检索结果-内蒙古大学图书馆

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

作者： Sharma, Divya Sharma, Shilpa Patil, Harshal Bhatnagar, Vaibhav Manipal University Jaipur Department of Computer Applications Jaipur India Symbiosis Institute of Technology Symbiosis International Computer Science and Engineering Pune India

ISBN: (纸本)9798350335774

Image dehazing and image defogging work towards the same goal, which is to reconstruct hazy or foggy images by eliminating noise. Among the many dehazing and defogging algorithms available, Dark Channel Prior (DCP) is among the most effective algorithm. DCP employs the dark pixels from the noisy image to perform image reconstruction using the standard four-step process. In this paper, we implement DCP single image dehazing for license plate images. Specifically, the transmission map refinement was implemented using the guided filter. The implemented model performs the DCP implementation along with its five important parameter evaluations and analyzes the performance. The paper concludes with a comparative analysis for five parameters that are patch size, epsilon value, window radius, value of and finally pixel values. © 2023 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Blockchain based Secure Erlang Server for Request based Group Communication over XMPP

Blockchain based Secure Erlang Server for Request based Grou...

引用

2023 International Conference on Advances in Intelligent Computing and applications, AICAPS 2023

作者： Johnpaul, C.I. Vivekanandan, Manojkumar Premkamal, Praveen Kumar Ramya, R. St. Thomas College Department of Computer Science and Applications Kerala Thrissur India Srm University-AP School of Engineering and Applied Sciences Department of Computer Science and Engineering Andhra Pradesh Amaravati India Kamaraj College of Engineering and Technology Department of Computer Science and Engineering Virudhunagar India

ISBN: (纸本)9798350333817

Many real world activities in computer science scenarios are linked with concurrency and security related issues and have to handle large number of processes to be executed in parallel with false safe security solutions. There are many traditional methods in programming languages to handle concurrency. Concurrency is one of the major issues that need to be addressed by most of the servers when dealing with the group communication operations. Security of the data as well as the credibility of the users are the other aspects when a group of users involve in real-time communication. Many light-weighted servers are designed to carryout elementary operations of request handling, file sharing etc. In design of such servers having large number of clients, the request service handling will be based on the individual server programs. Keeping track of individual credibility and establishing concurrency solutions in server design is challenging. The whole work describes the significance and implementation of an Erlang based XMPP server in comparison with a Python based XMPP server with a view to service the client request handling operations for sending messages, group chatting, buddy-list creation, presence identification integrated with XML messaging pattern as per the XMPP protocol. We also accomplish the security and credibility of the users using a blockchain based interface that keep track of user activities during group communication. The security analysis is also performed for blockchain based interface. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection Review: Concepts, Tools, Research gaps, and Possible solutions 7

Fake News Detection Review: Concepts, Tools, Research gaps, ...

引用

7th International Conference on Internet applications, Protocols, and Services, NETAPPS 2024

作者： Yakkundi, Sapana Patil, Rudragoud Goudar, Swetha Indudhar Department of Computer Science and Engineering KLS Gogte Institute of Technology Karnataka Belagavi India Department. of Master of Computer Applications KLS Gogte Institute of Technology Karnataka Belagavi India

ISBN: (纸本)9798331519513

The increasing number of social platforms means that there is a rapid expansion of online data. However, not all of this data can be trusted, as some users intentionally manipulate information to spread false news for personal or political reasons. Fake news can significantly impact public perception and societal outcomes. Its widespread influence was especially noticeable during the 2016 United States election cycle, leading to heated discussions about its role and consequences. Given the changing nature of news, real-time data processing has become essential for effectively identifying and countering misinformation. This research provides a comprehensive examination of the datasets, tools, and techniques utilized for detecting and combating fake news. Many researchers have developed models based on specific datasets, limiting their scope to particular domains. A thorough review of advanced models for real-time fake news detection highlights existing research gaps. The analysis of the review reveals that numerous datasets used in the literature are outdated, and there is a methodological challenge associated with the use of traditional machine learning approaches. With the continuous evolution of news, there is an urgent demand for utilizing sophisticated deep learning models for the automated, real-time verification of misinformation. This research presents promising approaches to tackle the challenge of detecting fake news. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Video Anomaly Detection Based on HSOE-FAST Modified Deep Neural Network

引用

SN computer science 2024年第5期5卷 1-11页

作者： Gupta, Anil Kumar Sharma, Rupak Ojha, Rudra Pratap Department of Computer Science and Engineering SRM Institute of Science and Technology NCR Campus Modinagar Uttar Pradesh Ghaziabad India Department of Computer Applications SRM Institute of Science and Technology NCR Campus Modinagar Uttar Pradesh Ghaziabad India Department of Computer Science and Engineering G.L. Bajaj Institute of Technology and Management (GLBITM) (Affiliated to AKTU) Uttar Pradesh Greater Noida India

In recent times, video surveillance has become indispensable for public security, leveraging computer vision advancements to analyze and comprehend lengthy video feeds. Anomaly detection and classification stand out as crucial components of this technology. Anomaly detection's primary objective is to swiftly identify irregularities within a given timeframe. It is promising to use Deep Neural Network (DNN) approaches for anomaly detection because they combine the ideas of deep learning and reinforcement learning, enabling artificial agents to learn from and gain insights from real-world data. A modified DNN (Deep Neural Network) technique known as HSOE-FAST (Histo sigmoid of Orientation and Enthalpy with Fast Accelerated Segment Test) was proposed in this study. From the dataset, the input is obtained. Initially, the input is pre-processed using a Gaussian filter followed by the feature extraction using the HSOE-FAST method and finally classification is done using the modified DNN approach. Compared to other approaches, our suggested solution achieves an accuracy of almost 99% while overcoming the shortcomings of the existing methodologies. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： DNN Enthalpy Fast Accelerated Segment Test Histo sigmoid of Orientation Video anomaly detection

来源：评论

学校读者我要写书评

暂无评论

IoT-Aided Charity-Redistribution of Excess Food 2

IoT-Aided Charity-Redistribution of Excess Food

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Yogananth, V.S. Balasubramani, M. Vellore Institute of Technology Department of Computer Applications Tamil Nadu Vellore India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798350328202

The utilization of the Internet of Things (IOT) has shown significant potential in various aspects of daily life, yet its application in addressing social issues remains underdeveloped. India, with a substantial number of orphanages, faces challenges in efficiently distributing crucial information, hindering donors from obtaining accurate data on food reserves. This project proposes an IOT-based system to tackle this issue, using Node MCU IOT devices connected to sensors that relay data through a network, accessible and monitorable via web applications. The proposed system architecture aims to bridge the gap between those who waste food and those in poverty who desperately need it. We intend to facilitate food donations by implementing smart containers equipped with IOT technology. These containers can detect excess food waste and share this information via a GSM module with trusted charitable organizations. This application is designed to serve three main stakeholders: service providers, donors, and food recipients in need. By creating smart containers, we ensure that donated food reaches the right individuals. We prioritize collaborating with trusted charities to oversee the distribution process. Only authorized charity members can access and distribute the food stored in these containers, ensuring that it reaches those who need it most. © 2024 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

pFedCal: Lightweight Personalized Federated Learning with Adaptive Calibration Strategy

引用

IEEE Transactions on Services Computing 2025年第3期18卷 1627-1640页

作者： Deng, Dongshang Wu, Xuangou Zhang, Tao Xiang, Chaocan Zhao, Wei Xu, Minrui Kang, Jiawen Han, Zhu Niyato, Dusit Anhui University of Technology School of Computer Science and Technology Anhui Province Key Laboratory of Digital Twin Technology in Metallurgical Industry Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Ma'anshan243002 China Beijing Jiaotong University School of Cyberspace Science and Technology Beijing100044 China Anhui Provincial Key Laboratory of Digital Twin Technology in Metallurgical Industry Anhui243002 China Chongqing University College of Computer Science Chongqing400044 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Guangdong University of Technology School of Automation Guangzhou510062 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

Federated learning (FL) is a promising artificial intelligence framework that enables clients to collectively train models with data privacy. However, in real-world scenarios, to construct practical FL frameworks, several challenges have to be addressed, including statistical heterogeneity, constrained resources, and fairness. Therefore, we first investigate an aggregation gap caused by statistical heterogeneity during local model initialization, which not only causes additional computational overhead for clients but also leads to the degradation of fairness. To bridge this gap, we propose pFedCal, a novel personalized federated learning with lightweight adaptive calibration strategy that performs calibration compensation through the prior knowledge of clients. Specifically, we introduce compensation for each client at the model initialization, with the compensation derived from the global gradient and the latest gradient bias. To enhance the calibration effect, we introduce a smoothing-based calibration strategy, and we design an adaptive calibration strategy. A representative example demonstrates that the proposed calibration and smoothing strategies improve fairness for clients. The theoretical analysis indicates that with an appropriate learning rate, pFedCal converges to a first-order stationary point for non-convex loss functions. Comprehensive experimental results show that pFedCal achieves faster convergence, higher accuracy, and improved fairness than the state-of-the-art methods. © 2008-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

LECF: recommendation via learnable edge collaborative filtering

引用

science China(Information sciences) 2022年第1期65卷 116-130页

作者： Shitao XIAO Yingxia SHAO Yawen LI Hongzhi YIN Yanyan SHEN Bin CUI School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing Key Lab of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications School of Information Technology and Electrical Engineering The University of Queensland Department of Computer Science and Engineering Shanghai Jiao Tong University Department of Computer Science and Technology Peking University National Engineering Laboratory for Big Data Analysis and Applications Peking University

The core of recommendation models is estimating the probability that a user will like an item based on historical interactions. Existing collaborative filtering(CF) algorithms compute the likelihood by utilizing simple relationships between objects, e.g., user-item, item-item, or user-user. They always rely on a single type of object-object relationship, ignoring other useful relationship information in data. In this paper, we model an interaction between user and item as an edge and propose a novel CF framework, called learnable edge collaborative filtering(LECF). LECF predicts the existence probability of an edge based on the connections among edges and is able to capture the complex relationship in data. Specifically, we first adopt the concept of line graph where each node represents an interaction edge; then calculate a weighted sum of similarity between the query edge and the observed edges(i.e., historical interactions) that are selected from the neighborhood of query edge in the line graph for a recommendation. In addition, we design an efficient propagation algorithm to speed up the training and inference of LECF. Extensive experiments on four public datasets demonstrate LECF can achieve better performance than the state-of-the-art methods.

关键词： collaborative filtering recommender system implicit feedback edge-edge similarity line graph

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Secure and Fair Online Lottery Systems Using Smart Contracts

Blockchain-Enabled Secure and Fair Online Lottery Systems Us...

引用

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Datta, Suseta Mondal, Rituparna Roy, Rajdeep Banerjee, Sourav Biswas, Utpal Narula Institute of Technology Department of Computer Application West Bengal Kolkata India Techno India University Department of Computer Applications West Bengal Kolkata India University of Kalyani Department of Computer Science and Engineering West Bengal Kalyani India Kalyani Government Engineering College Department of Computer Science and Engineering West Bengal Kalyani India

ISBN: (纸本)9798331540821

In the capricious digital dominion, conventional online lottery systems come across consequential impediment regarding transparency, fairness, and security. This paper presents an inventive solution by merging Blockchain technology and smart contracts into online lotteries to take forward these challenges. The preferred disperse implementation capitalizes on Blockchain's decentralized category to covenant the translucency and immutability of lottery transactions, thereby undoing the requisite for trusted interceders. Smart contracts are immersed to automate the entire lottery process-from ticket provisioning to winner selection and payout-certifying agreement to preconceived rules and reinforcing contender trust. Through meticulous perusal and enactment, illustration of how Blockchain technology can transform online lottery systems, providing users with a secure, transparent, and fair platform have been performed. Furthermore, the suggested system's resistance to recurrent deceit and its prospective impression on the online gambling industry are talked about, foregrounding the welfares of a Blockchain-drove technique to online lotteries. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Neural Networks-Based Predictive Models for Self-Healing in Cloud Computing Environments 2

Neural Networks-Based Predictive Models for Self-Healing in ...

引用

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

作者： Sujatha, D. Michael Raj, T.F. Ramesh, G. Agoramoorthy, Moorthy Ahamed Ali, S. St.Peters College of Engineering and Technology Department of Computer Science and Engineering Avadi Chennai India Sclas Smats Department of Computer Applications TamilNadu Chennai India K.L.N.College of Engineering Department of Information Technology Sivagangai Tamilnadu Pottapalayam India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Easwari Engineering College Computer Science and Engineering Ramapuram Chennai India

ISBN: (纸本)9798350306415

Due to the widespread adoption of cloud computing, protecting the security and uptime of cloud services is of crucial importance. Unforeseen malfunctions and performance bottlenecks in cloud settings can lead to considerable downtime and financial losses. Systems that can automatically detect, diagnose, and recover from errors using self-healing mechanisms are a promising new approach. This study investigates how neural network-based prediction models can be used to improve cloud-based systems' inherent capacity for self-healing. This research introduces a novel method of using neural networks to forecast cloud system failures and performance irregularities. The proposed prediction models are able to spot warning signs by assessing past data and current metrics in real time. Neural networks may accurately anticipate outcomes by recognizing complicated patterns and learning from large, varied information. Various forms of neural networks, including deep learning designs, are evaluated to determine their efficacy in diverse contexts. The study also looks into proactively reducing faults by incorporating these predictive models into self-healing systems. Responses, such as resource reallocation, workload migration, and backup procedures, are triggered automatically when problems are predicted. This preventative method drastically lessens the amount of time users spend waiting for their cloud-based systems to restart. Extensive simulations and real-world case studies yielded experimental data that prove the prediction models based on neural networks proposed for self-healing in cloud computing are effective. The models' proficiency in failure prediction enables corrective measures to be taken promptly and precisely. Implementing these predictive models in massive cloud environments is also discussed, as are their scalability, flexibility, and real-world consequences. by tapping into the potential of neural networks for predictive analysis, this study adds to the develop

关键词： Cloud Computing LSTM Neural Network Self-Healing

来源：评论

学校读者我要写书评

暂无评论

Potato Leaf Disease Detection Method is Based on the Support Vector Machines 2

Potato Leaf Disease Detection Method is Based on the Support...

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Srivastava, Animesh Singh Rawat, Bhupender Sawan, Vikash Vishal Dhondiyal, Shiv Ashish Graphic Era Hill University Department of Computer Science & Engineering Dehradun India College of Smart Computing COER University Roorkee India GLA University Department of Computer Engineering & Applications Uttar Pradesh Mathura India School of Computer Application Lovely Professional University Punjab Jalandhar India Department of Computer Science & Engineering Dehradun India

ISBN: (纸本)9798331519056

Potato production is challenged by plant diseases whose adverse effects are a reduction in the yield of the crops, and which have undesirable economic implications. Recognizing these diseases is of utmost importance since control should be applied. This paper describes a method for diagnosing diseases of the potato using Support Vector Machine (SVM) classification. A SVM is an ML algorithm that is effective in classification tasks such as classifying potato leaves in terms of their diseases. The results show that the proposed method is useful and works rather well for detecting potato plant leaf diseases. In this paper, the SVM method emphasizes detecting various potato plant leaf diseases for efficient intervention before the late stage of visual assessment for microbial-introduced disease. The main aim of this research is to assist in overcoming the limitations of existing agricultural practices in speeding up the diagnosis and control of diseases affecting potato plants. So the SVM-based methods can help farmers in making timely decisions, reducing economic losses, and increasing agricultural productivity. With linear SVM, the accuracy stands at 93.1%. Nevertheless, when non-linear SVM is employed, the accuracy rises to 95.6%. © 2024 IEEE.

关键词： Agricultural economics

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：