检索结果-内蒙古大学图书馆

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Mwendwa, Gideon Chouhan, Lokesh Etyang, Felix Mandela, Ngaira Gift, Uwineza School of Cyber Security and Digital Forensics National Forensic Sciences University Goa India Cochin University of Science and Technology School of Engineering Department of Computer Science Cochin India School of Cyber Security and Digital Forensics National Forensic Sciences University Gandhinagar India School of Cyber Security and Digital Forensics National Forensic Sciences University Jinja Uganda

ISBN: (纸本)9798331518592

This study investigates the efficacy of machine learning algorithms in detecting and evaluating extremist content on social media platforms, and we employ X, formerly known as Twitter. We therefore utilize Kaggle's dataset that contains 83,000 entries from both extremist and non-extremist posts to compare the performance of four machine learning models, namely Support Vector Machine (SVM), Random Forest, Gradient Boosting, and Naive Bayes. Moreover, we examine a Stacking Classifier that leverages the advantages of all four models. The models were assessed using accuracy, precision, recall, F1 Score, ROC-AUC Score, training duration, and prediction time. The findings of our study revealed that the Support Vector Machine (SVM) algorithm was the most accurate and resilient, whereas Naive Bayes showcased remarkable computing efficiency, rendering it well-suited for real-time detection. The Random Forest and Gradient Boosting algorithms offered a well-balanced approach. Notably, the novel Stacking Classifier outperformed individual models, demonstrating the strength of a hybrid methodology. Hence our study presents a thorough structure for improving the identification of extremist material on social media, thereby providing essential knowledge for creating efficient, immediate detection systems to combat online extremism successfully. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Extraction of Actionable Threat Intelligence from Dark Web Data 5

Extraction of Actionable Threat Intelligence from Dark Web D...

引用

5th International Conference on Control, Communication and Computing, ICCC 2023

作者： Varghese, Varsha Mahalakshmi, S. Senthilkumar, K.B. ER&DCI Institute of Technology Cyber Forensics and Information Security Department of Computer Science & Engineering Thiruvananthapuram India Cyber Security Group Centre for Development of Advanced Computing Thiruvananthapuram India

ISBN: (纸本)9798350334128

Darknet has emerged as an excellent platform for cybercriminals to conduct various illicit activities such as operating a fully functional crypto-currency-based marketplace or maintaining a highly anonymous communication channel. However, it also acts as a source of cyber Threat Intelligence which is the information about the techniques, tactics, or motives of an emerging threat. The life cycle of a Darknet-based cyber Threat Intelligence solution mainly consists of the Collection, Processing, Analysis, and Production of Data from the Darknet. The Collection and Processing stages deal with accumulating information from various dark web pages and transforming the data into some format using a big data system. The Analysis part is integral to the Threat Intelligence schema since it constitutes the extraction of named entities like Organization, Offensive Activity, Tools, etc., and the determination of relationships between these entities. The production stage is like data mining where some knowledge is extracted that can be relevant to an organization under consideration. Such knowledge can mitigate risks and disrupt any targeted cyber-attack campaigns, making cyber Threat Intelligence actionable. In this research, an open-source-intelligence toolset is used to scan and collect data from the dark web forums through crawling and scrapping. The collected data is then ingested into a state-of-the-art NLP model that extracts actionable threat intelligence using Named Entity Recognition. The experimental results indicate that the model could identify HackerIds, tools, software, organizations, and other entities in the discussions of dark web forums with better efficiency and accuracy. This could be used to identify the source of a data leak, the release of new malware, evidence of a new exploit, and other offensive activities. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Enhancing non-profiled side-channel attacks by time-frequency analysis

引用

cybersecurity 2023年第4期6卷 50-75页

作者： Chengbin Jin Yongbin Zhou Institute of Information Engineering Chinese Academy of SciencesBeijingChina School of Cyber Security University of Chinese Academy of SciencesBeijingChina School of Cyber Science and Engineering Nanjing University of Science and TechnologyNanjingChina

Side-channel analysis(SCA)has become an increasing important method to assess the physical security of cryptographic *** the process of SCA,the number of attack data directly determines the performance of *** sufficient attack data,the adversary can achieve a successful ***,in reality,the cryptographic device may be protected with some countermeasures to limit the number of encryptions using the same *** this case,the adversary cannot use casual numbers of data to perform *** performance of SCA will be severely dropped if the attack traces are *** this paper,we introduce wavelet scatter transform(WST)and short-time fourier transform(STFT)to non-profiled side-channel analysis domains,to improve the performance of side-channel attacks in the context of insufficient *** design a practical framework to provide suitable parameters for WST/STFT-based *** the proposed method,the WST/STFT-based SCA method can significantly enhance the performance and robustness of non-profiled *** practical attacks against four public datasets show that the proposed method is able to achieve more robust *** with the original correlation power analysis(CPA),the number of attack data can be reduced by 50–95%.

关键词： Correlation power analysis Side-channel analysis Proposed attack framework Wavelet scatter transform Short-time fourier transform

来源：评论

学校读者我要写书评

暂无评论

The Role of AI in Vehicle-to-Infrastructure Communication for Tolling Systems

The Role of AI in Vehicle-to-Infrastructure Communication fo...

引用

2024 IEEE International Women in engineering (WIE) Conference on Electrical and Computer engineering, WIECON-ECE 2024

作者： Mahalakshmi, S. Baskaran, Nithiya Partheeban, Pachaivanna Krishnara, Kowsalyadevi Arjun, S. Chennai Institute of Technology Department of Computer Science and Engineering Kundrathur Chennai India Chennai Institute of Technology Department Cyber Security Kundrathur Chennai India Chennai Institute of Technology Department Civil EngDepartment Cyber Security Kundrathur Chennai India Sona Institute of Technology Department of Cyber Security Salem India

ISBN: (纸本)9798331535476

The number of vehicles people use is substantial;thus, surveillance must be accurate. License plates are detected and recognized by detecting static and real-time images captured by the camera using OCR technology, Computer vision, and AI in the tool booth and other important roads. This model can be used for many things, such as automated services, increased security, determining whether a car is registered, and identifying and validating vehicles connected to traffic violations. Real-time investigations are part of the automated recognition of license plates and their application to other traffic control and highway surveillance aspects. To detect plates from the images and in real-time video, Use Easy OCR with the license plates to read the plate number, utilize tensor flow object detection to detect and recognize, and save the detected license plate for further analysis and search. © 2024 IEEE.

关键词： Highway traffic control

来源：评论

学校读者我要写书评

暂无评论

Terahertz metasurface biosensor for high-sensitivity salinity detection and data encoding with machine learning optimization based on random forest regression

引用

Optical and Quantum Electronics 2024年第11期56卷 1-39页

作者： Wekalao, Jacob Mandela, Ngaira Department of Optics and Optical Engineering University of Science and Technology of China Hefei230026 China School of Digital Forensics and Cyber Security National Forensic Sciences University Gujarat Gandhinagar382007 India

This research presents a terahertz-based biosensor for high-precision salinity detection, employing a synergistic integration of graphene, gold, and silver in a metasurface configuration. The sensor exhibits exceptional performance characteristics within the 0.6–2 THz frequency range, demonstrating a maximum sensitivity of 571 GHzRIU−1, quality factor of up to 6.107, and a figure of merit of 2.189 RIU−1. Electromagnetic field distribution analysis demonstrates enhanced light-matter interactions, with peak performance observed at 1.6 THz. The investigation further explored the sensor's potential for multilevel data encoding, illustrating its versatility beyond conventional detection methods. Simulation results indicate the efficiency of the proposed sensor which surpasses some of the previous existing designs in terms of sensitivity among other performance parameters. A machine learning approach using random forest regression was employed to predict sensor responses, achieving coefficient of determination (R2) values ranging from 0.88 to 1.00 across multiple parametric studies. This research presents a promising platform for high-precision salinity sensing with potential applications in environmental monitoring, desalination processes, and aquaculture industries. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Aquaculture

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Automated Wheelchair with Lane Detection 6

AI-Powered Automated Wheelchair with Lane Detection

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Abiraj, B. Sethuraman, K. Bethanney Janney, J. Prince Grace Kanmani, P. Sudhakar, T. Ezekiel Jebaraj, S. Sathyabama Institute of Science and Technology Dept. of Biomedical Engineering Chennai India University of Madras M.Sc. Cyber Forensics and Information Security Chennai India

ISBN: (纸本)9798350306613

A wheelchair is a revolutionary assistive mobility aid that improves the flexibility and standard of life for those with mobility limitations. There are many guidance systems for impaired people to navigate against obstacles and other dangers that are confronted rapidly and safely. With the developments of modern techniques, there are many distinct kinds of devices available to help with mobility. The key objective of the proposed study is to create a technologically intelligent wheelchair that can recognize voice, gesture, facial, lane, and gaze in a natural setting for individuals who have mobility impairments. In this paper, an automatic wheelchair based on lane detection is shown, which is made in real-Time using hardware through the use of deep learning algorithms and image manipulation. The device also promotes overall well-being with health-Tracking capabilities. It also offers communication support for those unable to speak. Empower Wheel Chair redefines accessibility, providing users with newfound freedom, convenience, and connection in their daily lives. © 2024 IEEE.

关键词： Face Recognition and Computer vision Gesture Control Lane Detection Voice Recognition Wheelchair

来源：评论

学校读者我要写书评

暂无评论

Assistance for Healthcare Professionals using Hand Gesture Recognition

Assistance for Healthcare Professionals using Hand Gesture R...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Sethuraman, K. Jeffrey Delaperle, S. Bethanney Janney, J. Mohammed Thoufeeq, A. Aadhitya, S. Solomon, Ezekiel Jebaraj Sathyabama Institute of Science and Technology Department of Biomedical Engineering Chennai India University of Madras Cyber Forensics and Information Security Chennai India

ISBN: (纸本)9798350319200

Bedridden and paralyzed individuals need to be continuously taken care of since they find it difficult to convey their requirements due to loss of movement management in their brain. This results in communication disabilities. The proposed system aims to reduce the burden on healthcare providers with a computer-aided system that interprets the hand gestures shown by the patient and displays the needs of the patient on a monitor. Hand gesture recognition involves three processes namely: hand detection, finger detection, and gesture detection. Firstly, Hand gestures are captured by a webcam and are recognized by a Deep learning model called Computational Neural Networks (CNN), followed by background subtraction, image recognition, and image processing. CNN is used as it provides accurate and efficient output. The output/need is displayed by connecting the webcams to any desk for the ease of healthcare providers. © 2023 IEEE.

关键词： Computational Neural Networks Deep Learning Hand gesture Hospital management Output transmission Patient monitoring

来源：评论

学校读者我要写书评

暂无评论

TU-IR Apple Image Dataset: Benchmarking, Challenges, and Asymmetric Characterization for Bruise Detection in Application of Automatic Harvesting

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2024年第1期2卷 105-124页

作者： Das, Dipak Hrishi Roy, Sourav Dey Saha, Priya Bhowmik, Mrinal Kanti Government Degree College Department of Information Technology Santirbazar 799144 India Department of Computer Science and Engineering Suryamaninagar 799022 India Department of Cyber Security and Digital Forensics Agartala799001 India

With the blooming interest in computer vision-based technologies for future automation of food producers, there is a need for incorporating an automatic bruise detection module in robotic apple harvesting because of decreasing accessibility and growing labor costs. Although numerous studies have been published for automatic quality inspection of fruit and other agricultural products, there is a lack of publicly available image-based datasets for quality inspection/automatic detection of bruises. Toward the aim of developing a bruise detection system for apple harvesting, especially at night time, this article describes the designing issues (i.e., protocol) and creation of a new infrared imaging-based dataset titled 'TU-IR Apple Image Dataset,' which contains 1375 infrared images of apples defining four major categories of bruises (i.e., fresh, slight, moderate, and severe). Along with the infrared images, ground truths (in the form of binary masks) and measurements of suspicious bruised regions are defined. This study also investigates the efficiency of infrared imaging technology for automatic bruise detection in apples by performing an analysis of temperature-based, intensity-based, texture-based, shape-based, and deep convolutional neural network-based features. The classification performance was evaluated using eight different feature sets. Based on the experimental results, considering the most outer-performed classifier, deep convolutional neural networks as a fixed feature extraction method were found to provide the highest prediction performance for discriminating between fresh and three categories of bruises in apples with an average accuracy, specificity, and sensitivity of 93.87%, 80.57%, and 92.02%, respectively. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

TransTM:A device-free method based on time-streaming multiscale transformer for human activity recognition

引用

Defence technology（防务技术） 2024年第2期32卷 619-628页

作者： Yi Liu Weiqing Huang Shang Jiang Bobai Zhao Shuai Wang Siye Wang Yanfang Zhang Institute of Information Engineering Chinese Academy of Sciences School of Cyber SecurityUniversity of Chinese Academy of SciencesBeijingChina School of Information Management Beijing Information Science and Technology UniversityBeijingChina

RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy *** RFID-based HAR methods use modeling,CNN,or LSTM to extract features ***,they have shortcomings:1)requiring complex hand-crafted data cleaning processes and 2)only addressing single-person activity recognition based on specific RF *** solve these problems,this paper proposes a novel device-free method based on Time-streaming Multiscale Transformer called *** model leverages the Transformer's powerful data fitting capabilities to take raw RFID RSSI data as input without ***,we propose a multiscale convolutional hybrid Transformer to capture behavioral features that recognizes singlehuman activities and human-to-human *** with existing CNN-and LSTM-based methods,the Transformer-based method has more data fitting power,generalization,and ***,using RF signals,our method achieves an excellent classification effect on human behaviorbased classification *** results on the actual RFID datasets show that this model achieves a high average recognition accuracy(99.1%).The dataset we collected for detecting RFID-based indoor human activities will be published.

关键词： Human activity recognition RFID Transformer

来源：评论

学校读者我要写书评

暂无评论

Design and Realization of Personal Password Management System Based on Domestic Cryptographic Algorithms 14th

Design and Realization of Personal Password Management Syste...

引用

14th International Conference on Computer engineering and Networks, CENet 2024

作者： Mo, Zixi Zhuge, Chengchen Ma, Zhuo Li, Xiang Zhang, Heyu Zhang, Xunrui Department of Computer Information and Cyber Security Jiangsu Police Institute Nanjing China Engineering Research Center of Electronic Data Forensics Analysis Nanjing China Department of Public Security of Jiangsu Province Key Laboratory of Digital Forensics Nanjing China

ISBN: (纸本)9789819642441

To address the problems of low password security and the use of the same password on multiple network platforms, we analyze the major techniques and shortcomings of the existing personal password manager, and a personal password management system based on domestic cryptographic algorithm is designed. This system mainly consists of four parts: identity authentication module, password management module, encryption and decryption module of domestic cryptographic algorithm, and visualization interaction module, which are responsible for user identity authentication, addition, deletion, modification and checking of passwords, encrypting and protecting passwords using SM2 in conjunction with SM4 algorithm, and displaying data on the front-end page through the interface and beautifying it, respectively. Compared with the traditional system, this system is easy to use, more secure in password preservation, more practical, and creatively uses the "SM2 + SM4" domestic cryptographic algorithms encryption combination instead of the traditional "RSA + AES" encryption combination, which is more reliable. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Human resource management

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：