检索结果-内蒙古大学图书馆

2nd International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Ramanan, K. Anandakumar, A. Prakash, M. Santhosh Sivaraja, P.M. Maheswari, G. Uma Npr College of Engineering and Technology Department of Computer Science Engineering Tamil Nadu India Amrita College of Engineering Department of Computer Science Engineering Tamil Nadu India Rmk College of Engineering and Technology Department of Computer Science Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350325799

The security implications of gathering and analyzing data on criminal activity in researcher's everyday lives are not well understood. Forecasting and analyzing crime rates involves mining a database of criminal offenses for hidden trends. Everyday criminal behavior in different regions of the globe may be predicted by user approach. They can make inferences about the data set using data mining and machine learning techniques. This method facilitates a quicker resolution to the crime. Setting information is offered instead of an explanation for the crime. To better the field of criminology, they use the K-means clustering technique and the linear regression algorithm. Crime statistics may be analyzed on a weekly or monthly basis. © 2023 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Question Answering FAQ Bot Using Natural Language Processing 11th

Question Answering FAQ Bot Using Natural Language Processing

引用

11th International Conference on Intelligent Computing and Applications, ICRTC 2023

作者： Vijay, K. Sowmia, K.R. Ravikumar, S. Arockia Raj, Y. Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India Department of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Computer Science and Engineering PSNA College of Engineering and Technology Dindigul India

ISBN: (纸本)9789819717231

The BOT retorts with the precise results that help the user for the query and also requests them to rate the response to provide better results. The [frequently answered questions] BOT is a program developed through machine learning and natural language processing. It classifies the queries and results as key-value pairs and maps the response to the user query. It extricates itself by providing additional capabilities such as NLU processes and reinforcement learning. NLU helps the bot to make it convenient for an array of languages to meet the diverse expectations. Reinforcement learning retrieves user rating to provide better performance and search results. The project was developed due to a concern about fetching meticulous responses for specific service-related queries. The overall satisfaction rate of users in getting responses to the questions they post is devastating. The root cause for the proposed project has aimed at providing an environment for a people to find their answers at better accuracy and also respond to their satisfaction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Computational Web Drug Discovery Application forSARS- Cov-2 Disease Using Predictive and Analytical Approach 10

Computational Web Drug Discovery Application forSARS- Cov-2 ...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Hemkiran, S. Kartik, R. Aswath, S. Rathan Kabilan, K. Sudha Sadasivam, G. Psg Institute of Technology and Applied Research Dept. of Computer Science and Engineering Coimbatore India Psg College of Technology Dept. of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350384369

In response to the urgent need for coronavirus treatments, this research focuses on leveraging bioactivity data collection and processing for efficient drug discovery, employing computational methods to predict potential antiviral compounds. Exploratory data analysis was performed to identify patterns and trends, and various molecular descriptors were computed for the Mpro inhibitors in the descriptor dataset preparation step. A regression model was trained using the developed random forest algorithm to predict the bioactivity of new compounds against the standard value and compared with other regression models. Additionally, a web-based application was created using the random forest model to allow users to obtain predicted bioactivity values against Mpro by providing information about molecular structures. Machine learning-based bioactivity prediction offers an intriguing plan for drug discovery, and the proposed work provides a comprehensive workflow for COVID- 19 drug discovery. The web application provides a user-friendly interface for drug discovery researchers to evaluate the potential of compounds against the Mpro target quickly. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

An Approach for Securing IoT Data using Blockchain and Proxy Re-Encryption

An Approach for Securing IoT Data using Blockchain and Proxy...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Saradha, M. Keerthivasan, B. Arunachalam, M.P.L. Gnanaprakash, K. Nivitha, K. K. S. Rangasamy College of Technology Computer Science and Engineering Tiruchengode637215 India Vellore Institute of Technology Computer Science and Engineering Vellore632014 India

ISBN: (纸本)9798350359688

The development of Internet of Things (IoT) devices has resulted in exponential data generation, creating substantial problems to guaranteeing the security and privacy of sensitive information. Traditional security mechanisms frequently fall short of meeting the unique needs of IoT contexts, demanding creative solutions. This research presents a unique way for improving IoT data security by leveraging blockchain technology and proxy re-encryption techniques. Our technique seeks to provide strong data confidentiality, integrity, and access control in IoT ecosystems by combining blockchain's immutability and decentralisation with the efficiency of proxy re-encryption. We go over the design, working principles, and implementation concerns of our proposed solution, emphasising its potential benefits and resolving any issues. Through study and testing, we demonstrate the efficacy and viability of our strategy to protecting IoT data from diverse security threats. © 2024 IEEE.

关键词： Access Control Blockchain Confidentiality Data Security Integrity Internet of Things (IoT) Proxy Re-encryption

来源：评论

学校读者我要写书评

暂无评论

A Novel Visual Transformer for Long-Distance Pipeline Pattern Recognition in Complex Environment

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2933-2945页

作者： Zhu, Chengyuan Pu, Yanyun Yang, Kaixiang Yang, Qinmin Chen, C.L. Philip Zhejiang University College of Control Science and Engineering Zhejiang Hangzhou310007 China Huzhou Institute of Zhejiang University Zhejiang Huzhou313000 China South China University of Technology College of Computer Science and Engineering Guangdong Guangzhou510006 China

The effective warning of dangerous events along long-distance pipelines is critical to ensure the safety of oil and gas transportation. Distributed optical fiber sensing (DOFS) technology can assist operators to identify threat vibration signals. However, due to the complex and changeable environmental background noise along long-distance pipeline, most of the existing methods only extract one-dimensional features of the signal, making it difficult to distinguish various types of environmental noise, strong interference, and dangerous events. Besides, the samples of different classes in the actual scene are unbalanced. The sample size of dangerous events is often smaller than others. To address these problems, we use image encoding to transform the time series signals collected by the DOFS system into image data, and fully extract the time dependence and the correlation between different elements in the signal. Moreover, a visual transformer model PipelineADWinT is proposed. The self-attention mechanism of diagonal-axial window designed in this model can perfectly combine image encoding features, and obtain local to global multiscale features through hierarchical structure. By optimizing the loss function, the model's ability to handle the class imbalance problem is enhanced. The experimental results show that PipelineADWinT has more comprehensive classification performance and fewer false alarms than all the baseline models, which proves the effectiveness and superiority of the model. © 2020 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing VANET Efficiency with ACRR Technique for Improved Traffic Management and Network Scalability

Enhancing VANET Efficiency with ACRR Technique for Improved ...

引用

2024 International Conference on science, technology, engineering and Management, ICSTEM 2024

作者： Karthick, K. Talari, Praveen Nishadevi, V. Krishna Prakash, R. Asokan, R. Velusamy, A. Dept. of Computer Science and Engineering Kongunadu College of Engineering and Technology Tamilnadu Trichy India Dept. of Computer Science and Engineering Vignan Bharathi institute of technology Telangana Hyderabad India Dept. of Computer Science and Engineering Mahendra College of Engineering Tamilnadu Salem India Dept. of Information Technology Sona College of Technology Salem India Dept. of Electronics and Communication Engineering Kongunadu College of Engineering and Technology Tamilnadu Trichy India Dept. of Information Technology Sona College of Technology Tamil Nadu Salem India

ISBN: (纸本)9798350376913

The role of Vehicular Ad Hoc Networks (VANETs) is crucial in enabling Intelligent Transportation System (ITS) technologies such as safe financial transactions, media applications, and effective traffic control. As traffic increases, the topology of vehicular networks is in constant flux, and the sparse distribution of vehicles, particularly on highways, presents challenges for network scalability. This situation makes it difficult for cars to keep consistent routes inside the network, which affects the stability of the network. To address these challenges, the developed Adaptive-ant Colony based Randomized Recommendation (ACRR) technique emerges as a unique solution for enhancing VANETs by reducing travel time. In instances of high traffic density on busy roads, the ACRR algorithm is effectively utilized to group vehicles. Leveraging data collected from these densely populated road segments, the system identifies congestion-prone areas and formulates optimal vehicle routes based on customized vehicle groupings. The framework's performance evaluation encompasses various parameters, including packet loss, message transmission rate, energy consumption, and average cluster growth. The proposed VANET framework, empowered by the ACRR algorithm, achieves an impressive message transmission rate of approximately 80%. In comparison, alternative methods like Re-RouTE exhibit a limited transmission rate of 70%, while others such as Net Run Rate (NRR), DIVERT 30, and DIVERT-60 demonstrate rates below 20%. Furthermore, the framework's parcel loss is significantly reduced to only 33% of that observed in the standard VANET framework. As a result, the ACRR algorithm integrated into the VANET framework demonstrates notable efficiency when compared to other approaches. It is crucial to recognize that, even with a refined technique, managing traffic congestion remains challenging if drivers disregard the recommended routing suggestions. Overall, this research offers insights into the p

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Wireless Sensor Networks: Revolutionizing Explosive Detection 5

Wireless Sensor Networks: Revolutionizing Explosive Detectio...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Sujith Kumar, P.S. Anand, C. Vasuki, N. Ramesh, V. Santhoshkumar, S.P. Sree Buddha College of Engineering Department of Computer Science and Engineering Kerala Alappuzha India Nandha College of Technology Department of Information Technology Erode India Government College of Engineering Department of Computer Science and Engineering Erode India School of Computing Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Avadi India

ISBN: (纸本)9798331518097

One of the important technologies for protecting civilian life from terrorist attacks is explosive detection techniques. The global incidence of terrorist activities has been considerably reduced by the development of explosive detection techniques, which has been made possible by ongoing technology improvements. Wireless sensor networks (WSNs) are one of these developments that has become an innovative tool for explosives detection. This work explores recent empirical research on the application of WSNs to explosives detection and includes statistical analysis of the investigations. Wireless sensor network with compatible specialized sensors is required for effective explosive detection. Three main wireless sensor system aspects that are relevant to explosives detection are covered in this research. It first looks at how scalable wireless sensors are in terms of explosives detection technologies. In the second section, it looks at the mobility and communication capabilities of WSNs and sensors in explosives detecting systems. Finally, it highlights potential hazards and weaknesses and addresses the crucial topic of data security inside wireless sensor networks used for explosive detection. The study also suggests incorporating drone assisted detection as a novel way to improve the coverage and effectiveness of explosives detection systems, adding to the continuous advancement of security technologies meant to shield civilian populations from terrorist threats. © 2024 IEEE.

关键词： Terrorism

来源：评论

学校读者我要写书评

暂无评论

SGTP: A Spatiotemporal Generalized Trajectory Publishing Method With Differential Privacy

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第3期14卷 2233-2247页

作者： Qiu, Shuyuan Pi, Dechang Wang, Yanxue Xu, Tongtong College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao266590 China College of Computer and Cyber Security Hebei Normal University Shijiazhuang050024 China

With the rapid development of location-based service technology, the leakage of trajectory privacy has become more and more serious. In order to solve the problems of insufficient privacy protection and low availability of published data in the existing trajectory privacy protection models, we propose a spatiotemporal generalized trajectory data publishing algorithm SGTP based on differential privacy. Firstly, a spatiotemporal generalization method of trajectories based on clustering is designed. The temporal location set is divided by a density peak trajectory clustering algorithm (DPTC), and the location is probabilistically generalized combined with an exponential mechanism to hide the real location information of users. Secondly, random noise is added to the generalized trajectory statistics by the Laplace mechanism, and the noise is post-processed by consistency constraints to improve the utility of the published data without affecting the privacy of the trajectories. Finally, we theoretically demonstrate that SGTP strictly satisfies differential privacy. Experimental results based on publicly available data show that SGTP can effectively protect user privacy and guarantee data utility and at the same time has a higher execution efficiency. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Hybrid Teaching Learning Approach for Improving Network Lifetime in Wireless Sensor Networks

引用

computers, Materials & Continua 2022年第1期70卷 1975-1992页

作者： P.Baskaran K.Karuppasamy Easwari Engineering College Chennai600089India Computer Science and Engineering RVS College of Engineering&TechnologyCoimbatore641402India

In a wireless sensor network(WSN),data gathering is more effectually done with the clustering *** is a critical strategy for improving energy efficiency and extending the longevity of a *** modeling-based clustering is proposed to enhance energy efficiency where nodes that hold higher residual energy may be clustered to collect data and broadcast it to the base ***,existing approaches may not consider data redundancy while collecting data from adjacent nodes or overlapping ***,an improved clustering approach is anticipated to attain energy efficiency by implementingMapReduction for regulatingmapping and reducing complexity in routing mechanisms for eliminating redundancy and *** order to optimize the network performance,this work considers intelligent behaviors’to adapt with network changes and to introduce computational intelligence *** the proposed research,improved teaching learning based optimization is used to evaluate the coordinates of target nodes and nodes upgradation for determining energy *** upgradation is performed by integratingMap reduction to attain modification in Hop size of *** variation reduces communication ***,network lifetime is increased,and redundancy is *** comparingwith existing approaches here,sleep and wake-up nodes are considered for data *** proposed algorithm clearly demonstrates 50%,16%&12%improvement in nodes lifetime,residual energy and throughput respectively compared to other *** it shows progressive improvement in reducing average waiting time,average queuing time and average energy utilization as 30%,20%and 46%*** has been done in NS-2 environment for distributed heterogeneous networks.

关键词： Map reduction optimization Teaching-learning energy efficiency network lifetime heterogeneous network

来源：评论

学校读者我要写书评

暂无评论

Secure Channel Creation for Task Delivery in Vehicular Cloud Computing to Avoid Denial of Service (DoS) 3

Secure Channel Creation for Task Delivery in Vehicular Cloud...

引用

3rd International Conference on Automation, Computing and Renewable Systems, ICACRS 2024

作者： Meenambika, A. Pavalarajan, S. Lavanya, N. Anu Jerom, B. Ajith Divya, S. Department of Computer Science and Business Systems PSNA College of Engineering and Technology Dindigul India PSNA College of Engineering and Technology Dindigul India Department of Artificial Intelligence and Data Science PSNA College of Engineering and Technology Dindigul India

ISBN: (纸本)9798331532420

Vehicular Cloud Computing (VCC) offers a promising platform for supporting various automotive applications and services. However, its distributed and dynamic nature makes it susceptible to Denial-of-Service (DoS) attacks, particularly during channel establishment. This research proposes a comprehensive approach to mitigate these risks by integrating a suite of security mechanisms. These include rate-limiting, resource management, traffic analysis, access control, authentication, encryption, intrusion detection, behavioral analysis, and blacklisting/whitelisting techniques. By incorporating these measures, the proposed approach enhances the security and reliability of VCC, ensuring the availability of critical automotive services and protecting vehicles from the impact of DoS attacks. © 2024 IEEE.

关键词： Cloud platforms

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：