检索结果-内蒙古大学图书馆

11th International Conference on Mechatronics and Robotics engineering, ICMRE 2025

作者： Attar, Hani Sharrab, Yousef Smadi, Saja Jbaily, Safa Zarqa University Faculty of Engineering Zarqa Jordan University of Business and Technology College of Engineering Jeddah21448 Saudi Arabia Isra University Department of Data Science and Artificial Intelligence Amman Jordan Yarmouk University Dept. Computer Science Irbid Jordan

ISBN: (纸本)9798331509293

Applying Machine Learning (ML) models for Arabic text classification is a growing research field that has recently raised a large number of research. Generally, classifying text involves selecting a category based on its content from a list of pre-established categories. data classification is among the most popular Natural Language Processing (NLP) activities. Moreover, automatic article classifications, such as the Single-label Arabic News Articles dataset (SANAD), are desperately needed to improve the retrieval of the requested data, which this paper investigates. The ML leverages large datasets to improve efficiency;indeed, by locating focal spots within the text, the learning mechanisms facilitate attention tools better suited for handling lengthy texts. The proposed work employs a dataset of 7,000 articles of separately classified Arab news items and then breaks them into seven categories of 1,000 news stories each: politics, education, sports, religion, culture, finance, and medicine. The investigated SANAD consists of three primary datasets from three news portals: Akhbarana, AlArabiva, and AlCtrl. Finally, to obtain trustable information, this study implements a variety of Conventional ML techniques, K-Nearest Neighbor (KNN), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Logistic Regression model to classify the investigated dataset. Our results show that the suggested solution outperformed the analytical search in the Arabic language in terms of accuracy, whereas the Logistic Regression model shows the best results among the seven utilized publicly available dataset classifications. © 2025 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Classification of Awareness in Disorders of Consciousness Using Common Spatial Pattern 13

Classification of Awareness in Disorders of Consciousness Us...

引用

13th International Winter Conference on Brain-Computer Interface, BCI 2025

作者： Lee, Chaewon Lee, Sunho Annen, Jitka Jeong, Ji-Hoon Massimini, Marcello Casarotto, Silvia Boly, Melanie Bodart, Olivier Thibaut, Aurore Rosanova, Mario Laureys, Steven Gosseries, Olivia Lee, Minji Dept. Data Science The Catholic University of Korea Bucheon Korea Republic of Dept. Biomedical Software Engineering The Catholic University of Korea Bucheon Korea Republic of Dept. GIGA-Research & Neurology University and University Hospital of Liege Liege Belgium Dept. Data Analysis University of Ghent GhentB9000 Belgium Dept. Computer Science Chungbuk National University Cheongju Korea Republic of Dept. Biomedical and Clinical Sciences "L. Sacco" University of Milan Milan Italy Wisconsin Institute for Sleep and Consciousness Dept. Psychiatry University of Wisconsin Madison United States Coma Science Group GIGA-Consciousness GIGA Research Center University of Liège Liège Belgium Centre du Cerveau Neurology department University Hospital of Liège Liège Belgium

ISBN: (纸本)9798331521929

Advances in intensive care have improved the survival rate of patients with severe acute brain injury, but diagnostic errors for patients with disorders of consciousness are still high. Accurate diagnosis of these patients is very important because effective treatment can vary depending on the diagnosis. In this study, we propose a framework for classifying unresponsive wakefulness syndrome and minimally conscious state, focusing on awareness. In particular, power spectral density and common spatial patterns were used together, considering that spatial information is a key feature in consciousness. The 16 patients with unresponsive wakefulness syndrome and 14 with minimally conscious state underwent resting-state electroencephalography measurements. In addition, we compared the performance by utilizing each frequency (delta, theta, alpha, beta, gamma bands) related to consciousness. As a result, the highest accuracy of 95.06% was achieved by the EEGNet classifier, especially in the beta frequency band. We demonstrated that spatial information is very important in consciousness, as we observed that classification performance improved when common spatial patterns were used. These results provide insight into various frameworks for diagnosing patients with disorders of consciousness and may help patients survive by increasing the diagnosis rate in the future. © 2025 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning for Smart Healthcare Using SDN-Driven Edge Computing

Personalized Federated Learning for Smart Healthcare Using S...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Basu, Deborsi Chaudhary, Ritu Ghosh, Uttam Datta, Raja G. S. Sanyal School of Telecommunications Indian Institute of Technology Kharagpur India Indian Institute of Technology Dept. of Electronics and Electrical Communication Engineering Kharagpur India School of Applied Computational Sciences Dept. of Computer Science and Data Science Mmc TN United States

ISBN: (纸本)9798331504847

The advancement in distributed Federated Learning (FL) techniques is transforming next-generation edge computing, especially in e-Helathcare systems where data integrity and security are critical concerns. Collecting, processing and analyzing such substantial medical data is highly challenging due to their non-identical and versatile nature. Conventional FL approaches often show unsatisfactory and inaccurate results while operating on those data. Traditional FL methods also lack optimal dynamic management mechanisms for edge devices in ehealthcare, which is crucial to ensure that only authorized devices participate in handling any system failures and new registrations. To tackle such important aspects, in this work, we propose a personalized FL technique to handle abrupt label shifts among clients' data. The proposed approach further targets to achieve personalized models for local edge clients. A statistical batch normalization is proposed on customized edge servers, keeping the data specificity intact. To make the proposed system more secure and robust, a Software Defined Network-based (SDN-based) centralized server is used that allows only authorized and efficient edge clients to participate. The proposed comprehensive experiments on two healthcare datasets demonstrate better accuracy than traditional FL methods with enhanced security and privacy. © 2025 IEEE.

关键词： mHealth

来源：评论

学校读者我要写书评

暂无评论

Behavioral and Hybrid Anomaly Detection Techniques for Enhanced Fraud Prevention in E-Commerce Transactions

Behavioral and Hybrid Anomaly Detection Techniques for Enhan...

引用

Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA), International Conference on

作者： Sumanth R Praveenkumar S Challagidad L Lakshmaiah Shilpashree S Surekha R Sakhare Jyothi V Kulkarni Dept. of Computer Science Engineering (Data Science) Nagarjuna College Of Engineering and Technnology Bangalore India Dept. of Computer Science Engineering Nagarjuna College Of Engineering and Technnology Bangalore India Dept. of Electronics and Telecommunication Engineering A G Patil Institute Of Technnology Solapur India

ISBN: (数字)9798331525439

ISBN: (纸本)9798331525446

This paper is designed to develop an automated fraud detection system for e-commerce by leveraging user behavior analysis and hybrid anomaly detection models. As e-commerce grows rapidly, fraud, which poses a huge financial risk and damages brand reputation, is also increasing. Modern fraud detection methods are often code-based or business-centric, limiting their ability to transform fraud strategies. This paper proposes a Behavior and Hybrid Anomaly Detection Model (BHADM) which integrates various data, including usage patterns, transaction details, and historical data, to increase accuracy. The BHAD model that combines vulnerability detection, formality testing, and risk scoring is then used to assess the probability of fraud for each transaction. Based on the risk score calculation, the system triggers alerts and suspicious transactions can be flagged or blocked. In addition, a study is ongoing to monitor performance and update the model to adapt to new fraud models. This method not only improves detection capability, but also maintains the performance of the operation, making it suitable for urgent applications in high-frequency e-commerce environments. The application process provides a unique, flexible and effective way to reduce e-commerce fraud transactions.

关键词： Adaptation models Analytical models Accuracy Transforms Fraud Telecommunication computing Electronic commerce Security Anomaly detection Testing

来源：评论

学校读者我要写书评

暂无评论

Multi-view Learning for the Identification of Risky Users in Dynamic Social Networks

arXiv

引用

arXiv 2025年

作者： Benedetti, Francesco Pellicani, Antonio Pio, Gianvito Ceci, Michelangelo Dept. of Computer Science University of Bari Bari Italy Dept. of Computer Science University of Pisa Pisa Italy Data Science Lab National Interuniversity Consortium for Informatics Rome Italy Dept. of Knowledge Technologies Jožef Stefan Institute Ljubljana Slovenia

Technological progress in the last few decades has granted an increasing number of people access to social media platforms such as Facebook, X (formerly Twitter), and Instagram. Consequently, the potential risks associated with these services have also risen due to users exploiting these services for malicious purposes. The platforms have tools capable of detecting and blocking dangerous users, but they primarily focus on the content posted by users and usually overlook additional factors, such as the relationships among users. Another key aspect to consider is that users’ beliefs and interests evolve over time. Therefore, a user who can be considered safe at one moment might later become malicious, and vice versa. This work describes a novel approach to node classification in temporal graphs, aimed at classifying users in social networks. The method was evaluated on a real-world scenario and was compared to a state-of-the-art system that treats the network as a static entity. Experiments showed that taking into account the temporal evolution of the network, in terms of node features and connections, is beneficial. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Optimized Steganographic Technique for 24-Bit Digital Images using Slab Partitioning

An Optimized Steganographic Technique for 24-Bit Digital Ima...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： Pinaki Pratim Acharjya Jayeeta Majumdar Subhabrata Barman Jayashri Deb Sinha Ramsundar Ghorai Arpan Ghosh Dept. of Computer Science and Engineering Haldia Institute of Technology Haldia West Bengal India Dept. of Computer Science and Engineering (Data Science) Haldia Institute of Technology Haldia West Bengal India

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

Based on image slabs and sheets, a novel kind of image steganography method for digital images has been proposed in this research work. Using the binary representation of the pixel, this approach splits the cover image into 24 fixed-size sheets. The secret message's binary counterpart is then incorporated into the cover image. It looks through each sheet's rows and columns to locate the one that most closely matches the secret message's binary counterpart. The row or column's position and how it differs from the message it stores in the LSB slab. Compared to previous ways, the proposed technique somewhat modifies the cover image.

关键词： Image quality Steganography Visualization Digital images Control systems Robustness Slabs

来源：评论

学校读者我要写书评

暂无评论

Predicting Customer Purchase Intent Using Logistic Regression: A data-Driven Approach

Predicting Customer Purchase Intent Using Logistic Regressio...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： C. Rajarajachozhan G. Karthika A. Rajakrishnammal M. Mano P. Nithish Kumar E. Jayahari Dept. of Electronics and Communication Engineering Saveetha Engineering College Chennai Tamil Nadu Dept. of Artificial Intelligence and Data Science Saveetha Engineering College Chennai Tamil Nadu Dept. of Computer Science and Engineering Saveetha Engineering College Chennai Tamil Nadu

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Predicting customer purchase intent is crucial for modern businesses in order to improve engagement, refine marketing strategies, and increase revenue. Conventional rule-based systems encounter difficulties with dynamic and extensive customer data, limiting their flexibility and precision. This project employs a machine learning methodology utilizing logistic regression to forecast customer intent based on demographic, transactional, and behavioral data. The proposed model analyses input features including age, browsing history, and previous purchases, employing sophisticated data preprocessing methods such as One-Hot Encoding and feature scaling to guarantee data integrity. Through hyperparameter tuning and the assessment of critical metrics including accuracy, precision, recall, and Fl-score, the system provides dependable and actionable insights. Real-time predictive capabilities enable businesses to customize customer interactions, facilitating targeted marketing and enhancing customer experience. This project underscores the capacity of predictive analytics to tackle real-world issues, facilitating data-driven decision-making and sustainable business development.

关键词： Logistic regression Adaptation models Accuracy Pipelines Companies Predictive models Real-time systems data models Predictive analytics Business

来源：评论

学校读者我要写书评

暂无评论

An Effective Crop Recommendation using Ensemble Classifier

An Effective Crop Recommendation using Ensemble Classifier

引用

Intelligent data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Ashok Reddy Kandula Jai Srinivas Vadapalli Srinivasa Sai Shanmukha Mannava Sai Seetharam Modugumudi Irfan Mohammad Dept. of Artificial Intelligence & Data Science Seshadri Rao Gudlavalleru Engineering College Gudlavalleru India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Modern expectations for efficiency and sustainability are sometimes not addressed by the existing approaches in the continually changing environment of agricultural activities. In order to fully address these difficulties, research investigates how precision farming practices may be integrated while utilizing technological improvements. Study attempts to estimate optimal crop choices by assessing important characteristics including area, rainfall, temperature, and district-specific data, giving farmers the power to make well-informed and data-driven decisions. Precision farming lowers risks related to climatic unpredictability, increases output, and minimizes resource waste. By using the strategy, encourage resilience and innovation in the agricultural industry while bridging the gap between current farming practices and the sustainable agriculture of the future. Employing advanced algorithms including LR, Ridge Regression, DTs, and classifiers, achieved a remarkable 96% accuracy rate. Additionally, the proposed system offers real-time alerts via email or SMS, delivering timely advice and actionable insights to enhance agricultural sustainability and productivity.

关键词： Productivity Technological innovation Temperature distribution Rain Crops Agriculture Real-time systems Sustainable development Farming Resilience

来源：评论

学校读者我要写书评

暂无评论

Interactive Augmented Reality System for Real- Time Pre-Car Inspection and Maintenance Assistance

Interactive Augmented Reality System for Real- Time Pre-Car ...

引用

Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA), International Conference on

作者： Anitha P DevaVirdha M Dinesh K Akilesh S Abishek R S Jayanitha Jayaprakash Jayadharani Dept. of Computer Science and Engineering Kumaraguru College of Technology Coimbatore TamilNadu Dept. of Artificial Intelligence and Data Science Kumaraguru College of Technology Coimbatore TamilNadu

ISBN: (数字)9798331525439

ISBN: (纸本)9798331525446

Vehicle checking along with upkeep are essential in order to assure safety as well as efficiency, but conventional examination techniques may prove to be cumbersome and need technical knowledge. In order to address this issue, an Interactive Augmented Reality (AR) System is proposed to facilitate pre-car real-time inspection and maintenance assistance. The system utilizes AR technology to monitor as well as examine numerous vehicle parts, such as the horn, dashboard lights, sunroof, cruise control, personal memory options, information display, gear system, air conditioning control, and audio control. With an interactive UI, every component is linked to a virtual button with visual and audio cues, as users receive information and instructions in real time. The system also includes comprehensive animated instructions for engine oil changes, providing accurate step-by-step guidance during required maintenance procedures on it. With the inclusion of real-time monitoring and interactive UI elements, the system enhances user understanding. Also, with audiovisual feedback, the system raises engagement, leading to better educated decisions when testing vehicles. The potential result is pretty much a streamlined inspection procedure, totally guaranteeing core vehicle systems remain in full operating condition prior to usage. This process doesn't only boost vehicle maintenance knowledge, it improves strength and performance, which makes it an effective tool for both work and personal use.

关键词： Visualization Manuals Inspection User interfaces Real-time systems User experience Maintenance Automobiles Augmented reality Automotive engineering

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：