Claim Missing Document
Check
Articles

Prediksi Suku Bunga Acuan (BI 7-Day Repo Rate) Menggunakan Metode Extreme Learning Machine (ELM) Yohana Yunita Putri; Putra Pandu Adikara; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1122.171 KB)

Abstract

Reference interest rates or often referred to as BI 7-Day Repo Rate is a policy interest rate that describes the establishment or view of monetary policy whose determination is made by Bank Indonesia which is then notified to the public.. BI 7-Day Repo Rate has an influence on economic activities, such as investment, inflation and currency changes. Investors and market players in making economic decisions will refer to the fluctuation of interest rates set by the central bank. Therefore, the prediction of the benchmark interest rate (BI 7-Day Repo Rate) is important. The purpose of the BI 7-Day Repo Rate prediction is to facilitate and assist investors and market players to make estimates of the decisions to be taken according to the prediction of the benchmark interest rate. This study uses the Extreme Learning Machine (ELM) method to predict the reference interest rate (BI 7-Day Repo Rate). The process of the first ELM algorithm is to normalize, then initialize the input and bias weights, then continue to carry out the training process and proceed with the testing process, then do the normalization to obtain the actual value. Based on the Extreme Learning Machine (ELM) algorithm that has been conducted, it produces the best Mean Absolute Percentage Error (MAPE) of 1,1% and the fastest processing time is 0.125 seconds using 50 hidden neurons, sigmoid activation function and 96 data counts.
Penerapan Term Frequency - Modified Inverse Document Frequency pada Analisis Sentimen Ulasan Barang menggunakan Metode Learning Vector Quantization Moch. Yugas Ardiansyah; Mochammad Ali Fauzi; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 6 (2019): Juni 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (456.314 KB)

Abstract

In online stores there are reviews of items that contain comments about feedback from previous buyers that are useful for subsequent buyers as well as sellers at online stores. Reviews Usually consist of negative comments or positive comments. The number of reviews is very much. In overcoming this problem, sentiment analysis is needed. This study uses the Learning Quantization Vector and Term Frequency-Modified Inverse Document Frequency methods. The LVQ method was chosen because it has the advantage of being able to summarize the dataset into a codebook vector. The data used consisted of 250 positive comments and 250 negative comments. The data will be preprocessing, weighting the word using TF-mIDF and consequently using the LVQ method. The results of testing the LVQ parameters obtained an accuracy value of 75.11%, recall of 75.11% precision of 77,80%, f-measure of 76.43% with parameter values ​​of learning rate 10-3, dec α 10-6, and values maximum epoch 19. Based on the final test results, obtained the value of the Learning Vector Quantization method with TF-mIDF resulted in an average accuracy of 72.47%, recall of 72.47%, precision of 76.39%, and f-measure of 74.33 % and using the Learning Vector Quantization method with TF-IDF resulted in an average accuracy of 54.80%, recall of 54.80%, precision of 54.30%, and f-measure of 52.61%.
Rekomendasi Film Berdasarkan Sinopsis Menggunakan Metode Word2Vec Alimah Nur Laili; Putra Pandu Adikara; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 6 (2019): Juni 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (695.813 KB)

Abstract

The number of movie production have increased each year. This shows that the society interest in the film industry is getting higher. It's difficult to get the appropriate result of what desired by searching for data with certain parameters on the internet because of the large amount of data exists but there is limited adequate tools. The screening of the excess data can be done using recommendation process. There are several stages in movie recommendation process. Those are Pre-processing to process film synopsis documents, TF-IDF method to obtain the highest value as much as the amount determined based on the query result on the document. Word2vec as a method to get the query expansion from the top word result that taken from TF-IDF process and Cosine Similarity is used to get the similarity between document and query. The Word2Vec method plays role to find the proximity value between words to one another in order to get the words that will be added to the initial query. The training data are 150 movies title with English synopsis. The evaluation process took 30 data of movie title and synopsis from the training data based on the movies selected by the examiners. The highest Precision@k value is 0,47 and the highest Mean Average Precision (MAP) value is 0.709603374.
Prediksi Ketinggian Gelombang Laut Menggunakan Metode Jaringan Saraf Tiruan Backpropagation Nurhana Rahmadani; Budi Darma Setiawan; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 7 (2019): Juli 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1250.274 KB)

Abstract

Sea wave height prediction is difficult thing to do. One factors become wave generator is wind that influenced by wind direction and wind speed. These factors are difficult to calculate and predict manually, because wind conditions change any time. Wave height prediction is important because useful for shipping safety. Many prediction methods can used to make predictions, one of them is ANN Backpropagation used in this study to predict wave height in the next hour. Time-series data used in this study is wave height, wind direction, and wind speed data every one hour in East Java Sea from 2013 to 2014. The application of ANN Backpropagation in prediction of wave height is through by several phases, there are data normalization, weight initialization using Nguyen-Widrow, training, testing, and forecasting. The training data used is wave height, wind direction, and wind speed data every one hour from January to December 2013 and the test data used is data from January to June 2014. The training process used learning rate 0.5 ,4 neurons input layer,3 neurons hidden layer,1 neuron output layer, error limit MAPE training of 13,2% and maximum of 30000 iterations.The combination of these parameters produces average MAPE test value of 17.53182%.
Pengelompokan Wilayah berdasarkan Penyandang Masalah Kesejahteraan Sosial (PMKS) dengan Optimasi Algoritme K-Means menggunakan Self Organizing Map (SOM) Iskarimah Hidayatin; Sigit Adinugroho; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 8 (2019): Agustus 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (295.489 KB)

Abstract

Persons with Social Welfare Problems are people, families, groups or someone who cannot function socially because there is a spiritual, physical or social difficulty. Grouping regions based on PMKS is very important to do to provide an overview of PMKS problems with the policy objectives taken right on target. Self Organizing Map (SOM) algorithm for determining the number of clusters and initial centroids while the K-Means algorithm for determining the cluster end result. The research flow, that is, the data is normalized, then the SOM process then to K-Means, then testing and analysis are carried out. SOM parameter testing using silhouette coefficient obtained the best parameter is the learning rate value of 0.2, beta at 0.8, r (neighboring) of 0, the number of clusters by 2, and epoch by 50. K-Means algorithm optimization using SOM is better than algorithm K-Means based on the silhouette coefficient value. The silhouette coefficient value in SOM is 0.21882702 while K-Means has a value of 0.201911102. Analysis of the results obtained K-Means algorithm optimization with SOM is cluster 1 with a total of 26 districts / cities by having similarities in the variable Social Problem Migrant Workers, Families with social psychological problems, and children who are victims of violence / who are treated wrongly have an average value high average and cluster 0 with the number of 12 districts / cities with similarities in variables other than cluster 1.
Pengelompokan Wilayah Berdasarkan Kesejahteraan Sosial Menggunakan Algoritme Self-Organizing Maps Dengan Perbaikan Missing Value K-Nearest Neighbors Dese Narfa Firmansyah; Sigit Adinugroho; Bayu Rahayudi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 7 (2019): Juli 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1014.215 KB)

Abstract

Persons with Social Welfare Problems (PMKS) are social groups that live below the community welfare line and are one of component for determining policies in East Java. The study aim to find out the characteristics of the region in East Java based on the PMKS dataset. The method proposed in this study is clustering with the Self-Organizing Maps algorithm and K-Nearest Neighbors (KNN) missing value imputation. KNN used to overcome the amount of missing value in PMKS dataset. First, missing value is filled using KNN imputation. Furthermore, the clustering done with training in SOM network and the result of cluster is evaluated using Silhouette Coefficient. The best parameters for SOM are learning rate=0.1; neighborhood coefficient=0.2; max epoch=160 and neuron size=2x2. The best parameter for KNN is K=2. K=2 gives an increase in Silhouette Coefficient value of 3.4% compared to clustering without missing value imputation KNN. Using best parameter, the highest Silhouette Coefficient obtained is 0.351 which categorized as weak structure. The shape of the cluster produced is a cluster with a proportion of 1:37. The five attributes with the highest difference between the two clusters were Neglected Elderly, Homeless and Psychotic Homeless, Scavengers, Beggars and Minority Groups.
Klasifikasi Teks Pengaduan Suara Warga Kabupaten Pasuruan menggunakan Metode Maximum Entropy Mayang Panca Rini; Putra Pandu Adikara; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 8 (2019): Agustus 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (362.71 KB)

Abstract

Suara Warga is a website that it provided by the government of Pasuruan Residence to receive complain from the society. In the application, the admin must pass on the complain to related official manually. To increase the efficient of time, it is needed a classification of the text, Maximum Entropy is a method that is used in this research with Confusion Matrix evaluation method which will count the evaluation from the equal-wont data and the unequal-wont data, with the complain as much 200 data. Before doing the classification, the first step which is done is pre-processing and the next is process of word quality. Classification is done through looking for the opportunity of every word in every document and the result of classification is got based on the higher opportunity result from document class. The result of equal-wont data evaluation produce better result than the result of the unequal-wont data evaluation with the accuration: 89,27%, precision: 92,49%, recall: 89,27% and f-measure: 89,44%.
Rekomendasi Lagu berdasarkan Lirik dan Genre Lagu menggunakan Metode Word Embedding (Word2Vec) Melati Ayuning Lestari; Putra Pandu Adikara; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 8 (2019): Agustus 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (368.322 KB)

Abstract

Listening to songs has become a norm in society, serving many different purposes, and songs are released frequently nowadays, especially by media-service providers. Users need to overcome the struggle of selecting specific songs because of the enormous information provided by media-service providers. The song recommendation model can play an important part in this puzzlement as an automatic song selector, thus improving the user's experience. In this research, the song recommendation model uses Word2Vec Skip-Gram that functions as a query expansion for the sole purpose of finding the desired lyrics by producing a weight for query expansion. TF-IDF is first used to select the words in the lyrics that will be expanded. The model will give a list of 10 recommended songs. The evaluation results of the recommended song list shows the highest average of precision@10 score of 0.584 and the highest Mean Average Score (MAP) score of 0.7278.
Klasifikasi Genre Lagu dengan Fitur Akustik Menggunakan Metode K-Nearest Neighbor Husein Abdulbar; Putra Pandu Adikara; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 8 (2019): Agustus 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (714.122 KB)

Abstract

Song cannot be separated from humans daily activities. When listening to songs humans can focus more on their activities. The rapid development of information on multimedia and electronic devices has led to a dramatic increase in music appreciation and creation. On the one hand this increase encourages people to enjoy songs more. But on the other hand, this increase forced the development of new technologies for the convenience of listening to songs. An example is how someone wants to find a song based on a song that has been heard. Genres classification is one of machine learning techniques that can group songs based on their usefulness. This technique can be used as a function in a system to support other functions, such as song recommendations, special word, or similar song searches. This study will use the K-Nearest Neighbor (K-NN) method as a genre classification technique for songs. To measure the similarity of two songs, a normalized cross correlation (NCC) equation is used to replace the distance calculation equation in the K-NN method. The features that extracted from a song are zero crossing rate, spectral centroid, spectral rolloff, and energy. Data obtained from feature extraction will be normalized using the z-score equation. The test results show that the best evaluation is obtained when the duration is 10, the offset is 120, and K in K-NN is 10. Precision, recall, and f-measure that obtained in this study are precision with a value of 0.637, recall with a value of 0.633, and f-measure with a value of 0.635.
Analisis Sentimen Opini Film Menggunakan Metode Naive Bayes dan Lexicon Based Features Arifin Kurniawan; Indriati Indriati; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 9 (2019): September 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (985.459 KB)

Abstract

The rapid development of information technology has resulted in many people writing their opinions on social media as in the KASKUS forum. KASKUS is an online forum site that provides a place to find information and share hobbies. One is called Movies forum which contains discussions about a movie that has been watched. Users writes their opinion about a film whether the film is good or bad. These opinions can be analyzed to determine how the user feedback about the film in order to produce useful output for the filmmaker by perform sentiment analysis to classify opinions into positive or negative classes. The process of sentiment analysis was performed using methods Naive Bayes for classification and Lexicon Based Features to weight the sentiment value of a word. The process starts from text preprocessing, term weighting, Naive Bayes training, and Naive Bayes testing with Lexicon Based Features weighting using Barasa's lexicon. Based on the results of tests performed, using Naive Bayes and Lexicon Features Based method, the values of accuracy, precision, recall, and f-measure were 0.8, 0.8, 0.8 and 0.8. While using the Naive Bayes method without Lexicon Based Features, the values of accuracy, precision, recall, and f-measure are 0.95, 1, 0.9 and 0.9474. So, the use of Naive Bayes and Lexicon Based Features methods still cannot provide better results.
Co-Authors Afif Musyayyidin Afrizal Aminulloh Afrizal Rivaldi Agus Wahyu Widodo Ahmad Afif Supianto Akhmad Muzanni Safi'i Alan Primandana Albert Bill Alroy Alimah Nur Laili Allysa Apsarini Shafhah Alqis Rausanfita Ananda Fitri Niasita Anggi Gustiningsih Hapsani Arifin Kurniawan Arrizal Amin Arrofi Reza Satria Aulia Rahma Hidayat Ayustina Giusti Bayu Rahayudi Brian Andrianto Budi Darma Setiawan Candra Dewi Cornelius Bagus Purnama Putra Dahnial Syauqy Danang Aditya Wicaksana Daris Hadyan Tisantri Dayinta Warih Wulandari Dese Narfa Firmansyah Dewan Rizky Bahari Dheby Tata Artha Diajeng Ninda Armianti Dwi Novi Setiawan Edy Santoso Eky Cahya Pratama Faizatul Amalia Felicia Marvela Evanita Fitra Abdurrachman Bachtiar Gessia Faradiksi Putri Gilang Pratama Hangga Eka Febrianto Hanson Siagian Humam Aziz Romdhoni Husein Abdulbar Ilham Firmansyah Ilham Firmansyah Imam Cholissodin Inas Hakimah Kurniasih Indah Wahyuning Ati Indriati Indriati Inosensius Karelo Hesay Irwin Deriyan Ferdiansyah Iskarimah Hidayatin Kenza Dwi Anggita Khairul Rizal Krishnanti Dewi Lailil Muflikhah Listiya Surtiningsih Lukman Hakim M. Ali Fauzi Mahendra Okza Pradhana Mayang Panca Rini Melati Ayuning Lestari Moch. Yugas Ardiansyah Mohammad Angga Prasetya Askin Muhammad Alif Fahrizal Muhammad Dio Reyhans Muhammad Dzulhilmi Rifqi Bassya Muhammad Iqbal Pratama Muhammad Mauludin Rohman Muhammad Reza Ravi Muhammad Sholeh Hudin Muhammad Tanzil Furqon Muhammad Yudho Ardianto Muria Naharul Hudan Najihul Ulum Naziha Azhar Nendiana Putri Nurhana Rahmadani Putra Pandu Adhikara Putra Pandu Adikara Putra Pandu Adikara Rahman Syarif Randy Cahya Wihandika Randy Cahya Wihandika Ratna Ayu Wijayanti Regina Anky Chandra Ridho Ghiffary Muhammad Rizal Maulana Rizky Adinda Azizah Salsabila Insani Salsabila Multazam Sarah Yuli Evangelista Simarmata Shima Fanissa Siti Mutrofin Sukma Fardhia Anggraini Sulaiman Triarjo Supraptoa Supraptoa Sutrisno Sutrisno Tibyani Tibyani Tri Kurniawan Putra Tri Rahayuni Utaminingrum, Fitri Wahyu Rizki Ferdiansyah Yohana Yunita Putri Yose Parman Putra Sinamo Yuita Arum Sari Yuita Arum Sari Yuita Arum Sari