Claim Missing Document
Check
Articles

Pelatihan Feedforward Neural Network Menggunakan PSO untuk Prediksi Jumlah Pengangguran Terbuka di Indonesia Bayu Septyo Adi; Dian Eka Ratnawati; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 11 (2017): November 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (794.323 KB)

Abstract

Open unemployment is a problem who faced by Indonesia in every year. In Indonesia, the number of an open unemployment is still in the high level. There are many factors influence the number of open unemployment, the one of that factor is the number of employement not comparable with the number of labor force. When the number of unemployment at the high level, it can influence the other sector, especially at the economy sector. Because of the number of unemployment is high, national income getting decrease and poorness getting increase. Prediction the number of open unemployment, can be expect to help government and other agence to decreasing the number of open unemployment in Indonesian. Feedforward Neural Network is model from artificial neural network which can be implemented for prediction. Backpropagation algorithm can be replaced by Particle Swarm Optimization Algorithm (PSO) for training Feedforward Neural Network . The result in this research, average value of error which is calculated by Average Forecast Error Rate (AFER) is 2.71399%. Based on value of AFER in this reaserch, Feedforward Neural Network trained by PSO method can be using for predicting the number of open unemployment in Indonesia with better accuracy.
Peramalan Suku Bunga Acuan (BI Rate) Menggunakan Metode Fuzzy Time Series dengan Percentage Change Sebagai Universe of Discourse Wiratama Paramasatya; Dian Eka Ratnawati; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 11 (2017): November 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (920.477 KB)

Abstract

BI rate is the interest rate policy that reflects the monetary stance policy which set by the Central Bank of Indonesia and announced to the public. BI rate greatly affects the trade, industry, stock prices, and especially banking. If the policy rate set by the Board of Governors is not in accordance with the trend of economic conditions at a certain time it will have a negative impact on the economic condition of Indonesia. This is what causes the importance of BI rate forecasting in the hope that business players can anticipate the long-term impact of BI rate determination. This research implements fuzzy time series using percentage change as the universe of discourse to predict BI rate in certain period. This method focuses on forming the universe of discourse and the development of steps to form an interval. Based on the results of the tests that have been done, using the best variable values ​​are 12 as the initial interval length, 2 as the value of n-topFrequency 2, and 10 as the length of sub-interval produce MAPE of 0.09005%. The final result obtained is the result of BI rate forecasting according to the period that the user wants to forecast.
Deteksi Penyakit Kucing dengan Menggunakan Modified K-Nearest Neighbor Teroptimasi (Studi Kasus: Puskeswan Klinik Hewan dan Satwa Sehat Kota Kediri) Fitri Dwi Astuti; Dian Eka Ratnawati; Agus Wahyu Widodo
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 11 (2017): November 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1017.915 KB)

Abstract

Cats are animals that are widely nurtured by people, so there are now many findings related to cat disease caused by many factors. Knowledge and understanding of the symptoms that occur in the cat to be an important factor, so that people can better anticipate the occurrence of more severe disease. With some of the problems that have been described before then give the idea to built an application "Deteksi Penyakit Kucing". In this study the method used is Modified K-Nearest Neighbor, but the method has a weakness in the biased k value, so the accuracy of the resulting level sometimes less than the maximum. Given the problem, the genetic algorithm is used to optimize k value in the Modified K-Nearest Neighbor method. Data used in this research is cat disease data at Puskeswan Klinik Hewan dan Satwa Sehat of Kediri with amount of training data as many as 105 and test data counted 35. From all data will be classified into 7 class with criterion as much as 19. Accuracy result of Modified K-Nearest Neighbor using genetic algorithm for optimal k 1 is 100%. From these results the application of cat disease detection with optimal k value can be used by the public to recognize diseases in cats.
Prediksi Waktu Panen Tebu Menggunakan Gabungan Metode Backpropagation dan Algoritma Genetika Dwi Ari Suryaningrum; Dian Eka Ratnawati; Budi Darma Setiawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 11 (2017): November 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (708.75 KB)

Abstract

Before sugar cane was milled by the factory, the first process is analysis of sugar cane maturity. The best sugar cane condition to be ground is mature cane that can be seen from several factors such as garden area, age, stem diameter, the average segment per stem and the average length per stem. These factors are used as attributes in the research conducted. To simplify the process, then we proposed this research on the prediction of sugar cane harvest time. With so much data being used and repeated processes, it will be difficult to process manually and takes a long time. In addition, the manual process does not close the possibility of an increasing error. This research uses a combination of genetic algorithm and backpropagation in the process of predicting the harvest time. Genetic algorithms are the best solution used to optimize prediction results by weight selection and bias. Backpropagation method is used to calculate Mean Square Error (MSE) value, which will be used in calculation of fitness value and also on prediction of data test. In this research will be done five kinds of testing, as follows generation test, population size test, test combination of crossover rate and mutation rate, testing of learning rate and testing of Average Forecasting Error Rate (AFER). The result of this research are predictions of harvest time, the value of fitness and AFER. The best result is result of AFER value is 0,0205%.
Penentuan Lokasi Pasang Baru Wifi.id Corner Menggunakan Metode AHP dan Algoritma Genetika (Studi Kasus : PT. Telkom Witel Kediri) Figgy Rosaliana; Dian Eka Ratnawati; Mochammad Ali Fauzi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 12 (2017): Desember 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (903.438 KB)

Abstract

Wifi.id corner is a location provided by Telkom Corporation to access @wifi.id network. Determining new location of wifi.id corner needs consideration and right decision. Several criterias are used to this study such as Fiber Optic network availability, level of crowdedness, location type and density level of wifi.id corner location. Analytical Hyrarchy Process (AHP) method and Genetic Algorithm are applied to solve those problems. Genetic Algorithm will optimize the weight of AHP process. This algorithm uses real code chromosome representation with length of 6 genes, each gene represent element of weighted matrix value. The Reproduction uses crossover intermediate and random mutation. In the evaluation, AHP process determine feasibility of location then will be calculated its fitness by using accuracy formula. Selection method uses elllism s election. From the result of study, optimal parameter obtained in population size of 80, number of generation 85, combination of cr 0.4 and mr 0.2 with average fitness value 0.700 or accuracy of 70%. Location feasibility will be shown to users as the final result of the system.
Penentuan Kelayakan Lokasi Wifi.Id Corner Dengan AHP-PSO (Studi Kasus: Telkom Kota Kediri) Ulfa Lina Wulandari; Dian Eka Ratnawati; Mochammad Ali Fauzi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 1 (2018): Januari 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (818.749 KB)

Abstract

Wifi.id Corner (wico) is a public facility of innovation from Telkom in the form of a place that provides internet access with high speed up to 100 Mbps. Currently, the determination of the location of Wifi.id Corner Telkom Kediri is done based on the consideration of the parties and managers of Wireless Broadband Division (DWB). So often have difficulty in determining the feasibility of installation location Wifi.id Corner from several proposed locations. This is due to the difficulty to determine the feasibility of location and which location can provide maximum benefits for the community and for Telkom Kediri. In determining the feasibility of Wifi.id Corner location there are 4 criteria by the company. There are the availability of network, users crowded, location type and density of Wifi.id Corner around the location. To solve this problem used Analytic Hierarchy Process (AHP) and Particle Swarm Optimization (PSO) methods. PSO is used to optimize the value of comparison matrix weight in AHP. The length of the used dimension is 6. Where each dimension value represents the comparative value of each criteria in the comparison matrix. In this research used 50 data location of Wifi.id Corner Telkom Kediri. From the test results obtained by the average fitness value of 0,94 with parameters of threshold value of 0,018, size of particles is 250 and number of iteration is 10 so that the obtained accuracy is 94%.
Optimasi Susunan Gizi Makanan Bagi Pasien Rawat Jalan Penyakit Jantung Menggunakan Real Coded Genetic Algorithm (RCGA) Ratih Diah Puspitasari; Dian Eka Ratnawati; Mochammad Ali Fauzi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 1 (2018): Januari 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1046.382 KB)

Abstract

Heart is one of the most important organs in the human body. Nowadays, coronary heart disease is one of the diseases that tend to invade a person's heart and dietary arrangements is a must for people who have this kind of disease in order to be healthy like normal people. This research is focused on recommending food nutrition for outpatients who suffers from coronary heart disease that often called diet heart 4. This study, titled optimization arrangement of food nutrition for outpatient using real coded genetic algorithm (rcga), the results that is displayed by the program is patient's data such as age, weight, height and foodstuffs that comply with the needs of the outpatients with the lowest prices of any food. This algorithm consists of an initial population of the initialization stage, the reproduction consisting of crossover and mutation, the calculation of the fitness and selection. The research on using the names of 271 food with nutrient content (source of carbohydrates, a source of protein, vegetable source of protein, vegetables, fruits, snacks, and oil/FAT). From the results of testing, this research obtained optimal parameters of 500 population with average fitness of 12347, 3, 50 generations with average fitness of 11795.8 and the combination of cr = 0 and mr = 0.9. with an average value of fitness 11940.7. The results of the program with the parameter generate an average median difference in actual data - with data from the program of 51.815 or 2.30%.
Prediksi Suku Bunga Acuan (BI Rate) Menggunakan Metode Adaptive Neuro Fuzzy Inference System (ANFIS) Nur Adli Ari Darmawand; Dian Eka Ratnawati; Rizal Setya Perdana
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 1 (2018): Januari 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (992.843 KB)

Abstract

BI Rate is the interest rate policy that reflects the monetary stance policy which set by Bank of Indonesia and announced to the public. BI Rate is used as the parameter of economic activity of a country. BI Rate will affect the turnover of bank financial flows, inflation, and currency movement. The ups and downs of BI Rate are highly important for investors and market participants to increase or decrease the amount of production and to increase or decrease existing investment. That's what makes the BI Rate prediction important. The predicted BI Rate is expected to help investors and market participants to determine long-term economic decisions. In this study used Adaptive Neuro Fuzzy Inference System method which is a combination of steepest descent and least square estimator (LSE) algorithm for training. Based on the test results, it produces the best RMSE value 0.0019165.The final result obtained is the predicted value of bi rate.
Klasifikasi Berita Online dengan menggunakan Pembobotan TF-IDF dan Cosine Similarity Bening Herwijayanti; Dian Eka Ratnawati; Lailil Muflikhah
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 1 (2018): Januari 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1034.548 KB)

Abstract

In discussing the online news by using the weighting of tf-idf and cosine of this similarity the previous research reference on online news information using single pass clustering algorithm, where the data to be used comes from the online news website that is kompas.com. Because of the many news that is on the website, so sometimes the news is posted not in accordance with the category. Human error will be the problem of wrong news posting. In addition to posting errors online news groupings are also important for the convenience of users to search for news according to their category. Implementing online news stories using tf-idf and cosine similarities, preprocessing processes ie tokenizing, stopword and stemming can reduce the term process of speeding the weighting of terms using tf-idf and accelerating the cosine process of similarity. The goal is to facilitate human error as well as reduce caution categorization. The value is able to classify news with accreditation rate of 91.25%.
Deteksi Dini Penyakit Gagal Ginjal menggunakan Gabungan Genetic Algorithm dan Fuzzy K-Nearest Neighbor (GAFKNN) Muhyidin Ubaiddillah; Dian Eka Ratnawati; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 2 (2018): Februari 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1039.517 KB)

Abstract

Chronic kidney disease is one type of non-infectious but deadly disease. According to Basic Health Research (2013), this disease in Indonesia has a value of prevention value of approximately 0.2 percent. But some people are still not aware that they have experienced this disease, and their kidney failure disease has been at the stage of chronic renal failure so that one of the treatment is to do dialysis. Whereas if the person is still in early or stage 2 kidney failure, can still do therapy without dialysis. In addition, some people are still lazy to consult, so it takes a program so that people can know their condition and motivated to do a checkup to the doctor. From these problems requires an early detection that can be done by classification. One method that can classify is Fuzzy KNN, but Fuzzy KNN has a weakness that is determining the value of k and m that yield optimal value. So do the merger with GAs. From the results of the merger the program can produce a fairly optimal accuracy of 98%, with parameters on the GAs of population 40, generation 15, CR 0.5 and MR 0.8.
Co-Authors Abdurrahman Airlangga, Aria Abhiram, Muhammad Tegar Achmad Arwan Achmad Ridok Achmad, Riza Putra Adhitya, I Made Yoga Adrian Firmansah, Dani Afif Ridhwan Afrida Djulya Ika Pratiwi Agus Wahyu Widodo Agustin Kartikasari Ahmad Afif Supianto Akbar, Rozaq Aldy Satria Alfa Fadlilah Alifah, Syafira Almira Syawli, Almira Alvian Akmal Nabhan Amonito, Kurnia Ana Mariyam Puspitasari Anak Agung Bagus Arisetiawan Anam, Syaiful Ardhiansyah, Muhammad Hanif Arief Andy Soebroto Arif Pratama Asmoro, Priandhita Sukowidyanti Asroru Maula Romadlon Audia Refanda Permatasari Ayu Dwi Lestari, Cynthia Ayulianita A. Boestari Azizul Hanifah Hadi Bayu Rahayudi Bayu Satriawan, Eka Bayu Septyo Adi Bella Krisanda Easterita Bening Herwijayanti Berton, Freddy Toranggi Buce Trias Hanggara Buce Trias Hanggara Buchori Anantya Firdaus Budi Darma Setiawan Cahyo Gusti Indrayanto Candra Dewi Dany Primanita Kartikasari Darma Setiawan, Budi Darmawan, Riski Davia Werdiastu Denny Manuel Yeremia Sinurat Deny Tisna Amijaya, Fidia Devi Nazhifa Nur Husnina Dewi Yanti Liliana Dhiva Mustikananda Dimas Diandra Audiansyah Dimas Fachrurrozi Azam diniyah, zubaidah Diva, Zahra Djoko Pramono Dwi Ari Suryaningrum Dwi Febry Indarwati Dwi Purwono, Prayoga Dwija Wisnu Brata Dyva Pandhu Adwandha Dzulkarnain, Tsania Dzulkarnain, Tsania - Easterita, Bella Krisanda Edgar Maulana Thoriq Edy Santoso Elfa Fatimah Ema Agasta Entra Betlin Ladauw Eva Agustina Ompusunggu Fadhil, Muhammad Farrasseka Fadila, Putri Nur Faiz Anggiananta Winantoro Fanka Angelina Larasati Fathin Al Ghifari Fatthul Iman Fauzan Dwi Kurniawan, Fauzan Dwi Fauzidan Iqbal Ghiffari Figgy Rosaliana Firdaus, Muhammad Fariz Fitra Abdurrachman Bachtiar Fitri Dwi Astuti Fitria Yesisca Fitria, Tharessa Ghani Fikri Baihaqi glenando Gusti Ngurah Wisnu Paramartha Hadi Wijoyo, Satrio Hamas, radityo Hana Chyntia Morama Hanggara, Buce Trias Hanifa Maulani Ramadhan Haris Haris, Haris Harris Imam Fathoni Hasibuan, Herida Hafni Hasibuan, Raka Ardiansyah Heru Nurwasito Hilal, Khaliffman Rahmat Hilmy Ramadhan, Achmad Zhafran Huda Minhajur Rosyidin I Dewa Gede Ngurah Bramasta Darmawan Ibnu Aqli Ibnu Aqli, Ibnu Ibrahim Kusuma Ilyas, Muhaimin Imam Cholissodin Imam Cholissodin Imam Cholissodin Immanuel Tri Putra Sihaloho Indriati ., Indriati Indriati Indriati Ismiarta Aknuranda Issa Arwani Issa Arwani Isti Marlisa Fitriani Izza, Aisyah Nurul Jesika Silviana Situmorang Jibril Averroes, Muhammad Juan Michel Hesekiel Kartika, Annisa Wuri Kelvin Anggatanata Kevin Renjiro Khairi Ubaidah Khoba, Ahmad Faiz Khofifatunnabilah, Khofifatunnabilah Kirana, Urdha Egha Krishna Febianda Kusuma, Salsabila Azzahra' Zulfa Lailil Muflikhah Leonardo, Ryan Luqman Rizky Dharmawan M. Ali Fauzi Madjid, Marchenda Fayza Maghfiroh, Sofita Hidayatul Mahendra Data Mahendra Data Mala Nurhidayati Maliha Athiya Rahmani Marji . Marji Marji Marji Marji Marji Marji Maulana Syahril Ramadhan Hardiono Michael Eggi Bastian Mochammad Iskandar Ardiyansyah Rochman Moh Fadel Asikin Muh. Arif Rahman MUHAJIR Muhammad Iqbal Mustofa Muhammad Kevin Sandryan Muhammad Reza Utama Pulungan Muhammad Tanzil Furqon Muhyidin Ubaiddillah Muslimah, Fakhriyyatum Muthia Maharani Nabilah Iftah Nella Naily Zakiyatil Ilahiyah Nanang Yudi Setiawan Nanang Yudi Setiawan Nanda Alifiya Santoso Putri Nanda Petty Wahyuningtyas Nilna Fadhila Ganies Norma Desitasari Novirra Dwi Asri Nugraha Perdana, Aditya Nugraheni, Miftakhul Fitria Nur Adli Ari Darmawand Nur Khilmiyatul Ilmiyah Nuraini Anitasari Nuralam, Inggang Perwangsa Nurul Hidayat Nyimas Ayu Widi Indriana Oceandra Audrey Pandu Adikara, Putra Pangestu Ari Wijaya Panjaitan, RE. Miracle Prahesti, Suherni Prakoso, Ricky Pratomo Adinegoro Priyono, Mochammad Fajri Rahmatullah Rendra Puji Indah Lestari Purnomo, Welly Putra Pandu Adikara Putra, Alland Rifqy Putri, Nindy Alya Rachmad, Zikfikri Yulfiandi Raden Rizky Widdie Tigusti Rahma, Dzakiyyah Afifah Rahmah, Yusriyah Raisha, Serefika Raja Farhan Ramadha Pohan Rama Humam Syarokha Randy Cahya Wihandika Rani Metivianis Ratih Diah Puspitasari RE. Miracle Panjaitan Rekyan Regasari Mardi Putri, Rekyan Regasari Mardi Retno Indah Rokhmawati, Retno Indah Revi Anistia Masykuroh Rifqi Irfansyah, Nandana Rizal Setya Perdana Rizal Setya Perdana Robiata Tsania Salsabila Aditya Putri Rodiah Rodiah Ryan Leonardo Salsabillah, Dinar Fairus Saparila Worokinasih Saputro, Dimas Sarie, Riza Athaya Rania Satriawan, Eka Bayu Satrio Agung Wicaksono Satrio Hadi Wijoyo Sema Yuni Fraticasari Setiawan, Alexander Christo Setya Perdana, Rizal Setyowati, Andri Shafira Margaretta Sherly Witanto Sherryl Sugiono Sindarto Sigit Pangestu Silvia Ikmalia Fernanda Siregar, Fauziah Syifa R. Siti Fatimah Al Uswah Sobakhul Munir Siroj Sormin, Hartati Penta Angelina Sri Indrayani, Sri Suhhy Ramzini Sukmawati, A'inun Sutrisno Sutrisno Sutrisno, Sutrisno Syaiful Anam Syifa Namira Neztigaty Thifal Fadiyah Basar Titis Sari Kusuma Ulfa Lina Wulandari Utomo, Yoga Cahyo Vina Adelina Welly Purnomo Wibowo, Shinta Dewi Putri Widhy Hayuhardhika Nugraha Putra Wijanarko, Rizqi Winda Fitri Astiti Winurputra, Raihan Wiratama Paramasatya Yahya, Faiz Yolanda Nailil Ula Yudi Setiawan, Nanang Yuita Arum Sari Yunita Dwi Alfiyanti Yure Firdaus Arifin Zahra, Wardah