Pub Date : 2024-08-08DOI: 10.3991/ijoe.v20i11.48029
Muhammad Daffa Khairi, Bedy Purnama, Imamura Kosuke, Miki Abo
In this study, we analyze mucociliary transport (MCT) by measuring the magnitude and identifying regions of ciliary beats using high-frame-rate microscopic videos. Our methodology, integrating dense optical flow (DOF), connected component labeling (CCL), Butterworth filter, and Fast Fourier Transform (FFT), captures ciliary movement and magnitude. We focus on region extraction, quantification of ciliary activity, and classification of power and recovery strokes in ciliary beat frequency (CBF), which are crucial for evaluating MCT efficiency. Our approach was able to extract the ciliary region semi-automatically, obtain the CBF, and visualize the ciliary movement in each frame. Despite dataset challenges and limited ground truth, our approach shows a promising result for ciliary dynamics research and medical diagnostics. We hope for future open-source datasets with ground-truth ciliary beat patterns to enable developing and evaluating automated ciliary analysis techniques, leading to improved assessment.
{"title":"Estimate the Region of Interest, Movement and Magnitude of Ciliary Beat with Dense Optical Flow","authors":"Muhammad Daffa Khairi, Bedy Purnama, Imamura Kosuke, Miki Abo","doi":"10.3991/ijoe.v20i11.48029","DOIUrl":"https://doi.org/10.3991/ijoe.v20i11.48029","url":null,"abstract":"\u0000\u0000\u0000In this study, we analyze mucociliary transport (MCT) by measuring the magnitude and identifying regions of ciliary beats using high-frame-rate microscopic videos. Our methodology, integrating dense optical flow (DOF), connected component labeling (CCL), Butterworth filter, and Fast Fourier Transform (FFT), captures ciliary movement and magnitude. We focus on region extraction, quantification of ciliary activity, and classification of power and recovery strokes in ciliary beat frequency (CBF), which are crucial for evaluating MCT efficiency. Our approach was able to extract the ciliary region semi-automatically, obtain the CBF, and visualize the ciliary movement in each frame. Despite dataset challenges and limited ground truth, our approach shows a promising result for ciliary dynamics research and medical diagnostics. We hope for future open-source datasets with ground-truth ciliary beat patterns to enable developing and evaluating automated ciliary analysis techniques, leading to improved assessment. \u0000\u0000\u0000","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"34 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928320","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}
Pub Date : 2024-08-08DOI: 10.3991/ijoe.v20i11.50277
A. Y. Al-Zoubi, Mamoun Aldmour, Afif Khoury, Dana Al-Thaher
The design of a smart water monitoring and control system in urban areas plays a pivotal role in providing efficient distribution mechanisms to reduce leakage, especially in regions facing water scarcity and limited resources. The convergence of the Internet of Things (IoT) and blockchain technology to improve the system’s performance, enhance its security, and provide a decentralized and tamper-proof environment presents an excellent opportunity to evolve the system further and form a state-of-the-art Water 4.0 ecosystem. The proposed Blockchain of Things (BCoT) water system is introduced as a pilot to explore its potential in delivering and managing Water 4.0 applications. An Ethereum platform formed the heart of the BCoT system, while a Raspberry Pi 4 acted as a node to the blockchain that collected data from various sensors and microcontrollers via MQTT programmed by Node-Red. LabVIEW software also provided supervisory control and data acquisition (SCADA). The BCoT system was tested, and its functionality was verified, showing good promise to take smart water systems to a new level of innovation that may resolve the many challenges faced by countries with limited water resources and address the challenges of the 21st-century “Water 4.0” ecosystem.
{"title":"Blockchain of Things for Securing and Managing Water 4.0 Applications","authors":"A. Y. Al-Zoubi, Mamoun Aldmour, Afif Khoury, Dana Al-Thaher","doi":"10.3991/ijoe.v20i11.50277","DOIUrl":"https://doi.org/10.3991/ijoe.v20i11.50277","url":null,"abstract":"The design of a smart water monitoring and control system in urban areas plays a pivotal role in providing efficient distribution mechanisms to reduce leakage, especially in regions facing water scarcity and limited resources. The convergence of the Internet of Things (IoT) and blockchain technology to improve the system’s performance, enhance its security, and provide a decentralized and tamper-proof environment presents an excellent opportunity to evolve the system further and form a state-of-the-art Water 4.0 ecosystem. The proposed Blockchain of Things (BCoT) water system is introduced as a pilot to explore its potential in delivering and managing Water 4.0 applications. An Ethereum platform formed the heart of the BCoT system, while a Raspberry Pi 4 acted as a node to the blockchain that collected data from various sensors and microcontrollers via MQTT programmed by Node-Red. LabVIEW software also provided supervisory control and data acquisition (SCADA). The BCoT system was tested, and its functionality was verified, showing good promise to take smart water systems to a new level of innovation that may resolve the many challenges faced by countries with limited water resources and address the challenges of the 21st-century “Water 4.0” ecosystem.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"7 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141927461","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}
Pub Date : 2024-08-08DOI: 10.3991/ijoe.v20i11.49893
Ahmed Abatal, Mourad Mzili, Toufik Mzili, Khaoula Cherrat, Asmae Yassine, L. Abualigah
This paper introduces the intelligent interconnected healthcare system (IIHS), an innovative fusion of the Internet of Things (IoT) and big data analytics technologies designed to revolutionize proactive and personalized healthcare. IIHS facilitates the integration of real-time data from various devices, ambient sensors, and hospital equipment, creating a continuous stream of comprehensive healthcare data. Leveraging advanced data analysis, IIHS offers actionable insights for ongoing patient health monitoring, trend prediction through machine learning, and rapid information access via a user-friendly interface. The system architecture features a combination of centralized cloud storage and edge storage at healthcare facilities, enhancing both efficiency and security in data management. The effectiveness of IIHS has been demonstrated in two healthcare facilities, which reported significant reductions in patient length of stay and readmission rates. This indicates the system’s potential to improve patient care while seamlessly integrating with existing healthcare infrastructures. IIHS represents the future of digital and personalized medicine, offering a scalable, patient-centric solution that supports the ongoing transformation towards data-driven healthcare.
{"title":"Intelligent Interconnected Healthcare System: Integrating IoT and Big Data for Personalized Patient Care","authors":"Ahmed Abatal, Mourad Mzili, Toufik Mzili, Khaoula Cherrat, Asmae Yassine, L. Abualigah","doi":"10.3991/ijoe.v20i11.49893","DOIUrl":"https://doi.org/10.3991/ijoe.v20i11.49893","url":null,"abstract":"This paper introduces the intelligent interconnected healthcare system (IIHS), an innovative fusion of the Internet of Things (IoT) and big data analytics technologies designed to revolutionize proactive and personalized healthcare. IIHS facilitates the integration of real-time data from various devices, ambient sensors, and hospital equipment, creating a continuous stream of comprehensive healthcare data. Leveraging advanced data analysis, IIHS offers actionable insights for ongoing patient health monitoring, trend prediction through machine learning, and rapid information access via a user-friendly interface. The system architecture features a combination of centralized cloud storage and edge storage at healthcare facilities, enhancing both efficiency and security in data management. The effectiveness of IIHS has been demonstrated in two healthcare facilities, which reported significant reductions in patient length of stay and readmission rates. This indicates the system’s potential to improve patient care while seamlessly integrating with existing healthcare infrastructures. IIHS represents the future of digital and personalized medicine, offering a scalable, patient-centric solution that supports the ongoing transformation towards data-driven healthcare.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"1 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141927584","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}
Pub Date : 2024-08-08DOI: 10.3991/ijoe.v20i11.49165
Asha V, Bhavanishankar K
The novel approach uses the V-Net architecture to segment pulmonary nodules from computed tomography (CT) scans, enhancing lung cancer detection’s efficiency. Addressing lung cancer, a major global mortality cause, underscores the urgency for improved diagnostic methods. The aim of this research is to refine segmentation, a critical step for early cancer detection. The study leverages V-Net, a three-dimensional (3D) convolutional neural network (CNN) tailored for medical image segmentation, applied to lung nodule identification. It utilizes the LUNA16 dataset, containing 888 annotated CT images, for model training and evaluation. This dataset’s variety of pulmonary conditions allows for a comprehensive method of assessment. The tailored V-Net architecture is optimized for lung nodule segmentation, with a focus on data preprocessing to elevate input image quality. Outcomes reveal significant progress in segmentation precision, achieving a loss score of 0.001 and a mIOU of 98%, setting new standards in the domain. Visuals of segmented lung nodules illustrate the method’s effectiveness, indicating a promising avenue for early lung cancer detection and potentially better patient prognoses. The study contributes significantly to enhancing lung cancer diagnostic methodologies through advanced image analysis. An improved segmentation method based on V-Net architecture surpasses current techniques and encourages further deep learning exploration in medical diagnostics.
{"title":"Towards Efficient Lung Cancer Detection: V-Net-based Segmentation of Pulmonary Nodules","authors":"Asha V, Bhavanishankar K","doi":"10.3991/ijoe.v20i11.49165","DOIUrl":"https://doi.org/10.3991/ijoe.v20i11.49165","url":null,"abstract":"The novel approach uses the V-Net architecture to segment pulmonary nodules from computed tomography (CT) scans, enhancing lung cancer detection’s efficiency. Addressing lung cancer, a major global mortality cause, underscores the urgency for improved diagnostic methods. The aim of this research is to refine segmentation, a critical step for early cancer detection. The study leverages V-Net, a three-dimensional (3D) convolutional neural network (CNN) tailored for medical image segmentation, applied to lung nodule identification. It utilizes the LUNA16 dataset, containing 888 annotated CT images, for model training and evaluation. This dataset’s variety of pulmonary conditions allows for a comprehensive method of assessment. The tailored V-Net architecture is optimized for lung nodule segmentation, with a focus on data preprocessing to elevate input image quality. Outcomes reveal significant progress in segmentation precision, achieving a loss score of 0.001 and a mIOU of 98%, setting new standards in the domain. Visuals of segmented lung nodules illustrate the method’s effectiveness, indicating a promising avenue for early lung cancer detection and potentially better patient prognoses. The study contributes significantly to enhancing lung cancer diagnostic methodologies through advanced image analysis. An improved segmentation method based on V-Net architecture surpasses current techniques and encourages further deep learning exploration in medical diagnostics.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"4 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928965","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}
Pub Date : 2024-08-08DOI: 10.3991/ijoe.v20i11.49139
M. Cabanillas-Carbonell, Joselyn Zapata-Paulini
Cancer ranks among the most lethal illnesses worldwide, and predicting its onset can be a crucial factor in enhancing people’s quality of life by taking preventive measures to improve treatment and survival. This study conducted comparative research to determine the machine learning model with the highest accuracy for tumor type classification, distinguishing between malignant (cancer) and benign tumors. The models evaluated include decision tree (DT), naive bayes (NB), extra trees classifier (ETM), random forest (RF), K-means clustering (K-means), logistic regression (LR), adaptive boosting (AdaBoost), gradient boosting (GB), light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost) to identify the one with the best accuracy. The models were trained using a dataset of 569 records and a total of 32 variables, containing patient information and tumor characteristics. The study was structured into sections, such as related studies, descriptions of the models, case study development, results, discussion, and conclusions. The models’ performance was evaluated based on metrics of precision, sensitivity, accuracy, and F1 score. Following the training, the results positioned the XGBoost model as having the best performance, achieving 98% precision, accuracy, sensitivity, and F1 score.
癌症是全球致死率最高的疾病之一，而预测癌症的发病可以通过采取预防措施提高治疗和生存率，从而成为提高人们生活质量的关键因素。本研究进行了比较研究，以确定在肿瘤类型分类（区分恶性肿瘤（癌症）和良性肿瘤）方面准确率最高的机器学习模型。评估的模型包括决策树（DT）、奈夫贝叶斯（NB）、额外树分类器（ETM）、随机森林（RF）、K-means 聚类（K-means）、逻辑回归（LR）、自适应提升（AdaBoost）、梯度提升（GB）、轻梯度提升机（LightGBM）和极端梯度提升（XGBoost），以找出准确率最高的模型。模型的训练使用了一个包含 569 条记录和总共 32 个变量的数据集，其中包含患者信息和肿瘤特征。本研究分为相关研究、模型描述、案例研究开发、结果、讨论和结论等部分。根据精确度、灵敏度、准确度和 F1 分数等指标对模型的性能进行了评估。训练结束后，结果表明 XGBoost 模型性能最佳，精确度、准确度、灵敏度和 F1 分数均达到 98%。
{"title":"Improving the Accuracy of Oncology Diagnosis: A Machine Learning-Based Approach to Cancer Prediction","authors":"M. Cabanillas-Carbonell, Joselyn Zapata-Paulini","doi":"10.3991/ijoe.v20i11.49139","DOIUrl":"https://doi.org/10.3991/ijoe.v20i11.49139","url":null,"abstract":"Cancer ranks among the most lethal illnesses worldwide, and predicting its onset can be a crucial factor in enhancing people’s quality of life by taking preventive measures to improve treatment and survival. This study conducted comparative research to determine the machine learning model with the highest accuracy for tumor type classification, distinguishing between malignant (cancer) and benign tumors. The models evaluated include decision tree (DT), naive bayes (NB), extra trees classifier (ETM), random forest (RF), K-means clustering (K-means), logistic regression (LR), adaptive boosting (AdaBoost), gradient boosting (GB), light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost) to identify the one with the best accuracy. The models were trained using a dataset of 569 records and a total of 32 variables, containing patient information and tumor characteristics. The study was structured into sections, such as related studies, descriptions of the models, case study development, results, discussion, and conclusions. The models’ performance was evaluated based on metrics of precision, sensitivity, accuracy, and F1 score. Following the training, the results positioned the XGBoost model as having the best performance, achieving 98% precision, accuracy, sensitivity, and F1 score.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"75 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141926687","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}
Pub Date : 2024-08-08DOI: 10.3991/ijoe.v20i11.49949
Ahmed Almaghthawi, Ebrahim A. A. Ghaleb, Nur Arifin Akbar, Layla Asiri, Meaad Alrehaili, Askar Altalidi
This study presents the implementation of a blockchain-based federated-learning (FL) intrusion detection system. This approach utilizes machine learning (ML) instead of traditional signature-based methods, enabling the system to detect new attack types. The FL technique ensures the privacy of sensitive data while still utilizing the large amounts of data distributed across client devices. To achieve this, we employed the federated averaging method and incorporated a custom preprocessing stage for data standardization. The use of blockchain technology in combination with FL created a fully decentralized and open learning system capable of overcoming new security challenges.
{"title":"Federated-Learning Intrusion Detection System Based Blockchain Technology","authors":"Ahmed Almaghthawi, Ebrahim A. A. Ghaleb, Nur Arifin Akbar, Layla Asiri, Meaad Alrehaili, Askar Altalidi","doi":"10.3991/ijoe.v20i11.49949","DOIUrl":"https://doi.org/10.3991/ijoe.v20i11.49949","url":null,"abstract":"This study presents the implementation of a blockchain-based federated-learning (FL) intrusion detection system. This approach utilizes machine learning (ML) instead of traditional signature-based methods, enabling the system to detect new attack types. The FL technique ensures the privacy of sensitive data while still utilizing the large amounts of data distributed across client devices. To achieve this, we employed the federated averaging method and incorporated a custom preprocessing stage for data standardization. The use of blockchain technology in combination with FL created a fully decentralized and open learning system capable of overcoming new security challenges.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"41 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141929286","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}
Pub Date : 2024-08-08DOI: 10.3991/ijoe.v20i11.49673
Muhyeeddin Alqaraleh, M. Alzboon, M. Al-Batah, Mutaz Abdel Wahed, Ahmad Abuashour, Firas Hussein Alsmadi
In this study, we evaluated the performance of various machine-learning models on multiple datasets labeled GR1, GR2, GR3, GR4, and GR5. We assessed the models using a range of evaluation metrics, including AUC, CA, F1, precision, recall, MCC, specificity, and log loss. The models examined were logistic regression, decision tree, kNN, random forest, gradient boosting, neural network, AdaBoost, and stochastic gradient descent. The results indicate that all models consistently demonstrated outstanding performance across all datasets, with most achieving perfect scores in all metrics. The models exhibited high accuracy and effectiveness in accurately classifying instances. Although random forests displayed slightly lower scores in some metrics, theyi still maintained an overall high level of accuracy. The findings highlight the models’ ability to effectively learn the underlying patterns within the data and make accurate predictions. The low log loss values further confirmed the models’ precise estimation of probabilities. Consequently, these models possess strong potential for practical applications in various domains, offering reliable and robust classification capabilities.
{"title":"Harnessing Machine Learning for Quantifying Vesicoureteral Reflux: A Promising Approach for Objective Assessment","authors":"Muhyeeddin Alqaraleh, M. Alzboon, M. Al-Batah, Mutaz Abdel Wahed, Ahmad Abuashour, Firas Hussein Alsmadi","doi":"10.3991/ijoe.v20i11.49673","DOIUrl":"https://doi.org/10.3991/ijoe.v20i11.49673","url":null,"abstract":"In this study, we evaluated the performance of various machine-learning models on multiple datasets labeled GR1, GR2, GR3, GR4, and GR5. We assessed the models using a range of evaluation metrics, including AUC, CA, F1, precision, recall, MCC, specificity, and log loss. The models examined were logistic regression, decision tree, kNN, random forest, gradient boosting, neural network, AdaBoost, and stochastic gradient descent. The results indicate that all models consistently demonstrated outstanding performance across all datasets, with most achieving perfect scores in all metrics. The models exhibited high accuracy and effectiveness in accurately classifying instances. Although random forests displayed slightly lower scores in some metrics, theyi still maintained an overall high level of accuracy. The findings highlight the models’ ability to effectively learn the underlying patterns within the data and make accurate predictions. The low log loss values further confirmed the models’ precise estimation of probabilities. Consequently, these models possess strong potential for practical applications in various domains, offering reliable and robust classification capabilities.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"52 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928034","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}
Pub Date : 2024-08-08DOI: 10.3991/ijoe.v20i11.49533
Mustafa Al-Fayoumi, Bushra Alhijawi, Q. Abu Al-haija, Rakan Armoush
The rapid growth of the Internet has led to an increased demand for online services. However, this surge in online activity has also brought about a new threat: phishing attacks. Phishing is a type of cyberattack that utilizes social engineering techniques and technological manipulations to steal crucial information from unsuspecting individuals. Consequently, there is a rising necessity to create dependable phishing URL detection models that can effectively identify phishing URLs with enhanced accuracy and reduced prediction overhead. This study introduces XAI-PhD, an innovative phishing detection method that utilizes machine learning (ML) and Shapley additive explanation (SHAP) capabilities. Specifically, XAI-PhD utilizes SHAP to thoroughly analyze the significance of each feature in influencing the decision-making process of the classifier. By selectively incorporating input characteristics based on their SHAP values, only the most crucial attributes are assessed, enabling the development of a highly adaptable and generalized model. XAI-PhD utilizes a lightweight gradient boosting machine as its classifier, and a series of rigorous tests are conducted to assess its performance compared to established baseline methods. The empirical findings unequivocally demonstrate the exceptional effectiveness of XAI-PhD, as evidenced by its remarkable accuracy and F1-score of 99.8% and 99%, respectively. Moreover, XAI-PhD exhibits high computational efficiency, requiring only 1.47 milliseconds and 18.5 microseconds per record to generate accurate predictions.
{"title":"XAI-PhD: Fortifying Trust of Phishing URL Detection Empowered by Shapley Additive Explanations","authors":"Mustafa Al-Fayoumi, Bushra Alhijawi, Q. Abu Al-haija, Rakan Armoush","doi":"10.3991/ijoe.v20i11.49533","DOIUrl":"https://doi.org/10.3991/ijoe.v20i11.49533","url":null,"abstract":"The rapid growth of the Internet has led to an increased demand for online services. However, this surge in online activity has also brought about a new threat: phishing attacks. Phishing is a type of cyberattack that utilizes social engineering techniques and technological manipulations to steal crucial information from unsuspecting individuals. Consequently, there is a rising necessity to create dependable phishing URL detection models that can effectively identify phishing URLs with enhanced accuracy and reduced prediction overhead. This study introduces XAI-PhD, an innovative phishing detection method that utilizes machine learning (ML) and Shapley additive explanation (SHAP) capabilities. Specifically, XAI-PhD utilizes SHAP to thoroughly analyze the significance of each feature in influencing the decision-making process of the classifier. By selectively incorporating input characteristics based on their SHAP values, only the most crucial attributes are assessed, enabling the development of a highly adaptable and generalized model. XAI-PhD utilizes a lightweight gradient boosting machine as its classifier, and a series of rigorous tests are conducted to assess its performance compared to established baseline methods. The empirical findings unequivocally demonstrate the exceptional effectiveness of XAI-PhD, as evidenced by its remarkable accuracy and F1-score of 99.8% and 99%, respectively. Moreover, XAI-PhD exhibits high computational efficiency, requiring only 1.47 milliseconds and 18.5 microseconds per record to generate accurate predictions.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"30 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141925978","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}
Pub Date : 2024-08-08DOI: 10.3991/ijoe.v20i11.49503
P. Anagnostopoulou, Athanasios Drigas
The following review examines the use of social robots in mindfulness practices, with a focus on their application in preschool settings. Additionally, it explores the key attributes of social robots that could enhance their effectiveness in achieving targeted outcomes. This study is the initial phase of a project that aims to investigate the advantages of technology and mindfulness in kindergarten. The selection of this age group is based on its significance in the comprehensive development of children, despite the lack of extensive study on mindfulness in this specific context. The objective of this paper is to present existing research on social robots and mindfulness, assess the potential benefits and challenges of integrating these two fields in kindergarten, and, most importantly, inspire future studies on the use of robots and mindfulness in early childhood education. A bibliographic review of articles was conducted. The findings of our study suggest that the use of robots and human-robot interactions can enhance self-development, well-being, and mindfulness. Robots have the capacity to capture attention and motivate young children, specifically. Both humanoid and non-humanoid robots seem suitable for facilitating mental well-being exercises. However, a well-designed social robot for children should incorporate both human-like and mechanical features. Our primary aim is to encourage further study on the integration of robots and mindfulness in preschool education, as there is still a vast unexplored territory in this rapidly advancing field.
{"title":"Social Robots, Mindfulness, and Kindergarten","authors":"P. Anagnostopoulou, Athanasios Drigas","doi":"10.3991/ijoe.v20i11.49503","DOIUrl":"https://doi.org/10.3991/ijoe.v20i11.49503","url":null,"abstract":"The following review examines the use of social robots in mindfulness practices, with a focus on their application in preschool settings. Additionally, it explores the key attributes of social robots that could enhance their effectiveness in achieving targeted outcomes. This study is the initial phase of a project that aims to investigate the advantages of technology and mindfulness in kindergarten. The selection of this age group is based on its significance in the comprehensive development of children, despite the lack of extensive study on mindfulness in this specific context. The objective of this paper is to present existing research on social robots and mindfulness, assess the potential benefits and challenges of integrating these two fields in kindergarten, and, most importantly, inspire future studies on the use of robots and mindfulness in early childhood education. A bibliographic review of articles was conducted. The findings of our study suggest that the use of robots and human-robot interactions can enhance self-development, well-being, and mindfulness. Robots have the capacity to capture attention and motivate young children, specifically. Both humanoid and non-humanoid robots seem suitable for facilitating mental well-being exercises. However, a well-designed social robot for children should incorporate both human-like and mechanical features. Our primary aim is to encourage further study on the integration of robots and mindfulness in preschool education, as there is still a vast unexplored territory in this rapidly advancing field.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"102 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141926724","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}
Pub Date : 2024-07-16DOI: 10.3991/ijoe.v20i10.49509
Archana Kalidindi, Mahesh Babu Arrama
The Internet of Things (IoT) is growing rapidly in an exponential manner due to its versatility in technology. This has led to many challenges in securing the IoT environment. Devices in IoT environments are vulnerable to various cyberattacks. Botnet-based attacks are predominant and widespread in nature. Due to insufficient memory and computational power, the IoT environment cannot handle the botnet attack that affects security. Identifying intrusions in IoT environments is another challenge for researchers. Finding unknown patterns in the data generated through IoT networks helps improve security in the IoT environment. Machine learning (ML) is a platform that helps identify patterns in the provided data. In this study, we present our research on classifying incoming data from the IoT as malicious or benign using machine learning techniques. We propose an ML-based botnet attack detection framework for nine commercial IoT devices that primarily target BASHLITE and Mirai botnet attacks. Rigorous pragmatic research was conducted on the N-BaIoT dataset, which was extracted from realtime IoT devices connected to a network. Using this framework, the results have been depicted, which can efficiently detect botnet attacks and can also be applied to any other types of attacks.
由于技术的多样性，物联网（IoT）正以指数级的方式迅速发展。这给物联网环境的安全带来了许多挑战。物联网环境中的设备容易受到各种网络攻击。基于僵尸网络的攻击在本质上占主导地位，而且非常普遍。由于内存和计算能力不足，物联网环境无法应对影响安全的僵尸网络攻击。识别物联网环境中的入侵是研究人员面临的另一个挑战。在物联网网络生成的数据中寻找未知模式有助于提高物联网环境的安全性。机器学习（ML）是一个有助于从所提供的数据中识别模式的平台。在本研究中，我们介绍了利用机器学习技术将来自物联网的传入数据分类为恶意或良性数据的研究。我们为九种商用物联网设备提出了基于 ML 的僵尸网络攻击检测框架，这些设备主要针对 BASHLITE 和 Mirai 僵尸网络攻击。我们在 N-BaIoT 数据集上进行了严格务实的研究，该数据集是从连接到网络的实时物联网设备中提取的。使用该框架描绘的结果可以有效地检测僵尸网络攻击，也可应用于任何其他类型的攻击。
{"title":"A Systematic Investigation on Botnet Intrusion Detection Using Various Machine Learning Techniques","authors":"Archana Kalidindi, Mahesh Babu Arrama","doi":"10.3991/ijoe.v20i10.49509","DOIUrl":"https://doi.org/10.3991/ijoe.v20i10.49509","url":null,"abstract":"The Internet of Things (IoT) is growing rapidly in an exponential manner due to its versatility in technology. This has led to many challenges in securing the IoT environment. Devices in IoT environments are vulnerable to various cyberattacks. Botnet-based attacks are predominant and widespread in nature. Due to insufficient memory and computational power, the IoT environment cannot handle the botnet attack that affects security. Identifying intrusions in IoT environments is another challenge for researchers. Finding unknown patterns in the data generated through IoT networks helps improve security in the IoT environment. Machine learning (ML) is a platform that helps identify patterns in the provided data. In this study, we present our research on classifying incoming data from the IoT as malicious or benign using machine learning techniques. We propose an ML-based botnet attack detection framework for nine commercial IoT devices that primarily target BASHLITE and Mirai botnet attacks. Rigorous pragmatic research was conducted on the N-BaIoT dataset, which was extracted from realtime IoT devices connected to a network. Using this framework, the results have been depicted, which can efficiently detect botnet attacks and can also be applied to any other types of attacks.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"3 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141640655","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：