检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Junwei Xiao Lei Deng Zhixiang Chen Xiu Li Baohua Chen Hanxi Yin Shenzhen International Graduate School Tsinghua University Shenzhen China School of Instrument Science and Opto-Electronics Engineering Beijing Information Science and Technology University Beijing China Department of Computer Science The University of Sheffield United Kingdom Department of Automation Tsinghua University Beijing China

Visual anomaly detection methods with localization are critically important for industrial manufacturing quality control. Because of the rarity of anomalies and the irregular variation of anomaly patterns, unsupervised methods have been widely explored. For the anomaly detection and localization tasks, the image reconstruction-based approaches have shown competitive performance. However, reconstruction results of those methods are coarse and visually blurred, which leads to a high rate of false detection and false pixel-level localization. To address those issues, we propose a framework called Dual-Path Re-construction Guided Segmentation Network (DRGS-Net), which determines the abnormal regions by segmenting the anomaly image with its reconstructed result as the reference template. DRGS-Net mainly consists of a novel dual-path reconstruction sub-network and a specifically designed anomaly segmentation sub-network. They are jointly trained end-to-end, with the former fusing texture repair and image reconstruction information to obtain fine-grained reconstruction results and the latter learning a decision boundary between normal and anomalous regions based on reconstruction results. On the standard benchmark dataset MVTecAD and an additional dataset DAGM, DRGS-Net shows competitive performance in image-level detection and achieves outstanding improvement in pixel-level localization. Further experiments with the few samples setting demonstrate that DRGS-Net retains strong performance with only few anomaly-free training images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Twenty Years of Personality Computing: Threats, Challenges and Future Directions

arXiv

引用

arXiv 2025年

作者： Celli, Fabio Kartelj, Aleksandar Ðorðević, Miljan Suhartono, Derwin Filipović, Vladimir Milutinović, Veljko Spathoulas, Georgios Vinciarelli, Alessandro Kosinski, Michal Lepri, Bruno Maggioli SpA Italy Faculty of Mathematics University of Belgrade Serbia School of Electrical Engineering University of Belgrade Serbia School of Computer Science Bina Nusantara University Indonesia Dept. of Information Security Norwegian University of Science and Technology Norway School of Computing Science University of Glasgow United Kingdom Graduate School of Business Stanford University United States Center for Augmented Intelligence Fondazione Bruno Kessler Italy

Personality Computing is a field at the intersection of Personality Psychology and computer science. Started in 2005, research in the field utilizes computational methods to understand and predict human personality traits. The expansion of the field has been very rapid and, by analyzing digital footprints (text, images, social media, etc.), it helped to develop systems that recognize and even replicate human personality. While offering promising applications in talent recruiting, marketing and healthcare, the ethical implications of Personality Computing are significant. Concerns include data privacy, algorithmic bias, and the potential for manipulation by personality-aware Artificial Intelligence. This paper provides an overview of the field, explores key methodologies, discusses the challenges and threats, and outlines potential future directions for responsible development and deployment of Personality Computing technologies. © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Radar-Assisted Predictive Beamforming for UAV-Aided Networks: A Deep-Learning Solution

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Yin, Rui Peng, Jingwei Cai, Yunlong Wu, Celimuge Champagne, Benoit Al-Dhahir, Naofal Hangzhou City University Laboratory for Microwave Spatial Intelligence and Cloud Platform Hangzhou310015 China Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China University of Electro-Communications Graduate School of Informatics & Engineering Japan McGill University Department of Electrical and Computer Engineering MontrealQCH3A 0E9 Canada The University of Texas at Dallas Department of Electrical and Computer Engineering RichardsonTX75080 United States

In the realm of Sixth-Generation (6G) mobile communication systems, unmanned aerial vehicle (UAV) technologies have gained significant attention, particularly within UAV-assisted wireless networks. This paper explores radar-assisted predictive beamforming to enhance communication in such networks. A mobile UAV equipped with multiple antennas and radar functionality is deployed to serve a group of mobile users on the ground. The primary objective is to optimize communication performance, ensuring stable and efficient data transmission rates within a specified time frame, under practical power and flight range constraints. To address this challenging problem, we introduce a novel solution framework that integrates a deep reinforcement learning (DRL) network and a dual-layer deepunfolding network (DUN). By leveraging a two-timescale processing structure, the new framework enables and facilitates the joint optimization of mobile user tracking, transmit beamforming and UAV trajectory. Simulation results confirm the effectiveness of our proposed scheme, demonstrating improvements in movement tracking accuracy and transmission rates. © 1967-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MHMC: Real-Time Hand Motion Capture Using Millimeter-Wave Radar

MHMC: Real-Time Hand Motion Capture Using Millimeter-Wave Ra...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Fan Deng Hao Zhou Peng Xia Zian Wang Xiaoyan Wang Xiang-Yang Li LINKE Lab School of Computer Science and Technology University of Science and Technology of China CAS Key Laboratory of Wireless-Optical Communications University of Science and Technology of China Deqing Alpha Innovation Institute Huzhou Zhejiang China School of Information Science and Technology University of Science and Technology of China Graduate School of Science and Engineering Ibaraki University Ibaraki Japan

Hand motion capture is essential for emerged augmented reality (AR) and virtual reality (VR) applications. We propose MHMC, a real-time hand motion capture system using millimeter-wave (mmWave) radar with the advantages of lighting independence, privacy protection and good user experience. When implementing such a system, we design a novel vertical neural network architecture to infer complex hand motion from limited resolution data of mmWave radar, a vision-based labeling method to acquire adequate labeled data, and effective loss functions to avoid abnormal output. The experimental results demonstrate that MHMC achieves similar accuracy as visionbased methods, along with fast processing speed, i.e., 7. 3ms per frame, for supporting real-time motion capture.

关键词： Privacy Neural networks Lighting Millimeter wave radar Motion capture Real-time systems User experience

来源：评论

学校读者我要写书评

暂无评论

Evaluating edge artificial intelligence-driven supply chain management platforms using collaborative large-scale fuzzy information fusion

引用

Applied Soft Computing 2024年 159卷

作者： Zhang, Chao Zhang, Jingjing Sangaiah, Arun Kumar Li, Deyu Li, Wentao School of Computer and Information Technology Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan Shanxi030006 China International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon College of Artificial Intelligence Southwest University Chongqing400715 China

The rapid development of edge artificial intelligence (AI) has brought about revolutionary changes in supply chain management (SCM). It not only provides real-time data processing capabilities but also accelerates the decision-making process, injecting more innovative elements into SCM. In this context, SCM platforms require new technological developments and effective evaluations, as they collectively drive the efficient coordination of complex business processes. SCM platforms enable the seamless coordination of various supply chain elements, facilitating streamlined operations and enhanced decision-making processes. The evaluation of these platforms not only serves to validate their performance and effectiveness, but also contributes to continual improvements in design and application, and addressing the evolving demands within the realms of global commerce and dynamic market conditions. The ongoing assessment and enhancement of SCM platforms play a crucial role in optimizing resource allocation, improving production efficiency, and fostering adaptability to changing market dynamics. However, the acquisition of assessment data often introduces imprecise data. Additionally, the large-scale nature and bounded rationality of decision-makers (DMs) significantly impact the evaluation of SCM platforms. This article aims to explore a collaborative large-scale information fusion approach and provide a robust fuzzy framework for evaluating SCM platforms. This approach employs a combination of spherical fuzzy sets (SFSs), large-scale group decision-making (LSGDM), behavioral theories and three-way decisions (TWD) to thoroughly explore collaborative large-scale information fusion and its practical application in assessing SCM platforms. It introduces an innovative spherical fuzzy (SF) LSGDM technique and integrates TWD with the inclusion of prospect theory (PT) and regret theory (RT) to mitigate potential decision risks. The developed collaborative large-scale information f

关键词： Supply chain management

来源：评论

学校读者我要写书评

暂无评论

Cloud Quantum Computing Concept and Development: A Systematic Literature Review

引用

Procedia computer science 2021年 179卷 944-954页

作者： Haryono Soeparno Anzaludin Samsinga Perbangsa Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480 Information System Department School of Information Systems Bina Nusantara University Jakarta Indonesia 11480

A cloud quantum computer is a quantum computer that can be accessed in a cloud environment through a network. Today, there are numbers of cloud quantum computing services that can be accessed by users. They are used to solve complex problems that require powerful computing. Different cloud quantum computing services deliver different architecture and performances. In our study, we conducted a research on some services to test and evaluate the performances of different cloud quantum computing services and make a comparison out of it. The test will be conducted using two different methods such as visual programming and qiskit. From the result, we can see that the amount of qubit per backend and shots per run pretty much affect the execution time of a cloud quantum computing. This test will give the users some insight and enables them to decide which cloud quantum computing services deliver better performance or faster execution time based on the specification each cloud quantum computer offers.

关键词： Cloud Quantum Computing Benchmarking Comparison

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Real-Time Multi-Person Pose Detection in Electrical Industrial Safety Scenarios Using YOLOv8-Pose and OpenPose

Comparative Analysis of Real-Time Multi-Person Pose Detectio...

引用

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Shang-Te Tsai Zong-Rong Wu Pin-Hsuan Lin Chin-Hsiung Chen Wei Chien Yu-Cheng Chang School of Art and Design Sanming University Fujian China Department of Technical and Vocational Program in Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan Department of Business Administration National Central University Taoyuan Taiwan Department of Electrical Engineering New Taipei Municipal Tamsui Commercial Industrial Vocational Senior High School New Taipei Taiwan Department of Computer Information and Network Engineering Lunghwa University of Science and Technology Taoyuan Taiwan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

We reviewed the application of modern technology for rapid and accurate multi-person real-time pose detection in the hazardous field of electrical engineering. We focused on two leading pose detection technologies: YOLOv8 and OpenPose. To optimize performance, we integrated these two techniques into the LSTM model for training and investigated frame rates and accuracy.

关键词： Training Accuracy Microcontrollers Neural networks Real-time systems Safety Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Strategic Planning and Knowledge Management Approaches as input to remote area strategic plans: A Case study in Aru Islands Regency Maluku Province 8

Strategic Planning and Knowledge Management Approaches as in...

引用

8th International Conference on ICT for Smart Society, ICISS 2021

作者： Irena Gutandjala, Ilona Harso Supangkat, Suhono Lumban Gaol, Ford Rianti, Benny Bina Nusantara University BINUS Graduate Program-Computer Science Computer Science Department Jakarta11480 Indonesia Bandung Institute of Technology Smart City and Community Innovation Center School of Electrical and Informatics Engineering Bandung Indonesia Information Systems Department BINUS Online Learning Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9781665416979

Knowledge is an important asset in an organization. Aru Islands District is one of the districts in Maluku Province. The Government of Aru Islands District Maluku has a vision and mission as outlined in the Regional Strategic Plan or commonly referred to as RENSTRA. This vision and mission are an activity that requires a policy direction that is planned and integrated with the strategic environment of all related aspects. The strategic plan is then realized with the implementation of the government with regional autonomy which is the modern governance in realizing quality public services, fast, easy, fair and unlimited for the welfare and progress of the region. In this research will be used a strategic approach as input from the analysis with knowledge management and assessment of the condition of Aru district. © 2021 IEEE.

关键词： Strategic planning

来源：评论

学校读者我要写书评

暂无评论

Lightweight Pedestrian Detection through Guided Filtering and Deep Learning 10

Lightweight Pedestrian Detection through Guided Filtering an...

引用

10th IEEE Global Conference on Consumer Electronics, GCCE 2021

作者： Muchtar, Kahlil Saddami, Khairun Bintang, Akhyar Cenggoro, Tjeng Wawan Pardamean, Bens Lin, Chih-Yang Ernita, Tia Universitas Syiah Kuala Department of Electrical And Computer Engineering Aceh Indonesia Universitas Syiah Kuala Department of Electrical And Computer Engineering Aceh Indonesia Bina Nusantara University School of Computer Science Bina Nusantara University Bioinformatics And Data Science Research Center Computer Science Department Jakarta Indonesia Bina Nusantara University BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Bioinformatics And Data Science Research Center Computer Science Department Jakarta Indonesia Yuan-Ze University Department of Electrical And Engineering Taoyuan Taiwan

ISBN: (纸本)9781665436762

In this paper, we propose a novel approach to locate and detect moving pedestrians in a video. Our proposed method first locates the region of interest (ROI) using a background subtraction algorithm based on guided filtering. This novel background subtraction algorithm allows our method to also filter unexpected noises at the same time, which could benefit the performance of our proposed method. Subsequently, the pedestrians are detected using YOLOv3 within the provided ROI. Our experiments showed that the proposed method has a competitive performance in the CDNET2014 dataset with a fast-processing time. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Using Res-Net For Organic and Anorganic Waste Classification

Convolutional Neural Network Using Res-Net For Organic and A...

引用

International Conference of computer science and information Technology

作者： Abba Suganda Girsang Rezky Yunanda Muhammad Edo Syahputra Ezra Peranginangin Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350399080

Convolutional Neural network is state of the art of image recognition or image classification. However to build the robust model using CNN needs many parameters adjusted, and choosing the good combination hyperparameter which impacts taking much computation time. Genetic algorithm is one method metaheuristic which is robust for choosing the combinatorial possible hyperparameter. This model also uses ResNet-50 which is a pretrained model of convolutional neural network that consists 50 layers. By using a pretrained like ResNet-50, it will increase the performance model. CNN-ResNet with efficient genetic algorithm (EGA) to optimize the hyperparameter. The EGA algorithm utilizes transfer learning techniques in its algorithm so that the optimization process on CNN can achieve unified accuracy values quickly. The best performance model optimized using EGA outperformed the ResNet-50 model and the model optimized using GA and VLGA in classifying organic and inorganic materials. The accuracy value obtained from EGA is 97.53% with a loss of 0.08.

关键词： Image recognition Computational modeling Transfer learning Metaheuristics Inorganic materials Iron Classification algorithms

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：