Claim Missing Document
Check
Articles

Prediksi Volume Impor Beras Nasional menggunakan Metode Support Vector Regression (SVR) Cindy Inka Sari; Budi Darma Setiawan; Sutrisno Sutrisno
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 (525.494 KB)

Abstract

In Indonesia domestic rice production and rice imports are needed in order to attain national rice consumption. As the number of people increases and imported rice are consumed continuously, therefore Indonesia depends on rice imports from other countries. Prediction is needed to control the volume of national rice imports because excessive imports will cause negative losses and impacts. Support Vector Regression (SVR) is used to predict the volume of national rice imports. The data used in the prediction are data on consumption, production, volume of rice imports 1 year earlier as bebas variables and data on the volume of national rice imports in the period 1971 - 2016 as terikat variables. Tests carried out using 9 test data obtained the best parameters Sigma (σ) = 0.07, Lambda (λ) = 0.4, Constanta Learning Rate (cLr) = 0.01, Kompleksitas (C) = 10, Epsilon (ε) = 0.0004, the number of Iterations = 2000 and the number of training data = 37. The evaluation results were measured using Mean Absolute Presentage Error (MAPE). The best MAPE value produced is included in the sufficient category of 32.2748
Identifikasi Jenis Penyakit Mental Ansietas Menggunakan Metode Modified K-Nearest Neighbor Zubaidah Al Ubaidah Sakti; Budi Darma Setiawan; Mochammad Ali Fauzi
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 (1057.689 KB)

Abstract

On every levels of society and age must have experienced anxiety, from early state to disorder state. Not everyone knows how to deal with it, if it not treated it would become dangerous mental illness for mental and physical condition. There are six kind of anxiety , that is General Anxiety Disorder, Panic Disorder, Social Anxiety Disorder, Specific Phobia, Obsessive Compulsive Disorder, and Post Traumatic Stress Disorder. In this research will be conducted the identification for kind of anxiety based on Hamilton Rating Scale of Anxiety (HIRS) questionnaire with Modified K-nearest Neighbor (MKNN) for the research method. Unlike K-Nearest Neighbor (KNN), MKNN is another version of that where on MKNN training data must be validated first and for the class voting would be weighted. This research indicates that MKNN could identify anxiety better on unbalanced data used 96 training data and 24 test data with value of h=1 and optimum value of K=3 with best average result 95%, while on balanced data with optimum value of K=2 best average result is 93,333%. This research also indicates as comparison with KNN that in this case resulted on KNN has better result processing balanced and unbalanced data because of noisy data on weighted process, and the result from K-fold Cross Validation that conclude the system is capable enough.
Perbandingan Peramalan Jumlah Penumpang Keberangkatan Kereta Api di DKI Jakarta Menggunakan Metode Double Exponential Smoothing dan Triple Exponential Smoothing Irma Nurvianti; Budi Darma Setiawan; Fitra Abdurrachman Bachtiar
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 (352.788 KB)

Abstract

Every year the population of DKI Jakarta Province always increases. It requires the government to improve the quality of public transportation. Train is one of public transportation in DKI Jakarta. Train is a transportation that is used as an alternative mode of transportation when going to travel far to avoid congestion in the city. Therefore, it needs to plan the train capacity for custumer satisfaction. The excessive or less passengers will have an impact on the performance of PT KAI, resulting in the need forecasting the number of passengers departure for trains which the result can be used by the local government and PT KAI to improve services. This research uses and compares the accuracy of Double Exponential Smoothing and Triple Exponential Smoothing. This research uses 156 records of number of passengers, from Januari 2005 to December 2017 obtained from the data published by Statistic Indonesia. From the study testing, the smallest MAPE is found in Triple Exponential Smoothing, it is 3,213% with the most optimal parameters are =0,4, =0,4 and =0,1. The MAPE value is under 10%, it means the method can predict very well.
Klasifikasi Penempatan Siswa di Sekolah Menengah Atas menggunakan Metode Extreme Learning Machine Akmal Subakti Wicaksana; Budi Darma Setiawan; Candra Dewi
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 (343.256 KB)

Abstract

Placement of majors is one of the actions that can support the ability and motivation of student learning. Placement of the department itself has several factors that are used as considerations to determine the majors according to the abilities and interests of students. Factors used in determining majors between student psychological test results, report card grades for junior high school, BK evaluation, student interest, and parents' interests. Efficient it is not efficient. In the process of validation, the results of department placement are needed for 1 semester by looking at student learning outcomes data. In the placement of majors a system is needed that can help in classifying students' majors quickly and accurately, can be adjusted to the completion time of majors and errors in the arrangement of majors that are not in accordance with the interests and abilities of students. In this study using the Extreme Learning Machine method in grouping majors in high school students. In applying the ELM method the classification results obtained with the best average value of 98% using 14 features. To transfer data, practice and test the data used is 80:20, and the weight value is changed [-1,1], the value is biased with a range of [0,1], and use the activate sigmoid function.
Peramalan Harga Cabai Merah Besar Wilayah Jawa Timur Menggunakan Metode Extreme Learning Machine Pindo Bagus Adiatmaja; Budi Darma Setiawan; Randy Cahya Wihandika
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 (921.466 KB)

Abstract

In fulfilling economic needs in Indonesia the agricultural commodity sector has a very important role. Due to agricultural commodities are the livelihoods and basic consumption of the people in Indonesia. Daily people's needs cannot be separated from agricultural commodities, one of which is large red chili. This is due to the level of consumption of large red chili used for kitchen spices and the ingredients are quite high. Therefore large red chili which is included in agricultural commodities can be categorized as the primary food needs in people's lives. The prices of large red chili which are erratic and tend to rise can cause losses to the state and society. To overcome this problem, one solution is to forecast prices that can be used to predict the possibility of chili price increases quickly and accurately. This study aims to forecast the price of large red chili using the ELM method. Based on the results of the implementation and analysis that has been carried out using the data of large red chili prices from July 18, 2016 to December 28, 2018 the smallest error was obtained using Mean Absolute Error (MAPE) of 3 % using 2 feature, the number of neurons as many as 3 and the range of weight values ​​[-1,8, 1,8].
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%.
Perbandingan Kualitas Hasil Klaster Algoritme K-Means dan Isodata pada Data Komposisi Bahan Makanan Reza Wahyu Wardani; Budi Darma Setiawan; Candra Dewi
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 (1042.913 KB)

Abstract

Health is the most important part of human beings. One way that can be done to maintain health to regulate diet. Setting diet can be done by calculating the amount of daily nutrient content that enters body. Problems related to nutrition in community are malnutrition or condition where body doesn't get enough nutrition according to daily needs. This happens because most people dont understand how to regulate and classify food according to portion nutrients body. Fulfillment daily nutrition can be done if food has been in group based on nutritional similarity. Food grouping algorithm is needed so that people can find out enough daily nutritional alternatives based on potential commodities in Indonesia. Data used in study amounted 250 data sourced from Indonesian Ministry of Health regarding composition of food ingredients. Purpose of this study is examine which method is best by comparing K-Means and Isodata clustering algorithms based on the quality of clusters produced. Cluster quality measurements using Silhoutte Coefficient method. Based on tests conducted, Silhoutte Coefficient K-Means algorithm is 0.996762 and Isodata algorithm is 0.996910. Both these methods have small difference value but Isodata algorithm has greater Silhouette Coefficient value than K-Means algorithm in clustering Food Composition Data.
Klasifikasi Status Gunung Berapi dengan Metode Learning Vector Quantization (LVQ) Chelsa Farah Virkhansa; Budi Darma Setiawan; Candra Dewi
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 (1011.183 KB)

Abstract

There are 129 active volcanoes and 500 inactive volcanoes located in Indonesia. Residents who live around areas that are susceptible to volcanic eruptions are quite numerous, which is as much as 10% of Indonesia's population. From the number of volcanoes that are still active there are only 69 mountains monitored, so there are still many active volcanoes which are not well monitored, which is around 40%. So that information on the status of the volcano is needed as quickly and accurately as possible to reduce the impact caused by the volcanic eruption. In this research, volcanic status classification will be carried out using the Learning Vector Quantization method. this study uses data totaling 110 data. The data was obtained from the website of the Volcanology Center and Geological Disaster Mitigation (PVMBG). From the tests that have been done, the highest accuracy is 88% when using the learning rate 0.1, the learning rate deduction is 0.1 and the minimum learning rate is 0.01.
Prediksi Harga Bekatul menggunakan Metode Fuzzy Time Series Oky Krisdiantoro; Budi Darma Setiawan; Muhammad Tanzil Furqon
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 (445.982 KB)

Abstract

Rice bran is one of the raw materials used as a mixture of animal feed concentrates, the use of rice bran in animal feed concentrates is 10% -30% from about 10 other types of raw materials mixed. with the number of percentages used, the company needs to pay attention to the availability of rice bran and also the price that changes every month, if the price of rice bran is too expensive it will change the basic price of animal feed concentrate, so the company must be able to predict the price of rice bran in the next month so that they can supply more rice bran when the prices would increase. To predict prices, we can use the fuzzy time series method with reference to historical data from the previous months, with which we can find out the price predictions of rice bran in the following month. The results of this study are expected to be able to help animal feed concentrate companies to be able to predict the price of bran in the coming months, in this study the best predictions resulted in a MAPE value of 4.43% with a number of training data 36 and interval length 12.
Optimasi Kombinasi Bahan Makanan untuk Mencegah Stunting pada Balita dengan menggunakan Algoritme Genetika Tria Melia Masdiana Safitri; Imam Cholisoddin; Budi Darma Setiawan
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 (511.969 KB)

Abstract

The number of good nutrients provided to kids in Indonesia has been a common problem and has yet to be solved. The lack of nutritional intake can cause malnutrition and stunting (the lack of height growth). Indonesia has become the fifth biggest country in terms of the numbers of toodlers suffering stunting, whose numbers have risen to nearly 9 million toddler. Stunting in toddlers can be caused by many factors, one of which is the lack of knowledge possessed by the parents of the combination of a variety of food ingredients which must be fed to the toddler in order to provide a perfectly balanced supply of nutrients. Providing a single dish does not always provide a perfectly balanced supply of nutrients. Providing a stable supply of perfectly balanced nutrients can be achieved by a variety of food ingredient combinations that contain roughly the same amount of nutrients. In this research, a recommendation of food compositions was provided through the course of 7 days using a genetic algorithm to assist parents in combining food ingredients which corresponded with a toddler's nutritional needs. Based on the testing parameters of the genetic algorithm, the optimal results from the combination of Cr:Mr test was 0,7:0,3 and the fitness results had an average score of 97,412. The testing results on the optimal size of the population was discovered to be 90 with an average fitness score of 96,95. Testing of the most optimal number of generations that need to be generated were 350 generations with an average fitness score of 96,664. The result of the test was capable of saving the parents expenses as much as 35,77% with the average cost of a dish was Rp.19269,21.
Co-Authors Abdul Fatih Achmad Basuki Achmad Fahlevi Addin Sahirah, Rafifa Adinugroho, Sigit Aditya Chandra Nurhakim Aditya Kresna Bayu Arda Putra Agung Nurjaya Megantara Agus Wahyu Widodo Ahmad Afif Supianto Akhmad Eriq Ghozali Akmal Subakti Wicaksana Alfi Nur Rusydi Almira Syawli, Almira Amaliah Gusfadilah Andhi Surya Wicaksana Andika Harlan Angga Dwi Apria Rifandi Anjasari, Ni Luh Made Beathris Aria Bayu Elfajar Asghany, Yusrian Ashidiq, Muhammad Fihan Azmi Makarima Yattaqillah Baihaqi, Galih Restu Barlian Henryranu Prasetio Bayu Rahayudi Bintang, Tulistyana Irfany Budi Santoso Cahyo Adi Prasojo Candra Dewi Candra Dewi Chelsa Farah Virkhansa Cindy Inka Sari Cinthia Vairra Hudiyanti Civica Moehaimin Dhewanty Deby Chintya Dellia Airyn Delpiero, Rangga Raditya Dewi, Buana Dhan Adhillah Mardhika Dian Eka Ratnawati Diva, Zahra Dwi Anggraeni Kuntjoro Dwi Ari Suryaningrum Dwi Damara Kartikasari Edo Fadila Sirat Eka Novita Shandra Eka Yuni Darmayanti Eti Setiawati Fadhlillah Ikhsan Fajar Nur Rohmat Fauzan Jaya Aziz Fajar Pradana Fanny Aulia Dewi Fattah, Rafi Indra Fatwa Ramdani, Fatwa Febri Ramadhani Fikri Hilman Fitra Abdurrachman Bachtiar Fitria, Tharessa Fitrotuzzakiyah, Shafira Puspa Gandhi Ramadhona Gembong Edhi Setiawan Gilang Ramadhan Hendra Pratama Budianto Husin Muhamad Imam Cholisoddin Imam Cholissodin Imam Cholissodin Imam Cholissodin Indah Larasati Indriati Indriati Indriati Irawati Nurmala Sari Irfan Aprison Irma Lailatul Khoiriyah Irma Nurvianti Irma Ramadanti Fitriyani Ismiarta Aknuranda Issa Arwani Issa Arwani Jobel, Roenrico Karina Widyawati Keintjem, Arthurito Khairunnisa, Alifah Kholifa'ul Khoirin Koko Pradityo Lailil Muflikhah Lathania, Laela Salma M Kevin Pahlevi M. Ali Fauzi M. Raabith Rifqi M. Rikzal Humam Al Kholili M. Tanzil Furqon Mahar Beta Adi Sucipto, Ekmaldzaki Royhan Mahendra Data Mahendra Data Marji Marji Masayu Vidya Rosyidah Maulana, M. Aziz Mayang Arinda Yudantiar Meilia, Vina Mimin Putri Raharyani Mindiasari, Irtiyah Izzaty Miracle Fachrunnisa Almas Moch. Khabibul Karim Mochamad Chandra Saputra Mohamad Alfi Fauzan Muhammad Arif Hermawan Muhammad Dimas Setiawan Sanapiah Muhammad Harish Rahmatullah Muhammad Khaerul Ardi Muhammad Rizkan Arif Muhammad Syaifuddin Zuhri Muhammad Tanzil Furqon Mustofa Robbani Muthia Azzahra Nadia Natasa Tresia Sitorus Nainggolan, Cesilia Natasya Nanda Agung Putra Nashrullah, Nashrullah Nelli Nur Rahma Ni'mah Firsta Cahya Susilo Nihru Nafi' Dzikrulloh Noval Dini Maulana Novanto Yudistira Nur Intan Savitri Bromastuty Nurfansepta, Amira Ghina Nurhana Rahmadani Nurudin Santoso Nurul Hidayat Oky Krisdiantoro Olive Khoirul L.M.A. Panjaitan, Mutiharis Dauber Pindo Bagus Adiatmaja priharsari, diah Purnomo, Welly Putra Pandu Adikara Putra, Octo Perdana Putri, Rania Aprilia Dwi Setya Rachmatika, Isnayni Sugma Radifah Radifah Rafely Chandra Rizkilillah Rahmadi, Anang Bagus Rahmat Faizal Raissa Arniantya Ramadhianti, Fatiha Randy Cahya Wihandika Ratna Candra Ika Rekyan Regasari Mardi Putri, Rekyan Regasari Mardi Rekyan Regasari MP, Rekyan Regasari Rendi Cahya Wihandika Retiana Fadma Pertiwi Sinaga Revanza, Muhammad Nugraha Delta Revinda Bertananda Reza Wahyu Wardani Rhobith, Muhammad Ridho Agung Gumelar Rima Diah Wardhani Rinda Wahyuni Rizal Setya Perdana Rizal Setya Perdana Rizki Agung Pambudi Rizky Haqmanullah Pambudi Robih Dini Rosi Afiqo Rudito Pujiarso Nugroho Rudy Usman Azzakky Ryan Mahaputra Krishnanda Sabriansyah Rizkiqa Akbar Santoso, Nurudin Satrio Hadi Wijoyo Shelly Puspa Ardina Sigit Adinugroho Silfiatul Ulumiyah Sintiya, Karena Siti Fatimah Al Uswah Siti Utami Fhylayli Sri Wahyuni Suryani Agustin Sutrisna, Naufal Putra Sutrisno Sutrisno Tahajuda Mandariansah Talitha Raissa Tibyani Tibyani Tri Afirianto Tria Melia Masdiana Safitri Ulfah Mutmainnah Vina Meilia Wayan Firdaus Mahmudy Wildannantha, Jawadi Ahmad Yerry Anggoro Yosendra Evriyantino Yuhand Pramudita, Rezzy Yuita Arum Sari Yuita Arum Sari Yulfa Hadi Wicaksono Zubaidah Al Ubaidah Sakti