Egyptian Informatics Journal最新文献

{"title":"Novel validity indices for dynamic clustering and an Improved Dynamic Fuzzy C-Means","authors":"Ramiro Saltos ,&nbsp;Ignacio Carvajal ,&nbsp;Fernando Crespo ,&nbsp;Richard Weber","doi":"10.1016/j.eij.2025.100613","DOIUrl":"10.1016/j.eij.2025.100613","url":null,"abstract":"<div><div>Dynamic clustering algorithms play a crucial role in numerous real-world applications by continuously adapting to evolving data patterns and identifying changes within the underlying cluster structure. However, unlike static clustering, where a plethora of validation indices exist to assess the solution’s quality, evaluating the effectiveness of dynamic clustering algorithms remains a challenge. This paper addresses this gap by proposing a novel set of six validation indices specifically designed for dynamic clustering. These indices assess the quality of solutions generated at three distinct granularities: individual clusters, individual observation periods, and the entire observation horizon. Our focus centers on cluster creation and elimination, recognized as the most critical structural changes within the dynamic clustering literature. To illustrate the application of these novel indices, we introduce an improved version of the dynamic fuzzy c-means algorithm (I-DFCM) which offers enhanced computational stability for handling dynamic data. We demonstrate the effectiveness of both the I-DFCM algorithm and the new validation indices through computational experiments using both synthetic and real-world datasets. The experiments showcase how these indices can effectively validate dynamic clustering solutions and guide parameter tuning for optimal performance, and support practical applications such as dynamic community detection in social networks and informed decision-making in dynamic environments. The results highlight the significant potential of these new validation indices and the I-DFCM algorithm in advancing the field of dynamic clustering.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100613"},"PeriodicalIF":5.0,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143175764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Benchmark Arabic news posts and analyzes Arabic sentiment through RMuBERT and SSL with AMCFFL technique","authors":"Mustafa Mhamed ,&nbsp;Richard Sutcliffe ,&nbsp;Jun Feng","doi":"10.1016/j.eij.2024.100601","DOIUrl":"10.1016/j.eij.2024.100601","url":null,"abstract":"<div><div>Sentiment analysis aims to extract emotions from textual data; sentiment analysis and text recognition are two of the most common tasks associated with natural language processing. Emergent technologies have been developed and employed in various fields, including marketing, health care, and policy making. However, with the growth of social media platforms and the flow of data, especially in the Arabic language, substantial difficulties have emerged that call for the creation of new frameworks to address problems, such as the lack of datasets related to news platforms, the complicated formation of the Arabic language, and complications with classifying, and system challenges, whether in machine learning, deep learning, or online analysis tools. This paper provides a new framework that helps address ASA challenges and work on various tasks based on the state-of-the-art ASA. First, it presents a new collection named (ANP5) from Arabic news posts from several Arabic platforms, then uses SSL with AMCFFL technique to analyze the Arabic sentiment and generate a second dataset (ANPS2). Next, applied ML classifiers, RF and SVM, do the best among the other classifiers, with an accuracy of 82.00%; however, the measurement distributions for each class are different (Experiment 1). Following that, DL models, BIGRU, CNN-LSTM, LSTM, and CNN, had accuracies of 88.10%, 89.30%, 89.85%, and 90.10% (Experiment 2). Experiments 1 and 2 represent the initial benchmark classification as the first baseline. Afterward, a new RMuBERT Model was developed and compared with four transformers on the two datasets: ANPS2 accuracy (90.87%) and ANP5 (90.33%). RMuBERT performed better than the baselines (Experiment 3). Further testing of RMuBERT on various Arabic corpora with different classes, lengths, and sizes: ArSarcasm (3C), STD (2C), AJGT (2C), and AAQ (2C), revealed accuracies of 77.76%, 91.79%, 94.07%, and 93.48%, respectively. Still, RMuBERT performed better than the baselines (Experiment 4). Finally, on the largest Arabic sentiment corpora with six million Arabic tweets, the performance is up to (91.12%); RMuBERT works efficiently with less training time (Experiment 5).</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100601"},"PeriodicalIF":5.0,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143175766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Next-Generation energy Management: Particle Density algorithm for residential microgrid optimization","authors":"Liang Wang ,&nbsp;Nan Sun","doi":"10.1016/j.eij.2025.100611","DOIUrl":"10.1016/j.eij.2025.100611","url":null,"abstract":"<div><div>This study presents an innovative approach to optimize energy management in residential microgrids, in light of the rising demand for energy and mounting environmental concerns. The research underscores the vital role of efficient energy management and responsive load control to improve energy efficiency and reduce consumer costs. To this end, a framework is proposed in which a power aggregator operates within a microgrid to manage residential electricity consumption. The primary goal of this framework is to minimize energy costs while considering subscriber preferences and the capacity limitations of the distribution network. The improved particle swarm optimization (IPSO) algorithm is employed to optimize energy management, resolve convergence challenges, and ensure user requirements are effectively prioritized. Integrating emergency, economic, and planned strategies provides cost savings, ensures grid stability, and enhances user satisfaction. The incorporation of Internet of Things (IoT) technology enables seamless communication, precise device control, and data-driven decision-making, empowering households to manage their energy loads more effectively and contribute to grid efficiency. Through scenario analysis, this research demonstrates the IPSO algorithm’s potential for significant cost reductions and improved grid stability. In Scenario 1, focused exclusively on affordability, numerical analyses present the total cost of electricity under different load conditions over three months. Scenario 2, also prioritizing affordability, highlights the impact of economic considerations on electricity expenses. Furthermore, Scenario 3 (80 % emergency + 20 % affordable) and Scenario 4 (50 % emergency + 20 % affordable + 30 % planned) showcase the potential for cost reduction through various priority combinations. These insights reflect the effectiveness of load management strategies facilitated by IoT technology. This comprehensive energy management approach lays a strong foundation for a resilient and adaptable energy infrastructure that meets society’s evolving demands.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100611"},"PeriodicalIF":5.0,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143175763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The financial impact of human resources configuration: A quantitative analysis based on modified single candidate optimizer","authors":"Zhuozhuo Zhang ,&nbsp;Jun Lu ,&nbsp;Qi Wang","doi":"10.1016/j.eij.2024.100584","DOIUrl":"10.1016/j.eij.2024.100584","url":null,"abstract":"<div><div>Recently, by complicated and fast changing business environments, the effective allocation of Human Resources (HR) is considered as an important task to achieve success within organizations. However, the optimal allocation of HR is considered as a complicated challenge due to the uncertainties that are inherent in the process. Traditional approaches often rely on manual decision-making, which can result in less effective allocations and reduced productivity. With the rise of big data and advanced analytics, there is an increasing demand for data-driven methodologies to enhance HR allocation. This paper presents an innovative HR optimization framework that uses a modified metaheuristic model, called the Modified Single Candidate Optimizer (MSCO) algorithm to resolve this task. The framework integrates big data analytics and system analysis to establish a quantitative management strategy for optimizing HR configurations. By using the advantages of the proposed MSCO, the framework can effectively address the HR allocation problems to provide an optimal solution. The results indicate that the proposed framework significantly improves HR utilization rates, labor productivity.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100584"},"PeriodicalIF":5.0,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The role of hybrid models in financial decision-making: Forecasting stock prices with advanced algorithms","authors":"Xiaoyi Zhu","doi":"10.1016/j.eij.2025.100610","DOIUrl":"10.1016/j.eij.2025.100610","url":null,"abstract":"<div><div>Stock price volatility is influenced by many factors, which are significant obstacles to achieving accurate stock price forecasting in the financial market. This study introduces a novel hybrid model to tackle the abovementioned issues by integrating various algorithms, including bidirectional long short-term memory and random forest. Additionally, it incorporates ensemble empirical mode decomposition, sample entropy clustering, and sea-horse optimizer as part of its methodology. Exponential moving average 30, relative strength index 14, simple moving average 30, moving average convergence divergence, on-balance-volume, and daily open price, high price, low price, close price, and trading volume of the S&amp;P 500 index between 01/04/2013 and 12/29/2022 were utilized as the dataset. To reduce the complexity of the time series decomposition and clustering methods were employed. Then, the high sequences underwent processing using the optimized random forest algorithm, and the remaining sequences were subjected to processing utilizing optimized bidirectional long short-term memory. This approach allowed the model to generalize effectively across a variety of global indices, as demonstrated by its high prediction accuracy (coefficient of determination (<span><math><msup><mrow><mi>R</mi></mrow><mn>2</mn></msup></math></span>) values exceeding 0.98 for the Dow Jones, CSI, Nikkei, and DAX indices). Additionally, robustness testing was conducted by introducing incremental noise levels to simulate real-market conditions, which demonstrated that the model remains highly accurate even at the highest noise level. In comparison to other methods, the proposed model demonstrated superior performance on the S&amp;P 500, with an R² of 0.99 and low error metrics. This model’s adaptability and reliability in diverse and volatile market conditions are emphasized by this robust framework, which renders it a potent financial forecasting tool.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100610"},"PeriodicalIF":5.0,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143175762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Basketball technical action recognition based on a combination of capsule neural network and augmented red panda optimizer","authors":"Nu Sha","doi":"10.1016/j.eij.2024.100603","DOIUrl":"10.1016/j.eij.2024.100603","url":null,"abstract":"<div><div>Basketball is a group sport that needs precise identification of the players’ practical actions in different shooting movements for effective training and performance enhancement. This subjective nature of training assessments that most of the time rely only on coaches’ observations, highlights the need for objective analysis tools. The subjective and non-objective nature of present educational calculations that are often based on the observations and experiences of coaches and coaches, highlights the requirement for objective and data-driven analysis tools. Such tools can help trainers make more precise and unbiased calculations of student performance and make better instructional choices. This study presents a new model to identify the basketball technical actions based on combination of the CapsNets or Capsule Neural Networks with an ARPO or augmented variant of Red Panda Optimizer. The study conducts the tasks presented by changing lighting settings and complicated human movements in basketball. By means of the suggested CapsNets/ARPO model, the network’s capability can be improved in distinguishing the dynamic targets. The CapsNet/ARPO system reaches advanced performance in the recognition of shooting actions in basketball, with an accuracy of 92.6% and outperforming existing approaches. Its modular design and user-friendly interface make it easily integrable, and a case study with a professional team indicates significant improvements in player performance (15.6% increase in shooting accuracy) and reduced implementation time (30%) to demonstrate its potential to improve basketball analytics and coaching.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100603"},"PeriodicalIF":5.0,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A file archival integrity check method based on the BiLSTM + CNN model and deep learning","authors":"Jinxun Li,&nbsp;Tingjun Wang,&nbsp;Chao Ma,&nbsp;Yunxuan Lin,&nbsp;Qing Yan","doi":"10.1016/j.eij.2024.100597","DOIUrl":"10.1016/j.eij.2024.100597","url":null,"abstract":"<div><div>Validating and integrity-checking archives ensures that files are authentic, trustworthy, and usable. In the age of digital technology, historical records must be genuine. Researching in archives raises ethical issues while having little to do with individuals. Traditional archive integrity solutions have scaling issues, real-time monitoring issues, and missed opportunities. An updated Archive File Integrity Check Method (AFICM) may solve these issues, and the paper explains it. Deep learning allows the combination of a Bidirectional Long-Short Term Memory (Bi-LSTM) with adaptive gating and an adaptive Temporal Convolutional Neural Network (TCNN) with multi-scale temporal attention. This method protects archived material against manipulation, which is crucial. The recommended method extracts complex sequential patterns and variants using adaptive TCNN trained on file data. Next, it analyzes these features using a Bi-LSTM network and attenuation method. It allows it to highlight significant temporal correlations while downplaying irrelevant data selectively. The hybrid model outperforms checksums in accuracy and dependability. It uses adaptive TCNNs for time-related feature extraction and attenuated Bi-LSTM for refinement. The F1 score, recall, accuracy, precision, and AU-ROC are critical measures for model evaluation. The AICM performed well overall, with 97.32% precision and 98.95% accuracy. This integrity check method outperforms others with an F1 score of 97.58, an AU-ROC of 0.983, and a recall rate of 98.18%. The findings set a new standard for archiving system integrity testing by showing the model’s dependability and security in several use scenarios.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100597"},"PeriodicalIF":5.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Bayesian regularization intelligent computing scheme for the fractional dengue virus model","authors":"Manoj Gupta ,&nbsp;Pattarasinee Bhattarakosol","doi":"10.1016/j.eij.2024.100606","DOIUrl":"10.1016/j.eij.2024.100606","url":null,"abstract":"<div><div>This research’s goal is to investigate the numerical assessments of a fractional order dengue viral model (FO-DVM) by using the artificial intelligence procedure of Bayesian regularization neural networks (BRNNs). The FO derivatives present more precise results as compared to integer order for solving the DVM. The dynamics of the mathematical DVM form is considered into five classes. The computing stochastic BRNNs approach is presented for three variations with the selection of the data as testing 13%, authentication 11% and training 76% together with sixteen hidden neurons. The result’s comparison is accessible in the form of overlapping, which is based on the BRNNs approach and reference Adam solutions. However, minor absolute error around 10^-05 to 10^-07 enhances the worth of the proposed solver. The BRNNs approach is used to minimize the mean square error for the mathematical FO-DVM. The obtained measurements of error histograms values, and regression coefficient calculated as 1 are presented to verify the efficiency of stochastic BRNNs approach.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100606"},"PeriodicalIF":5.0,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced breast cancer detection and classification via CAMR-Gabor filters and LSTM: A deep Learning-Based method","authors":"Vinit Kumar ,&nbsp;Chandrashekhara K T ,&nbsp;Naga Padmaja Jagini ,&nbsp;K Varada Rajkumar ,&nbsp;Rakesh Kumar Godi ,&nbsp;Praveen Tumuluru","doi":"10.1016/j.eij.2024.100602","DOIUrl":"10.1016/j.eij.2024.100602","url":null,"abstract":"<div><div>Breast cancer detection and classification are crucial for early diagnosis and effective treatment planning. This work proposed Modified Context-Aware Multiresolution Gabor Filters-Based Breast Cancer Classification (CAMR- GF-BCC) for identifying and categorizing breast cancer. Initially, the mammographic images are preprocessed through normalization and Gaussian filtering to enhance image quality and suppress noise. Subsequently, the processed images are segmented using the DeepLabv3 + model, which effectively delineates the regions of interest. Post-segmentation, the images are masked to isolate the significant features for analysis. Arithmetic features and CAMR-GF are then performed from these masked images, capturing essential characteristics pertinent to breast cancer detection. These features serve as inputs to a Long Short-Term Memory (LSTM). It is utilized in the work of categorization, leveraging its capability to handle sequential data and capture complex patterns. The proposed method is rigorously evaluated using standard performance metrics, showing its effectiveness in precisely identifying and categorizing breast cancer. This CAMR-GF-BCC work has 99.48 accuracy, 99.64 sensitivity, 99.14 specificity, 99.01 precision, and 98.16 F1-score. The results indicate a promising improvement in diagnostic accuracy, potentially aiding in timely and precise breast cancer treatment decisions.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100602"},"PeriodicalIF":5.0,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced colon cancer detection: Integrating context-aware multi-image fusion (Camif) in a multi-stage framework","authors":"M.V.R. Vittal","doi":"10.1016/j.eij.2025.100609","DOIUrl":"10.1016/j.eij.2025.100609","url":null,"abstract":"<div><div>Colon cancer begins in the large intestine, often evolving from benign polyps into malignant cancer. Early detection through screening is vital for effective treatment and better survival rates. Risk factors include age, genetics, diet, and lifestyle, with symptoms like changes in bowel habits and blood in the stool, though early stages may be asymptomatic. This work proposed a comprehensive multi classes detection and classification of colon cancer. In this work we used publicly available Curated Colon Dataset to diagnose conditions such as esophagitis, ulcerative colitis, polyps, and normal cases. The proposed approach uses advanced deep learning models to integrate pre-processing, segmentation, and classification. The process begins with pre-processing, which involves resizing, contrast enhancement, noise reduction, and normalization of pixel values. This work proposes a Context-Aware Multi-Image Fusion (CA-MIF) technique in the preprocessing phase to improve the visibility of blood vessels and tissue texture, enhancing diagnostic accuracy. The processed images are then input to a U-Net++ model for segmentation, generating masks highlighting regions of interest, including the colon and affected areas. Post-segmentation, image enhancement techniques further refine the quality and clarity of the images. Enhanced images are then classified using the ResNet-50 model, trained to categorize images into four distinct classes: esophagitis, ulcerative colitis, polyps, and normal. In the classification phase, cancerous classes (ulcerative colitis and polyps) undergo additional segmentation using DeepLabv3+. Model 1 (DeepLabv3+) is applied to ulcerative colitis, generating detailed masks to analyze affected regions, while Model 2 (DeepLabv3+) is used for polyps. For the U-Net++ and DeepLabv3+ models, evaluation measures are segmentation accuracy, precision, recall, and F1 score; for the ResNet-50 model, these metrics are classification accuracy, precision, recall, and F1 score. When it comes to detecting and differentiating between malignant and non-cancerous illnesses, the framework achieves great accuracy., demonstrating its effectiveness and potential for clinical applications in medical image analysis. The results indicate the proposed method’s high efficacy, achieving an F1 score of 99.31. It also demonstrated strong performance metrics with a specificity of 99.91, sensitivity of 99.10, accuracy of 98.18, and a Dice coefficient of 99.82, highlighting its robust capability in accurately detecting colon cancer.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100609"},"PeriodicalIF":5.0,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}