检索结果-内蒙古大学图书馆

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

作者： Dixon, G.C. Srithanujan, S. Ranaweera, H.D.T.N. Ariyarathne, R.M.P.M. Weerasinghe, K.L. Gamage, N. Department of Information Technology SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka Department of Computer System engineering SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka Department of Computer Science and Software Engineering SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka

ISBN: (纸本)9798331532420

This study developed and implemented a machine learning-driven HR system designed to enhance recruitment outcomes, particularly in online interviews. Challenges such as candidate impersonation, interview question memorization, and deepfake manipulations were addressed. The system incorporated several critical processes utilizing advanced algorithms: pre-interview shortlisting employed Support Vector Machines (SVM) achieving 92% accuracy;cognitive skills assessment utilized adaptive testing methods powered by fine-tuned Large Language Models (LLMs) with 88% accuracy;emotional intelligence evaluation was conducted using deep learning-based emotion detection algorithms attaining 85% accuracy;face verification leveraged Convolutional Neural Networks (CNNs) for identity and deepfake detection with 90% accuracy;online video interviews were analyzed through integrated audio-visual processing techniques;language proficiency testing employed Natural Language Processing (NLP) models reaching 87% accuracy;analysis of thinking patterns was performed using sentiment analysis algorithms with 83% accuracy;and candidate grading was facilitated by ensemble learning methods ensuring consistent and reliable evaluations. The results demonstrated the system’s effectiveness in verifying candidate authenticity and assessing competence, providing a robust solution for modern recruitment challenges. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Calibration Approaches for Single-Beam and Multiple-Beam Distance Sensors

引用

IEEE Sensors Journal 2024年第1期24卷 975-983页

作者： Syu, Jia-Hao Lin, Jerry Chun-Wei Biernacki, Piotr Ziebinski, Adam National Taiwan University Department of Computer Science and Information Engineering Taipei10617 Taiwan Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Distributed Systems and Informatics Devices Gliwice44-100 Poland Silesian University of Technology Department of Distributed Systems and Informatic Devices Gliwice44-100 Poland

Sensors are the foundation to facilitate smart cities, smart grids, and smart transportation, and distance sensors are especially important for sensing the environment and gathering information. Researchers have developed various methods to calibrate distance sensors;however, they mainly focus on using external information for calibration, which is inefficient and computationally expensive. To alleviate the above problems, we propose machine learning (ML)-based calibration approaches for distance sensors. We develop two calibration mechanisms, where the naive mechanism directly predicts the true distance, while the residual mechanism predicts the residual for calibration. The conventional ML regression algorithms are then adopted to predict the true distance or calibration residual. Experimental results show that the designed residual calibration mechanism outperforms the naive mechanism by reducing the root mean square error (RMSE) by 92.2% and mean absolute error (MAE) by 93.3% in the fitting task. In prediction, the proposed 2-D-residual mechanism achieves an improvement of 78.6% and 65.7% compared to the state-of-the-art method. The experimental results show the effectiveness and generalization of the proposed ML-based calibration method, especially for the 2-D mechanism, which achieves the highest robustness in all fitting and prediction tasks. © 2001-2012 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Expert Phishing Detection System

Expert Phishing Detection System

引用

2024 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications technology, IAICT 2024

作者： Alsarhan, Ayoub Al-Aiash, Issa Al-Fraihat, Dimah Aljaidi, Mohammad Abu Laila, Dena Abd Al Hakem Department of Information Technology Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology The Hashemite University Zarqa13133 Jordan Department of Cybersecurity Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology The Hashemite University Zarqa13133 Jordan Department of Software Engineering Faculty of Information Technology Isra University Amman11622 Jordan Department of Computer Science Faculty of Information Technology Zarqa University Zarqa13110 Jordan Department of Cyber Security Faculty of Information Technology Zarqa Technical Intermediate College Zarqa Jordan

ISBN: (纸本)9798350353464

Phishing attacks are a threat that continuously emphasizes the need for effective detection methods. This paper presents a machine learning detection method that employs a random forest classifier, which is an adaptable algorithm that can handle a variety of feature sets. The dataset used in this work offers a range of features extracted from various URLs, addressing elements such as URL length, domain structure, and keyword presence. We deployed a computational approach for feature engineering. The random forest classifier is employed for both prediction and to assess feature importance, guiding an automated feature selection process. By doing this, the model’s performance is optimized, and the most important features are utilized. The findings of this study show the effectiveness of our method with an impressive accuracy of 98.45% on a test set. The classifier exhibits balanced precision and recall for both phishing and legitimate instances. Moreover, the automated feature selection process improves the interpretation of the model, emphasizing key indicators of phishing attacks. The proposed approach not only produces outstanding outcomes but also offers a flexible and scalable approach to address the dynamically evolving threat landscape of phishing attempts. ©2024 IEEE.

关键词： Cyber-security Phishing attacks Phishing URLs

来源：评论

学校读者我要写书评

暂无评论

A Tutorial on Federated Learning from Theory to Practice:Foundations,software Frameworks,Exemplary Use Cases,and Selected Trends

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 824-850页

作者： M.Victoria Luzón Nuria Rodríguez-Barroso Alberto Argente-Garrido Daniel Jiménez-López Jose M.Moyano Javier Del Ser Weiping Ding Francisco Herrera Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Communications Engineering University of the Basque Country(UPV/EHU)and also with TECNALIABasque Research&Technology Alliance(BRTA)Spain School of Information Science and Technology Nantong UniversityNantong 226019China

When data privacy is imposed as a necessity,Federated learning(FL)emerges as a relevant artificial intelligence field for developing machine learning(ML)models in a distributed and decentralized *** allows ML models to be trained on local devices without any need for centralized data transfer,thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third *** paradigm has gained momentum in the last few years,spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data *** virtue of FL,models can be learned from all such distributed data sources while preserving data *** aim of this paper is to provide a practical tutorial on FL,including a short methodology and a systematic analysis of existing software ***,our tutorial provides exemplary cases of study from three complementary perspectives:i)Foundations of FL,describing the main components of FL,from key elements to FL categories;ii)Implementation guidelines and exemplary cases of study,by systematically examining the functionalities provided by existing software frameworks for FL deployment,devising a methodology to design a FL scenario,and providing exemplary cases of study with source code for different ML approaches;and iii)Trends,shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL *** ultimate purpose of this work is to establish itself as a referential work for researchers,developers,and data scientists willing to explore the capabilities of FL in practical applications.

关键词： Data privacy distributed machine learning federated learning software frameworks

来源：评论

学校读者我要写书评

暂无评论

OntoMG: a unique and ontological-based intelligent framework for early identification of myasthenia gravis (MG)

引用

International Journal of information technology (Singapore) 2024年第6期16卷 3847-3853页

作者： Mahajan, Prerna Agarwal, Trapty Vekariya, Daxa Gupta, Rajesh Malviya, Ashwini Anandaraj, S.P. Jain, Garima Anand, D. Department of Computer Science and Information Technology Jain (Deemed to Be University) Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Lucknow India Department of Computer Science and Engineering Faculty of Engineering and Technology Parul University Gujarat Vadodara India Department of Management Sanskriti University UP Mathura India Department of UGDX ATLAS SkillTech University Mumbai India Department of Computer Science Engineering Presidency University Bengaluru India Department of Computer Science and Business Systems (CBS) Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India

Myasthenia Gravis (MG) is a neuromuscular disease causing extreme muscular fatigue, triggering problems with vision, swallowing, speech, mobility, dexterity, and breathing. However, early detection and prediction of MG is a crucial and quite challenging task for medical practitioners. So, in our proposed work, we are focused on introducing an ontology-based intelligent system for the prognosis of patients affected by this neuromuscular disease. The given paper presents a novel framework that employs the concepts of ontology, semantic web rules, and reasoner for deriving whether the patient is tested positive or negative. The suggested framework's effectiveness is assessed by comparing it to machine learning classifiers using parameters from the NIH repository for Myasthenia Gravis. The experimental results show that the ontological-based framework is able to achieve higher accuracy (80.85%), higher precision (78.37%), and higher recall (76.55%) than the existing classifiers used in the recent studies. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Machine learning (ML) Myasthenia gravis disease Ontology Reasoners Semantic web rules language (SWRL)

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Weapons in Surveillance Cameras Using Efficient-Net

引用

computers, Materials & Continua 2022年第9期72卷 4615-4630页

作者： Erssa Arif Syed Khuram Shahzad Muhammad Waseem Iqbal Muhammad Arfan Jaffar Abdullah S.Alshahrani Ahmed Alghamdi Department of Computer Science Superior UniversityLahore54000Pakistan Department of Informatics&Systems University of Management&TechnologyLahore54000Pakistan Department of Software Engineering Superior UniversityLahore54000Pakistan Faculty of Computer Science&Information Technology Superior UniversityLahore54000Pakistan Department of Computer Science&Artificial Intelligence College of Computer Science&EngineeringUniversity of JeddahJeddah21493Saudi Arabia Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddah21493Saudi Arabia

The conventional Close circuit television(CCTV)cameras-based surveillance and control systems require human resource *** all the criminal activities take place using weapons mostly a handheld gun,revolver,pistol,swords ***,automatic weapons detection is a vital requirement now a *** current research is concerned about the real-time detection of weapons for the surveillance cameras with an implementation of weapon detection using Efficient–*** time datasets,from local surveillance department’s test sessions are used for model training and *** consist of local environment images and videos from different type and resolution cameras that minimize the *** research also contributes in the making of Efficient-Net that is experimented and results in a positive *** results are also been represented in graphs and in calculations for the representation of results during training and results after training are also shown to represent our research ***-Net algorithm gives better results than existing *** using Efficient-Net algorithms the accuracy achieved 98.12%when epochs increase as compared to other algorithms.

关键词： Detection algorithms machine learning machine vision video surveillance

来源：评论

学校读者我要写书评

暂无评论

Proposed 3D chaos-based medical image cryptosystem for secure cloud-IoMT eHealth communication services

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 1-28页

作者： El-Shafai, Walid Khallaf, Fatma El-Rabaie, El-Sayed M. El-Samie, Fathi E. Abd Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electrical Engineering Faculty of Engineering Ahram Canadian University Giza 6th October City Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh84428 Saudi Arabia

Medical image encryption is a mandatory process in various healthcare, Internet of Medical Things (IoMT) and cloud services. This paper provides a robust cryptosystem based on a 3D chaotic map for the medical image encryption in secure IoMT and cloud services. The proposed encryption method depends on a 3D chaotic map. With this map, a nonlinear ciphering process is implemented for pixel value diffusion and position permutation. Five operations are conducted in the suggested cryptosystem on the medical images to be transmitted in order to attain a high security level. These operations are 3D chaos generation, chaos histogram equalization, row rotation, column rotation, and XOR operation. To validate the suggested cryptosystem, different medical images with different characteristics are tested. Moreover, the suggested cryptosystem and more recent state-of-the-art security systems are discussed and analyzed in a comparative study. Different assessment parameters are adopted to assess the suggested cryptosystem, which reveals high security performance. The simulation outcomes show that the suggested cryptosystem is trustworthy. Furthermore, it offers high robustness levels and recommended security levels for utilization in healthcare, IoMT and cloud service applications. It is observed that the amount of average entropy obtained by the proposed 3D chaos cryptosystem is 7.95 which is very close to its best value of 8, and the average NPCR value is 99.62% which is also much close to its supreme value of 99.60%. In addition, all other results scored for the test evaluation parameters on the suggested cryptosystem are superior to those of the traditional security systems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Challenges and future directions of secure federated learning:a survey

引用

Frontiers of computer science 2022年第5期16卷 173-180页

作者： Kaiyue ZHANG Xuan SONG Chenhan ZHANG Shui YU Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Faculty of Engineering and Information Technology University of Technology SydneySydney 2007Australia SUSTech-UTokyo Joint Research Center on Super Smart City Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China

Federated learning came into being with the increasing concern of privacy security,as people’s sensitive information is being exposed under the era of big *** is an algorithm that does not collect users’raw data,but aggregates model parameters from each client and therefore protects user’s ***,due to the inherent distributed nature of federated learning,it is more vulnerable under attacks since users may upload malicious data to break down the federated learning *** addition,some recent studies have shown that attackers can recover information merely from ***,there is still lots of room to improve the current federated learning *** this survey,we give a brief review of the state-of-the-art federated learning techniques and detailedly discuss the improvement of federated *** open issues and existing solutions in federated learning are *** also point out the future research directions of federated learning.

关键词： federated learning privacy protection security

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning with an Ensemble of Binary Action Deep Q-Networks

引用

computer Systems science & engineering 2023年第9期46卷 2651-2666页

作者： A.M.Hafiz M.Hassaballah Abdullah Alqahtani Shtwai Alsubai Mohamed Abdel Hameed Department of Electronics&Communication Engineering Institute of TechnologyUniversity of KashmirSrinagarJ&K190006India Department of Computer Science Faculty of Computers and InformationSouth Valley UniversityQenaEgypt College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAlkhrjKSA Department of Computer Science Faculty of Computers and InformationLuxor UniversityLuxorEgypt

With the advent of Reinforcement Learning(RL)and its continuous progress,state-of-the-art RL systems have come up for many challenging and real-world *** the scope of this area,various techniques are found in the *** such notable technique,Multiple Deep Q-Network(DQN)based RL systems use multiple DQN-based-entities,which learn together and communicate with each *** learning has to be distributed wisely among all entities in such a scheme and the inter-entity communication protocol has to be carefully *** more complex DQNs come to the fore,the overall complexity of these multi-entity systems has increased many folds leading to issues like difficulty in training,need for high resources,more training time,and difficulty in fine-tuning leading to performance *** a cue from the parallel processing found in the nature and its efficacy,we propose a lightweight ensemble based approach for solving the core RL *** uses multiple binary action DQNs having shared state and *** benefits of the proposed approach are overall simplicity,faster convergence and better performance compared to conventional DQN based *** approach can potentially be extended to any type of DQN by forming its *** extensive experimentation,promising results are obtained using the proposed ensemble approach on OpenAI Gym tasks,and Atari 2600 games as compared to recent *** proposed approach gives a stateof-the-art score of 500 on the Cartpole-v1 task,259.2 on the LunarLander-v2 task,and state-of-the-art results on four out of five Atari 2600 games.

关键词： Deep Q-networks ensemble learning reinforcement learning OpenAI Gym environments

来源：评论

学校读者我要写书评

暂无评论

Video and image quality improvement using an enhanced optimized dehazing technique

引用

Multimedia Tools and Applications 2024年 1-19页

作者： Ayoub, Abeer El-Shafai, Walid El-Samie, Fathi E. Abd Hamad, Ehab K. I. EL-Rabaie, El-Sayed M. Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt Department of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

The detrimental effects of atmospheric haze frequently plague outdoor imagery. This phenomenon arises from the scattering of light by minute particles within the ambient environment surrounding the scene to be imaged. Haze engenders an overall whitening of the image, leading to diminished contrast. To address these issues and enhance the quality of hazy images and videos, an enhanced dehazing technique is proposed. The proposed technique includes image enhancement before the optimal dehazing process. The enhancement stage entails the implementation of both homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE), serving to control the image dynamic range, while concurrently heightening the image contrast. The culminating stage encompasses an optimized dehazing technique, adept at expunging haze-induced artifacts from images. The homomorphic processing and CLAHE, applied in the pre-processing step, establish a foundation for the subsequent dehazing procedure. This proposed methodology is systematically applied to a gamut of visual outputs, including visible videos, Near-Infrared (NIR) frames, and authentic hazy images. Comparative evaluations of the proposed technique, homomorphic-processing-based enhanced dehazing, and standalone dehazing techniques is undertaken on different video types encompassing five frames. It is evident that the proposed technique, synergizing the homomorphic processing, CLAHE, and dehazing, outperforms alternative strategies. Furthermore, the proposed technique is subjected to a comparative study with various existing dehazing techniques over real hazy images. The assessment depends on Peak Signal-to-Noise Ratio (PSNR), correlation, and entropy metrics. The results underscore the efficacy of the proposed technique, particularly in terms of spectral entropy enhancement of dehazed frames. For both visible and NIR frames, the percentages of enhancement by the proposed technique are 17.66% and 118.48%, respectively. ©

关键词： Image enhancement

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：