{"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}
{"title":"Analyzing urban public sports facilities for recognition and optimization using intelligent image processing","authors":"Zhongqian Zhang","doi":"10.1016/j.eij.2024.100604","DOIUrl":"10.1016/j.eij.2024.100604","url":null,"abstract":"<div><div>Quality of urban public sports facilities has an implication for increasing sports satisfaction levels in individuals and for developing a better way of life in cities. The current study aims to assess and improve urban public sports services through intelligent image processing techniques for assessing sports facilities. The method incorporates an optimized Residual-Shuffle Network modified by a boosted variant of Spring Search Algorithm (BSSA) for efficient image recognition along with metaheuristics and super-efficiency data envelopment analysis (SE-DEA) model. The images captured systematically using photographic equipment identify such key information as facility usage, viewer demographics, and activity levels by deep learning algorithms. Sports facilities’ effectiveness evaluation for improvement and optimization has been done using metaheuristics and SE-DEA model. The model has been verified with other modern methods, including Faster R-CNN and Convolutional Neural Network (CNN). The results indicate that the SE-DEA model with an accuracy of 94.76% in recognizing sports facilities, outperforming advanced comparative models like Faster R-CNN (74.21%) and CNN (60.54%). The mean execution time of SE-DEA is 5.6 s, which is slower than Faster R-CNN (4.13 s) but faster than CNN (10.98 s). Also, the SE-DEA model provides a significant reduction in costs, with a public service fee of 1200 (compared to 3200 for traditional public services) and a facility maintenance cost of 1000 (compared to 2500 for traditional public services).</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100604"},"PeriodicalIF":5.0,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174179","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}
Shadan Mohammed Jihad , Ali Aalsaud , Firas H. Almukhtar , Shahab Kareem , Raghad Zuhair Yousif
{"title":"Investigating feature extraction by SIFT methods for prostate cancer early detection","authors":"Shadan Mohammed Jihad , Ali Aalsaud , Firas H. Almukhtar , Shahab Kareem , Raghad Zuhair Yousif","doi":"10.1016/j.eij.2024.100607","DOIUrl":"10.1016/j.eij.2024.100607","url":null,"abstract":"<div><div>Globally, for this leading type of cancer among males, early detection is indispensable for increasing treatment success rates and prognoses of the patients. This research study, therefore, seeks to explore the effectiveness of the SIFT method in improving feature extraction toward the accurate detection of incipient prostate cancer. The robust SIFT relates to tasks of object recognition within computer vision, in the recognition of prostatic regions where grey-level distributions differ remarkably between benign and malignant tissues. The adopted methodology was based on the comparative analysis and benchmarking of the performance of feature extraction based on SIFT against traditional image processing techniques with a generic representation on a number of metrics: sensitivity, specificity, and overall diagnostic accuracy. A dataset consisting of annotated prostate MRI images was utilized to train and validate the model. According to the results so far revealed, the SIFT model can isolate and recognize key features across different scales and angles far better than the cue given by any of the conventional methods currently in use, therefore indicating a much more accurate and reliable cue to early-stage prostate cancer.</div><div>Besides, the model developed on SIFT was found to have significantly improved the rate of detection for early-stage prostate tumors, which usually go undetected in conventional methods of imaging. This study, therefore, highlights the potential for use in the early detection of prostate cancer with advanced feature extraction methods, such as SIFT, and points toward a very promising direction of further research on applying computer vision techniques to problems in medical diagnostic applications. It would, therefore, suggest further experimentations to optimize these methodologies in clinical settings, otherwise which may revolutionize clinical diagnostics for prostate cancer and early intervention strategies.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100607"},"PeriodicalIF":5.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174183","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}
Amna Iqbal , Muhammad Younas , Saman Iftikhar , Fakeeha Fatima , Rabia Saleem
{"title":"Spam detection using hybrid model on fusion of spammer behavior and linguistics features","authors":"Amna Iqbal , Muhammad Younas , Saman Iftikhar , Fakeeha Fatima , Rabia Saleem","doi":"10.1016/j.eij.2024.100605","DOIUrl":"10.1016/j.eij.2024.100605","url":null,"abstract":"<div><div>E-commerce sites, forums, and blogs have become popular platforms for people to share their views. Reviews have emerged as a crucial source of information for potential customers, influencing their purchasing decisions. Similarly for gaining profit or fame, Spam reviews are deliberately written with the intention of defaming businesses or individuals. This act is known as review spamming. Spam review detection is rapidly answered by various ML techniques. Review of spamming is more challenging task in multilingual communities. Spammer behavior features and linguistic features often exhibit complex relationships that influence the nature of spam reviews. The unified representation of features is another challenging task in spam detection. Various deep learning approaches have been proposed for review spamming, including different neural networks (Convolutional Neural Network, CNN). These methods are specialized in extracting the features but lack to capture feature dependencies effectively with other features. Spam Review Detection using the Fusion Gradient Boosting (GB) Model and Support Vector Machine (SVM) (Hybrid-BoostSVM) is proposed with fusion of spammer behavior features and linguistic features to automatically detect and classify the spam reviews. Fusion enables the proposed model to automatically learn the interactions between the features during the training process, allowing it to capture complex relationships and make predictions based on both types of features. It apparently shows the promising result by obtaining <strong>94.6 %</strong> accuracy.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100605"},"PeriodicalIF":5.0,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174186","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}
Viacheslav Kovtun , Oksana Kovtun , Krzysztof Grochla , Oleh Yasniy
{"title":"The quality of service assessment of eMBB and mMTC traffic in a clustered 5G ecosystem of a smart factory","authors":"Viacheslav Kovtun , Oksana Kovtun , Krzysztof Grochla , Oleh Yasniy","doi":"10.1016/j.eij.2024.100598","DOIUrl":"10.1016/j.eij.2024.100598","url":null,"abstract":"<div><div>Industry 4.0 demands seamless integration of smart factories with the Industrial Internet of Things (IIoT), reliant on robust communication infrastructure. Leveraging 5G’s support for enhanced Mobile Broadband (eMBB), massive Machine Type Communication (mMTC), and Network Slicing (NS), this study explores quality of service assurance within a clustered 5G ecosystem of a smart factory. The article proposes two new multi-parameter scenarios for allocating the entire channel pool between different types of requests (mMTC, eMBB) for the model of an integrated open 5G cluster. The scenario with isolation does not allow channel reassignment between requests of different types or originating zones (handover or from the coverage area of the target 5G cluster), while the virtual scenario allows such reassignment. It is shown that using these scenarios, the stationary distribution of probabilities of states of the corresponding two-dimensional Markov chains has a multiplicative form. An information technology has been developed to calculate QoS indicators for different types of requests using these channel allocation scenarios. Studies have been conducted on the effectiveness of using one or another access strategy depending on the loads on the 5G cluster. Based on the proposed mathematical apparatus, the information technology enables finding the optimal scenario for channel allocation, as well as calculating the parameters’ values for such a scenario.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100598"},"PeriodicalIF":5.0,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174185","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":"Graph Sample and Aggregate-Attention network optimized for automatic translation of five line stanzas of Tang poems to poetic language","authors":"Haiyan Yang , Yuping Fu","doi":"10.1016/j.eij.2024.100575","DOIUrl":"10.1016/j.eij.2024.100575","url":null,"abstract":"<div><div>Tang poems, also known as Tang poetry is a significant genre of classical Chinese poetry that flourished during the Tang dynasty, which spanned from 7th to the 9th century. These poems are celebrated for their artistic elegance, rich imagery, and profound emotional expressions. Tang poetry covers a wide range of themes, including nature, love, politics, society, and personal reflections. The Tang dynasty’s poetic legacy has left an indelible mark on Chinese literature and has had a lasting influence on poetry throughout the world. The Tang dynasty saw the propagation of Buddhism in China, and this spiritual influence is evident in many Tang poems. Poets often blended Buddhist concepts and imagery into their verses, adding a layer of depth and universality. In this manuscript, Graph Sample and Aggregate-Attention Network optimized for automatic translation of five line stanzas of tang poems to poetic language (GSAAN-AT-FLS-TPPL) is proposed. First, the data is collected from Poem Comprehensive Dataset (PCD). Then the collected data is given to preprocessing using Modified Fractional Order Unscented Kalman Filter for identifying the errors. Then the data is trained using GSAAN and Pelican Optimization algorithm for getting accurate results. The proposed GSAAN-AT-FLS-TPPL is performed in Python and its efficacy is analyzed under some metrics, such as Accuracy, Computational time, Recall, Mean Square Error and Power Dissipation. The simulation outcomes proves that the proposed technique attains 25.34%, 22.39% and 28.45 % higher precision, 24.98%, 18%, 29.1% lower computational time compared with the existing methods.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100575"},"PeriodicalIF":5.0,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174181","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}
Arjon Turnip , Mohammad Taufik , Dwi Esti Kusumandari
{"title":"Precision blood pressure prediction leveraging Photoplethysmograph signals using Support Vector Regression","authors":"Arjon Turnip , Mohammad Taufik , Dwi Esti Kusumandari","doi":"10.1016/j.eij.2024.100599","DOIUrl":"10.1016/j.eij.2024.100599","url":null,"abstract":"<div><div>To facilitate the operation of more sophisticated medical robots, blood pressure prediction technology was developed using Photoplethysmograph (PPG) signals from a single finger, using the Support Vector Regression (SVR) method. The data collection process involved 110 participants aged 20 to 70 years for modeling and validation. The model training phase was carried out with various parameter variations to obtain the optimal model based on the Mean Absolute Error (MAE) value. The blood pressure estimation results showed an average error of around 2.78 mmHg for systolic pressure and 7.34 mmHg for diastolic pressure. Validation on 30 new participants revealed a slight increase in the average error, which was around 4.23 mmHg (with 93.90 % accuracy) for systolic pressure and 5.12 mmHg (with 96.64 % accuracy) for diastolic pressure. These results, which are characterized by a low error rate, indicate that the SVR model is able to predict blood pressure accurately and consistently, both on training data and new data that was previously unseen.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100599"},"PeriodicalIF":5.0,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174184","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":"Reinforcement learning for process Mining: Business process optimization with avoiding bottlenecks","authors":"Ghada Soliman , Kareem Mostafa, Omar Younis","doi":"10.1016/j.eij.2024.100595","DOIUrl":"10.1016/j.eij.2024.100595","url":null,"abstract":"<div><div>Process mining extracts knowledge from event data to understand, analyze, and improve processes. The activity of manually identifying the optimal sequence of transitions for process mining is challenging due to several difficulties, including the high complexity of business processes that may involve numerous activities and decision points, and the significant effort required to collect and analyze the necessary data, ex1plore different transition possibilities, and evaluate their impact on process performance. In our study, we have implemented Process Mining Environment in OpenAI gym format aimed at enhancing the development of reinforcement learning algorithms for process optimization tasks. The capabilities of these approaches of reinforcement learning using the Q-learning and Deep Q-network (DQN) techniques to identify the optimal path. This is achieved by constructing a reward matrix tailored to each method, designed to circumvent absorption states that signify bottlenecks. The environment was tested using a proprietary dataset containing 3,414 tickets, with event logs sourced from the ServiceNow ticketing system. The findings indicate a significant reduction in the action space, with Q-learning and DQN achieving a decrease of 75% and 67%, respectively.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100595"},"PeriodicalIF":5.0,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174380","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":"An information dissemination strategy in social networks based on graph and content analysis","authors":"Jing Huang","doi":"10.1016/j.eij.2024.100563","DOIUrl":"10.1016/j.eij.2024.100563","url":null,"abstract":"<div><div>Social networking platforms like Facebook, Twitter, Instagram, and LinkedIn have revolutionized communication, but there’s growing concern about invalid information, misinformation, and disinformation. Malicious actors exploit these platforms for economic, political, or ideological purposes, impacting public trust, democratic processes, and individual decision-making. Research is being conducted to develop tools to distinguish genuine and invalid information. Twitter, with its vast user base, has become a focal point for studying information diffusion patterns and identifying potential sources of misinformation. A novel method is proposed for identifying information dissemination paths based on node centrality criteria, analyzing the network structure and characteristics of Twitter users to uncover influential nodes that play a crucial role in spreading information across the network. The study explores the potential of deep learning and ensemble learning techniques in content development to improve the accuracy of information classification. Examining the performance of the proposed hybrid model in classifying misinformation showed that in terms of average accuracy, f-measure, and AUC, it achieved 98.6 %, 0.9858, and 0.9862 respectively, which are at least 1.6 %, 1.62 % and 1.5 % higher than the compared method. Additionally, the proposed model could recognize the leader nodes in information dissemination by the highest accuracy of 86% which is competitive with the metaheuristic-based approaches such as FFO and GWO. By leveraging advanced computational techniques and data analysis, we can strive towards a more informed and trustworthy digital environment, where users can navigate through the sea of information with confidence and make well-informed decisions.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100563"},"PeriodicalIF":5.0,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174381","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":"High-accuracy lung disease classification via logistic regression and advanced feature extraction techniques","authors":"Swapandeep Kaur , Sheifali Gupta , Deepali Gupta , Sapna Juneja , Ali Nauman , Mudassir Khan , Izhar Husain , Asharul Islam , Saurav Mallik","doi":"10.1016/j.eij.2024.100596","DOIUrl":"10.1016/j.eij.2024.100596","url":null,"abstract":"<div><div>Lung disease diagnosis through medical imaging integrated with machine learning has seen significant advancements. This study investigates the optimization of lung disease classification by exploring various preprocessing, feature extraction, and machine-learning classifier combinations. Our methodology begins with an input dataset of lung X-ray images, which undergoes preprocessing steps such as image sharpening and histogram equalization to enhance image quality. Subsequently, feature extraction techniques, including Scale-Invariant Feature Transform (SIFT), Histogram of Oriented Gradients (HOG), and Local Binary Patterns (LBP), are applied to the pre-processed images. We evaluate the effectiveness of several machine learning classifiers—Naive Bayes (NB), K Nearest Neighbors (KNN), Decision Tree (DT), Logistic Regression (LR), and Support Vector Machine (SVM)—on both original and pre-processed images to determine the optimal classifier. Following the selection of the best-performing classifier, i.e., Logistic Regression, we further optimize the classification process by applying combinations of the feature extraction techniques (SIFT + HOG, SIFT + LBP, HOG + LBP, SIFT + HOG + LBP). The SIFT + HOG + LBP feature extraction, in combination with Logistic Regression, performed the best on the original images, obtaining an accuracy of 97.12 %, precision of 97.97 %, recall of 97.55 %, and F1-score of 97.76 %. Our study presents the comparative performance of each preprocessing and feature extraction technique, both individually and in combination, in bringing about an improvement in the accuracy of lung disease detection. The study concludes with the identification of the most effective preprocessing and feature extraction combination, coupled with the best machine learning classifier, providing a robust framework for enhanced lung disease diagnosis.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"29 ","pages":"Article 100596"},"PeriodicalIF":5.0,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143175669","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}