检索结果-内蒙古大学图书馆

IIAI International Conference on Advanced Applied Informatics (IIAIAAI)

作者： Sujan Shrestha Yoji Taniguchi Tetsuo Tanaka Course of Information and computer sciences Graduate school of Engineering Kanagawa Institute of Tehnology Atsugi Japan Department of Information Artificial Intelligence and Data Science Daiichi Institute of Technology Tokyo Japan Dept. of Information and Computer Sciences Faculty of Information Technology Kanagawa Institute of Technology Atsugi Japan

ISBN: (数字)9798350377903

ISBN: (纸本)9798350377910

Shoplifting presents a significant challenge for retailers, leading to substantial financial losses and security concerns. Current surveillance systems effectively identify shoplifting incidents postoccurrence; however, the capability to detect and prevent such activities preemptively remains limited. This research focuses on identifying behaviors that likely precede shoplifting events. To this end, we introduce a novel benchmark dataset, specifically designed for the early detection of suspicious behavior that may lead to shoplifting. This dataset is curated by selecting and segmenting relevant sequences from the UCF101-Crime dataset, encompassing suspicious behavior, actual shoplifting incidents, and normal activities. Our approach addresses the limitations of existing datasets where the brief duration of shoplifting events may skew neural network performance. The dataset includes clips of only a few seconds each, for which we propose a robust neural network architecture combining the strengths of convolutional neural networks (CNN) for efficient feature extraction and Bidirectional long short-term memory (BiLSTM) networks for capturing temporal dependencies within action sequences. Our model achieves an impressive classification accuracy of 86.21 % on the newly created dataset.

关键词： Deep learning Recurrent neural networks Accuracy Surveillance Benchmark testing Feature extraction Convolutional neural networks Security Informatics Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Copy and Move Forged Image Detection by Deep Learning

Copy and Move Forged Image Detection by Deep Learning

引用

Communication & Computing (WCONF), World Conference on

作者： Yogesh Kumar Sharma Senthil Athithan Savya Sachi Ajay Kumar Singh Arpit Jain Suman Devi Department of Computer Science & Engineering Koneru Lakshmaiah Education Foundation Greenfield Vaddeswaram Guntur AP Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of information technology Lalit Narayan Mishra College of Business Management Muzaffarpur Bihar India Allenhouse Institute of Technology Kanpur India Department of Computer Science & Engineering Koneru Lakshmaiah Education Foundation Greenfield Vaddeswaram Guntur A.P. India Department of Computer Science and Engineering Chaudhary Devi Lal University Sirsa Haryana India

Copy-Move forgery detection (CMFD) is one of the most active study topics in blind image forensics. Most known algorithms are based on block and key-point approaches or a mix. Recently, various deep convolutional neural network approaches have been utilised in image classification, image forensics, image hashing retrieval, and other areas, and they have outperformed the previous way. The paper proposes a unique copy-move forgery detection system based on a convolutional neural network. The suggested technique takes a trained model from an extensive database such as ImageNet and minimally modifies the net structure using tiny training examples. The experimental findings indicate that the approach we presented outperforms the counterfeit picture created automatically by the computer using a simple image copy-move operation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Breaking the Familiarity Bias: Employing Virtual Reality Environments to Enhance Team Formation and Inclusion 25

Breaking the Familiarity Bias: Employing Virtual Reality Env...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Fernandez-Espinosa, Mariana Clouse, Kara Sellars, Dylan Tong, Danny Bsales, Michael Alcindor, Sophonie Hubbard, Timothy D Villano, Michael Gómez-Zará, Diego University of Notre Dame Notre DameIN United States Management & Organization University of Notre Dame Notre DameIN United States Department of Psychology University of Notre Dame Notre DameIN United States Computer Science and Engineering University of Notre Dame Notre DameIN United States

ISBN: (纸本)9798400713941

Team closeness provides the foundations of trust and communication, contributing to teams' success and viability. However, newcomers often struggle to be included in a team since incumbents tend to interact more with other existing members. Previous research suggests that online communication technologies can help team inclusion by mitigating members' perceived differences. In this study, we test how virtual reality (VR) can promote team closeness when forming teams. We conducted a between-subject experiment with teams working in-person and VR, where two members interacted first, and then a third member was added later to conduct a hidden-profile task. Participants evaluated how close they felt with their teammates after the task was completed. Our results show that VR newcomers felt closer to the incumbents than in-person newcomers. However, incumbents' closeness to newcomers did not vary across conditions. We discuss the implications of these findings and offer suggestions for how VR can promote inclusion. © 2025 Copyright held by the owner/author(s).

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Report Based Face Detection and Recognition 7

Report Based Face Detection and Recognition

引用

7th Annual International Conference on Network and Information Systems for computers, ICNISC 2021

作者： Ahmed, Hameer Li, Hengjian Dharejo, Fayaz Hussain Laghari, Asif Ali Karim, Shahid University of Jinan Department of Information Science and Engineering Jinan China University of Chinese Academy of Sciences Computer Network Information Center Chinese Academy of Sciences Beijing China Sindh Madressautal Islam University Department of Computer Science Pakistan Barani Institute of Management Science Department of Computer Science Rawalpindi Pakistan

ISBN: (纸本)9781665402323

Face recognition is a computer dynamic that determines the position and size of a human face in a digital image. This study suggests a system that will help you recognize students' faces, know entrance times, and create timing reports with 'smart surveillance and instant reporting. An instant report that displays the admittances results in the form of a graphical report as well as a textual report. © 2021 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Exploring Consumer Behavior in E-Commerce with AI Personalization and Market Trends Analysis Models

Exploring Consumer Behavior in E-Commerce with AI Personaliz...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Gaurav Kumar G. Devayani C Saraswathi R. Melba Kani Sandeep Dongre M. S. Mohamed Mallick School of Computer Application Lovely Professional University Phagwara India Department of Computer Science and Business Systems M.Kumarasamy College of Engineering Karur India School of Management Studies Bannari Amman Institute of Technology Erode India Master of Business Administration Mar Ephraem college of Engineering and Technology Kanyakumari India Symbiosis Institute of Business Management (SIBM) Constituent of Symbiosis International (Deemed University) Nagpur India Department of Computer Science Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology (Deemed to be University) Chennai India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Online retailers must monitor and respond to changing consumer trends to stay competitive. AI-driven customization's revolutionary impact on market trends is the focus of this study on online buying and customer behavior. As AI advances, e-commerce platforms will be able to customize user experiences. Preprocessing, feature extraction, and model training comprise the AI-driven personalization process. Customer data from online marketplaces is collected first. It manages missing values, balance the data, encode categorical variables, scale the features, and minimize the dimensions as part of our thorough data preprocessing to ensure fair and applicable results. To trained the algorithms with CNN and Convolutional LSTM Based on key criteria, the AI model beat LSTM and CNN. It provides personalized insights and recommendations with an average accuracy of 92.03%. Personalized experiences and product suggestions enabled by AI-powered personalization have transformed e-commerce. It's important to use smart algorithms to engage customers and examine large databases. This proposed approach to shows that AI can transform online shopping and improve customer experiences.

关键词： Consumer behavior Accuracy Data preprocessing Transforms Market research Electronic commerce Convolutional neural networks Integrated circuit modeling Artificial intelligence Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Hydraulic System Failure Prediction Method with Limited Failure Data

Hydraulic System Failure Prediction Method with Limited Fail...

引用

International Symposium on computer, Consumer and Control (IS3C)

作者： Cheng-Hui Chen Yung-Kuan Chan Shyr-Shen Yu Department of Computer Science and Engineering National Chung Hsing University Taichung Taiwan Department of Management Information Systems National Chung Hsing University Taichung Taiwan

Hydraulic systems in production equipment are relatively complex, involving various time series sensor data, such as operating sound frequencies and hydraulic pressure. However, fault prediction generally faces the bottleneck of insufficient fault data, leading to a severe imbalance between normal and fault data ratios. This imbalance makes it difficult for prediction models to effectively learn fault trends. In this paper, we propose a synthesis method for time series data to address this issue. The experimental results demonstrate that the synthesized data lead to significant improvements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of moral decision-making and trust dynamics: human reasoning vs. ChatGPT-3 narratives

引用

AI and Ethics 2024年 1-14页

作者： Rehman, Umair Shah, Muhammad Umair Iqbal, Farkhund Fatima, Ramsha Department of Computer Science Western University London Canada Department of Management Sciences Faculty of Engineering University of Waterloo London Canada College of Technological Innovation Zayed University Dubai United Arab Emirates Graduate School of Education University of Pennsylvania Philadelphia USA

As artificial intelligence (AI) becomes increasingly integrated into everyday decision-making, so does the influence of large language models like ChatGPT. While AI systems generate moral judgments, there may be distinct differences between how humans and AI approach moral dilemmas. This study explores these differences by conducting a comparative analysis of moral decision-making narratives produced by human participants and AI, specifically ChatGPT-3. Key evaluation metrics included causality, explicability, and overall satisfaction. Participants were presented with a complex moral dilemma and asked to provide justifications for their decisions, which were then compared with AI-generated responses. Surprisingly, the study found no significant difference in the quality of the explanations produced by ChatGPT-3 and human respondents. In the second phase, we examined the role of verification methods in fostering trust in these explanations. Participants evaluated explanations verified by humans, AI, or left unverified and assigned trust scores accordingly. The results demonstrate that human verification significantly enhances trust in explanations, while AI verification, though beneficial, had a smaller impact. This study underscores the importance of distinguishing between moral and ethical reasoning in AI systems and highlights the role of verification in trust-building.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Attack Detection and Analysis in IoT Environment Data Derived from Intrusion Detection Systems

Improved Attack Detection and Analysis in IoT Environment Da...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： Mahesh Manchanda Dharmesh Dhabliya K. Ranjith Singh Suhas Gupta Srisainath R Yashoda L Computer Science and Engineering Graphic Era Hill University Dehradun Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Information Technology Vishwakarma Institute of Technology Pune India Department of Computer Science Karpagam Academy of Higher Education Coimbatore Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Mechanical Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai School of Management - UG Management JAIN (Deemed to be University) Bangalore Karnataka

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

The interconnection and communication capabilities of many smart gadgets are made possible by the Internet of Things. Despite the practical advantages of the Internet of Things (IoT), it is susceptible to new forms of assaults due to the introduction of new technology. Intrusion detection systems (IDSs) need a lot of resources to determine the kind of assaults due to the complicated networks and vast amounts of data generated by the Internet of Things (IoT). In contrast, most intrusion detection methods are impractical for IoT networks due to the fact that these networks need greater computational resources for attack detection, which are in short supply on IoT devices. As a result, you need an intrusion detection system (IDS) that isn't too heavy yet can still detect emerging threats. In contrast, most intrusion detection methods are impractical for IoT networks due to the fact that these networks need greater computational capacity for attack detection, which are in short supply on IoT devices. As a result, you need an intrusion detection system (IDS) that isn't too heavy yet can still detect emerging threats. This study recommends a combination of Long Short-Term Memory (LSTM) and Random Forest to optimize detection performance while simultaneously reducing network complexity via the efficient elimination of unnecessary features. Applying hold-out, Stratified k-fold cross-validation, as well as percentage split test mode on the CICIDS-2017 dataset MachineLearning CSV version, the suggested IDS is verified with testing and training data. We opted for this dataset since it contains actual data from IoT networks. The suggested hybrid IDS shows promising experimental results for performance enhancement. Recall values average out to 1.000, resulting in an accuracy rating of 99.9%.

关键词： Accuracy Intrusion detection Training data Traffic control Feature extraction Internet of Things Particle swarm optimization Long short term memory Random forests Testing

来源：评论

学校读者我要写书评

暂无评论

A new (p;q)- rung orthopair fuzzy SIR method with a multi-criteria decision-making approach

引用

Granular Computing 2024年第2期9卷

作者： Shahzadi, Gulfam Luqman, Anam Shahzadi, Sundas Deveci, Muhammet Department of Mathematics University of Management and Technology Sialkot Campus Pakistan Division of Science and Technology Department of Mathematics University of Education Lahore Pakistan Department of Industrial Engineering Turkish Naval Academy National Defence University Istanbul Tuzla34942 Turkey Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

In comparison to Fermatean, Pythagorean, and intuitionistic fuzzy sets, (p,q)-rung orthopair fuzzy sets have a wider range of displaying membership grades and can therefore provide more uncertain situations. In this work, the accuracy of (p,q)-rung orthopair fuzzy numbers is investigated using sine trigonometric functions. First, the (p,q)-rung orthopair fuzzy data are extended to the sine trigonometric operational laws (STOLs). In this study, we suggest a novel (p,q)-rung orthopair fuzzy superiority and inferiority ranking (SIR) approach to address the uncertainty group multiple-attribute decision-making (MADM) problem. This strategy handles unclear information, incorporates individual perspectives into group viewpoints, makes conclusions based on many criteria, and ultimately structures a specific decision map. The proposed SIR method utilizes two kinds of information, the superiority and the inferiority information, to obtain two types of flows, including the superiority and the inferiority flows. Then, these flows are utilized to rank the set of alternatives partially or completely. Using sine trigonometric functions and the flexibility of (p,q)-rung orthopair fuzzy sets, novel STOLs have been created. Further, we conduct a case study of the selection of the best journal to demonstrate the feasibility and applicability of the developed technique. The main contributions of this article are as follows: (1) The aggregation operators for (p,q)-rung orthopair fuzzy numbers and their characteristics have been studied under sine trigonometric functions. (2) The SIR approach has been developed under (p,q)-rung orthopair fuzzy sets. The proposed technique is explained through a step-by-step Algorithm. (3) Then, a case study of journal selection is considered to apply the developed technique. (4) The results obtained have been compared with the ranking obtained through various existing techniques. © The Author(s), under exclusive licence to Springer Nature Switzerland AG

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Implementation of ABC & WOA-Based Security Defense Mechanism for Distributed Denial of Service Attacks

Implementation of ABC & WOA-Based Security Defense Mechanism...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Suman Devi Yogesh Kumar Sharma Senthil Athithan Savya Sachi Ajay Kumar Singh Arpit Jain Department of Computer Science and Engineering Chaudhary Devi Lal University Sirsa Haryana India Department of Computer Science & Engineering Koneru Lakshmaiah Education Foundation Guntur AP Department of Computer Science & Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Information Technology Lalit Narayan Mishra College of Business Management Muzaffarpur Bihar India Allen House Institute of Technology India

computer systems are vulnerable to information theft as a result of the extensive use of the internet, which has caused an increase in security defence mechanisms. In order to overcome these theft various approaches have been proposed like Machine Learning, Swarm Intelligent Algorithm, Bayesian-based algorithms etc. For choosing effective and efficacious features and improve the Security Defense Mechanism. In order to lessen Distributed Denial of Service (DDO) assaults, we suggested a novel hybrid classification approach in this study based on Artificial Bee Colony (ABC) and Whale Optimisation Algorithm (WOA). The results are compared with other algorithms. These algorithms have shown promising results.

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：