检索结果-内蒙古大学图书馆

Detection and Classification of Novel Attacks and Anomaly in IoT Network using Rule based Deep Learning Model

SN computer science 2024年第8期5卷 1056页

作者： Chakraborty, Sanjay Pandey, Saroj Kumar Maity, Saikat Dey, Lopamudra Department of Computer and Information Science (IDA) REAL AIICS at Linköping University Linköping Sweden Department of Computer Science and Engineering Techno International New Town Kolkata India Department of Computer Engineering and Applications GLA University Mathura India Department of Computer Science and Engineering Sister Nivedita University Kolkata India Department of Computer Science and Engineering Meghnad Saha Institute of Technology Kolkata India Department of Biomedical and Clinical Sciences Linköping University Linköping Sweden

Attackers are now using sophisticated techniques, like polymorphism, to change the attack pattern for each new attack. Thus, the detection of novel attacks has become the biggest challenge for cyber experts and researchers. Recently, anomaly and hybrid approaches are used for the detection of network attacks. Detecting novel attacks, on the other hand, is a key enabler for a wide range of IoT applications. Novel attacks can easily evade existing signature-based detection methods and are extremely difficult to detect, even going undetected for years. Existing machine learning models have also failed to detect the attack and have a high rate of false positives. In this paper, a rule-based deep neural network technique has been proposed as a framework for addressing the problem of detecting novel attacks. The designed framework significantly improves respective benchmark results, including the CICIDS 2017 dataset. The experimental results show that the proposed model keeps a good balance between attack detection, untruthful positive rates, and untruthful negative rates. For novel attacks, the model has an accuracy of more than 99%. During the automatic interaction between network devices (IoT), security and privacy are the primary obstacles. Our proposed method can handle these obstacles efficiently and finally identify, and classify the different levels of threats. A brief set of comparisons on detection accuracy and time measurements with some state-of-the-art methods are discussed in this paper. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Anomaly detection Classification Deep Learning Machine Learning Network-attack

来源：评论

学校读者我要写书评

暂无评论

GUARDEV: Guided Unified Adaptive Response for Defending Electric Vehicles 27th

GUARDEV: Guided Unified Adaptive Response for Defending Elec...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Mondal, Koustav Kumar Das, Debasis Inter-Disciplinary Research Division - IoT and Applications Indian Institute of Technology Jodhpur Rajasthan Jodhpur India Department of Computer Science Engineering Indian Institute of Technology Jodhpur Rajasthan Jodhpur India

ISBN: (纸本)9783031783821

In the rapidly evolving landscape of electric vehicles (EVs), integrating the Internet of Vehicles (IoV) has opened up new dimensions in automotive technology. While enhancing vehicle performance, safety, and security, this advancement also exposes EVs to heightened cyber threats. To address this critical concern, we introduce GUARDEV: Guided Unified Adaptive Response for Defending Electric Vehicles, a novel Machine Learning (ML)-enhanced conflict resolution-based ensemble Intrusion Detection System (IDS) architecture. GUARDEV leverages the power of adaptive ML techniques to provide a unified and guided response in safeguarding EVs against sophisticated cyber-attacks. Our framework evaluates the effectiveness of three prominent ML models - XGBoost, Random Forest, and Extra Trees - in detecting specific categories of cyber threats. By harnessing the prediction confidence scores from these models, GUARDEV offers a nuanced and intelligent approach to recognizing and thwarting diverse cyber-attacks. Our research, grounded in rigorous experimentation using public IoV security datasets, demonstrates GUARDEV’s exceptional accuracy of 99.47% in intrusion detection. This remarkable achievement not only underscores the potential of ML in enhancing vehicular cybersecurity but also establishes GUARDEV as a powerful tool for creating safer, more secure EVs. GUARDEV paves the way for robust protection of internet-connected electric vehicles in today’s digital age by providing a guided, unified, and adaptive response to cyber threats. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques for Object Detection in Underwater Environments

Deep Learning Techniques for Object Detection in Underwater ...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Praveen, R.V.S. Maindola, Meenakshi Anandhi, R.J. Thandra, Nagarjuna Bansal, Saloni Sharma, Vishal LTIMindtree Limited Telangana Hyderabad India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India New Horizon College of Engineering Department of Information Science Engineering Bangalore India MLR Institute of Technology Dept. Computer Science and Engineering Telangana Hyderabad India GLA University Department of Computer Engineering and Applications Mathura India Lovely Professional University Phagwara India

ISBN: (纸本)9798331512965

The degradation of image quality caused by things like light absorption, scattering, and distortion makes object detection in underwater environments a unique challenge. applications like marine research, environmental monitoring, and autonomous underwater vehicles (AUVs) are restricted in their effectiveness by traditional image processing techniques, which often struggle with these complexities. Recent years have seen the rise of deep learning techniques as a potent weapon in the fight against these obstacles. In order to accurately detect objects underwater, this paper investigates the use of deep learning models, specifically convolutional neural networks (CNNs). We explore cutting-edge models and methods like attention mechanisms, transfer learning, and hybrid deep learning architectures to improve detection performance in challenging underwater environments. Furthermore, we utilize data augmentation techniques and synthetic dataset generation to tackle the critical issue of limited labeled underwater datasets. From a detection accuracy and robustness perspective, the experimental results show that our suggested deep learning method is light years ahead of the competition. Marine exploration, autonomous underwater vehicle navigation, and underwater surveillance systems can all benefit from this study's new insights into how to better detect objects in real time while submerged. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Blood Cell Classification and Counting in Hematology through Deep Learning 4

Blood Cell Classification and Counting in Hematology through...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Ananthi, P. Devi, K. Nirmala Ramya, T.E. Shanmugapriya, P. Aradhya, T. Kongu Engineering College Department of Computer Technology Perundurai Tamil Nadu Erode India Madanapalle Institute of Technology & Science Department of Computer Applications India Kongu Engineering College Perundurai Tamil Nadu Erode India

ISBN: (纸本)9798331540364

Medical diagnosis is one of the areas that has been greatly influenced by the progress of computer vision technologies. This study presents a unique approach for the detection and counting of blood cells in hematology: You Only Look One algorithm version 7 (YOLOv7). YOLO is designed for real-time object detection, making it ideal for applications such as blood vessel detection where speed is critical. The architecture allows the model to process images faster than other recognition models, such as R-CNN or SSD, which is very important for situations that require fast results, such as analysis automatic blood at clinical sites. The purpose of the proposed method is to overcome the shortcomings of conventional methods and to accurately and quickly identify blood cells in mechanical images. The YOLOv7 model has been utilizedbecause it can detect objects in real-time with highprecision and speed. The methodology for bloodcell counting involves the use of YOLOv7 togenerate bounding boxes around each detectedblood cell in an image, where the count of these bounding boxes directly corresponds to the number of cells. This advancement in hematology not onlyimproves blood cell analysis efficiency but also expedites the process of diagnosing and planningtreatment in various medical situations. This paper details how YOLOv7 was modified and adjusted to meet the specific requirements of hematologicalimage analysis, including training models, preparing datasets, and evaluating performance. The study also addresses the potential impact of this technology on clinical workflows, highlightinghow it might help medical practitioners make decisions more quickly and intelligently. Hematology analysis systems including YOLOv7 are able to improve laboratory diagnostics and help patients by providing better care and results. This workconcludes by demonstrating the revolutionary potential of YOLOv7 in blood cell identificationand counting in hematology, paving the way for accurate and better

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Enhanced Monitoring and Security Measures with Video Analysis

Enhanced Monitoring and Security Measures with Video Analysi...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Jyothi, V. Esther Rakesh, G. Aruna, Vipparla Gorintla, Shobana Ayyappa, Yalanati Naidu, U. Ganesh Velagapudi Ramakrishna Siddhartha Engineering College Deemed to be University Department of Computer Applications A.P. Vijayawada India Department of Computer Science and Engineering Pothavarapadu A.P India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Avadi India B V Raju Institute of Technology Telangana Narsapur India

ISBN: (纸本)9798331509828

In modern surveillance, activities have increasingly become dependent on the continuous observation offered by CCTV systems. Still, with massive amounts of video data generated in a minute, sifting through this information manually to pick up any anomalies would be extremely burdensome and nearly impossible without significant human labor and vigilant watchfulness. CNN and CLIP models changed everything with regards to the working of surveillance systems. It makes use of CNN's capability for video frame processing and analysis to detect and classify these activities in the frames as either normal or suspicious. At the same time, it improves this by adding the CLIP model's capability of understanding textual descriptions and visual content together for better nuance detection in suspicious activities. This methodology transforms video surveillance by breaking video streams into frames and analyzing the behavior and interactions of persons in those frames. The synergy of CNN and CLIP models not only ensures real-time, efficient, and accurate surveillance but also minimizes dependency on extensive manual labor for monitoring. This paper aims to provide a contribution toward developing better security infrastructures in public spaces, transportation hubs, and private facilities. The introduction of this anomaly-detection mechanism can hugely improve the capability of implemented surveillance systems with a proactive response based on real-time detection and response capabilities against suspicious activities. © 2025 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Coupling Mobile Brain Imaging and Virtual Reality Omnidirectional Treadmill to Explore Attenuated Situational Awareness during Distracted Walking

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年第3期16卷 1063-1076页

作者： Chuang, Chun-Hsiang Chiu, Tsai-Feng Hsu, Hao-Che Lin, Shih-Syun National Tsing Hua University Research Center for Education and Mind Sciences College of Education The Institute of Information Systems and Applications College of Electrical Engineering and Computer Science Hsinchu300 Taiwan National Tsing Hua University Research Center for Education and Mind Sciences Hsinchu300 Taiwan National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300193 Taiwan National Taiwan Ocean University Department of Computer Science and Engineering Keelung20224 Taiwan

Walking while engaging in distracting activities affects our perception of changes happening on the road, leading to exposure to hazardous conditions. This study aimed to evidence that pedestrians who become distracted when absorbed in their smartphones fail to maintain situational awareness. Thirty-six recruited participants performed a psychomotor vigilance task and a wayfinding task designed to simulate a multitasking scenario;meanwhile, an auditory oddball paradigm presented to participants tested their situational awareness of an external stimulus. The experiment was conducted in virtual reality (VR) environment with an omnidirectional treadmill. Participant's behavioral and electroencephalographic (EEG) responses were measured and analyzed using a newly proposed brain network measure, phase locking distance (PLD), to capture multitasking-associated couplings between brain regions. The current study supports the notion that multitasking can lead to diminished behavioral performance and changes in walking patterns. Despite the increased interregional brain connectivity, which may be an adaptive response to heightened cognitive demands, the associated reduction in event-related EEG activity suggests competition for neural resources during multitasking. Moreover, the observed EEG activities could indicate additional information processing capacity limitations and provide evidence of decreased situational awareness during multitasking, thereby increasing susceptibility to potentially hazardous situations. © 2016 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Predictive Maintenance Model Using Hybrid Procedure of Improved Quantum Cat Swarm Optimisation for Asset Management in Industry 4.0

Predictive Maintenance Model Using Hybrid Procedure of Impro...

引用

International Conference on Data Analytics and Management, ICDAM 2023

作者： Kanchana, S. Rajan, Dhivya Mahaveerakannan, R. Sagar, K. V. Daya Subramanian, P. Rajakumar, B. Department of Computer Science Faculty of Science and Humanities SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Computer Applications CMR Institute of Technology Bengaluru India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Electronics and Computer Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of AI & DS JNN Institute of Engineering Chennai Periyapalayam Highway Tamil Nadu Thiruvallur601102 India

ISBN: (纸本)9789819965465

Contemporary manufacturing system design centres on the Industry 4.0 paradigm. A versatile platform secondary the efficient optimisation of manufacturing-related activities, such as predictive keep, is necessary for the successful mixing of cutting-edge technologies like the (IoT), cyber-physical schemes, computing. Predictive maintenance research that already exists often either develops a model without taking maintenance decisions into account or seeks to optimise maintenance in the light of the degradation replicas of the already-known scheme. With the use of predictive maintenance, a company's owner can make decisions like fixing or replacing a failing part of the manufacturing line before it actually fails. Because of this, Industry 4.0 necessitates efficient asset management in order to maximise the distribution of duties and the accuracy of predictive maintenance models. To address the issue of predictive maintenance in fog computing, this paper proposes an enhanced version of the quantum cat swarm optimisation (QCSO) algorithm by combining the quantum bit (Q-bit) and the cat swarm procedure (CSO) and updating the cats based on the quantum rotation angle site. Finally, the (MR) worth is chosen based on the sum of times the procedure is run. FogWorkflowsim uses simulated real-time datasets to evaluate the forecasting performance of QCSO and other existing models. The outcomes prove that the projected method is superior to the currently used predictive maintenance resource allocation methods. In comparison to the approximately 91% to 95% accuracy achieved by previous models, the proposed model has an accuracy of 96%, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Automated X-Ray Image Classification for COVID-19 Detection Using DenseNet-121 and SVM 3

Automated X-Ray Image Classification for COVID-19 Detection ...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Ameta, Gaurav Kumar Khekare, Ganesh Phulre, Ajay Kumar Jayachitra, S. Singh, Vijendra Pratap Vijayan, Vinodh P. Parul Institute of Technology Parul University Department of Computer Science and Engineering Gujarat Vadodara India School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Computing Science Engineering and Artificial Intelligence Vit Bhopal University Sehore India Psna College of Engineering and Technology Department of Ece Dindigul India Mahatma Gandhi Kashi Vidyapith Department of Computer Science & Applications Uttar Pradesh Varanasi India Mangalam College of Engineering Kerala Kottayam India

ISBN: (纸本)9798331542375

This paper provides an algorithm to detect COVID-19 from the chest X-Ray images using Two-class classification with DenseNet-121 and Support Vector Machine. For effective identification of patterns suggestive of COVID-19 in the provided X-ray images, we leverage the DenseNet-121 model due to its feature extracting prowess, complemented by the SVM classifier to accurately classify the images between the COVID-19 to non-COVID-19 positive cases. The method delivers a high accuracy, which is more than 93% for accuracy, precision, recall, and F1-score, which makes it efficient in the COVID-19 quick screening. The Improved DenseNet-121 + SVM was compared with other deep learning models like ResNet50, VGG16, and confirmed that the proposed model has better efficiency in classifying COVID-19 cases. The performance of the model is checked with a five fold cross validation to ensure consistency and reliability on different sets of data not only in terms of performance with the IMDB data but also with the test data. The working paper is relevant to the current research practices in an effort to construct machine diagnostic systems that can be used by practicing healthcare professionals for identifying COVID-19 in the early stages, thus enhancing outcomes in patients' treatment. © 2025 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

PSST: A Benchmark for Evaluation-driven Text Public-Speaking Style Transfer

PSST: A Benchmark for Evaluation-driven Text Public-Speaking...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Sun, Huashan Wu, Yixiao Ye, Yuhao Yang, Yizhe Li, Yinghao Li, Jiawei Gao, Yang School of Computer Science and Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China

ISBN: (纸本)9798891761681

Language style is necessary for AI systems to understand and generate diverse human language ***, previous text style transfer primarily focused on sentence-level data-driven approaches, limiting exploration of potential problems in large language models (LLMs) and the ability to meet complex application *** overcome these limitations, we introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform passage-level, official texts into a public-speaking *** in the analysis of real-world data from a linguistic perspective, we decompose public-speaking style into key sub-styles to pose challenges and quantify the style modeling capability of *** such intricate text style transfer, we further propose a fine-grained evaluation framework to analyze the characteristics and identify the problems of stylized *** experiments suggest that current LLMs struggle to generate public speaking texts that align with human preferences, primarily due to excessive stylization and loss of semantic information. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Telecom Churn Classification using Scatter Search and Random Forest Classifier

Telecom Churn Classification using Scatter Search and Random...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Varun, A.S. Babu, Tina Nair, Rekha R Kishore, S. Dayananda Sagar Univerity School of Engineering Department of Computer Science & Engineering Bengaluru India Alliance Univerity Department of Computer Science and Engineering Bengaluru India Nitte Institute of Professional Education Nitte University Department of Computer Applications Karnataka India

ISBN: (纸本)9798350313413

The Telecom Churn Dataset is a valuable resource that contains customer-related information such as demographics, usage patterns, billing data, and customer service interactions. The proposed model is used to explore various factors that might impact churn behavior and apply machine learning techniques to create predictive models for proactive retention efforts. This study have employed different approaches and methods, including random forest, logistic regression, and decision trees, as well as feature selection techniques like Correlation-based Feature Selection (CFS), scatter search etc. The proposed methodology involves preprocessing the data using techniques like SMOTE to handle class imbalance, selecting relevant features through Scatter search, and applying classification algorithms like the Random Forest (RF) classifier. The proposed model using Scatter search and Random Forest classifier has best formed with an accuracy of 91.9%, precision and recall of 0.919. Thus the model is well suited for telephone churn classification with the optimized feature set selection and classification. © 2023 IEEE.

关键词： Classification feature reduction random forest SMOTE Telecom churn

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：