Pub Date : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624294
Riky Tri Yunardi, E. Sutanto, Aji Akbar Firdaus, Elsyea Adia Tunggadewi, Hammam Ali, Silvi Nurwahyuni
Electrical equipment protection system is required to maintain electrical equipment. A detection system is needed that handles specific protection and performs monitoring. One of the electrical equipment protection systems which detect leakage current. The residual current device (RCD) circuit is a circuit that detects leakage current using a coil. The output value of the RCD circuit is the induced voltage. This study describes the development of an internet of things-based leakage current monitoring system is implemented on three different electrical loads. Electrical loads using the lamps with the power of 3, 5, and 9 watts. The microcontroller is used to process the induced voltage value data and Wi-Fi module is used to connect to the Internet network and database. Then, we use a database of Blynk server as an online monitoring system. System test results show that the leakage current monitoring system to electrical load with different loads can work well with the threshold voltage as a set-point.
{"title":"Leakage Current Monitoring for Electrical Loads Based on Internet of Things","authors":"Riky Tri Yunardi, E. Sutanto, Aji Akbar Firdaus, Elsyea Adia Tunggadewi, Hammam Ali, Silvi Nurwahyuni","doi":"10.23919/eecsi53397.2021.9624294","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624294","url":null,"abstract":"Electrical equipment protection system is required to maintain electrical equipment. A detection system is needed that handles specific protection and performs monitoring. One of the electrical equipment protection systems which detect leakage current. The residual current device (RCD) circuit is a circuit that detects leakage current using a coil. The output value of the RCD circuit is the induced voltage. This study describes the development of an internet of things-based leakage current monitoring system is implemented on three different electrical loads. Electrical loads using the lamps with the power of 3, 5, and 9 watts. The microcontroller is used to process the induced voltage value data and Wi-Fi module is used to connect to the Internet network and database. Then, we use a database of Blynk server as an online monitoring system. System test results show that the leakage current monitoring system to electrical load with different loads can work well with the threshold voltage as a set-point.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125853837","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624244
Muhammad Khosyi'in, E. N. Budisusila, Sri Arttini Dwi Prasetyowati, B. Suprapto, Z. Nawawi
The autonomous vehicle navigation system is heavily dependent on the use of GPS sensors. The poor accuracy of GPS sensors can be circumvented by combining other sensors using a Kalman filter-based method. Combining GPS and IMU sensors or other sensors is an option because of the relatively low cost. The use of controllers to build an autonomous vehicle navigation system becomes an important thing, so the controller devices used must have excellent performance, and it is found in UA V technology with autopilot-based controllers. The sensor combination method is carried out by combining the IMU sensor on the pixhawk 2.1 controller module with the Here2 GPS/GNSS Module, which is expected to make autonomous vehicles' position and heading orientation more accurate. The initial test results show that the navigation system accuracy is very good with the orientation angle towards the vehicle as expected. However, there was a problem in sending data from the vehicle to the ground station via telemetry radio due to distance and buildings constraints.
{"title":"Design of Autonomous Vehicle Navigation Using GNSS Based on Pixhawk 2.1","authors":"Muhammad Khosyi'in, E. N. Budisusila, Sri Arttini Dwi Prasetyowati, B. Suprapto, Z. Nawawi","doi":"10.23919/eecsi53397.2021.9624244","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624244","url":null,"abstract":"The autonomous vehicle navigation system is heavily dependent on the use of GPS sensors. The poor accuracy of GPS sensors can be circumvented by combining other sensors using a Kalman filter-based method. Combining GPS and IMU sensors or other sensors is an option because of the relatively low cost. The use of controllers to build an autonomous vehicle navigation system becomes an important thing, so the controller devices used must have excellent performance, and it is found in UA V technology with autopilot-based controllers. The sensor combination method is carried out by combining the IMU sensor on the pixhawk 2.1 controller module with the Here2 GPS/GNSS Module, which is expected to make autonomous vehicles' position and heading orientation more accurate. The initial test results show that the navigation system accuracy is very good with the orientation angle towards the vehicle as expected. However, there was a problem in sending data from the vehicle to the ground station via telemetry radio due to distance and buildings constraints.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125467724","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624270
L. Subiyanto, A. Arfianto, S. Alfuat, D. P. Riananda, E. Supriyanto, F. Nofandi, T. Santoso, N. Gunantara, V. Ardhana
The potential of fish in the sea is a hope for fishers. During fishing, fishers must go around and map the fishing location because the distance and direction of the ship to the fishing location is not yet known accurately. Fishers only rely on the experience and information from other fishers to find out the location of fish distribution, and this will cause boat fuel losses because of the uncertain goals. In this research will shown the making process of the design of mobile navigation applications to find the location of the fish distribution. The device works based on information data in the form of latitude and longitude data from the Center for Marine Research and Observation. By entering the fish distribution data, the distance and direction of the location can be known. Android mobile application called Mobile Virtual Assistant (MVA) works by using smartphone GPS data, maps, and gyroscope compass sensors to locate fish distribution and data analysis will be compared with the Android application “Polaris Navigation” to find out the coordinates. From 10 tests, the Android Virtual Mobile Assistant application successfully headed to the destination location with a different accuracy of 24 meters from the Mobile Navigation Apps coordinate point detector. So it can be concluded that the android mobile application that is made can read the coordinates accurately.
{"title":"Mobile Application for Unmanned Ship Monitoring Based on LoRA Communication","authors":"L. Subiyanto, A. Arfianto, S. Alfuat, D. P. Riananda, E. Supriyanto, F. Nofandi, T. Santoso, N. Gunantara, V. Ardhana","doi":"10.23919/eecsi53397.2021.9624270","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624270","url":null,"abstract":"The potential of fish in the sea is a hope for fishers. During fishing, fishers must go around and map the fishing location because the distance and direction of the ship to the fishing location is not yet known accurately. Fishers only rely on the experience and information from other fishers to find out the location of fish distribution, and this will cause boat fuel losses because of the uncertain goals. In this research will shown the making process of the design of mobile navigation applications to find the location of the fish distribution. The device works based on information data in the form of latitude and longitude data from the Center for Marine Research and Observation. By entering the fish distribution data, the distance and direction of the location can be known. Android mobile application called Mobile Virtual Assistant (MVA) works by using smartphone GPS data, maps, and gyroscope compass sensors to locate fish distribution and data analysis will be compared with the Android application “Polaris Navigation” to find out the coordinates. From 10 tests, the Android Virtual Mobile Assistant application successfully headed to the destination location with a different accuracy of 24 meters from the Mobile Navigation Apps coordinate point detector. So it can be concluded that the android mobile application that is made can read the coordinates accurately.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116112379","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624267
A. A. Nugroho, Muhammad Khosyi'in, Bustanul Arifin, B. Suprapto, Muhamad Haddin, Z. Nawawi
Performance of the switched reluctance motor at starting depends on the current and hence the voltage applied to the motor. This paper will find the different performance of Switched Reluctance Motor both using hysteresis current control and the voltage control to start the motor at no load and a certain load. The use of reluctance motors is due to the simple motor construction, no magnetic parts, ruggedness, high-speed capability, high torque to inertia ratio although there are disadvantages such as vibration and complicated strategy to control the converter to drive the motor. The speed achieved, current, and torque will be identified using Matlab Simulink for hysteresis current regulation by using magnetic current reference and hysteresis current limiter at a predetermined value. The voltage control got better performance compared to hysteresis current control while the hysteresis current control achieved safe and smooth current, but lower performance.
{"title":"Load Effect on Switched Reluctance Motor Using Hysteresis Current and Voltage Control","authors":"A. A. Nugroho, Muhammad Khosyi'in, Bustanul Arifin, B. Suprapto, Muhamad Haddin, Z. Nawawi","doi":"10.23919/eecsi53397.2021.9624267","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624267","url":null,"abstract":"Performance of the switched reluctance motor at starting depends on the current and hence the voltage applied to the motor. This paper will find the different performance of Switched Reluctance Motor both using hysteresis current control and the voltage control to start the motor at no load and a certain load. The use of reluctance motors is due to the simple motor construction, no magnetic parts, ruggedness, high-speed capability, high torque to inertia ratio although there are disadvantages such as vibration and complicated strategy to control the converter to drive the motor. The speed achieved, current, and torque will be identified using Matlab Simulink for hysteresis current regulation by using magnetic current reference and hysteresis current limiter at a predetermined value. The voltage control got better performance compared to hysteresis current control while the hysteresis current control achieved safe and smooth current, but lower performance.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115858617","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624313
E. N. Budisusila, Muhammad Khosyi'in, S. Prasetyowati, B. Suprapto, Z. Nawawi
Autonomous vehicles need sensors to detect the surroundings of the vehicle, especially if there are obstructions that could harm the vehicle or the object itself. The goal is to avoid accidents by detecting as early as possible if there are obstacles. In this study, a series of ultrasonic sensors are used and placed in strategic positions around the vehicle. They are placed in front, in side and in rear of vehicle. When the sensor detects an object, each sensor provides information on the existence of the object in the form of a detection point. These points are still formed as detection points as the results of individual detection from each sensor. In order to integrate all the resulting points, it is necessary to establish a comprehensive detection pattern, to provide information about the safe distance of the vehicle from surrounding objects. The sensors are connected to a programmable microcontroller unit to monitor and control the transmitted signal and sensor detection results. The signal obtained by the microcontroller is fed to the computer unit through the serial port, which is then read using the Data Stream to be displayed on the monitor screen. With this method, the data will be reprocessed to display an integrated detection pattern from all sensors graphically. There are two kinds of graphical pattern formed, spider web pattern and bar pattern.
{"title":"Ultrasonic Multi-Sensor Detection Patterns On Autonomous Vehicles Using Data Stream Method","authors":"E. N. Budisusila, Muhammad Khosyi'in, S. Prasetyowati, B. Suprapto, Z. Nawawi","doi":"10.23919/eecsi53397.2021.9624313","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624313","url":null,"abstract":"Autonomous vehicles need sensors to detect the surroundings of the vehicle, especially if there are obstructions that could harm the vehicle or the object itself. The goal is to avoid accidents by detecting as early as possible if there are obstacles. In this study, a series of ultrasonic sensors are used and placed in strategic positions around the vehicle. They are placed in front, in side and in rear of vehicle. When the sensor detects an object, each sensor provides information on the existence of the object in the form of a detection point. These points are still formed as detection points as the results of individual detection from each sensor. In order to integrate all the resulting points, it is necessary to establish a comprehensive detection pattern, to provide information about the safe distance of the vehicle from surrounding objects. The sensors are connected to a programmable microcontroller unit to monitor and control the transmitted signal and sensor detection results. The signal obtained by the microcontroller is fed to the computer unit through the serial port, which is then read using the Data Stream to be displayed on the monitor screen. With this method, the data will be reprocessed to display an integrated detection pattern from all sensors graphically. There are two kinds of graphical pattern formed, spider web pattern and bar pattern.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"31 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120983751","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624304
Sarah Kamil, L. Muhammed
Arrhythmia is a heart condition that occurs due to abnormalities in the heartbeat, which means that the heart's electrical signals do not work properly, resulting in an irregular heartbeat or rhythm and thus defeating the pumping of blood. Some cases of arrhythmia are not considered serious, while others are very dangerous, life-threatening, and cause death in a short period of time. In the clinical routine, cardiac arrhythmia detection is performed by electrocardiogram (ECG) signals. The ECG is a significant diagnosis tool that is used to record the electrical activity of the heart, and its signals can reveal abnormal heart activity. However, because of their small amplitude and duration, visual interpretation of ECG signals is difficult. Many deep and machine learning approaches have been proposed for automatically arrhythmia classification. Convolutional neural networks (CNNs) have been achieved promising performances in this field that proved the efficiency of deep convolutional neural networks in automated detection and, therefore, cardiovascular disease protection as well as help cardiologists in medical practice by saving.
{"title":"A Convolutional Neural Network for Arrhythmia Classification: A Review","authors":"Sarah Kamil, L. Muhammed","doi":"10.23919/eecsi53397.2021.9624304","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624304","url":null,"abstract":"Arrhythmia is a heart condition that occurs due to abnormalities in the heartbeat, which means that the heart's electrical signals do not work properly, resulting in an irregular heartbeat or rhythm and thus defeating the pumping of blood. Some cases of arrhythmia are not considered serious, while others are very dangerous, life-threatening, and cause death in a short period of time. In the clinical routine, cardiac arrhythmia detection is performed by electrocardiogram (ECG) signals. The ECG is a significant diagnosis tool that is used to record the electrical activity of the heart, and its signals can reveal abnormal heart activity. However, because of their small amplitude and duration, visual interpretation of ECG signals is difficult. Many deep and machine learning approaches have been proposed for automatically arrhythmia classification. Convolutional neural networks (CNNs) have been achieved promising performances in this field that proved the efficiency of deep convolutional neural networks in automated detection and, therefore, cardiovascular disease protection as well as help cardiologists in medical practice by saving.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115152231","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624259
Bustanul Arifin, A. A. Nugroho, B. Suprapto, S. Prasetyowati, Z. Nawawi
The industry is closely related to motors. Motor is used as the prime mover to run the production machines. Control of the motor is needed so that it can work according to its designation. Motor parameters must be known to control it. The required parameters include electrical and mechanical parameters. These parameters are often not easy to obtain then one way to find out is by identifying the system. This paper aimed to convey the various methods that have been used in motor identification systems. Brushed DC motor, brushless DC motor, servo motor, stepper motor, induction motor, and switch reluctance motor were motors analyzed. These methods included the least square, recursive least square in the form of autoregressive with exogenous input, autoregressive moving average with exogenous. Another system identification method utilizes artificial intelligence. This method used fuzzy logic, neural network, genetic algorithm, particle swarm optimization, and various combinations of these methods. The review results showed that the artificial intelligence method was very interesting and promising because it has advantages compared to conventional methods. Modification or combination of two or more artificial intelligence methods would get better and closer results to the actual situation.
{"title":"Review of Method for System Identification on Motors","authors":"Bustanul Arifin, A. A. Nugroho, B. Suprapto, S. Prasetyowati, Z. Nawawi","doi":"10.23919/eecsi53397.2021.9624259","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624259","url":null,"abstract":"The industry is closely related to motors. Motor is used as the prime mover to run the production machines. Control of the motor is needed so that it can work according to its designation. Motor parameters must be known to control it. The required parameters include electrical and mechanical parameters. These parameters are often not easy to obtain then one way to find out is by identifying the system. This paper aimed to convey the various methods that have been used in motor identification systems. Brushed DC motor, brushless DC motor, servo motor, stepper motor, induction motor, and switch reluctance motor were motors analyzed. These methods included the least square, recursive least square in the form of autoregressive with exogenous input, autoregressive moving average with exogenous. Another system identification method utilizes artificial intelligence. This method used fuzzy logic, neural network, genetic algorithm, particle swarm optimization, and various combinations of these methods. The review results showed that the artificial intelligence method was very interesting and promising because it has advantages compared to conventional methods. Modification or combination of two or more artificial intelligence methods would get better and closer results to the actual situation.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133019593","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624265
W. A. A. Praditasari, Ria Aprilliyani, I. Kholis
Covid-19 Pandemic forces people to physical distancing. It affects the business of Museum, especially National Defense Museum. This research designs the National Defense Interactive Virtual Museum in Jakarta, Indonesia, based on OpenCV mediapipe hand and PyautoGUI. The system used MDLC method. OpenCV mediapipe hand is used to generate the method of Interactive program for Users. The virtual museum https://museumnasional.iheritage.id/ is used in this research. The result is that National Defense Interactive Virtual Museum Application can recognize the movement of users' hands using mediapipe hand to control mouse. Moreover, the resources which are used by program are 81 % CPU, 44% of RAM 8GB, and 90% Disk resources. Based on the results, the program requires high performances PC to run smoothly.
{"title":"Design and Implementation of Interactive Virtual Museum based on Hand Tracking OpenCV in Indonesia","authors":"W. A. A. Praditasari, Ria Aprilliyani, I. Kholis","doi":"10.23919/eecsi53397.2021.9624265","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624265","url":null,"abstract":"Covid-19 Pandemic forces people to physical distancing. It affects the business of Museum, especially National Defense Museum. This research designs the National Defense Interactive Virtual Museum in Jakarta, Indonesia, based on OpenCV mediapipe hand and PyautoGUI. The system used MDLC method. OpenCV mediapipe hand is used to generate the method of Interactive program for Users. The virtual museum https://museumnasional.iheritage.id/ is used in this research. The result is that National Defense Interactive Virtual Museum Application can recognize the movement of users' hands using mediapipe hand to control mouse. Moreover, the resources which are used by program are 81 % CPU, 44% of RAM 8GB, and 90% Disk resources. Based on the results, the program requires high performances PC to run smoothly.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121415229","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624234
Agnes Diza Fahira, A. H. Saputro
Colorimetric is a system used to measure and describe color. Several previous studies have successfully implemented this system using a smartphone camera for image acquisition of test strips. But unfortunately, most of these studies still transfer image data manually to a computer for processing. In this study, the colorimetric system applied to predict the value of total chlorine levels was made as an Android application. The application can take a picture and directly get results on the smartphone screen. This makes the system work more portable than previous studies. The application is made in a client-server architectural style with RESTful API communication and has two servers, one server is used to transfer images and the other is used to process images into total chlorine values. The application's success rate to reach the two servers is 100%, with the average time required is 2.58 seconds to reach the upload server and 2.68 seconds to reach the computational server. The evaluation results of the regression model used in the application are 0.31 to 0.13 RMSE. These results indicate that the regression model, Artificial Neural Network with Levenberg-Marquardt function, can be used for total chlorine levels prediction system on test strip based on colorimetric.
{"title":"Colorimetric System Based on Android Smartphone: Study Case of Total Chlorine Level Prediction","authors":"Agnes Diza Fahira, A. H. Saputro","doi":"10.23919/eecsi53397.2021.9624234","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624234","url":null,"abstract":"Colorimetric is a system used to measure and describe color. Several previous studies have successfully implemented this system using a smartphone camera for image acquisition of test strips. But unfortunately, most of these studies still transfer image data manually to a computer for processing. In this study, the colorimetric system applied to predict the value of total chlorine levels was made as an Android application. The application can take a picture and directly get results on the smartphone screen. This makes the system work more portable than previous studies. The application is made in a client-server architectural style with RESTful API communication and has two servers, one server is used to transfer images and the other is used to process images into total chlorine values. The application's success rate to reach the two servers is 100%, with the average time required is 2.58 seconds to reach the upload server and 2.68 seconds to reach the computational server. The evaluation results of the regression model used in the application are 0.31 to 0.13 RMSE. These results indicate that the regression model, Artificial Neural Network with Levenberg-Marquardt function, can be used for total chlorine levels prediction system on test strip based on colorimetric.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116607476","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624287
D. Hemanth
{"title":"Automated feature extraction in deep learning models: A boon or a bane?","authors":"D. Hemanth","doi":"10.23919/eecsi53397.2021.9624287","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624287","url":null,"abstract":"","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131042926","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：