Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Not a member yet
1071 research outputs found
Sort by
Monitoring dan Kendali Tegangan Jaringan Listrik Fase-tiga melalui Smartphone
Get PDFThis paper describes the creation of a minimum system for monitoring and controlling the voltage on a three-phase electrical network. Making a minimum system based on the result of previous research that has been implemented in the forms of device assembly, programming, and performance measurement. The research objectives are (i) assembling the hardware and programming based on Arduino software version 1.8.10 and (ii) measuring the minimum system performance. The research method for achieving the objective of assembling a minimum system is carried out through integrated wiring as an effort to get the hardware achievement, while for programming is an effort to get the software achievement. The implementation of the research method for measuring the performance as an effort to get the achievements of hardware and software is carried out by giving the orders to activate the paths of each phase. The result of the assembly is the integration of the Arduino UNO R3 module, Ethernet Shield type of W5100, MikroTik RouterBoard, relay modules, and Android smartphone, while the results of the programming are compiling and uploading the syntax to the Arduino module and making applications in the .apk format for a smartphone. Performance measurements are carried out by activating conditions for the three phases of phase-R, phase-S, and/or phase-T. The conclusion can be obtained, that the manufacture of a minimum system is appropriate for the fulfillment with respect to the presence of an electronic device for monitoring and controlling the voltage on a three-phase electrical network.
Makalah ini merupakan penjabaran terkait pembuatan sistem minimum (minimum system) untuk pemantauan dan pengendalian tegangan listrik pada jaringan fase-tiga. Pembuatan sistem minimum didasarkan kepada hasil penelitian sebelumnya yang telah diimplementasikan dalam bentuk perakitan perangkat, pemrograman, dan pengukuran kinerja. Sasaran penelitian ini, yaitu (i) merakit dan memrogram perangkat keras berbantuan Arduino software versi 1.8.10 dan (ii) mengukur kinerja sistem minimum. Metode penelitian untuk pencapaian sasaran terhadap perakitan sebuah sistem minimum dilakukan melalui pengawatan terintegrasi sebagai upaya untuk ketercapaian secara perangkat keras, sedangkan pembuatan program merupakan upaya untuk ketercapaian secara perangkat lunak. Pelaksanaan metode penelitian untuk pengukuran kinerja sebagai upaya bentuk ketercapaian secara perangkat keras dan lunak, dilakukan melalui pemberian perintah untuk pengaktifan ketiga jalur fase. Hasil perakitan berupa pengintegrasian dari modul Arduino UNO R3, Ethernet Shield tipe W5100, MikroTik RouterBoard, modul relai, dan smartphone Android. Hasil pemrograman berupa compiling dan uploading sintaks ke modul Arduino dan pembuatan aplikasi format .apk untuk smartphone. Pengukuran kinerja dilakukan melalui pengaktifan kondisi untuk tiga-fase pada fase-R, fase-S, dan/atau fase-T. Berdasarkan hasil-hasil penelitian dapat disimpulkan, bahwa sistem minimum terpabrikasi telah sesuai untuk pemenuhan terkait dengan keberadaan perangkat elektronika yang digunakan untuk pemantauan dan pengendalian tegangan jaringan listrik fase-tig
Gradient Boosting Machine, Random Forest dan Light GBM untuk Klasifikasi Kacang Kering
Get PDFBean seed classification is critical in determining the quality of beans. Previously, the same dataset was tested using the MLP, SVM, KNN, and DT algorithms, with SVM producing the best results. The purpose of this study is to determine the most effective model through the use of the BoxCox transformation selection feature and the random forest (RF) algorithm, as well as the gradient boosting machine (GBM), light GBM, and repeated k-folds evaluation model. The bean dataset is available on the UCI Repository website. The BoxCox transformation and repeated k-folds improved the classification prediction's accuracy. The model is used in the optimal training phase for a random forest with decision tree parameters 50 and depth 10, a gradient boosting machine model with a learning rate of 1, and a light gradient boosting machine model with a learning rate of 0.5 and estimator of 500. The best training accuracy results are obtained with light GBM. which is 99 percent accurate, but only 91 percent accurate in terms of validation. According research, the Barbunya, Bombay, Cali, Dermason, Horoz, Seker, and Sira beans classes provided accuracy values of 91 percent, 100 percent, 92 percent, 92 percent, 95 percent, 94 percent, and 84 percent, respectively. Klasifikasi biji kacang sangat penting dalam penentuan mutu kacang. Dataset yang sama sebelumnya telah diuji menggunakan algoritma MLP, SVM, KNN dan DT, dimana SVM memberikan hasil yang paling baik. Penelitian ini bertujuan untuk melihat model yang paling efektif dengan menggunakan fitur seleksi transformasi BoxCox dan algoritma random forest (RF), gradient boosting machine (GBM), light GBM serta model evaluasi repeated k-folds. Dataset kacang berasal dari website UCI Repository. Didapatkan bahwa transformasi BoxCox dan repeated k-folds meningkatkan akurasi dari prediksi klasifikasi. Penggunaan pada model pada fase training terbaik untuk random forest dengan paramater pohon keputusan 50 dan depth 10, model gradient boosting machine pada learning rate 1, dan model light gradient boosting pada learning rate 0,5 dan estimator 500. Light GBM memberikan hasil akurasi training terbaik yakni 99 persen namun akurasi validasi hanya 91 persen. Dari prediksi tersebut, didapatkan hasil bahwa Kelas kacang Barbunya, Bombay, Cali, Dermason, Horoz, Seker dan Sira memberikan nilai akurasi berturut-turut yakni 91%, 100%, 92%, 92%, 95%, 94% dan 84%
LRDDoS Attack Detection on SD-IoT Using Random Forest with Logistic Regression Coefficient
Get PDFSoftware-Defined Internet of Things (SD-IoT) is currently developed extensively. The Software-Defined Network (SDN) architecture allows Internet of Things (IoT) networks to separate control and data delivery areas into different abstraction layers. However, Low-Rate Distributed Denial of Service (LRDDoS) attacks are a significant problem in SD-IoT networks because they can overwhelm centralized control systems or controllers. Therefore, a system is needed to identify and detect these attacks comprehensively. This paper built an LRDDoS detection system using the Random Forest (RF) algorithm as the classification method. The dataset used during the experiment was considered a new dataset schema with 21 features. The dataset was selected using feature importance - logistic regression to increase the classification accuracy results and reduce the computational burden of the controller during the attack prediction process. The results of the RF classification with the LRDDoS packet delivery speed of 200 packets per second (PPS) had the highest accuracy of 98.7%. The greater the delivery rates of the attack pattern, the increased accuracy results.
 
Detection of Covid-19 on X-Ray Image of Human Chest Using CNN and Transfer Learning
Get PDFAt the end of 2019, a new disease called Coronavirus Disease (COVID-19) originated in Wuhan, China. This disease is caused by respiratory tract infections, ranging from the common cold to serious diseases such as Middle East Respiratory Syndrome (MERS) and Severe Acute Respiratory Syndrome (SARS). In Indonesia, there are tests to detect COVID-19, such as PCR and Rapid Test. This detector takes a long time and is less accurate in producing a diagnosis. This study aims to classify chest X-ray images using CNN and Transfer Learning methods to diagnose COVID-19. The proposed model has 4 scenarios: CNN Handcraft Model, Transfer Learning (VGG 16, VGG 19, and ResNet 50). This model is accompanied by data augmentation and data balancing techniques using undersampling techniques. The dataset used in this study is the “Covid-19 (COVID-19 and Normal) Radiographic Database” with 13,808 data divided into two classes, namely COVID-19 and Normal. Each model built will produce values for accuracy, precision, recall, and confusion matrix. The results of CNN Scenario 1 accuracy is 95%, in Scenario 2 VGG 16 the accuracy is 93%, Scenario 3 VGG 19 is 90% and Scenario 4 ResNet 50 is 80%.At the end of 2019, a new disease called Coronavirus Disease (COVID-19) originated in Wuhan, China. This disease is caused by respiratory tract infections, ranging from the common cold to serious diseases such as Middle East Respiratory Syndrome (MERS) and Severe Acute Respiratory Syndrome (SARS). In Indonesia, there are tests to detect COVID-19, such as PCR and Rapid Test. This detector takes a long time and is less accurate in producing a diagnosis. This study aims to classify chest X-ray images using CNN and Transfer Learning methods to diagnose COVID-19. The proposed model has 4 scenarios: CNN Handcraft Model, Transfer Learning (VGG 16, VGG 19, and ResNet 50). This model is accompanied by data augmentation and data balancing techniques using undersampling techniques. The dataset used in this study is the “Covid-19 (COVID-19 and Normal) Radiographic Database” with 13,808 data divided into two classes, namely COVID-19 and Normal. Each model built will produce values for accuracy, precision, recall, and confusion matrix. The results of CNN Scenario 1 accuracy is 95%, in Scenario 2 VGG 16 the accuracy is 93%, Scenario 3 VGG 19 is 90% and Scenario 4 ResNet 50 is 80%
Performance Analysis of Hybrid Machine Learning Methods on Imbalanced Data (Rainfall Classification)
Get PDFThis study proposes several methods to analyze the performance of the hybrid machine learning method using Voting and Stacking on rainfall classification. The two hybrid methods will combine five classification methods, namely Logistic Regression, Support Vector Machine, Random Forest, Artificial Neural Network, and eXtreme Gradient Boosting. The data used is Bandung City rainfall data for the years 2005 until 2021. The hybrid method is classified as an ensemble, which means combining several individual classification models to improve the performance of the built model. Voting algorithm has weaknesses in imbalanced data, while stacking does not. The results show that by combining five machine learning methods on an imbalanced dataset, the Stacking algorithm obtains an accuracy value of 99.60%. Meanwhile, with the addition of the SMOTE technique, the accuracy increases to 99.71%. This is supported by the performance of the Stacking method which is superior because it takes the best classification value for each individual model and can overcome the imbalance. Model evaluation does not only focus on accuracy, but also precision, recall, and f1-score. The contribution of this research is to provide information about the best Hybrid method between Voting and Stacking in obtaining model performance results on rainfall classification.This study proposes several methods to analyze the performance of the hybrid machine learning method using Voting and Stacking on rainfall classification. The two hybrid methods will combine five classification methods, namely Logistic Regression, Support Vector Machine, Random Forest, Artificial Neural Network, and eXtreme Gradient Boosting. The data used is Bandung City rainfall data for the years 2005 until 2021. The hybrid method is classified as an ensemble, which means combining several individual classification models to improve the performance of the built model. Voting algorithm has weaknesses in imbalanced data, while stacking does not. The results show that by combining five machine learning methods on an imbalanced dataset, the Stacking algorithm obtains an accuracy value of 99.60%. Meanwhile, with the addition of the SMOTE technique, the accuracy increases to 99.71%. This is supported by the performance of the Stacking method which is superior because it takes the best classification value for each individual model and can overcome the imbalance. Model evaluation does not only focus on accuracy, but also precision, recall, and f1-score. The contribution of this research is to provide information about the best Hybrid method between Voting and Stacking in obtaining model performance results on rainfall classification
Comparison of Dairy Cow on Morphological Image Segmentation Model with Support Vector Machine Classification
Get PDFPattern recognition is viral in object recognition and classification, as it can cope with the complexity of problems related to the object of the image. For example, the category of dairy cows is essential for farmers to distinguish the quality of dairy cows for motherhood. The current problem with breeders is still using the selection process manually. If the selection process using the morphology of dairy cows requires the presence of computer vision. The purpose of this study is to make it easier for dairy farmers to choose the mothers to be farmed. This work uses several processes ranging from preprocessing, segmentation, and classification of images. This study used the classification of three segmentation algorithms, namely Canny, Mask Region-Based Convolutional Neural Networks (R-CNN), and K-Means. This method aims to compare the results of the segmentation algorithm model with SVM); the model is measured with accuracy, precision, recall, and F1 Score. The expected results get the most optimal model by using multiple resistant segmentation. The most optimal model testing achieved 90.29% accuracy, 92.49% precision, 89.39% recall, and 89.95% F1 Score with a training and testing ratio of 90:10. So the most optimal segmentation method uses the K-Means algorithm with a test ratio of 90:10.Pattern recognition is viral in object recognition and classification, as it can cope with the complexity of problems related to the object of the image. For example, the category of dairy cows is essential for farmers to distinguish the quality of dairy cows for motherhood. The current problem with breeders is still using the selection process manually. If the selection process using the morphology of dairy cows requires the presence of computer vision. The purpose of this study is to make it easier for dairy farmers to choose the mothers to be farmed. This work uses several processes ranging from preprocessing, segmentation, and classification of images. This study used the classification of three segmentation algorithms, namely Canny, Mask Region-Based Convolutional Neural Networks (R-CNN), and K-Means. This method aims to compare the results of the segmentation algorithm model with SVM); the model is measured with accuracy, precision, recall, and F1 Score. The expected results get the most optimal model by using multiple resistant segmentation. The most optimal model testing achieved 90.29% accuracy, 92.49% precision, 89.39% recall, and 89.95% F1 Score with a training and testing ratio of 90:10. So the most optimal segmentation method uses the K-Means algorithm with a test ratio of 90:10
Fire Detection on Video Using ViBe Algorithm and LBP-TOP
No full textIn this research, we built a system to detect fire using the ViBe (Visual Background Extractor) algorithm to extract dynamic targets. The ViBe algorithm is better at detecting moving target objects such as flame combustion. In this research we combined the ViBe algorithm with three frame differencing to gain better results on movement object. The HSI color space model was applied after the movement object was obtained. We used Local Binary Pattern-Three Orthogonal Planes to obtain the feature extraction to be classified with Support Vector Machine. Our result has shown that the proposed system were able to detect the fire using the LBP-TOP and ViBe algorithm methods with an average accuracy rate of 88.10%, and the best accuracy was 90.37%. The parameters used to achieve this accuracy in the feature extraction process were T=120, Radius=2, and frame gap=15, then the threshold value parameter for three-frame difference parameter was 25.In this research, we built a system to detect fire using the ViBe (Visual Background Extractor) algorithm to extract dynamic targets. The ViBe algorithm is better at detecting moving target objects such as flame combustion. In this research we combined the ViBe algorithm with three frame differencing to gain better results on movement object. The HSI color space model was applied after the movement object was obtained. We used Local Binary Pattern-Three Orthogonal Planes to obtain the feature extraction to be classified with Support Vector Machine. Our result has shown that the proposed system were able to detect the fire using the LBP-TOP and ViBe algorithm methods with an average accuracy rate of 88.10%, and the best accuracy was 90.37%. The parameters used to achieve this accuracy in the feature extraction process were T=120, Radius=2, and frame gap=15, then the threshold value parameter for three-frame difference parameter was 25
Best Employee Decision Using Multi Attribute Utility Theory Method
Get PDFSelection of the best employee is a form of appreciation that can be shown by the company for the achievements of its employees. This appreciation can motivate employees to be more enthusiastic in improving their performance at work. Appropriate evaluation and decision-making methods need to be taken so that the best employee selection process runs objectively, transparently, and in accordance with established standards. This study aimed to select the best employee candidates at PT Kerry Express Indonesia using the multi attribute utility theory (MAUT) method. The criteria for the selection process as follows: attendance (weight = 2), output obtained (weight = 3), discipline (weight = 3), and reporting (weight= 2). The employees in this study were 30 respondents from 150 populations. The assessment was carried out for three months from January to April 2022. The calculations were carried out using the Microsoft Access tool. The results of calculations using the MAUT method show that the highest rank among all candidates has a score of 7.75 while the lowest rank had a score of 3.25. It can be concluded that the MAUT method can be used to select the best employees at PT. Kerry Express Indonesia effectively and efficiently.
Selection of the best employee is a form of appreciation that can be shown by the company for the achievements of its employees. This appreciation can motivate employees to be more enthusiastic in improving their performance at work. Appropriate evaluation and decision-making methods need to be taken so that the best employee selection process runs objectively, transparently, and in accordance with established standards. This study aimed to select the best employee candidates at PT Kerry Express Indonesia using the multi attribute utility theory (MAUT) method. The criteria for the selection process as follows: attendance (weight = 2), output obtained (weight = 3), discipline (weight = 3), and reporting (weight= 2). The employees in this study were 30 respondents from 150 populations. The assessment was carried out for three months from January to April 2022. The calculations were carried out using the Microsoft Access tool. The results of calculations using the MAUT method show that the highest rank among all candidates has a score of 7.75 while the lowest rank had a score of 3.25. It can be concluded that the MAUT method can be used to select the best employees at PT. Kerry Express Indonesia effectively and efficiently
A Comparison of the Smoothing Constant Values Among Exponential Smoothing Methods in Commodity Prices Forecasting
Get PDFCommodity prices forecasting is one of the business functions to estimate future demand based on past data trend. This study aims to implement a trial and error technique of the constant (alpha α) value in the exponential smoothing method. Dealing with confusion that often researchers find in selecting an alpha (α) value among exponential smoothing families, which suits characteristics of the investigated case. As selection of the constant value precisely contributes to reduce the forecasting deviation. This paper used the alpha (α) value in the range 0,1 to 0,9 and utilized the mean absolute percentage error (MAPE) and Mean Absolute Error (MAE) as the parameter to know the grade of prediction. In data training, the authors used Single Exponential Smoothing (SES) and Brown’s Double Exponential Smoothing (B-DES) as methods to compare the results of prediction. It is addressed that forecasting with alpha (α) 0,1 is the most optimal values for Single Exponential Smoothing (SES) in this case with margin error 0,00036 of MAPE and 16,84 of MAE.
Commodity prices forecasting is one of the business functions to estimate future demand based on past data trend. This study aims to implement a trial and error technique of the constant (alpha α) value in the exponential smoothing method. Dealing with confusion that often researchers find in selecting an alpha (α) value among exponential smoothing families, which suits characteristics of the investigated case. As selection of the constant value precisely contributes to reduce the forecasting deviation. This paper used the alpha (α) value in the range 0,1 to 0,9 and utilized the mean absolute percentage error (MAPE) and Mean Absolute Error (MAE) as the parameter to know the grade of prediction. In data training, the authors used Single Exponential Smoothing (SES) and Brown’s Double Exponential Smoothing (B-DES) as methods to compare the results of prediction. It is addressed that forecasting with alpha (α) 0,1 is the most optimal values for Single Exponential Smoothing (SES) in this case with margin error 0,00036 of MAPE and 16,84 of MAE
Topic Modeling for Support Ticket using Latent Dirichlet Allocation
No full textIn the business world, communication over customers must be built properly to make it easier for companies to find out what customers want. Support ticket is one of the business instrument for communication between the customers and the companies. Through a support ticket, customers can respond, complain or ask questions about products with a support team. Increasing the business process of the companies will be increasing the support ticket volume that should be handled by support team. It also has a value for analysis to get business intelligence decision. With that chance, an efficient data processing method is needed to find topics are being discussed by customers. One way that can be used to solve this problem is Topic Modeling. This research uses several parameters the number of topics, alpha value, beta value, iteration, and random seed. With this combination of parameters, the best results based on evaluation of human judgement and topic coherence with 5 topics, an alpha value of 50, a beta value of 0.01, 100 iterations, and 50 random seeds. The five topics interpretation consists of hosting migration, error problems in wordpress, domain email settings and domain transfer, ticketing and transaction processing. The total of 5 topics has a coherence value of 0.507897.In the business world, communication over customers must be built properly to make it easier for companies to find out what customers want. Support ticket is one of the business instrument for communication between the customers and the companies. Through a support ticket, customers can respond, complain or ask questions about products with a support team. Increasing the business process of the companies will be increasing the support ticket volume that should be handled by support team. It also has a value for analysis to get business intelligence decision. With that chance, an efficient data processing method is needed to find topics are being discussed by customers. One way that can be used to solve this problem is Topic Modeling. This research uses several parameters the number of topics, alpha value, beta value, iteration, and random seed. With this combination of parameters, the best results based on evaluation of human judgement and topic coherence with 5 topics, an alpha value of 50, a beta value of 0.01, 100 iterations, and 50 random seeds. The five topics interpretation consists of hosting migration, error problems in wordpress, domain email settings and domain transfer, ticketing and transaction processing. The total of 5 topics has a coherence value of 0.507897