Agus Wahyu Widodo
Fakultas Ilmu Komputer, Universitas Brawijaya

Published : 114 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Analisis Perbandingan Metode K-Means Dengan Improved Semi-Supervised K-Means Pada Data Indeks Pembangunan Manusia (IPM) Gusti Ngurah Wisnu Paramartha; Dian Eka Ratnawati; Agus Wahyu Widodo
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 9 (2017): September 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (983.505 KB)

Abstract

At this time with the growing amount of information, the concept of data mining getting known as an important tool in the management information. Refers to the concept of data mining, the most popular concept in data mining is a clustering technique. One well known clustering method is k-means traditional. But in its application, k-means method has some problems such as determining the value of K cluster and determining the initial cluster centers were done randomly making process was inconsistent and the results of the cluster becomes worse. Therefore, there is a method to overcome these problems are improved semi-supervised k-means clustering. With improved semi-supervised method that combines the supervised and unsupervised method, users only need to label a bit of data that has not been labeled, then the labeled data is used to find the optimal value of initial cluster center and K cluster that will optimizes the process and result of clustering process. On implementation, this research combine k-means algorithm and improved semi-supervised k-means to clustering human development index (HDI) data. HDI data chosen because it has the right characteristics for clustering such amounts of data and the data is divided into several clusters. On the testing improved semi-supervised k-means method giving out the average accuracy of 90.3%, better than k-means clustering that giving 73.7% accuracy. In the second testing, improved semi-supervised k-means method produces an average time for one convergent 1222.9959 seconds, better than k-means with 1504.75 seconds. The third testing, improved semi-supervised k-means generates an average number of iterations for one convergent more efficient than k-means with the number of iterations of 7.11 compared 9.72. Last, on the cluster quality testing using silhouette coefficient, improved semi-supervised k-means method giving average value 0.69880, better than the traditional k-means with an average value of 0.62734.
Optimasi Multiple Travelling Salesman Problem Pada Pendistribusian Air Minum Menggunakan Algoritme Particle Swarm Optimization (Studi Kasus: UD. Tosa Malang) Rinindya Nurtiara Puteri; Agus Wahyu Widodo; Imam Cholissodin
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 9 (2017): September 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (776.05 KB)

Abstract

If the distribution application was not run optimally ,it can obstruct the distribution of drinking water process.The tardiness of drinking water transmission become an obstacle in the process and it is also effected by many factors, such as sales ignorance about the shortest path to where the customers are.So this system can lead and make the process easier to determine the shorthest path. In that Distribution obstacle we called it Multiple Travelling Salesman Problem because implicate more than one factor .One of the main purpose from this research is to determine the shortest path for every saleses.This thesis uses Particle Swarm Optimization Algorithm. There were some thesis talked about Multiple Travelling Salesman Problem but to PSO method is scarce. Particle Swarm Optimization is one of the method that solved M-TSP which is that method will gives some effective solutions.Based on the background,researcher choose to use The optimization of Multiple Travelling Salesman Problem application,and in drinking water distribution use Particle Swarm Optimization Algorithm. The result that had been proved show the route sequence that used is better from optimum parameter made 30 iterations and with 90 particle.
Optimasi Multiple Travelling Salesman Problem Pada Pendistribusian Air Minum Menggunakan Algoritme Genetika (Studi Kasus: UD. Tosa Malang) Sayyidah Karimah; Agus Wahyu Widodo; Imam Cholissodin
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 9 (2017): September 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1074.867 KB)

Abstract

A good distribution is one of the company's strategy to increase the productivity of the company. Distribution strategy is indispensable in bottled drinking water, because bottled water business has increased every year. Distributor of bottled water has a variety of types and brands of goods with different packaging forms. The number of shipping destinations poses many problems in the distribution process, because it takes more time to arrive at different address and distances. This research has a goal to create a system that can help the process of distribution of goods with number of sales more than one, the problem is called Multiple Traveling Salesman Problem (M-TSP). One method to solve M-TSP problem is to use genetic algorithm, so it can determine the route with the shortest distance that will be visited by every sales. The genetic algorithm process uses permutation representations with chromosome length according to many customer orders and the number of orders on each sales, each gene is a number representing the customer number and the number of orders that each salesperson should visit. The test results show that the route sequence generated from the application of the genetic algorithm is better than that applied to the distributor with a total distance of 89.3 km and the fitness difference is 10.656578. The optimal parameters were obtained by generating population size 180, 400 generation and crossover rate 0.6 and mutation rate 0.4.
Pengenalan Citra Tanda Tangan Off-Line dengan Pemanfaatan Ciri Centroid Distance Function Rizka Husnun Zakiyyah; Agus Wahyu Widodo; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 10 (2017): Oktober 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1060.86 KB)

Abstract

A person's signature is one of the most valid proof that shows ownership of documents and transactions that contain their most important data. However, the process of analizing its authenticity is still done manually. To resolve this problem, an image recognition system for signature will be developed by applying characteristic centroid distance function. This Image recognition process begins with preprocessing, such as binerisasi, filtering, cropping, resizing, and thinning. Next the position of pixels will be searched to store all the foreground pixels and centroid pixels of the image. All pixels stored distance will be calculated using centroid function and grouped according to the amount of features that were selected so that each group has the same amount of data. The average of centroid distance function will be counted on every group so that each group will generate one feature. The results of feature extraction will be processed with the k-nearest neighbor classification method. On the research that has been done the highest accuracy obtained from extraction characteristics of centroid distance function uses 20 class is 88.5% obtained from 20 features and k= 1 with the amount of 10 and 14 training data for each class. The highest accuracy to 50 class is 67.4% obtained from 15 features and k= 3 with 10 and 14 training data for each class.
Seleksi Fitur Dengan Particle Swarm Optimization Untuk Pengenalan Pola Wajah Menggunakan Naive Bayes (Studi Kasus Pada Mahasiswa Universitas Brawijaya Fakultas Ilmu Komputer Gedung A) Satria Habiburrahman Fathul Hakim; Imam Cholissodin; Agus Wahyu Widodo
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 10 (2017): Oktober 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1061.426 KB)

Abstract

The Presence system of students in the Faculty of Computer Science, Brawijaya University is still using the manual system that is very prone to be misused by the students as entrusted that presence to his friend. Therefore we need a system that has been digitized and also fast in finding solution problem. Optimization method is a method of searching for faster solutions. For this time the researchers is using the Particle Swarm Optimization (PSO) method, that method was inspired by the social behavior of bird movements in their daily lives. While the method of classification is a method that is closely related to the probability hypothesis. So there are 2 methods and have different functions in facial recognition at the student presences where PSO here is as a feature selection and Naive Bayes here as a classification engine as well as a function to get fitness. In the test results obtained that iteration with the best total fitness value is on the number of particles 38 with the highest total fitness is 13,38, then on testing the effect of the number of iterations obtained the conclusion that the largest total fitness is at iteration 190 is 36,799, in other words the greater of iteration the fitness is also better and the last test is on testing for the weight of inertia is 1,2 with the highest total fitness result is 1,588.
Sistem Pendukung Keputusan Untuk Pemilihan Penanaman Varietas Unggul Padi Menggunakan Metode AHP dan TOPSIS Muhamad Rendra Husein Roisdiansyah; Agus Wahyu Widodo; Nurul Hidayat
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 10 (2017): Oktober 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (684.077 KB)

Abstract

According to the data from Indonesian Center for Rice Research, until today there is already 48 varieties of inpari, 19 varieties of hipa, 11 varieties of inpago, and 9 varieties if inpara that has been relased and there is a possibility that this ammount will increase each year. This amount does not include the high yielding varieties that are still cultivated to date such as ciherang, IR 64, Cibogo, IPB 3S, and others. The excessive ammount of varieties of rice crops along with their own criteria can cause problems, how do farmers choose the right varieties to maintain their crops maximally.There is a solution for this problem that is using a Decision Support System (DSS). In this research, the system is created by combining 2 DSS methods, that is Analytic Hierachy Process (AHP) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). Those methods was chosen because it is considered to produce a more accurate decisions and more objective than using one method alone. The AHP method will generate the weight of criteria that can also be used in the weighting process in the TOPSIS method. The Input from the system created is divided into 2. In the AHP using pairwise comparison table data from the criteria of superior varieties, the TOPSIS method uses data description of varieties that become the alternatives. The results of the system made shown as a ranking of alternatives from best to worst. System testing is done by matching the results of the system with the results of the experts, based on testing conducted, obtained the results of accuracy at 83.33%.
Verifikasi Citra Tanda Tangan Berdasarkan Ciri Pyramid Histogram of Oriented Gradient (PHOG) Menggunakan Metode Klasifikasi K-Nearest Neighbor Latifa Nabila Harfiya; Agus Wahyu Widodo; Randy Cahya Wihandika
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 10 (2017): Oktober 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1036.411 KB)

Abstract

Signature have been widely accepted by people as one of many tools that used to verify a person's identity. Signature verification is highly needed in order to avoid crimes regarding signature's validity. The process of signature image verification uses feature extraction based on Pyramid Histogram of Oriented Gradient (PHOG) for extracting feature from global to local image area that used for the next process, classification using K-Nearest Neighbor method. There are some parameters that can affect the feature extraction of PHOG and K-NN as classification method such as number of bin, level, range of angles, and K. As for the additional parameters, namely the amount of training data that affect the overall results of the classification used. Feature extraction and classification by the method with the best parameter values and training data used produces the highest accuracy of 99.5% on Indonesian original signature data and 98.5% on the data of the Persian original signatures. While the forgery signatures data produces accuray only as much as 56% on data from Indonesia and 35,5% on data from Persian. Results from tests show that the algorithm is not good enough for distinguishing forgery signature that has high similarity with genuine signature even it is works well for recognizing genuine signature.
Klasifikasi Berita Twitter Menggunakan Metode Improved Naive Bayes Budi Kurniawan; Mochammad Ali Fauzi; Agus Wahyu Widodo
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 1 No 10 (2017): Oktober 2017
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1083.037 KB)

Abstract

Twitter is one of the most widely used social media today. Besides being used as a social media, Twitter is also used to read news. Every year Twitter users have increased, so that information is also increasing. Increased information causes users who want to look for a certain information to experience difficulties. To solve the problem, news categorization is required. This study use Improved Naive Bayes method to categorize tweets by news contents. In Improved Naive Bayes posterior value will be calculated after the word is done by weighting using Bernoulli representation or by 1 and 0. This study use eight categories of news in Indonesia, which are: economy, entertainment, sports, technology, health, food, automotive, and travel. Based on the results of tests that have been done this study obtain precision value of 0.962961, recall 0.789164 and f-measure of 0.862973.
Implementasi Metode Improved K-Means untuk Mengelompokkan Titik Panas Bumi Al-Mar'atush Shoolihah; Muhammad Tanzil Furqon; 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 (1051.2 KB)

Abstract

Disaster is an incident or a series of incidents that threaten and disturb people's lives and livelihoods caused by both natural and / or non-natural factors. One of the disasters that happen is fire. Fire is a flame that occur either in small or large size, burning in an unexpected area and difficult to control. Therefore, early prevention is needed. one of the way is with geothermal point which is detected by the satellite. It is used as the indicator of land and forest fires in a region, so that the more geothermal point exist, the more potential for landfill incidents in a region. Hence, it is necessary to implement a system that can cluster the geothermal point data that has the potential in causing fire with farious status such as high, middle, and low potential. Improved K-Means is one of the most popular clustering methods and it can be used for geothermal point grouping. This algorithm performs clustering process based on the maximum distance as the cluster center and the cluster center distance will be calculated with the other data to be grouped. The calculation is done continuously until the data clustering does not change. That case is proven in this research where the evaluation result that uses silhouette coefficient give the highest point of 0.908000874 for the value of cluster 2 and the amount of data 700.
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.
Co-Authors Achmad Arwan Achmad Dewanto Aji Wibisono Adam Hendra Brata Adinugroho, Sigit Afrida Djulya Ika Pratiwi Aida Fitri Nur Amrina Ainun Najib Eka Christianto Aisha Laras Akmilatul Maghfiroh Al-Mar'atush Shoolihah Allifira Andara Hasna Ana Mariyam Puspitasari Andika Indra Kusuma Andreas Pardede Angelika Trivena Lodong Anggita Nurfadilla Mahardika Annisa Amalia Nur'aini Anto Satriyo Nugroho Ardiansyah Setiajati Arry Supriyanto Arya Agung Andika Aryu Hanifah Aji Asfie Nurjanah Ayu Anggrestianingsih Ayudiya Pramisti Regitha Ayustina Giusti Azizah Nurul Asri Bagas Laksono Bayu Rahayudi Beryl Labique Ahmadie Budi Darma Setiawan Budi Kurniawan Cahya Chaqiqi Candra Dewi Dani Devito Delischa Novia Sabilla Deo Hernando Dian Eka Ratnawati Diantarakita Diantarakita Dwi Retnoningrum Dyan Putri Mahardika Eko Wahyu Hidayat Erlyan Eka Pratiwi Faizatul Amalia Fajar Pangestu Fajar Pradana Fajri Eka Saputra Farizky Novanda Pramuditya Femilia Nopianti Feris Adi Kurnia Sadiva Fitri Dwi Astuti Fransiskus Cahyadi Putra Pranoto Grace Theresia Situmorang Gusti Ngurah Wisnu Paramartha Hafid Satrio Priambodo Hardyan Zalfi Haris Bahtiar Asidik Harits Abdurrohman Herman Tolle Imam Cholissodin Indriati Indriati Irwan Shofwan Javier Ardra Figo Jefri Hendra Prasetyo Kholifa'ul Khoirin Lailil Muflikhah Latifa Nabila Harfiya Laviana Agata M. Ali Fauzi Maharani Tri Hastuti Maria Sartika Tambun Miftahul Arifin Muh Arif Rahman Muh. Arif Rahman Muh. Arif Rahman Muh. Ihsan As Sauri Muhamad Rendra Husein Roisdiansyah Muhammad Dimas Setiawan Sanapiah Muhammad Fahmi Hidayatullah Muhammad Fahmi Wibawa Muhammad Faiz Abdul Hamif Muhammad Fajriansyah Muhammad Heryan Chaniago Muhammad Ikhsan Nur Muhammad Rafi Farhan Muhammad Tanzil Furqon Muhja Mufidah Afaf Amirah Nabilla Putri Sakinah Nanda Dwi Putra Miskarana Ade Natassa Anastasya Naufal Sakagraha Kuspinta Nelli Nur Rahma Ni'mah Firsta Cahya Susilo Ningsih Puji Rahayu Nizar Riftadhi Prabandaru Novanto Yudistira Nur Afifah Sugianto Nur Faiqoh Laely Ambarwati Nur Firra Hasjidla Nur Kholida Afkarina Nurudin Santoso Nurul Hidayat oktiyas muzaky Luthfi, oktiyas muzaky Olive Khoirul L.M.A. Puteri Aulia Indrasti Putra Pandu Adikara Putri Bunga Rahmalita Putu Satya Cahyani Rahma Juwita Sany Randy Cahya Wihandika Rekyan Regasari Mardhi Putri Rekyan Regasari Mardi Putri, Rekyan Regasari Mardi Restu Widodo Resya Futri Hadi Febryana Retno Dewi Anissa Revan Yosua Cornelius Sianturi Ridho Saputra Rinindya Nurtiara Puteri Rizka Husnun Zakiyyah Rizki Aziz Amanullah Rosi Afiqo Rr Dea Annisayanti Putri Ryan Iriany Satria Habiburrahman Fathul Hakim Sayyidah Karimah Sindy Erika Br Ginting Sri Rahadian Ramadhan Sakti Susiawan Hastomo Ajie Talitha Raissa Tusiarti Handayani Tusty Nadia Maghfira Umar Zaki Izzuddin Utaminingrum, Fitri Vriza Wahyu Saputra Wayan Firdaus Mahmudy Wayan Firdaus Mahmudy Wenny Ramadha Putri Willy Karunia Sandy Winda Cahyaningrum Winda Ika Praseptiyana Witriana Sumarni Yane Marita Febrianti Yosafat Vincent Saragih Yuita Arum Sari Yunita Kristanti Emilia