Zahraa Saddi Kadhim, Hasanen S. Abdullah, K. I. Ghathwan
{"title":"Automatically Avoiding Overfitting in Deep Neural Networks by Using Hyper-Parameters Optimization Methods","authors":"Zahraa Saddi Kadhim, Hasanen S. Abdullah, K. I. Ghathwan","doi":"10.3991/ijoe.v19i05.38153","DOIUrl":"https://doi.org/10.3991/ijoe.v19i05.38153","url":null,"abstract":"Overfitting is one issue that deep learning faces in particular. It leads to highly accurate classification results, but they are fraudulent. As a result, if the overfitting problem is not fully resolved, systems that rely on prediction or recognition and are sensitive to accuracy will produce untrustworthy results. All prior suggestions helped to lessen this issue but fell short of eliminating it entirely while maintaining crucial data. This paper proposes a novel approach to guarantee the preservation of critical data while eliminating overfitting completely. Numeric and image datasets are employed in two types of networks: convolutional and deep neural networks. Following the usage of three regularization techniques (L1, L2, and dropout), apply two optimization algorithms (Bayesian and random search), allowing them to select the hyperparameters automatically, with regularization techniques being one of the hyperparameters that are automatically selected. The obtained results, in addition to completely eliminating the overfitting issue, showed that the accuracy of the image data was 97.82% and 90.72 % when using Bayesian and random search techniques, respectively, and was 95.3 % and 96.5 % when using the same algorithms with a numeric dataset. \u0000 \u0000 \u0000 ","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"576 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122932349","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}
{"title":"Gray Level Co-Occurrence Matrices and Support Vector Machine for Improved Lung Cancer Detection","authors":"M. Yunianto, A. Suparmi, C. Cari, T. Ardyanto","doi":"10.3991/ijoe.v19i05.35665","DOIUrl":"https://doi.org/10.3991/ijoe.v19i05.35665","url":null,"abstract":"A detection system based on digital image processing and machine learning classification was developed to detect normal and cancerous lung conditions. 340 data from LIDC –IDRI were processed through several stages. The first stage is pre-processing using three filter variations and contrast stretching, which reduce noise and increase image contrast. The image segmentation process uses Otsu Thresholding to clarify the ROI of the image. The texture feature extraction with GLCM was applied using 21 feature variations. Data extraction is used as a label value learned by the classification system in the form of SVM. The results of the training data classification are processed with a confusion matrix which shows that the high pass filter has higher accuracy than the other two variations. The proposed method was assessed in terms of accuracy, precision and recall. The model provided an accuracy of 99.67 % training data and 97.50 % testing data.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128408428","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}
{"title":"Adolescents' Cognitive Abilities, Reaction Time, and Working Memory Performance by Vienna Test Systems","authors":"V. Veliks, J. Porozovs, A. Kļaviņa, A. Zuša","doi":"10.3991/ijoe.v19i05.37057","DOIUrl":"https://doi.org/10.3991/ijoe.v19i05.37057","url":null,"abstract":"Abstract - Mental and physical health components are critical in child’s development. However, adolescents are especially vulnerable group presenting multiple health risks of chronic disease, sleeping and eating problems. Moreover, the long time spent at screens increases possibility to develop addictions. There is a lack of comprehensive interdisciplinary assessment tools for adolescents, to assess their mental health components, and provide preventive activities. It is very important to develop a methodology that can accurately assess the minor cognitive and health deviations that can be caused by an unhealthy lifestyle and excessive time spent on screens. This research explores the possibilities to record and compare parameters of cognitive abilities, reaction time, and working memory using Vienna test systems for different groups of adolescents by their physical activity and health levels. The results of this study demonstrated that the reaction time in adolescents was shorter using the leading hand in comparison with using the non-leading hand, 272.842±44.001ms vs 306.631±57.081ms on Vienna test for low physical activity (LPA) adolescents group. In the STROOP test color evaluation results were faster than word reading test results. The median of reaction time of LPA adolescents for color evaluation was 0.897±0.221ms and 0.968±0.15ms for reading. Vienna test system has specific tests that can be used to determine memory parameters, providing different assessment approaches to compare the obtained results. Group of adolescents with mild chronic health conditions performs statistically significantly lower parameter in particular tests in comparison with adolescents with low and high physical activity.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"05 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130482770","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}
Rina Novalinda, M. Giatman, Syahril, R. Wulansari, Chau Trung Tin
{"title":"Constructivist Computer-Based Instruction (CBI) Approach: A CBI Flipped Learning Integrated Problem Based and Case Method (PBL-cflip) in Clinical Refraction Course","authors":"Rina Novalinda, M. Giatman, Syahril, R. Wulansari, Chau Trung Tin","doi":"10.3991/ijoe.v19i05.37707","DOIUrl":"https://doi.org/10.3991/ijoe.v19i05.37707","url":null,"abstract":"Based on the preliminary study conducted, it was revealed that critical thinking skills, creativity, and student learning outcomes were low in clinical refraction courses. Whereas in 21st-century learning, students must master the skills of critical thinking, communication, collaboration, and creativity (4Cs) as recommended. Because of this phenomenon, it is critical to use the appropriate learning approach; one solution offered is CBI Flipped Learning Integrated Problem-Based and Case Method (PBL-cflip). The purpose of this study is to describe the effectiveness of the CBI Flipped Learning Integrated Problem Based and Case Method (PBL-cflip) in improving student learning outcomes in clinical refraction courses. This research is quantitative, using a quasi-experimental method. Participants in this study were 61 vocational education students who took the clinical refraction course. The results showed an increase in students' critical thinking, collaboration, communication, and creativity skills, which helped them achieve the expected learning outcomes. It can be concluded that this PBL-cflip is very useful for students to understand and solve cases in clinical refraction courses and can create an interesting learning atmosphere according to student interests, making students more enthusiastic about participating in learning. The novelty of this study is the use of problem-based CBI, which is implemented in a flipped, whereas previous studies have not focused on implementing problem-based in a flipped manner","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"4 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120885679","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}
{"title":"New Technologies for Inclusive Learning for Students with Special Educational Needs","authors":"Eleni Karagianni, A. Drigas","doi":"10.3991/ijoe.v19i05.36417","DOIUrl":"https://doi.org/10.3991/ijoe.v19i05.36417","url":null,"abstract":"In recent years, in the context of the educational reform, dominant position is held by the social demand for the inclusion of all students in the regular classroom and the request to redesign the educational process to align with the individualized needs of students. Τhe concept of inclusion, which view the heterogeneity in the light of social justice and equality, refers not simply to the placement of the SEN students in the mainstream school, but basically, to their dynamic engagement in every aspect of the educational process and in the social interactions that flow from it. “E-inclusive” pedagogy refers to teachers’ decisions to providing their students innovative ways of learning and alternative means of completing their tasks, by incorporating the technology in the educational activities. The aim of this paper is to propose tech tools and e-services for the accessibility and active participation of students with special educational needs in teaching and learning procedures of the ordinary classroom and examine the role of teachers in realizing their inclusion / e-inclusion, as the main facilitators and modulators of the classroom settings to an open learning and development ecosystem. The results showed that teachers who provide authentic opportunities for interaction and learning for all their students and incorporate, flexibly, new technologies into their teaching strategies to meet their unique needs, contribute significantly to their acquisition of academic but mainly functional life skills, preparing them for substantial employment and integration opportunities in community life.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129332107","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}
{"title":"Fiat lux et facta est lux: Leonardo Reveals the Secrets of the Heart and Arteries (in Health and Disease)","authors":"R. Armentano","doi":"10.3991/ijoe.v19i05.37567","DOIUrl":"https://doi.org/10.3991/ijoe.v19i05.37567","url":null,"abstract":"Five hundred years after his death, the figure of Leonardo da Vinci continues transmitting his tireless desire to know and learn. Leonardo is the symbol of a century in which progress impacted, shattering the thickness of dogmas. In the Quattrocento, the doors were opened, ideas spread and still feed us, clear our path, and enlighten us. Florence, in Leonardo's time, was the Silicon Valley of the Renaissance. Leonardo studied the dynamics of water flow in rivers, using colors to show the flow patterns, thus defining the continuous stress on the side walls of the river. He determined, with different colors, the flow characteristics in the center and near the edges of the rivers and extrapolated those findings to the blood that flows in the arteries. Leonardo studied the coronary artery and veins, heart and bronchia in detail and made several assumptions about the cause of atherosclerosis, based on his previous hydrodynamic studies of water flow. Leonardo theorized that diseases were derived from some imperfection in the structure of the human body and addressed the issue of atherosclerosis and its correlation with aging. He accurately described a case of portal hypertension with liver cirrhosis as well as pulmonary circulation and chronic obstructive pulmonary disease. Leonardo was the great pioneer in revealing the secrets of the heart and arteries","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126155354","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}
{"title":"Performance Analysis for 3D Reconstruction Objects in Meshroom and Agisoft - A Comparative Study","authors":"I. Enesi, A. Kuqi","doi":"10.3991/ijoe.v19i05.37257","DOIUrl":"https://doi.org/10.3991/ijoe.v19i05.37257","url":null,"abstract":"3D reconstruction of objects is with interest nowadays, mainly in production industry. The main challenge of them is accuracy and processing time, especially for small and detailed objects. The field of photogrammetry realizes the 3D reconstruction of objects through 2D photos. Different software, free or non-free exists, providing different quality and performance. Accurate 3D reconstruction is important in cloning objects, especially in the industry of spare parts or in the production of prostheses in medicine, etc. Determining accurately the sizes of the object, especially those with complex geometric shapes is very important in the 3D printing process. \u0000The purpose of this paper is the analysis of the performance of 3D reconstruction in terms of accuracy for objects of different sizes regarding the number of its photos and the time evaluation of this process. The 3D reconstruction will be performed by free software Meshroom, measurement will be done in MeshLab and non-free software Agisoft. Experimental results show that quality and performance of 3D reconstruction depends on the number of photos of the object, concluding in finding the optimal balance between these parameters. By comparing obtained results from MeshRoom and Meshlag versus Agisoft, it is claimed that Agisoft performs better than MeshRoom. It offers more optimization techniques, reduces processing time, more visual quality in the reconstructed 3D object as well as more accuracy in measurement.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126314022","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}
{"title":"Algorithms for Machine Learning with Orange System","authors":"I. Popchev, D. Orozova","doi":"10.3991/ijoe.v19i04.36897","DOIUrl":"https://doi.org/10.3991/ijoe.v19i04.36897","url":null,"abstract":"Emphasized is the need for new approaches and solutions for forming of increased information awareness, knowledge and competencies in the present and future generations to use the possibilities of emerging technologies for technological breakthroughs. The article presents basic machine learning tools of both types: supervised learning, which trains a model on known input and output data and predicts future results, and unsupervised learning, which finds hidden patterns or inherent structures in the input data. Algorithms for the processes of creating an information flow when applying the tools of the Orange system, which can be used for research, analysis and training, are formulated. Experiments related to smart crop production and analyses with different classification, regression and clustering algorithms. The results show that the formulated solutions can be successfully used for different tasks and can be adapted to new technologies and applications.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122510553","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}
{"title":"A Novel Method of Invisible Video Watermarking Based on Index Mapping and Hybrid DWT-DCT","authors":"H. Hazim, Nawar S. Alseelawi, H. Alrikabi","doi":"10.3991/ijoe.v19i04.37581","DOIUrl":"https://doi.org/10.3991/ijoe.v19i04.37581","url":null,"abstract":"Watermarking is widely used in multimedia preservation and communication, which comprises, and is therefore not limited to, data security and validation. Security, readability, imperceptibility, and resilience are some of the key advantages of this technology. However, there are still certain issues that need to be addressed, such as the ability to withstand a variety of assaults without substantially affecting the quality and value of embedded data. Based on its operational domain, the watermarking technology may be divided into two groups: spatial and frequency watermarking. An index mapping-based watermarking approach for copyright protection of multi-media color videos is presented in this paper. We offer a hybrid discrete wavelet transform and discrete cosine transform (DCT) watermarking algorithm for digital video watermarking of a color video watermark. Peak signal to noise ratio (PSNR), similarity structure index measure (SSIM), have been used to analyze the distortion produced by watermarking. It is suggested that the proposed video watermarking method provides greater imperceptibility in conjunction with each other with the human visual system and it offers higher robustness against different attacks.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116753874","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}
{"title":"Determining the Optimal Number of Clusters using Silhouette Score as a Data Mining Technique","authors":"Ylber Januzaj, E. Beqiri, A. Luma","doi":"10.3991/ijoe.v19i04.37059","DOIUrl":"https://doi.org/10.3991/ijoe.v19i04.37059","url":null,"abstract":"The identification of the same objects is very important in determining the similarity between different objects. Nowadays, there are several techniques that allow us to divide objects into different groups that differ from one to another. In order to have the best separation between the clusters, it is required that the optimal determination of the number of clusters of a corpus be made in advance. In our research, the Silhouette score technique was used in order to make the optimal determination of this number of clusters. The application of such a technique was done through the Python language, and a corpus of unstructured job vacancy data was used. After determining the optimal number, at the end we present these clusters and the similarity between them, this presentation will be done in the form of a graph in a suitable format.","PeriodicalId":247144,"journal":{"name":"Int. J. Online Biomed. Eng.","volume":"248 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131956982","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}