检索结果-内蒙古大学图书馆

Drone-Based Intelligent System for Social Distancing Compliance Using YOLOv5 and YOLOv6 with Euclidean Distance Metric

引用

SN computer science 2024年第8期5卷 1-19页

作者： Parkavi, A. Alex, Sini Anna Pushpalatha, M.N. Shukla, Prashant Kumar Pandey, Ankur Sharma, Sachin Department of Computer Science and Engineering M S Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering (AI and ML) M S Ramaiah Institute of Technology Bangalore India Department of Information Science and Engineering M S Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur 522302 India Department of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur India Manav Rachna International Institute of Research and Studies Faridabad India

The COVID-19 pandemic forced rigorous social distancing measures to be put in place to halt the virus’s spread;compliance was extremely difficult. In response, we have designed a highly advanced intelligent drone system that maintains and controls distance measures following social distance principles through advanced machine learning skills. This paper describes an intelligent monitoring and compliance system in public places using drone technology with a focus on social distance requirements. Boosting the efficiency of human detection in real-time video streams acquired by drones, our solution employs the You Only Look Once version 5 (YOLOv5) and YOLO version 6 (YOLOv6) object detection algorithms which are the most potent computer vision tools today. The distances between the recognized individuals are computed based on the Euclidean distance measurement to distinguish cases of nonadherence to social distance measures. Our technique integrates the recently developed deep learning models with aerial imagery and monitoring to make it easily scalable for population health surveillance. Thus, we prove impressively that the underlying inventive method works well in different environmental conditions and can potentially contribute to people’s safety in the event of a pandemic. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： COVID-19 Drones Euclidean distance metric Social distancing YOLOv6

来源：评论

学校读者我要写书评

暂无评论

Where am I? Large Language Models Wandering between Semantics and Structures in Long Contexts

Where am I? Large Language Models Wandering between Semantic...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Koo, Seonmin Kim, Jinsung Jang, YoungJoon Park, Chanjun Lim, Heuiseok Department of Computer science and Engineering Korea University Korea Republic of Upstage AI

ISBN: (纸本)9798891761643

As the utilization of Large Language Models (LLMs) becomes more widespread, there is a growing demand for their ability to handle more complex and longer external knowledge across various use cases. Most existing evaluations of the open-ended question answering (ODQA) task, which necessitates the use of external knowledge, focus solely on whether the model provides the correct answer. However, even when LLMs answer correctly, they often fail to provide an obvious source for their responses. Therefore, it is necessary to jointly evaluate and verify the correctness of the answers and the appropriateness of grounded evidence in complex external contexts. To address this issue, we examine the phenomenon of discrepancies in abilities across two distinct tasks-QA and evidence selection-when performed simultaneously, from the perspective of task alignment. To verify LLMs' task alignment, we introduce a verification framework and resources considering both semantic relevancy and structural diversity of the given long context knowledge. Through extensive experiments and detailed analysis, we provide insights into the task misalignment between QA and evidence selection. Our code and resources can be found at https://***/seonminkoo/Wai. © 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

Classifying Misinformation of User Credibility in Social Media Using Supervised Learning

引用

computers, Materials & Continua 2023年第5期75卷 2921-2938页

作者： Muhammad Asfand-e-Yar Qadeer Hashir Syed Hassan Tanvir Wajeeha Khalil Department of Computer Science Center of Excellence in Artificial Intelligence(CoE-AI)Bahria UniversityIslamabad44000Pakistan Department of Computer Science and Information Technology University of Engineering and TechnologyPeshawar25000Pakistan

The growth of the internet and technology has had a significant effect on social *** information has become an important research topic due to the massive amount of misinformed content on social *** is very easy for any user to spread misinformation through the ***,misinformation is a problem for professionals,organizers,and ***,it is essential to observe the credibility and validity of the News articles being shared on social *** core challenge is to distinguish the difference between accurate and false *** studies focus on News article content,such as News titles and descriptions,which has limited their ***,there are two ordinarily agreed-upon features of misinformation:first,the title and text of an article,and second,the user *** the case of the News context,we extracted different user engagements with articles,for example,tweets,i.e.,read-only,user retweets,likes,and *** calculate user credibility and combine it with article content with the user’s *** combining both features,we used three Natural language processing(NLP)feature extraction techniques,i.e.,Term Frequency-Inverse Document Frequency(TF-IDF),Count-Vectorizer(CV),and Hashing-Vectorizer(HV).Then,we applied different machine learning classifiers to classify misinformation as real or ***,we used a Support Vector Machine(SVM),Naive Byes(NB),Random Forest(RF),Decision Tree(DT),Gradient Boosting(GB),and K-Nearest Neighbors(KNN).The proposed method has been tested on a real-world dataset,i.e.,“fakenewsnet”.We refine the fakenewsnet dataset repository according to our required *** dataset contains 23000+articles with millions of user *** highest accuracy score is 93.4%.The proposed model achieves its highest accuracy using count vector features and a random forest *** discoveries confirmed that the proposed classifier would effectively classify misinformat

关键词： Misinformation user credibility fake news machine learning

来源：评论

学校读者我要写书评

暂无评论

A Traffic-Aware and Cluster-Based Energy Efficient Routing Protocol for IoT-Assisted WSNs

引用

computers, Materials & Continua 2024年第8期80卷 1831-1850页

作者： Hina Gul Sana Ullah Ki-Il Kim Farman Ali Department of Computer and Software Technology University of SwatMingora19130Pakistan Department of Computer Science and Engineering Chungnam National UniversityDaejeon34134Republic of Korea Department of Applied AI Sungkyunkwan UniversitySeoul03063Republic of Korea

The seamless integration of intelligent Internet of Things devices with conventional wireless sensor networks has revolutionized data communication for different applications,such as remote health monitoring,industrial monitoring,transportation,and smart *** and reliable data routing is one of the major challenges in the Internet of Things network due to the heterogeneity of *** paper presents a traffic-aware,cluster-based,and energy-efficient routing protocol that employs traffic-aware and cluster-based techniques to improve the data delivery in such *** proposed protocol divides the network into clusters where optimal cluster heads are selected among super and normal nodes based on their residual *** protocol considers multi-criteria attributes,i.e.,energy,traffic load,and distance parameters to select the next hop for data delivery towards the base *** performance of the proposed protocol is evaluated through the network simulator *** different traffic rates,number of nodes,and different packet sizes,the proposed protocol outperformed LoRaWAN in terms of end-to-end packet delivery ratio,energy consumption,end-to-end delay,and network *** 100 nodes,the proposed protocol achieved a 13%improvement in packet delivery ratio,10 ms improvement in delay,and 10 mJ improvement in average energy consumption over LoRaWAN.

关键词： Internet of Things wireless sensor networks traffic load clustering routing energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Enhancing Data Privacy and Accountability in Smart Grids with Blockchain Technology

Enhancing Data Privacy and Accountability in Smart Grids wit...

引用

Electrical Electronics and Computing Technologies (ICEECT), International Conference on

作者： G. Indiravathi M. P. Kumar Anumulagundam Usha Roshan Kumar T. Lohith Shaik Shahid Department of Computer Science and Engineering Siddharth Institute of Engineering & Technology Chittoor Andhra Pradesh India Department of Computer Science and Engineering (AI&ML) Siddharth Institute of Engineering & Technology Chittoor Andhra Pradesh India

ISBN: (数字)9798350378092

ISBN: (纸本)9798350378108

Smart grids offer promising opportunities for energy efficiency but raise concerns about data privacy and transparency. This paper presents a new framework for Secure and Auditable Private Data Sharing designed specifically for smart grids, with a focus on its functionality as a password manager. By utilizing smart contracts and blockchain technology, the framework creates explicit guidelines for data usage that guarantee clear oversight of data access and intended uses. In addition to managing smart grid data, the framework securely stores passwords and credentials, providing users with a comprehensive solution for data security and access management. The use of off-chain smart contract execution and trusted execution environments maximizes performance. To further assure transactional reliability during the result dissemination and payment procedures, the framework employs a two-phase atomic delivery mechanism. Energy service providers gain from optimum contracts because they encourage high-quality data exchange and customer participation through the use of contract theory. Extensive simulations validate the efficacy of the proposed approach, enabling users to securely access their data remotely through a cloud platform integrated with open-source services.

关键词： Data privacy Data security Smart contracts Passwords Reliability theory Energy efficiency Data models Smart grids Blockchains Guidelines

来源：评论

学校读者我要写书评

暂无评论

Aspect term extraction and snake driving training-based optimization-enabled deep learning for Facebook sentiment analysis

引用

Knowledge and Information Systems 2025年 1-30页

作者： Kotagiri, Srividya Owk, Mrudula Priyanka, Tata Sowjanya, A. Mary Department of CSE-AI&ML GMR Institute of Technology Rajam India Department of Computer Science and Engineering GITAM School of Technology GITAM University Visakhapatnam India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Hyderabad India Department of CS&SE College of Engineering (A) Andhra University Visakhapatnam India

In this modern world, social media plays a vital role in communicating with each other across the globe. Sentiment analysis plays an essential role on social media platforms in tracking online conversations among themselves and with competitors in real time. They also gain measurable insights about how positively or negatively they are viewed by the users. In this research, a Facebook sentiment analysis approach named snake driving training-based optimization-enabled random multimodal deep learning (SDTBO_RMDL) is developed. Initially, the acquisition of Facebook review from the BuzzFeed News dataset is done. Then, to break down the sentence into tokens, BERT tokenization is carried out. After that, the aspect terms in the sentences are identified using the ATE. Next, the extraction of relevant features is done on the raw data using feature extraction. Then, sentiment analysis classification is performed using RMDL, where the network parameters are optimally tuned using the proposed SDTBO. Here, the SDTBO is the integration of driving training-based optimization and snake optimizer. Finally, the classified output comes from the RMDL. Thus, the Facebook reviews are categorized as positive as well as negative. The performance of SDTBO_RMDL is of values 0.948, 0.974, and 0.961 for precision, recall, and F1-score, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Model for Spectrum Sensing Classification in Cognitive Radio Networks

Hybrid Deep Learning Model for Spectrum Sensing Classificati...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Padmakala, S. Alsalami, Zaid Supriya, R. Sahana, M.P. Deepthi, Palakurthy Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Ise Bengaluru India Dayananadha Sagar College of Engineering Department of Cse Bangalore India Gokaraju Rangaraju Institute of Engineering and Technology Department of Ai&ml Hyderabad India

ISBN: (纸本)9798350375442

Spectrum sensing (SS) uses cognitive radio technology at base transceiver stations in order to discover the licensed spectra used by Primary Users (PUs). This enables the SUs to make wireless network transmissions without causing interference. Cognitive Radio Networks (CRNs) help in the problem on the restricted radio frequency spectrum that wireless devices depend on. For enhanced classification of SS in CRN, the proposed research focused on using hybrid Deep Learning (DL) model by integrating Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). Initially, the data is generated through eight modulation types considering the varied oversampling rate. The spatial features of signal are extracted through CNN and temporal features are identified by LSTM. the Cooperative Spectrum Sensing (CSS) algorithm is integrated increase the reliability of spectrum detection. The hyper parameters of the trained model are fine tuned for enhanced classification of SS. Experimental results showed that the proposed LSTM-CNN-CSS achieved sensing accuracy at 98.34%, precision at 95.62%, recall at 96.77% when compared to the traditional SS classification models such as Ensemble Convolutional Recurrent Neural Network (ECRNN) and LSTM-Extreme Learning Machine (LSTM-ELM). © 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

Securing Wireless and Optical Networks: Advanced Strategies for Network and Information Security in Modern Communication Systems

Securing Wireless and Optical Networks: Advanced Strategies ...

引用

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

作者： Dhasmana, Gulshan Sharma, Vishal Boob, Nandini Shirish Aravind, K. Reddy, R. Akhilesh Yadav, Kanchan Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Lovely Professional University Phagwara India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India New Horizon College of Engineering Department of Electronics and Communication Engineering Bangalore India MLR Institute of Technology Department of CSE-AI&ML Telangana Hyderabad India GLA University Department of Electrical Engineering Mathura India

ISBN: (纸本)9798331512965

In the era of rapidly changing communication systems, securing wireless and optical networks has become of essence to protect sensitive data and ensure operation. This study addresses network and information security in current communication systems by studying cutting edge techniques to enhance network and information security in wireless and optical networks. The wireless networks are convenient and may be moved around, but they are also prone to hacking, illegal access or some other cyberattacks. As optical networks possess both a large capacity and relatively low latency, it is not without special security issues such as fibre tapping and signal jamming. This study presents detailed analyses of state of the art authentication techniques, intrusion detection systems (IDS), and encryption algorithms specifically designed for these networks. Then there are, such as Quantum Key Distribution (QKD) which almost assuarly unbreakable techniques are examined alongside conventional cryptographic methods. Additionally, anomaly detection based on machine learning is explored for real time threat identification in optical and wireless channels. It stresses the need of the cross domain solutions and multi layered security frameworks covering the network layer and the physical security measures. Through case studies and recent developments in cyber threats and network resilience, this article provides a thorough understanding of how these tactics could be used to make networks such as wireless network and optical network more resilient against increasing cyber risks. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Comparision of Principal Component Analysis, K-means, and Generative Adversarial Network for Compression and reconstruction of medical image

Comparision of Principal Component Analysis, K-means, and Ge...

引用

Artificial Intelligence and Data engineering (aiDE), International Conference on

作者： Anusha Prashanth Shetty Deepthi L Raksha Puthran Surendra Shetty Mohammad Anzil Parveez Shravan Kumar Department of Master of Computer Applications NMAM Insitute of Technology Nitte (Deemed to be University) Nitte Karkala India Department of Computer Science and Engineering (AI&ML) Sahyadri College of Engineering and Management Mangalore India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

Medical images are essential in healthcare, but their large file sizes present challenges for storage and transmission. This study proposes a framework for compressing color medical images while preserving key visual information. We apply three compression models: Principal Component Analysis (PCA), K-Means clustering, and Generative Adversarial Networks (GANs), and evaluate their performance based on Compression Ratio (CR), Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), and Structural Similarity Index (SSIM). K-Means with 100 clusters outperforms the other models, achieving the highest compression (CR of 1.20), with excellent image quality (PSNR of 66.77 dB, SSIM of 1.0000). PCA shows moderate performance with a CR of 2.45, while GAN provides the least effective compression and image quality. These results demonstrate that K-Means offers the best trade-off between compression and image fidelity.

关键词： Measurement Image quality Analytical models Image coding PSNR Medical services Generative adversarial networks Image reconstruction Principal component analysis Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Human Action Recognition Using Difference of Gaussian and Difference of Wavelet

引用

Big Data Mining and Analytics 2023年第3期6卷 336-346页

作者： Gopampallikar Vinoda Reddy Kongara Deepika Lakshmanan Malliga Duraivelu Hemanand Chinnadurai Senthilkumar Subburayalu Gopalakrishnan Yousef Farhaoui Department of Computer Science and Engineering(AI&ML) CMR Technical CampusHyderabad 501401India. Department of Information Technology Kakatiya Institute of Technology and ScienceWarangal 506015India. Department of Electronics and Communication Engineering Malla Reddy Engineering College for Women(Autonomous)Hyderabad 500100India. Department of Computer Science and Engineering S.A.Engineering College(Autonomous)Thiruverkadu 600077India. Department of Electronics and Communication Engineering Saveetha Institute of Medical and Technical Sciences(SIMATS)Chennai 602105India. Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyChennai 600062India. IDMS Team STI LaboratoryFaculty of Sciences and TechniquesMoulay Ismail University of MeknèsErrachidia 25003Morocco.

Human Action Recognition(HAR)attempts to recognize the human action from images and *** major challenge in HAR is the design of an action descriptor that makes the HAR system robust for different environments.A novel action descriptor is proposed in this study,based on two independent spatial and spectral *** proposed descriptor uses a Difference of Gaussian(DoG)filter to extract scale-invariant features and a Difference of Wavelet(DoW)filter to extract spectral *** create a composite feature vector for a particular test action picture,the Discriminant of Guassian(DoG)and Difference of Wavelet(DoW)features are *** Discriminant Analysis(LDA),a widely used dimensionality reduction technique,is also used to eliminate duplicate ***,a closest neighbor method is used to classify the *** and UCF 11 datasets were used to run extensive simulations of the suggested strategy,and the accuracy assessed after the simulations were run on Weizmann datasets for five-fold cross validation is shown to perform *** average accuracy of DoG+DoW is observed as 83.6635%while the average accuracy of Discrinanat of Guassian(DoG)and Difference of Wavelet(DoW)is observed as 80.2312%and 77.4215%,*** average accuracy measured after the simulation of proposed methods over UCF 11 action dataset for five-fold cross validation DoG+DoW is observed as 62.5231%while the average accuracy of Difference of Guassian(DoG)and Difference of Wavelet(DoW)is observed as 60.3214%and 58.1247%,*** the above accuracy observations,the accuracy of Weizmann is high compared to the accuracy of UCF 11,hence verifying the effectiveness in the improvisation of recognition accuracy.

关键词： human action recognition difference of Gaussian difference of wavelet linear discriminant analysis Weizmann UCF 11 accuracy

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：