PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021最新文献
It has been observed that domestic household bins are still being manually collected by the municipality. This old method of trash removal has flaws. It is labour-intensive. In this paper, we design and implement a novel innovative domestic waste management system. To achieve this aim, specific objectives had to be achieved. These were to design and implement a motor driver controller (MDC), obstacle detection system (ODS), email notification system, trash status monitoring, internet time-based trigger (ITT), and finally, integrating all the systems together. The project was divided into two phases: the design phase and the integration phase. The finished prototype was tested and demonstrated to function according to the design specifications. When the bin is empty, the system remains at the origin. Only when the bin is full that the system moves to the disposal point. When an obstacle is detected, it stops and sends a push notification via email to the user. Once the obstacle is removed, the system continues its path until it reaches its destination. The design objectives were achieved.
{"title":"Smart Waste Management System: A Novel Approach to Waste Collection in Twenty-First Century Smart City","authors":"Diedricks Sinvula, Joshua A. Abolarinwa","doi":"10.58190/icat.2023.16","DOIUrl":"https://doi.org/10.58190/icat.2023.16","url":null,"abstract":"It has been observed that domestic household bins are still being manually collected by the municipality. This old method of trash removal has flaws. It is labour-intensive. In this paper, we design and implement a novel innovative domestic waste management system. To achieve this aim, specific objectives had to be achieved. These were to design and implement a motor driver controller (MDC), obstacle detection system (ODS), email notification system, trash status monitoring, internet time-based trigger (ITT), and finally, integrating all the systems together. The project was divided into two phases: the design phase and the integration phase. The finished prototype was tested and demonstrated to function according to the design specifications. When the bin is empty, the system remains at the origin. Only when the bin is full that the system moves to the disposal point. When an obstacle is detected, it stops and sends a push notification via email to the user. Once the obstacle is removed, the system continues its path until it reaches its destination. The design objectives were achieved.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969523","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 quantity of solid wastes (domestic, agricultural or industrial) throughout the world is increasing and their elimination becomes more complex. However, recycling industrial by-product materials waste has become an attractive topic of materials research in civil engineering. These industrial by-product materials waste must be managed responsibly to insure a clean environment. The use of waste in fired clay brick production may also save clay from avoidable depletion and reduce the environmental contamination by waste, contributing to sustainability. The aim of this research is to study the influence of Ground Cork Waste (GCW) on the thermo-mechanical properties of fired clay brick. For this purpose, increasing amounts of Cork Waste (0, 5, 10 and 15% of weight) with a grain size under 1.00 mm were mixed with a clay to produce clay bricks by pressing, drying and then firing at 900°C. The results obtained demonstrate that an increase in the content of CW leads to a significant increase in apparent porosity of fired clay brick. The compressive strength and thermal conductivity of the samples decreased with the increase in content of (GCW).
{"title":"Thermo-mechanical properties of fired clay brick incorporating industrial by-product materials cork waste","authors":"BOUZEROURA MANSOUR, SEBBAH YACINE, DJAFRI GHANI, CHELOUAH NASSER","doi":"10.58190/icat.2023.38","DOIUrl":"https://doi.org/10.58190/icat.2023.38","url":null,"abstract":"The quantity of solid wastes (domestic, agricultural or industrial) throughout the world is increasing and their elimination becomes more complex. However, recycling industrial by-product materials waste has become an attractive topic of materials research in civil engineering. These industrial by-product materials waste must be managed responsibly to insure a clean environment. The use of waste in fired clay brick production may also save clay from avoidable depletion and reduce the environmental contamination by waste, contributing to sustainability. The aim of this research is to study the influence of Ground Cork Waste (GCW) on the thermo-mechanical properties of fired clay brick. For this purpose, increasing amounts of Cork Waste (0, 5, 10 and 15% of weight) with a grain size under 1.00 mm were mixed with a clay to produce clay bricks by pressing, drying and then firing at 900°C. The results obtained demonstrate that an increase in the content of CW leads to a significant increase in apparent porosity of fired clay brick. The compressive strength and thermal conductivity of the samples decreased with the increase in content of (GCW).","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969525","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}
Using the Peltier effect for power generation is a relatively new technology that has been gaining attention in recent years. Using Peltier chips for power generation in EVs is an interesting approach that has the potential to provide a renewable and sustainable source of energy. By using the heat generated by the car's components during operation, the Peltier chips can generate electricity, which can be used to charge the battery. This approach has several benefits, including reducing the reliance on fossil fuels, improving the efficiency of the vehicle, and reducing the carbon footprint of the EV. The Peltier effect is a thermoelectric phenomenon that converts temperature differences into electrical energy to generate enough power to recharge an electric vehicle battery, several Peltier chips can be connected in series, and a converter can be used to convert the generated voltage into a sufficient voltage and can charge the battery. In this paper, an in-depth exploration will be conducted to evaluate the overall effectiveness and efficiency of Pelter chips, with a particular focus on simulating the utilization of these chips through the utilization of Proteus software.
{"title":"Utilization of Peltier Chipsets in Electric Vehicles to Charge Li-Ion Batteries","authors":"Abdalrahman Skheta, Onur Akar","doi":"10.58190/icat.2023.27","DOIUrl":"https://doi.org/10.58190/icat.2023.27","url":null,"abstract":"Using the Peltier effect for power generation is a relatively new technology that has been gaining attention in recent years. Using Peltier chips for power generation in EVs is an interesting approach that has the potential to provide a renewable and sustainable source of energy. By using the heat generated by the car's components during operation, the Peltier chips can generate electricity, which can be used to charge the battery. This approach has several benefits, including reducing the reliance on fossil fuels, improving the efficiency of the vehicle, and reducing the carbon footprint of the EV. The Peltier effect is a thermoelectric phenomenon that converts temperature differences into electrical energy to generate enough power to recharge an electric vehicle battery, several Peltier chips can be connected in series, and a converter can be used to convert the generated voltage into a sufficient voltage and can charge the battery. In this paper, an in-depth exploration will be conducted to evaluate the overall effectiveness and efficiency of Pelter chips, with a particular focus on simulating the utilization of these chips through the utilization of Proteus software.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969383","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}
There is a large number of power stations suffering from fatigue failures of the steam turbine blades. The steam turbine blades are also subjected to steam flow bending, centrifugal loading, vibration response, and structural mistuning. These mentioned factors significantly contribute to the fatigue failure of the steam turbine blades. Low-Pressure (LP) steam turbines experience premature blade and disk failures due to the stress concentrations at the blade root area of its bladed disk. Driven by the problems encountered by the steam power plant electricity generating utilities with regards to steam turbine blades fatigue failure, this study of the mistuned steam turbine blades subjected to variation in blade geometry will be of great significance to the electricity generation industry. A simplified, scaled-down mistuned steam turbine bladed disk model was developed using ABAQUS finite element analysis (FEA) software. Acquisition of the vibration characteristics and steady-state stress response of the disk models was performed through FEA. Thereafter, numerical stress distributions were acquired, and the model was subsequently exported to Fe-Safe software for fatigue life calculations based on centrifugal and harmonic sinusoidal pressure loading. The vibration characteristics and the response of the variation steam turbine geometric blade was conducted. The FEA natural frequencies compared well with published literature of the real steam turbines indicating reliability of the developed FEA model. The study found that the fatigue life is most sensitive to changes in blade length, followed by the width, and then the thickness, in this order. The analytical life cycles and Fe-Safe software shows the percentage difference of less than 4.86%. This concludes that the developed numerical methodology can be used for real-life mistuned steam turbine blades subjected to variations in blade geometry.
{"title":"Prediction of fatigue life of mistuned steam turbine blades subjected to variations in blade geometry","authors":"Makgwantsha Mashiachidi, Dawood Desai","doi":"10.58190/icat.2023.22","DOIUrl":"https://doi.org/10.58190/icat.2023.22","url":null,"abstract":"There is a large number of power stations suffering from fatigue failures of the steam turbine blades. The steam turbine blades are also subjected to steam flow bending, centrifugal loading, vibration response, and structural mistuning. These mentioned factors significantly contribute to the fatigue failure of the steam turbine blades. Low-Pressure (LP) steam turbines experience premature blade and disk failures due to the stress concentrations at the blade root area of its bladed disk. Driven by the problems encountered by the steam power plant electricity generating utilities with regards to steam turbine blades fatigue failure, this study of the mistuned steam turbine blades subjected to variation in blade geometry will be of great significance to the electricity generation industry. A simplified, scaled-down mistuned steam turbine bladed disk model was developed using ABAQUS finite element analysis (FEA) software. Acquisition of the vibration characteristics and steady-state stress response of the disk models was performed through FEA. Thereafter, numerical stress distributions were acquired, and the model was subsequently exported to Fe-Safe software for fatigue life calculations based on centrifugal and harmonic sinusoidal pressure loading. The vibration characteristics and the response of the variation steam turbine geometric blade was conducted. The FEA natural frequencies compared well with published literature of the real steam turbines indicating reliability of the developed FEA model. The study found that the fatigue life is most sensitive to changes in blade length, followed by the width, and then the thickness, in this order. The analytical life cycles and Fe-Safe software shows the percentage difference of less than 4.86%. This concludes that the developed numerical methodology can be used for real-life mistuned steam turbine blades subjected to variations in blade geometry.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"289 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969385","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}
To prevent unplanned machine downtime in production, machine conditions can be monitored and even predicted using condition and failure models based on current machine and process data. As most of these models are data-intensive, machine users often do not have enough data to develop these models themselves and want to collaborate with other companies. Since these models often require critical and classified machine and process data, which could be extracted from the models using attacks such as model inversion, sharing existing models between companies is not an option as it leaves one party vulnerable. Privacy preserving technologies such as homomorphic encryption, differential privacy, federated learning and secure multi-party computation can help overcome this problem. With the help of these approaches, there is no need to transmit sensitive data unencrypted to third parties in order to cooperate and take advantage of high-performance models. The aim of this paper is to first summarize the current state of research on privacy-preserving technologies in production, and then to provide a simple to use evaluation method and criteria. The focus is on enabling production workers to make informed decisions and exploit the full potential of existing data without the need for prior knowledge of privacy-preserving technologies. Finally, the evaluation method is validated using two example use cases in a production environment and the results are discussed.
{"title":"Evaluation Framework for the Use of Privacy Preserving Technologies for Production Data","authors":"Lennard Sielaff, Ruben Hetfleisch, Michael Rader","doi":"10.58190/icat.2023.33","DOIUrl":"https://doi.org/10.58190/icat.2023.33","url":null,"abstract":"To prevent unplanned machine downtime in production, machine conditions can be monitored and even predicted using condition and failure models based on current machine and process data. As most of these models are data-intensive, machine users often do not have enough data to develop these models themselves and want to collaborate with other companies. Since these models often require critical and classified machine and process data, which could be extracted from the models using attacks such as model inversion, sharing existing models between companies is not an option as it leaves one party vulnerable. Privacy preserving technologies such as homomorphic encryption, differential privacy, federated learning and secure multi-party computation can help overcome this problem. With the help of these approaches, there is no need to transmit sensitive data unencrypted to third parties in order to cooperate and take advantage of high-performance models. The aim of this paper is to first summarize the current state of research on privacy-preserving technologies in production, and then to provide a simple to use evaluation method and criteria. The focus is on enabling production workers to make informed decisions and exploit the full potential of existing data without the need for prior knowledge of privacy-preserving technologies. Finally, the evaluation method is validated using two example use cases in a production environment and the results are discussed.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969515","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 increasing accessibility and affordability of unmanned aerial vehicles (UAVs), commonly known as drones, have led to the emergence of malicious users. In precaution to this perceived threat, various anti-UAV systems are being developed, including electro-optical systems utilizing cameras. It is possible to detect UAVs from images using various machine learning methods. However, the similarity between UAVs and birds poses a challenge, as birds can be mistakenly identified as UAVs, leading to false alarms in a security system. In order to avoid this problem, this study provided the classification of birds and unmanned aerial vehicles over images using deep learning methods. In this study, a data set consisting of 400 birds and 428 UAV images was used. The data were divided into 70% for training, 30% for testing and validation purposes. Three different deep learning models, based on DenseNet, VGG16, and VGG19 architectures, were trained using transfer learning techniques, and their performances were compared. Experimental results on the test data showed an accuracy of 94.64% with the DenseNet model, 89.67% with the VGG16 model, and 90.67% with the VGG19 model.
{"title":"Classification of Unmanned Aerial Vehicle and Bird Images Using Deep Transfer Learning Methods","authors":"Ahmet Özdemir, İlker Ali OZKAN","doi":"10.58190/icat.2023.37","DOIUrl":"https://doi.org/10.58190/icat.2023.37","url":null,"abstract":"The increasing accessibility and affordability of unmanned aerial vehicles (UAVs), commonly known as drones, have led to the emergence of malicious users. In precaution to this perceived threat, various anti-UAV systems are being developed, including electro-optical systems utilizing cameras. It is possible to detect UAVs from images using various machine learning methods. However, the similarity between UAVs and birds poses a challenge, as birds can be mistakenly identified as UAVs, leading to false alarms in a security system. In order to avoid this problem, this study provided the classification of birds and unmanned aerial vehicles over images using deep learning methods. In this study, a data set consisting of 400 birds and 428 UAV images was used. The data were divided into 70% for training, 30% for testing and validation purposes. Three different deep learning models, based on DenseNet, VGG16, and VGG19 architectures, were trained using transfer learning techniques, and their performances were compared. Experimental results on the test data showed an accuracy of 94.64% with the DenseNet model, 89.67% with the VGG16 model, and 90.67% with the VGG19 model.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969519","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}
In recent times, the need for the use of image classification techniques of machine learning to solve worldly problems in various areas such as agriculture, the health sector, and tourism is rocketing up day by day. Traditionally, one of the most used techniques in image classification is the use of deep neural networks called convolution neural networks (CNN). To come up with a good network model, one needs to have an enormous quantity of data in the form of images and design a network model from scratch in a trial-and-error way. This not only takes a lot of time but also requires very powerful computation equipment such as graphical processing units (GPU). To overcome such barriers, a machine learning technique called transfer learning enables the use of already trained network models in the form of fine-tuning them to solve related issues. In this work, the 2014 ImageNet winner model called Vgg16 was adopted to classify landscape images in the Intel dataset. The dataset contains 5 categories of images namely buildings, forest, glacier, mountain, sea, and street. The performance of Vgg16 was compared to that of a 7-layer ordinary convolution neural network and the results showed that transfer learning with Vgg16 outperformed the ordinary network by 90.1% for Vgg16 compared to 62.5% for the ordinary convolutional neural network model.
{"title":"Utilizing Transfer Learning on Landscape Image Classification Using the VGG16 Model","authors":"Abubakar MAYANJA, İlker Ali ÖZKAN, Şakir TAŞDEMİR","doi":"10.58190/icat.2023.20","DOIUrl":"https://doi.org/10.58190/icat.2023.20","url":null,"abstract":"In recent times, the need for the use of image classification techniques of machine learning to solve worldly problems in various areas such as agriculture, the health sector, and tourism is rocketing up day by day. Traditionally, one of the most used techniques in image classification is the use of deep neural networks called convolution neural networks (CNN). To come up with a good network model, one needs to have an enormous quantity of data in the form of images and design a network model from scratch in a trial-and-error way. This not only takes a lot of time but also requires very powerful computation equipment such as graphical processing units (GPU). To overcome such barriers, a machine learning technique called transfer learning enables the use of already trained network models in the form of fine-tuning them to solve related issues. In this work, the 2014 ImageNet winner model called Vgg16 was adopted to classify landscape images in the Intel dataset. The dataset contains 5 categories of images namely buildings, forest, glacier, mountain, sea, and street. The performance of Vgg16 was compared to that of a 7-layer ordinary convolution neural network and the results showed that transfer learning with Vgg16 outperformed the ordinary network by 90.1% for Vgg16 compared to 62.5% for the ordinary convolutional neural network model.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969521","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 STMAS system is intended to imitate a soccer team and its behavior; we believe it can be used effectively as a test bed for multi-agent systems. It is constructed utilizing distributed agents that interact, communicate, and negotiate with each other to achieve the team objectives. It is based on the Jade simulation platform. The system is tested and compared to a pure soccer team using multiple MAS techniques. The results demonstrated that applying MAS techniques of negotiation and task distribution improves team performance, and STMAS is offered as an efficient test bed for new and distinct MAS techniques with varied scenario experiments. In addition, a mathematical model is created to compare the simulation results. Overall, STMAS provides a versatile and efficient MAS simulation and evaluation test bed. It is an excellent platform for comparing and evaluating various MAS approaches.
{"title":"Using a Soccer team as a test bed for multi-agent systems simulation","authors":"Areen Naji, Rashid Jayousi, Amjad Rattrout","doi":"10.58190/icat.2023.26","DOIUrl":"https://doi.org/10.58190/icat.2023.26","url":null,"abstract":"The STMAS system is intended to imitate a soccer team and its behavior; we believe it can be used effectively as a test bed for multi-agent systems. It is constructed utilizing distributed agents that interact, communicate, and negotiate with each other to achieve the team objectives. It is based on the Jade simulation platform. The system is tested and compared to a pure soccer team using multiple MAS techniques. The results demonstrated that applying MAS techniques of negotiation and task distribution improves team performance, and STMAS is offered as an efficient test bed for new and distinct MAS techniques with varied scenario experiments. In addition, a mathematical model is created to compare the simulation results. Overall, STMAS provides a versatile and efficient MAS simulation and evaluation test bed. It is an excellent platform for comparing and evaluating various MAS approaches.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969379","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}
In our age, the usage areas of artificial intelligence have increased considerably. These areas were particularly concerned with the correct predictability of future data using available data. It has become necessary to work on various machine learning algorithms to be used in the calculations of the resolver circuit, which is a feedback element used for tracking the position and position information of the electric motor unit used in various vehicles. The use of machine learning algorithms in the design and implementation of the resolver circuit, which is one of the most important elements of electric motor designs, will shed light on future studies. In this study, it is focused on the use of machine learning algorithms in the calculation of the resolver circuit, position and position information and the performance differences between each other. In this study, LSTM (Long Short Term Memory) and Reinforcement Learning (RL) algorithms were compared. While comparing these algorithms, the types of LSTM and RL algorithms were also studied and compared. As a result of the results obtained, it was aimed that the motor designs would be less costly, and the results obtained in terms of more reliable motor position and position information to be used were promising. In addition, with this study, a basis was created for working on machine learning algorithms in the calculation of different parameters. With this study, a great way has been achieved in integrating algorithms used in electric vehicles, which are quite obsolete today, into AI-based algorithms.
{"title":"Development of Resolver Circuit with Long Short Term Memory and Reinforcement Learning Algorithms","authors":"Yusuf Çağlayan","doi":"10.58190/icat.2023.23","DOIUrl":"https://doi.org/10.58190/icat.2023.23","url":null,"abstract":"In our age, the usage areas of artificial intelligence have increased considerably. These areas were particularly concerned with the correct predictability of future data using available data. It has become necessary to work on various machine learning algorithms to be used in the calculations of the resolver circuit, which is a feedback element used for tracking the position and position information of the electric motor unit used in various vehicles. The use of machine learning algorithms in the design and implementation of the resolver circuit, which is one of the most important elements of electric motor designs, will shed light on future studies. In this study, it is focused on the use of machine learning algorithms in the calculation of the resolver circuit, position and position information and the performance differences between each other. In this study, LSTM (Long Short Term Memory) and Reinforcement Learning (RL) algorithms were compared. While comparing these algorithms, the types of LSTM and RL algorithms were also studied and compared. As a result of the results obtained, it was aimed that the motor designs would be less costly, and the results obtained in terms of more reliable motor position and position information to be used were promising. In addition, with this study, a basis was created for working on machine learning algorithms in the calculation of different parameters. With this study, a great way has been achieved in integrating algorithms used in electric vehicles, which are quite obsolete today, into AI-based algorithms.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969382","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}
Sleep, as an indispensable element of human life, is accepted as one of the main sources of health, vitality and productivity. There are many factors that affect sleep health. Stress level, irregularity of sleep patterns and excessive use of technological devices can be given as examples. Sleep health can be determined by analyzing various variables about sleep. Sleep health can be determined by using these variables with machine learning methods. For this purpose, a dataset containing 374 rows of data and 13 features was used in this study. Sleep disorder conditions can be classified as None, Sleep Apnea, and Insomnia using 12 features. Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR) and k Nearest Neighbor (kNN) methods were used for classification. Classification success was 91.66% from the RF model, 90.27% from the SVM model, 90.27% from the LR model and 87.50% from the kNN model. In order to analyze which feature is more effective in classification processes, box plot and correlation analysis methods were used. As a result of the analyzes, it was determined that the body mass index has the greatest effect on the determination of sleep disorder.
{"title":"Prediction of Sleep Health Status, Visualization and Analysis of Data","authors":"Yavuz Selim Taspinar, Ilkay Cinar","doi":"10.58190/icat.2023.13","DOIUrl":"https://doi.org/10.58190/icat.2023.13","url":null,"abstract":"Sleep, as an indispensable element of human life, is accepted as one of the main sources of health, vitality and productivity. There are many factors that affect sleep health. Stress level, irregularity of sleep patterns and excessive use of technological devices can be given as examples. Sleep health can be determined by analyzing various variables about sleep. Sleep health can be determined by using these variables with machine learning methods. For this purpose, a dataset containing 374 rows of data and 13 features was used in this study. Sleep disorder conditions can be classified as None, Sleep Apnea, and Insomnia using 12 features. Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR) and k Nearest Neighbor (kNN) methods were used for classification. Classification success was 91.66% from the RF model, 90.27% from the SVM model, 90.27% from the LR model and 87.50% from the kNN model. In order to analyze which feature is more effective in classification processes, box plot and correlation analysis methods were used. As a result of the analyzes, it was determined that the body mass index has the greatest effect on the determination of sleep disorder.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"276 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86363878","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}
PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021
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：