The adoption of HIS has many benefits including reduced waiting time, errors, less paperwork and errors, and easy data retrieval and reporting. The research aims to define whether the training provided by the IT department has an effect on the successful implementation of HIS at the hospital. System and information qualities were significantly associated with the benefit of HIS. Data taken from 296 hospital employees of Mongolian Japan Hospital is used to assess the effect of the implementation of HIS on employee satisfaction and individual benefit. Training had a mediating role in enhancing the effects of system and information quality effects on net benefits perceived by employees. Assessing individual training results may lead to the effective administration of training at the hospitals.
采用 HIS 有很多好处，包括减少等待时间、错误、减少文书工作和错误，以及方便数据检索和报告。研究旨在确定信息技术部门提供的培训是否对医院成功实施 HIS 系统有影响。系统和信息质量与 HIS 的益处有很大关系。研究使用蒙古日本医院 296 名员工的数据来评估实施 HIS 对员工满意度和个人利益的影响。培训在增强系统和信息质量对员工所感知的净收益的影响方面起到了中介作用。对个人培训结果进行评估可促进医院对培训的有效管理。
{"title":"Role of Training in The Successful Implementation of Hospital Information Systems","authors":"Oyuntungalag Buyantur, Sumjidmaa Tumurchudur, Munkhzul Ochirbat, Zaya Mashlai","doi":"10.14464/ess.v10i7.659","DOIUrl":"https://doi.org/10.14464/ess.v10i7.659","url":null,"abstract":"The adoption of HIS has many benefits including reduced waiting time, errors, less paperwork and errors, and easy data retrieval and reporting. The research aims to define whether the training provided by the IT department has an effect on the successful implementation of HIS at the hospital. System and information qualities were significantly associated with the benefit of HIS. Data taken from 296 hospital employees of Mongolian Japan Hospital is used to assess the effect of the implementation of HIS on employee satisfaction and individual benefit. Training had a mediating role in enhancing the effects of system and information quality effects on net benefits perceived by employees. Assessing individual training results may lead to the effective administration of training at the hospitals.","PeriodicalId":322203,"journal":{"name":"Embedded Selforganising Systems","volume":"210 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139237959","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}
The 12th International Symposium on Computer Science, Computer Engineering and Educational Technologies (ISCSET 2023) is published in a special issue of the Embedded Self-Organizing Systems journal of the Chemnitz University of Technology for the second time. In a significant first, ISCSET 2023 utilized the EasyChair conference management platform for paper submissions. Each submission underwent thorough review by three esteemed professors and researchers from our partner universities, resulting in 27 submissions with an acceptance rate of 62%. But ISCSET 2023 was more than just papers; it was a dynamic symposium that featured engaging keynote presentations, thought-provoking talks by invited speakers as well as lively paper presentations. We had participants from 18 countries: Germany, Mongolia, China, France, Jordan, Algeria, Japan, Kazakhstan, Uzbekistan, Bangladesh, India, Iraq, Turkey, Afghanistan, Iran, Tunis, Pakistan and Syria. Thus, with ISCSET 2023 we celebrated a true global convergence of knowledge and ideas.
{"title":"Introduction to the Proceedings of the ISCSET 2023","authors":"U. Tudevdagva, René Bergelt","doi":"10.14464/ess.v10i7.644","DOIUrl":"https://doi.org/10.14464/ess.v10i7.644","url":null,"abstract":"The 12th International Symposium on Computer Science, Computer Engineering and Educational Technologies (ISCSET 2023) is published in a special issue of the Embedded Self-Organizing Systems journal of the Chemnitz University of Technology for the second time. In a significant first, ISCSET 2023 utilized the EasyChair conference management platform for paper submissions. Each submission underwent thorough review by three esteemed professors and researchers from our partner universities, resulting in 27 submissions with an acceptance rate of 62%. But ISCSET 2023 was more than just papers; it was a dynamic symposium that featured engaging keynote presentations, thought-provoking talks by invited speakers as well as lively paper presentations. We had participants from 18 countries: Germany, Mongolia, China, France, Jordan, Algeria, Japan, Kazakhstan, Uzbekistan, Bangladesh, India, Iraq, Turkey, Afghanistan, Iran, Tunis, Pakistan and Syria. Thus, with ISCSET 2023 we celebrated a true global convergence of knowledge and ideas.","PeriodicalId":322203,"journal":{"name":"Embedded Selforganising Systems","volume":"204 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139316784","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}
This study shows the relationship between the types of cultural differences and learning styles of Kolb's learning model. Although several cross-cultural studies on learning styles suggest that learning styles may differ from one culture to another, the question of which cultures are associated with which learning styles and abilities has been less explored. This study focuses on the empirical findings of comparative studies on past cross-cultural differences in learning styles and considers how the propositions generated by the theory tests may reflect their past empirical findings. This research shows that culture is associated with specific learning styles and abilities.
{"title":"Learning Styles and Cultural Differences: A comparative study of cultural differences in Austrian and Mongolian Students","authors":"Ariunaa Khaskhuu, Nyambayar Chimed-Ochir","doi":"10.14464/ess.v10i7.613","DOIUrl":"https://doi.org/10.14464/ess.v10i7.613","url":null,"abstract":"This study shows the relationship between the types of cultural differences and learning styles of Kolb's learning model. Although several cross-cultural studies on learning styles suggest that learning styles may differ from one culture to another, the question of which cultures are associated with which learning styles and abilities has been less explored. This study focuses on the empirical findings of comparative studies on past cross-cultural differences in learning styles and considers how the propositions generated by the theory tests may reflect their past empirical findings. This research shows that culture is associated with specific learning styles and abilities.","PeriodicalId":322203,"journal":{"name":"Embedded Selforganising Systems","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139323942","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}
The article discusses ways of increasing students' engagement, motivation and participation in higher education using "Network Boomerang" technology, as an example of pre-service IT teacher training. With the onset of the global pandemic, the role of digital technologies has significantly increased, highlighting the importance of digital transformation, particularly for developing countries, including Uzbekistan. Indeed, digital transformation has the potential to further modernize society and integrate the national economy into global processes. In this context, within the framework of ongoing reforms and the Development Strategy of the New Uzbekistan for the next five years, special attention is being given to the digitization of key areas of activity and the establishment of a genuine information society in the country.
{"title":"Developing Information Competences of the Students in Technical Direction with Helping the Technology of “Network Boomerang” Principles","authors":"Dilnoza Zaripova","doi":"10.14464/ess.v10i7.633","DOIUrl":"https://doi.org/10.14464/ess.v10i7.633","url":null,"abstract":"The article discusses ways of increasing students' engagement, motivation and participation in higher education using \"Network Boomerang\" technology, as an example of pre-service IT teacher training. With the onset of the global pandemic, the role of digital technologies has significantly increased, highlighting the importance of digital transformation, particularly for developing countries, including Uzbekistan. Indeed, digital transformation has the potential to further modernize society and integrate the national economy into global processes. In this context, within the framework of ongoing reforms and the Development Strategy of the New Uzbekistan for the next five years, special attention is being given to the digitization of key areas of activity and the establishment of a genuine information society in the country.","PeriodicalId":322203,"journal":{"name":"Embedded Selforganising Systems","volume":"64 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139333215","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}
This article discusses the results and evaluation of a training course focused on developing spatial visualization using interactive dynamic tools. The course aims to effectively integrate technology with the Descriptive Geometry course by combining content, pedagogy, and technology while considering the course's characteristics. The training course consists of three phases: seeing, imagining, and drawing. Each phase has different tasks that involve manipulating 3D objects in a virtual environment, corresponding to the level of geometric thinking and cognitive steps of mental rotation. The results of the organized training showed a statistically significant increase in student's spatial skills, and the evaluation of students using the SURE (Structure-Oriented Evaluation) model was deemed sufficient.
{"title":"Some Results and Evaluation of Training for the Development of Students’ Spatial Visualization","authors":"Suvd Erdenechimeg, G. Danaa","doi":"10.14464/ess.v10i7.630","DOIUrl":"https://doi.org/10.14464/ess.v10i7.630","url":null,"abstract":"This article discusses the results and evaluation of a training course focused on developing spatial visualization using interactive dynamic tools. The course aims to effectively integrate technology with the Descriptive Geometry course by combining content, pedagogy, and technology while considering the course's characteristics. The training course consists of three phases: seeing, imagining, and drawing. Each phase has different tasks that involve manipulating 3D objects in a virtual environment, corresponding to the level of geometric thinking and cognitive steps of mental rotation. The results of the organized training showed a statistically significant increase in student's spatial skills, and the evaluation of students using the SURE (Structure-Oriented Evaluation) model was deemed sufficient.","PeriodicalId":322203,"journal":{"name":"Embedded Selforganising Systems","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139334024","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}
This article focuses on the development of a methodology aimed at fostering the digital competence of future engineering pedagogues through the utilization of digital tools. With the digital transformation of the education system, it becomes imperative to adapt the methods of working with educational stakeholders. The creation of a digital educational environment involves equipping organizations with modern equipment and advancing digital services and content. Future engineering pedagogues require digital competencies to effectively integrate digital technologies into the educational process. This article presents a concept for the methodology, which involves the design of practical tasks at three levels: basic, intermediate, and advanced. The results of an experiment conducted with students demonstrate that the proposed methodology yields higher grades compared to traditional methods. The findings underscore the importance of empowering engineering pedagogues with digital competences to prepare students for the digital era.
{"title":"Innovative Teaching Methodology for Developing Digital Competence in Future Engineering Pedagogues","authors":"Насибахон Расулова","doi":"10.14464/ess.v10i7.628","DOIUrl":"https://doi.org/10.14464/ess.v10i7.628","url":null,"abstract":"This article focuses on the development of a methodology aimed at fostering the digital competence of future engineering pedagogues through the utilization of digital tools. With the digital transformation of the education system, it becomes imperative to adapt the methods of working with educational stakeholders. The creation of a digital educational environment involves equipping organizations with modern equipment and advancing digital services and content. Future engineering pedagogues require digital competencies to effectively integrate digital technologies into the educational process. This article presents a concept for the methodology, which involves the design of practical tasks at three levels: basic, intermediate, and advanced. The results of an experiment conducted with students demonstrate that the proposed methodology yields higher grades compared to traditional methods. The findings underscore the importance of empowering engineering pedagogues with digital competences to prepare students for the digital era.","PeriodicalId":322203,"journal":{"name":"Embedded Selforganising Systems","volume":"183 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139335232","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}
This paper describes a cooperative study of university lecturers with a focus on figuring out influence factors of students’ achievements in higher education. The evaluation survey is applied as the main method for research. Several lecturers (research team) who teach different courses in the university together developed influence factors in the form of survey questions, which are divided into four core groups: university, library, courses, and professors. The research team plans to collect as much data periodically from all universities in the country which is open to supporting this study. This paper showed the analyses of the first step of the study. 291 students from eight different universities voluntarily sent responses to an online survey.The collected data is processed by structure-oriented evaluation (SURE) model and by standard statistic function. The SURE evaluation score was calculated as 0.88 which we can read that all defined influence factors received evaluation scores from students with very high positive answers. The statistic maximum scores emphasized some factors that influence a lot to students’ achievement and students confirmed by their responses that some factors are very important for them. Further statistic ANOVA test was made for the case of the university group with 13 factors.For the ANOVA test, the null hypothesis. H0 – Null hypothesis stands for no difference between groups. No influence of study years on evaluation scores. By the ANOVA test, the null hypothesis isn’t proven. This concludes first step analyses as not significant statistically. Therefore, the researchteam needs to continue data collection and may apply some other statistical methods to compare the first results.
{"title":"Influence Rate Evaluation by Students’ Opinion: University, Library, Courses and Professors","authors":"U. Tudevdagva, Narantsatsral Delgerkhuu, Gansaikhan Osorkhuu, Batdorj Davaagombo, Yeruulbat Galbadrakh, Serjmyadag Sergelen","doi":"10.14464/ess.v10i7.631","DOIUrl":"https://doi.org/10.14464/ess.v10i7.631","url":null,"abstract":"This paper describes a cooperative study of university lecturers with a focus on figuring out influence factors of students’ achievements in higher education. The evaluation survey is applied as the main method for research. Several lecturers (research team) who teach different courses in the university together developed influence factors in the form of survey questions, which are divided into four core groups: university, library, courses, and professors. The research team plans to collect as much data periodically from all universities in the country which is open to supporting this study. This paper showed the analyses of the first step of the study. 291 students from eight different universities voluntarily sent responses to an online survey.The collected data is processed by structure-oriented evaluation (SURE) model and by standard statistic function. The SURE evaluation score was calculated as 0.88 which we can read that all defined influence factors received evaluation scores from students with very high positive answers. The statistic maximum scores emphasized some factors that influence a lot to students’ achievement and students confirmed by their responses that some factors are very important for them. Further statistic ANOVA test was made for the case of the university group with 13 factors.For the ANOVA test, the null hypothesis. H0 – Null hypothesis stands for no difference between groups. No influence of study years on evaluation scores. By the ANOVA test, the null hypothesis isn’t proven. This concludes first step analyses as not significant statistically. Therefore, the researchteam needs to continue data collection and may apply some other statistical methods to compare the first results.","PeriodicalId":322203,"journal":{"name":"Embedded Selforganising Systems","volume":"230 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139335245","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}
Universities around the world have been using electronic learning systems more and more in recent years. Due to the Covid-19 pandemic, Mongolian universities are changing the way of teaching online and thus starting from the second semester of the 2019-2020 academic year. The purpose of this study is to investigate the satisfaction of students towards e-learning and the factors affecting it. 321 first-year students of the School of Nursing of NUMS participated in this survey, the survey questionnaire filled in Google form, and received by electronically. The relationship between satisfaction and its influencing factors was evaluated by using the Pearson test (correlation coefficient). According to the indicators of the research results, students' satisfaction is the most satisfied with learning materials (4.16), student engagement (4.15), and the lowest with e-educational technology (3.25). Due to this, there is a didactic need to improve the quality of e-learning and to update the lesson technology. Students' satisfaction level had a direct strong positive correlation (r=0.65) with grade (r=0.65) and a weak direct positive correlation (r=0.38) with lesson access (p<0.001), and e-learning satisfaction scores had a direct correlation (p<0.001) to the quality of teaching, supply of learning materials, assessment, and student engagement.
{"title":"First-Year Students' Satisfaction by E-Learning","authors":"Orkhontuya Puntsag, Javkhlantuya Altansuvd, Tuvshinjargal Radnaa","doi":"10.14464/ess.v10i7.614","DOIUrl":"https://doi.org/10.14464/ess.v10i7.614","url":null,"abstract":"Universities around the world have been using electronic learning systems more and more in recent years. Due to the Covid-19 pandemic, Mongolian universities are changing the way of teaching online and thus starting from the second semester of the 2019-2020 academic year. The purpose of this study is to investigate the satisfaction of students towards e-learning and the factors affecting it. 321 first-year students of the School of Nursing of NUMS participated in this survey, the survey questionnaire filled in Google form, and received by electronically. The relationship between satisfaction and its influencing factors was evaluated by using the Pearson test (correlation coefficient). According to the indicators of the research results, students' satisfaction is the most satisfied with learning materials (4.16), student engagement (4.15), and the lowest with e-educational technology (3.25). Due to this, there is a didactic need to improve the quality of e-learning and to update the lesson technology. Students' satisfaction level had a direct strong positive correlation (r=0.65) with grade (r=0.65) and a weak direct positive correlation (r=0.38) with lesson access (p<0.001), and e-learning satisfaction scores had a direct correlation (p<0.001) to the quality of teaching, supply of learning materials, assessment, and student engagement.","PeriodicalId":322203,"journal":{"name":"Embedded Selforganising Systems","volume":"53 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139335445","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}
Error messages are a helpful tool for everyone interested in learning a programming language. Even after learning the language, novice and experienced programmers alike, have to interact with an error message one way or another. However, there is no single programming language that is usedacross all platforms and systems, so the programmers have to write programs in many different languages. If the programming languages have similar structures, working with a new language is relatively easy. We have asked the question, whether the same effect could be observed in case of error messages. We designed an online survey which was conducted internationally to measure whether the general experience of programmers from any programming language influences the programmer’s ability to correct python error message. The survey was aimed at students who have some experience with programming. We find in comparison with novices, on average the experiencedprogrammers find and fix an error in the code given the sameerror message with its corresponding code snippet. Additionally,we see correlations between the average of correctly fixed errorsand number of programming languages that the participants hadexperience with, as well as their chosen major and their age.
{"title":"Evaluation of Python Error Message Interpretation: Study on Students with Different Levels of Programming Experience","authors":"Gantogoo Oyunbat, Ahmad Hamdy Sayed Hassanien","doi":"10.14464/ess.v10i7.626","DOIUrl":"https://doi.org/10.14464/ess.v10i7.626","url":null,"abstract":"Error messages are a helpful tool for everyone interested in learning a programming language. Even after learning the language, novice and experienced programmers alike, have to interact with an error message one way or another. However, there is no single programming language that is usedacross all platforms and systems, so the programmers have to write programs in many different languages. If the programming languages have similar structures, working with a new language is relatively easy. We have asked the question, whether the same effect could be observed in case of error messages. We designed an online survey which was conducted internationally to measure whether the general experience of programmers from any programming language influences the programmer’s ability to correct python error message. The survey was aimed at students who have some experience with programming. We find in comparison with novices, on average the experiencedprogrammers find and fix an error in the code given the sameerror message with its corresponding code snippet. Additionally,we see correlations between the average of correctly fixed errorsand number of programming languages that the participants hadexperience with, as well as their chosen major and their age.","PeriodicalId":322203,"journal":{"name":"Embedded Selforganising Systems","volume":"60 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139335836","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}
Wood plates are widely used in the interior design of houses primarily for their aesthetic value. However, considering its esthetical values, surface defect detection is necessary. The development of computer vision and CNN-based object detection methods has opened the way for wood surface defect detection process automation. This paper investigates deep-learning applications for automatic wood surface defect detection. It includes the evaluation of deep learning algorithms, including data generation and labeling, preprocessing, model training, and evaluation. Many adjustments regarding the dataset size, the model, and the modification of the neural network were made to evaluate the model's performance in the specified challenge. The results indicate that modifications can increase the YOLOv5s performance in detection. The model with GCNet added and trained in 4800 images has achieved 88.1% of mAP. The paper also evaluates the time performance of models based on different GPU units. The results show that in A100 40GB GPU, the maximum time to process a wood plate is 2.2 seconds. Finally, an Active learning approach for the continual increase in performance while detecting with the smaller size of manual labeling has been implemented. After detecting 500 images in 5 cycles, the model achieved 98.8% of mAP. This scientific paper concludes that YOLOv5s modified model is suitable for wood surface defect detection. It can perform with high accuracy in real time. Moreover, applying the active learning approach can facilitate the labeling process by increasing the performance during detection.
{"title":"Automated Identification of Wood Surface Defects Based on Deep Learning","authors":"Besfort Syla, Shadi M. Saleh, Wolfram Hardt","doi":"10.14464/ess.v10i7.627","DOIUrl":"https://doi.org/10.14464/ess.v10i7.627","url":null,"abstract":"Wood plates are widely used in the interior design of houses primarily for their aesthetic value. However, considering its esthetical values, surface defect detection is necessary. The development of computer vision and CNN-based object detection methods has opened the way for wood surface defect detection process automation. This paper investigates deep-learning applications for automatic wood surface defect detection. It includes the evaluation of deep learning algorithms, including data generation and labeling, preprocessing, model training, and evaluation. Many adjustments regarding the dataset size, the model, and the modification of the neural network were made to evaluate the model's performance in the specified challenge. The results indicate that modifications can increase the YOLOv5s performance in detection. The model with GCNet added and trained in 4800 images has achieved 88.1% of mAP. The paper also evaluates the time performance of models based on different GPU units. The results show that in A100 40GB GPU, the maximum time to process a wood plate is 2.2 seconds. Finally, an Active learning approach for the continual increase in performance while detecting with the smaller size of manual labeling has been implemented. After detecting 500 images in 5 cycles, the model achieved 98.8% of mAP. This scientific paper concludes that YOLOv5s modified model is suitable for wood surface defect detection. It can perform with high accuracy in real time. Moreover, applying the active learning approach can facilitate the labeling process by increasing the performance during detection.","PeriodicalId":322203,"journal":{"name":"Embedded Selforganising Systems","volume":"42 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139336570","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：