Murat Erhan ÇİMEN, Zeynep GARİP, Yaprak YALÇIN, Mustafa KUTLU, Ali Fuat BOZ
{"title":"Self Adaptive Methods for Learning Rate Parameter of Q-Learning Algorithm","authors":"Murat Erhan ÇİMEN, Zeynep GARİP, Yaprak YALÇIN, Mustafa KUTLU, Ali Fuat BOZ","doi":"10.38016/jista.1250782","DOIUrl":"https://doi.org/10.38016/jista.1250782","url":null,"abstract":"Machine learning methods can generally be categorized as supervised, unsupervised and reinforcement learning. One of these methods, Q learning algorithm in reinforcement learning, is an algorithm that can interact with the environment and learn from the environment and produce actions accordingly. In this study, eight different on-line methods have been proposed to determine online the value of the learning parameter in the Q learning algorithm depending on different situations. In order to test the performance of the proposed methods, these algorithms are applied to Frozen Lake and Car Pole systems and the results are compared graphically and statistically. When the obtained results are examined, Method 1 has produced better performance for Frozen Lake, which is a discrete system, while Method 7 has produced better results for the Cart Pole System, which is a continuous system.","PeriodicalId":486116,"journal":{"name":"Zeki sistemler teori ve uygulamaları dergisi","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135958352","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 Real-Time Location System Design for Production Facilities Working under COVID-19 Pandemic Precautions","authors":"Sena KIR","doi":"10.38016/jista.1015515","DOIUrl":"https://doi.org/10.38016/jista.1015515","url":null,"abstract":"By reason of the COVID-19 pandemic, essential digital transformations are taking place in many areas of business life. Although the most important one of these transformations is due to the widespread use of the remote working model, the production sector does not have the opportunity to switch to such a model completely. Therefore, it is inevitable to maintain social distance to prevent the spread of COVID-19 while working in production facilities. In this study, a real-time location system (RTLS) model is proposed to keep track of social distance in production facilities and to ensure occupational health safety (OHS) at the same time. Since the social distance rule is essential for every production facility, the most important feature of the proposed system is that it can easily be integrated into the standard personnel tracking system in almost every enterprise. Besides, the proposed RTLS is designed as an efficient system based on ultra-wideband and radio-frequency identification, which can operate as a closed-loop monitoring system within itself. An adequately installed RTLS can monitor the position of employees in real-time and provides to intervene in the situation instantly when necessary. In case of a violation of social distance or a situation against OHS, it can be prevented instantly by the proposed system. It is also a useful model in the management of emergencies.","PeriodicalId":486116,"journal":{"name":"Zeki sistemler teori ve uygulamaları dergisi","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135598691","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}