检索结果-内蒙古大学图书馆

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Zhu, Yanying Song, Haotian Wu, Kaishun Sun, Min Zhou, Li Guangzhou Thrust of Data Science and Analytics Hong Kong Thrust of Internet of Things Guangzhou China China Mobile Information Technology Shenzhen China

ISBN: (纸本)9798331515966

Accurate fall detection systems are vital to address the global health concern of elderly falls, which often lead to severe injuries, hospitalizations, and fatalities. Since falls can happen at any time in any location, it is imperative to have a comprehensive system that boasts high applicability across a broad range of scenarios, operating seamlessly 24/7. However, within a range of fall detection systems, most of the existing work is built upon mono-modal sensors, which are inevitably inherited and constrained by mono-modal shortages. To overcome the constraints of mono-modal systems, we introduce VRFfall, a novel multi-modal fall detection system that seamlessly fuses mmWave radar and camera technologies. As a system with high generalization capabilities, VRFfall supports both multi-modal and mono-modal inputs with its independent feature extraction pipeline for each modality. Utilizing a cross-modal knowledge transfer design, VRFfall enhances performance with mono-modal input by leveraging fused knowledge from the other modality. Moreover, to ensure optimal fusion decisions under modal discrepancies, VRFfall incorporates an adaptive Modal Quality Assessment Module (MQAM) that dynamically evaluates and fuses features from both modalities. Extensive evaluations using a dataset collected from 20 volunteers across two environments and three conditions have been conducted on VRFfall. The results demonstrate its high performance and excellent generalization across diverse environments and conditions, promising a 24/7 continuous fall detection system. © 2024 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Continual Learning for Adaptable Car-Following in Dynamic Traffic Environments 27

Continual Learning for Adaptable Car-Following in Dynamic Tr...

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Chen, Xianda Tiu, PakHin Han, Xu Chen, Junjie Wu, Yuanfei Zheng, Xinhu Zhu, Meixin Intelligent Transportation Thrust Guangzhou511400 China Data Science and Analytics Thrust Guangzhou China Guangdong Provincial Key Lab of Integrated Communication Sensing and Computation for Ubiquitous Internet of Things China

ISBN: (纸本)9798331505929

The continual evolution of autonomous driving technology requires car-following models that can adapt to diverse and dynamic traffic environments. Traditional learning-based models often suffer from performance degradation when encountering unseen traffic patterns due to a lack of continual learning capabilities. This paper proposes a novel car-following model based on continual learning that addresses this limitation. Our framework incorporates Elastic Weight Consolidation (EWC) and Memory Aware Synapses (MAS) techniques to mitigate catastrophic forgetting and enable the model to learn incrementally from new traffic data streams. We evaluate the performance of the proposed model on the Waymo and Lyft datasets which encompass various traffic scenarios. The results demonstrate that the continual learning techniques significantly outperform the baseline model, achieving 0 % collision rates across all traffic conditions. This research contributes to the advancement of autonomous driving technology by fostering the development of more robust and adaptable car-following models. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Flexible,efficient,and accurate tests for epidemics

引用

science China Mathematics 2024年第8期67卷 1881-1898页

作者： Linjiajie Fang Bing-Yi Jing Shen Ling Qiyue Wang Qing Yang Data Science and Analytics Thrust The Hong Kong University of Science and TechnologyHong KongChina Department of Statistics and Data Science Southern University of Science and TechnologyShenzhen 518055China Department of Mathematics and Statistics Dalhousie UniversityHalifaxNS B 3H 4R 2Canada Department of Mathematics The Hong Kong University of Science and TechnologyHong KongChina

Group testing involves discovering a small subset of distinguished subjects from a large population while efficiently reducing the total number of *** has been widely used for industrial testing,information technology,and biology,especially epidemic ***,in reality,are noisy for the presence of false *** tests are accurate but time-consuming,while others are cheaper but less *** which test to use is constrained by various considerations,such as availability,cost,accuracy,and *** this paper,we propose flexible,efficient,and accurate tests(FEATs).FEATs are based on group testing with simple but careful designs by incorporating ideas such as close contact cliques and repeated *** could dramatically improve the efficiency or accuracy of existing *** example,for accurate but slow tests,the FEAT can improve efficiency multiple times without compromising *** the other hand,for fast but inaccurate tests,the FEAT can sharply reduce the false-negative rate(FNR)and significantly increase *** justifications are *** point out some scenarios where the FEAT can be effectively employed.

关键词： epidemiology control blood testing testing efficiency testing accuracy

来源：评论

学校读者我要写书评

暂无评论

Generating and Evolving Reward Functions for Highway Driving with Large Language Models 27

Generating and Evolving Reward Functions for Highway Driving...

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Han, Xu Yang, Qiannan Chen, Xianda Chu, Xiaowen Zhu, Meixin Data Science and Analytics Thrust Information Hub Guangzhou China Guangdong Provincial Key Lab of Integrated Communication Sensing and Computation for Ubiquitous Internet of Things qyangan Intelligent Transportation Thrust Systems Hub Guangzhou China

ISBN: (纸本)9798331505929

Reinforcement Learning (RL) plays a crucial role in advancing autonomous driving technologies by maximizing reward functions to achieve the optimal policy. However, crafting these reward functions has been a complex, manual process in many practices. To reduce this complexity, we introduce a novel framework that integrates Large Language Models (LLMs) with RL to improve reward function design in autonomous driving. This framework utilizes the coding capabilities of LLMs, proven in other areas, to generate and evolve reward functions for highway scenarios. The framework starts with instructing LLMs to create an initial reward function code based on the driving environment and task descriptions. This code is then refined through iterative cycles involving RL training and LLMs' reflection, which benefits from their ability to review and improve the output. We have also developed a specific prompt template to improve LLMs' understanding of complex driving simulations, ensuring the generation of effective and error-free code. Our experiments in a highway driving simulator across three traffic configurations show that our method surpasses expert handcrafted reward functions, achieving a 22 % higher average success rate. This not only indicates safer driving but also suggests significant gains in development productivity. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MedPipe: End-to-End Joint Search of data Augmentation and Neural Architecture for 3D Medical Image Classification 1

MedPipe: End-to-End Joint Search of Data Augmentation and Ne...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： He, Xin Chu, Xiaowen Hong Kong Baptist University Dept. Computer Science Hong Kong Hong Kong Data Science and Analytics Thrust Guangzhou China

ISBN: (纸本)9798350358780

data augmentation plays a crucial role in deep learning-based medical imaging analysis, but manually designing tailored data augmentation strategies for each dataset is impractical. Although automatic data augmentation (ADA) techniques have been explored, they often focus solely on data augmentation without considering the importance of neural architecture. Similarly, neural architecture search (NAS) methods mainly concentrate on optimizing the neural architecture while overlooking the impact of data augmentation. However, both data augmentation and neural architecture are interrelated and should be considered together. The joint optimization of data augmentation and neural architecture can lead to improved model performance by harnessing the complementary effects of customized data augmentation strategies and compatible neural architectures. Despite this, the seamless integration of data augmentation and neural architecture search remains under-explored. To address this research gap, we propose MedPipe, an approach that enables end-to-end joint search of data augmentation and neural architecture. We introduce a compact data augmentation search space and unify data augmentation and neural architecture into a cohesive network. This allows simultaneous exploration, optimizing their synergy for enhanced performance. Experimental evaluation on nine medical datasets highlights the necessity of the joint search for data augmentation and neural architecture, demonstrating the superior performance of our approach. Our work opens up possibilities for future applications in diverse medical domains. © 2023 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

How Generative-AI can be Effectively used in Government Chatbots

arXiv

引用

arXiv 2023年

作者： Lin, Zeteng Data Science and Analytics Thrust China

With the rapid development of artificial intelligence and breakthroughs in machine learning and natural language processing, intelligent question-answering robots have become widely used in government affairs. This paper conducts a horizontal comparison between Guangdong Province's government chatbots, ChatGPT, and Wenxin Ernie, two large language models, to analyze the strengths and weaknesses of existing government chatbots and AIGC technology. The study finds significant differences between government chatbots and large language models. China's government chatbots are still in an exploratory stage and have a gap to close to achieve "intelligence." To explore the future direction of government chatbots more deeply, this research proposes targeted optimization paths to help generative AI be effectively applied in government chatbot conversations. Copyright © 2023, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

AI-Generated Content for Academic Visualization and Communication in Maker Education 3

AI-Generated Content for Academic Visualization and Communic...

引用

3rd International Conference on Educational Technology, ICET 2023

作者： Xing, Qingqing Zheng, Chenghong Zhu, Nan Yip, David The Hong Kong University of Science and Technology College of Education Sciences Guangzhou China The Hong Kong University of Science and Technology Data Science and Analytics Thrust Guangzhou China The Hong Kong University of Science and Technology Innovation Policy and Entrepreneurship Thrust Guangzhou China The Hong Kong University of Science and Technology Computational Media and Arts Thrust Guangzhou China

ISBN: (纸本)9798350302332

Collaborative learning in higher education, such as the emerging makerspaces, has contributed to research on innovation and participant expertise. However, there is little research on knowledge management in makerspaces or how learners transfer their individual tacit knowledge in the collaborative space. In addition, the functionality of maker education to promote individualized and personalized learning still needs to be explored. This study is based on Chinese STEM graduate students' experiences with project-based learning in a Maker Education environment to test how AIGC tools help to acquire and transfer students' individual tacit knowledge. The sample was formed from 266 MPhil students taking the "Design Thinking and Effective Academic Communication"course in their first academic year at the world's first interdisciplinary university in southern China. The AIGC teaching intervention was based on the four-phase knowledge management model. In a cycle of socialization-externalization-combination-internalization,learners first explore expertise in a research area in project teams and formulate their research interest. Then, storytelling, analogy, and metaphor data were first used to assess students' abilities to communicate their research topic in text and images on an A4 paper. The subsequent AIGC-supported instructional intervention consisted of 20-minute instructional Sprints with two instructors from Computational Media Arts and Academic Communication over two consecutive weeks. The students' work shows that combining AIGC tools allows for a higher quality of visualization of tacit knowledge in the combination phase -. © 2023 IEEE.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

DAHA: Accelerating GNN Training with data and Hardware Aware Execution Planning 50th

DAHA: Accelerating GNN Training with Data and Hardware Aware...

引用

50th International Conference on Very Large data Bases, VLDB 2024

作者： Li, Zhiyuan Jian, Xun Wang, Yue Shao, Yingxia Chen, Lei The Hong Kong University of Science and Technology Hong Kong Shenzhen Institute of Computing Sciences China Beijing University of Posts and Telecommunications China Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou Hong Kong

Graph neural networks (GNNs) have been gaining a reputation for effective modeling of graph data. Yet, it is challenging to train GNNs efficiently. Many frameworks have been proposed but most of them suffer from high batch preparation cost and data transfer cost for mini-batch training. In addition, existing works have limitations on the device utilization pattern, which results in fewer opportunities for pipeline parallelism. In this paper, we present DAHA, a GNN training framework with data and hardware aware execution planning to accelerate end-to-end GNN training. We first propose a data and hardware aware cost model that is lightweight and gives accurate estimates on per-operation time cost for arbitrary input and hardware settings. Based on the cost model, we further explore the optimal execution plan for the data and hardware with three optimization strategies with pipeline parallelism: (1) group-based in-turn pipelining of batch preparation neural training to explore more optimization opportunities and prevent batch preparation bottlenecks;(2) data and hardware aware rewriting for intra-batch execution planning to improve computation efficiency and create more opportunities for pipeline parallelism;and (3) inter-batch scheduling to further boost the training efficiency. Extensive experiments demonstrate that DAHA can consistently and significantly accelerate end-to-end GNN training and generalize to different message-passing GNN models. © 2024, VLDB Endowment. All rights reserved.

关键词： Cost benefit analysis

来源：评论

学校读者我要写书评

暂无评论

Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits 38

Almost Minimax Optimal Best Arm Identification in Piecewise ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hou, Yunlong Tan, Vincent Y.F. Zhong, Zixin Department of Mathematics National University of Singapore Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore Singapore Data Science and Analytics Thrust Hong Kong University of Science and Technology Guangzhou China

We propose a novel piecewise stationary linear bandit (PSLB) model, where the environment randomly samples a context from an unknown probability distribution at each changepoint, and the quality of an arm is measured by its return averaged over all contexts. The contexts and their distribution, as well as the changepoints are unknown to the agent. We design Piecewise-Stationary Ε-Best Arm Identification+ (PSΕBAI+), an algorithm that is guaranteed to identify an Ε-optimal arm with probability ≥ 1 − δ and with a minimal number of samples. PSΕBAI+ consists of two subroutines, PSΕBAI and NAÏVE Ε-BAI (NΕBAI), which are executed in parallel. PSΕBAI actively detects changepoints and aligns contexts to facilitate the arm identification process. When PSΕBAI and NΕBAI are utilized judiciously in parallel, PSΕBAI+ is shown to have a finite expected sample complexity. By proving a lower bound, we show the expected sample complexity of PSΕBAI+ is optimal up to a logarithmic factor. We compare PSΕBAI+ to baseline algorithms using numerical experiments which demonstrate its efficiency. Both our analytical and numerical results corroborate that the efficacy of PSΕBAI+ is due to the delicate change detection and context alignment procedures embedded in PSΕBAI. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beyond Non-Degeneracy: Revisiting Certainty Equivalent Heuristic for Online Linear Programming

arXiv

引用

arXiv 2025年

作者： Chen, Yilun Wang, Wenjia China Data Science and Analytics Thrust Information Hub The Hong Kong University of Science and Technology Guangzhou China

The Certainty Equivalent (CE) heuristic is a widely-used algorithm for various dynamic resource allocation problems in OR and OM. Despite its popularity, existing theoretical guarantees of CE are limited to settings satisfying restrictive fluid regularity conditions, particularly, the non-degeneracy conditions, under the widely held belief that the violation of such conditions leads to performance deterioration and necessitates algorithmic innovation beyond CE. In this work, we conduct a refined performance analysis of CE within the general framework of online linear programming. We show that CE achieves uniformly near-optimal regret (up to a polylogarithmic factor in T) under only mild assumptions on the underlying distribution, without relying on any fluid regularity conditions. Our result implies that, contrary to prior belief, CE effectively beats the curse of degeneracy for a wide range of problem instances with continuous conditional reward distributions, highlighting the distinction of the problem’s structure between discrete and non-discrete settings. Our explicit regret bound interpolates between the mild (log T)2 regime and the worst-case √T regime with a parameter β quantifying the minimal rate of probability accumulation of the conditional reward distributions, generalizing prior findings in the multisecretary setting. To achieve these results, we develop novel algorithmic analytical techniques. Drawing tools from the empirical processes theory, we establish strong concentration analysis of the solutions to random linear programs, leading to improved regret analysis under significantly relaxed assumptions. These techniques may find potential applications in broader online and offline stochastic decision-making contexts. Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：