Articles
Penyusunan Bahan Makanan Keluarga Penderita Penyakit Hiperkolesterolemia Menggunakan Algoritme Genetika
Sabrina Nurfadilla;
Imam Cholissodin;
Sutrisno Sutrisno
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 8 (2018): Agustus 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (733.002 KB)
To improve the quality of human resource generation required good nutritional needs for everybody. Each member of family needs a nutrition in the same kind but amount of the nutrition is different, that is influenced by age, body shape, gender, physical condition, genetic heredity, and life style. Information of data analysis from Riskesdas which is held in 2007 and 2013 revealed that Indonesian citizen Having problems with quality food consumption of between 80 to 90 percent tend to be less fruit and/or vegetable consumption and approximately 40.7% consume risky foods containing excess fat, cholesterol and fried more than equal to one time per day. From these data nutritional needs with food processing which is consumed by Indonesian citizen still lack. Therefore, the preparation of family food ingredients of patients with hypercholesterolemia using genetic algorithms needed for food ingredients that are consumed are variety and able to meet the nutritional needs with minimal cost. Genetic algorithm is a stochastic optimization technique because using random value. Genetic algorithms are capable of providing complex and wide-ranging problem solutions objectively. In crossover process using extended intermediate method and mutation process using random mutation method. The best solution results obtained when the population size of 100, crossover rate of 0.8, mutation rate of 0.2, permutation limit value of 115 and generation of 65.
Penerapan Parallel Genetic Algorithm untuk Optimasi Penyusunan Bahan Makanan Keluarga Penderita Hiperkolesterolemia
Anandita Azharunisa Sasmito;
Imam Cholissodin;
Sutrisno Sutrisno
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 8 (2018): Agustus 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1058.971 KB)
Cholesterol is a fatty substance that is essential for the sustainability of body functions. However, if cholesterol is above normal levels, the body can not eliminate it and will accumulate in the arteries that can cause heart attacks or strokes. A person with hypercholesterolaemia should maintain a diet and nutritional intake. The composition of food consumed should be in accordance with the needs. Unfortunately, few Indonesians realize the importance to pay attention to the diet and nutritional content of the food consumed each day. The algorithm to be used in this research is parallel genetic algorithm (PGA) where the algorithm is the result of modification of the genetic algorithm. In the PGA population will be divided into several sub-populations that run in parallel. In this study PGA still uses the concept of multi-population and migration but will only run on a single processor. In the application of parallel genetic algorithm for this research resulted the highest fitness solution using method parameter with popsize number of 65, sub population of 5, using generation 60, crossover rate with value 0,4 and mutation rate equal to 0,6, Permutation with value 145.
Optimasi Gizi Pada Bahan Makanan Balita Menggunakan Algoritme Genetika
Vivilia Putri Agustin;
Imam Cholissodin;
Bayu Rahayudi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 8 (2018): Agustus 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1133.512 KB)
In the Golden Age (children under five years old) have an important phase in child growth. Based on Basic Health Research in 2013, the development of children in East Java is still experiencing nutritional problems. The first because, lack of knowledge of parents to the nutritional needs of children. The second because, the lack of attention to the price of food in accordance with food ingredients that have balanced nutrition.One efforts of Dinkes Malang was involving Posyandu to do counseling related to improve child nutrition. However, these efforts were still experiencing obstacles in the form of the number of portions of food given to each children has not been adjusted based on weight and age, in addition the children lack variety of foodstuffs. Thus, the reseracher search a system to optimize it. Genetic algorithm was a Algorithm that was often used to overcome the problem of optimization. The results of the system in the form of lists of food and weight and price adjusted to the weight and age of children.Based on the test results obtained optimal parameters that the optimal population amount of 100, the optimal generation amount of 70 and the optimal combination of cr value and mr value was 0.5 and 0.5 resulted in a fitness value of 50.821.
Penerapan Optimasi Susunan Bahan Makanan untuk Ibu Hamil Penderita Kurang Energi Kronis (KEK) Menggunakan Algoritme Evolution Strategies
Firda Priatmayanti;
Imam Cholissodin;
Indriati Indriati
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 (1146.061 KB)
Maternal health during pregnancy, growth, birth, preparation of breastfeeding and infant growth is influenced by the addition of nutrients during pregnancy. The causes of Chronic Energy Deficiency or in Indonesia is Kurang Energi Kronis (KEK) in pregnant women is not sufficient to intake of energy and protein. The risk of pregnant women will experiencing KEK if the Upper Arm Circumference or in Indonesia is Lingkar Lengan Atas (LILA) have less than 23.5 cm. KEK in pregnant women can cause death indirectly and can cause Low Birth Weight or in Indonesia is Berat Badan Lahir Rendah (BBLR) in the children and BBLR can also cause to death and growing disordes of the child. Evolution Strategies used cycle of type (μ/r+ λ). Chromosome representation used real-vector, recombination used intermediate recombination and mutation used self-adaption mechanism. Based on the results test, the best solution come from the population of 100 with an average fitness value of 20.34, the number of offspring of 30 with an average fitness value of 18.53, the number of generations of 100 with an average fitness value of 19.35. The solution given is the composition of food material to the nutritional nedds of pregnant women KEK for 7 days with anaverage of adequate nutritional needs of 78.5% and an average cost saving 35.81%.
Implementasi Algoritme Shazam untuk Mengidentifikasi Hadis dan Surah dalam Al-Quran Menggunakan Suara
Bahruddin El Hayat;
Imam Cholissodin;
Marji Marji
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 (1153.372 KB)
For muslims, understanding Al-Qur'an and Hadis are an obligation because those two is the basic of Islam. In the learning process, a person usually will begin by memorizing the pronounciation and the surah's or hadis's name. After the person can pronounce the surah or hadis fluently, then they will continue to understand the meaning and the content of the surah or hadis. The problem is sometimes a person can forget the name of surah or hadis when another person says a verse from the surah or hadis. So, a solution is needed to handle the problem. In this research, the writer offers a solution to build a system that can identify the name of surah or hadis in Al-Qur'an by taking an input in the form of a sound file with WAV extension using Shazam algorithm. The identification process is done by doing these following actions: numeric value extraction, conversion, feature extraction, filtering and matching. The result is the name and information of the surah or hadis. The best accuracy from identifying surah and hadis from Al-Qur'an is 82% in the testing phase using a test data with 15 second duration, chunk size=4096 and range=60.
Optimasi Penjadwalan Kuliah Pengganti Menggunakan Algoritme Genetika
Holiyanda Husada;
Imam Cholissodin;
Fitra Abdurrachman Bachtiar
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 (755.582 KB)
Rescheduling is an option that can be chosen when lecturers are unable to attend on a schedule that has been determined by the academic or when there is a day off. This makes the lecturer need a rescheduling system to find another schedule quickly and appropriately to fulfill his duties as a lecturer. In this study use genetic algorithm for rescheduling based on lecturer schedule, student schedule, available room, course, and available time. The solution quality is measured using the fitness function. Based on the testing results that have obtained the optimal fitness value is 0.667. Result of Solution without clashed schedules but soft-constraint violated. The parameters with the highest fitness value from 10 experiments obtained the number of generation 30, population size 50, crossover rate 0.7 and mutation rate 0.3. The result is the optimal schedule available where the lecturers and most students of the class are reliable.
Optimasi Asupan Makanan Harian Ibu Hamil Penderita Hipertensi Menggunakan Algoritme Genetika
Novirra Dwi Asri;
Imam Cholissodin;
Dian Eka Ratnawati
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 (853.845 KB)
Hypertension is a risky disease and one of the main causes of death in pregnant women. For Hypertension pregnant women, the wrong food arrangement can affect the growth and development of the fetus. The recommended food arrangements for pregnant women with Hypertension is arrange the portion of food that can increase hypertension but not reducing the nutrition for fetus. There is one way that can be used to serve food of pregnant women with Hypertension is use a Genetic Algorithm. Genetic Algorithm is a heuristic method that uses rules to get the best solution. The process of Genetic Algorithm in research using representation chromosome integer number, crossover using extended intermediate crossover, mutation using random mutation and selection using elitism selection. The results provided are food recommendations for several days consisting of breakfast, lunch, and dinner. Based on the research results, the optimal generation size is 240 with the average fitness value is 525.0720, the optimal population size is 90 with the average fitness value is 525.0680 and the combination of cr and mr is 0.6 and 0.5 with average fitness value is 525. 0695.
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)
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.
Penentuan Durasi Nyala Lampu Lalu Lintas Berdasarkan Panjang Antrian Kendaraan Menggunakan Metode Backpropagation
Shibron Arby Azizy;
Imam Cholissodin;
Edy Santoso
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 (1042.434 KB)
Traffic is one location where people spend a lot of time. Currently with the rapid growth of vehicles makes conditions in Indonesia is getting crowded every day. One way to solve this problem is with traffic lights. However, the current traffic light performance is considered less than optimal. Therefore required a system that can determine the time, so the time at the traffic light can be more dynamic based on traffic conditions. This research uses backpropagation method to determine the duration of traffic lights based on queue lenght of vehicle. The result of the trained data test obtained is the Linear function with a = 3, the optimal iteration obtained at iteration 10, the optimal number of nodes in the hidden layer is 2, and the optimal value of learning rate is 0,02. The evaluation result when processing the test data using the optimal activation function, the optimal number of iterations, the optimal number of nodes in the hidden layer, and the optimal learning rate yields RMSE value of 0,0888978841028.
Implementasi Metode Bayesian Network Untuk Diagnosis Penyakit Kambing (Studi Kasus : UPTD Pembibitan Ternak dan Hijauan Makanan Ternak Singosari Malang)
Andika Eka Putra;
Nurul Hidayat;
Imam Cholissodin
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 (1345.651 KB)
Infectious disease factors are serious constraints that farmers should be aware of especially for traditional farmers who do not join livestock groups. Slow and improper handling can endanger livestock conditions. However, if the initial treatment is done, the chances of infection of the disease can be handled so as not to be more severe and contagious to other goats in a herd. Unfortunately, the uncertainty between the symptoms and the type of disease makes the farmers obstructed in the initial treatment, and do not know what to do without an expert. Based on these problems, the authors make a system of diagnosis of goat disease that is able to perform the diagnosis process based on the symptoms of goat. This diagnostic system uses Bayesian network method, the system is built on mobile device applications using the Android platform as the user interface, while the calculation process using PHP programming language, and MySQL database to store the prevalence of goat disease that has occurred. This system through the process of system functional testing and system accuracy testing. In the process of testing the functionality of this diagnostic system shows the functions that exist on the system goes well. In addition, the process of accuracy testing of goat disease diagnosis system using Bayesian Network method is done by entering the variation of symptoms by experts get the result of 86.6%.