Claim Missing Document
Check
Articles

Implementasi Fuzzy k-Nearest Neighbor (Fk-NN) untuk Klasifikasi Jenis Kanker berdasarkan Susunan Protein Tahtri Nadia Utami; Marji Marji; Lailil Muflikhah
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (288.21 KB)

Abstract

Cancer is the most deadly disease besides heart disease. A common cause of cancer is gene mutation in protein 53 that serves to control the replication of DNA as a regulator of the cell function resulting in the wrong protein sequence. The protein sequences is used as a basis to classifying the types of cancer and then it can ease in determining the right handling or therapeutics method. The classification of cancer using the Fuzzy k-Nearest Neighbor (Fk-NN) method. The data used are 752 protein sequences with 393 sequence length on every sequence. The classification class includes non-cancer, breast cancer, collorectal cancer and lung cancer. The Fk-NN method calculates the degree of membership of each class at the k smallest distances generated from k-Nearest Neighbor method. The highest average accuracy rate is 52.56% of the test results using k-fold-validation. The optimal k value of the Fk-NN method is k = 5 with the average accuracy rate of 54.99%. The large variation in the amount of training data that is 90% of the dataset results in the highest accuracy rate of 55.33%.
Sistem Diagnosis Penyakit Kelinci Menggunakan Metode Fuzzy Tsukamoto Gustian Ri'pi; Nurul Hidayat; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 2 (2019): Februari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (957.714 KB)

Abstract

Rabbit is one of the many pets maintained by the general public in Indonesia. Like others pet, rabbits are also susceptible to various diseases. This will cause harm to rabbit farmers if not treated properly. Most rabbit farmers have difficulty identifying the type of rabbit disease and the way of treatment, so they should consult directly with the veterinarian to get the right solution. To fix this problem, then in this research a system was created to help rabbit farmers in identifying diseases in rabbits quickly and precisely. The system is made in the platform android application so users can diagnose diseases flexibly whenever and wherever. This research using Fuzzy Tsukamoto method to calculate recommendations for diseases detected. In application, begins with the formation of fuzzy sets. Then rule formation in the inference machine using the MIN implication function. The final step is calculating the z value of each rule using a weighted average. The biggest z value is used as a recommendation for a detected disease. The data used were 16 types of rabbit disease with 49 symptoms of the disease obtained from interviews with one of the veterinarians in Malang City. The results of the implementation and testing of accuracy in this research amounted to 95% of the 20 test data indicating that the system was working properly.
Optimasi Pemetaan Tugas Mengajar Dosen Menggunakan Memetic Algorithm Okvio Akbar Karuniawan; Nurul Hidayat; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (412.497 KB)

Abstract

Submission of information relating to teaching and learning activities is very important, one of the first things to consider is scheduling. 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 assignment problem can be solved by a population-based heuristic methods, Memetic Algorithm (MA) 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. From the obtained data, it determined constraints such a lecturer's teaching priority, the maximum and minimum amount of credits, and the number of course that can be taken to calculate fitness value for each particles. Through the obtained results, it had parameter tested to find the effect of tested parameters on the resulted fitness values. From MA parameters test results, it obtained the best population number as 100, best iteration number as 100, and combination of parameter cr and mr as 0,8 and 0.2 with resulted fitness value as 87830. From the results of system, The fitness value of the test is optimal solution of generation 100 because the stop conditioning memetic algorithm is a maximum iteration. But the results do not guarantee if the value of Cr is getting smaller and the greater the value of Mr will produce better fitness.
Penerapan Penjadwalan Program Kerja Indonesian Future Leaders Chapter Malang Menggunakan Algoritme Genetika Rafely Chandra Rizkilillah; Budi Darma Setiawan; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1052.275 KB)

Abstract

Indonesian Future Leaders is a youth-led Non-Governmental Organization concerning on social activies education and youth empowerment. Indonesian Future Leaders is moved by implementing a variety of work programs that have been created and designed by Indonesian Future Leaders itself. Indonesian Future Leaders work programs are required to be done in a structured way. The programs that are being implemented by Indonesian Future Leaders takes about one year. The problems that Indonesian Future Leaders has is they didn't have structured work program schedules from the start of the beginning starting period. The data that is used by this research are all the work programs of Indonesian Future Leaders. Afterwards, the data will be proceeds with Genethics Algorithm with various of steps, such as cromosom representation, crossover, mutation, evaluation, and selection. The results of the schedule from Genetic Algorithm examination is the best fitness schedule has value of 0,001524 , which has 180 generation combination, 240 populations, and value of 0,7 cr and 0,3 mr.
Implementasi Topsis Pada Sistem Rekomendasi Tempat Wisata Pantai Di Sekitar Malang Berbasis Lokasi Muhamad Hilmi Hibatullah; Ratih Kartika Dewi; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 4 (2019): April 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1236.448 KB)

Abstract

The tourism sector in Indonesia currently considered to be an effective role in increasing the country's foreign exchange. In 2016, the tourism sector was the second largest constributor to foreign exchange in the amount of USD12.5 billion. Malang is one of the areas that have a lot of potential tourism object. Beach tourism in Malang is a lot where it is cause visitors confused to choose the beach to be visited. This research propose to make a beach recommendation system around Malang by applying the Technique For Order Preference by Similiarity to Ideal Solution (TOPSIS) method. The TOPSIS method was chosen because TOPSIS was able to do the selected alternative ranking, where the selected alternative had the closest distance from the positive ideal solution and the farthest distance from the negative ideal solution. The criteria used in this system are distance, cost, rating, facilities and transportation. System functional testing shows that 100% of the functionality is valid. Furthermore, testing the validation of the algorithm, obtained the results 100% of similarities between the system output and manual calculation. While rank consistency testing obtained results that show that the TOPSIS method has a good level of consistency when implemented on the beach recommendation system
Rekomendasi Perbaikan Rumah Tidak Layak Huni Menggunakan Metode TOPSIS Studi Kasus Badan Keswadayaan Masyarakat Di Kelurahan Bekasi Jaya Muhammad Fakhri Mubarak; Nurul Hidayat; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 4 (2019): April 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (666.939 KB)

Abstract

Houses that are habitable, clean and have good infrastructure are the hopes of every human being. Conversely, non-habitable homes can cause discomfort for residents, and can also be a source of disease that should be avoided by residents. To avoid this, residents of the house must spend not a little money to improve the infrastructure for their place of residence. The problem is that there are still families who do not have excessive financial resources to repair their homes, which makes them have to survive in places that are not suitable for habitation. To overcome this, the governments of each region prepared a variety of programs to help disadvantaged communities, one of which was responsible to the Badan Keswadayaan Masyarakat. Unfortunately, these funds cannot be given to all applicants for repairing unfit for housing. Due to the imbalance in the number of applicants for repairs to improper housing, with funds owned by the Community Self-Help Agency. So the Badan Keswadayaan Masyarakat needs a system that is used to help provide recommendations for homes that are preferred to be repaired. The application of the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method will be used to get home improvement recommendations that will be repaired. This system uses data as much as 50 data which form the basis of calculations and 8 home recommendation data which become test data. The application of the TOPSIS method in determining recommendations for repairing uninhabitable homes uses several factors, namely: the status of the house, the walls of the house, the floor of the house, the roof of the house and family income. From this study, it was obtained an accuracy of 75% obtained from testing of decision-making data in the Community Empowerment Agency and ranking using the TOPSIS method.
Klasifikasi Jenis Kanker Berdasarkan Struktur Protein Menggunakan Metode Neighbor Weighted K-Nearest Neighbor (NWKNN) Aldy Satria; Marji Marji; Dian Eka Ratnawati
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 4 (2019): April 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (937.462 KB)

Abstract

Cancer is non-infectious disease with large population in the world. Cancer is ranked on 7th deadliest disease in Indonesia. Mostly cancer happened because of gene mutation that cause changes in protein form,one of them happens in protein 53 (p53). Mutation of gene p53 most commonly found in human cancers. From this case required a system that can classify the types of cancer. One of methods used is Neighbor Weighted K-Nearest Neighbor (NWKNN). Data used in this paper consists of 752 protein sequences data with 393 sequence length. Classification class includes non-cancer, breast cancer, collorectal cancer and lung cancer. NWKNN is improvement of K-Nearest Neighbor (KNN) method with addition of weight class in its classification class scoring calculation. The test is conducted by dividing dataset into training data and testing data with training data and testing data ratio 80%:20%, 70%:30%, 60%:40, 50%:50, 40%:60%, 30%:70%, 20%:80%, 10%:90% from dataset. The result shows that 80%:20% ratio with K=8 and E=3 provided the highest accuracy eate of 80.666%.
Identifikasi Kerusakan Mesin Pada Sepeda Motor Menggunakan Metode Modified K-Nearest Neighbor (MKNN) Adhiyatma Mugiprakoso; Nurul Hidayat; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 4 (2019): April 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (560.161 KB)

Abstract

The transportation vehicle most used by the public today is motorcycles. According to data from the national statistics center, 81.5% of the transportation equipment used by the public is motorcycles from all transportation equipment in Indonesia. Motorcycles have advantages compared to other transportation equipment such as low maintenance costs, affordable prices, economical fuel and low maintenance costs. On motorcycles there can also be various problems with the engine which can interfere with driving comfort or even accidents. Many of the motorcycle riders have little knowledge of motor engine damage. Of the many classification methods that can be used to repair machine damage, one of them is the Modified K-Nearest Neighbor (MK-NN) method. The method studied the pattern of previous examination data based on symptoms of demage with eucledian distance calculation process, calculation of validity value and weighted voting calculation that the end result is used for class classification determination based on predetermined value of k. To identify damage to a motorcycle engine by using 9 types of damage with 13 symptoms and a total of 110 training data. The highest accuracy obtained from the test results was 86.67%.
Algoritme Information Gain Feature Selection pada Sistem Temu Kembali Citra Makanan Menggunakan Ekstraksi Fitur Warna dan Tekstur Dyva Agna Fauzan; Yuita Arum Sari; Marji Marji
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 (889.16 KB)

Abstract

The food name used as a keyword or query in conducting a food recipe search on the search system has limitations, namely the knowledge of the name of the food that the recipe wants to find. So another approach is needed to do recipe searches, namely by the display or the image of food. However, with the many features that are generated from the image it will cause high dimensional data which results in the effectiveness of the search system. For this reason, feature selection is needed to handle high-dimensional data. This research conducted a study of the effect of the number of returns that can provide the highest MAP value and the effect of the Information Gain feature selection on food image retrieval systems using texture feature extraction using Gray Level Co-occurance Matrix and color features using Color Moments and Color Histogram. The number of retrieves (r) of 5 is outperforming other r values with the value of MAP = 1 on the use of only color features and textures and the value of MAP = 0.98 in the combination of both. This indicates a smaller number of returns can give a higher MAP value. The effect of the Information Gain feature selection algorithm on the system is that it can provide the MAP = 1 value on the number of features (n) = 10 on the color feature, n = 5 on the texture feature, and n = 30 on the combination. This shows that the system with feature selection can provide results that are as good (in color and texture) and even better (in combination of features) with fewer features when compared to without feature selection.
Klasifikasi Dokumen pada Laporan Kepolisian dengan Menggunakan Metode BM25 dan Improved K-Nearest Neighbor (IKNN) Ardhimas Ilham Bagus Pranata; Indriati Indriati; Marji Marji
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 (389.617 KB)

Abstract

The National Police of the Republic of Indonesia is one of the law enforcers in the Unitary State of the Republic of Indonesia. One of the tasks of the Indonesian Police is to provide services to the community. Accusation of crime is one form of service to the community offered by the Police. Crime can happen to anyone no matter an employee, a student or others. The stage after the report of a crime is received by the police is the issuance of investigation. However, within one month the police had difficulty classifying every police report that have been accepted especially Polres Kota Malang. Therefore a system for helping the police to classified a accusation of crime into three cases are persecution, stealing, and fraud is needed. Process in this study is by doing a pre-processing text which the next stage is counting the weight of tf, df, and idf and continue to classification. In this study classification do by using BM25 and Improved K-Nearest Neighbor Methods (IKNN). The results of the k-fold cross validation test, the highest average value of precision=0,953373, recall=0,931382, f-measure=0,938122 and accuracy=0,956795 at the value of k = 15.
Co-Authors Achmad Burhannudin Adam Hendra Brata Adhikari, Basanta Prasad Adhiyatma Mugiprakoso Afifah, Nadiyah Hanun Agi Putra Kharisma Agung Kurniawan Agustian, Moch. Alfredo Barta Ahmad Fauzan Rahman Ahmad, Baihaqi Aldy Satria Andika Harlan Andini Agustina Anita Sulistyorini Annisa Selma Zakia Ardhimas Ilham Bagus Pranata Arifin, Maulana Muhamad Asti Melani Astari Atika Anggraeni Audi Nuermey Hanafi Bagus Abdan Aziz Fahriansyah Bahruddin El Hayat Baihaq, Firda Barlian, Salwa Isna Bayu Rahayudi Bayu Septyo Adi Budi Darma Setiawan Budi Darma Stiawan Cahyo Adi Prasojo Candra Ardiansyah Choirul Anam Cindy Puspita Sari Cindy Rizki Amalya Dani Irawan Daud, Nathan Dea Widya Hutami Dewi Yanti Liliana Dian Eka R Dian Eka Ratnawati Djoko Kustono Dwi Yana Wijaya Dyva Agna Fauzan Edy Santoso Edy Santoso Edy Santoso Endang Wahyu Handamari Erwin Komara Mindarta Fanani, Erianto Fatih Kamala Nurika Gilang Ramadhan Gustian Ri'pi Hadi, Moch. Sholihul Handoyo, Samingun Hary Suswanto Hasan Ismail Ilham Romadhona Imam Cholisoddin Imam Cholissodin Imam Muda Nauri Imran Imran Indriati Indriati Indriati Indriati Issa Arwani Istiana Rachmi Istiqomah, Mutiara Titian Januar Dwi Amanda Jeffrey Simanjuntak Kenty Wantri A Kohei Arai Kurnianingtyas, Diva Lailatul Fitriah Lailil Muflikah Lailil Muflikhah Lailil Muflikkah Laily Putri Rizby Laksono Trisnantoro Leni Istikomah Liana Shanty Wato Wele Keaan Lilik Zuhriyah Lilis Damayanti Luthfi Faisal Rafiq M Chandra Cahyo Utomo M. Alfian Mizar Made Bela Pramesthi Putri Mahmudi, Wayan Firdaus Maududi, Affan Al Michael Adrian Halomoan Mochammad Pratama Viadi Mountaz, Lotu Muchammad Harly Muhamad Altof Muhamad Hilmi Hibatullah Muhammad Fakhri Mubarak Muhammad Hafidzullah Muhammad Indra Harjunada Muhammad Ramanda Hasibuan Muhammad Rizkan Arif Muhammad Robby Dharmawan Muhammad Tanzil Furqon Muhammad, Naufalsyah Falah Muzdalifah Yully Ayu Nonny Aji Sunaryo Nurul Hidaya Nurul Hidayat Nurul Hidayat Okvio Akbar Karuniawan P. P. S, Gladis Viona Pangestu, Wiyan Dwi Panji Prasuci Saputra Paryono Permadani , Anda Permatasari, Adelia Pratitha Vidya Sakta Prawidiastri, Firnadila Pricielya Alviyonita Rafely Chandra Rizkilillah Ratih Kartika Dewi Ratna Candra Ika Razaq, Hilal Nurfadhilah Retiana Fadma Pertiwi Sinaga Revinda Bertananda Riana Nurmalasari Ricky Irfandi Ricky Marten Sahalatua Tumangger Rizqi Addin Arfiansyah Rosalinda, Nadia Ryan Mahaputra Krishnanda Sabrina Hanifah Sari, Resti Novita Shinta Anggun Larasati Sri Wahyuni Sri Widyarti Sumarli Sumarli, Sumarli Supraptoa Supraptoa Supriyadi Supriyadi Sutrisno Sutrisno Swandy Raja Manaek Pakpahan Syarif Suhartadi Tahtri Nadia Utami Tawang Wulandari Tika Dwi Tama Usman Adi Nugroho Wayan Firdaus Mahmudy Wulandadi, Retno Yamlikho Karma Yayuk Wiwin Nur Fitriya Yuita Arum Sari Yusufrakadhinata, Muhammad Zulianur Khaqiqiyah