检索结果-内蒙古大学图书馆

2023 Australasian Conference on Robotics and Automation, ACRA 2023

作者： Lin, Zihan Cruz, Francisco Sandoval, Eduardo Benitez School of Computer Science and Engineering University of New South Wales Sydney Australia Escuela de Ingeniería Universidad Central de Chile Santiago Chile School of Art and Design Creative Robotics Lab University of New South Wales Sydney Australia

Emotion recognition plays a crucial role in various domains of human-robot interaction. In long-term interactions with humans, robots need to respond continuously and accurately, however, the mainstream emotion recognition methods mostly focus on short-term emotion recognition, disregarding the context in which emotions are perceived. Humans consider that contextual information and different contexts can lead to completely different emotional expressions. In this paper, we introduce self context-aware model (SCAM) that employs a two-dimensional emotion coordinate system for anchoring and re-labeling distinct emotions. Simultaneously, it incorporates its distinctive information retention structure and contextual loss. This approach has yielded significant improvements across audio, video, and multimodal. In the auditory modality, there has been a notable enhancement in accuracy, rising from 63.10% to 72.46%. Similarly, the visual modality has demonstrated improved accuracy, increasing from 77.03% to 80.82%. In the multimodal, accuracy has experienced an elevation from 77.48% to 78.93%. In the future, we will validate the reliability and usability of SCAM on robots through psychology experiments. © 2023 Australasian Robotics and Automation Association. All rights reserved.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

GitFL: Uncertainty-Aware Real-Time Asynchronous Federated Learning Using Version Control 44

GitFL: Uncertainty-Aware Real-Time Asynchronous Federated Le...

引用

44th IEEE Real-Time Systems Symposium, RTSS 2023

作者： Hu, Ming Xia, Zeke Yan, Dengke Yue, Zhihao Xia, Jun Huang, Yihao Liu, Yang Chen, Mingsong School of Computer Science and Engineering Nanyang Technological University Singapore MoE Engineering Research Center of SW/HW Co-Design Tech. and App. East China Normal University China East China Normal University Moe International Joint Lab of Trustworthy Software China

ISBN: (纸本)9798350328578

As a promising distributed machine learning paradigm that enables collaborative training without compromising data privacy, Federated Learning (FL) has been increasingly used in large-scale A IoT (Artificial Intelligence of Things) system design. However, due to the lack of efficient management of straggling devices, existing FL methods greatly suffer from the problems of long response time (e.g., training and communication latency) and low inference accuracy. Things become even worse when taking various uncertain factors (e.g., network delays, performance variances caused by process variation) existing in AIoT scenarios into account. To address this issue, this paper proposes a novel asynchronous FL framework named GitFL, whose implementation is inspired by the famous version control system Git. Unlike traditional FL, the cloud server of GitFL maintains a master model (i.e., the global model) together with a set of branch models indicating the trained local models committed by selected devices, where the master model is updated based on both all the pushed branch models and their version information, and only the branch models after the pull operation are dispatched to devices. By using our proposed Reinforcement Learning (RL)-based device selection mechanism, a pulled branch model with an older version will be more likely to be dispatched to a faster and less frequently selected device for the next round of local training. In this way, GitFL enables both effective controls of model staleness and adaptive load balance of versioned models among straggling devices, thus avoiding performance deterioration while ensuring real-time performance. Comprehensive experimental results on well-known models and datasets show that, compared with state-of-the-art asynchronous and synchronous FL methods, GitFL can achieve up to 2.64X training acceleration and 7.88 % inference accuracy improvements in various uncertain scenarios. © 2023 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Image processing with deep-learning and transfer learning for cutting tool degradation monitoring

引用

Procedia CIRP 2025年 132卷 50-55页

作者： Lorenzo Colantonio Lucas Equeter Hugo Giovannelli Pierre Dehombreux Saïd Mahmoudi François Ducobu Machine Design and Production Engineering Lab University of Mom Place du pare 20 7000 Mons Belgium Computer Science Unit University of Mons Place du parc 20 7000 Mons Belgium

Monitoring the degradation of cutting tools is of utmost importance in the manufacturing world. Tools with substantial wear fail to produce high-quality parts in terms of geometry, residual stress, and surface finish. Furthermore, replacing tools in a non-optimal manner can lead to increased production costs and downtime. Therefore, monitoring the condition of the tool is essential to avoid these additional costs and ensure good production quality. This article explores various classification models, specifically VGG19, EfficientNetV2, and Vision Transformers. These models classify the state of tools using their images. Using transfer learning, a comparison of the best-performing artificial intelligence-based image analysis models is conducted to identify those most suitable for monitoring cutting tools. A comparative analysis of their generalizability, performance and explainability is realized. The model with the best performance is VGG19 with an accuracy of 94%, followed by EfficientNetV2 and ViT with an accuracy of 87%. A full comparison of these results is carried out.

关键词： Cutting Tool Degradation Monitoring Deep-Learning Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Turning to Information Theory to Bring in-Memory Computing into Practice

IEEE BITS the Information Theory Magazine

引用

IEEE BITS the Information Theory Magazine 2023年第3期3卷 64-77页

作者： Dupraz, Elsa Leduc-Primeau, Francois Cai, Kui Dolecek, Lara Lab-STICC UMR CNRS IMT Atlantique Brest29238 France Polytechnique Montreal Department of Electrical Engineering MontrealQCH3T 1J4 Canada Singapore University of Technology and Design Science Mathematics and Technology Cluster Singapore487372 Singapore UCLA Department of Electrical and Computer Engineering Los AngelesCA90095 United States

This article explores the emerging field of in-memory computing, which has the potential to significantly improve energy efficiency in many signal processing and machine learning applications. In-memory computing systems are impacted by various sources of noise and perturbations that can affect their computation accuracy. Therefore, this article aims to identify the key challenges to be addressed from an information-theoretic point of view in this area. It first identifies relevant computation structures and noise models from the literature of hardware implementation, and then reviews existing works in information theory and error-correction for in-memory computing. Finally, it identifies key open avenues for establishing information-theoretic foundations of in-memory computing systems, and for providing insightful design rules leading to highly energy-efficient computing systems. © 2021 IEEE.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Interactions Beyond the Pandemic: Lessons Learned from Large-scale Emergency Remote Teaching in Higher Education 25

Interactions Beyond the Pandemic: Lessons Learned from Large...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Matin Yarmand Haowei Li Nadir Weibel Computer Science and Engineering & The Design Lab UC San Diego La Jolla California USA Graduate School of Education University of Pennsylvania Philadelphia Pennsylvania USA

ISBN: (纸本)9798400713941

Online education - given the enhanced access for diverse populations and flexible participation - has been a topic of interest for many computer science and learning science researchers. The sudden shift to online settings during the COVID-19 Emergency Remote Teaching (ERT) provided a valuable opportunity to examine the use of educational technologies on a global scale with various digital readiness skills, beyond many past works that relied on small lab studies. Following a PRISMA-inspired methodology grounded on Moore's three types of classroom interaction, this descriptive review investigates 22 empirical research papers published during the COVID-19 ERT era focused on higher-education online classrooms. We explore the empirical evidence reported in the collected corpus, and given how ERT remains a likely future occurrence, we suggest key directions for future research, including a new learning paradigm that centralizes and augments Learner-Content interaction to balance between flexibility and structure of online learning. © 2025 Copyright held by the owner/author(s).

关键词： Online Classroom

来源：评论

学校读者我要写书评

暂无评论

Data Reconstruction from Gradient Updates in Federated Learning 4th

Data Reconstruction from Gradient Updates in Federated Lea...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zhang, Xiaoxue Li, Junhao Zhang, Jianjie Yan, Jijie Zhu, Enmin Chen, Kongyang School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou China Pazhou Lab Guangzhou China Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Wuxi China

ISBN: (纸本)9783031200953

Federated learning has become an emerging technology to protect data privacy in the distributed learning area, by keeping each client user’s data locally. However, recent work shows that client users’ data might still be stolen (or reconstructed) directly from gradient updates. After exploring the attack and defense techniques of these data reconstruction methods, we discover that the attacker cannot steal the victim’s data unless it has prior knowledge about the victim’s data size. Thus, the attacker can hardly reconstruct any useful information without these prior knowledge. In this paper, we provide a novel data reconstruction method to obtain a high-dimensional compressed data from the gradient updates, without these prior knowledge. Experiment results show that our reconstructed data can be used to attack the model, with high attack accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Data Leakage with label Reconstruction in Distributed Learning Environments 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zhang, Xiaoxue Zhou, Xiuhua Chen, Kongyang School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou China Pazhou Lab Guangzhou China Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Wuxi China

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

Distributed learning is commonly applied for the high demands of computation resources while training models with large-scale data. However, existing solutions revealed that it may lead to information leakage of private data. Attackers are able to reconstruct data via minimizing the difference between shared gradients and fake gradients that are produced by themselves. This is so-called data leakage attack from gradients. We find that, in many cases, such attack can only obtain random noises or extreme fuzzy information, which are quite different from the raw data. To deal with this problem, we exploit the gradient updates as well as their labels during the parameter-server training, and discover significant information losses during the label coding. Thus, in our method, we reconstruct the labels of samples with a fine-grained method, and we recover the raw inputs with these processed labels. We test our method on different datasets (i.e. CIFAR100 dataset and solid color images) and obtained the reconstructed results which are obviously clearer than the ones of the state-of-the-arts. The results prove the effectiveness of our algorithm in fixing defects to some extent as well. Extensive experiments are also conducted to explore defense strategies against data leakage. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

What Did My Car Say? Impact of Autonomous Vehicle Explanation Errors and Driving Context On Comfort, Reliance, Satisfaction, and Driving Confidence 25

What Did My Car Say? Impact of Autonomous Vehicle Explanatio...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Robert A Kaufman Aaron Broukhim David Kirsh Nadir Weibel Cognitive Science University of California San Diego La Jolla California USA Computer Science & Engineering University of California San Diego San Diego California USA Cognitive Science University of California San Diego San Diego California USA Computer Science and Engineering & The Design Lab UC San Diego La Jolla California USA

ISBN: (纸本)9798400713941

Explanations for autonomous vehicle (AV) decisions may build trust, however, explanations can contain errors. In a simulated driving study (n = 232), we tested how AV explanation errors, driving context characteristics (perceived harm and driving difficulty), and personal traits (prior trust and expertise) affected a passenger's comfort in relying on an AV, preference for control, confidence in the AV's ability, and explanation satisfaction. Errors negatively affected all outcomes. Surprisingly, despite identical driving, explanation errors reduced ratings of the AV's driving ability. Severity and potential harm amplified the negative impact of errors. Contextual harm and driving difficulty directly impacted outcome ratings and influenced the relationship between errors and outcomes. Prior trust and expertise were positively associated with outcome ratings. Results emphasize the need for accurate, contextually adaptive, and personalized AV explanations to foster trust, reliance, satisfaction, and confidence. We conclude with design, research, and deployment recommendations for trustworthy AV explanation systems. © 2025 Copyright held by the owner/author(s).

关键词： Autonomous Vehicles

来源：评论

学校读者我要写书评

暂无评论

Broadening Participation through Physical Computing: Replicating Sensor-Based Programming Workshops for Rural Students in Sri Lanka

arXiv

引用

arXiv 2025年

作者： Meegammana, Poornima Suriyaarachchi, Hussel Denny, Paul Nanayakkara, Suranga Faculty of Engineering and Design University of Auckland Auckland New Zealand School of Computer Science University of Auckland Auckland New Zealand Augmented Human Lab National University of Singapore Singapore

In today’s digital world, computing education offers critical opportunities, yet systemic inequities exclude under-represented communities, especially in rural, under-resourced regions. Early engagement is vital for building interest in computing careers and achieving equitable participation. Recent work has shown that the use of sensor-enabled tools and block-based programming can improve engagement and self-efficacy for students from under-represented groups, but these findings lack replication in diverse, resource-constrained settings. This study addresses this gap by implementing sensor-based programming workshops with rural students in Sri Lanka. Replicating methods from the literature, we conduct a between-group study (sensor vs. non-sensor) using Scratch and real-time environmental sensors. We found that students in both groups reported significantly higher confidence in programming in Scratch after the workshop. In addition, average changes in both self-efficacy and outcome expectancy were higher in the experimental (sensor) group than in the control (non-sensor) group, mirroring trends observed in the original study being replicated. We also found that using the sensors helped to enhance creativity and inspired some students to express an interest in information and communications technology (ICT) careers, supporting the value of such hands-on activities in building programming confidence among under-represented groups. Copyright © 2025, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

LibAMM: empirical insights into approximate computing for accelerating matrix multiplication 24

LibAMM: empirical insights into approximate computing for ac...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xianzhi Zeng Wenchao Jiang Shuhao Zhang National Engineering Research Center for Big DataTechnology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China and Nanyang Technological University Singapore University of Technology and Design National Engineering Research Center for Big DataTechnology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798331314385

Matrix multiplication (MM) is pivotal in fields from deep learning to scientific computing, driving the quest for improved computational efficiency. Accelerating MM encompasses strategies like complexity reduction, parallel and distributed computing, hardware acceleration, and approximate computing techniques, namely AMM algorithms. Amidst growing concerns over the resource demands of large language models (LLMs), AMM has garnered renewed focus. However, understanding the nuances that govern AMM's effectiveness remains incomplete. This study delves into AMM by examining algorithmic strategies, operational specifics, dataset characteristics, and their application in real-world tasks. Through comprehensive testing across diverse datasets and scenarios, we analyze how these factors affect AMM's performance, uncovering that the selection of AMM approaches significantly influences the balance between efficiency and accuracy, with factors like memory access playing a pivotal role. Additionally, dataset attributes are shown to be vital for the success of AMM in applications. Our results advocate for tailored algorithmic approaches and careful strategy selection to enhance AMM's effectiveness. To aid in the practical application and ongoing research of AMM, we introduce LibAMM —a toolkit offering a wide range of AMM algorithms, benchmarks, and tools for experiment management. LibAMM aims to facilitate research and application in AMM, guiding future developments towards more adaptive and context-aware computational solutions.

关键词：

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：