Claim Missing Document
Check
Articles

Found 19 Documents
Search
Journal : Journal of Data Science and Software Engineering

PERFORMANCE COMPARISON OF ADAPTIVE NEURO FUZZY INFERENCE SYSTEM AND SUPPORT VECTOR MACHINE ALGORITHM IN BALANCED AND UNBALANCED MULTICLASS DATA CLASSIFICATION Muhammad Irfan Saputra; Irwan Budiman; Dwi Kartini; Dodon Turianto Nugrahadi; Mohammad Reza Faisal
Journal of Data Science and Software Engineering Vol 2 No 03 (2021)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (278.287 KB)

Abstract

Data is a record collection of facts. At first the data in the real world were largely unbalanced. Although, the existence of data on fewer categories is much more important to know data on more categories. However, there are some balanced data. This balanced data is the possibility of a ratio of 1:1 in which, the data in the dataset is the same. In this study, using the ANFIS algorithm and SVM to see affected performance on balanced and imbalanced data with multiclass. Data is taken from the UCI Machine Learning. From the research conducted, it is known that the SVM method on the Wine dataset has an accuracy of 96.6% and the ANFIS method on the Iris dataset has an accuracy of 94.7%.
Optimasi Bobot Weighted Moving Average Dengan Particle Swarm Optimization Dalam Peramalan Tingkat Produksi Karet Dendy Fadhel Adhipratama Dendy; Irwan Budiman; Fatma Indriani; Radityo Adi Nugroho; Rudy Herteno
Journal of Data Science and Software Engineering Vol 2 No 03 (2021)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (336.447 KB)

Abstract

Rubber is a mainstay commodity in the country, in 2014 Indonesia ranked second as the largest natural rubber producing country in the world. However, rubber production in Indonesia experiences uncertain ups and downs so it is necessary to predict it in order to benefit small farmers and the state. Weighted Moving Average ( WMA) is a method for predicting time series data. However, the parameters on the WMA need to be optimized in order to get optimal weight results on the WMA and get accurate results. Algorithm Particle Swarm Optimization implemented to determine the weight value of the method Weighted Moving Average more optimal. PSO-WMA and WMA were carried out on three weights, namely from weighting 3 4 and 5 on rubber production data. So that the results of this study are WMA with 3 weights get 81% accuracy, 4 weight 80.5% and 5 weight 80.3%. And for PSO-WMA, the accuracy at weighting 3 is 81.4%, weighting 4 is 80.9% and for weighting 5 it is 81.6%. The test results of this study have the effect of the weight value on WMA in increasing the accuracy results.
OPTIMASI NILAI N PADA SINGLE MOVING AVERAGE (SMA) DENGAN PARTICLE SWARM OPTIMIZATION (PSO) STUDI KASUS SAHAM BRI Rahman Hadi Rahman; Irwan Budiman; Friska Abadi; Andi Farmandi; Muliadi
Journal of Data Science and Software Engineering Vol 2 No 03 (2021)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (456.928 KB)

Abstract

The stock market is a promising business area. The potential to obtain high returns in a fairly short time is one of the main attractions of this business. Prediction of stock prices has become a very interesting and challenging thing for researchers and academics, recently it was found that stock prices can be predicted with a certain degree of accuracy. Single Moving Average (SMA) is one method for predicting time series data. However, the N value in SMA needs to be optimized in order to get the N value with optimal results at the SMA and get accurate results. The Particle Swarm Optimization Algorithm is implemented to find out the best N value in the Single Moving Average methodwhich is more optimal. SMA+PSO and SMA are calculated using the initial N values ​​of 3,5,7,9,11. So the results of this study are SMA with an accuracy of 97.98464% and for SMA+PSO with an accuracy of 98.15442% . The test results from this study are the influence of PSO on SMA in increasing accuracy in determining the best N value.
SOLUSI KLASIFIKASI DATA TIDAK SEIMBANG DENGAN PENDEKATAN BERBASIS COMBINATION OF OVERSAMPLING AND UNDERSAMPLING Riza Susanto Banner; Irwan Budiman; Dodon Turianto Nugrahadi; M. Reza Faisal; Friska Abadi
Journal of Data Science and Software Engineering Vol 3 No 01 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (345.141 KB)

Abstract

This study applies the Combination of Oversampling and Undersampling method to deal with class imbalances. Researchers do Preprocessing to normalize the attributes used for prediction, then divide the training data and testing data. Researchers resampled unbalanced data using Oversampling, Undersampling and a combination of Oversampling and Undersampling. The results of the classification with the experimental data class balancing approach, the best classification performance is the combination of Oversampling and Undersampling classified by the k-Nearest Neighbor (KNN) method with an accuracy of 0.8672; sensitivity of 0.9000; specificity of 0.3750; and AUC of 0.6651042. Classification with Oversampling has performance results, namely accuracy of 0.875; sensitivity of 0.9250; specificity of 0.1250; and AUC of 0.6078125, while Undersampling classification has classification performance, namely accuracy of 0.3438; sensitivity of 0.33333; specificity of 0.50000; and AUC of 0.3645833.
Text Mining Untuk Mengklasifikasi Judul Berita Online Studi Kasus Radar Banjarmasin Menggunakan Metode TF-IDF dan K-NN Salsabila Anjani; Andi Farmadi; Dwi Kartini; Irwan Budiman; Mohammad Reza Faisal
Journal of Data Science and Software Engineering Vol 3 No 01 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (299.003 KB)

Abstract

ABSTRACT The news media that used to be commonly used were newspapers. However, with the development of the times, the news media is now entering the digital era. Many online news media spread on the internet. The sophistication of the internet makes it easier for readers to choose which news they want to read. Unlike newspapers, online news media have categories where readers can choose. In general, the categorization of a news in online media is determined by the editor. Given the number of news published in a day, of course, makes the editor's job difficult. A category in the news is usually not appropriate because usually the headline is made as attractive as possible to attract the interest of the reader. So there are times when the news title does not match the category that has been entered by the editor. The use of the K-Nearest Neighbor (K-NN) method can be used in determining the categorization of a news. By using a case study of the online media Radar Banjarmasin, a research was conducted to find out how well the Canberra and Euclidean classification methods were using news headline data for categorization. The results obtained in this study are the better classification method is Euclidean and with an accuracy value of 65.00%. Improvements that should be made for further research is to use other methods for comparison.
COMPARATIVE ANALYSIS OF FUZZY TIME SERIES METHOD WITH FUZZY TIME SERIES MARKOV CHAIN ON RAINFALL FORECAST IN SOUTH KALIMANTAN M Kevin Warendra; Irwan Budiman; Rudy Herteno; Dodon Turianto Nugrahadi; Friska Abadi
Journal of Data Science and Software Engineering Vol 3 No 01 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1219.79 KB)

Abstract

Abstract Time series data (TS) is a type of data that is collected according to the order of time within a certain time span. Time Series data analysis is one of the statistical procedures applied to predict the probability structure of future conditions for decision making. FTS (FTS) is a data forecasting method that uses fuzzy principles as its basis. Forecasting systems with FTS capture patterns from past data and then use them to project future data. FTS Markov Chain is a new concept that was first proposed by Tsaur, in his research to analyze the accuracy of the prediction of the Taiwan currency exchange rate with the US dollar. In his research, Tsaur combines the FTS method with Markov Chain, The merger aims to obtain the greatest probability using a transition probability matrix. The results obtained from this research are tests with the best number of presentation values ​​from FTS Markov Chain with FTS, resulting in different accuracy values ​​depending on the two methods. The best accuracy performance is obtained by the Markov Chain FTS method with an error value of 1.6% and an accuracy value of 98.4% and for FTS with an error value of 7.4% and an accuracy value of 92.6%. produce different accuracy values ​​depending on the two methods. The best accuracy performance is obtained by the Markov Chain FTS method with an error value of 1.6% and an accuracy value of 98.4% and for FTS with an error value of 7.4% and an accuracy value of 92.6%. produce different accuracy values ​​depending on the two methods. The best accuracy performance is obtained by the Markov Chain FTS method with an error value of 1.6% and an accuracy value of 98.4% and for FTS with an error value of 7.4% and an accuracy value of 92.6%.
IMPLEMENTASI METODE TEMPLATE MATCHING TERHADAP PENGENALAN CITRA PLAT NOMOR KENDARAAN BERMOTOR Ahmad Shofi Khairian; Irwan Budiman; Muhammad Itqan Mazdadi; Andi Farmadi; Dwi Kartini
Journal of Data Science and Software Engineering Vol 3 No 02 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (851.121 KB)

Abstract

Abstract The motorized vehicle number (TNKB) sign or commonly referred to as the police license plate is a plate made of aluminum that shows the sign of a motorized vehicle in Indonesia that has been registered with the Samsat Office. The motor vehicle number sign in the form of an aluminum plate consists of 2 (two) lines, the first line showing the area code (letters), police number (numbers), and the final code/series. This study uses 10 license plates of motorized vehicles as test data taken for each character and 3 data sets of letters AZ and numbers 0-9 number plates of motorized vehicles for each character as training data. The purpose of this study was to determine the level of accuracy of the method Template Matching on image recognition of motor vehicle numbers. The results of the implementation of the method Template Matching on the image recognition of motorized vehicle license plates is to produce an accuracy rate of 95.56%.
IMPLEMENTASI ALGORITMA GENETIKA UNTUK OPTIMASI NEURAL NETWORK PADA STUDI KASUS PERMAINAN TRON Muhammad Darmadi; Irwan Budiman; Muliadi; Andi Farmadi; Triando Hamonangan Saragih
Journal of Data Science and Software Engineering Vol 3 No 02 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1491.944 KB)

Abstract

Abstract Tron is played in an arena composed of grids and often both players are placed at different starting points, each player basically playing the game by aiming straight, turning left or turning right until one or both of them hit a wall or laser object. This study aims to examine how good genetic algorithms are in optimizing neural networks for artificial intelligence. As well as to find out what the winning percentage is for each researched artificial intelligence. The results obtained are that N5 is faster in obtaining optimal results, which only requires 9 generations but has the lowest percentage. So it can be concluded that the faster finding optimal results does not guarantee that artificial intelligence will be better..
PREDIKSI DATA PENARIKAN UANG TUNAI DI MESIN ATM MENGGUNAKAN METODE SEASONAL AUTOREGRESSIVE INTEGRATED MOVING AVERAGE (SARIMA) Fitrinadi; Irwan Budiman; Andi Farmadi; Dodon Turianto Nugrahadi; Muhammad Itqan Mazdadi
Journal of Data Science and Software Engineering Vol 3 No 02 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1712.756 KB)

Abstract

Abstract Data mining is a series of processes to explore the added value of knowledge that has been unknown from a data set. Many algorithms can be used in solving a problem related to prediction or forecasting a new data value for the future based on pre-existing data. Sarima model is a model in time series analysis. The performance of the Seasonal Autoregressive Integrated Moving Average (SARIMA) method produces a suitable or good model used to predict cash withdrawal data at ATM machines. The data used in the study is a dataset of ATM transactions originating from Finhacks. The result of error using MAPE (Mean Absolute Percenttage Error) on the predicted result of cash withdrawal data at atm machines is K1 16.75%, K2 18.09%, K3 7.85%, K4 5.67%, and K5 11.80%. So it can be concluded that the data matches using the SARIMA model that has been selected because the MAPE value is smaller than 20%.
Co-Authors A.A. Ketut Agung Cahyawan W Abdul Gafur Achmad Zainudin Nur Ahmad Faris Asy'arie Ahmad Faris Asy’arie Ahmad Rusadi Arrahimi Ahmad Rusadi Arrahimi - Universitas Lambung Mangkurat) Ahmad Rusadi Arrahimi - Universitas Lambung Mangkurat) Ahmad Shofi Khairian Aji Triwerdaya Ajwa Helisa Akhmad Yusuf Andi Farmadi Andi Farmadi Andi Farmadi Andi Farmandi Antar Sofyan Aris Pratama Artesya Nanda Akhlakulkarimah Dendy Fadhel Adhipratama Dendy Dita Amara Dodon Turianto Nugrahadi Dwi Kartini Dwi Kartini Dwi Kartini Dwi Kartini Dwi Kartini, Dwi Faisal Murtadho Fatma Indriani Fatma Indriani Fitrinadi Friska Abadi Halimah Halimah Halimah Ichwan Dwi Nugraha Kevin Yudhaprawira Halim Lutfi Salisa Setiawati M Kevin Warendra Mera Kartika Delimayanti Muflih Ihza Rifatama Muhammad Adhitya Pratama Muhammad Darmadi Muhammad Haekal Muhammad Halim Muhammad Haris Qamaruzzaman Muhammad I Mazdadi Muhammad Iqbal Muhammad Irfan Saputra Muhammad Itqan Masdadi Muhammad Itqan Mazdadi Muhammad Latief Saputra Muhammad Mada Muhammad Nazar Gunawan Muhammad Reza Faisal, Muhammad Reza Muhammad Ridha Maulidi Muhammad Rizky Adriansyah Muhammad Rusli Muliadi Muliadi Muliadi - Muliadi Aziz muliadi muliadi Muliadi Muliadi Muliadi Muliadi Muliadi Muliadi Mutiara Ayu Banjarsari Nahdhatuzzahra Nahdhatuzzahra Nor Indrani Nursyifa Azizah Oni Soesanto Patrick Ringkuangan Radityo Adi Nugroho Rahman Hadi Rahman Rahmat Hidayat Rahmat Ramadhani Retma Ramadina Riana Riana Riza Susanto Banner Rizki Amelia Rudy Herteno Rudy Herteno Salsabila Anjani Sam'ani Sam'ani Saragih, Triando Hamonangan Septiadi Marwan Annahar Septyan Eka Prastya Setyo Wahyu Saputro Sofyan, Antar Sulastri Norindah Sari Sutami Sutan Takdir Alam Toni Prahasto Tri Mulyani Wahyu Caesarendra Wahyudi Wahyudi Yuli Christyono