Pub Date : 2023-05-03DOI: 10.37394/23202.2023.22.43
H. Sakai
Currently, Japanese companies are working to survive and develop "global production" to realize "the same quality and simultaneous start’, ’up" in the world. From such a background, the production operator is required to change from simple labor until now to an intelligent production operator, and it is important not only to carry out the decided standard work but also to train the operator who can conceive himself and self "kaizen" at an early stage. The author has defined them as intelligent operator and consider that "the evolution of technology and skill (man)" which makes "the advanced production system be used and guaranteed high quality in the manufacturing site" decides the success or failure of the global strategy. Therefore, the author has devised an integrated human management system "HI’, ’POS (Human Intelligence–Production Operating System" aiming at strategic operation to "global production", and demonstrated the effectiveness of the proposed "HI’, ’POS" at an advanced company, Toyota.
{"title":"New Human-centered Production System. Building an Integrated Human Management System","authors":"H. Sakai","doi":"10.37394/23202.2023.22.43","DOIUrl":"https://doi.org/10.37394/23202.2023.22.43","url":null,"abstract":"Currently, Japanese companies are working to survive and develop \"global production\" to realize \"the same quality and simultaneous start’, ’up\" in the world. From such a background, the production operator is required to change from simple labor until now to an intelligent production operator, and it is important not only to carry out the decided standard work but also to train the operator who can conceive himself and self \"kaizen\" at an early stage. The author has defined them as intelligent operator and consider that \"the evolution of technology and skill (man)\" which makes \"the advanced production system be used and guaranteed high quality in the manufacturing site\" decides the success or failure of the global strategy. Therefore, the author has devised an integrated human management system \"HI’, ’POS (Human Intelligence–Production Operating System\" aiming at strategic operation to \"global production\", and demonstrated the effectiveness of the proposed \"HI’, ’POS\" at an advanced company, Toyota.","PeriodicalId":39422,"journal":{"name":"WSEAS Transactions on Systems and Control","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84685314","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 : 2023-05-03DOI: 10.37394/23202.2023.22.41
Karel Greiner
The paper describes a new method of developing the annual train timetable in the information system of the infrastructure manager in the Czech Republic. The system is accessible to the information systems of railway undertakings through a data interface that allows receiving and providing messages compliant with the TAF / TAP TSI specifications of the European Union. In order to develop a timetable, processes are designed for processing a new request, modifying and cancelling a request by the railway undertaking, deleting a route by the infrastructure manager, and processing data that is not needed at the time of path construction.
本文介绍了在捷克基础设施管理信息系统中编制年度列车时刻表的一种新方法。铁路企业的资讯系统可透过一个数据接口，接收和提供符合欧洲联盟TAF / TAP TSI规格的讯息。为了制定时间表，流程被设计用于处理新的请求，修改和取消铁路企业的请求，基础设施管理人员删除路线，以及处理在道路建设时不需要的数据。
{"title":"Implementing the TSI EU into the System of Developing the Annual Train Timetable of the Infrastructure Manager","authors":"Karel Greiner","doi":"10.37394/23202.2023.22.41","DOIUrl":"https://doi.org/10.37394/23202.2023.22.41","url":null,"abstract":"The paper describes a new method of developing the annual train timetable in the information system of the infrastructure manager in the Czech Republic. The system is accessible to the information systems of railway undertakings through a data interface that allows receiving and providing messages compliant with the TAF / TAP TSI specifications of the European Union. In order to develop a timetable, processes are designed for processing a new request, modifying and cancelling a request by the railway undertaking, deleting a route by the infrastructure manager, and processing data that is not needed at the time of path construction.","PeriodicalId":39422,"journal":{"name":"WSEAS Transactions on Systems and Control","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90806204","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 : 2023-05-03DOI: 10.37394/23202.2023.22.42
Siti Talidah, Advia Fildzah, M. Ichsan, Diena Dwidienawati, Maharani Syahratu Kertapati, Olinda Calista Yetri, Rafahana Ansiklia Kirana, Adji Pradana, R. Aditya
This study aimed to validate previous studies’ five core competencies of PMO Managers. It describes the competencies of effective PMO Managers as evidence of PMO practices in companies. Researchers obtained data sources from five members of PMO Professional Indonesia (PMOPI) focused on the financial industry. This study uses a qualitative research approach, collecting the data using structured interviews with selected respondents. Certified experts have validated and calculated the percentage of occurrence of each core competency and the PMO management function. A final analysis of the data is conducted using NVIVO Software. The study has produced a percentage of the emergence of PMO managers’ competencies, especially in the financial industry, to validate the five core competencies from previous studies by specific dimensions. The analysis results of this validation, with an inter’, ’rater percentage of 95,31%, indicated that the data analyzed had high accuracy. This study reveals that business mainframe is a competency often applied in the financial industry PMO. The findings are 26,83%, significantly different from the results of other competencies. The Technical & Professional Specialty is 10,87%, Effective Intersocial Competencies is 15,85%, Organizational Stewardship is 10,98%, and Effective Personal Competencies is 3,05%. This study has provided new insight into PMO manager competencies which are required for PMO managers to perform their work effectively. This set of competencies is required by organizations that see the need to develop PMO managers’ capabilities in managing their projects.
{"title":"Revealing the Project Management Office Manager’s Competencies: A Qualitative Study in Financial Industry","authors":"Siti Talidah, Advia Fildzah, M. Ichsan, Diena Dwidienawati, Maharani Syahratu Kertapati, Olinda Calista Yetri, Rafahana Ansiklia Kirana, Adji Pradana, R. Aditya","doi":"10.37394/23202.2023.22.42","DOIUrl":"https://doi.org/10.37394/23202.2023.22.42","url":null,"abstract":"This study aimed to validate previous studies’ five core competencies of PMO Managers. It describes the competencies of effective PMO Managers as evidence of PMO practices in companies. Researchers obtained data sources from five members of PMO Professional Indonesia (PMOPI) focused on the financial industry. This study uses a qualitative research approach, collecting the data using structured interviews with selected respondents. Certified experts have validated and calculated the percentage of occurrence of each core competency and the PMO management function. A final analysis of the data is conducted using NVIVO Software. The study has produced a percentage of the emergence of PMO managers’ competencies, especially in the financial industry, to validate the five core competencies from previous studies by specific dimensions. The analysis results of this validation, with an inter’, ’rater percentage of 95,31%, indicated that the data analyzed had high accuracy. This study reveals that business mainframe is a competency often applied in the financial industry PMO. The findings are 26,83%, significantly different from the results of other competencies. The Technical & Professional Specialty is 10,87%, Effective Intersocial Competencies is 15,85%, Organizational Stewardship is 10,98%, and Effective Personal Competencies is 3,05%. This study has provided new insight into PMO manager competencies which are required for PMO managers to perform their work effectively. This set of competencies is required by organizations that see the need to develop PMO managers’ capabilities in managing their projects.","PeriodicalId":39422,"journal":{"name":"WSEAS Transactions on Systems and Control","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74080769","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 : 2023-04-26DOI: 10.37394/23202.2023.22.40
M. Lefebvre
The problem of controlling a one-dimensional Markov chain until is leaves a given set C is considered. The optimizer tries to minimize the time spent by the Markov chain inside C. The control variable can take two different values. An exact formula is obtained for the value function, from which the optimal control is deduced.
{"title":"An Explicit Solution to a Discrete-time Stochastic Optimal Control Problem","authors":"M. Lefebvre","doi":"10.37394/23202.2023.22.40","DOIUrl":"https://doi.org/10.37394/23202.2023.22.40","url":null,"abstract":"The problem of controlling a one-dimensional Markov chain until is leaves a given set C is considered. The optimizer tries to minimize the time spent by the Markov chain inside C. The control variable can take two different values. An exact formula is obtained for the value function, from which the optimal control is deduced.","PeriodicalId":39422,"journal":{"name":"WSEAS Transactions on Systems and Control","volume":"256 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75556655","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 : 2023-04-26DOI: 10.37394/23203.2023.18.10
D. Krokavec, A. Filasová
This paper is concerned with the design of switching observers for nonlinear positive systems, where the basic parameters of the Metzler-Takagi-Sugeno fuzzy models are intervally defined. With consideration of the measurable set of premise variables the associated structure of the switching fuzzy interval observers is proposed for system state estimation to maintain stability and H1 performance level under the influence of norm-bounded additive disturbance. The design conditions take into account the lower and upper bounds of nonnegative system state. A numerical example is included to demonstrate the effectiveness of the developed theory for the condisered class of systems.
{"title":"Interval Observers for Switched Metzler-Takagi-Sugeno Fuzzy Systems","authors":"D. Krokavec, A. Filasová","doi":"10.37394/23203.2023.18.10","DOIUrl":"https://doi.org/10.37394/23203.2023.18.10","url":null,"abstract":"This paper is concerned with the design of switching observers for nonlinear positive systems, where the basic parameters of the Metzler-Takagi-Sugeno fuzzy models are intervally defined. With consideration of the measurable set of premise variables the associated structure of the switching fuzzy interval observers is proposed for system state estimation to maintain stability and H1 performance level under the influence of norm-bounded additive disturbance. The design conditions take into account the lower and upper bounds of nonnegative system state. A numerical example is included to demonstrate the effectiveness of the developed theory for the condisered class of systems.","PeriodicalId":39422,"journal":{"name":"WSEAS Transactions on Systems and Control","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46085370","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 : 2023-03-30DOI: 10.37394/23203.2023.18.9
Nikolaos E. Fragiadakis, A. T. Baklezos, T. Kapetanakis, I. Vardiambasis, C. D. Nikolopoulos
Authors prior to this work proposed a methodology providing electric or magnetic cleanliness on spacecraft implementation by reordering equipment units. More precisely, since the mission's scientific goal relies on the payload's high sensitivity and accuracy for capturing the space environment, field minimization in measuring instrument location is imperative. Electromagnetic cleanliness is a constant open issue, since the mission target relies on clean measurements without including spacecraft self-emissions. A lot of science missions of ESA, NASA, or JAXA select usually a set of a couple of basic units as standard payload, i.e. batteries, Radio Frequency switches, Command units or Data Handling Management units, S-Band Transceivers, Power Distribution Units, etc. The later is usually measured and electromagnetically characterized by employing the on-ground facilities providing equivalent radiating models. This work provides a supplementary module to the formerly created framework for an entire unit positioning approach, taking into account the unit’s test-level data, for suitable allocation of the space vessel’s equipment toward electric cleanliness purposes taking into consideration the unit’s induced behavior.
{"title":"Electric Cleanliness Algorithm based on Multi-Unit Interaction and Reallocation","authors":"Nikolaos E. Fragiadakis, A. T. Baklezos, T. Kapetanakis, I. Vardiambasis, C. D. Nikolopoulos","doi":"10.37394/23203.2023.18.9","DOIUrl":"https://doi.org/10.37394/23203.2023.18.9","url":null,"abstract":"Authors prior to this work proposed a methodology providing electric or magnetic cleanliness on spacecraft implementation by reordering equipment units. More precisely, since the mission's scientific goal relies on the payload's high sensitivity and accuracy for capturing the space environment, field minimization in measuring instrument location is imperative. Electromagnetic cleanliness is a constant open issue, since the mission target relies on clean measurements without including spacecraft self-emissions. A lot of science missions of ESA, NASA, or JAXA select usually a set of a couple of basic units as standard payload, i.e. batteries, Radio Frequency switches, Command units or Data Handling Management units, S-Band Transceivers, Power Distribution Units, etc. The later is usually measured and electromagnetically characterized by employing the on-ground facilities providing equivalent radiating models. This work provides a supplementary module to the formerly created framework for an entire unit positioning approach, taking into account the unit’s test-level data, for suitable allocation of the space vessel’s equipment toward electric cleanliness purposes taking into consideration the unit’s induced behavior.","PeriodicalId":39422,"journal":{"name":"WSEAS Transactions on Systems and Control","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44253572","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 : 2023-03-28DOI: 10.37394/23203.2023.18.8
Ricardo Yauri, Martin Gonzales, Vanessa Gamero
The problems related to the proper management and control in the distribution of potable water affect environmental sustainability generated by leaks and breaks in the infrastructure, causing leaks and loss of water. According to reports from the National Superintendence of Sanitation Services of Peru, more than 50% of complaints about the water service are related to billing problems and water leaks. It is for this reason that technologies such as the Internet of Things technology contribute to generating solutions for the automatic acquisition of data in residences and houses. That is why this paper aims to use long-range and low-power wireless communication systems to improve the service-oriented to the control of the water distribution network, monitoring of vandalism, and detection of anomalous events, reducing response time and economic losses. The paper's development methodology considers the implementation of a water controller node with flow control sensors and solenoid valves and a gateway with Lora communication. In addition, a solenoid valve control circuit and a remote visualization and control system are implemented. The results indicate that the implemented nodes allow adequate monitoring and control in real-time of the water flow, contributing to the adequate management of its consumption and supporting the detection of anomalous events using a Web application.
{"title":"Remote Monitoring and Control System of a Water Distribution Network using LoRaWAN Technology","authors":"Ricardo Yauri, Martin Gonzales, Vanessa Gamero","doi":"10.37394/23203.2023.18.8","DOIUrl":"https://doi.org/10.37394/23203.2023.18.8","url":null,"abstract":"The problems related to the proper management and control in the distribution of potable water affect environmental sustainability generated by leaks and breaks in the infrastructure, causing leaks and loss of water. According to reports from the National Superintendence of Sanitation Services of Peru, more than 50% of complaints about the water service are related to billing problems and water leaks. It is for this reason that technologies such as the Internet of Things technology contribute to generating solutions for the automatic acquisition of data in residences and houses. That is why this paper aims to use long-range and low-power wireless communication systems to improve the service-oriented to the control of the water distribution network, monitoring of vandalism, and detection of anomalous events, reducing response time and economic losses. The paper's development methodology considers the implementation of a water controller node with flow control sensors and solenoid valves and a gateway with Lora communication. In addition, a solenoid valve control circuit and a remote visualization and control system are implemented. The results indicate that the implemented nodes allow adequate monitoring and control in real-time of the water flow, contributing to the adequate management of its consumption and supporting the detection of anomalous events using a Web application.","PeriodicalId":39422,"journal":{"name":"WSEAS Transactions on Systems and Control","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44523495","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 : 2023-03-24DOI: 10.37394/23202.2023.22.38
Christos Pechlivanis
The Internet of Things (IoT) is proliferating, with thousands of new sensors and equipment going live each month. Despite its lengthy evolution, the Internet of Things has only recently begun to take off in the mass market due to low-cost, reduced-power elements, ubiquitous web access, and high business and consumer interest. The Internet of Things includes anything from intelligent kitchen appliances to smart buildings, smart lighting on streets to automated manufacturing processes, and adaptive home heaters to autonomous vehicles. This research concerns studying and applying Internet of Things (IoT) technology to monitor the supply chain and achieve more sustainable operations by ensuring accurate and real-time data monitoring. In this context, an experimental device is developed to read the values of selected physical quantities from the wine supply chain environment through appropriate sensors. The values are then sent to an IoT platform to facilitate the remote monitoring of the above physical quantities and extract valuable insights from the large volume of data generated. The results show that crucial information can be gathered in real-time, enabling quick decision-making and ensuring safer and more sustainable supply chain operations.
{"title":"Implementing IoT Technology in Practice: Monitoring the Supply Chain for Sustainable Operation","authors":"Christos Pechlivanis","doi":"10.37394/23202.2023.22.38","DOIUrl":"https://doi.org/10.37394/23202.2023.22.38","url":null,"abstract":"The Internet of Things (IoT) is proliferating, with thousands of new sensors and equipment going live each month. Despite its lengthy evolution, the Internet of Things has only recently begun to take off in the mass market due to low-cost, reduced-power elements, ubiquitous web access, and high business and consumer interest. The Internet of Things includes anything from intelligent kitchen appliances to smart buildings, smart lighting on streets to automated manufacturing processes, and adaptive home heaters to autonomous vehicles. This research concerns studying and applying Internet of Things (IoT) technology to monitor the supply chain and achieve more sustainable operations by ensuring accurate and real-time data monitoring. In this context, an experimental device is developed to read the values of selected physical quantities from the wine supply chain environment through appropriate sensors. The values are then sent to an IoT platform to facilitate the remote monitoring of the above physical quantities and extract valuable insights from the large volume of data generated. The results show that crucial information can be gathered in real-time, enabling quick decision-making and ensuring safer and more sustainable supply chain operations.","PeriodicalId":39422,"journal":{"name":"WSEAS Transactions on Systems and Control","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74708002","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 : 2023-03-24DOI: 10.37394/23202.2023.22.39
Yani Riyani, Kartawati Mardiah, Mahyus Mahyus, Endang Kusmana, S. Andriana, Nengzih Nengzih, Irzan Soepriyadi, Endri Endri
Several research results in the Indonesian Capital Market have found a market anomaly phenomenon caused by the market reacting to internal and external information. This study aims to examine whether companyspecific factors (company size, growth, and risk), national macroeconomic factors (Inflation, interest rates, and exchange rates on a national scale), and world macroeconomic factors (market returns, Inflation, interest rates, and world-scale exchange rates) ) may cause the Indonesian Capital Market to react. The form of this research is associative descriptive with a population of all companies indexed by LQ45, totaling 45 companies. According to purposive sampling, the sample used is 22 companies, and data analysis using panel data regression with the help of software Eviews 12. The study's results found that only national interest rates and world inflation could cause the Indonesian Capital Market to react. In contrast, size, growth, risk, national Inflation, world returns, world interest rates, and world exchange rates did not cause the Indonesian Capital Market to react.
{"title":"Determinants of Indonesian Capital Market Reaction","authors":"Yani Riyani, Kartawati Mardiah, Mahyus Mahyus, Endang Kusmana, S. Andriana, Nengzih Nengzih, Irzan Soepriyadi, Endri Endri","doi":"10.37394/23202.2023.22.39","DOIUrl":"https://doi.org/10.37394/23202.2023.22.39","url":null,"abstract":"Several research results in the Indonesian Capital Market have found a market anomaly phenomenon caused by the market reacting to internal and external information. This study aims to examine whether companyspecific factors (company size, growth, and risk), national macroeconomic factors (Inflation, interest rates, and exchange rates on a national scale), and world macroeconomic factors (market returns, Inflation, interest rates, and world-scale exchange rates) ) may cause the Indonesian Capital Market to react. The form of this research is associative descriptive with a population of all companies indexed by LQ45, totaling 45 companies. According to purposive sampling, the sample used is 22 companies, and data analysis using panel data regression with the help of software Eviews 12. The study's results found that only national interest rates and world inflation could cause the Indonesian Capital Market to react. In contrast, size, growth, risk, national Inflation, world returns, world interest rates, and world exchange rates did not cause the Indonesian Capital Market to react.","PeriodicalId":39422,"journal":{"name":"WSEAS Transactions on Systems and Control","volume":"R-36 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84563914","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 : 2023-03-24DOI: 10.37394/23202.2023.22.34
Recep Eryigit, Yilmaz Ar, Bulent Tugrul
Traditional machine learning methods have been extensively used in computer vision applications. However, recent improvements in computer technology have changed this trend. The dominance of deep learning methods in the field is observed when state-of-the-art studies are examined. This study employs traditional computer vision methods and deep learning to classify five different types of Trifolium seeds. Trifolium, the leading food for nutritious dairy products, plays an essential role in livestock in some parts of the world. First, an image data set consisting of 1903 images belonging to five different species of Trifolium was created. Descriptive and quantitative morphological features of each species are extracted using image-processing techniques. Then a feature matrix was created using eight different features. After feature selection and transformation, unnecessary and irrelevant features were removed from the data set to build more accurate and robust classification models. Four common and frequently applied classification algorithms created a prediction model in the seed data set. In addition, the same dataset was trained using VGG19, a convolutional neural network. Finally, the performance metrics of each classifier were computed and evaluated. The decision tree has the worst accuracy among the four traditional methods, 92.07%. On the other hand, Artificial Neural Network has the highest accuracy with 94.59%. As expected, VGG19 outperforms all traditional methods with 96.29% accuracy. However, as the results show, traditional methods can also produce results close to the deep learning methods.
{"title":"Classification of Trifolium Seeds by Computer Vision Methods","authors":"Recep Eryigit, Yilmaz Ar, Bulent Tugrul","doi":"10.37394/23202.2023.22.34","DOIUrl":"https://doi.org/10.37394/23202.2023.22.34","url":null,"abstract":"Traditional machine learning methods have been extensively used in computer vision applications. However, recent improvements in computer technology have changed this trend. The dominance of deep learning methods in the field is observed when state-of-the-art studies are examined. This study employs traditional computer vision methods and deep learning to classify five different types of Trifolium seeds. Trifolium, the leading food for nutritious dairy products, plays an essential role in livestock in some parts of the world. First, an image data set consisting of 1903 images belonging to five different species of Trifolium was created. Descriptive and quantitative morphological features of each species are extracted using image-processing techniques. Then a feature matrix was created using eight different features. After feature selection and transformation, unnecessary and irrelevant features were removed from the data set to build more accurate and robust classification models. Four common and frequently applied classification algorithms created a prediction model in the seed data set. In addition, the same dataset was trained using VGG19, a convolutional neural network. Finally, the performance metrics of each classifier were computed and evaluated. The decision tree has the worst accuracy among the four traditional methods, 92.07%. On the other hand, Artificial Neural Network has the highest accuracy with 94.59%. As expected, VGG19 outperforms all traditional methods with 96.29% accuracy. However, as the results show, traditional methods can also produce results close to the deep learning methods.","PeriodicalId":39422,"journal":{"name":"WSEAS Transactions on Systems and Control","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82385044","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：