Claim Missing Document
Check
Articles

Penerapan Hibridisasi Algoritme Genetika dan Simulated Annealing untuk Optimasi Vehicle Routing Problem pada Kasus Pengangkutan Sampah Kota Denpasar Putu Gede Pakusadewa; Candra Dewi; Randy Cahya Wihandika
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 9 (2018): September 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (969.154 KB)

Abstract

Handling municipal garbage is one of the problems that exist in a big city including the city of Denpasar. The amount of waste on certain days such as religious holidays will increase significantly where the 4-shift schedule used is inadequate to transport all the waste at certain TPS. Determination of the optimal route of garbage transportation is needed to save work time, lower operational costs and capable to transport all the waste. This research applies hybrid genetic algorithm and simulated annealing to optimize municipal garbage collection transportation route. The representation of chromosomes used is permutation representation with two segments namely the route segment and the truck segment. The process stage uses crossover with order crossover method and mutation with one-cut point method. The test results show the best fitness value is 1,042568623 with optimal parameters using population number = 400, crossover rate and mutation rate = 0.9 and 0.1, number of generations = 200, initial temperature = 1000, final temperature = 1, and alpha/cooling rate = 0.1. The result of this research is recommendation of optimal transportation route to collect garbage from a number of TPS.
Identifikasi Penyakit Gagal Ginjal Menggunakan Metode Neighbor Weighted K-Nearest Neighbor (NWKNN) Azizul Hanifah Hadi; Dian Eka Ratnawati; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 9 (2018): September 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (664.785 KB)

Abstract

Kidney disease can be caused by several factors such as hypertension, uric acid levels, creatinine levels, diabetes, and many others. From that factors, we know about the level of kidney disease risk. Some people are unaware, lazy and indifferent about health, especially on kidney disease because of the long process and complicated. According to the Indonesian Renal Registry, in 2014 patients with kidney disease in Indonesia reach 12,770 inhabitants. Therefore, we need a system that can detect or identify the kidney disease. In this research, we will identify the kidney disease using Neighbor Weighted K-Nearest Neighbor (NWKNN) method. This method is similar to the KNN method but the differentiates are in the weighting process in each identification class. Identification class in this study decided in two part, ckd or exposed to kidney disease and notckd or not affected kidney disease. The results of this study indicate that the NWKNN method can identify kidney disease when the data are 150 data and the test data are 50 data with K = 2 and E = 2 and accuracy level is 88%.
Pemodelan Regresi Linear untuk Prediksi Konsumsi Energi Primer Indonesia Menggunakan Hybrid Particle Swarm Optimization dan Continuous Ant Colony Optimization Faris Febrianto; Candra Dewi; Bayu Rahayudi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 9 (2018): September 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1294.789 KB)

Abstract

Primary energy consumption prediction is an important to project future government energy policy in any country. However, many primary energy consumption prediction often lack of accuracy and data sources. Indonesia primary energy consumption is the biggest than other country in south east asia region and fourth in asia pacific. Indonesia primary energy consumption always increased due to rapid economic growth in last few years, it raised 16% only in three years, 149.31Mtoe in 2010 to 174.24Mtoe in 2013. Indonesia primary energy sources from fossils energy, oil, gas, and coal, otherwise hydro energy, and other renewables energy only 3.33% from total consumption. Our aim is to create primary energy consumption prediction accurately from five input parameter, gross national income, gross domestic product, population, import, and eksport. We use multiple linear regression modelling with find intercept and slope coefficient using hybrid Particle Swarm Optimization and Continuous Ant Colony Optimization. Experiment results shows that linear regression model has average Mean Absolute Percentage Error 10.1% which is good category for primary energy consumption prediction. Hybrid method also compared with regression using standalone Particle Swarm Optimization and standalone Continuous Ant Colony Optimization.
Klasifikasi Jenis Audio Berdasarkan Kondisi Psikologi Menggunakan Kombinasi Algoritme Self Organizing Maps dan Learning Vector Quantization Rayhan Tsani Putra; Imam Cholissodin; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 9 (2018): September 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (976.197 KB)

Abstract

The characteristics of each type of audio have different effects on human emotions as well as what activities are being performed. The most common case in most societies is listening to music that has been commonly heard without caring about the right conditions. It would be better if you can maximize the positive impact of the audio. Classification of audio types will be very helpful in determining the appropriate audio type. This study classifies the type of audio based on one of the psychological conditions of emotion and also some types of activities using a combination of SOM-LVQ algorithms (Self Organizing Map and Learning Vector Quantization). SOM is used as an algorithm that accompanies and trains initial weights for LVQ because it has a structure and workflow similar to LVQ. Feature used in this research is 11 which consist of psychology condition and activity type. There are 4 types of audio that became the class in this study. The maximum accuracy obtained in this study was 89.583%. The SOM-LVQ algorithm combination achieves the maximum accuracy with 4 training iterations, while LVQ requires 6 iterations to achieve maximum value. Although with the same accuracy, SOM-LVQ is faster to get the optimal value.
Optimasi Multiple Travelling Salesman Problem (M-TSP) Pada Penentuan Rute Optimal Penjemputan Penumpang Travel Menggunakan Algoritme Genetika. Pande Made Rai Raditya; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 10 (2018): Oktober 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1115.651 KB)

Abstract

Passengers enthusiasm in using travel services can be figured out through the increasing number of travel companies that are easily found in every city. Malang city is a region where the population is quite crowded with the large number of students, as well as students who come from outside the city. This makes more and more travel services emerge in Malang. Optimal route determination is a very notable problem to solve because it influences the time and operational costs of the vehicle. In this study, optimization of the optimal route determination using more than one salesman and starts from the travel office to the address of picking up each passenger. These problems belong to the problem of Multi Traveling Salesman Problem (M-TSP) and one of the algorithms to solve the M-TSP problem is by using genetic algorithm. In this case, it is used permutation representation, crossover reproduction process by one cut point crossover, mutation process by exchange mutation, and selection process by elitism selection. After conducting trials by using 30 locations, it is obtained that the results of the most optimal parameters is in the population which the population size is 80, with the number of cars traveling is 6, 450 generations, 0.6 and mr 0.4 and 0.4. The results of the program with these parameters resulted in the highest average fitness value of 8.09338.
Clustering Titik Panas Bumi Menggunakan Algoritme Affinity Propagation Barik Kresna Amijaya; Muhammad Tanzil Furqon; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 10 (2018): Oktober 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (283.298 KB)

Abstract

Forest and land fires are catastrophic and can disrupt the activity of living things around the fire location. Forest and land fires should be prevented by knowing the cause of the fire. One of the ways of fire prevention is to monitor the hotspot. The hotspot is an area where the temperature is relatively higher compared to the area around which the satellite is detected. The area is represented in a point that has certain coordinates. hotspot needs to be grouped or clustered to know the similarity of each point and easy to do monitoring. Clustering is the process of grouping data into clusters, so that objects that exist within a cluster have a high similarity with each other and very different from the objects that exist in other clusters. Affinity Propagation method is a method used to perform data grouping by specifying the exemplar as data centers. Affinity Propagation performs clustering by searching for responsibility value and availability of each data to find the right exemplar. In this research has done clustering using Affinity Propagation with the best silhouette coefficient value that is 0.317818 with 125 data and formed 44 clusters.
Sistem Temu Kembali Citra Lubang Jalan Aspal Berdasarkan Tingkat Kerusakan Menggunakan Ekstraksi Fitur Gray Level Co-occurrence Matrix Anggita Mahardika; Yuita Arum Sari; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 10 (2018): Oktober 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (832.732 KB)

Abstract

One factors of the road repair process that takes a long time caused by the process of recording the condition of road damage that is still done manually by human labor. Along with the development of technology, many research related to road damage detection system using digital image processing. The purpose of this research is to build a retrieval system of asphalt pavement image based on damage level. The process begins with pre-processing to get a segmented hole area. Furthermore, utilizing feature extraction of Gray Level Co-occurrence Matrix (GLCM) texture. Features used in this research are as many as 52 features derived from 13 features with angles 0o, 45o, 90o and 135o. Of the 52 features performed feature selection using Wrapper and CFS (Correlation Based Feature Selection) methods. Based on the results of the tests that have been done we get the image of 117 holes that successfully segmented successfully on the diameter of 101x101, = 75 and =75. Use of the Wrapper feature selection method gives higher average accuracy and MAP (Mean Average Precision) results than using the CFS feature selection method or not using feature selection. Accuracy and MAP resulting from Wrapper method with d = 1 respectively that is equal to 55.61% and 0.710.
Penerapan Metode Extreme Learning Machine (ELM) Untuk Memprediksi Jumlah Produksi Pipa Yang Layak (Studi Kasus Pada PT. KHI Pipe Industries) Nirzha Maulidya Ashar; Imam Cholisoddin; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 11 (2018): November 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (496.85 KB)

Abstract

KHI Pipe Industries is a company that specializes in producing high-quality steel pipes. This company produces its end product based on customer demand, with the measurement specifications which is diameter, thickness and the pipe length. In the production process, the amount of viable pipes do not always match with the number of customers demand since there were always a number of damaged pipes. Therefore, the company has always have to spend additional cost to cover the the damaged pipes. The number of production on each specifications varies so that it becomes a challenge for the company to predict the exact amount of pipes to produce. With the appropriate prediction of the number of pipes to produce can help the company to determine the production target. In this research applied method of Artificial Neural Network (ANN) that is Extreme Learning Machine (ELM) to predict the amount of approved pipe production. The prediction process is normalization, training, testing, and denormalization, and to calculate the error value using Mean Square Error (MSE). Based on evaluation performed, the use of 7 hidden neurons, 5 features, and percentage comparison 80% of training data 20% of testing data resulted in the smallest error average is 0,00372 with difference ± 1% to actual data.
Prediksi Nilai Tukar Rupiah Terhadap Dolar Amerika Dengan Menggunakan Algoritme Genetika - Backpropagation Dwi Novi Setiawan; Candra Dewi; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 11 (2018): November 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (925.462 KB)

Abstract

The exchange rate is the value of the currency of a country which is expressed in the form of currency of another country. Exchange rate has an important role in international trade. To maintain the stability of the rupiah exchange rate, the government needs to enact the right policy. Therefore, a prediction algorithm that is able to recognize the pattern of exchange rate changes is needed. Backpropagation is one of method that is able to recognize patterns in time series data, while Genetic Algorithm is one of the capable method to exploring wider solutions for Backpropagation. In the Genetic Algorithm, the weight of Backpropagation is represented in real-code. Implementation of Genetic Algorithm - Backpropagation has initialization phase of population, crossover, mutation, individual training using Backpropagation, evaluation, and selection. The most optimum parameters for Genetic Algorithm - Backpropagation are in 90th generation, 20 population size, 0.1 crossover rate, 0.9 mutation rate, number of neurons in hidden layer 13, learning rate 1 and number of iteration of Backpropagation training were 500. The results of the tests that have been done got the best MAPE value of 1.575318 and the average MAPE of 1.741747. The algorithm is also capable of performing the best validation with MAPE of 1,0004917 and the average MAPE of 1.077603.
Peramalan Jumlah Pemakaian Air di PT Pembangkit Jawa Bali Unit Gresik dengan Extreme Learning Machine dan Ant Colony Optimization Anim Rofi'ah; Imam Cholissodin; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 11 (2018): November 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1134.215 KB)

Abstract

PT. PJB Unit Gresik using seawater as a steam power plant. Water has advantages such as it is high availability and environmentally friendly. However, seawater requires a refining process in order to be used. Using seawater as a power plant often experiences water-reduction problems caused by certain problems, such a pipeline leakage, tempering, and removal of gases that still contain water so that additional water is required to keep the turbin working. To anticipate the lack of water that can inhibit the process, an intelligent system required to estimate the amount of water that generation process needed. One of forecasting method is Extreme Learning Machine (ELM), to maximize forecasting results with optimization algorithm Ant Colony Optimization that can be used in the optimization input weight and bias of ELM parameters. After optimization process for ELM parameters, then the next process is training and testing to get forecasting result. This study uses 103 data. Based on the research, the optimal parameter number of ants is 40, the parameter range of the input weight is 0 to 1, the using 82 of training data and 21 testing data (80%: 20%), and the maximum iteration is 500. From these parameters obtained the MAPE value for ELM-ACO is 0.170% with 3799.200 ms running time and for the ELM algorithm the MAPE value is 4.851% with 162.400 ms, so the optimization of ELM parameters can improve the forecasting results.
Co-Authors Abdul Fatih Achmad Yusuf Adam Sulthoni Akbar Adinugroho, Sigit Aditya Chandra Nurhakim Aditya Septadaya Adiyasa, Bhisma Afrialdy, Firman Aghata Agung Dwi Kusuma Wibowo Agi Putra Kharisma Agus Wahyu Widodo Ahmad Afif Supianto Ahmad Afif Supianto Ahmada Bastomi Wijaya Akmal Subakti Wicaksana Alan Primandana Almasyhur, Muhammad Bin Djafar Amalia Luhung Amita Tri Prasasti, Pinkan Anang Tri Wiratno Andhika Satria Pria Anugerah Anggita Mahardika Ani Budi Astuti Ani Rusilowati Anim Rofi'ah Annisa Puspitawuri Annisa Salamah Rahmadhani Arbawa, Yoke Kusuma Aria Bayu Elfajar Arief Andy Soebroto Arjunani, Rusmalistia Intan Ayuri Alfarianti Azhari, Muhammad Rizqi Azizul Hanifah Hadi Barik Kresna Amijaya Bayu Rahayudi Brillian Aristyo Rahadian Budi Astuti Budi Darma Setiawan Chelsa Farah Virkhansa Daneswara Jauhari Daneswara Jauhari, Daneswara Dany Primanita Kartikasari Dennes Nur Dwi Iriantoro Deo Hernando Desy Wulandari Dewanti, Amalya Trisuci Diajeng Tania Ananda Paramitha Dian Eka Ratnawati Dloifur Rohman Alghifari Dwi Fitriani Dwi Novi Setiawan Dwi, Endah Dyang Falila Pramesti Edo Ergi Prayogo Edy Santoso Edy Santoso Erik Aditia Ismaya Eriq Muh. Adams Jonemaro Falih Gozi Febrinanto Faris Febrianto Febri Ramadhani Fenori, Muhammad Dajuma Feri Angga Saputra Fianti Fianti, Fianti Fitri Anggarsari Fitriana, Rosita Nur Fitriani , Dwi Fitriani, Delvi Guntur Syafiqi Adidarmawan Himawan, Alfian Iftinan, Salsa Nabila Ikhwanul Kiram, Muh Zaqi Ilham Harazki Imam Cholisoddin Imam Cholissodin Imam Cholissodin Indah Lestari, Indah Indah Wahyuning Ati Indah, Yuliana Indra Eka Mandriana Indriati Indriati Indriati Indriati Indriati, Indriati - Iqbal Santoso Putra Iskarimah Hidayatin JANAH, NURUL Jumadi Jumadi Khairiyyah Nur Aisyah Kharisma, Agi Krisyanto, Edy Kurnianingtyas, Diva Kurniawan, I Gede Jayadi Kusumawardani, Septyana Dwi Lailil Muflikah Lailil Muflikhah Maharani Tri Hastuti Mardji Mardji Marinda Ika Dewi Sakariana Marinda, Vira Marwa Mudrikatussalamah Maulan, Erika Maulana Putra Pambudi Maulida, Farida Mochammad Tanzil Furqon Mohammad Nuh Mohammad Setya Adi Fauzi Muh Arif Rahman Muhammad Ihsan Diputra Muhammad Misbachul Asrori Muhammad Noor Taufiq Muhammad Prabu Sutomo Muhammad Riduan Indra Hariwijaya Muhammad Tanzil Furqon Muhja Mufidah Afaf Amirah Muhyidin Ubaiddillah Mukh. Mart Hans Luber Nabila Arief Nadia Artha Dewi Naily Zakiyatil Ilahiyah Naniek Kusumawati Nazzun Hanif Ahsani Nirzha Maulidya Ashar Nooriza Fariha Rumagutawan Noval Dini Maulana Novanto Yudistira Nur Hidayat Nur Sa'diyah Nurhidayati Desiani Nurul Faridah, Nurul Nurul Hidayat Nuryatman, Pamelia Nuzula, Nila Firdauzi Pande Made Rai Raditya Phutpitasari, Rosa Devi Pupung Adi Prasetyo Putra Pandu Adikara Putri Aprilia Putu Gede Pakusadewa Rachmalia Dewi Rahma Juwita Sany Randy Cahya Wihandika Ratih Kartika Dewi Rayhan Tsani Putra Reiza Adi Cahya Reza Wahyu Wardani Rifan, Mohamad Rina Christanti, Rina Rizal Setya Perdana Rizal, Moch. Khabibur Robih Dini Rohmah, Yushinta Lailatul Rohmanurmeta, Fauzatul Ma’rufah Rokky Septian Suhartanto Romlah Tantiati Rosyita, Elyana Santoso, Allegra Santoso, Andri Saputra, Rendi Ramadani Saputro, Rinaldi Eko Saputro Sekar Dwi Ardianti Selle, Nurfatima Selvi Marcellia Setya Perdana, Rizal Sigit Pangestu Siti Nurjanah Siti Nurlaela Sundari, Suci Sunyoto Eko Nugroho, Sunyoto Eko Susenohaji, Susenohaji Sutrisno . Syarif, Adnan Tirana Noor Fatyanosa, Tirana Noor Ulfah Mutmainnah Veni, Silvia Wahyu, Dwi Wayan Firdaus Mahmudy Werdha Wilubertha Himawati, Werdha Wilubertha Wiandono Saputro Wilis Biro Syamhuri Wiratama Paramasatya Yasin, Patbessani Septani Firman Yessica Inggir Febiola Yosua Christopher Sitanggang Yudha Eka Permana Yudistira, Indrajati Yuita Arum Sari Yulia Trianandi Yulian Ekananta Yusi Tyroni Mursityo Zulhan, Galang