Pub Date : 2023-08-31DOI: 10.3991/ijoe.v19i12.40905
Setiawati, Asrul Huda, Ismaniar, Noper Ardi
The aim of this research is to address the issue of low prosocial behavior in children, both at home and in public spaces. This was identified through observations and interviews with parents, who believe that the lack of their participation in their children’s prosocial development is due to their limited understanding. To improve early childhood prosocial behavior, the research team developed an Android-based E-Module that is practical and user-friendly, as well as accessible to a wider audience. This type of research is referred to as development research. The study’s objective is to design an Android-based E-Module application that can improve early childhood prosocial behavior within families. The ADDIE Model development method was utilized, with a survey conducted to assess the application’s validity, which was further validated by multiple experts. The results showed that the Android-based E-Module application’s validation test was deemed valid, and can be concluded that it is a useful tool to enhance early childhood prosocial behavior within families, specifically in the city of Padang.
{"title":"Design and Development of Android-Based E-Modul Application to Improve Prosocial Early Children by Family","authors":"Setiawati, Asrul Huda, Ismaniar, Noper Ardi","doi":"10.3991/ijoe.v19i12.40905","DOIUrl":"https://doi.org/10.3991/ijoe.v19i12.40905","url":null,"abstract":"The aim of this research is to address the issue of low prosocial behavior in children, both at home and in public spaces. This was identified through observations and interviews with parents, who believe that the lack of their participation in their children’s prosocial development is due to their limited understanding. To improve early childhood prosocial behavior, the research team developed an Android-based E-Module that is practical and user-friendly, as well as accessible to a wider audience. This type of research is referred to as development research. The study’s objective is to design an Android-based E-Module application that can improve early childhood prosocial behavior within families. The ADDIE Model development method was utilized, with a survey conducted to assess the application’s validity, which was further validated by multiple experts. The results showed that the Android-based E-Module application’s validation test was deemed valid, and can be concluded that it is a useful tool to enhance early childhood prosocial behavior within families, specifically in the city of Padang.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42256887","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 : 2023-08-31DOI: 10.3991/ijoe.v19i12.40079
Martín Díaz-Choque, Omar Chamorro-Atalaya, O. Ortega-Galicio, J. Arévalo-Tuesta, Elvira Cáceres-Cayllahua, Ronald Fernando Dávila-Laguna, Irma Aybar-Bellido, Yina Betty Siguas-Jerónimo
During the context of COVID-19, educational processes migrated to a strictly virtual scenario, so the quantity of information grew in such a way that techniques such as data mining or machine learning contributed to generating knowledge for decision-making. In this sense, it is relevant to define the state of the art of the contributions of data mining in the university environment, and from there, to see in perspective how these could be applied in scenarios of return to the face-to-face. In this sense, a systematic review of the literature is carried out, based on scientific evidence extracted from the Taylor & Francis, ERIC and Scopus databases. A qualitative content analysis approach and the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) statement were used to extract the findings published in scientific articles. The results were that educational data mining was applied to a greater extent in the field of “teaching”, and it was focused on the search for patterns and predictive models to improve student performance, reduce student dropout, improve the student’s quality of life, and teacher performance. In addition, as a resource for data extraction, university learning management systems (LMS) were used to a greater extent. It is concluded that tools such as data mining should be implemented as academic management policies, achieving a prospective on indicators linked to the improvement of student learning and performance.
{"title":"Contributions of Data Mining to University Education, in the Context of the Covid-19 Pandemic: A Systematic Review of the Literature","authors":"Martín Díaz-Choque, Omar Chamorro-Atalaya, O. Ortega-Galicio, J. Arévalo-Tuesta, Elvira Cáceres-Cayllahua, Ronald Fernando Dávila-Laguna, Irma Aybar-Bellido, Yina Betty Siguas-Jerónimo","doi":"10.3991/ijoe.v19i12.40079","DOIUrl":"https://doi.org/10.3991/ijoe.v19i12.40079","url":null,"abstract":"During the context of COVID-19, educational processes migrated to a strictly virtual scenario, so the quantity of information grew in such a way that techniques such as data mining or machine learning contributed to generating knowledge for decision-making. In this sense, it is relevant to define the state of the art of the contributions of data mining in the university environment, and from there, to see in perspective how these could be applied in scenarios of return to the face-to-face. In this sense, a systematic review of the literature is carried out, based on scientific evidence extracted from the Taylor & Francis, ERIC and Scopus databases. A qualitative content analysis approach and the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) statement were used to extract the findings published in scientific articles. The results were that educational data mining was applied to a greater extent in the field of “teaching”, and it was focused on the search for patterns and predictive models to improve student performance, reduce student dropout, improve the student’s quality of life, and teacher performance. In addition, as a resource for data extraction, university learning management systems (LMS) were used to a greater extent. It is concluded that tools such as data mining should be implemented as academic management policies, achieving a prospective on indicators linked to the improvement of student learning and performance.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45082148","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 : 2023-08-31DOI: 10.3991/ijoe.v19i12.41181
Zakaria Bousalem, Aimad Qazdar, Inssaf El Guabassi
Cooperative learning is a pedagogical approach in which students collaborate in small groups to attain a shared academic objective. In the classroom, cooperative learning aims to enhance learning outcomes by promoting the exchange of information, social, and personal resources among students. Group formation is a critical and complex step that significantly impacts the effectiveness of cooperative learning. In this article, we propose a novel approach for constructing cooperative learning groups that employs machine learning to predict student performance and incorporates the most common grouping strategies to recommend optimal group formation.
{"title":"Cooperative Learning Groups: A New Approach Based on Students’ Performance Prediction","authors":"Zakaria Bousalem, Aimad Qazdar, Inssaf El Guabassi","doi":"10.3991/ijoe.v19i12.41181","DOIUrl":"https://doi.org/10.3991/ijoe.v19i12.41181","url":null,"abstract":"Cooperative learning is a pedagogical approach in which students collaborate in small groups to attain a shared academic objective. In the classroom, cooperative learning aims to enhance learning outcomes by promoting the exchange of information, social, and personal resources among students. Group formation is a critical and complex step that significantly impacts the effectiveness of cooperative learning. In this article, we propose a novel approach for constructing cooperative learning groups that employs machine learning to predict student performance and incorporates the most common grouping strategies to recommend optimal group formation.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41921415","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 : 2023-08-31DOI: 10.3991/ijoe.v19i12.40471
Fatima Barkani, Mohamed Hamidi, Ouissam Zealouk, H. Satori
This paper introduces an innovative technique for creating a cough detection system that relies on speech recognition algorithms. The strategy utilizes the Kaldi platform, which is open source and incorporates a hybrid system of Gaussian Mixture Model-based Hidden Markov Models (GMM-HMM) through a straightforward monophone training model. Additionally, the study examines the effectiveness of two different feature extraction approaches, Mel Frequency Cepstral Coefficient (MFCC) and Perceptual Linear Prediction (PLP). The proposed system can function as a collection tool for gathering natural and spontaneous cough data from conversations or continuous speech. The paper also compares the Kaldi and CMU Sphinx4 toolkits, concluding that Kaldi’s use of GMM-HMM outperforms CMU Sphinx4.
{"title":"Speech Recognition Algorithms based Cough Recognition System","authors":"Fatima Barkani, Mohamed Hamidi, Ouissam Zealouk, H. Satori","doi":"10.3991/ijoe.v19i12.40471","DOIUrl":"https://doi.org/10.3991/ijoe.v19i12.40471","url":null,"abstract":"This paper introduces an innovative technique for creating a cough detection system that relies on speech recognition algorithms. The strategy utilizes the Kaldi platform, which is open source and incorporates a hybrid system of Gaussian Mixture Model-based Hidden Markov Models (GMM-HMM) through a straightforward monophone training model. Additionally, the study examines the effectiveness of two different feature extraction approaches, Mel Frequency Cepstral Coefficient (MFCC) and Perceptual Linear Prediction (PLP). The proposed system can function as a collection tool for gathering natural and spontaneous cough data from conversations or continuous speech. The paper also compares the Kaldi and CMU Sphinx4 toolkits, concluding that Kaldi’s use of GMM-HMM outperforms CMU Sphinx4.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49629022","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}
RSUD Mohammad Natsir Solok, located in Solok City, provides comprehensive individual health services within its premises, offering both inpatient and outpatient care with 24-hour service availability. Inpatient services encompass emergency care and basic health services. A crucial component of healthcare operations is medical records, which consist of documented information pertaining to patient identity, examinations, treatments, procedures, and other services rendered. Medical records are essential and should be meticulously created in written or electronic form to ensure completeness and clarity. One common challenge encountered in maintaining medical records is the presence of overlapping data. To tackle this issue, data mining techniques are employed, with clustering being the primary method of choice. The K-Means algorithm is specifically utilized for clusterization purposes. By applying this data mining process and grouping patient medical records, valuable insights into the patterns of disease spread across different villages can be obtained. After applying K-Means clustering method, four distinct clusters were identified. The first cluster comprises 562 items, the second has 406 items, and the third and fourth have 791 and 279 items, respectively. These findings can serve as a reference for the local government, particularly the Solok City Health Office, to facilitate disease prevention initiatives and awareness campaigns. Decision-making related to disease sources, diagnosis, age, and gender of the affected patient can be informed by this data analysis.
RSUD Mohammad Natsir Solok位于Solok市，在其经营场所内提供全面的个人健康服务，提供24小时服务的住院和门诊护理。住院服务包括急救和基本保健服务。医疗保健操作的一个关键组成部分是医疗记录，它由与患者身份、检查、治疗、程序和提供的其他服务有关的记录信息组成。医疗记录是必不可少的，应该以书面或电子形式精心创建，以确保完整性和清晰度。在维护医疗记录时遇到的一个常见挑战是存在重叠的数据。为了解决这个问题，采用了数据挖掘技术，聚类是主要的选择方法。K-Means算法专门用于聚类目的。通过应用这一数据挖掘过程并对患者医疗记录进行分组，可以获得对疾病在不同村庄传播模式的有价值的见解。应用K-Means聚类方法，识别出四个不同的聚类。第一集群包括562个项目，第二集群有406个项目，而第三集群和第四集群分别有791个和279个项目。这些发现可以作为地方政府，特别是索洛克市卫生办公室的参考，以促进疾病预防举措和宣传运动。与疾病来源、诊断、年龄和受影响患者性别相关的决策可以通过该数据分析得到信息。
{"title":"Optimizing Patient Medical Records Grouping through Data Mining and K-Means Clustering Algorithm: A Case Study at RSUD Mohammad Natsir Solok","authors":"Dony Novaliendry, Tegar Wibowo, Noper Ardi, Tiolina Evi, Dwi Admojo","doi":"10.3991/ijoe.v19i12.42147","DOIUrl":"https://doi.org/10.3991/ijoe.v19i12.42147","url":null,"abstract":"RSUD Mohammad Natsir Solok, located in Solok City, provides comprehensive individual health services within its premises, offering both inpatient and outpatient care with 24-hour service availability. Inpatient services encompass emergency care and basic health services. A crucial component of healthcare operations is medical records, which consist of documented information pertaining to patient identity, examinations, treatments, procedures, and other services rendered. Medical records are essential and should be meticulously created in written or electronic form to ensure completeness and clarity. One common challenge encountered in maintaining medical records is the presence of overlapping data. To tackle this issue, data mining techniques are employed, with clustering being the primary method of choice. The K-Means algorithm is specifically utilized for clusterization purposes. By applying this data mining process and grouping patient medical records, valuable insights into the patterns of disease spread across different villages can be obtained. After applying K-Means clustering method, four distinct clusters were identified. The first cluster comprises 562 items, the second has 406 items, and the third and fourth have 791 and 279 items, respectively. These findings can serve as a reference for the local government, particularly the Solok City Health Office, to facilitate disease prevention initiatives and awareness campaigns. Decision-making related to disease sources, diagnosis, age, and gender of the affected patient can be informed by this data analysis.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44698070","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 : 2023-08-31DOI: 10.3991/ijoe.v19i12.42607
Nadia Ibrahim Nife, Mohammed Chtourou
This paper presents the latest advances in machine learning techniques and highlights deep learning (DL) methods in recent studies. This technology has recently received great attention as it can solve complex problems. This paper focuses on covering one of the deep learning algorithms (deep neural network) and learning about its types such as convolutional neural network (CNN), Recurrent Neural Networks (RNN), etc. We have discussed recent changes, such as advanced DL technologies. Next, we continue analyzing and discussing the challenges and possible solutions of machine learning, such as big data and object detection, studying more papers in deep learning, and knowing the main experiments and future directions. In addition, this review also identifies some successful deep learning applications in recent years. Moreover, in this paper, one of the deep learning methods, convolutional neural networks, is applied to detect objects in images by using the You Only Look One model and comparing it with RetinaNet using pre-trained models. The results found that CNN (using YOLOv3) is a more accurate model than RetinaNet.
本文介绍了机器学习技术的最新进展，并重点介绍了最近研究中的深度学习（DL）方法。这项技术最近受到了极大的关注，因为它可以解决复杂的问题。本文重点介绍了深度学习算法之一（深度神经网络），并了解了其类型，如卷积神经网络（CNN）、递归神经网络（RNN）等。我们讨论了最近的变化，如先进的DL技术。接下来，我们继续分析和讨论机器学习的挑战和可能的解决方案，如大数据和对象检测，研究更多深度学习中的论文，并了解主要实验和未来方向。此外，这篇综述还确定了近年来一些成功的深度学习应用。此外，在本文中，深度学习方法之一卷积神经网络通过使用You Only Look one模型来检测图像中的对象，并使用预先训练的模型将其与RetinaNet进行比较。结果发现，CNN（使用YOLOv3）是一个比RetinaNet更准确的模型。
{"title":"A Comprehensive Study of Deep Learning and Performance Comparison of Deep Neural Network Models (YOLO, RetinaNet)","authors":"Nadia Ibrahim Nife, Mohammed Chtourou","doi":"10.3991/ijoe.v19i12.42607","DOIUrl":"https://doi.org/10.3991/ijoe.v19i12.42607","url":null,"abstract":"This paper presents the latest advances in machine learning techniques and highlights deep learning (DL) methods in recent studies. This technology has recently received great attention as it can solve complex problems. This paper focuses on covering one of the deep learning algorithms (deep neural network) and learning about its types such as convolutional neural network (CNN), Recurrent Neural Networks (RNN), etc. We have discussed recent changes, such as advanced DL technologies. Next, we continue analyzing and discussing the challenges and possible solutions of machine learning, such as big data and object detection, studying more papers in deep learning, and knowing the main experiments and future directions. In addition, this review also identifies some successful deep learning applications in recent years. Moreover, in this paper, one of the deep learning methods, convolutional neural networks, is applied to detect objects in images by using the You Only Look One model and comparing it with RetinaNet using pre-trained models. The results found that CNN (using YOLOv3) is a more accurate model than RetinaNet.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49121078","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 : 2023-08-31DOI: 10.3991/ijoe.v19i12.37625
Angeliki Sideraki, A. Drigas
The combination of virtual reality and fMRI is an innovative methodology that is used to make inferences about the neurological stimulations that take place in the brain of the person with ASD during the use of the VR tool. At the same time, the use of the Brain-Computer Interface (BCI) will be important, as it can be used to achieve direct interaction between the person with ASD and the computer. Still, equally important conclusions can be arrived at through the EEG electroencephalogram, also establishing the neurological processes that are carried out during the use of the VR tool. The use of the two technologies mentioned above contributes to presenting in-depth conclusions and data about the emotional state experienced by children with ASD throughout the experimental process and their interaction with the virtual reality tool.
{"title":"Combination of Virtual Reality (VR) and BCI & fMRI in Autism Spectrum Disorder","authors":"Angeliki Sideraki, A. Drigas","doi":"10.3991/ijoe.v19i12.37625","DOIUrl":"https://doi.org/10.3991/ijoe.v19i12.37625","url":null,"abstract":"The combination of virtual reality and fMRI is an innovative methodology that is used to make inferences about the neurological stimulations that take place in the brain of the person with ASD during the use of the VR tool. At the same time, the use of the Brain-Computer Interface (BCI) will be important, as it can be used to achieve direct interaction between the person with ASD and the computer. Still, equally important conclusions can be arrived at through the EEG electroencephalogram, also establishing the neurological processes that are carried out during the use of the VR tool. The use of the two technologies mentioned above contributes to presenting in-depth conclusions and data about the emotional state experienced by children with ASD throughout the experimental process and their interaction with the virtual reality tool.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47989261","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 : 2023-08-31DOI: 10.3991/ijoe.v19i12.39681
Taoufik Elmissaoui
Remote lab systems are one of the essential requirements for an increased academic productivity in the modern digital world. These systems support and facilitate effective migration from face-to-face classroom education to online education. Digital technology applications and processes are required to easily build a remote lab system. With the availability of multiple access techniques, users can comfortably share laboratory equipment among themselves. The sharing of resources using the remote lab system is highly required for a smooth deployment and implementation of online education. This paper therefore proposed and tested some techniques that combine Code Division Multiple Access (CDMA) and Orthogonal Frequency Division Multiplexing (OFDM) in remote lab systems. The tested techniques are Multi-Carrier Direct Sequence CDMA (MC-DS-CDMA), Multi-Tone CDMA (MT-CDMA), Multi-Carrier CDMA (MC-CDMA), and Spread Spectrum Multi-Carrier Multiple Access (SS-MC-MA). The first step proposed in this work had to do with the setting of the comparison criteria. At the second step, the solutions cited previously in the real equipment was tested and the best option that met the criteria was selected for the eLab system since the performance technique varies with the laboratory equipment characteristic. The four techniques that were tested demonstrated high performance in telecommunications and online laboratory systems. The implementation of these techniques will benefit universities in several ways, which include reduction of remote lab cost and optimization of sharing of online resources among users. This will further provide students with conducive learning environment by addressing the challenges of reservation and time slot limit. It is therefore recommended that MC-CDMA should be integrated into remote lab system.
{"title":"Multi-Access Techniques Comparison for Remote Lab System","authors":"Taoufik Elmissaoui","doi":"10.3991/ijoe.v19i12.39681","DOIUrl":"https://doi.org/10.3991/ijoe.v19i12.39681","url":null,"abstract":"Remote lab systems are one of the essential requirements for an increased academic productivity in the modern digital world. These systems support and facilitate effective migration from face-to-face classroom education to online education. Digital technology applications and processes are required to easily build a remote lab system. With the availability of multiple access techniques, users can comfortably share laboratory equipment among themselves. The sharing of resources using the remote lab system is highly required for a smooth deployment and implementation of online education. This paper therefore proposed and tested some techniques that combine Code Division Multiple Access (CDMA) and Orthogonal Frequency Division Multiplexing (OFDM) in remote lab systems. The tested techniques are Multi-Carrier Direct Sequence CDMA (MC-DS-CDMA), Multi-Tone CDMA (MT-CDMA), Multi-Carrier CDMA (MC-CDMA), and Spread Spectrum Multi-Carrier Multiple Access (SS-MC-MA). The first step proposed in this work had to do with the setting of the comparison criteria. At the second step, the solutions cited previously in the real equipment was tested and the best option that met the criteria was selected for the eLab system since the performance technique varies with the laboratory equipment characteristic. The four techniques that were tested demonstrated high performance in telecommunications and online laboratory systems. The implementation of these techniques will benefit universities in several ways, which include reduction of remote lab cost and optimization of sharing of online resources among users. This will further provide students with conducive learning environment by addressing the challenges of reservation and time slot limit. It is therefore recommended that MC-CDMA should be integrated into remote lab system.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43854620","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 : 2023-08-31DOI: 10.3991/ijoe.v19i12.41631
Z. Oleiwi, Ebtesam N. Alshemmary, Salam Al-augby
This paper presents a novel model for arrhythmia detection based on a cascading technique that utilizes a combination of the One-Sided Selection (OSS) method, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) algorithms, this model denoted by (OWSK) model to classify four types of electrocardiogram (ECG) heartbeats following inter-patient scheme. The OWSK model consists of three stages. The first stage involves resampling using the One-Sided Selection (OSS) method to solve the imbalance problem and reduce data by removing noisy, borderline, and redundant samples. The second stage involves using Wavelet Transformation (WT) and Power Spectral Density (PSD) to extract the most relevant frequency domain features. The third stage involves a cascading process by constructing the classifier from SVM trained on the whole dataset to classify normal and abnormal beats. Then, KNN (K-Nearest Neighbors) is trained on only the three irregular minority classes to classify the three types of arrhythmias for the detection of ventricular ectopic beats, supraventricular ectopic beats, and fusion beats (V, S, and F). The performance of the proposed model is evaluated in terms of different metrics, including accuracy, recall, precision, and F1 score. The results show the superiority of the proposed model in medical diagnosis compared to the latest works, where it achieves 90%, 90%, 93%, and 91% for accuracy, recall, precision, and F1 score under the inter-patient paradigm and 98%, 98%, 98%, and 98% under the intra-patient paradigm.
{"title":"Arrhythmia Detection Based on New Multi-Model Technique for ECG Inter-Patient Classification","authors":"Z. Oleiwi, Ebtesam N. Alshemmary, Salam Al-augby","doi":"10.3991/ijoe.v19i12.41631","DOIUrl":"https://doi.org/10.3991/ijoe.v19i12.41631","url":null,"abstract":"This paper presents a novel model for arrhythmia detection based on a cascading technique that utilizes a combination of the One-Sided Selection (OSS) method, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) algorithms, this model denoted by (OWSK) model to classify four types of electrocardiogram (ECG) heartbeats following inter-patient scheme. The OWSK model consists of three stages. The first stage involves resampling using the One-Sided Selection (OSS) method to solve the imbalance problem and reduce data by removing noisy, borderline, and redundant samples. The second stage involves using Wavelet Transformation (WT) and Power Spectral Density (PSD) to extract the most relevant frequency domain features. The third stage involves a cascading process by constructing the classifier from SVM trained on the whole dataset to classify normal and abnormal beats. Then, KNN (K-Nearest Neighbors) is trained on only the three irregular minority classes to classify the three types of arrhythmias for the detection of ventricular ectopic beats, supraventricular ectopic beats, and fusion beats (V, S, and F). The performance of the proposed model is evaluated in terms of different metrics, including accuracy, recall, precision, and F1 score. The results show the superiority of the proposed model in medical diagnosis compared to the latest works, where it achieves 90%, 90%, 93%, and 91% for accuracy, recall, precision, and F1 score under the inter-patient paradigm and 98%, 98%, 98%, and 98% under the intra-patient paradigm.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48211400","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 : 2023-08-31DOI: 10.3991/ijoe.v19i12.40329
Moulay Hafid Aabidi, Adil El Makrani, B. Jabir, Imane Zaimi
Deep learning has gained significant popularity due to its exceptional performance in various machine learning and artificial intelligence applications. In this paper, we propose a comprehensive methodology for enhancing leaf disease detection using Convolutional Neural Networks (CNNs). Our approach leverages the power of CNNs and introduces innovative techniques to improve accuracy and provide insights into the inner workings of the models. The methodology encompasses multiple stages. We describe the methodology as follows: Firstly, we employ advanced preprocessing techniques to enhance the leaf image dataset, including data augmentation methods to augment the training data and improve model accuracy. Secondly, we design and implement a robust Convolutional Neural Network architecture with multiple layers and ReLU activation, enabling the network to effectively learn complex patterns and features from the input images. To facilitate monitoring and control of the CNN processes, we introduce a novel network visualization module. This module offers a filter-level 2D embedding view, providing real-time insights into the inner workings of the network and aiding in the interpretation of the learned features. Additionally, we develop an interactive module that enables real-time model control, allowing researchers and practitioners to fine-tune the model parameters and optimize its performance. To evaluate the effectiveness of our proposed methodology, we conduct extensive experiments using the PlantVillage dataset, which contains a diverse range of plant diseases captured through a large number of leaf images. Through rigorous analysis and evaluation, we demonstrate the superior performance of our approach, achieving classification accuracy exceeding 99%.
{"title":"A Model Proposal for Enhancing Leaf Disease Detection Using Convolutional Neural Networks (CNN)","authors":"Moulay Hafid Aabidi, Adil El Makrani, B. Jabir, Imane Zaimi","doi":"10.3991/ijoe.v19i12.40329","DOIUrl":"https://doi.org/10.3991/ijoe.v19i12.40329","url":null,"abstract":"Deep learning has gained significant popularity due to its exceptional performance in various machine learning and artificial intelligence applications. In this paper, we propose a comprehensive methodology for enhancing leaf disease detection using Convolutional Neural Networks (CNNs). Our approach leverages the power of CNNs and introduces innovative techniques to improve accuracy and provide insights into the inner workings of the models. The methodology encompasses multiple stages. We describe the methodology as follows: Firstly, we employ advanced preprocessing techniques to enhance the leaf image dataset, including data augmentation methods to augment the training data and improve model accuracy. Secondly, we design and implement a robust Convolutional Neural Network architecture with multiple layers and ReLU activation, enabling the network to effectively learn complex patterns and features from the input images. To facilitate monitoring and control of the CNN processes, we introduce a novel network visualization module. This module offers a filter-level 2D embedding view, providing real-time insights into the inner workings of the network and aiding in the interpretation of the learned features. Additionally, we develop an interactive module that enables real-time model control, allowing researchers and practitioners to fine-tune the model parameters and optimize its performance. To evaluate the effectiveness of our proposed methodology, we conduct extensive experiments using the PlantVillage dataset, which contains a diverse range of plant diseases captured through a large number of leaf images. Through rigorous analysis and evaluation, we demonstrate the superior performance of our approach, achieving classification accuracy exceeding 99%.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45194638","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：