检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Shekhar, Raj Tomar, Deepak Singh Sharan, Bhagwati Pateriya, R.K. Maulana Azad National Institute of Technology Department of Computer Science and Engineering Bhopal India Srm University-AP School of Engineering and Sciences Department of Computer Science and Engineering Andhra Pradesh India

ISBN: (纸本)9798350370249

The idea of smart healthcare is gradually gaining traction with the rapid advancement in information technologies. Smart healthcare is the intelligent transformation of the current medical system to make it more reliable, efficient, and individualized through the intelligent use of next-generation technologies like artificial intelligence, and the Internet of Things (IoT). This study offered the recent advancement of Deep learning (DL) techniques for healthcare systems, and the use of DL techniques to identify human physical activity with wearable sensors. In this paper, convolutional neural networks (CNN), CNN-LSTM, Multi Headed CNN-LSTM, and Multi Headed CNNBiLSTM are used. The obtained outcomes of these Deep Learning models are compared in terms of accuracy, precision, recall and F1 score. The Multi-Headed CNN-BiLSTM model exhibits better performance than the rest of the models when applied to the UCI HAR dataset. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Autotrack: a framework for query-based vehicle tracking and retrieval from CCTV footages using machine learning at the edge

引用

International Journal of Information technology (Singapore) 2023年第7期15卷 3827-3837页

作者： Sreedhar, Sreela Philip, Abin Oommen Sreeja, M.U. Department of Computer Science and Engineering Toc H Institute of Science and Technology Ernakulam India Department of Electronics Cochin University of Science and Technology Kochi India Department of Computer Science and Engineering-Cybersecurity Indian Institute of Information Technology Kottayam (IIIT Kottayam) Kottayam India

Automobile theft and hit and run incidents have become ever rampant than before urging the need for automated tracking systems. However, prompt detection of the vehicle involved in incident and recovery of the stolen vehicle is crucial as these are immediately forged to reduce the chances of getting caught. Hence, the proposed model puts forth a query-based framework to intelligently detect and track vehicles from CCTV surveillance footages using queries involving custom input features such as model, make, colour and license plate number. The model uses a combination of techniques for detecting the vehicle make and model, tracking vehicle, and for identifying the license plate number based on You Only Look Once (YOLO), Kalman filters, and Tesseract respectively. Further, the model performs vehicle detection and tracking from multiple surveillance videos which can ensure that the suspicious vehicle which is reported of either theft, license plate forgery or any unusual activity like hit and run cases is located immediately. The detection model is trained and deployed on edge device integrated to CCTVs and hence overcoming the drawbacks associated with a centralized system. The performance of the proposed vehicle detection model compared to baseline models on the basis of popular classification metrics precision, recall and f1-score proves the superiority of the proposed model compared to the existing ones. Additional experimental analysis of the entire framework further establishes the relevance of the combination of selected input features as well as emphasizes the significance of query-based models over its generic counterparts. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Edge computing Kalman filter Object detection Tracking Vehicle detection YOLO

来源：评论

学校读者我要写书评

暂无评论

Non-Contact Vital Prediction Using rPPG Signals 1

Non-Contact Vital Prediction Using rPPG Signals

引用

1st IEEE International Conference on Contemporary Computing and Communications, InC4 2023

作者： Madhu, Meghna Gurudas, V.R. Manjunath, Chinthakunta Naik, Praveen Kulkarni, Praveen School of Engineering and Technology Department of Computer Science and Engineering Bangalore India Dayananda Sagar University Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350335774

In this paper, we present the clinical significance of various cardiac symptoms with the use of heart rate detection, ongoing monitoring and present emotions. The development of algorithms for remote photoplethysmography has drawn a lot of interest during the past decade (rPPG). As a result, using data gathered from the video feed, we can now precisely follow the heart rate of individuals who are still seated. rPPG algorithms have also been developed, in addition to technique based on hand-crafted characteristics. Deep learning techniques often need a lot of data to train on, but biomedical data frequently lacks real-world examples. The experiment described in this work, we looked at how illumination affected the rPPG signals' SNR. The findings show that the SNR in each RGB channel varies depending on the colour of the light source. Paper describes development in video filtering for recognising the comprehending human face emotions. In our method, emotions are deduced by identifying facial landmarks and analysing their placement. © 2023 IEEE.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Hybrid Marine Predators Optimization and Improved Particle Swarm Optimization-Based Optimal Cluster Routing in Wireless Sensor Networks(WSNs)

引用

China Communications 2022年第6期19卷 219-247页

作者： A.Balamurugan Sengathir Janakiraman M.Deva Priya A.Christy Jeba Malar Department of Computer Science&Engineering KPR Institute of Engineering and TechnologyCoimbatoreTamilnaduIndia Department of Information Technology CVR College of EngineeringHyderabadTelanganaIndia Department of Computer Science&Engineering Sri Eshwar College of EngineeringCoimbatoreTamilnaduIndia Department of Information Technology Sri Krishna College of TechnologyCoimbatoreTamilnaduIndia

Wireless Sensor Networks(WSNs)play an indispensable role in the lives of human beings in the fields of environment monitoring,manufacturing,education,agriculture etc.,However,the batteries in the sensor node under deployment in an unattended or remote area cannot be replaced because of their wireless *** this context,several researchers have contributed diversified number of cluster-based routing schemes that concentrate on the objective of extending node survival ***,there still exists a room for improvement in Cluster Head(CH)selection based on the integration of critical *** meta-heuristic methods that concentrate on guaranteeing both CH selection and data transmission for improving optimal network performance are *** this paper,a hybrid Marine Predators Optimization and Improved Particle Swarm Optimizationbased Optimal Cluster Routing(MPO-IPSO-OCR)is proposed for ensuring both efficient CH selection and data *** robust characteristic of MPOA is used in optimized CH selection,while improved PSO is used for determining the optimized route to ensure sink *** specific,a strategy of position update is included in the improved PSO for enhancing the global searching efficiency of *** high-speed ratio,unit speed rate and low speed rate strategy inherited by MPOA facilitate better exploitation by preventing solution from being struck into local optimality *** simulation investigation and statistical results confirm that the proposed MPOIPSO-OCR is capable of improving the energy stability by 21.28%,prolonging network lifetime by 18.62%and offering maximum throughput by 16.79%when compared to the benchmarked cluster-based routing schemes.

关键词： Marine Predators Optimization Algorithm(MPOA) Particle Swarm Optimization(PSO) Optimal Cluster-based Routing Cluster Head(CH)selection Wireless Sensor Networks(WSNs)

来源：评论

学校读者我要写书评

暂无评论

Efficient Classification of Rice Varieties Using Optimized Convolutional Neural Networks 8

Efficient Classification of Rice Varieties Using Optimized C...

引用

8th IEEE International Conference on Information and Communication technology, CICT 2024

作者： Pathak, Abhishek Kumar Singh, Ankit Kumar Bhatia, Vimal Singh, Puneet Indian Institute of Technology Department of Electrical Engineering Indore India Motihari College of Engineering Department of Computer Science and Engineering India

ISBN: (纸本)9798331531539

Rice type classification is a crucial task in agri-cultural automation, aimed at improving quality control and ensuring market standards. This study presents a deep learning-based approach using a optimized Convolutional Neural Network (CNN) model implemented with PyTorch to classify five rice varieties: Arborio, Basmati, Ipsala, Jasmine, and Karacadag. Our proposed model diverges from conventional methods that rely heavily on complex machine learning algorithms or pretrained CNN architectures like MobileNetV2, VGG16, EfficientNetB0 etc., which require a large number of parameters and layers, re-sulting in increased computational complexity. Through proposed approach, we achieved a remarkable 99.81% validation accuracy and a minimal validation loss of 0.01 % with a significantly reduced model size 30.76 MB. The simplicity of the proposed CNN architecture not only enhances computational efficiency but also maintains high accuracy, making it a viable solution for rice type classification in practical applications. This study demonstrates that a fine-tuned CNN model can outperform more complex models, providing an efficient and effective alternative for agricultural classification tasks. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Energy Consumption in Smart Grids Using Demand Response Techniques

引用

Distributed Generation and Alternative Energy Journal 2024年第1期39卷 111-136页

作者： SwornaKokila, M.L. Venkatarathinam, R. Rose Bindu, Joseph P. Manivasagam, M.A. Kishore, Kakarla Hari Department of Computing Technologies School of Computing College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology SRM Nagar Kattankulathur TN Chennai India Department of Information Technology Sri BalajiChockalingam Engineering College A.C.S. Nagar Irumbedu Thiruvannamalai District Tamil Nadu Arni India Department of Mathematics Dayananda Sagar College of Engineering Bangalore India Computer Science and Engineering Siddartha Institute of Science and Technology Andhra Pradesh India Department of Electronics and Communication Engineering KoneruLakshmaiah Education Foundation Guntur Andhra Pradesh Vaddeswaram India

Smart grids have developed as a potentially game-changing strategy for controlling the demand and supply of energy. Unfortunately, peak demand is a significant source of grid instability and rising energy prices, making it one of the most critical difficulties in smart grids. During times of high energy demand on the grid, demand response (DR) strategies incentivize consumers to change how they use energy. This study’s overarching goal is to learn how DR methods may be used to help smart grids make better use of their energy resources. The primary research is to develop a smart DR system that can predict times of high energy demand and proactively alter usage to reduce such periods. Machine learning strategies are utilized in the proposed system to estimate peak demand via past data, weather predictions, and other variables. The system will then alter energy use based on real-time data from smart meters along with other sensing devices to meet the projected demand. The simulation model will include several scenarios for testing the DR system’s flexibility, including a range of weather conditions, load profiles, and grid topologies. Several indicators, including peak demand reduction (80.04%), energy savings (38.09%), environmental consequences, and reaction time ( © 2024 Taylor and Francis Inc.. All rights reserved.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

An Evolution of Hybrid Bagging Technique in Chemoinformatic and Drug Discovery 2

An Evolution of Hybrid Bagging Technique in Chemoinformatic ...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Aluvala, Srinivas Kalshetty, Jagadevi N. Husain, Saif O. Kaur, Jagroop Thind, Harpreet Kaur Sr University School Of Computer Science And Engineering Telangana Warangal India Nitte Meenakshi Institute Of Technology Department Of Computer Science And Engineering Bengaluru India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq Punjabi University Department Of Computer Science And Engineering Patiala India Dayananda Sagar College Of Engineering Department Of Computer Science And Engineering Bengaluru India

ISBN: (纸本)9798350381665

The drug deals with every living organism on the earth, for classification of drugs based on their action is an important element in drug development. This research paper presents a machine learning model that predicts the action of a drug, utilizing a large drug network. The model integrates J-48 algorithm and random forest algorithm, and form the hybrid bagging technique with the neural network model demonstrating. The model uses the struck2vec data feature, which derived from the large network. Then the data features and dataset are trained on the hybrid bagging technique for drug classification according to the drug properties. The study's findings highlight the important of machine learning models in drug classification which offers a valuable tool for researchers and pharmaceutical companies in the drug development process. The output includes the top classes of drugs, the prediction of action and aiding in new drugs discovery with higher accuracy of 95.83% which is superior over other learning models. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

GFT Centrality Computation Based on Laguerre Polynomial Graph Filtering Method 13

GFT Centrality Computation Based on Laguerre Polynomial Grap...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Lee, Su-Ling Tseng, Chien-Cheng Chang Jung Christian University Department of Computer Science and Informationn Engineering Tainan Taiwan National Kaohsiung University of Science and Technology Department of Computer and Communication Engineering Kaohsiung Taiwan

ISBN: (纸本)9798350355079

Graph Fourier transform centrality (GFTC) is a valuable tool for identifying influential nodes within complex networks. However, applying the graph Fourier transform (GFT) to compute node centrality measures requires calculating the eigenvectors and eigenvalues of the graph Laplacian matrix. This eigen-decomposition is time-consuming, prompting the development of a graph filtering method to calculate GFTC directly from the network's importance signals, bypassing the need for eigen-decomposition. In this paper, the ideal transfer matrix of the graph filter is first derived from the definition of GFTC. Next, a Laguerre polynomial graph filter is designed to approximate this ideal transfer matrix as accurately as possible. The closed-form solution for the filter coefficients is obtained using the orthogonal properties of Laguerre polynomials. Third, the recursive relation of Laguerre polynomials is applied to derive an implementation structure that allows GFTC to be computed in a distributed manner. Finally, the proposed GFTC computation method is used to identify important stations in the Taipei metro network, demonstrating the effectiveness of the graph filtering method. © 2024 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models with Retrieval-Augmented Generation for an Interactive Slide Presentation System

Leveraging Large Language Models with Retrieval-Augmented Ge...

引用

2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024

作者： Chen, Ming-Che Wang, Ming-Shun Wu, Shang-Cian Lin, Min-Yu Chien, Chien-Yan Hsu, Ren-Guei Chang, Wan-Jung Chen, Liang-Bi Southern Taiwan University of Science and Technology Department of Electronic Engineering Tainan Taiwan National Kaohsiung University of Science and Technology Department of Electronic Engineering Kaohsiung Taiwan National Penghu University of Science and Technology Department of Computer Science and Information Engineering Penghu Taiwan

ISBN: (纸本)9798331530839

This paper proposes an interactive slide presentation system named Gen-tell-men, based on Large Language Models (LLM) and incorporating the Retrieval-Augmented Generation (RAG) framework. The Gen-tell-men system consists of an edge computing device integrated with a microphone, speakers, and display screen, along with a natural language processing server. The system automatically plays presentation content and responds to visitor inquiries by selecting and displaying relevant slides while generating corresponding voice explanations. Experimental results show that Gen-tell-men is highly efficient in selecting presentation slides related to the inquiries, with an accuracy rate of 0.82, achieving the goal of real-time and appropriate slide presentations and interactive Q & A. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

ML Based Intrusion Detection Scheme for various types of attacks in a WSN using C4.5 and CART classifiers

引用

Materials Today: Proceedings 2023年 80卷 3769-3776页

作者： Gite, Pratik Chouhan, Kuldeep Murali Krishna, K. Kumar Nayak, Chinmaya Soni, Mukesh Shrivastava, Amit Department of Computer Science and Engineering IPSA-IES Indore AB Road MP Indore India Department of Computer Science and Engineering I.T.S Engineering College Greater Noida India Department of Electronics and Communication Engineering Vignan's Institute of Information Technology Duvvada Andhra Pradesh Visakhapatnam India Faculty of Emerging Technology Sri Sri University Odisha751001 India Department of Computer Science & Engineering Jagran Lakecity University Bhopal India Department of Computer Science Engineering Swami Vivekanand College of Engineering Khandwa Road Near Tolnaka Vivekanand Knowledge City Indore India

A key component for preserving a WSN's integrity is designing an intrusion detection system (IDS). This article covers several sorts of security threats that may occur in a WSN. It proposes a detection of malicious nodes in a WSN. This system identifies four common assaults (i.e., black hole, wormhole, gray hole, and DDoS attacks) and is based on a Base Station machine learning (ML) algorithm (BS). The suggested ML algorithm continually analyzes data patterns from each node. Based on this technique, BS recognizes the network's harmful behavior and provides notifications to neighbor nodes to prevent attacker. First, the various assaults are examined and their characteristics are derived in terms of network parameters. Furthermore, the gathered pattern trains an ML algorithm. Then, the attacker node is effectively and properly classified within the BS. The NS2 simulator simulated the needed secure WSN. The experimental findings revealed excellent accuracy of the suggested method for attack detection. This precision can enhance network performance in terms of energy usage and packet delivery (PDR). © 2021

关键词： Base stations

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：