检索结果-内蒙古大学图书馆

IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)

作者： Maorong Wang Hao Yu Ling Xiao Toshihiko Yamasaki Dept. Inf. Commun. Eng. The University of Tokyo Tokyo Japan Dept. of Computer Science Boston University Boston USA

Online knowledge distillation (KD) has drawn increasing attention in recent years. However, little attention has been paid to the capacity gap that exists between the models in the online KD paradigm. In this work, we investigate the impact of the capacity gap and experimentally verified that a large capacity gap can have a detrimental effect on performance. Moreover, to address this issue, we propose Auxiliary Branch assisted Mutual Learning (ABML), which leverages auxiliary branches to mitigate performance deterioration caused by the capacity gap. Experimental results show that our ABML can significantly improve the performance of online KD even when a capacity gap is present. Our code is available at https://***/maorongwang/ABML.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Managing Human Factors in Automated Vehicle Development: Towards Challeng.s and Practices

arXiv

引用

arXiv 2024年

作者： Muhammad, Amna Pir Knauss, Eric Bärgman, Jonas Knauss, Alessia Dept. of Computer Science and Eng. Chalmers | University of Gothenburg Gothenburg Sweden Dept. of Mechanics and Maritime Sciences Chalmers University of Technology Gothenburg Sweden Zenseact AB Gothenburg Sweden

Due to the technical complexity and social impact, automated vehicle (AV) development challeng.s the current state of automotive eng.neering practice. Research shows that it is important to consider human factors (HF) knowledge when developing AVs to make them safe and accepted. This study explores the current practices and challeng.s of the automotive industries for incorporating HF requirements during agile AV development. We interviewed ten industry professionals from several Swedish automotive companies, including HF experts and AV eng.neers. Based on our qualitative analysis of the semi-structured interviews, a number of current approaches for communicating and incorporating HF knowledge into agile AV development and associated challeng.s are discussed. Our findings may help to focus future research on issues that are critical to effectively incorporate HF knowledge into agile AV development. © 2024, CC BY.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Ethics in AI-Driven Brain Tumor Detection 3

Ethics in AI-Driven Brain Tumor Detection

引用

3rd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2025

作者： Kaushik, Priyanka Rawat, Priyanka Afzal, Mohd. Faiz Saranraj, G. Dwivedi, Shivansh Kaliappan, S. Chandigarh University Dept. of Cse (AIML) CSE-APEX Chandigarh India Chandigarh University Dept. of Computer Science & Eng. Chandigarh India Sustainable Health Care Centre Kerala India Dhanalakshmi Srinivasan College Dept. of Ai & Ds Coimbator India Chandigarh University Dept. of Cse (AIML) Chandigarh India Lovely Professional University Division of Research and Development Punjab India

ISBN: (纸本)9798331521691

The paper addresses the application of artificial intelligence in healthcare and specifically focuses on detecting brain tumors. The study then looks at some of the ethical and regulatory challeng.s to implementing AI-based systems for this critical medical task. Application of the principles of medical ethics-that is, beneficence, non-maleficence, autonomy, and justice-in conjunction with existing regulatory frameworks tries to shed light on what can be expected with the integration of AI in healthcare. The study draws on case studies and current practices to provide a detailed analysis of ethical and regulatory issues raised by AI-driven detection of brain tumors. The aim is to present actionable recommendations that would help address such complexities while ensuring patient safety, equity, and privacy and foster the responsible adoption of AI technologies in medical settings. © 2025 IEEE.

关键词： AI Beneficence Brain Tumor Detection Ethical Considerations Healthcare Medical Ethics Non- Maleficence Regulatory Frameworks

来源：评论

学校读者我要写书评

暂无评论

Acoustic measurement framework for audio systems based on structured periodic test signals 12

Acoustic measurement framework for audio systems based on st...

引用

12th IEEE Global Conference on Consumer elec.ronics, GCCE 2023

作者： Kawahara, Hideki Yatabe, Kohei Sakakibara, Ken-Ichi Mizumachi, Mitsunori Kitamura, Tatsuya Wakayama University Cntr. Innovative Research and Liaison Wakayama Japan Tokyo University of Agriculture and Technology Dept. Electrical Engineering and Computer Science Tokyo Japan Health Sciences University of Hokkaido Dept. Speech-Language-Hearing Therapy Hokkaido Japan Kyushu Institute of Technology Dept. Electrical and Electronic Eng. Kitakyushu Japan Konan University Dept. Intelligence and Informatics Kitakyushu Japan

ISBN: (纸本)9798350340181

We introduce a framework for acoustic measurement that allows everyday sounds into acoustic measurement test signals and standard test signals such as swept-sine and MLS (Maximum Leng.h Sequence). The framework extends our extended Time-Stretched-Pulse generation method and safeguarding method for any signals to make them appropriate for acoustic measurement. The extension uses the periodic nature of discrete Fourier transform combined with orthogonalization based on the Walsh-Hadamerd matrix. This framework enables simultaneous measurement of acoustic attributes such as linear time-invariant response, signal-dependent non-linear and time-invariant components, and random time-varying components. We also discuss and demonstrate practical scenarios in classes and laboratory lessons using tools developed based on the proposed framework. © 2023 IEEE.

关键词： Audio systems

来源：评论

学校读者我要写书评

暂无评论

Natural Language Instructions for Intuitive Human Interaction with Robotic Assistants in Field Construction Work

arXiv

引用

arXiv 2023年

作者： Park, Somin Wang, Xi Menassa, Carol C. Kamat, Vineet R. Chai, Joyce Y. Dept. of Civil and Env. Engineering University of Michigan United States Dept. of Construction Science Texas A&M University United States Dept. of Elec. Engineering and Computer Science University of Michigan United States

The introduction of robots is widely considered to have significant potential of alleviating the issues of worker shortage and stagnant productivity that afflict the construction industry. However, it is challeng.ng to use fully automated robots in complex and unstructured construction sites. Human-Robot Collaboration (HRC) has shown promise of combining human workers’ flexibility and robot assistants’ physical abilities to jointly address the uncertainties inherent in construction work. When introducing HRC in construction, it is critical to recognize the importance of teamwork and supervision in field construction and establish a natural and intuitive communication system for the human workers and robotic assistants. Natural language-based interaction can enable intuitive and familiar communication with robots for human workers who are non-experts in robot programming. However, limited research has been conducted on this topic in construction. This paper proposes a framework to allow human workers to interact with construction robots based on natural language instructions. The proposed method consists of three stages: Natural Language Understanding (NLU), Information Mapping (IM), and Robot Control (RC). Natural language instructions are input to a language model to predict a tag for each word in the NLU module. The IM module uses the result of the NLU module and building component information to generate the final instructional output essential for a robot to acknowledge and perform the construction task. A case study for drywall installation is conducted to evaluate the proposed approach. The results of the NLU and IM modules show high accuracy over 99%, allowing a robot to perform tasks accurately for a given set of natural language instructions in the RC module. The obtained results highlight the potential of using natural language-based interaction to replicate the communication that occurs between human workers within the context of human-robot teams. Copyri

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Blockchain Revolution: Empowering the elec.ric Vehicle Industry through Integration and Case Study Analysis

Blockchain Revolution: Empowering the Electric Vehicle Indus...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Ajmery Sultana Md Moniruzzaman Lian Zhao Dept. of Computer Science Algoma University Brampton Canada Dept. of Software Engineering Lakehead University Thunder Bay Canada Dept. of Electrical Computer and Biomedical Eng. Toronto Metropolitan University Toronto Canada

In the rapidly evolving landscape of elec.ric vehicles (EVs), blockchain technology emerges as a transformative force, empowering the industry with enhanced security, transparency, and efficiency in transactions and energy management. However, the successful integration of blockchain technology in the context of EV is still in its infancy. Thus, this work aims to provide a comprehensive study of this young field from a broader perspective. We first discuss the integration process of blockchain technology in the EV domain. Then we explore the potential applications of blockchain technology in enhancing the efficiency, reliability, and sustainability of EV infrastructure and discuss some of the promising research in each category. Finally, we provide a typical application scenario and its specific embodiment in the EV infrastructure and strive to shed light on all-inclusive future research directions, which may facilitate the integration of blockchain technology in the EV ecosystem from theory to practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Data Visualization Techniques for Large Datasets

Exploring Data Visualization Techniques for Large Datasets

引用

Advances in Computing, Communication and Networking (ICAC2N), International Conference on

作者： Shailendra Singh Sikarwar Bhawesh Kumawate Arun Vaishnav Love Kumar Seema Bushra S. Teitsana Devi Dept. of Computer Science PGV College Gwalior India Dept. of CSE Madhav University Pindwara India Dept. of Computer Eng. & Applications Mangalayatan University Beswan India Deen Academics Lingayas Vidyapeeth Faridabad India Dept. of CSE Dhanalakshmi Srinivasan University Coimbatore India

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

In a world of Big Data, being able to easily visualize large data sets can make the difference between understanding & wisely judging that data - or not. Big Data is the word with which not many people are aware of, but these success stories make sure that organizations sit back & take notice to what this large data can show then when it collated together over time from different sources. The methods traditionally used for visualization rarely fit into the Big-Data world because they do not have scalability, given that volume (huge amounts), velocity (high speed), or variety (complex details) are now more prevalent in big-data processing. This paper then explores data visualization techniques that can be used to manage very large datasets, including streaming data visualization, dimensionality reduction (e.g. T-SNE), & hierarchical clustering among other Node XL analyses. In this paper, based on accumulated observations & implementations of these techniques over the years, an extensive review is provided for researchers or practitioners to selec. suitable visualization methodologies that not only suit the scale but also discover patterns in their data. The results highlight the need for enabling tools, methods, & practices to make sense of big data in an interactive visual context that enables better orchestration between complex systems using diverse hardware/software stacks. Additionally, the pros & cons of each method are explained, with real-world use cases & case studies demonstrating their practicality.

关键词： Visualization Technological innovation Reviews Scalability Heuristic algorithms Data visualization Organizations Big Data Software tools Smart phones

来源：评论

学校读者我要写书评

暂无评论

Tunable Antenna-Coupled Intersubband Terahertz (TACIT) Mixer Integrated with Self-complementary Antenna 32

Tunable Antenna-Coupled Intersubband Terahertz (TACIT) Mixer...

引用

32nd International Symposium of Space Terahertz Technology, ISSTT 2022

作者： Yoo, Changyun Kawamura, Jonathan H. West, Ken W. Pfeiffer, Loren N. Karasik, Boris S. Sherwin, Mark S. Physics Dept. Inst. for Terahertz Science and Technology University of California at Santa Barbara Santa BarbaraCA93106 United States Jet Propulsion Laboratory California Institute of Technology PasadenaCA91109 United States Dept. of Elec. Eng. Princeton University PrincetonNJ08544 United States

We are developing a novel THz hot-elec.ron bolometer (HEB) mixer based on a high-mobility 2-dimensional elec.ron gas (2DEG) confined in a single GaAs/AlGaAs quantum well. Named as Tunable Antenna-Coupled Intersubband Terahertz (TACIT) mixer, the device takes advantages of intersubband transitions of the confined 2DEG for efficient, tunable absorption of THz radiation. Here we demonstrate a TACIT mixer integrated with a self-complementary antenna suitable for the broadband operation of the device. We study the tunability in both direct detection and heterodyne detection responses and show that the observed tunability behavior is consistent with our device model based on intersubband transitions. In addition, we study the DC-bias dependence of the noise at 1.4 GHz and show that the noise behavior follows that of a HEB device. © 2022 32nd International Symposium of Space Terahertz Technology, ISSTT 2022 All rights reserved.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

Spatial and Temporal Attention-based emotion estimation on HRI-AVC dataset

arXiv

引用

arXiv 2023年

作者： Subramanian, Karthik Singh, Saurav Namba, Justin Heard, Jamison Kanan, Christopher Sahin, Ferat Dept. Elect. & Microelectronic Eng. Rochester Institute of Technology Rochester United States Dept. Computer Science Rochester Institute of Technology Rochester United States Dept. Computer Science University of Rochester Rochester United States

Many attempts have been made at estimating discrete emotions (calmness, anxiety, boredom, surprise, anger) and continuous emotional measures commonly used in psychology, namely ‘valence’ (The pleasantness of the emotion being displayed) and ‘arousal’ (The intensity of the emotion being displayed). Existing methods to estimate arousal and valence rely on learning from data sets, where an expert annotator labels every image frame. Access to an expert annotator is not always possible, and the annotation can also be tedious. Hence it is more practical to obtain self-reported arousal and valence values directly from the human in a real-time Human-Robot collaborative setting. Hence this paper provides an emotion data set (HRI-AVC) obtained while conducting a human-robot interaction (HRI) task. The self-reported pair of labels in this data set is associated with a set of image frames. This paper also proposes a spatial and temporal attention-based network to estimate arousal and valence from this set of image frames. The results show that an attention-based network can estimate valence and arousal on the HRI-AVC data set even when Arousal and Valence values are unavailable per frame. Copyright © 2023, The Authors. 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

AI4COLLAB: An AI-based Threat Information Sharing Platform

AI4COLLAB: An AI-based Threat Information Sharing Platform

引用

Cyber Security and Resilience (CSR), IEEE International Conference on

作者： Christos Dalamagkas Dimitrios Asimopoulos Panagiotis Radoglou-Grammatikis Nikolaos Maropoulos Thomas Lagkas Vasileios Argyriou Gohar Sargsyan Panagiotis Sarigiannidis Dept. of Computer Science Democritus University of Thrace Kavala GR Public Power Corporation S.A. Athens GR Dept. of Information and Electronic Eng. International Hellenic University Thessaloniki GR MetaMind Innovations Kozani Greece Dept. of Electrical and Computer Eng. University of Western Macedonia Kozani GR Dept. of Networks and Digital Media Kingston University London UK Celesta Advice

ISBN: (数字)9798350375367

ISBN: (纸本)9798350375374

In the rapidly evolving field of cybersecurity, Cyber Threat Intelligence (CTI) sharing has become an essential practice to enhance awareness of emerging threats and enable infrastructure owners to defend against cyber incidents more efficiently. AI4COLLAB introduces a comprehensive CTI sharing platform designed to address the various challeng.s associated with CTI sharing, including data privacy, interoperability, and the speed of information dissemination. AI4COLLAB integrates two major CTI sharing platforms, MISP and OpenCTI, to broaden CTI coverage and leverages advanced AI techniques to automate the detection and anonymization of sensitive information. This ensures compliance with privacy regulations such as the General Data Protection Regulation while maintaining the utility of the shared data. By providing an in-dept. analysis of existing CTI sharing solutions and presenting the innovative features of AI4COLLAB, this paper highlights the platform's potential to significantly improve the efficiency, security, and effectiveness of CTI sharing in the cybersecurity community.

关键词： Protocols Regulation Cyber threat intelligence Information filtering Stakeholders Artificial intelligence Standards

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：