Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315464
A. Winursito, Ibnu Masngut, G. Pratama
In this paper, we present an approach to increase the robustness of the sensors' readings. It is quite troublesome to get noises as IoT sensors need to be installed outdoor. As the problems have to be addressed properly, we decide on implementing Kalman Filter to reduce the noises. Based on the experiments, Kalman Filter serves better sensors' readings. It can reduce the errors due to noises up to 66.49 percents. Therefore, the implementation of Kalman Filter will bring additional values to precision agriculture.
{"title":"Development and Implementation of Kalman Filter for IoT Sensors: Towards a Better Precision Agriculture","authors":"A. Winursito, Ibnu Masngut, G. Pratama","doi":"10.1109/ISRITI51436.2020.9315464","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315464","url":null,"abstract":"In this paper, we present an approach to increase the robustness of the sensors' readings. It is quite troublesome to get noises as IoT sensors need to be installed outdoor. As the problems have to be addressed properly, we decide on implementing Kalman Filter to reduce the noises. Based on the experiments, Kalman Filter serves better sensors' readings. It can reduce the errors due to noises up to 66.49 percents. Therefore, the implementation of Kalman Filter will bring additional values to precision agriculture.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123953106","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315331
M. Archi, D. Gunawan
5G communication services, which provide many benefits and advantages, require several good technical specifications for each process mechanism. A delay is still a problem in the initial access mechanism to reach the 5G communication performance specification. Significant delays can occur when finding appropriate beam alignments to obtain directional links between the Base Station (BS) and the User Equipment (UE). Solving the problem with a suitable method makes the topic is important. In this paper, we propose a new beam refinement method based on Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), namely Hybrid Genetic Algorithm and Particle Swarm Optimization (HGAPSO), which this method has several advantages over GA and PSO respectively. We use the capacity parameter against the number of iterations (delay) as a performance evaluation metric, where the suitable method is determined using these parameters. The simulation results show that HGAPSO has the second-lowest number of iterations in achieving convergence with the highest capacity compared to the GA and PSO methods. From these results, we conclude that HGAPSO is a suitable method compared to GA and PSO for the initial access mechanism in mmWave 5G communication systems.
{"title":"Initial Access in 5G mmWave Communication using Hybrid Genetic Algorithm and Particle Swarm Optimization","authors":"M. Archi, D. Gunawan","doi":"10.1109/ISRITI51436.2020.9315331","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315331","url":null,"abstract":"5G communication services, which provide many benefits and advantages, require several good technical specifications for each process mechanism. A delay is still a problem in the initial access mechanism to reach the 5G communication performance specification. Significant delays can occur when finding appropriate beam alignments to obtain directional links between the Base Station (BS) and the User Equipment (UE). Solving the problem with a suitable method makes the topic is important. In this paper, we propose a new beam refinement method based on Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), namely Hybrid Genetic Algorithm and Particle Swarm Optimization (HGAPSO), which this method has several advantages over GA and PSO respectively. We use the capacity parameter against the number of iterations (delay) as a performance evaluation metric, where the suitable method is determined using these parameters. The simulation results show that HGAPSO has the second-lowest number of iterations in achieving convergence with the highest capacity compared to the GA and PSO methods. From these results, we conclude that HGAPSO is a suitable method compared to GA and PSO for the initial access mechanism in mmWave 5G communication systems.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123530526","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315426
A. Najmurrokhman, Kusnandar, Ahmad Daelami, E. Nurlina, U. Komarudin, Hasbi Ridhatama
Oyster mushrooms are a kind of mushrooms that have high nutritional content and medicinal properties. This plant can be cultivated using planting media with the proper composition and the certain temperature as well as humidity. This paper describes the design and implementation of a prototype of temperature and humidity control system in the oyster mushroom cultivation based on the internet-of-things framework to obtain the good quality mushrooms. Controlling is carried out by utilizing DHT-11 sensor, Arduino Uno microcontroller, MCU ESP8266, and the internet-of-things (IoT) platforms which are called Cayenne. The temperature is maintained between 22°C-28°C and humidity of 60%-80% through continuous monitoring remotely. The Cayenne application installed on the desktop computer or an Android-based mobile phone provides data on temperature and humidity at all times. Experimental results show that monitoring and controlling temperature and humidity can be done well through the Cayenne application so that the whole system realizes the concept of IoT.
{"title":"Development of Temperature and Humidity Control System in Internet-of-Things based Oyster Mushroom Cultivation","authors":"A. Najmurrokhman, Kusnandar, Ahmad Daelami, E. Nurlina, U. Komarudin, Hasbi Ridhatama","doi":"10.1109/ISRITI51436.2020.9315426","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315426","url":null,"abstract":"Oyster mushrooms are a kind of mushrooms that have high nutritional content and medicinal properties. This plant can be cultivated using planting media with the proper composition and the certain temperature as well as humidity. This paper describes the design and implementation of a prototype of temperature and humidity control system in the oyster mushroom cultivation based on the internet-of-things framework to obtain the good quality mushrooms. Controlling is carried out by utilizing DHT-11 sensor, Arduino Uno microcontroller, MCU ESP8266, and the internet-of-things (IoT) platforms which are called Cayenne. The temperature is maintained between 22°C-28°C and humidity of 60%-80% through continuous monitoring remotely. The Cayenne application installed on the desktop computer or an Android-based mobile phone provides data on temperature and humidity at all times. Experimental results show that monitoring and controlling temperature and humidity can be done well through the Cayenne application so that the whole system realizes the concept of IoT.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127700606","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315519
S. Sa'adah, Muhammad Satrio Wibowo
Growth Domestic Product (GDP) is the important factor to know the stability of financial condition in a country. Regarding into GDP value could be known the economic condition per capita. Especially, during this pandemic situation, GDP need study further about its sudden fluctuation. The solution can be covered using the prediction approach. Deep learning as new method from machine learning schema had been observed in this research to cope the prediction of GDP problem. Two methods of deep learning techniques that were used, LSTM and RNN, shown that the prediction could fit the data actual very well. The accuracy at around 80% until 90% emerge from LSTM architecture 2 and RNN architecture 2. Based on this result, it could bring new perspective to use this model to know the GDP fluctuation in a country even in catastrophe of Covid-19.
{"title":"Prediction of Gross Domestic Product (GDP) in Indonesia Using Deep Learning Algorithm","authors":"S. Sa'adah, Muhammad Satrio Wibowo","doi":"10.1109/ISRITI51436.2020.9315519","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315519","url":null,"abstract":"Growth Domestic Product (GDP) is the important factor to know the stability of financial condition in a country. Regarding into GDP value could be known the economic condition per capita. Especially, during this pandemic situation, GDP need study further about its sudden fluctuation. The solution can be covered using the prediction approach. Deep learning as new method from machine learning schema had been observed in this research to cope the prediction of GDP problem. Two methods of deep learning techniques that were used, LSTM and RNN, shown that the prediction could fit the data actual very well. The accuracy at around 80% until 90% emerge from LSTM architecture 2 and RNN architecture 2. Based on this result, it could bring new perspective to use this model to know the GDP fluctuation in a country even in catastrophe of Covid-19.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125789658","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315341
L. Muflikhah, N. Widodo, W. Mahmudy, Solimun
Chronic hepatitis B virus (HBV) infection is strongly associated with liver cancer. The DNA sequence of the virus is integrated into the human genome and affected the cell cycle. $HBx$ is a virus gene that is responsible to replicate for survival even though it has a high mutation rate. Machine learning methods are an effective way in biological analysis and are widely used in diagnosis to make a prediction. This study is addressed to predict liver cancer using a machine learning method based on the DNA sequence of HBV. However, unbalanced data impacts the performance evaluation of the learning method, especially for sensitivity and specificity. Therefore, this paper is proposed the ensemble method to improve the performance of prediction. We compare several classifier methods including Naive Bayes, GLM, KNN, SVM, and C5.0 Decision Tree. The results show that the ensemble method achieves a high evaluation performance value with an accuracy rate of 88.4%, a sensitivity rate of 88.4%, and a specificity rate of 91.4%.
{"title":"Prediction of Liver Cancer Based on DNA Sequence Using Ensemble Method","authors":"L. Muflikhah, N. Widodo, W. Mahmudy, Solimun","doi":"10.1109/ISRITI51436.2020.9315341","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315341","url":null,"abstract":"Chronic hepatitis B virus (HBV) infection is strongly associated with liver cancer. The DNA sequence of the virus is integrated into the human genome and affected the cell cycle. $HBx$ is a virus gene that is responsible to replicate for survival even though it has a high mutation rate. Machine learning methods are an effective way in biological analysis and are widely used in diagnosis to make a prediction. This study is addressed to predict liver cancer using a machine learning method based on the DNA sequence of HBV. However, unbalanced data impacts the performance evaluation of the learning method, especially for sensitivity and specificity. Therefore, this paper is proposed the ensemble method to improve the performance of prediction. We compare several classifier methods including Naive Bayes, GLM, KNN, SVM, and C5.0 Decision Tree. The results show that the ensemble method achieves a high evaluation performance value with an accuracy rate of 88.4%, a sensitivity rate of 88.4%, and a specificity rate of 91.4%.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121734492","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315365
G. V. Nivaan, A. Emanuel
Hepatitis is an inflammation of the liver which is one of the diseases that affects the health of millions of people in the world of all ages. Predicting the outcome of this disease can be said to be quite challenging, where the main challenge for public health care services itself is due to a limited clinical diagnosis at an early stage. So by utilizing machine learning techniques on existing data, namely by concluding diagnostic rules to see trends in hepatitis patient data and see what factors are affecting patients with hepatitis, can make the diagnosis process more reliable to improve their health care. The approach that can be used to carry out this prediction process is a regression technique. The regression itself provides a relationship between the independent variable and the dependent variable. By using the hepatitis disease dataset from UCI Machine Learning, this study applies a logistic regression model that provides analysis results with an accuracy rate of 83.33%.
{"title":"Analytic Predictive of Hepatitis using The Regression Logic Algorithm","authors":"G. V. Nivaan, A. Emanuel","doi":"10.1109/ISRITI51436.2020.9315365","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315365","url":null,"abstract":"Hepatitis is an inflammation of the liver which is one of the diseases that affects the health of millions of people in the world of all ages. Predicting the outcome of this disease can be said to be quite challenging, where the main challenge for public health care services itself is due to a limited clinical diagnosis at an early stage. So by utilizing machine learning techniques on existing data, namely by concluding diagnostic rules to see trends in hepatitis patient data and see what factors are affecting patients with hepatitis, can make the diagnosis process more reliable to improve their health care. The approach that can be used to carry out this prediction process is a regression technique. The regression itself provides a relationship between the independent variable and the dependent variable. By using the hepatitis disease dataset from UCI Machine Learning, this study applies a logistic regression model that provides analysis results with an accuracy rate of 83.33%.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131958088","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315430
Ramadhan Rizki Setyadi, Istikmal, A. Irawan
The safe box is currently considered safe but is not truly safe. That is because safe storage has a security method using PINs that can be seen by others. Therefore, a more secure safe box security system is needed. This paper purpose a safe box prototype with an added security system using a two-way verification system and an integrated Internet of Things (IoT) system. The face recognition system and fingerprint system used in this system. The face recognition system developed an LBP (Local Binary Pattern) clarification and embedded Haar cascade program in raspberry Pi. For real-time monitoring, the safe box has been designed to provide violation alerts via notifications on android apps. Two-way verification smart safe box has a good face recognition system especially when the conditions are bright and also the best way to identify fingerprints on a flat position. In LOS conditions, the best distance is at 4 meters with a delay value of 0.373 s and throughput of 3680.533 bps. In non-LOS condition, the best distance is 2 meters with a delay value of 0.380 seconds and throughput of 4055.73 bytes/s.
{"title":"Smart Safe Prototype Based Internet of Things (IoT) with Face and Fingerprint Recognition","authors":"Ramadhan Rizki Setyadi, Istikmal, A. Irawan","doi":"10.1109/ISRITI51436.2020.9315430","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315430","url":null,"abstract":"The safe box is currently considered safe but is not truly safe. That is because safe storage has a security method using PINs that can be seen by others. Therefore, a more secure safe box security system is needed. This paper purpose a safe box prototype with an added security system using a two-way verification system and an integrated Internet of Things (IoT) system. The face recognition system and fingerprint system used in this system. The face recognition system developed an LBP (Local Binary Pattern) clarification and embedded Haar cascade program in raspberry Pi. For real-time monitoring, the safe box has been designed to provide violation alerts via notifications on android apps. Two-way verification smart safe box has a good face recognition system especially when the conditions are bright and also the best way to identify fingerprints on a flat position. In LOS conditions, the best distance is at 4 meters with a delay value of 0.373 s and throughput of 3680.533 bps. In non-LOS condition, the best distance is 2 meters with a delay value of 0.380 seconds and throughput of 4055.73 bytes/s.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133997916","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315340
Satriya Herayudha Samudera, M. Rifadil, I. Ferdiansyah, Syechu Dwitya Nugraha, O. Qudsi, E. Purwanto
The speed of an induction motor is difficult to control, it happens because the torque and flux produced are not independent or related to each other so that they cannot maintain a constant speed when a load changes. Therefore, we need a control to increase the response of three-phase induction motors. This research applies IP controller and scalar control to regulate the motor speed with electric vehicle loads using SVPWM inverter (space vector pulse width modulation) to improve the inverter output signal so that it can adjust the speed of the induction motor when the load changes. System performance has been tested using Matlab. The simulation results show that the IP controller can improve the dynamic response system and reduce the overshoot value compared with the conventional PI controller. The speed change on the IP controller has succeeded in reaching the 1000 rpm set point with a rise time of 0.342 seconds at a steady state of 0.36 seconds and an overshoot of 2.830%. At a set point speed up to 800 Rpm, a stable condition is obtained with rise time of 0.12 seconds and an overshoot of 5.649%.
{"title":"Three Phase Induction Motor Dynamic Speed Regulation Using IP Controller","authors":"Satriya Herayudha Samudera, M. Rifadil, I. Ferdiansyah, Syechu Dwitya Nugraha, O. Qudsi, E. Purwanto","doi":"10.1109/ISRITI51436.2020.9315340","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315340","url":null,"abstract":"The speed of an induction motor is difficult to control, it happens because the torque and flux produced are not independent or related to each other so that they cannot maintain a constant speed when a load changes. Therefore, we need a control to increase the response of three-phase induction motors. This research applies IP controller and scalar control to regulate the motor speed with electric vehicle loads using SVPWM inverter (space vector pulse width modulation) to improve the inverter output signal so that it can adjust the speed of the induction motor when the load changes. System performance has been tested using Matlab. The simulation results show that the IP controller can improve the dynamic response system and reduce the overshoot value compared with the conventional PI controller. The speed change on the IP controller has succeeded in reaching the 1000 rpm set point with a rise time of 0.342 seconds at a steady state of 0.36 seconds and an overshoot of 2.830%. At a set point speed up to 800 Rpm, a stable condition is obtained with rise time of 0.12 seconds and an overshoot of 5.649%.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133346000","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 human face can be used in various biometrics procedures to identify an individual through face recognition or for facial expression recognition. However, not many studies have addressed the problem of face recognition along with facial expression recognition. In addition, some studies have directed more attention to finding the most suitable feature to extract and feed to a classifier. This study focused on addressing the problem using a convolutional neural network (CNN)-based method. Unlike other methods that require suitable features to be found, this study utilized raw images as the input to the CNN. A total of 16,640 images showing four facial expressions (normal, smiling, surprised, and angry) were used as input data. These data were obtained from 52 people and captured under outdoor conditions (in midday and the afternoon) using a webcam. The CNN-VGG was utilized because it is deep and fast enough for both face recognition and facial expression recognition purposes. The results showed that the VGG-f model architecture could overcome the underfitting and overfitting problems stemming from simpler CNN architectures. The testing results showed that the VGG-f model could recognize faces and facial expressions well. The average accuracies achieved in recognizing 104 faces during the day and in the afternoon were 86.5% and 90.4%, respectively. Additionally, the average accuracies achieved in recognizing the four different facial expressions of 52 people were 72% and 74% during the day and at noon, respectively. Recognition errors may have been caused by similarities between images.
{"title":"Facial Expression Recognition and Face Recognition Using a Convolutional Neural Network","authors":"Suci Dwijayanti, Rahmad Rhedo Abdillah, Hera Hikmarika, Hermawati, Zaenal Husin, B. Suprapto","doi":"10.1109/ISRITI51436.2020.9315513","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315513","url":null,"abstract":"The human face can be used in various biometrics procedures to identify an individual through face recognition or for facial expression recognition. However, not many studies have addressed the problem of face recognition along with facial expression recognition. In addition, some studies have directed more attention to finding the most suitable feature to extract and feed to a classifier. This study focused on addressing the problem using a convolutional neural network (CNN)-based method. Unlike other methods that require suitable features to be found, this study utilized raw images as the input to the CNN. A total of 16,640 images showing four facial expressions (normal, smiling, surprised, and angry) were used as input data. These data were obtained from 52 people and captured under outdoor conditions (in midday and the afternoon) using a webcam. The CNN-VGG was utilized because it is deep and fast enough for both face recognition and facial expression recognition purposes. The results showed that the VGG-f model architecture could overcome the underfitting and overfitting problems stemming from simpler CNN architectures. The testing results showed that the VGG-f model could recognize faces and facial expressions well. The average accuracies achieved in recognizing 104 faces during the day and in the afternoon were 86.5% and 90.4%, respectively. Additionally, the average accuracies achieved in recognizing the four different facial expressions of 52 people were 72% and 74% during the day and at noon, respectively. Recognition errors may have been caused by similarities between images.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114614192","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315523
J. Siswantoro, Heru Arwoko, M. Z. Siswantoro
Fruit image classification has several applications and can be used as alternative to traditionally fruit classification performed by human expert. This paper aims to propose fruits classification method from image using extreme learning machine (ELM), MPEG-7 visual descriptors, and principle component analysis (PCA). The optimum parameters of ELM and PCA were determined using grid search optimization. The best classification performance of 97.33% has been achieved in classifying Indonesian fruit images consisted of 15 classes. By applying the ensemble of ELMs, the classification accuracy was increased to 98.03%. This result shows that the proposed method produces high classification performance.
{"title":"Fruits Classification from Image using MPEG-7 Visual Descriptors and Extreme Learning Machine","authors":"J. Siswantoro, Heru Arwoko, M. Z. Siswantoro","doi":"10.1109/ISRITI51436.2020.9315523","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315523","url":null,"abstract":"Fruit image classification has several applications and can be used as alternative to traditionally fruit classification performed by human expert. This paper aims to propose fruits classification method from image using extreme learning machine (ELM), MPEG-7 visual descriptors, and principle component analysis (PCA). The optimum parameters of ELM and PCA were determined using grid search optimization. The best classification performance of 97.33% has been achieved in classifying Indonesian fruit images consisted of 15 classes. By applying the ensemble of ELMs, the classification accuracy was increased to 98.03%. This result shows that the proposed method produces high classification performance.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117053227","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：