检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Jhansi Ida, S. Balasubadra, K. Skandarsini, R.R. Lakshmi Narayanaa, T. RMK Engineering College Dept. of Computer Science and Business Systems Thiruvallur India RMD Engineering College Department of Information Technology Thiruvallur India

ISBN: (纸本)9798350365269

There is still a serious problem with credit card fraud in the world of financial transactions, requiring innovative solutions to effectively detect and halt illicit behavior. This research presents a unique method of detecting credit card fraud by strategically implementing early pausing in a Long Short-Term Memory (LSTM) neural network. Leveraging the sequential dependencies inherent in transaction data, the LSTM model demonstrates remarkable efficacy in discerning fraudulent from legitimate transactions. The early stopping mechanism ensures that the model's training halts at the optimal epoch, preventing over fitting and enhancing generalization. Our thorough analysis highlights the model's versatility by demonstrating a dynamic compromise between recall and accuracy throughout training. Practical implications include enhanced fraud detection accuracy, reduced false alarms, and real-time decision support for financial institutions. The model's adaptability and generalization make it a valuable asset in the ongoing battle against credit card fraud, contributing to a more secure financial environment. Future research directions may explore additional features and alternative architectures to further advance fraud detection capabilities. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Device Identification using Network Traces in a Smart Home IoT Network 17

Device Identification using Network Traces in a Smart Home I...

引用

17th IEEE International Conference on Advanced Networks and Telecommunications systems, ANTS 2023

作者： Brahma, Jwngfu Matam, Rakesh Choudhury, Nikumani Indian Institute of Information Technology Dept. of Computer Science & Engineering Guwahati India Birla Institute of Technology & Science Dept. of Computer Science & Information Systems Hyderabad India

ISBN: (纸本)9798350307672

Device identification is a crucial aspect of securing networks, particularly in the context of the Internet of Things (IoT), where a vast variety of devices are interconnected. Recently, there has been significant research on developing techniques for identifying IoT devices based on their unique characteristics, called as device fingerprints. These techniques use machine learning algorithms, which can effectively learn and classify devices based on their features. However, device identification remains a challenging task due to the diversity of IoT devices and the constant evolution of their characteristics. This paper presents our attempt at device identification by analyzing distinct device characteristics observed during network communication and using different machine learning techniques. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Effective Outlier Detection using Scalable and Robust Clustering (SRC) Algorithm 2

Effective Outlier Detection using Scalable and Robust Cluste...

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Adusumilli, Ramana Lakshmi Shashi, M. Andhra University Dept of Computer Science and Systems Engineering Visakhapatnam India Andhra University Au College of Engineering Dept of Computer Science and Systems Engineering Visakhapatnam India

ISBN: (纸本)9781665400527

Clustering large datasets with high dimensionality effectively and efficiently is a challenging task. The authors made an attempt to face the challenge by developing a Scalable and Robust Clustering(SRC) algorithm by hybridizing the grid and density based clustering algorithms. In contrast to the data points belonging to various clusters based on their similarity, the outliers are the data points with dissimilar / abnormal behavior from the rest of the points. Hence this paper investigates the applicability of the SRC algorithm developed by the authors for Outlier Detection (SRC-OD) from large datasets with high dimensionality. A framework is developed to analyze the performance of proposed SRC algorithm for outlier detection compared with that of the existing outlier detection (OD) algorithms using Jaccard Similarity metric and execution time. The results produced by SRC-OD algorithm are comparable with Isolation forest Outlier detection algorithm (ISO) which is the best known OD algorithm, based on Jaccard similarity, while the proposed SRC_OD algorithm is more scalable than all other Outlier detection algorithms except ISO as its execution time grows slower. Moreover, SRC-OD framework detects the outliers as a by product while clustering large datasets. © 2022 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network-based image tamper detection with Error Level Analysis 2

Convolutional Neural Network-based image tamper detection wi...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Manjunatha, S. Swetha, M.D. Rashmi, S. Subramanian, Ananda Kumar Vinoth Kumar, V. Mallikarjuna Swamy, S. Global Academy of Technology Department of Information Science and Engineering Bengaluru India BNM Institute of Technology Department of Computer Science and Engineering Bengaluru India Bengaluru India Vit - University School of Computer Science Engineering Dept of Computational Intelligence Vellore India Vit - University School of Computer Science Engineering and Information Systems Vellore India Jss Academy of Technical Education Dept of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350306415

Photography is the most important, powerful, and reliable means of expression. Today, digital images not only provide disinformation but also act as agents for secret communication. Users and editing professionals work with digital images for a variety of purposes. Images are often regarded as facts or proof of reality, so they are misleading and fake news or publications of any form that use images manipulated in a highly misleading way. To recognize image tampering needs multiple image data and a model that can handle all the pixels in the image. Furthermore, training the data more efficiently and needed flexibility support everyday use. Models based on Deep learning such as Convolutional Neural Networks with error level analysis (ELA) are the perfect solution. © 2024 IEEE.

关键词： Convolutional Neural Network Deep Learning Efficiency Error Level Analysis Image Forgery Detection

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic-based Energy Management for WSNs in Smart Grid Applications 4

Fuzzy Logic-based Energy Management for WSNs in Smart Grid A...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Vengatesan, K. Vijayalakshmi, R. Samee, Sayyad Chopade, Neha Mahalle, Shilpa Bashkaran, K. Department of AIDS Sanjivani University Kopargaon India Department of Computer Science and Engineering Velammal College of Engineering and Technology Madurai India Dept.of Computer Science Al Sadara School Al Ain Abu Dhabi United Arab Emirates SIES College of Management Studies India Kongunadu College of Engineering and Technology Thottiam India

ISBN: (纸本)9798331515720

Fuzzy Logic-Based Energy Management (FLBEM) is an innovative approach for optimizing energy consumption in Wireless Sensor Networks (WSNs) utilized in Smart Grid applications. This technique employs fuzzy logic principles to dynamically adjust network parameters, such as transmission power and data sampling rates, to enhance energy efficiency while maintaining reliable communication. By intelligently adapting to network conditions and environmental factors, FLBEM extends the operational lifetime of sensor nodes and ensures the stability of the WSN, thus facilitating real-Time monitoring and control of Smart Grid systems. The proposed FLBEM approach encompasses a comprehensive framework that includes the design of fuzzy logic controllers, the development of energy-Aware routing protocols, and the integration of renewable energy sources for powering sensor nodes. Simulation results demonstrate significant improvements in energy efficiency, network lifetime, and overall performance, validating the effectiveness of the FLBEM strategy in the context of Smart Grid applications. As energy management remains a critical concern for WSNs, the implementation of FLBEM offers a promising solution to address the challenges of energy conservation and sustainability in modern power systems. © 2024 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Synchrosqueezed Wavelet transform Based Power Quality Disturbance Detection and Monitoring of Solar Integrated Micro-Grid 2

Synchrosqueezed Wavelet transform Based Power Quality Distur...

引用

2nd International Conference on Power Electronics and Energy, ICPEE 2023

作者： Pattanaik, Debasish Swain, Sarat Chandra Samanta, Indu Sekhar Rout, Ullash Kumar Dash, Ritesh Swain, Kunjabihari Kiit Deemed to Be University School of Electrical Engineering Bhubaneswar India Iter Soa University Dept.of Computer Science and Engineering Bhubaneswar India Odisha University of Technology and Research Dept. of Electrical Engineering Bhubaneswar India Reva University Dept.of Electrical and Electronics Engineering Bangalore India Nist Institute of Science and Technology Dept. of Electrical and Electronics Engineering Berhampur India

ISBN: (纸本)9781665470582

Microgrid monitoring has gained popularity in recent years, owing to their popularity and the power quality disturbances (PQD) caused by renewable energies. Many artificial intelligence-based PQD monitoring strategies have been proposed by researchers. This paper presents a novel method for detecting, classifying and monitoring the power quality disturbances in solar integrated microgrids. Power quality events are detected by analysing the frequency signal with the wavelet synchro-squeezing transform (WSST). The features of power quality disturbances are used to classify them. For PQD classification, the retrieved features are fed into a Convolutional neural network (CNN) classifier, using GoogLeNet and SqueezeNetfier. Thus the accuracy was found to be 99.90% and 93.76% respectively. © 2023 IEEE.

关键词： Artificial Neural Network Convolutional Neural Network GoogLeNet neural network Innovation Micro Grid Power Quality Disturbances Renewable Energy Sources Wavelet synchro-squeezing transform

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing–Based UAV Imaging in Heat Pattern Analysis Impact on Climate Change Detection Using Fuzzy Stacked Lasso Elastic-Net Model

引用

Remote Sensing in Earth systems sciences 2024年第4期7卷 699-708页

作者： Sailaja, M. Kumar, M. Prema Jyothi, B. Swarna Vanguri, G. L. Narasamba Manjula, S. Priya, D. Divya Department of Computer Science and Engineering Ravindra College of Engineering for Women Andhra Pradesh Kurnool India Dept. of ECE Shri Vishnu Engineering College for Women (A) Andhra Pradesh Bhimavaram 534202 India Department of Computer Science & amp Engineering Madanapalle Institute of Technology & amp Science Andhra Pradesh Madanapalle India Information Technology Aditya College of Engineering & amp Technology(A) Andhra Pradesh Surampalem 533437 India Department of Computer Science and Business Systems Nehru Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Urban heat islands raise surface temperatures, which has an effect on city dwellers’ health and welfare. Urbanisation-related changes to the land surface, which are especially notable right after sunset, have an impact on radiative forcing. Recently, there has been a surge in the usage of unmanned aerial vehicle (UAV) technology, particularly for precision agriculture and plant phenotyping. This is due to the declining cost and increased accessibility of both UAVs and thermal imaging sensors. This interruption affects subsequent operations like target item categorisation and water quality parameter inversion. The goal of this study was to evaluate the potential for combining machine learning (ML) with unmanned aerial vehicle (UAV)–based imaging technology. In this research, the novel technique in UAV image–based temperature pattern detection of various regions of earth and their sea level rise analysis using image classification by machine learning model. Here, the input is collected as UAV images which have been processed for noise removal and normalisation. These image features have been extracted using convolutional active contour–based kernel component analysis and classified using region-based fuzzy stacked lasso elastic-net model. The classified output shows temperature analysis with sea level rise based on image analysis. The experimental analysis has been carried out for various UAV image dataset in terms of detection accuracy, RMSE, F-measure, mean average precision (MAP), and recall. Proposed technique F-measure of 89%, detection accuracy of 96%, MAP of 94%, recall of 92%, and RMSE of 60%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Convolutional active contour Heat pattern detection Kernel component analysis Lasso elastic-net model Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification

Bidirectional Multi-Step Domain Generalization for Visible-I...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Alehdaghi, Mahdi Shamsolmoali, Pourya Cruz, Rafael M. O. Granger, Eric Livia Ills Dept. of Systems Engineering Ets Montreal Canada University of York Dept. of Computer Science United Kingdom

ISBN: (纸本)9798331510831

A key challenge in visible-infrared person re-identification (V-I ReID) is training a backbone model capable of effectively addressing the significant discrepancies across modalities. State-of-the-art methods that generate a single intermediate bridging domain are often less effective, as this generated domain may not adequately capture sufficient common discriminant information. This paper introduces Bidirectional Multi-step Domain Generalization (BMDG), a novel approach for unifying feature representations across diverse modalities. BMDG creates multiple virtual intermediate domains by learning and aligning body part features extracted from both I and V modalities. In particular, our method aims to minimize the cross-modal gap in two steps. First, BMDG aligns modalities in the feature space by learning shared and modality-invariant body part prototypes from V and I images. Then, it generalizes the feature representation by applying bidirectional multi-step learning, which progressively refines feature representations in each step and incorporates more prototypes from both modalities. Based on these prototypes, multiple bridging steps enhance the feature representation. Experiments11Our code is available at: ***/BMDG conducted on V-I ReID datasets indicate that our BMDG approach can outperform state-of-the-art part-based and intermediate generation methods, and can be integrated into other part-based methods to enhance their V-I ReID performance. © 2025 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Accident Detection and Severity Analysis System for Enhanced Emergency Response 1

Intelligent Accident Detection and Severity Analysis System ...

引用

1st IEEE International Conference on Computing and Data science, ICCDS 2024

作者： Harini, P. Chidambarathanu, K. Ramachandran, Lalitha R.M.K Engineering College Dept. Computer Science and Business Systems Kavarapettai India R.M.K Engineering College Dept. Science and Humanities Kavarapettai India

ISBN: (纸本)9798350365337

Road accidents cause serious injuries and deaths worldwide. The previous year's Ministry of Road Transport and Highways Annual Report on Road Accidents in India showed that many road accidents were fatal. A large percentage of Indian deaths occur without rapid medical intervention or first assistance. Delays in reporting incidents to emergency services increased fatalities. A sophisticated method using deep learning and analytics to locate CCTV accidents, classify their severity, and speed up emergency response. Accident detection and analysis are efficient with cutting-edge technologies. The accident detection phase uses YOLOv7, a deep-learning object detection model, to evaluate CCTV footage in real time. A stratified K-fold deep neural network classifies accidents as major or minor based on collision severity. Real-time GPS tracking alerts ambulance drivers within three km of the accident using the mobile app. This expedites emergency response, lowering mortality by reducing the time between the accident and medical assistance. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Using Multi Class SVM for Creating an Algorithm for Human Activity Recognition

Using Multi Class SVM for Creating an Algorithm for Human Ac...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： Kaarthik Ganapathy S Kaarthick C R. Sethuraman Dept.of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai TamilNadu India

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Identifying human activity is a crucial task in numerous fields involving human-computer interaction. This study introduces a innovative approach for human activity recognition using a multi-class Support Vector Machine (SVM). The methodology unfolds in three crucial steps: preprocessing, feature extraction, and classification. In the preprocessing stage, a depth map undergoes transformation into a silhouette for each frame, achieved by segregating foreground elements from the background. To mitigate the effects of variations in size and position, foreground silhouettes undergo normalization via shrinking and cropping. The process of feature extraction includes deriving spatial and temporal features from these normalized silhouettes. This involves integrating the directed gradients histogram, optical flow histogram, the motion history image, and the 2D Discrete Cosine Transform. Each frame is represented by a comprehensive feature vector obtained by concatenating these extracted features. These aggregated features are subsequently utilized for activity identification using a multi-class SVM classifier. Experimental results on three benchmark datasets validate the effectiveness of this approach, achieving commendable accuracy rates in activity recognition. A notable strength of the proposed method is its robustness to occlusions, changes in illumination, and variations in view angles, making it a compelling choice for accurate and reliable human activity identification in real- world scenarios.

关键词： Support vector machines Histograms Accuracy Transforms Feature extraction Vectors Robustness

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：