Articles
<![CDATA[Performance Comparison of Rule Generation Method Substractive Clustering and Fuzzy C-Means Clustering on Sugeno's Inference for Stroke Risk Detection ]]>
<![CDATA[Mardi Putri, Rekyan Regasari]]>;
<![CDATA[Santoso, Edy]]>
<![CDATA[ MATICS Vol 9, No 2 (2017): MATICS ]]>
Publisher : <![CDATA[Department of Informatics Engineering ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (598.178 KB)
|
DOI: 10.18860/mat.v9i2.4587
<![CDATA[Abstract - Fuzzy Inference is one method that cansolve the problem of uncertainty in a decision-makingor classification well. In inference, fuzzy rules thatrepresent the need of expert knowledge in the relevantfields, so that the classification given decision or beappropriate expert knowledge. However there are timeswhen experts are less able to represent the rules of theappropriate knowledge or knowledge that there is needof too many rules, so we need a method that cangenerate rules based on the data given expert.At issue troke s disease risk detection, it also occursbecause of the research that has been done by taking thedirect rule of experts, it turns out less than the maximumaccuracy, still 82.89%. Substractive methodsClustering and Fuzzy C-Means (FCM) could generaterules by grouping algorithm, in which the existingtraining data are grouped in common and the rules ofthe group raised. Differences in the two methods are indetermining the center of the cluster and assign eachincoming data which groups.Based on research that has been done, substractiveaverage Clustering membrika better accuracy is84.46%, while 73.81% FCM. However, in theprocessing time FCM faster at 16.75 seconds to give anaverage processing time of 13:02 seconds.]]>
<![CDATA[PENGUKURAN PENERIMAAN PETANI TERHADAP TEKNOLOGI WEB MENGGUNAKAN METODE TECHNOLOGY ACCEPTANCE MODEL ]]>
<![CDATA[Candra Dewi]]>;
<![CDATA[Rekyan Regasari Mardi Putri]]>
<![CDATA[ Jurnal Pengabdian Sriwijaya Vol 6, No 1 (2018) ]]>
Publisher : <![CDATA[Lembaga Pengabdian pada Masyarakat ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37061/jps.v6i1.1955
<![CDATA[Website merapakan media yang saat ini banyak digunakan untuk mempromosikan usaha. Akan tetapi penggunaan website sebagai media promosi belum banyak dilakukan oleh petani dan kelompok usaha kecil karena sebagian besar dari mereka berpendidikan rendah dan tidak mengenal penggunaan website. Akan tetapi memperkenalkan teknologi ini kepada petani dan kelompok usaha kecil perlu untuk dilakukan. Dalam kegiatan ini dikembangkan media promosi tanaman sayur berbasis web bagi Kelompok Rumah Pangan Lestari (KRPL) Dewi Sri, Sumbergempol, Tulungagung. Website dikembangkan dengan tampilan yang sederhana dan dapat diakses menggunakan telepon genggam. Selanjutnya dilakukan pelatihan penggunaan media ini kepada anggota kelompok. Berdasarkan kuisioner yang dilakukan, kemudian dilakukan analisa  menggunakan Technology Acceptance Model (TAM). Dari hasil analisa dapat diketahui bahwa kelompok dapat menerima penggunaan teknologi ini dengan cukup mudah sehingga diharapkan dapat secara kontinyu memanfaatkan media ini untuk kegiatan promosi dan pemasaran produk.]]>
<![CDATA[THE ACCEPTANCE OF EDUCATION GAME AS LEARNING MEDIA OF INDONESIAN CULTURE FOR PRIMARY SCHOOL STUDENTS ]]>
<![CDATA[Candra Dewi]]>;
<![CDATA[Rekyan Regasari Mardi Putri]]>
<![CDATA[ Journal of Innovation and Applied Technology Vol 2, No 2 (2016) ]]>
Publisher : <![CDATA[Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (349.486 KB)
|
DOI: 10.21776/ub.jiat.2016.002.02.9
<![CDATA[Indonesia is a country known for its cultural diversity. Getting to know the culture of a nation which starts from an early age is needed to foster national values to form the nation's character. However, the cultural lesson is not a favorite subject for student todays. For this reason, we need efforts to bring the matter of culture to be fun and interesting to learn. Related to primary school students, the ways of learning by playing is much preferred. Recently, the game can be simulated by using computer technology. Therefore, it is possible to develop computer games based learning media. The activities carried out in this community service activity include the design and manufacture of culture learning games package. After that, the training about using the game as learning media is conducted for primary school teacher. Based on the analysis results of a questionnaire given during training showed that the game are made is easy to operate, to understand and to play. Similarly, the benefits provided are considered significant in terms of giving out a fun learning experience, helping to evaluate learning outcomes and decent used to support teaching and learning process.]]>
<![CDATA[Deteksi Autisme pada Anak Menggunakan Metode Modified K-Nearest Neighbor (MKNN) ]]>
<![CDATA[Zahra Swastika Putri]]>;
<![CDATA[Rekyan Regasari Mardi Putri]]>;
<![CDATA[Indriati Indriati]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 3 (2017): Maret 2017 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1123.03 KB)
<![CDATA[Autism is a childhood and developmental disorder that characterized by lack of communication, cognition, imagination and social interaction activities. Many people didn't recognize the symptoms of autism disorder until the first three or seven years of life. Delay, similarities of symptoms and lack of knowledge about autism cause imprecision treatment handling, and increased number of sufferers. Identification of autism differentiated into severe autism, moderate autism, mild autism and non- autism. Modified K-Nearest Neighbor (MKNN) method is a method that enhancing performance of conventional K-Nearest Neighbor method. There're validity of the train data process and weight voting process to robust neighbors of training dataset and strengthen the performance results. Based on variant value of k testing obtained 83.33% accuracy at dissimilarity measure. Based on composition of balance training data testing obtained 90% accuracy at euclidean distance. Based on amount of training data testing obtained 79.17% average accuracy. Based on variation of training data testing obtained 83.33% accuracy at dissimilarity measure. Based on results of such testing accuracy, pointed out that the detection of children's autism using MKNN method have a pretty good degree of accuracy and capable to classify and detection the autism symptoms based on perceived symptoms user input.]]>
<![CDATA[Optimasi Komposisi Makanan Pada Penderita Diabetes Melitus dan Komplikasinya Menggunakan Algoritma Genetika ]]>
<![CDATA[Maryamah Maryamah]]>;
<![CDATA[Rekyan Regasari Mardi Putri]]>;
<![CDATA[Satrio Agung Wicaksono]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 4 (2017): April 2017 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1024.937 KB)
<![CDATA[Diabetes Mellitus (DM) is the 4th largest cause of death in the world and causes more deaths than other diseases so needed serious attention is required. One that can be done is by diet therapy that is composing daily food menu. Diabetic diet is done with attention of energy, carbohydrates, proteins, and fats with precise and accurate. The calculation of the patient's energy can be done manually or with the help of a system that implements an algorithm. If done by manual process will take a long time especially if the available food is very much and diabetic diet every complication has different needs. With the help of computation process system will take place quickly and if applied a calculation algorithm will yield more optimal solution, one of the algorithm is genetic algorithm. Genetic algorithm is a heuristic method that is a search method, in implementation there are rules to obtain a better solution than the previous solution. Genetic algorithm is widely applied to various optimization problems so it is also expected to optimize the problem on the optimization of food composition. The results obtained from the research conducted are individuals in the optimal population of 250 individuals with the number of generations of 145 and the combination of cr and mr most optimal is 0.7 and 0.3 with fitnes 0. 01857.]]>
<![CDATA[Sistem Pakar Klasifikasi Permasalahan Berdasar AUM Menggunakan FCM-FIS Tsukamoto ]]>
<![CDATA[Ainun Najib Eka Christianto]]>;
<![CDATA[Rekyan Regasari Mardi Putri]]>;
<![CDATA[Agus Wahyu Widodo]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 4 (2017): April 2017 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (810.385 KB)
<![CDATA[Alat ungkap masalah is an instrument in guidance and counseling are used to discover and understand any problems experienced by students. Alat ungkap masalah is used because of the lack of a deep understanding of teachers' guidance and counseling to students. Although already used alat ungkap masalah student counseling service process is still less than the maximum because of the lack of human resources that exist in schools and teachers' understanding of guidance and counseling about the tool according to the problems and issues faced by the students. Therefore, it is necessary to develop an expert system that can adopt the knowledge of an expert counseling in the process of recognition of the problem by using the tool revealed the problem. The purpose of this application is to help the teachers counseling to ease the process of guidance and counseling and facilitate students in recognizing the problems that it faces. This application uses the FCM Clustering as the generation process and FIS rules Tsukamoto as an inference engine, the application can generate an accuracy rate of 75.71% compared with the results of the expert diagnosis.]]>
<![CDATA[Sistem Pakar Diagnosis Penyakit Demam: DBD, Malaria dan Tifoid Menggunakan Metode K-Nearest Neighbor - Certainty Factor ]]>
<![CDATA[Elsa Nuramilus Shofia]]>;
<![CDATA[Rekyan Regasari Mardi Putri]]>;
<![CDATA[Achmad Arwan]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 5 (2017): Mei 2017 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1193.865 KB)
<![CDATA[Fever is one of the health problems that disrupt everyone's productivity, even it can cause death and remain a health problem in Indonesia. There are several types of fever that needs to be wary, it includes dengue, malaria and typhoid. These three diseases have similar symptoms, so many medical personnel and doctors internship often make mistakes in diagnosing the disease. Therefore, an expert system is required to resolve the issue. The method used to support the expert system is K-Nearest Neighbor - Certainty Factor which is a merger of two methods in which the classification results of K-Nearest Neighbor to be rated certainty by a Certainty Factor method and resulting a diagnosis of the disease. In this study, the training data and test data used were 143 data. Based on test results obtained K value variation accuracy of 88.37%. On testing variations training data obtained an accuracy of 86.04%. In testing the ratio of training data and test data obtained an accuracy of 95%. In testing the variation of the number of test data obtained an accuracy of 90%. In testing the variety of test data obtained an average accuracy of 97.22%. In comparison testing method, the method k-nearest neighbor certainty factor gets an accuracy of 84.79%.]]>
<![CDATA[Implementasi Algoritma Genetika Untuk Penjadwalan Customer Service (Studi Kasus: Biro Perjalanan Kangoroo) ]]>
<![CDATA[Chusnah Puteri Damayanti]]>;
<![CDATA[Rekyan Regasari Mardi Putri]]>;
<![CDATA[Mochammad Ali Fauzi]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 6 (2017): Juni 2017 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1310.161 KB)
<![CDATA[Due to the high demand of public transport, travel agency must be ready to serve the citizen. Travel need to be ready to serve the customer; called customer service. Customer service should provide information that is precise, accurate and fast to customers. At Travel Kangaroo which owns more than 300 fleet, has two locations namely central office and branches as well as long operating hours, a responsive customer service needed to serve the customers There are various rules that must be fulfilled in making the schedule of customer service too. Thus, in this study scheduling problems solved using genetic algorithms. Genetic algorithms can solve a complex problem as well as it has wide scope. Through the examination, it was obtained the best parameters that produce the most optimal fitness value with a population size of 110, 110 and comparison generation size crossover rate and mutation rate of 0.7: 0.3. By using these parameters, scheduling customer service have optimal results, although there are violations that occur with shorter computation time compared with the manual.]]>
<![CDATA[Penerapan Fuzzy K-Nearest Neighbor (FK-NN) Dalam Menentukan Status Gizi Balita ]]>
<![CDATA[Satria Dwi Nugraha]]>;
<![CDATA[Rekyan Regasari Mardi Putri]]>;
<![CDATA[Randy Cahya Wihandika]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 9 (2017): September 2017 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1088.679 KB)
<![CDATA[Infants or so-called children is a group that have an important period in physical growth. Infants itself is categorized as a group of children between age 1 to 3 as a teddler group, and age 3 to 5 as a pre-school group. Some says children has a big role in order to attaining of growth success in the future for human, hence they call it as the golden age of living. Children's growth not only discribing as an increasing of body dimensions but also as the continuity of intake and nutrient needs. An indicator to know the children's health is by determining their nutritional status. Based on SK Minister of Health in Indonesia, they use a method called anthropometry to determining children's nutritonal status. While this method only reviewing 4 internal factors, there're some other factors which influence of children's nutritional status itself such as genetic, disease, education, knowledge, and income. Therefore Fuzzy K-Nearest Neighbor is used in this study as a classifiaction method that can determining children's nutritional status because this method using the data training as the knowledge to clasify and would adjust other factors of nutritional status itself right in the future. From the test results of the study, this system can clasify well with maximum accuracy of 84,37% when using 160 training data with k value = 4.]]>
<![CDATA[Optimasi Pembagian Tugas Dosen Pengampu Mata Kuliah Dengan Metode Particle Swarm Optimization ]]>
<![CDATA[Muhammad Abduh]]>;
<![CDATA[Rekyan Regasari Mardi Putri]]>;
<![CDATA[Lailil Muflikhah]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 10 (2017): Oktober 2017 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (917.094 KB)
<![CDATA[In forming a lectures schedule, an absolute thing that had to be done is division of labor teaching duties in accordance with their field in order to create an effective teaching and learning activities. At Faculty of Computer Science (FILKOM) Brawijaya University, the assignment process is still manually designed where it requires some substantial time, therefore it needed a right optimization methods in dealing with this case. This problem can be solved by a population-based heuristic methods, Particle Swarm Optimization (PSO) which has been applied in various fields such as scheduling and assignments. The data used in this study is the data division of lecturers teaching tasks as a priority of lecturer's teaching interests to a course. Through the obtained results, it had tested to find the effect of tested parameters on the resulted fitness values. From PSO parameters test results, it obtained the best particle number as 100, best iteration number as 100, and combination of velocity parameter c1 and c2 as 1.5 and 1.5 with resulted fitness value as 94878. From the results of system, the obtained assignment solution gives good results, which is still within the limits of tolerance with decreasingly obtained error values in putting a lecturer on courses that according to their interests.]]>
