HKBU Faculty of Science

#Article 📜 An Obstacle-Avoidance Motion Planning Method for Redundant Space Robot via Reinforcement Learning by Zeyuan Huang, Gang Chen, Yue Shen, Ruiquan Wang, Chuankai Liu and Long Zhang 🔗 https://lnkd.in/giVv9ufx MDPI; Beijing University of Posts and Telecommunications; Beijing Aerospace Control Center; Chinese Academy of Sciences #redundantspacerobot #reinforcementlearning #nullspace #Abstract On-orbit operation tasks require the space robot to work in an unstructured dynamic environment, where the end-effector’s trajectory and obstacle avoidance need to be guaranteed simultaneously. To ensure the completability and safety of the tasks, this paper proposes a new obstacle-avoidance motion planning method for redundant space robots via reinforcement learning (RL). First, the motion planning framework, which combines RL with the null-space motion for redundant space robots, is proposed according to the decomposition of joint motion. Second, the RL model for null-space obstacle avoidance is constructed, where the RL agent’s state and reward function are defined independent of the specific information of obstacles so that it can adapt to dynamic environmental changes. Finally, a curriculum learning-based training strategy for RL agents is designed to improve sample efficiency, training stability, and obstacle-avoidance performance. The simulation shows that the proposed method realizes reactive obstacle avoidance while maintaining the end-effector’s predetermined trajectory, as well as the adaptability to unstructured dynamic environments and robustness to the space robot’s dynamic parameters.

1

A computer vision-approach for activity recognition and residential monitoring of elderly people https://lnkd.in/g9zmkuyN In this study, we explore a human activity recognition (HAR) system using computer vision for assisted living systems (ALS). Most existing HAR systems are implemented using wired or wireless sensor networks. These systems have limitations such as cost, power issues, weight, and the inability of the elderly to wear and carry them comfortably. These issues could be overcome by a computer vision based HAR system. But such systems require a highly memory-consuming image dataset. Training such a dataset takes a long time. The proposed computer-vision-based system overcomes the shortcomings of existing systems. The authors have used key-joint angles, distances between the key joints, and slopes between the key joints to create a numerical dataset instead of an image dataset. All these parameters in the dataset are recorded via real-time event simulation. The data set has 780,000 calculated feature values from 20,000 images. This dataset is used to train and detect five different human postures. These are sitting, standing, walking, lying, and falling. The implementation encompasses four distinct algorithms: the decision tree (DT), random forest (RF), support vector machine (SVM), and an ensemble approach. Remarkably, the ensemble technique exhibited exceptional performance metrics with 99 ​% accuracy, 98 ​% precision, 97 ​% recall, and an F1 score of 99 ​%. #Assisted living systems #Human activity recognition #Fall detection #Key joint angle #Landmarks #technology #research #innovation

1

Check out this #OA paper, “Research on Animation Character Expression Generation Based on Attention Conditioned Cyclegan”, by Chunling Kong (Zhengzhou University of Industrial Technology, China), featured in the Journal of Cases on Information Technology (JCIT). With advancements in computer vision and AI, deep learning is applied in animation and game design to enhance facial expression realism. This study proposes ACCGAN, an innovative method for automated animated character expression generation and transfer using deep learning. Access the full paper here > https://buff.ly/4eMhOsv #ZhengzhouUniversityofIndustrialTechnology #CharacterExpression #GenerativeAdversarialNetworks

1

#HotPapers Machine learning is leading the way in reshaping healthcare decisions and treatments, and our prestigious researcher’s paper maps the path forward! Professor Jiming Liu, Chair Professor in Computer Science at Hong Kong Baptist University, provides an extensive overview of reinforcement learning (a subfield of machine learning) applications from revolutionising chronic disease treatment to automating medical diagnosis, considering the challenges in the current research and highlighting potential solutions and future research directions. 𝐑𝐞𝐚𝐝 𝐭𝐡𝐞 𝐏𝐚𝐩𝐞𝐫 (published in 𝘈𝘊𝘔 𝘊𝘰𝘮𝘱𝘶𝘵𝘪𝘯𝘨 𝘚𝘶𝘳𝘷𝘦𝘺𝘴): https://lnkd.in/gWzse3DS  🗝 Cluster: Data Analytics and Artificial Intelligence #Cluster_Data_Analytics_and_Artificial_Intelligence #HKBU #ResearchOffice #HKBUResearch #HKBURO #HKBUCOMP #ComputerScience #ReinforcementLearning #MachineLearning #Healthcare #ESI #Clarivate #citations #ACMComputingSurveys #ComputingSurvey HKBU Department of Computer Science ACM Digital Library Shamim Nemati Guosheng Yin

17

Research IEEE Xplore coauthored by Prof. Chen Guoqing from 清华大学经济管理学院 Tsinghua University School of Economics and Management proposed an effective framework to improve the performance of sequential #recommendation models, which many recommender systems are aiming at, by solving the problem that sequentiality of user interactions can vary greatly in different recommendation scenarios. More: bit.ly/3XmJLkB #InnovativeTsinghua

10

#Article Classification of Mental Stress from Wearable Physiological Sensors Using Image-Encoding-Based Deep Neural Network by Sayandeep Ghosh, SeongKi Kim, Muhammad Fazal Ijaz, Pawan Kumar Singh and Mufti Mahmud https://lnkd.in/gkYB-N4H MDPI Jadavpur University Sangmyung University Sejong University Nottingham Trent University #stressdetection #deepneuralnetwork #openaccess #Abstract The human body is designed to experience stress and react to it, and experiencing challenges causes our body to produce physical and mental responses and also helps our body to adjust to new situations. However, stress becomes a problem when it continues to remain without a period of relaxation or relief. When a person has long-term stress, continued activation of the stress response causes wear and tear on the body. Chronic stress results in cancer, cardiovascular disease, depression, and diabetes, and thus is deeply detrimental to our health. Previous researchers have performed a lot of work regarding mental stress, using mainly machine-learning-based approaches. However, most of the methods have used raw, unprocessed data, which cause more errors and thereby affect the overall model performance. Moreover, corrupt data values are very common, especially for wearable sensor datasets, which may also lead to poor performance in this regard. This paper introduces a deep-learning-based method for mental stress detection by encoding time series raw data into Gramian Angular Field images, which results in promising accuracy while detecting the stress levels of an individual. The experiment has been conducted on two standard benchmark datasets, namely WESAD (wearable stress and affect detection) and SWELL. During the studies, testing accuracies of 94.8% and 99.39% are achieved for the WESAD and SWELL datasets, respectively. For the WESAD dataset, chest data are taken for the experiment, including the data of sensor modalities such as three-axis acceleration (ACC), electrocardiogram (ECG), body temperature (TEMP), respiration (RESP), etc.

4

#IJCAI2024 #Panel: Reviewing and Large AI Conferences. In his answer to the question How can we experiment with new ideas for the review process, James Kwok mentioned that he hopes to introduce more reviewer recognition awards to acknowledge the community's efforts. They are also exploring new methods for matching reviewers, including using embeddings. The biggest challenge is scalability, which he sees as a research problem. While we don’t know exactly what will work, we have a wealth of data, and our plan is to test the most promising ideas derived from it.

10

🗓️ Save the Date — last #MDIWorkshop for Fall 2024 is next week 🗓️ Join MDI Postdoc Lucy Qin to explore Privacy through Cryptography. As data is accumulated and consumed at an increasingly massive scale, it is important to consider what data should be protected from who and how. Cryptography offers a variety of techniques that are used for data protection and secure communications. This workshop is open to everyone — no previous experience necessary. Register here ➡️ https://lnkd.in/etRww7f3

2

The Role of AI in Healthcare: https://lnkd.in/gyWuaAbf Amy Juan Li Pauline Ikpa Raúl Hernán Medina Campos Nazir Abbas📈🇦🇪 #health #heathcare #ai #aritificialintelligence #wellness #technology

2

IASS Webinar 40 on 29 May, “An Estimation of Variance of Random Effects to Solve Multiple Problems in Small Area Estimation”, 2:00pm – 3:30 pm (CEST) by Masayo Hirose, Institute of Mathematics for Industry, Kyushu University, Japan. Register: https://lnkd.in/dwQW7-kK 𝗪𝗲𝗯𝗶𝗻𝗮𝗿 𝗮𝗯𝘀𝘁𝗿𝗮𝗰𝘁 For several decades, area-level models have played a critical role in the theory and practice of small area estimation. For an area-level model, we propose a random effects variance estimator that simultaneously (i) improves on the estimation of the related shrinkage factors, (ii) protects empirical best linear unbiased predictors (EBLUP) of the random effects from the common over-shrinkage problem, (iii) avoids complex bias correction in generating strictly positive second-order unbiased mean square error (MSE) estimator either by the Taylor series or single parametric bootstrap method. The idea of achieving multiple desirable properties in an EBLUP method through a suitably devised random effects variance estimator is the first of its kind and holds promise in providing good inferences for random effects under the EBLUP framework. The proposed methodology is also evaluated using a Monte Carlo simulation study and real data analysis. This is a joint work with Prof. Partha Lahiri at the University of Maryland, College Park. 𝗕𝗶𝗼𝗴𝗿𝗮𝗽𝗵𝘆 Masayo Hirose received her Ph.D. degree in Engineering from Osaka University, Japan, in 2014. She is now an assistant professor at the Institute of Mathematics for Industry of Kyushu University, Japan. Her research interests include a model-based Approach to Small Area Estimation, linear mixed Models, and Empirical Bayes estimation. She has been a visiting research scholar at the University of Maryland, College Park, since October 2024. International Statistical Institute - ISI #sae #survey #estimation #variance

17

Welcome to read and share the Highly Accessed Article in 2024. 📢 Title: Activation-Based Pruning of Neural Networks 📢 Authors: Tushar Ganguli and Edwin Chong 📢 Paper link: https://lnkd.in/gHQC-3Hq via MDPI MDPI Colorado State University #networkpruning #machinelearning #dimensionalityreduction

1

Digital Promise's Xin Wei unveils new insights in a study on AI and mathematics education, now published in Frontiers. In “Evaluating ChatGPT-4 and ChatGPT-4o: Performance Insights from NAEP Mathematics Problem Solving," Wei’s assessment of the capabilities of ChatGPT-4 and ChatGPT-4o in solving mathematics problems from the NAEP exams across grades 4, 8, and 12 are highlighted. The findings show that AI has the potential to support instruction in specific mathematical areas, but there remains a need for teacher-mediated strategies in areas where AI is less effective. https://bit.ly/3ZwyFej

14

1 Comment

This paper develops #Cooperative #Federated unsupervised #Contrastive #Learning (#CF-#CL) to facilitate #Federated #learning (#FL) across edge devices with unlabeled datasets. CF-CL employs local device cooperation where either explicit (i.e., raw data) or implicit (i.e., embeddings) information is exchanged through #device-#to-#device (#D2D) communications to improve local diversity. Specifically, the authors introduce a #smart #information #push-#pull methodology for data/embedding exchange tailored to FL settings with either soft or strict data privacy restrictions. Information sharing is conducted through a #probabilistic #importance #sampling #technique at receivers leveraging a carefully crafted reserve dataset provided by transmitters.----Satyavrat Wagle, Seyyedali Hosseinalipour (Ali Alipour), Naji Khosravan, Christopher Brinton More details can be found at this link: https://lnkd.in/ghBxdR95

4