检索结果-内蒙古大学图书馆

International Conference on Computing and Networking technology (ICCNT)

作者： Avni Garg T. Vanaja Sudhanshu Dev R Thanga Kumar Yashwant S. Ingle N. V. Balaji Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Punjab India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India DSchool of Mangement - UG JAIN (Deemed to be University) Bangalore Karnataka India Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India Department of Computer Science Karpagam Academy of Higher Education Coimbatore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Convolutional Neural Networks (CNNs) have been gaining big interest in packages related to video reputation. This abstract focuses on their application to the recognition events in crowd scenes. Multi-view event popularity is proposed, with the CNN receiving a concatenated two-flow input contemporary pictures and optical waft-primarily based 3-D data from a couple of digi cam views. The CNN parameters are trained and tuned with the use of a multi-view low-stage feature aggregation level. The experiments performed on benchmark datasets demonstrate that the proposed approach gives advanced performance over current algorithms. The improved overall performance is attributed to the blended impact of state-of-the-art multi-view information and stepped forward CNN schooling. Moreover, it is verified that the low-level feature aggregation considerably improves the event’s reputation and overall performance.

关键词： Training Integrated optics Accuracy Computational modeling Optical computing Computer architecture Benchmark testing Optical coupling Digital cameras Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Text-Guided Graph Temporal Modeling for Few-Shot Video Classification

SSRN

引用

SSRN 2024年

作者： Fuqin, Deng Jiaming, Zhon Li, Nannan Lanhui, Fu Jiang, Bingchun Yi, Ningbo Feng, Qi He, Xin Lun, Lam Tin School of Intelligent Manufacturing the Wuyi University Jiangmen China School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology China School of Textile Materials and Engineering the Wuyi University Jiangmen China School of Applied Physics and Materials Science the Wuyi University Jiangmen China School of Mechanical and Electrical Engineering Guangdong University of Science and Technology Dongguan China Shenzhen Vatop Semicon Tech Co. Ltd. Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Science and Engineering The Chinese University of Hong Kong Shenzhen China

Large-scale pre-trained models and graph neural networks have recently demonstrated remarkable success in few-shot video classification tasks. However, they generally suffer from two key limitations: i) the temporal relations between adjacent frames tends to be ambiguous due to the lack of explicit temporal modeling. ii) the absence of multi-modal semantic knowledge in query videos results in inaccurate prototypes construction and an inability to achieve multi-modal temporal alignment metrics. To address these issues, we develop a Text-guided Graph Temporal Modeling (TgGTM) method that consists of two crucial components: a text-guided feature refinement module and a learnable query text-token contrastive objective. Specifically, the former leverages the temporal masking layer to guide the model in learning temporal relationships between adjacent frames. Additionally, it utilizes multi-modal information to refine video prototypes for comprehensive few-shot video classification. The latter addresses the feature discrepancy between multi-modal support features and single-modal query features by aligning a learnable query text-token with corresponding base class text descriptions. Extensive experiments on three commonly used benchmarks demonstrate the effectiveness of our proposed method, which significantly outperforms existing state-of-the-art methods under various settings. A detailed ablation showcases the importance of learning temporal relationships between adjacent frames and obtaining query text-token. The source code and models will be publicly available at https://***/JiaMingZhong2621/TgGTM. © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Implementing hardware primitives based on memristive spatiotemporal variability into cryptography applications

引用

Chip 2023年第1期2卷 33-44页

作者： Bo Liu Yudi Zhao YinFeng Chang Han Hsiang Tai Hanyuan Liang Tsung-Cheng Chen Shiwei Feng Tuo-Hung Hou Chao-Sung Lai Faculty of Information Technology College of MicroelectronicsBeijing Univer-sity of TechnologyBeijing 100124BeijingChina School of Information and Communication Engineering Beijing Information Science&Technology Univer-sityBeijing 100101BeijingChina Artificial Intelligence and Green Technol-ogy Research Center Chang Gung UniversityGuishan Dist.Taoyuan 33302TaiwanChina Department of Electronic Engineering Chang Gung UniversityGuishan Dist.Taoyuan 33302TaiwanChina School of Electrical Engineer-ing and Computer Science The Pennsylvania State UniversityUniversity ParkPA 16802USA Institute of Electronics National Yang Ming Chiao Tung UniversityHsinchu 300TaiwanChina Department of Nephrology Chang Gung Memorial HospitalGuishan Dist.Linkou 33305TaiwanChina Department of Materials Engineering Ming Chi University of TechnologyTaishan Dist.New Taipei City 24301TaiwanChina

Implementing hardware primitives into cryptosystem has become a new trend in electronic ***,with intrinsic stochastic characteristics including the switching voltages,times and energies,as well as the fluctuations of the resistance state over time,could be a naturally good entropy source for cryptographic key *** this study,based on kinetic Monte Carlo Simula-tion,multiple artificial intelligence techniques,as well as kernel density map and time constant analysis,memristive spatiotemporal variability within graphene based conductive bridging RAM(CBRAM)have been synergistically analyzed to verify the inher-ent randomness of the memristive ***,the ran-dom number based on hardware primitives passed the Hamming Distance calculation with high randomness and uniqueness,and has been integrated into a Rivest-Shamir-Adleman(RSA)*** security of the holistic cryptosystem relies both the modular arithmetic algorithm and the intrinsic randomness of the hardware primitive(to be more reliable,the random num-ber could be as large as possible,better larger than 2048 bits as NIST suggested).The spatiotemporal-variability-based random number is highly random,physically unpredictable and machinelearningattack resilient,improving the robustness of the entire cryptosystem.

关键词： Spatiotemporal variability Graphene based memristor RTN True random number generator Rivest-Shamir-Adleman cryptosystem

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Granule Density-Based Outlier Detection with Multi-Scale Granular Balls

arXiv

引用

arXiv 2025年

作者： Gao, Can Tan, Xiaofeng Zhou, Jie Ding, Weiping Pedrycz, Witold The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The School of Artificial Intelligence and Computer Science Nantong University Nantong226019 China The Faculty of Data Science City University of Macau Macau999078 China The Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland The Department of Electrical and Computer Engineering King Abdulaziz University Jeddah Saudi Arabia The Department of Computer Engineering Istinye University Istanbul Turkey

Outlier detection refers to the identification of anomalous samples that deviate significantly from the distribution of normal data and has been extensively studied and used in a variety of practical tasks. However, most unsupervised outlier detection methods are carefully designed to detect specified outliers, while real-world data may be entangled with different types of outliers. In this study, we propose a fuzzy rough sets-based multi-scale outlier detection method to identify various types of outliers. Specifically, a novel fuzzy rough sets-based method that integrates relative fuzzy granule density is first introduced to improve the capability of detecting local outliers. Then, a multi-scale view generation method based on granular-ball computing is proposed to collaboratively identify group outliers at different levels of granularity. Moreover, reliable outliers and inliers determined by the three-way decision are used to train a weighted support vector machine to further improve the performance of outlier detection. The proposed method innovatively transforms unsupervised outlier detection into a semi-supervised classification problem and for the first time explores the fuzzy rough sets-based outlier detection from the perspective of multi-scale granular balls, allowing for high adaptability to different types of outliers. Extensive experiments carried out on both artificial and UCI datasets demonstrate that the proposed outlier detection method significantly outperforms the state-of-the-art methods, improving the results by at least 8.48% in terms of the Area Under the ROC Curve (AUROC) index. The source codes are released at https://***/Xiaofeng-Tan/MGBOD. © 2025, CC BY.

关键词： Granulation

来源：评论

学校读者我要写书评

暂无评论

MPRE: Multi-perspective Patient Representation Extractor for Disease Prediction

MPRE: Multi-perspective Patient Representation Extractor for...

引用

IEEE International Conference on data Mining (ICDM)

作者： Ziyue Yu Jiayi Wang Wuman Luo Rita Tse Giovanni Pau Faculty of Applied Sciences Macao Polytechnic University China Engineering Research Centre of Applied Technology on Machine Translation and Artificial Intelligence of Ministry of Education Macao Polytechnic University China Department of Computer Science and Engineering University of Bologna Italy Department of Computer Science University of California Los Angeles USA

Patient representation learning based on electronic health records (EHR) is a critical task for disease prediction. This task aims to effectively extract useful information on dynamic features. Although various existing works have achieved remarkable progress, the model performance can be further improved by fully extracting the trends, variations, and the correlation between the trends and variations in dynamic features. In addition, sparse visit records limit the performance of deep learning models. To address these issues, we propose the Multi-perspective Patient Representation Extractor (MPRE) for disease prediction. Specifically, we propose Frequency Transformation Module (FTM) to extract the trend and variation information of dynamic features in the time-frequency domain, which can enhance the feature representation. In the 2D Multi-Extraction Network (2D MEN), we form the 2D temporal tensor based on trend and variation. Then, the correlations between trend and variation are captured by the proposed dilated operation. Moreover, we propose the First-Order Difference Attention Mechanism (FODAM) to calculate the contributions of differences in adjacent variations to the disease diagnosis adaptively. To evaluate the performance of MPRE and baseline methods, we conduct extensive experiments on two real-world public datasets. The experiment results show that MPRE outperforms state-of-the-art baseline methods in terms of AUROC and AUPRC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Overview of using of artificial intelligence in Enhancing Security and Privacy in Mobile Social Networks

An Overview of using of Artificial Intelligence in Enhancing...

引用

International Conference on Fog and Mobile Edge Computing (FMEC)

作者： Hussam N. Fakhouri Sadi Alawadi Feras M. Awaysheh Faten Hamad Sawsan Alzubi Mohammad Naser AlAdwan Data Science and Artificial Intelligence Department Faculty of Information Technology University of Petra Amman Jordan Department of Computer Science Blekinge Institute of Technology Karlskrona Sweden University of Tartu Tartu Estonia Sultan Qaboos University Sultanate of Oman The University of Jordan Amman Amman Jordan Tartu University Tartu Estonia Jerash University Jerash Jordan

Mobile Social Networks (MSNs) have emerged as pivotal platforms for communication, information dissemination, and social connection in contemporary society. As their prevalence escalates, so too do concerns regarding security and privacy. This paper presents a furnishes a detailed analysis of these pressing issues and elucidates how artificial intelligence (AI) can be instrumental in addressing them. The study thoroughly explores a spectrum of security and privacy challenges endemic to MSNs, such as data leakage, unauthorized access, cyberstalking, location privacy, and more. Additionally, the investigation expands to encompass problems like impersonation, phishing attacks, malware threats, information overload, user profiling, inadequate privacy policies, third-party application vulnerabilities, and privacy issues related to photos, videos, end-to-end encryption, Wi-Fi connections, and data retention. Each of these issues is dissected in depth, highlighting the potential risks and implications for users. Furthermore, the paper underlines how AI can provide in mitigating these problems, establishing its fundamental role in fortifying the security and privacy of MSNs. This thorough analysis offers valuable insights and feasible solutions using AI to bolster security and privacy in the ever-evolving landscape of Mobile Social Networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of Wearable and Computer Vision Based Approaches to Knee Flexion Angle Measurement

Comparison of Wearable and Computer Vision Based Approaches ...

引用

IST-Africa

作者： Antony Gitau Victor Kulankash Gachathi Wanjema Ciira Wa Maina Centre for Data Science and Artificial Intelligence Dedan Kimathi University of Technology. P.O. BOX - PRIVATE BAG Dedan Kimathi - Nyeri Kenya Dept of Electrical & Electronic Engineering BSc Biomedical Engineering Kenyatta University Nairobi Kenya School of Health Sciences Dedan Kimathi University of Technology Nyeri Kenya

This paper outlines the development of a wearable device to measure knee joint flexion angles and compares its performance to a computer vision based human pose model. The objective is to advance techniques used in measuring joint flexion angles, which have several drawbacks such as relying heavily on the clinician for accuracy while also being invasive as they require physical contact between the patient and orthopaedic specialist. The proposed implementations integrate digital innovation in orthopaedic healthcare while being affordable and easy to deploy, making them marketable to clinicians and patients in developing countries. To evaluate the workability of the implementations, knee flexion angle measurements of a test subject were obtained using both techniques which yielded consistent and comparable flexion angle readings. Further development of this work can have a significant impact on the accessibility and affordability of innovative healthcare monitoring technologies, especially for patients in developing countries.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on the Master-slave Control System of the Fracture Reduction Surgery 12

Study on the Master-slave Control System of the Fracture Red...

引用

12th International Conference on CYBER technology in Automation, Control, and Intelligent Systems, CYBER 2022

作者： Liu, Minghe Sun, Hao Li, Jian Tan, Yinglun Xuan, Bokai Guo, Xin Xu, Yuexuan Ma, Tianyi Ding, Qingsong School of Artificial Intelligence and Data Science and Engineering Research Center of Intelligent Rehabilitation Device and Detection Technology Ministry of Education Hebei University of Technology Tianjin300130 China School of Automation Beijing University of Posts and Telecommunications Beijing100876 China Beijing Key Laboratory of Rehabilitation Technical Aids for Old-Age Disability Key Laboratory of Neuro-functional Information and Rehabilitation Engineering The Ministry of Civil Affairs National Research Center for Rehabilitation Technical Aids Beijing100176 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Aiming at the negative factors brought by environment in fracture reduction surgery, a master-slave control system of the fracture reduction surgery was studied. The system was composed of teleoperation control and master hand operation control. In this paper, the teleoperation mode adopts B/S(Browse/Server) mode. The operator realizes the real-time control of the remote reset robot by accessing the Web, and the working status information of the robot is fed back to the Web interface in real time. In this paper, the design of the fuzzy PID-smith predictor compensation algorithm controller is completed to compensate the network delay in the control process, and the effectiveness of the algorithm is verified through simulation experiments. For the operation control of the master hand, the heterogeneous master hand design was selected in this paper to establish the mapping relationship between the master hand and the reduction robot, and the slave robot was controlled by the inverse kinematics solution of the fracture reduction robot. The Savitzky-Golay least square fitting method was used to solve the problem of physiological tremor during the reduction operation with the main hand. The simulation experiment of this method is carried out. Experimental results show that Savitzky-Golay least square fitting algorithm has good filtering effect. © 2022 IEEE.

关键词： Real time control

来源：评论

学校读者我要写书评

暂无评论

A Literature Review of Machine Learning Techniques for Recommender System In E-Commerce

A Literature Review of Machine Learning Techniques for Recom...

引用

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Samuel-Soma M. Ajibade Muhammed Basheer Jasser Angela Lee Siew Hoong Rex V. Culpable Celestino A. Quirante Arvie L. Dacillo Adedotun O. Adetunla Kayode Akinlekan Akintoye Department of Data Science and Artificial Intelligence School of Engineering and Technology Sunway University No. 5 Jalan Universiti Selangor Darul Ehsan Malaysia Research Centre for Nanomaterials and Energy Technology (RCNMET) Sunway University Selangor Malaysia College of Technology Cebu Technological University Moalboal Cebu Philippines Dept. of Mechanical and Mechatronics Engineering Afe Babalola University Ado Ekiti Nigeria Dept. of Mechanical Engineering Science University of Johannesburg Johannesburg South Africa Department of Computer Science The Federal Polytechnic Ado Ekiti Ekiti State Nigeria

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

The swift expansion of e-commerce has prompted the creation of advanced recommender systems to augment user experience and boost sales. Machine learning techniques have become fundamental for the development of these systems, allowing firms to provide tailored product recommendations based on customer preferences and habits. This research presents a thorough literature assessment of machine learning methodologies utilized in recommender systems, emphasizing their predictive efficacy in the e-commerce sector. We analyze essential methodologies, including collaborative filtering, content-based filtering, hybrid models, and sophisticated techniques such as deep learning. Through the examination of 38 research in the domain, we elucidate the limitations, advantages, and possibilities of machine learning algorithms in delivering precise and scalable suggestions. Our research indicates that hybrid models, which integrate many recommendation strategies, demonstrate significant potential in addressing challenges like the cold start problem and data sparsity. The report delineates prospective research avenues, underscoring the necessity for continued innovation in the integration of machine learning into recommender systems to improve accuracy and customer happiness in e-commerce settings.

关键词： Deep learning Machine learning algorithms Filtering Collaborative filtering Machine learning data models User experience Electronic commerce Recommender systems Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

LogisticsVISTA: 3D Terminal Delivery Services With UAVs, UGVs and USVs Based on Foundation Models and Scenarios engineering

LogisticsVISTA: 3D Terminal Delivery Services With UAVs, UGV...

引用

IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI

作者： Yonglin Tian Fei Lin Xinyuan Zhang Jingwei Ge Yutong Wang Xingyuan Dai Yisheng Lv Fei-Yue Wang State Key Laboratory of Multimodal Artificial Intelligence Systems and State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Department of Engineering Science Faculty of Innovation Engineering Macau University of Science and Technology Macau China University of Chinese Academy of Sciences Beijing China Department of Automation Tsinghua University Beijing China

ISBN: (数字)9798350379167

ISBN: (纸本)9798350379174

Intelligent logistics with autonomous vehicles is promising to improve the efficiency of rapidly expanding delivery systems. However, complex environments, diverse packages, and irregular human interaction have imposed challenges to the application of unmanned delivery vehicles. Combining various forms of vehicles and developing knowledge-driven delivery services have been the key to further facilitating the upgrading of logistics systems. In this paper, we propose an integrated framework named LogisticsVISTA (Logistics on Vehicles with Intelligent Systems for Transport Automation) comprised of UAVs (Unmanned Aerial Vehicles), UGVs (Unmanned Ground Vehicles), and USVs (Unmanned Surface Vehicles) to provide timely and flexible 3D delivery services. In LogisticsVISTA, we design Large language models (LLMs) and large multimodal models (LMMs) for task planning, active perception, autonomous decision, and human-machine interaction. Besides, virtual-real integrated parallel scenarios are constructed to provide the playing ground for embodied agents efficiently and flexibly.

关键词： Human computer interaction Training Three-dimensional displays Foundation models Transportation Transforms Real-time systems Resource management Logistics Testing

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：