检索结果-内蒙古大学图书馆

Trends in Material Science and Inventive Materials (ICTMIM), International Conference on

作者： T. Kavitha Koushik Reddy Chaganti Sivananda Lahari Reddy Elicherla M. Ravi Kumar D. Chaithanya K Manikanta Assistant Professor Department of CSE Srinivasa Ramanujan Institute of Technology Research Scholar Dept. of Computer and Information Systems University of the Cumberlands Associate Professor Department of CSE Dayananda Sagar University Assistant Professor Department of Cyber Security & IoT Malla Reddy University Assistant Professor Department of CSE CVR College of Engineering Assistant Professor Department of CSE Gates Institute of Technology

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

Smart cities face vital waste management challenges regarding efficiency and sustainability in their development period. The established waste collection approaches that depend on pre-set schedules together with unchanging routes create problems by possessing both inefficient resource usage and elevated fuel usage as well as delayed waste pickup times. The proposed framework builds a Deep Reinforcement Learning (DRL)-based system for dynamic waste collection route optimization using Autonomous Waste Collection Vehicles (AWCVs) with Internet of Things (IoT)-based smart bins. The system uses Deep Q-networks (DQNs) to analyze traffic conditions data alongside vehicle battery level data with smart bin information from the system so vehicles carry out efficient waste collection operations using minimal energy. The newly proposed algorithm provides 30% distance reduction and 28% faster responses and 30% lower energy usage than baseline heuristic methods do. The conclusions show that AI-powered waste management strategies can create sustainable operations which increase both service performance and overall energy efficiency in cities. The research team plans to apply the proposed approach to actual waste collection systems while exploring methods of deploying multiple agents alongside renewable energy systems to enhance future urban waste management operations.

关键词： Waste management Schedules Renewable energy sources Smart cities Deep reinforcement learning Energy efficiency Real-time systems Vehicle dynamics Sustainable development Optimization

来源：评论

学校读者我要写书评

暂无评论

UI/UX Design for Online Learning Approach by Predictive Student Experience

UI/UX Design for Online Learning Approach by Predictive Stud...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： Koushik Reddy Chaganti Uttham Sai Ramula Cheruku Sathyanarayana Ravindra Changala N. Kirankumar K. Gurnadha Gupta Dept. of Computer and Information Systems University of the Cumberlands KY USA Dept of CSE Nalla Malla Reddy Engineering College Dept of IT Guru Nanak Institutions Technical Campus Hyderabad India Dept of CSE JNTUA Anantapuram Dept of CSE K L Deemed To Be University Vaddeswaram AP

This study examines how an User Interface (UI) and User Experience (UX) design for online learning/educational platforms can be designed in a way that can be fully effective for achieving educational outcomes. In order to find out the importance of UI/UX design, a quick survey was conducted using Google Form about user experience in terms of UI of tools and websites, audio, video clarity, screen sharing, messaging chat, number of maximum participants, network adaptability, course, name, age, cost and demographic location. In this survey, 560 students participated from across the discipline. Out of 560 participants only 530 respondents, out of 530, 359(67.9%) were male and 171(32.1%) respondents are female. 470 (88.7%) respondents feel that UI design is vital for a tool or website while 401 (75.6%) respondents had bad experience of UI, 106 (26.4%) students continue with website even it has bad UX and 295 (73.6%) students leave the website. 350 (66.6%) respondents prefer to ease of use, 53 (10%) respondents prefer mobile accessibility, 111 (21%) students prefer technical support and 148 (28%) respondents prefer cost more than UI design of e-learning platforms. The survey shows that most of the respondents are male and mean (SD) age 21 years. Zoom app and Udemy are their most preferred tool and online learning platform respectively. In this study, a number of user studies are given that may be used to evaluate UI and UX and examine usability as well as utility. Additionally, applying ML techniques on curated datasets to find best UI design of tool and website for online platform.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NoFish;Total anti-phishing protection system 2

NoFish;Total anti-phishing protection system

引用

2nd International Conference on Advancements in Computing, ICAC 2020

作者： Atimorathanna, Dhanushka Niroshan Ranaweera, Tharindu Shehan Devdunie Pabasara, R.A.H. Perera, Jayani Rukshila Abeywardena, Kavinga Yapa Dept. of Computer Systems Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9781728184128

Phishing attacks have been identified by researchers as one of the major cyber-attack vectors which the general public has to face today. Although many vendors constantly launch new anti-phishing products, these products cannot prevent all the phishing attacks. The proposed solution, 'NoFish' is a total anti-phishing protection system created especially for end-users as well as for organizations. This paper proposes a machine learning computer vision-based approach for intelligent phishing detection. In this paper, a realtime anti-phishing system, which has been implemented using four main phishing detection mechanisms, is proposed. The system has the following distinguishing properties from related studies in the literature: language independence, use of a considerable amount of phishing and legitimate data, real-time execution, detection of new websites, detecting zero hour phishing attacks and use of feature-rich classifiers, visual image comparison, DNS phishing detection, email client plugin and especially the overall system is designed using a level-based security architecture to reduce the time-consumption. Users can simply download the NoFish browser extension and email plugin to protect themselves, establishing a relatively secure browsing environment. Users are more secure in cyberspace with NoFish which depicts a 97% accuracy level. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Deep Ear Biometrics for Gender Classification

arXiv

引用

arXiv 2023年

作者： Singh, Ritwiz Kashyap, Keshav Mukherjee, Rajesh Bera, Asish Chakraborty, Mamata Dalui Department of Computer Science and Engineering Haldia Institute of Technology WB India Department of Computer Science and Information Systems Birla Institute of Technology and Science Pilani Pilani Campus Rajasthan333 031 India Dept. of Computer Science and Engineering National Institute of Technology West Bengal Durgapur India

Human gender classification based on biometric features is a major concern for computer vision due to its vast variety of applications. The human ear is popular among researchers as a soft biometric trait, because it is less affected by age or changing circumstances, and is non-intrusive. In this study, we have developed a deep convolutional neural network (CNN) model for automatic gender classification using the samples of ear images. The performance is evaluated using four cutting-edge pre-trained CNN models. In terms of trainable parameters, the proposed technique requires significantly less computational complexity. The proposed model has achieved 93% accuracy on the EarVN1.0 ear dataset. © 2023, CC BY.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

引用

4th International Conference on Inventive Research in Computing Applications, ICIRCA 2022

作者： Soumya, T.R. Manohar, S.Solai Ganapathy, N.Bala Sundara Nelson, Leema Mohan, A. Pandian, M.Thurai Prathyusha Engineering College Dept. of Cse Tamilnadu Thiruvallur India Cm R Institute of Technology Deptartment of Eee Karnataka Bengaluru India Panimalar Engineering College Department of It Tamilnadu Chennai India Chitkara University Institute of Engineering & Technology Chitkara University Department of Computer Science & Engineering Punjab India Simats Schools of Engineering Saveetha University Department of Information Security Tamilnadu India School of Cse Vellore Institute of Technology Vellore India

ISBN: (数字)9781665497077

ISBN: (纸本)9781665497077

Now-a-days., On-line Social networks (OSN) plays a major role. It helps to maintain a social bond across world. People can share their information like personal, political and other career related work within minutes. High number of people started indulging in social networks because of its time complexity and easiest way of sharing details. On the other hand, the threats on social networks increased in a rapid way to gain sensitive information of a people sharing important details like passwords, bank details, personal details etc. The online privacy and security threats reports gone to top. It made researchers to involve more on this area of threats in order to protect individual privacy and security regarding social networks. Attackers started to exploit the vulnerabilities of OSNs which highly attracted malicious entities. Each OSNs had ten to hundred million users collectively generate billions of personal sensitive data content. To protect users from exploitation is one of the major challenges. The current research are mainly focused to protect the privacy of an individual's online profile in OSN. The creator constructs a fake profile to pretend himself as a genuine person in these sites. The aim in this paper is to check and detect the trusted and fake profiles created in OSN through machine learning based techniques. By using algorithms like (SVM)Support vector machine, (DNN) Deep neural network, Random Forest to overcome processes such as treating missing value, identification of variable, cleaning and validation of data will be done on the entire dataset. Here, python language is used for improving the efficiency of code. With help of this, millions of fake profiles can be detected automatically. Additionally, various machine learning algorithms are compared and discussed along with the classification report. By identifying the confusion matrix, the results show the effectiveness of the proposed machine learning algorithm, which has best accuracy, precisio

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Multi-Model Federated Learning Optimization Based on Multi-Agent Reinforcement Learning

Multi-Model Federated Learning Optimization Based on Multi-A...

引用

IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)

作者： S. Kaveh Atapour S. Jamal Seyedmohammadi S. Mohammad Sheikholeslami Jamshid Abouei Arash Mohammadi Konstantinos N. Plataniotis Department of Computer & Electrical Engineering Tarbiat Modares University Tehran Iran Concordia Institute of Information Systems Engineering (CIISE) Montreal Canada The Edward S. Rogers Sr. Dept. of Electrical & Computer Engineering University of Toronto Canada Department of Electrical Engineering Yazd University Yazd Iran

This paper addresses the problem of Multi-Model Federated Learning (MMFL) in a typical wireless network, where a cellular Base Station (BS) cooperates with multiple clients to simultaneously train several Machine Learning (ML) models. Accordingly, the objective of this paper is to make an efficient joint decision for client association and communication-computation resource allocation to optimize the performance of the MMFL algorithm. In this regard, an optimization problem is formulated to minimize the average global loss of ML models under clients' energy and delay constraints. It is shown that the problem is a mixed-integer optimization whose objective is implicit in terms of the decision variables. To solve the optimization problem, we propose a Multi-Agent Multi-Model Federated Learning (MAMMFL) scheme based on a cooperative multi-agent configuration to intelligently assign models and resources to clients. Specifically, the problem is first converted to a Markov Decision Process (MDP) problem, then it is divided into four sub-MDP problems, where each problem relates to a phase in MMFL. The reinforcement learning algorithm solves each sub-problem, and a team-Q algorithm is adopted to coordinate agents in a cooperative multi-agent setting. Simulation results show that the proposed method can outperform other baselines in terms of average global loss and resource consumption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Task Scheduling Algorithm with Complex Dependencies in Edge Computing

引用

Procedia computer Science 2022年 202卷 158-163页

作者： Lei Shi Zhaoxing Ma Yuqi Fan Yi Shi Xu Ding Zhehao Li School of Computer Science and Information Engineering Intelligent Interconnected Systems Laboratory of Anhui Procince Hefei University of Technology Hefei 230009 China Virginia Tech Dept. of ECE Blacksburg VA 24061 USA

In the edge computing network environment, our applications can be deployed on edge servers. The request to execute the application can be produced on the edge device and transmitted to the edge server for calculation. A complex request may be divided into multiple computing tasks and transmitted to different servers and then parallel calculated before obtaining the final result. How to schedule computing tasks in multiple requests so that all requests can be completed faster is a difficult problem, especially in the edge computing environment where we should consider the communicating work and the calculating work simultaneously. In this paper, we first build a task dependency model of the computing tasks included in the request based on the idea of dividing the method components of the application. The dependencies include sequence, selection and parallel. Then we propose an online scheduling algorithm MCOS based on optimizing the task with the maximum amount of calculation to solve the problem of the minimum sum of the completion time of all requests. In simulations, we show the algorithm MCOS has a better completion time.

关键词： Edge computing Online scheduling Dependent task

来源：评论

学校读者我要写书评

暂无评论

Device to Device Communication in 5G network using Device-Centric Resource Allocation Algorithm 4

Device to Device Communication in 5G Network using Device-Ce...

引用

4th International Conference on Inventive Research in Computing Applications, ICIRCA 2022

作者： Goswami, Chandrashekhar Das, Anupam Ogaili, Karrar Imran Verma, Vivek Kumar Singh, Vijay Sharma, Dilip Kumar Chandubhai S Patel Institute of Technology Department of Information Technology Charusat Gujrat India The Assam Royal Global University India College of Information Technology University of Babylon Info. Security Dept. Iraq Manipal University Jaipur Jaipur India Graphic Era Deemed to Be University Department of Computer Science & Engineering Gujrat Dehradun India Jaypee University of Engineering and Technology Department of Mathematics M.P. Guna India

ISBN: (数字)9781665497077

ISBN: (纸本)9781665497077

Due to the overutilization of commercial buildings, climatic changes have occurred, which has caused a major impact on the environment Global warming is the main issue faced by society due to ozone weakening. Many researchers conclude that commercial buildings in society are a major part of consuming energy and generating carbon equally in the environment Most of the living areas are filled with commercial buildings where the peoples have to get their needs. This commercial building consists of an HVAC and Refrigeration system which is the major reason for the energy consumption in the commercial building. These systems are utilized in commercial buildings for customer satisfaction, comfortable shopping, and avoiding food wastage. But the main motive of this is to reduce the carbon emission produced from the commercial building and achieve optimal energy consumption without reducing the customer's comfort and avoiding food wastage. This article is categorized into two articles to construct an algorithm with an effective prediction to achieve a plan. This article concentrates on the requirements of a Zero Carbon (Z.C.) building. So that the data of energy consumption required for the commercial building are to be analyzed. For such analysis, the first part of this article is done with an Internet of thigh (IoT) technology to collect the dataset of sensors in the building. This IoT Edge system is interconnected with all the devices of sensors used in HVAC and Refrigeration systems with the support of microcontrollers. The devices like sensors, consumers, actuators with user interfaces, and other technical gadgets are controlled and communicated by the Building Management System (BMS). This IoT Edge system collects and transfers the data into the IoT hub. IoT hub maintains the two-way communication among the cloud and Edge system utilized to secure the sensor data. This system supports the huge dataset storage used to predict and analyze the exact reason for energy con

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of WLAN Access Points Selection Metrics for Fingerprinting based Localization

Performance Evaluation of WLAN Access Points Selection Metri...

引用

IEEE International Conference on Utility and Cloud Computing (UCC)

作者： Sohaib Bin Altaf Khattak Moustafa M. Nasralla Maged Abdullah Esmail Mohamed Marey Nikumani Choudhury Smart Systems Engineering Lab College of Engineering Prince Sultan University Riyadh Kingdom of Saudi Arabia Dept. of Computer Science and Information Systems Birla Institute of Technology and Science Pilani Hyderabad India

abstract Reliability and cost are essential elements to consider in all engineering network designs. In RF-localization systems, reliability can be defined as seamless coverage with precise and accurate localization. Cost-efficiency aims to reduce the infrastructure while simultaneously maintaining high accuracy. Both the cost and reliability can be associated with Access Points (APs) deployment. Therefore, it is paramount to study how to optimize the APs placement in RF-localization systems. To select the optimal AP configuration, different selection metrics are proposed. This paper investigates different AP placement and optimization strategies for WLAN fingerprinting indoor localization systems. Performance of selection metrics are evaluated experimentally in a realistic indoor environment. A fingerprinting database is developed by a grid spacing of 2m using 7 WLAN APs, by collecting Received Signal Strength (RSS) values using an Android smartphone app. The experimental results show, the AP configuration obtained by the metric combining the fingerprint difference metric with the geometric dilution of precision, results in high localization accuracy.

关键词： Location awareness Performance evaluation Wireless LAN Costs Fingerprint recognition Reliability engineering Minimization

来源：评论

学校读者我要写书评

暂无评论

A new framework to protect privacy of location from malicious applications 8

A new framework to protect privacy of location from maliciou...

引用

8th International Conference on Computing for Sustainable Global Development, INDIACom 2021

作者： Alharbi, Awad Saleh Halikias, George Abi Sen, Adnan Ahmed Yamin, Mohammad School of Mathematics Computer Science and Engineering Dept. of Electrical and Electronic Engg. London United Kingdom Islamic University Faculty of Computer and Information Systems Al-Madinah Saudi Arabia Research School of Computer Science Australian National University Canberra Australia

ISBN: (纸本)9789380544434

Location-based applications have become very popular in recent years, especially during the ongoing COVID-19 pandemic. The pandemic has intensified the trend towards applications for electronic purchases and delivery services, to provide customers the facility of buying from anywhere and anytime, with great ease. However, there are some issues with these kind of purchases and delivery services. In particular, the data collected by these applications has the potential of having their security and privacy breached. Thus, trust of the service provider cannot be taken for granted. In fact, the service provider may prove to be a source of real danger to the privacy of users, especially if the service provider itself is a malicious party. Thus, it is difficult for the user to determine which applications can be trusted, and who to share their home or business location with. To solve this problem, in this research, we propose a new central platform that enables users to gather all of their (main) locations and control access to these locations in one place. Then the user can share them with other applications, such as link with hash-code included in a quick response (QR) barcode without the need to save their data in any application database. Moreover, the QR-code will be deactivated once it is used by the service provider, after the order is delivered. Therefore, the service provider will not be able to exploit the data stored in it, which means greater protection for the user's privacy. The system will offer other features for the user and the service provider as well. We have also implemented this system in a real manner to confirm its ability to improve the level of service in electronic purchase applications, in addition to improving the level of privacy of users' data. © 2021 Bharati Vidyapeeth, New Delhi. Copy Right in Bulk will be transferred to IEEE by Bharati Vidyapeeth.

关键词： COVID-19

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：