behavior of decision-makers.

Details DOI

IROS Conference 2020 Conference Paper

Practical Verification of Neural Network Enabled State Estimation System for Robotics

Wei Huang 0035
Yifan Zhou
Youcheng Sun
James Sharp
Simon Maskell
Xiaowei Huang 0001

We study for the first time the verification problem on learning-enabled state estimation systems for robotics, which use Bayes filter for localisation, and use deep neural network to process sensory input into observations for the Bayes filter. Specifically, we are interested in a robustness property of the systems: given a certain ability to an adversary for it to attack the neural network without being noticed, whether or not the state estimation system is able to function with only minor loss of localisation precision? For verification purposes, we reduce the state estimation systems to a novel class of labelled transition systems with payoffs and partial order relations, and formally express the robustness property as a constrained optimisation objective. Based on this, practical verification algorithms are developed. As a major case study, we work with a real-world dynamic tracking system that uses a Kalman filter (a special case of the Bayes filter) to localise and track a ground vehicle. Its perception system, based on convolutional neural networks, processes a high-resolution Wide Area Motion Imagery (WAMI) data stream. Experimental results show that our algorithms can not only verify the robustness of the WAMI tracking system but also provide useful counterexamples.

Details

ICRA Conference 2020 Conference Paper

Reliability Validation of Learning Enabled Vehicle Tracking

Youcheng Sun
Yifan Zhou
Simon Maskell
James Sharp
Xiaowei Huang 0001

This paper studies the reliability of a real-world learning-enabled system, which conducts dynamic vehicle tracking based on a high-resolution wide-area motion imagery input. The system consists of multiple neural network components - to process the imagery inputs - and multiple symbolic (Kalman filter) components - to analyse the processed information for vehicle tracking. It is known that neural networks suffer from adversarial examples, which make them lack robustness. However, it is unclear if and how the adversarial examples over learning components can affect the overall system-level reliability. By integrating a coverage-guided neural network testing tool, DeepConcolic, with the vehicle tracking system, we found that (1) the overall system can be resilient to some adversarial examples thanks to the existence of other components, and (2) the overall system presents an extra level of uncertainty which cannot be determined by analysing the deep learning components only. This research suggests the need for novel verification and validation methods for learning-enabled systems.

Details