检索结果-内蒙古大学图书馆

7th International Conference on Software engineering and Information Management, ICSIM 2024

作者： Sharma, Bibhya Reddy, Pritika Singh, Vineet School of Information Technology Engineering Mathematics and Physics The University of the South Pacific Fiji Department of Computing Science and Information Systems Fiji National University Fiji

ISBN: (纸本)9798400709197

Good Governance of any country is reflected through transparency and accountability of its activities and the availability of information and open data in a timely manner to its citizens. The Right to Information (RTI) Act guides the government and its citizens to achieve the objectives availability, and effective communication between the government and society, hence leading to good governance. While there are about 135 countries globally who have adopted the RTI Act, the Act is yet to be fully enacted in Fiji and the advocacy and awareness about RTI is in the infancy stage. This study entails details of an RTI awareness initiative in Fiji through the design and implementation of an e-course. The RTI e-course was developed using Articulate Storyline 360 and integrated into a learning management platform - Moodle. The course was then piloted to the university students in Fiji, Tonga and Vanuatu. The effectiveness of the course was measured in terms of course completion and collected feedback using an online questionnaire. The results from the Cronbach Alpha test showed that the RTI e-course was valid and reliable. Furthermore, the participants were satisfied with the design, structure and content of the e-course. The RTI e-course is the first-ever course on RTI as such this can be used by South Pacific countries to create awareness and educate their populace on their right to information. The awareness created will assist the people of the South Pacific to be more aware of the activities carried out by the government and eventually improve civic engagement and participation of the South Pacific populace to economic development of their society. © 2024 ACM.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Energy Theft Detection in Smart Grids:Taxonomy,Comparative Analysis,Challenges,and Future Research Directions

引用

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 578-600页

作者： Mohsin Ahmed Abid Khan Mansoor Ahmed Mouzna Tahir Gwanggil Jeon Giancarlo Fortino Francesco Piccialli the Department of Computer Science COMSATS University Islamabad the Department of Computer Science School of ComputingEngineering and Digital TechnologiesTeesside University the Innovative Value Institute Maynooth University the Department of Computer Science Bahria University the School of Electronic Engineering Xidian University the Department of Embedded Systems Engineering Incheon National University IEEE the Department of Informatics ModelingElectronics and SystemsUniversity of Calabria the Department of Mathematics and Applications“R.Caccioppoli” University of Naples FedericoⅡ

Electricity theft is one of the major issues in developing countries which is affecting their economy *** with the introduction of emerging technologies,this issue became more *** many new energy theft detection(ETD)techniques have been proposed by utilising different data mining(DM)techniques,state&network(S&N)based techniques,and game theory(GT)***,a detailed survey is presented where many state-of-the-art ETD techniques are studied and analysed for their strengths and *** levels of taxonomy are presented to classify state-of-the-art ETD *** types and ways of energy theft and their consequences are studied and summarised and different parameters to benchmark the performance of proposed techniques are extracted from *** challenges of different ETD techniques and their mitigation are suggested for future *** is observed that the literature on ETD lacks knowledge management techniques that can be more effective,not only for ETD but also for theft *** can help in the prevention of energy theft,in the future,as well as for ETD.

关键词： Challenges comparative analysis energy theft detection future research directions smart grid taxonomy

来源：评论

学校读者我要写书评

暂无评论

Enhancing face recognition performance: a comprehensive evaluation of deep learning models and a novel ensemble approach with hyperparameter tuning

引用

Soft computing 2024年第20期28卷 12399-12424页

作者： Selvaganesan, Jana Sudharani, B. Shekhar, S. N. Chandra Vaishnavi, K. Priyadarsini, K. Raju, K. Srujan Rao, T. Srinivasa Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R & ampD Institute of Science and Technology Avadi Tamil Nadu Chennai600062 India Guntur Dist. Andhra Pradesh Vadlamudi India Department of Electronics and Communication Engineering Sreenidhi Institute of Science and Technology Telangana Hyderabad501301 India Department of Computer Science and Engineering Sona College of Technology Tamil Nadu Salem636005 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Computer Science and Engineering CMR Technical Campus Medchal Telangana Hyderabad501401 India Department of Electronics and Communication Engineering Aditya Engineering College Surampalem533437 India

In response to growing security concerns and the increasing demand for face recognition (FR) technology in various sectors, this research explores the application of deep learning techniques, specifically pre-trained Convolutional Neural Network (CNN) models, in the field of FR. The study harnesses the power of five pre-trained CNN models—DenseNet201, ResNet152V2, MobileNetV2, SeResNeXt, and Xception—for robust feature extraction, followed by SoftMax classification. A novel weighted average ensemble model, meticulously optimized through a grid search technique, is introduced to augment feature extraction and classification efficacy. Emphasizing the significance of robust data pre-processing, encompassing resizing, data augmentation, splitting, and normalization, the research endeavors to fortify the reliability of FR systems. Methodologically, the study systematically investigates hyperparameters across deep learning models, fine-tuning network depth, learning rate, activation functions, and optimization methods. Comprehensive evaluations unfold across diverse datasets to discern the effectiveness of the proposed models. Key contributions of this work encompass the utilization of pre-trained CNN models for feature extraction, extensive evaluation across multiple datasets, the introduction of a weighted average ensemble model, emphasis on robust data pre-processing, systematic hyperparameter tuning, and the utilization of comprehensive evaluation metrics. The results, meticulously analyzed, unveil the superior performance of the proposed method, consistently outshining alternative models across pivotal metrics, including Recall, Precision, F1 Score, Matthews Correlation Coefficient (MCC), and Accuracy. Notably, the proposed method attains an exceptional accuracy of 99.48% on the labeled faces in the wild (LFW) dataset, surpassing erstwhile state-of-the-art benchmarks. This research represents a significant stride in FR technology, furnishing a dependable and accurate

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Public Transport: RFID-Enabled Occupancy Monitoring and Frequency Analysis System

Revolutionizing Public Transport: RFID-Enabled Occupancy Mon...

引用

2024 International Conference on Communication, computing and Internet of Things, IC3IoT 2024

作者： Mageswaran, J. Uma Indumathi, G. Kalpana, A.V. Elangovan, G. Lalitha, S.D. Nalini, S. Sohanda, Mayank Kumar Dept. of Computer Science Engineering Amrita School of Computing Vengal Campus Tiruvallur DistTamil Nadu India Srm Institute Of Science And Technology Ramapuram India Srm Institute Of Science And Technology Department Of Data Science And Business Systems Kattankulathur India R.M.K Engineering College Department Of Computer Science And Engineering India Srm Institute Of Science And Technolog Department Of Computing Technologies Kattankulathur India

ISBN: (纸本)9798350352689

Public bus stops in India are becoming more crowded due to the country's fast population expansion. People wait a long time for buses to come, then suddenly congregate around them when they do, packing the buses with people and pushing them up into the footboards, which causes accidents. An additional concern of overcrowding is theft. All of this is the result of numerous bus stops not having adequate information on when busses would arrive. The proposed work paves a very important role for the passengers. The passengers will be provided with the information of the arrival of next bus, seat occupancy and the total passengers inside the bus. The information about the seat occupancy, in-passengers and out-passengers is done with the help of Radio Frequency Identification (RFID) tags. The arrival of the next bus is determined by calculating the duration of the buses that are near using RFID readers placed in different bus stations. The count and the frequency will be interfaced in the web application. The passengers can check the application to know the occupancy and today's society where people can catch the right bus at the station and at the right time. This will solve the problems like waiting in bus stops and wasting time and going in a crowded bus. © 2024 IEEE.

关键词： Buses

来源：评论

学校读者我要写书评

暂无评论

ERBM: A Machine Learning-Driven Rule-Based Model for Intrusion Detection in IoT Environments

引用

Computers, Materials and Continua 2025年第3期83卷 5155-5179页

作者： Mehmmod, Arshad Batool, Komal Sajid, Ahthsham Alam, Muhammad Mansoor Su'ud, Mazliham MohD Khan, Inam Ullah Department of Information Security and Data Science Riphah Institute of Systems Engineering Riphah International University Islamabad46000 Pakistan Faculty of Computing Riphah International University Islamabad46000 Pakistan Faculty of Computing and Informatics Multimedia University Cyberjaya63100 Malaysia

Traditional rule-based Intrusion Detection systems (IDS) are commonly employed owing to their simple design and ability to detect known threats. Nevertheless, as dynamic network traffic and a new degree of threats exist in IoT environments, these systems do not perform well and have elevated false positive rates—consequently decreasing detection accuracy. In this study, we try to overcome these restrictions by employing fuzzy logic and machine learning to develop an Enhanced Rule-Based Model (ERBM) to classify the packets better and identify intrusions. The ERBM developed for this approach improves data preprocessing and feature selections by utilizing fuzzy logic, where three membership functions are created to classify all the network traffic features as low, medium, or high to remain situationally aware of the environment. Such fuzzy logic sets produce adaptive detection rules by reducing data uncertainty. Also, for further classification, machine learning classifiers such as Decision Tree (DT), Random Forest (RF), and Neural Networks (NN) learn complex ways of attacks and make the detection process more precise. A thorough performance evaluation using different metrics, including accuracy, precision, recall, F1 Score, detection rate, and false-positive rate, verifies the supremacy of ERBM over classical IDS. Under extensive experiments, the ERBM enables a remarkable detection rate of 99% with considerably fewer false positives than the conventional models. Integrating the ability for uncertain reasoning with fuzzy logic and an adaptable component via machine learning solutions, the ERBM system provides a unique, scalable, data-driven approach to IoT intrusion detection. This research presents a major enhancement initiative in the context of rule-based IDS, introducing improvements in accuracy to evolving IoT threats. Copyright © 2025 The Authors.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

NEGATIVELY CORRELATED ENSEMBLE REINFORCEMENT LEARNING FOR ONLINE DIVERSE GAME LEVEL GENERATION 12

NEGATIVELY CORRELATED ENSEMBLE REINFORCEMENT LEARNING FOR ON...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Wang, Ziqi Hu, Chengpeng Liu, Jialin Yao, Xin Department of Computer Science and Engineering Southern University of Science and Technology China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology China Department of Computing and Decision Sciences Lingnan University Hong Kong

Deep reinforcement learning has recently been successfully applied to online procedural content generation in which a policy determines promising game-level segments. However, existing methods can hardly discover diverse level patterns, while the lack of diversity makes the gameplay boring. This paper proposes an ensemble reinforcement learning approach that uses multiple negatively correlated sub-policies to generate different alternative level segments, and stochastically selects one of them following a dynamic selector policy. A novel policy regularisation technique is integrated into the approach to diversify the generated alternatives. In addition, we develop theorems to provide general methodologies for optimising policy regularisation in a Markov decision process. The proposed approach is compared with several state-of-the-art policy ensemble methods and classic methods on a well-known level generation benchmark, with two different reward functions expressing game-design goals from different perspectives. Results show that our approach boosts level diversity notably with competitive performance in terms of the reward. Furthermore, by varying the regularisation coefficient values, the trained generators form a well-spread Pareto front, allowing explicit trade-offs between diversity and rewards of generated levels. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Communication Accessibility:UrSL-CNN Approach to Urdu Sign Language Translation for Hearing-Impaired Individuals

引用

Computer Modeling in engineering & sciences 2024年第10期141卷 689-711页

作者： Khushal Das Fazeel Abid Jawad Rasheed Kamlish Tunc Asuroglu Shtwai Alsubai Safeeullah Soomro Department of Computer Engineering Modeling Electronics and Systems EngineeringUniversity of CalabriaRende Cosenza87036Italy Department of Information Systems University of Management and TechnologyLahore54770Pakistan Department of Computer Engineering Istanbul Sabahattin Zaim UniversityIstanbul34303Turkey Department of Software Engineering Istanbul Nisantasi UniversityIstanbul34398Turkey Department of Computer Science COMSATS University IslamabadLahore CampusLahore54700Pakistan Faculty of Medicine and Health Technology Tampere UniversityTampere33720Finland Department of Computer Science College of Computer Engineering and Sciences in Al-KharjPrince Sattam Bin Abdulaziz UniversityP.O.Box 151Al-Kharj11942Saudi Arabia Second Department of Computer Science College of Engineering and ComputingGeorge Mason UniversityFairfaxVA 4418USA

Deaf people or people facing hearing issues can communicate using sign language(SL),a visual *** works based on rich source language have been proposed;however,the work using poor resource language is still *** other SLs,the visuals of the Urdu Language are *** study presents a novel approach to translating Urdu sign language(UrSL)using the UrSL-CNN model,a convolutional neural network(CNN)architecture specifically designed for this *** existingworks that primarily focus on languageswith rich resources,this study addresses the challenge of translating a sign language with limited *** conducted experiments using two datasets containing 1500 and 78,000 images,employing a methodology comprising four modules:data collection,pre-processing,categorization,and *** enhance prediction accuracy,each sign image was transformed into a greyscale image and underwent noise *** analysis with machine learning baseline methods(support vectormachine,GaussianNaive Bayes,randomforest,and k-nearest neighbors’algorithm)on the UrSL alphabets dataset demonstrated the superiority of UrSL-CNN,achieving an accuracy of ***,our model exhibited superior performance in Precision,Recall,and F1-score *** work not only contributes to advancing sign language translation but also holds promise for improving communication accessibility for individuals with hearing impairments.

关键词： Convolutional neural networks Pakistan sign language visual language

来源：评论

学校读者我要写书评

暂无评论

Predicting software vulnerability based on software metrics: a deep learning approach

引用

Iran Journal of Computer science 2024年第4期7卷 801-812页

作者： Agbenyegah, Francis Kwadzo Asante, Micheal Chen, Jinfu Akpaku, Ernest Department of Computer Science Kwame Nkrumah University of Science and Technology Kumasi Ghana School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China Department of Information Technology Faculty of Computing and Information Systems Ghana Communication Technology University Accra Ghana

The security of IT systems is the topmost priority of software developers. Software vulnerabilities undermine the security of computer systems. Lately, there have been a lot of reported issues of software vulnerabilities recorded in individuals and corporate systems. Software metrics-based techniques have been used and found to be effective due to low false positives and false negatives. However, there are software metrics that have not been investigated and could have an impact on the performance of the predictive model. In this study, we developed an ensemble deep learning algorithm made of LSTM, CNN, and MLP models with the non-investigated metrics as a feature to learn the latent representation of code metrics to predict anomalies in source code effectively. We trained the proposed model on the SySeVR datasets and compared the model's performance against five deep learning algorithms and four state-of-the-art SVPs. The proposed model performs better than the other deep learning with a classification accuracy of 96.17%, and a precision of 97.72%. The model's classification accuracy is 4.98% higher than that of the five deep learning models and 1.71% lower in precision than the state-of-the-art SVP. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Deep learning Machine learning Software metrics Software security Software vulnerabilities

来源：评论

学校读者我要写书评

暂无评论

Cursive Hand writing Recognition Using Neural Networks with VGG-16 2

Cursive Hand writing Recognition Using Neural Networks with ...

引用

2nd IEEE International Conference on Advances in computing, Communication and Applied Informatics, ACCAI 2023

作者： Rangari, Anushka Anil Das, Swagat Rajeswari, D. College of Engineering and Technology Srm Institute of Science and Technology School of Computing Department of Data Science and Business Systems Tamilnadu Kattankulathur603203 India

ISBN: (纸本)9798350315905

Recognition of cursive handwritten text from photographs is a method for finding handwritten text. Identification is difficult because every author has a distinctive writing style. The proposed work uses cutting-edge technologies including RNN, KNN, MLP, and CRNN twith VGG16 to push the boundaries of character and handwriting recognition. Additionally, it compares neural networks to CNNwith VGG16 and finds that neural networks are more accurate. In the first stage, image acquisition, the scanned image is acquired along with its normalization, feature extraction, and segmentation. Additionally, it combines with the most effective feature extraction technique to improve the accuracy of our model. It also compares the accuracy with six uniquepretreat. approach, which are image segmentation image data generator data augmentation closed loop pre-processing, sigmoid Stretching and geometric *** provides the highest accuracy (98.36%) when using data augmentation. CNN has the highest accuracy (95.25%) when using picture segmentation. The third experiment's results for the image data generator show that CNN produced the best results (92.47%), while the highest model, RNN, gave closed loop processing accuracy of 92.20%. a change in geometry KNN has the highest accuracy at 95.39%. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Battery Health Prediction Using Deep Hybrid Learning 3

Battery Health Prediction Using Deep Hybrid Learning

引用

3rd International Conference on Pervasive computing and Social Networking, ICPCSN 2023

作者： Nair, Rahul Anil Suresh, Dev Karan Rajeswari, D. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Department of Data Science and Business Systems Tamil Nadu Kattankulathur India

ISBN: (纸本)9798350322842

The type and condition of the road the vehicle travels;how long the battery is used for are just a few of the variables that affect the battery life of electric cars (EVs). These elements might affect the battery's lifespan by causing it to drain more quickly than usual. By understanding the various factors that impact battery life, work can be done to mitigate these issues and extend the useful life of the battery. To find the best circumstances for increasing the battery's longevity, this research paper is concentrated on examining the impacts of road conditions on battery life. The previous article classified routes with an accuracy of 83.56% based on battery health while arriving at the destination [1]. This article examines EV routed and categorises them on the basis of the number of brakes applied upon arrival at the destination. By doing so, it aims to develop recommendations for drivers on how to optimize their driving habits to extend the battery's lifespan. Observations indicate that bad routes generally involve a lot more brakes as compared to good routes. Vehicle speed has a negative correlation with heater power in a bad route and a positive correlation in a good route. Battery voltage and Battery state- of-charge have opposing correlations in both categories. In this research, a prediction of the route category was attempted by using Deep Hybrid Learning to integrate three pre-trained models., VGGI6, Resnet50 and VGG19 with two boosting algorithms:- XGBoost and AdaBoost. The accuracy of the six deep hybrid learning models in predicting the category of these routes are as follows:-0.87625, 0.84875, 0.80125, 0.7925, 0.8425 and 0.855. © 2023 IEEE.

关键词： Deep learning

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：