Pub Date : 2022-10-18DOI: 10.1109/ICITEE56407.2022.9954091
I. Wirawan, I. M. G. Sunarya, I. M. D. Maysanjaya
This research contributes to the application of image processing in the optimization and automation of agricultural drones to modernize agricultural systems. This study aims to perform semantic segmentation of rice field bunds using UNet. The method proposed in this study starts from the dataset finalization stage, data preparation, and finally evaluates the segmentation model. The input from the UNet model will be an RGB image of a wet rice field with a resolution of 512 × 512 pixels which is the result of the frame extraction process and the output is a binary image of the predicted pixel of the rice field bund. Based on the results of the testing model that has been carried out on computers with Intel i7 processor, RTX 3070 Ti GPU, 32GB RAM, and 1 TB SSD, the UNet model underwent training with a dataset configuration of type split 1 (792 images of train set, 44 images of validation set, and 45 images of test set) and without going through the binarization stage has the highest performance with an average accuracy of 99% and an average segmentation time of 0.32 per second.
{"title":"Semantic Segmentation of Rice Field Bund on Unmanned Aerial Vehicle Image using UNet","authors":"I. Wirawan, I. M. G. Sunarya, I. M. D. Maysanjaya","doi":"10.1109/ICITEE56407.2022.9954091","DOIUrl":"https://doi.org/10.1109/ICITEE56407.2022.9954091","url":null,"abstract":"This research contributes to the application of image processing in the optimization and automation of agricultural drones to modernize agricultural systems. This study aims to perform semantic segmentation of rice field bunds using UNet. The method proposed in this study starts from the dataset finalization stage, data preparation, and finally evaluates the segmentation model. The input from the UNet model will be an RGB image of a wet rice field with a resolution of 512 × 512 pixels which is the result of the frame extraction process and the output is a binary image of the predicted pixel of the rice field bund. Based on the results of the testing model that has been carried out on computers with Intel i7 processor, RTX 3070 Ti GPU, 32GB RAM, and 1 TB SSD, the UNet model underwent training with a dataset configuration of type split 1 (792 images of train set, 44 images of validation set, and 45 images of test set) and without going through the binarization stage has the highest performance with an average accuracy of 99% and an average segmentation time of 0.32 per second.","PeriodicalId":246279,"journal":{"name":"2022 14th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124736996","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 : 2022-10-18DOI: 10.1109/ICITEE56407.2022.9954121
A. Surriani, O. Wahyunggoro, A. Cahyadi
Reinforcement learning (RL) is one of the most important algorithms for artificial intelligence. DDPG as continuous controller approach which can work at continuous and high dimensional data applies in this paper to solve nonlinear valve system. The aim of this paper is gaining analysis of the DDPG noise parameterization. Noise parameter addition is known to be able to increase the exploration ability of the algorithm. The noise parameterization is using the Ornstein-Uhlenbeck (OU) noise injection. This exploration investigation concerns to the algorithm’s performance. The evaluation measurement is based on the total reward to system during training. The result indicates that noise parameterization affects the performance of the algorithm. The comparisons show that the injection of OU noise for DDPG algorithm influences the total reward. The simulation find that the total reward that is achieved by DDPG with OU noise injection is higher than DDPG without OU noise injection at 317,810.
{"title":"Noise Parameterization of Continuous Deep Reinforcement Learning for a Class of Non-linear System","authors":"A. Surriani, O. Wahyunggoro, A. Cahyadi","doi":"10.1109/ICITEE56407.2022.9954121","DOIUrl":"https://doi.org/10.1109/ICITEE56407.2022.9954121","url":null,"abstract":"Reinforcement learning (RL) is one of the most important algorithms for artificial intelligence. DDPG as continuous controller approach which can work at continuous and high dimensional data applies in this paper to solve nonlinear valve system. The aim of this paper is gaining analysis of the DDPG noise parameterization. Noise parameter addition is known to be able to increase the exploration ability of the algorithm. The noise parameterization is using the Ornstein-Uhlenbeck (OU) noise injection. This exploration investigation concerns to the algorithm’s performance. The evaluation measurement is based on the total reward to system during training. The result indicates that noise parameterization affects the performance of the algorithm. The comparisons show that the injection of OU noise for DDPG algorithm influences the total reward. The simulation find that the total reward that is achieved by DDPG with OU noise injection is higher than DDPG without OU noise injection at 317,810.","PeriodicalId":246279,"journal":{"name":"2022 14th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115937830","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 : 2022-10-18DOI: 10.1109/ICITEE56407.2022.9954094
Umi Proboyekti, P. Santosa, R. Ferdiana
Trust perception is the reason for information use. Researchers defined trust perception through experiments to understand the factors that shape it. The factors that shape trust perception are proven to be reliable and valid through measurement. The study measured the reliability and validity of Trust Perception and Information Use during online information evaluation and the relationship between the two. With fifty-one academic librarians participating in a user study, this research aims to measure the reliability and validity of Trust Perception and Use using PLS-SEM and SmartPLS software. The measurement model and structural model assessment results show that the five indicators are reliable and valid to support Trust Perception as a construct, while Information Use is a single item. The relationship of both constructs is positively significant. The study’s result contributes Trust Perception construct and its indicators for evaluating informational websites provided by non-education institutions. Content designers may consider the indicators of trust perception as they design a website’s content. Researchers may use trust perception’s construct and indicators to relate them with other website factors to understand factors affecting user trust.
{"title":"Measuring Trust Perception during Information Evaluation","authors":"Umi Proboyekti, P. Santosa, R. Ferdiana","doi":"10.1109/ICITEE56407.2022.9954094","DOIUrl":"https://doi.org/10.1109/ICITEE56407.2022.9954094","url":null,"abstract":"Trust perception is the reason for information use. Researchers defined trust perception through experiments to understand the factors that shape it. The factors that shape trust perception are proven to be reliable and valid through measurement. The study measured the reliability and validity of Trust Perception and Information Use during online information evaluation and the relationship between the two. With fifty-one academic librarians participating in a user study, this research aims to measure the reliability and validity of Trust Perception and Use using PLS-SEM and SmartPLS software. The measurement model and structural model assessment results show that the five indicators are reliable and valid to support Trust Perception as a construct, while Information Use is a single item. The relationship of both constructs is positively significant. The study’s result contributes Trust Perception construct and its indicators for evaluating informational websites provided by non-education institutions. Content designers may consider the indicators of trust perception as they design a website’s content. Researchers may use trust perception’s construct and indicators to relate them with other website factors to understand factors affecting user trust.","PeriodicalId":246279,"journal":{"name":"2022 14th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114065510","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 : 2022-10-18DOI: 10.1109/ICITEE56407.2022.9954087
Michael Nato Andrety, A. Malik, Dzuhri Radityo Utomo, A. Cahyadi
Anti-surge controller has a very important role in industrial size compressor system to avoid the occurrence of a surge phenomenon. This anti-surge controller can be constructed using a component known as Active Magnetic Bearing (AMB), which can also provide a better efficiency for the overall compressor system compared the conventional bearing. The AMB consists of two components, a thrust magnetic bearing (TMB), and a radial magnetic bearing (RMB). The discussion presented in this paper will mainly focus on the design of the proposed RMB controller system, which is essential in AMB based anti-surge controller, for the industrial size compressor system. The RMB controller system consists of 3 main components, LQR controller, Kalman filter, and automatic compressor trip system. The RMB controller system helps to stabilize the rotor radial position and protect the compressor system when the rotor radial displacement is too far from its nominal value. The simulation result shows that the proposed system has a good performance to stabilize the rotor radial position. The simulation result also shows that the automatic compressor trip system can properly generate an appropriate output command when the rotor displacement is outside the permitted value.
{"title":"Design of Active Magnetic Bearing for Industrial Size Compressor System using Kalman Filter Based Optimal Controller","authors":"Michael Nato Andrety, A. Malik, Dzuhri Radityo Utomo, A. Cahyadi","doi":"10.1109/ICITEE56407.2022.9954087","DOIUrl":"https://doi.org/10.1109/ICITEE56407.2022.9954087","url":null,"abstract":"Anti-surge controller has a very important role in industrial size compressor system to avoid the occurrence of a surge phenomenon. This anti-surge controller can be constructed using a component known as Active Magnetic Bearing (AMB), which can also provide a better efficiency for the overall compressor system compared the conventional bearing. The AMB consists of two components, a thrust magnetic bearing (TMB), and a radial magnetic bearing (RMB). The discussion presented in this paper will mainly focus on the design of the proposed RMB controller system, which is essential in AMB based anti-surge controller, for the industrial size compressor system. The RMB controller system consists of 3 main components, LQR controller, Kalman filter, and automatic compressor trip system. The RMB controller system helps to stabilize the rotor radial position and protect the compressor system when the rotor radial displacement is too far from its nominal value. The simulation result shows that the proposed system has a good performance to stabilize the rotor radial position. The simulation result also shows that the automatic compressor trip system can properly generate an appropriate output command when the rotor displacement is outside the permitted value.","PeriodicalId":246279,"journal":{"name":"2022 14th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129137436","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 : 2022-10-18DOI: 10.1109/ICITEE56407.2022.9954108
Lailatul Mukarromah, P. Permatasari, E. Tridianto
The steam drum is one of the components in the boiler that functions to separate water from steam, before the production of dry steam in the superheater. To produce quality dry steam, the water level in the steam drum boiler must be maintained at NWL (Normally Water Level) conditions. To control the water level in the steam drum boiler, a stable control is needed and has a fast response, and is close to a real plant such as PID control. One method to determine control parameters is the Internal Model Control (IMC-PID) tuning method, the IMC-PID tuning method has a very effective performance as a controller, especially in the maximum overshoot and settling time performance parameters. To speed up the control system’s response so that it is by the desired set point, a feedback control strategy is combined with feedforward to overcome the disturbance that occurs. In this research, aims to model a steam drum level control system with several variations of filter factor ($lambda$) values are used as particular parameters in the Internal Model Control (IMC-PID) tuning method, it shows that the performance of the designed control system can realize the set point and deal with the given disturbance. From several variations of the filter factor ($lambda$) value, variation $lambda$=1 with parameter value Kp=0.860; $tau_{i}=14.07$ and $tau_{D}=14.54$ offers the best performance when dealing with changes in the set point and disturbances of pm 5%.
{"title":"Modeling of Level Control System using IMC-PID Tuning Method with Filter Tuning Factor Variation on Steam Drum Boiler of Power Plant","authors":"Lailatul Mukarromah, P. Permatasari, E. Tridianto","doi":"10.1109/ICITEE56407.2022.9954108","DOIUrl":"https://doi.org/10.1109/ICITEE56407.2022.9954108","url":null,"abstract":"The steam drum is one of the components in the boiler that functions to separate water from steam, before the production of dry steam in the superheater. To produce quality dry steam, the water level in the steam drum boiler must be maintained at NWL (Normally Water Level) conditions. To control the water level in the steam drum boiler, a stable control is needed and has a fast response, and is close to a real plant such as PID control. One method to determine control parameters is the Internal Model Control (IMC-PID) tuning method, the IMC-PID tuning method has a very effective performance as a controller, especially in the maximum overshoot and settling time performance parameters. To speed up the control system’s response so that it is by the desired set point, a feedback control strategy is combined with feedforward to overcome the disturbance that occurs. In this research, aims to model a steam drum level control system with several variations of filter factor ($lambda$) values are used as particular parameters in the Internal Model Control (IMC-PID) tuning method, it shows that the performance of the designed control system can realize the set point and deal with the given disturbance. From several variations of the filter factor ($lambda$) value, variation $lambda$=1 with parameter value Kp=0.860; $tau_{i}=14.07$ and $tau_{D}=14.54$ offers the best performance when dealing with changes in the set point and disturbances of pm 5%.","PeriodicalId":246279,"journal":{"name":"2022 14th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128765405","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 : 2022-10-18DOI: 10.1109/ICITEE56407.2022.9954099
Pankaj Kumar Sharma, Prashant Kumar, R. Ranjan
In this article, we have proposed a grounded memristor emulator model using CCII and VDIBA blocks. The proposed circuit also uses one resistor and one capacitor along with analog building blocks. The presented memristor emulator operates up to 25 MHz. The proposed memristor is simulated using Cadence Virtuoso 180 nm CMOS parameter. The proposed memristor works at ± 0.9 V and the power consumption is 2.4 mW. The adaptability of the memristor emulator during circuit implementation is tested by connecting the memristors in parallel.
{"title":"A High-Frequency Flux Controlled Grounded Memristor Emulator","authors":"Pankaj Kumar Sharma, Prashant Kumar, R. Ranjan","doi":"10.1109/ICITEE56407.2022.9954099","DOIUrl":"https://doi.org/10.1109/ICITEE56407.2022.9954099","url":null,"abstract":"In this article, we have proposed a grounded memristor emulator model using CCII and VDIBA blocks. The proposed circuit also uses one resistor and one capacitor along with analog building blocks. The presented memristor emulator operates up to 25 MHz. The proposed memristor is simulated using Cadence Virtuoso 180 nm CMOS parameter. The proposed memristor works at ± 0.9 V and the power consumption is 2.4 mW. The adaptability of the memristor emulator during circuit implementation is tested by connecting the memristors in parallel.","PeriodicalId":246279,"journal":{"name":"2022 14th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123741747","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 : 2022-10-18DOI: 10.1109/ICITEE56407.2022.9954077
Ja’Far Madani, Bobby Rian Dewangga, A. Cahyadi, S. Herdjunanto
Battery current estimation rises as there is a need to eliminate current sensor components in battery management system (BMS). Elimination of current sensors is intended to reduce the cost of BMS production. In addition, the elimination of current sensors can also reduce the total power consumption in the BMS. Instead of utilizing current sensors to read the current values, a current-estimation scheme is installed in the BMS. In this paper a current-estimation algorithm is proposed based on a simple battery model by updating the internal capacitance that changes over time based on a polynomial function of State of Charge - Open Circuit Voltage (SOC-OCV) relationship. The optimal order of the polynomial function is then sought in the hope of minimizing current estimation errors. To demonstrate the effectiveness of the proposed method, current estimation was performed for the pulsed-load test. The current estimation results are then compared to the current sensor readings. The results show that the current estimate is able to follow the trend of the current sensor readings.
{"title":"Parameter Optimization of Current Estimator for Lithium Polymer Battery (LiFePO4)","authors":"Ja’Far Madani, Bobby Rian Dewangga, A. Cahyadi, S. Herdjunanto","doi":"10.1109/ICITEE56407.2022.9954077","DOIUrl":"https://doi.org/10.1109/ICITEE56407.2022.9954077","url":null,"abstract":"Battery current estimation rises as there is a need to eliminate current sensor components in battery management system (BMS). Elimination of current sensors is intended to reduce the cost of BMS production. In addition, the elimination of current sensors can also reduce the total power consumption in the BMS. Instead of utilizing current sensors to read the current values, a current-estimation scheme is installed in the BMS. In this paper a current-estimation algorithm is proposed based on a simple battery model by updating the internal capacitance that changes over time based on a polynomial function of State of Charge - Open Circuit Voltage (SOC-OCV) relationship. The optimal order of the polynomial function is then sought in the hope of minimizing current estimation errors. To demonstrate the effectiveness of the proposed method, current estimation was performed for the pulsed-load test. The current estimation results are then compared to the current sensor readings. The results show that the current estimate is able to follow the trend of the current sensor readings.","PeriodicalId":246279,"journal":{"name":"2022 14th International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"115 18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126369846","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：