检索结果-内蒙古大学图书馆

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Yuxuan Zhang Miaojing Shi Taiyi Su Hanli Wang Department of Computer Science & Technology Tongji University Shanghai P. R. China Key Laboratory of Embedded System & Service Computing Ministry of Education Tongji University Shanghai P. R. China Department of Control Science & Engineering Tongji University Shanghai P. R. China

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

Incremental few-shot semantic segmentation (IFSS) aims to incrementally expand a semantic segmentation model’s ability to identify new classes based on few samples. However, it grapples with the dual challenges of catastrophic forgetting (due to feature drift in old classes) and overfitting (triggered by inadequate samples in new classes). To address these issues, a novel approach is proposed to integrate pixel-wise and region-wise contrastive learning, complemented by an optimized example and anchor sampling strategy. The proposed method incorporates a region memory and pixel memory designed to explore the high-dimensional embedding space more effectively. The memory, retaining the feature embeddings of known classes, facilitates the calibration and alignment of seen class features during the learning process of new classes. To further mitigate overfitting, the proposed approach implements an optimized example and anchor sampling strategy. Extensive experiments show the competitive performance of the proposed method. The source code of this work can be found in https://***.

关键词： Circuits and systems Semantic segmentation Source coding Semantics Calibration

来源：评论

学校读者我要写书评

暂无评论

A structural equation modeling framework for exploring the industry 5.0 and sustainable supply chain determinants

Supply Chain Analytics

引用

Supply Chain Analytics 2024年 6卷

作者： Jamil, Md. Asfaq Mustofa, Ridwan Hossain, Niamat Ullah Ibne Rahman, S.M. Atikur Chowdhury, Sudipta Department of Industrial Engineering and Management Khulna University of Engineering & Technology Khulna 9203 Bangladesh Engineering Management Department College of Engineering and Computer Science Arkansas State University 72467 AR United States Department of Industrial Manufacturing and System Engineering University of Texas at El Paso 79968 TX United States Department of Mechanical and Industrial Engineering Marshall University Huntington 25755 WV United States

Sustainable Supply Chain and Industry 5.0 are two important concepts reshaping how businesses operate in the modern world. Together, these two concepts drive the advancement of a highly sustainable and robust worldwide economy. Companies are now becoming more sustainable in supply chain management, using technologies like blockchain and co-bots to track the origin of goods, ensure ethical and sustainable sourcing, and work with humans safely and effectively. This study develops a theoretical model highlighting the determinants of Industry 5.0, Sustainable Supply Chain Practices, by combining theoretical frameworks from the manufacturing, supply chain, and information systems literature. The study's analytic sample comprises 342 responses collected from professionals working in the electronics industry's supply chain. Hypotheses were constructed employing deductive reasoning, leveraging insights gleaned from prior research. The study is conducted utilizing the Structural Equation Modeling (SEM) to substantiate the presumed connections among various constructs, namely, Industry 5.0 innovations, Sustainable Supply Chain Practices (SSCP), Sustainable Supply Chain Performance (SCP), and Supply Chain Risks (SCR). The Structural Equation Modeling analysis results show a direct impact of Industry 5.0 technologies through Sustainable Supply Chain Practices can enhance Supply Chain Performance and mitigate Supply Chain Risks. Combining the two paradigms can foster the development of new business models that prioritize sustainability and contribute to a more equitable and environmentally friendly economy that brings positive change for both businesses and society. © 2024 The Authors

关键词： Industry 5.0 Statistical Analysis Structural Equation Modelling Supply Chain Performance Supply Chain Risks Sustainable Supply Chain

来源：评论

学校读者我要写书评

暂无评论

Active Legibility in Multiagent Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Liu, Yanyu Pan, Yinghui Zeng, Yifeng Ma, Biyang Prashant, Doshi School of Automation Central South University No.605 South Lushan Road Hunan Changsha410083 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen China Department of Computer and Information Sciences Northumbria University Newcastle United Kingdom School of Computer Science Minnan Normal University Fujian Zhangzhou China Department of Computer Science University of Georgia AthensGA United States

A multiagent sequential decision problem has been seen in many critical applications including urban transportation, autonomous driving cars, military operations, etc. Its widely known solution, namely multiagent reinforcement learning, has evolved tremendously in recent years. Among them, the solution paradigm of modeling other agents attracts our interest, which is different from traditional value decomposition or communication mechanisms. It enables agents to understand and anticipate others’ behaviors and facilitates their collaboration. Inspired by recent research on the legibility that allows agents to reveal their intentions through their behavior, we propose a multiagent active legibility framework to improve their performance. The legibility-oriented framework allows agents to conduct legible actions so as to help others optimise their behaviors. In addition, we design a series of problem domains that emulate a common scenario and best characterize the legibility in multiagent reinforcement learning. The experimental results demonstrate that the new framework is more efficient and costs less training time compared to several multiagent reinforcement learning algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Chatbot Persona Selection Methodology for Emotional Support

Chatbot Persona Selection Methodology for Emotional Support

引用

SICE Annual Conference

作者： Akihiro Yorita Simon Egerton Carina Chan Naoyuki Kubota Department of Engineering Kwansei Gakuin University Hyogo Japan Department of Computer science & IT La Trobe University VIC Australia Department of Psychology Counselling and Therapy La Trobe University VIC Australia Department of System Design Tokyo Metropolitan University Tokyo Japan

Self-help groups are one way to cope with mental illness. Here, people in similar circumstances come together to provide peer support and help each other. However, some people are not comfortable using such groups. Therefore, it is necessary to investigate the possibility of using robots or other means of support. There are two types of identity: social identity and personal identity. Personal identity is defined as a kind of personality. Social identity is like a persona, a profile, such as a job or position. So far, we have suggested implementing personalities as chatbot identities and adapting the communication method to the user. However, using personalities alone would result in bland content. Therefore, we implement social identity in chatbots and use the chatbot’s personal information to enable the chatbot to speak in a way that is sympathetic to the user.

关键词：

来源：评论

学校读者我要写书评

暂无评论

iGateLink: A Gateway Library for Linking IoT, Edge, Fog, and Cloud Computing Environments 1st

iGateLink: A Gateway Library for Linking IoT, Edge, Fog, and...

引用

1st International Conference on Intelligent and Cloud Computing, ICICC 2019

作者： Mancini, Riccardo Tuli, Shreshth Cucinotta, Tommaso Buyya, Rajkumar Lab School of Computing and Information System The University of Melbourne Melbourne Australia Scuola Superiore Sant’Anna Pisa Italy Department of Computer Science and Engineering Indian Institute of Technology Delhi India

ISBN: (纸本)9789811559709

In recent years, the Internet of Things (IoT) has been growing in popularity, along with the increasingly important role played by IoT gateways, mediating the interactions among a plethora of heterogeneous IoT devices and cloud services. In this paper, we present iGateLink, an open-source Android library easing the development of Android applications acting as a gateway between IoT devices and edge/fog/cloud computing environments. Thanks to its pluggable design, modules providing connectivity with a number of devices acting as data sources or fog/cloud frameworks can be easily reused for different applications. Using iGateLink in two case studies replicating previous works in the healthcare and image processing domains, the library proved to be effective in adapting to different scenarios and speeding up development of gateway applications, as compared to the use of conventional methods. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Surveillance system Utilizing mmWave-FMCW Radar for Restricted Control Area

A Surveillance System Utilizing mmWave-FMCW Radar for Restri...

引用

International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON

作者： Nattakarn Shutimarrungson Seksan Eiadkaew Akkarat Boonpoonga Krit Athikulwongse Suramate Chalermwisutkul Department of Business Computer Mahasarakham Business School Mahasarakham University Maha Sarakham Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand Department of Electrical and Computer Engineering Faculty of Engineering Research Center of Innovation Digital and Electromagnetic Technology (iDEMT) King Mongkut's University of Technology North Bangkok Bangkok Thailand National Electronics and Computer Technology Center National Science and Technology Development Agency Pathumthani Thailand Communication and Smart System Engineering The Sirindhorn International Thai- German Graduate School of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798350381559

ISBN: (纸本)9798350381566

In this paper, we introduce a surveillance system utilizing mmWave-FMCW radar designed for restricted control areas. The experiment, conducted in our laboratory, defines the restricted control area parameters. Employing the TI-IWR6843AOPEVM model, operating at 60–64 GHz, and providing point cloud and Doppler information, we assumed walking paths for testing, partitioning scenarios into four distinct cases to simulate real-world scenarios. system performance evaluation, assessed through confusion matrices, demonstrates an achieved accuracy of up to 76.9%. Notably, errors are mainly caused by multipath effects due to static objects within the testing environment.

关键词： Point cloud compression Measurement Accuracy Surveillance system performance Radar tracking Doppler radar

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Cooperative Robots Based on Adaptive Sentiment Feedback

SSRN

引用

SSRN 2023年

作者： Jeon, Haein Kim, Dae-Won Kang, Bo-Yeong Department of Artificial Intelligence Kyungpook National University Daegu41566 Korea Republic of School of Computer Science and Engineering Chung-Ang University Seoul06974 Korea Republic of Department of Robot and Smart System Engineering Kyungpook National University Daegu41566 Korea Republic of

Human–robot cooperative tasks have gained importance with the emergence of robotics and artificial intelligence technology. In interactive reinforcement learning techniques, robots learn target tasks by receiving feedback from an experienced human trainer. However, most interactive reinforcement learning studies require a separate process to integrate the trainer's feedback into the training dataset, making it challenging for robots to learn new tasks from humans in real-time. Furthermore, the types of feedback sentences that trainers can use are limited in previous research. To address these limitations, this paper proposes a robot teaching strategy that uses deep RL via human–robot interaction to learn table balancing tasks interactively. The proposed system employs Deep Q-Network with real-time sentiment feedback delivered through the trainer's speech to learn cooperative tasks. We designed a novel reward function that incorporates sentiment feedback from human speech in real-time during the learning process. The paper presents an improved reward shaping technique based on subdivided feedback levels and shrinking feedback. This function serves as a guide for the robot to engage in natural interactions with humans and enables it to learn the tasks effectively. Experimental results demonstrate that the proposed interactive deep reinforcement learning model achieved a high success rate of up to 99.06%, outperforming the model without sentiment feedback. © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of FC-RDVM and LDIWM Router Placement Methods for WMNs by WMN-PSODGA Hybrid Simulation system Considering Load Balancing and Chi-Square Distribution of Mesh Clients 1

引用

37th International Conference on Advanced Information Networking and Applications, AINA 2023

作者： Barolli, Admir Sakamoto, Shinji Kulla, Elis Barolli, Leonard Takizawa, Makoto Department of Information Technology Aleksander Moisiu University of Durres L.1 Rruga e Currilave Durres Albania Department of Information and Computer Science Kanazawa Institute of Technology 7-1 Ohgigaoka Ishikawa Nonoichi921-8501 Japan Department of System Management Fukuoka Institute of Technology 3-30-1 Wajiro-Higashi Fukuoka Higashi-Ku811-0295 Japan Department of Information and Communication Engineering Fukuoka Institute of Technology 3-30-1 Wajiro-Higashi Fukuoka Higashi-Ku811-0295 Japan Department of Advanced Sciences Faculty of Science and Engineering Hosei University 3-7-2 Kajino-machi Koganei-shi Tokyo184-8584 Japan

ISBN: (数字)9783031284519

ISBN: (纸本)9783031284502

In this paper, we present WMN-PSODGA hybrid simulation system for optimization of mesh routers in Wireless Mesh Networks (WMNs). We consider Chi-square distribution of mesh clients and compare the results of a Fast Convergence Rational Decrement of Vmax Method (FC-RDVM) with Linearly Decreacing Inertia Weight Method (LDIWM). The simulation results show that FC-RDVM has better load balancing than LDIWM. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： MESH networking

来源：评论

学校读者我要写书评

暂无评论

E-Learning Privacy in the Context of Machine Learning

E-Learning Privacy in the Context of Machine Learning

引用

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： N. Kirubakaran Varadha Rajan S R. Parijatham Ramya Bharathi K P. Jegadeeshwari V. Vijayaraja Chennai Institue Of Technology Chennai India Department Of Computer Science And Business System Chennai Institue Of Technology Chennai India Madha Institute of Engineering and Technology Chennai S. A. Engineering College Chennai India Dr. MGR Educational and Research Institute (Deemed to be University) Chennai India RMK College of Engineering and Technology Chennai

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

The present paper discusses the privacy issues associated with the usage of machine learning in e-learning systems. Although ML is a promising technology that increases personalization and engagement, it also poses significant security concerns in terms of gathering and using sensitive data. E-learning platforms are vulnerable to problems such as breaches, unauthorized access, and misutilization of personal information. The paper addresses two major concerns: recommendation engines and predictive performance systems, which emphasize the weaknesses and shortcomings in current data privacy and protection measures. In an attempt to address these challenges, the paper develops a privacy-preserving framework based on federated learning and data anonymization technologies. Together, these technologies work in the decentralization of data storage and reduction of exposure yet provide personalized experiences. There is a comparative study that will analyze whether such solutions could help improve data privacy and at the same time maintain functionality in ML. Finally, a balance between security and user experience is brought into discussion, but this time it puts emphasis on the need to have personalization without sacrificing privacy. The final result is a framework for privacy that supports the fulfillment of laws like GDPR, while in the meantime maintaining the best of the personalization that this brings with the ML approach so that an effective solution towards modern e-learning systems can be availed.

关键词： Training Data privacy Privacy Electronic learning Federated learning Data breach User experience Information filtering Protection Information integrity

来源：评论

学校读者我要写书评

暂无评论

A systematic Literature Review on Latest Keystroke Dynamics Based Models

引用

IEEE Access 2022年 1-1页

作者： Roy, Soumen Pradhan, Jitesh Kumar, Abhinav Adhikary, Dibya Ranjan Das Roy, Utpal Sinha, Devadatta Pal, Rajat Kumar Department of Computer Science and Engineering University of Calcutta Acharya Prafulla Chandra Roy Siksha Prangan JD-2 Sector - III Saltlake City Kolkata India Department of Computer Science and Engineering Siksha O' Anusandhan Deemed to be University Bhubaneswar Odisha India Department of Computer System Sciences VisvaBharati Santiniketan India

The purpose of this study is to conduct a comprehensive evaluation and analysis of the most recent studies on the implications of keystroke dynamics (KD) patterns in user authentication, identification, and the determination of useful information. Another aim is to provide an extensive and up-to-date survey of the recent literature and potential research directions to understand the present state-of-the-art methodologies in this particular domain that are expected to be beneficial for the KD research community. From January 1st, 2017 to March 13th, 2022, the popular six electronic databases have been searched using a search criterion (keystroke dynamics OR typing pattern) AND (authentication OR verification OR identification). With this criterion, a total of nine thousand three hundred forty-eight results, including duplicates, were produced. However, one thousand five hundred forty-seven articles have been chosen after removing duplicates and preliminary screening. Due to insufficient information, only one hundred twenty-seven high-quality quantitative research articles have been included in the article selection process. We compared and summarised several factors with multiple tables to comprehend the various methodologies, experimental settings, and findings. In this study, we have identified six unique KD-based designs and presented the status of findings toward an effective solution in authentication, identification, and prediction. We have also discovered considerable heterogeneity across studies in each KD-based design for desktops and smartphones separately. Finally, this paper found a few open research challenges and provided some indications for a deeper understanding of the issues and further study. Author

关键词： Authentication

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：