IJCI. International Journal of Computers and Information最新文献_第2页

Enhancing the Performance of Generative Adversarial Networks with Identity Blocks and Revised Loss Function to Improve Training Stability 利用身份块和修正损失函数增强生成对抗网络的性能以提高训练稳定性

IJCI. International Journal of Computers and Information Pub Date : 2023-09-01 DOI: 10.21608/ijci.2023.200402.1101

Mohamed Salem, Mohamed Sakr, Sherif Eletriby

{"title":"Enhancing the Performance of Generative Adversarial Networks with Identity Blocks and Revised Loss Function to Improve Training Stability","authors":"Mohamed Salem, Mohamed Sakr, Sherif Eletriby","doi":"10.21608/ijci.2023.200402.1101","DOIUrl":"https://doi.org/10.21608/ijci.2023.200402.1101","url":null,"abstract":"Generative adversarial networks (GANs) are a powerful deep learning model for synthesizing realistic images; however, they can be difficult to train and are prone to instability and mode collapse. This paper presents a modified deep learning model called Identity Generative Adversarial Network (IGAN) to address the challenges of training and instability faced by generative adversarial models in synthesizing realistic images. The IGAN model includes three modifications to improve the performance of DCGAN: a non-linear identity block to ease complex data fitting and reduce training time; a modified loss function with label smoothing to smooth the standard GAN loss function; and minibatch training to use other examples from the same minibatch as side information for better quality and variety of generated images. The effectiveness of IGAN was evaluated and compared with other state-of-the-art generative models using the inception score (IS) and Fréchet inception distance (FID) on CelebA and stacked MNIST datasets. The experiments demonstrated that IGAN outperformed the other models in terms of convergence speed, stability, and diversity of results. Specifically, in 200 epochs, IGAN achieved an IS of 13.6 and an FID of 46.2. Furthermore, the IGAN collapsed modes were compared with other generative models using a stacked MNIST dataset, showing the superiority of IGAN in producing all the modes while the other models failed to do so. These results demonstrate that the modifications implemented in IGAN can significantly enhance the performance of GANs in synthesizing realistic images, providing a more stable, high-quality, and diverse output.","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133547627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Security Evaluation of Different Hashing Functions with RSA for Digital Signature 不同哈希函数在RSA数字签名中的安全性评估

IJCI. International Journal of Computers and Information Pub Date : 2023-09-01 DOI: 10.21608/ijci.2023.208602.1108

M. Badawy

{"title":"Security Evaluation of Different Hashing Functions with RSA for Digital Signature","authors":"M. Badawy","doi":"10.21608/ijci.2023.208602.1108","DOIUrl":"https://doi.org/10.21608/ijci.2023.208602.1108","url":null,"abstract":"The emergence of the Internet of Things (IoT) represents a significant trend, where integrating IP, data, and wireless technologies onto a single network yields substantial advantages that are both essential and appealing. However, the amalgamation of these entities introduces novel susceptibilities and opportunities for infiltrating IoT networks, thereby necessitating the perpetual advancement of integrated security methodologies. This study investigates the feasibility of utilizing the Rivest–Shamir–Adleman (RSA) method, based on the Miller-Rabin technique, as a stream key generator with five distinct hashing functions to attain robust digital signatures. The RSA encryption method underwent a comprehensive battery of tests to assess its validity, and its encryption efficacy was evaluated through mathematical analysis. This research examines the assessment of digital signatures by utilizing five distinct hash functions in conjunction with RSA keys. Each signature file was assessed based on four tests: entropy, floating frequency, autocorrelation, and histogram analysis. The tests were conducted on a document with a size of 256 bytes. In addition, nine hash algorithms were utilized, namely SHA224, SHA256, SHA384, SHA512, BLAKE2B, BLAKE2S, MD5, MD2, and RIPEMD160. Different algorithms were used for varying key sizes and word counts for hashing. The experiment was repeated 100 times to obtain precise measurements of the average time and entropy. The findings indicate that when implemented with an appropriate key length, RSA exhibits both efficiency and sufficient security to be deployed in IoT networks.","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131384429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparative Study of Intelligent Scheduling Algorithms for Heterogeneous Systems 异构系统智能调度算法的比较研究

IJCI. International Journal of Computers and Information Pub Date : 2023-08-10 DOI: 10.21608/ijci.2023.213534.1114

A. Kafafy, abla elsayed, O. Abdel Raouf

引用次数: 0

Machine Learning Algorithms for Enhancing Emotion Recognition from EEG Signals 从脑电图信号增强情绪识别的机器学习算法

IJCI. International Journal of Computers and Information Pub Date : 2023-06-14 DOI: 10.21608/ijci.2023.199502.1099

Aseel Attia, Khalid Amin, Mina I. S. Ibrahim

引用次数: 0

Brain Tumor Detection Based on A Combination of GLCM and LBP Features with PCA and IG 基于GLCM和LBP特征结合PCA和IG的脑肿瘤检测

IJCI. International Journal of Computers and Information Pub Date : 2023-05-31 DOI: 10.21608/ijci.2023.205444.1107

Mohamed Wageh, Khalid Amin, A. Zytoon, Mina Ibrahim

引用次数: 0

Q-rank Metric to measure Search Engine Optimization Q-rank度量搜索引擎优化

IJCI. International Journal of Computers and Information Pub Date : 2023-05-09 DOI: 10.21608/ijci.2023.170064.1090

Dina Shafiq, Hayam Mousa, Khalid Amin

引用次数: 0

Historical Isolated Forest for detecting and adaptation concept drifts in nonstationary data streaming 历史孤立森林用于非平稳数据流中概念漂移的检测和自适应

IJCI. International Journal of Computers and Information Pub Date : 2023-03-05 DOI: 10.21608/ijci.2023.185429.1095

Ahmed H. Madkour

引用次数: 1

A New Approach To Suicide Ideation Detection from Text Content 基于文本内容的自杀意念检测新方法

IJCI. International Journal of Computers and Information Pub Date : 2023-02-20 DOI: 10.21608/ijci.2023.173255.1092

Abdallah Basyouni, Hatem Abdelkader, Asmaa Ali

引用次数: 1

An evaluation framework for selecting cloud service provider in neutrosophic environment and Modified Generative Adversarial Network 中性环境下云服务提供商选择评估框架及改进生成对抗网络

IJCI. International Journal of Computers and Information Pub Date : 2022-11-14 DOI: 10.21608/ijci.2022.164289.1088

Mohammed Attya, M. El-Sayed, Ahmed S. Sakr, Hatem Ahmed

引用次数: 1

Improved version of explainable decision forest: Forest-Based Tree 可解释决策森林的改进版本:基于森林的树

IJCI. International Journal of Computers and Information Pub Date : 2022-11-11 DOI: 10.21608/ijci.2022.155977.1082

Faten Khalifa, Asmaa Ali, Hatem Abdel-Kader

引用次数: 1