检索结果-内蒙古大学图书馆

Read for me: developing a mobile based application for both visually impaired and illiterate users to tackle reading challenge

引用

i-com 2023年第3期22卷 225-240页

作者： Alfayez, Zainab Hameed Alfayez, Batool Hameed Abdul-Samad, Nahla Hamad Department of Computer Information Systems College of Computer Science and Information Technology University of Basrah Basrah Iraq Department of Library and Information College of Art University of Basrah Basrah Iraq

In recent years, there have been several attempts to help visually impaired and illiterate people to overcome their reading limitations through developing different applications. However, most of these applications are based on physical button interaction and avoid the use of touchscreen devices. This research mainly aims to find a solution that helps both visually impaired and illiterate people to read texts present in their surroundings through a touchscreen-based application. The study also attempts to discover the possibility of building one application that could be used by both type of users and find out whether they would use it in the same efficiency. Therefore, a requirements elicitation study was conducted to identify the users’ requirements and their preferences and so build an interactive interface for both visually impaired and illiterate users. The study resulted in several design considerations, such as using voice instructions, focusing on verbal feedback, and eliminating buttons. Then, the reader mobile application was designed and built based on these design preferences. Finally, an evaluation study was conducted to measure the usability of the developed application. The results revealed that both sight impaired and illiterate users could benefit from the same mobile application, as they were satisfied with using it and found it efficient and effective. However, the measures from the evaluation sessions also reported that illiterate users had used the develop app more efficiently and effectively. Moreover, they were more satisfied, especially with the application’s ease of use. © 2023 the author(s), published by De Gruyter.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Healthcare Privacy-Preserving Federated Transfer Learning using CKKS-Based Homomorphic Encryption and PYHFEL Tool

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer science and Mathematics 2024年第3期5卷 473-488页

作者： Al-Janabi, Anmar A. Al-Janabi, Sufyan Al-Khateeb, Belal Computer Science Department University of Technology – Iraq Baghdad10066 Iraq University of Anbar Ramadi Iraq College of Computer Science & Information Technology Anbar Ramadi31001 Iraq

Digitization of healthcare data has shown an urgent necessity to deal with privacy concerns within the field of deep learning for healthcare organizations. A promising approach is federated transfer learning, enabling medical institutions to train deep learning models collaboratively through sharing model parameters rather than raw data. The objective of this research is to improve the current privacy-preserving federated transfer learning systems that use medical data by implementing homomorphic encryption utilizing PYthon for Homomorphic Encryption Libraries (PYFHEL). The study leverages a federated transfer learning model to classify cardiac arrhythmia. The procedure begins by converting raw Electrocardiogram (ECG) scans into 2-D ECG images. Then, these images are split and fed into the local models for extracting features and complex patterns through a finetuned ResNet50V2 pre-trained model. Optimization techniques, including real-time augmentation and balancing, are also applied to maximize model performance. Deep learning models can be vulnerable to privacy attacks that aim to access sensitive data. By encrypting only model parameters, the Cheon-Kim-Kim-Song (CKKS) homomorphic scheme protects deep learning models from adversary attacks and prevents sensitive raw data sharing. The aggregator uses a secure federated averaging method that averages encrypted parameters to provide a global model protecting users’ privacy. The system achieved an accuracy rate of 84.49% when evaluated using the MIT-BIH arrhythmia dataset. Furthermore, other comprehensive performance metrics were computed to gain deeper insights, including a precision of 72.84%, recall of 51.88%, and an F1-score of 55.13%, reflecting a better understanding of the adopted framework. Our findings indicate that employing the CKKS encryption scheme in a federated environment with transfer cutting-edge technology achieves relatively high accuracy but at the cost of other performance metrics, which is lower

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

VeriFace:Defending against Adversarial Attacks in Face Verification Systems

引用

computers, Materials & Continua 2023年第9期76卷 3151-3166页

作者： Awny Sayed Sohair Kinlany Alaa Zaki Ahmed Mahfouz Information Technology Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Computer Science Department Faculty of ScienceMinia UniversityAl MinyaEgypt Faculty of Computer Studies Arab Open UniversityMuscatOman

Face verification systems are critical in a wide range of applications,such as security systems and biometric ***,these systems are vulnerable to adversarial attacks,which can significantly compromise their accuracy and *** attacks are designed to deceive the face verification system by adding subtle perturbations to the input *** perturbations can be imperceptible to the human eye but can cause the systemtomisclassifyor fail torecognize thepersoninthe *** this issue,weproposeanovel system called VeriFace that comprises two defense mechanisms,adversarial detection,and adversarial *** first mechanism,adversarial detection,is designed to identify whether an input image has been subjected to adversarial *** second mechanism,adversarial removal,is designed to remove these perturbations from the input image to ensure the face verification system can accurately recognize the person in the *** evaluate the effectiveness of the VeriFace system,we conducted experiments on different types of adversarial attacks using the Labelled Faces in the Wild(LFW)*** results show that the VeriFace adversarial detector can accurately identify adversarial imageswith a high detection accuracy of 100%.Additionally,our proposedVeriFace adversarial removalmethod has a significantly lower attack success rate of 6.5%compared to state-of-the-art removalmethods.

关键词： Adversarial attacks face aerification adversarial detection perturbation removal

来源：评论

学校读者我要写书评

暂无评论

A Reputation-Based AODV Protocol for Blackhole and Malfunction Nodes Detection and Avoidance

引用

computers, Materials & Continua 2024年第8期80卷 1867-1888页

作者： Qussai M.Yaseen Monther Aldwairi Ahmad Manasrah Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjman346United Arab Emirates Department of Computer Information Systems Faculty of Computer and Information TechnologyJordan University of Science and TechnologyIrbid22110Jordan College of Technological Innovation Zayed UniversityAbu Dhabi144534United Arab Emirates Faculty of Information Technology and Computer Science Yarmouk UniversityIrbid21163Jordan Computer Information Systems Higher Colleges of TechnologySharjah341214United Arab Emirates

Enhancing the security of Wireless Sensor Networks(WSNs)improves the usability of their ***,finding solutions to various attacks,such as the blackhole attack,is crucial for the success of WSN *** paper proposes an enhanced version of the AODV(Ad Hoc On-Demand Distance Vector)protocol capable of detecting blackholes and malfunctioning benign nodes in WSNs,thereby avoiding them when delivering *** proposed version employs a network-based reputation system to select the best and most secure path to a *** achieve this goal,the proposed version utilizes the Watchdogs/Pathrater mechanisms in AODV to gather and broadcast reputations to all network nodes to build the network-based reputation *** minimize the network overhead of the proposed approach,the paper uses reputation aggregator nodes only for forwarding reputation ***,to reduce the overhead of updating reputation tables,the paper proposes three mechanisms,which are the prompt broadcast,the regular broadcast,and the light broadcast *** proposed enhanced version has been designed to perform effectively in dynamic environments such as mobile WSNs where nodes,including blackholes,move continuously,which is considered a challenge for other *** the proposed enhanced protocol,a node evaluates the security of different routes to a destination and can select the most secure routing *** paper provides an algorithm that explains the proposed protocol in detail and demonstrates a case study that shows the operations of calculating and updating reputation values when nodes move across different ***,the paper discusses the proposed approach’s overhead analysis to prove the proposed enhancement’s correctness and applicability.

关键词： AODV blackhole malfunction nodes pathrater reputation system wireless sensor networks(WSNs) watchdogs

来源：评论

学校读者我要写书评

暂无评论

A Review on Deep Learning Techniques for EEG-Based Driver Drowsiness Detection Systems

引用

Informatica (Slovenia) 2024年第3期48卷 359-378页

作者： Latreche, Imene Slatnia, Sihem Kazar, Okba Barka, Ezedin Harous, Saad Department of Computer Science University of Mohamed Khider Biskra Algeria College of Arts Sciences & Information Technology University of Kalba Sharjah United Arab Emirates Department of Information Systems and Security UAE University Al Ain United Arab Emirates Computer Science Department College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates

Driver Drowsiness is considered one of the significant causes of road accidents and fatal injuries. Due to this, creating systems that can monitor drivers and detect early drowsiness has become an important field of research and a challenging task in recent years. Several research attempts were proposed to solve this problem based on several approaches and techniques. The Electroencephalogram (EEG) is one of the most efficient and reliable method, among the physiological signals-based monitoring approaches. In this area, many Machine Learning (ML) techniques have been used to detect EEG-based driver drowsiness. However, due to the limitations of ML techniques, many researchers have shifted their focus to the use of deep learning (DL) techniques, which have demonstrated superior performance in many fields including the physiological signals classification tasks. This paper reviews and discusses numerous new research papers that have proposed and implemented driver drowsiness detection systems based on EEG and deep learning techniques. In addition, we have outlined the limitations and difficulties of the existing works and highlighted and proposed some propositions that will help future field researchers enhance and generalize the results. Based on our thorough analysis, we have determined that the latest advancements in detecting driver drowsiness have employed the convolutional neural network (CNN) technique, which has demonstrated effective performance in classifying signals. Furthermore, the primary issue encountered in all works is developing a more precise and accurate method. Nevertheless, we seek a precise system capable of swiftly identifying a state of drowsiness while using minimal spatial memory and processing resources. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

SMART AGRICULTURE: INTEGRATING AIR QUALITY MONITORING WITH DEEP LEARNING FOR PROCESS OPTIMIZATION*

引用

Scalable computing 2025年第3期26卷 1005-1016页

作者： Shobana, J. Subramanian, A Venkata Balamurugan, P. Perumal, Sivakumar Sankari, V. Eldho, K.J. Nareshkumar, R. Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur India Department of Computer Science and Engineering GITAM University Bengaluru India Department of Computer Science and Engineering J N N Institute of Enginering India Saveetha university Chennai India Department of Computer Science and Engineering Sasi Institute of Technology and Engineering Andhra Pradesh Tadepalligudem India Department of Artificial Intelligence and Data Science K.Ramakrishnan College of Engineering Kariyamanickam Rd Tamil Nadu Samayapuram India PG and Research Department of Computer Science Mary Matha Arts and Science College Kerala Mananthavady India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur India

Modernization and intense industrialization have led to a substantial improvement in people’s quality of life. However, the aspiration for achieving an improved quality of life results in environmental contamination. A primary consequence of environmental degradation is air pollution, resulting from rising levels of poisonous chemicals in the atmosphere, which may induce detrimental health conditions in humans. It is harmful to both humans and agriculture. Given that the effects of air pollution on plants may not be readily apparent, it is important to analyse the necessary data and compute the outcomes. Farmers prioritise on pests and plant diseases, frequently neglecting the detrimental impacts of air pollution. Some plant species can withstand high amounts of pollution from suspended particulate matter and accumulated gases, while others are more susceptible to harm. Therefore, plants’ reaction to air pollution is influenced by the kind of harmful compounds, their levels, and the plant’s susceptibility to them. The LSTM +CNN Proposed Ensemble method may be used to analyse the impact of air pollution on agriculture by examining trends in crop production over time and predicting which crop is more resistant based on the pollution data. The initiative created for this aim may assist farmers in determining the most suitable crop to cultivate in their fields to minimize the impact of air pollution on agricultural yield. The findings show deep learning algorithms correctly predict hourly pollutant concentrations such as carbon monoxide, sulphur dioxide, nitrogen dioxide, ground-level ozone, and particulate matter 2.5, along with the hourly Air Quality Index (AQI) for California. A proposed model used test RMSE values as a measure to evaluate prediction performance, achieving the best possible results. © 2025 SCPE.

关键词： Nitrogen oxides

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey for Privacy-Preserving Biometrics: Recent Approaches, Challenges, and Future Directions

引用

computers, Materials & Continua 2024年第2期78卷 2087-2110页

作者： Shahriar Md Arman Tao Yang Shahadat Shahed Alanoud AlMazroa Afraa Attiah Linda Mohaisen School of Computer Science and Technology Zhejiang Gongshang UniversityHangzhou310018China School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China College of Computer and Information Sciences Princess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia

The rapid growth of smart technologies and services has intensified the challenges surrounding identity authenti-cation *** credentials are increasingly being used for verification due to their advantages over traditional methods,making it crucial to safeguard the privacy of people’s biometric data in various *** paper offers an in-depth exploration for privacy-preserving techniques and potential threats to biometric *** proposes a noble and thorough taxonomy survey for privacy-preserving techniques,as well as a systematic framework for categorizing the field’s existing *** review the state-of-the-art methods and address their advantages and limitations in the context of various biometric modalities,such as face,fingerprint,and eye *** survey encompasses various categories of privacy-preserving mechanisms and examines the trade-offs between security,privacy,and recognition performance,as well as the issues and future research *** aims to provide researchers,professionals,and decision-makers with a thorough understanding of the existing privacy-preserving solutions in biometric recognition systems and serves as the foundation of the development of more secure and privacy-preserving biometric technologies.

关键词： Biometric modalities biometric recognition biometric security privacy-preserving security threats

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Enabled Social Media Recommendation Based on User Comments

引用

computer Systems science & Engineering 2023年第2期44卷 1691-1702页

作者： K.Saraswathi V.Mohanraj Y.Suresh J.Senthilkumar Department of Computer Science and Engineering Government College of EngineeringSalem636011India Department of Information Technology Sona College of TechnologySalem636005India

Nowadays,review systems have been developed with social media Recommendation systems(RS).Although research on RS social media is increas-ing year by year,the comprehensive literature review and classiﬁcation of this RS research is limited and needs to be *** previous method did notﬁnd any user reviews within a time,so it gets poor accuracy and doesn’tﬁlter the irre-levant comments efﬁ*** Recursive Neural Network-based Trust Recom-mender System(RNN-TRS)is proposed to overcome this method’s *** it is efﬁcient to analyse the trust comment and remove the irrelevant sentence ***ﬁrst step is to collect the data based on the transactional reviews of social *** second step is pre-processing using Imbalanced Col-laborative Filtering(ICF)to remove the null values from the *** the features from the pre-processing step using the Maximum Support Grade Scale(MSGS)to extract the maximum number of scaling features in the dataset and grade the weights(length,count,etc.).In the Extracting features for Training and testing method before that in the feature weights evaluating the softmax acti-vation function for calculating the average weights of the ***,In the classiﬁcation method,the Recursive Neural Network-based Trust Recommender System(RNN-TRS)for User reviews based on the Positive and negative scores is analysed by the *** simulation results improve the predicting accuracy and reduce time complexity better than previous methods.

关键词： Recommendation systems(RS) social media recursive neural network-based trust recommender system(RNN-TRS) user reviews

来源：评论

学校读者我要写书评

暂无评论

Facial Image-Based Autism Detection:A Comparative Study of Deep Neural Network Classifiers

引用

computers, Materials & Continua 2024年第1期78卷 105-126页

作者： Tayyaba Farhat Sheeraz Akram Hatoon SAlSagri Zulfiqar Ali Awais Ahmad Arfan Jaffar Faculty of Computer Science and Information Technology The Superior UniversityLahore54600Pakistan Intelligent Data Visual Computing Research(IDVCR) Faculty of Computer Science and Information TechnologyThe Superior UniversityLahore54600Pakistan Information Systems Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh12571Saudi Arabia School of Computer Science and Electronic Engineering(CSEE) University of EssexWivenhoe ParkColchesterCO43SQUK

Autism Spectrum Disorder(ASD)is a neurodevelopmental condition characterized by significant challenges in social interaction,communication,and repetitive *** and precise ASD detection is crucial,particularly in regions with limited diagnostic resources like *** study aims to conduct an extensive comparative analysis of various machine learning classifiers for ASD detection using facial images to identify an accurate and cost-effective solution tailored to the local *** research involves experimentation with VGG16 and MobileNet models,exploring different batch sizes,optimizers,and learning rate *** addition,the“Orange”machine learning tool is employed to evaluate classifier performance and automated image processing capabilities are utilized within the *** findings unequivocally establish VGG16 as the most effective classifier with a 5-fold cross-validation ***,VGG16,with a batch size of 2 and the Adam optimizer,trained for 100 epochs,achieves a remarkable validation accuracy of 99% and a testing accuracy of 87%.Furthermore,the model achieves an F1 score of 88%,precision of 85%,and recall of 90% on test *** validate the practical applicability of the VGG16 model with 5-fold cross-validation,the study conducts further testing on a dataset sourced fromautism centers in Pakistan,resulting in an accuracy rate of 85%.This reaffirms the model’s suitability for real-world ASD *** research offers valuable insights into classifier performance,emphasizing the potential of machine learning to deliver precise and accessible ASD diagnoses via facial image analysis.

关键词： Autism Autism Spectrum Disorder(ASD) disease segmentation features optimization deep learning models facial images classification

来源：评论

学校读者我要写书评

暂无评论

Cognition2Vocation: meta-learning via ConvNets and continuous transformers

引用

Neural computing and Applications 2024年第21期36卷 12935-12950页

作者： Kamran, Sara Hosseini, Saeid Esmailzadeh, Sayna Kangavari, Mohammad Reza Hua, Wen School of Computer Engineering Iran University of Science and Technology Tehran Iran Faculty of Computing and Information Technology Sohar University Sohar Oman Department of Computing The Hong Kong Polytechnic University Hong Kong

Estimating the suitability of individuals for a vocation via leveraging the knowledge within cognitive factors comes with numerous applications: employment resourcing, occupation counseling, and workload management. Accordingly, the enterprises aim to hire the most suitable person from a massive array of similar applicants, maximizing performance and minimizing the gap between strategic indicators and predefined targets. While cognitive factors signify the best-suited person from similarly skilled workers, inferring pertinent latent cues from noisy and growing social network contents is time-intensive. To tackle the challenges involved, we propose a framework that, on the one hand, extends influential features based on the correlations between cognitive cues and, on the other hand, leverages a novel continuous transformer to mitigate the overlapping and approximation issues in discrete modeling. Rather than relying on discrete patterns that may evolve frequently, we use continuous elements that include not only numerous aggregating components but also sense minor irregular fluctuations. In a hybrid manner, we fuse multiple base models to transfer a higher representation to the meta-learning unit, agglomerating outputs from gradient boosters and the ConvNets. The experimental results show that our proposed framework can outperform trending vocation estimation methods by 1.36% in F1-Score and approximately 1% in accuracy. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Knowledge management

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：