Article Per Year (5 Year)
p-Index From 2020 - 2025
1.513
P-Index
This Author published in this journals
All Journal Epsilon: Jurnal Matematika Murni dan Terapan KLIK (Kumpulan jurnaL Ilmu Komputer) (e-Journal) Jambura Journal of Mathematics Journal of Mathematics: Theory and Applications Jurnal Pengabdian Ilung (Inovasi Lahan Basah Unggul) Bioscientiae, Jurnal ilmu ilmu Biologi
Soesanto, Oni
Program Studi Ilmu Komputer, Fakultas Matematika Dan Pengetahuan Alam, Universitas Lambung Mangkurat, Indonesia
Agriculture, Biological Sciences & Forestry Arts Humanities Astronomy Biochemistry, Genetics & Molecular Biology Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Dentistry Economics, Econometrics & Finance Education Energy Environmental Science Immunology & microbiology Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Medicine & Pharmacology Nursing Physics Public Health Social Sciences Transportation Veterinary Other

Published : 17 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 17 Documents
Search

 1   2 
PENERAPAN METODE RBPNN UNTUK KLASIFIKASI KANKER PAYUDARA Fairudz Shahura; Oni Soesanto; Fatma Indriani
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 3, No 2 (2016)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v3i2.51

Abstract

Breast cancer is the most commonly diagnosed cancer in women. Breast cancer cases are increasing each year. Therefore, early detection of breast cancer plays an important role in anticipating the spread of cancer. Fine-needle aspiration (FNA) biopsy is one way to detect breast cancer. FNA is a method of taking the majority of tissue with a syringe that is intended to aid in the diagnosis of various tumor diseases. The FNA samples that have been studied generate ten characteristics, namely radius, texture, perimeter, area, compactness, smoothness, concavity, concave points, symmetry, and fractal dimension. These characteristics are used to classify benign and malignant breast cancer. To classify breast cancer, Radial Basis Probabilistic Neural Network (RBPNN) required. This study aims to determine how the performance of the method of Radial Basis Probabilistic Neural Network for classifying breast cancer. The accuracy was found to be equal 93.19% for training data, and 90.35% for testing data.Keywords: Radial Basis Probabilistic Neural Network, Classification, Breast Cancer.Kanker payudara merupakan penyakit yang paling banyak menyerang kaum wanita. Penderita penyakit kanker payudara semakin meningkat pada tiap tahunnya. Oleh karena itu deteksi dini kanker payudara memegang peranan penting dalam mengantisipasi penyebaran kanker. Salah satu cara untuk mendeteksi kanker payudara adalah  dengan fine-needle aspiration (FNA) biopsy. FNA merupakan suatu metode pengambilan sebagian jaringan tubuh manusia dengan jarum suntik yang bertujuan untuk membantu diagnosis berbagai penyakit tumor. Sampel FNA yang telah diteliti menghasilkan sepuluh karakteristik, yaitu radius, texture, perimeter, area, compactness, smoothness, concavity, concave points, symmetry, dan fractal dimension. Kesepuluh karakteristik tersebut digunakan untuk mengklasifikasikan kanker payudara jinak dan ganas. Untuk mengklasifikasi tingkat keganasan dari kanker payudara dapat dilakukan dengan metode Radial Basis Probabilistic Neural Network (RBPNN). Penelitian ini bertujuan untuk mengetahui bagaimana performansi metode Radial Basis Probabilistic Neural Network untuk mengklasifikasikan kanker payudara. Dari hasil penelitian didapat akurasi 93.19% untuk data training, serta 90.35% untuk data testing.Kata kunci : Radial Basis Probabilistic Neural Network, Klasifikasi, Breast Cancer.
ANALYTIC NETWORK PROCESS (ANP) PADA BALANCED SCORECARD (BSC) DENGAN PENDEKATAN FUZZY Oni Soesanto; Muhammad Mahfuzh Shiddiq; Oktarini Oktarini
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 3, No 2 (2016)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v3i2.56

Abstract

ABSTRAKHimpunan fuzzy merupakan perkembangan dari himpunan klasik. Himpunan fuzzy digunakan sebagai dasar dalam logika fuzzy. Logika fuzzy banyak diterapkan pada penelitian teknik pengambilan keputusan. Teknik pengambilan keputusan yang menerapkan logika fuzzy juga dapat digunakan dalam Balanced ScoreCard (BSC). Salah satu metode teknik pengambilan keputusan adalah Fuzzy Analytic Hierarchy Process (FAHP). FAHP telah diterapkan dalam BSC, namun tidak mencerminkan kondisi BSC sehingga diperlukan metode lain yang  memperhatikan keterkaitan antar aspek,  yaitu Fuzzy Analytic Network Process (FANP). FANP mampu memperbaiki kelemahan FAHP berupa kemampuan mengakomodasi keterkaitan antar kriteria atau alternatif. Paper ini membahas konsep pendekatan Fuzzy pada metode ANP menggunakan extent analysis method untuk mengukur kinerja perusahaan berdasarkan indikator dalam perspektif BSC.Kata Kunci: Balanced Scorecard (BSC), Metode extent analysis, Fuzzy Analytic Network Process (FANP), Triangular Fuzzy Number (TFN)
OPTIMASI LEARNING RADIAL BASIS FUNCTION NEURAL NETWORK DENGAN EXTENDED KALMAN FILTER Oni Soesanto; Arfan Eko Fahrudin; Dodon T. Nugrahadi
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 2, No 2 (2015)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v2i2.40

Abstract

Dalam paper ini dibahas mengenai optimasi Radial Basis Function Neural Network (RBFNN) dengan Extended Kalman Filter. Proses learning RBF dengan Extended Kalman Filter menggunakan parameter bobot pada hidden center RBF yaitu noise proses pada perhitungan bobot hidden center dan noise pengukuran pada data output. Extended Kalman Filter pada jaringan syaraf RBF berfungsi mengoptimalkan bobot pada hidden center dengan meminimalkan error pada output RBF dengan parameter proses pada unit center RBF dan parameter bobot output pada output layer. Bobot output optimal diperoleh pada saat error output pada training RBF telah konvergen, selanjutnya digunakan untuk proses testing. Algoritma Extended Kalman Filter dan Radial Basis Fuction (EKF-RBF) memungkinkan proses learning memungkinkan center dan variansi pada hidden layer tidak perlu dihitung sebelum bobot output optimum ditemukan. Hasil simulasi menunjukkan bahwa pada training, performansi klasifikasi algoritma EKF-RBF mampu mengenali rata-rata 92.42% dan untuk prediksi didapatkan MAE sebesar 5,3846 dan RMSE sebesar 16,2398 dengan CPU time 24,4146 detik dengan iterasi rata-rata 68,8 iterasi, testing in sample rata-rata MAE sebesar 4,3388, rata-rata RMSE sebesar 13,2230 dan rata-rata CPU time sebesar 0,1123 detik sedangkan pada testing out sample didapatkan rata-rata MAE sebesar 4,1065, RMSE sebesar 11,0126 dan CPU time sebesar 0,0265 detik. Kata kunci : Extended Kalman Filter, Extended Kalman Filter – Radial Basis Function (EKF-RBF), Optimasi Jaringan Syaraf RBF
SISTEM FUZZY LOGIC TERTANAM PADA MIKROKONTROLER UNTUK PENYIRAMAN TANAMAN PADA RUMAH KACA Andi Farmadi; Dodon T Nugrahadi; Fatma Indriani; Oni Soesanto
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 4, No 2 (2017)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v4i2.121

Abstract

Greenhouse use is often used as a crop development site for cultivation or research, by controlling temperature, soil moisture and irrigation, and continuously being developed in automated control systems. Greenhouse control developed in this research is by using fuzzy system algorithm. The fuzzy system is embedded in arduino uno wifi microcontroller for the control of crop irrigation in greenhouses with C programming language on arduino IDE. The system input consists of two variables that are inputted through the temperature sensor input and the soil moisture sensor. The sensor input variable is then made fuzzy set for mapping the temperature condition in the cold, or hot, for soil moisture variable made with three sets that is dry, moist and wet, from the two variables of the input with each of the three sets made rule in this case made in nine decision rule for plant watering status. fuzzy method used is to use sugeno method because it is simpler in decision making which allows more efficient in writing source code on arduino microcontroller which has small memory limitations. The result of the decision or output of the fuzzy system is comprised of a watering system of plants with non-flush status, medium flush, and flushKeywords: Fuzzy system, microcontol, greenhouse.Pemanfaatan Rumah Kaca sering digunakan sebagai tempat pengembangan tanaman untuk budidaya ataupun penelitian, dengan mengontrol suhu, kelembaban tanah dan pengairan, yang terus mengalami perkembangan dalam sistem kontrol otomatis. Pengontrolan pada rumah kaca yang dikembangkan pada penelitian ini yaitu dengan menggunakan algoritma sistem fuzzy. Sistem Fuzzy yang ditanamkan pada mikrokontroller arduino uno wifi untuk mengontol otomatis penyiraman tanaman pada rumah kaca dengan bahasa pemrograman C pada IDE arduino. Input sistem terdiri dari dua variabel yang dimasukkan melalui input sensor suhu dan sensor kelembaban tanah. Variabel inputan sensor kemudian dibuat himpunan fuzzy untuk memetakan keadaan suhu pada kondisi dingin sedang, atau panas, untuk variabel kelembaban tanah dibuat dengan tiga himpunan yaitu kering, lembab dan basah, dari kedua varibel inputan tersebut dengan masing masing tiga himpunan dibuatkan rule dalam kasus ini dibuat dalam sembilan buah rule keputusan untuk status penyiraman tanaman.metode fuzzy yang digunakan adalah menggunakan metode sugeno karena lebih simpel dalam pengambilan keputusan yang memungkinkan lebih efisien dalam penulisan source code pada mikrokontroller arduino yang memiliki keterbatasan memori yang kecil. Hasil dari keputusan atau output dari sistem fuzzy tersebut adalah terdiri sistem penyiraman tanaman dengan status tidak siram, siram sedang, dan siram banyakKata Kunci : Sistem  Fuzzy, mikrokontol, rumah kaca.
Algoritma Ant Colony Optimization pada Quadratic Assignment Problem Oni Soesanto; Pardi Affandi; Nurul Dasima Astuti
Jambura Journal of Mathematics Vol 1, No 2: Juli 2019
Publisher : Department of Mathematics, Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (310.11 KB) | DOI: 10.34312/jjom.v1i2.2353

Abstract

Quadratic Assignment Problem (QAP) is one extension of the assignment problem by setting n facilities to n certain locations to minimize the total assignment costs. QAP is also a combinatorial optimization problem that is a problem that has a finite set of solutions. Basically the solution of combinatorial problems can be obtained with the right results but for complex problems with larger data sizes it is quite difficult to calculate because the time used is long enough for the completion process. One of the algorithms implemented in the completion of QAP is the Ant Colony Optimization (ACO) algorithm is an algorithm that mimics the behavior of ants in finding food from the nest to a food source with the help of indirect communication called pheromone, so that pheromone is used to find optimal solutions with quite a short time. in this research ACO is used to solve the QAP problem by using a random proportional of rule formula then getting the smallest solution and renewing the pheromone until the assignment is stable and the solution obtained is fixed until the maximum assignment solution. The results obtained to complete the Quadratic Assignment Problem with the Ant Colony Optimization algorithm to get a solution to the QAP problems tested in the Nugent case resulted in a more minimal solution and the placement of appropriate location facilities through pheromone assistance and stored in a taboo list so that all facilities get a decent location with a worth it short time in completion.
Fuzzy Logic (Bagian 1): Senandung Lukisan Cadas Dari Situs Bukit Bangkai Untuk Pendidikan Wisata Masyarakat Tanto Budi Susilo; Oni Oni Soesanto
Jurnal Pengabdian ILUNG (Inovasi Lahan Basah Unggul) Vol 2, No 1 (2022)
Publisher : Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/ilung.v2i1.5327

Abstract

Ini tulisan pertama terdiri atas tiga bagian, terkait pengabdian masyarakat di kawasan situs Bukit Bangkai tahun 2017 dan 2022. Tujuan tulisan ini pula sekedar memberikan suatu deskripsi dan orientasi logika yang tersamar (fuzzy logics) makna artifak berupa lukisan cadas “Burung Enggang dan Perahu” situs Bukit Bangkai, dan menghubungkan dengan burung Enggang yang sebenarnya. Data pengabdian masyarakat yang utama diperoleh berupa lukisan cadas “burung enggang” pada situs Bukit Bangkai kawasan wisata pendidikan, desa Dukuhrejo, Kecamatan Mantewe, Batulicin. Untuk menjadikan wisata pendidikan masyarakat secara umum, maka lukisan itu perlu ditafsirkan atau diberi makna secara akademis. Untuk mengetahui respon masyarakat terhadap pendidikan ekowisata, digunakan metode quisioner terhadap 70 responden. Hasilnya berturut-turut 67 %, 29% dan 3% menyatakan sangat penting, penting dan cukup penting. Para responden merupakan kalangan pelajar milineal. Khusus tangapan responden terhadap karya seni senandung “lukisan cadas” dan “antara kasturi, enggang dan elang”https://youtube.com/shorts/JzvYN4_8LtU?feature=shareatauwww.youtube.com/watch?v=YvDOS83GPkQdanhttps://www.youtube.com/watch?v=Qdkg8MdEhmY, menyatakan isi syair berturut-turut 49 % (aktivitas nenek moyang prasejarah), 39% (lingkungan tempat tinggal nenek moyang dalam gua), sisanya 12% (tradisi religiusitas nenek moyang). Sedangkan tanggapan responden terhadap kajian simbol lukisan cadas berupa “burung enggang dan perahu” menyatakan berturut-turut 55% (sangat penting), 36% (penting) dan 9% (cukup penting). Para responden mengenal lukisan cadas berupa burung enggang dan perahu umumnya melalui media sosial dan jarang melalui kunjungan ke situs. Untuk simbol burung enggang dan perahu, para responden mengenal melalui logo pendidikan atau rumah adat. Oleh karena itu, senandung lukisan cadas situs Bukit Bangkai untuk wisata pendidikan masyarakat merupaka kegiatan yang urgen.Kata Kunci: simbol, senandung lukisan cadas, akademis
REDUKSI DIMENSI INPUT PADA JARINGAN SYARAF PCA-RBF DENGAN SINGULAR VALUE DECOMPOSITION Abdul Hakim Maulana; Oni Soesanto; Thresye Thresye
EPSILON: JURNAL MATEMATIKA MURNI DAN TERAPAN Vol 9, No 2 (2015): JURNAL EPSILON VOLUME 9 NOMOR 2
Publisher : Mathematics Study Program, Faculty of Mathematics and Natural Sciences, Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (240.444 KB) | DOI: 10.20527/epsilon.v9i2.13

Abstract

Artificial neural network is an information processing system that has characteristics similar to biological neural networks. Artificial neural networks are divided into single layers and multiple layers. One of the multiple layer neural networks is Radial Basis Function (RBF). RBF is known to have high computing speed. However, the performance of RBF decreases when it involves the input space with high dimension so it requires simplification of the network. One method of simplifying RBF with respect to the dimension of input space is to use Principal Component Analysis (PCA). When the number of data variables is greater than the number of observations, the ability of PCA to be less effective then required Singular Value Decomposition (SVD) to solve the problem. The purpose of this research is to apply Singular Value Decomposition (SVD) process on PCA-RBF neural network. This study discusses the neural network PCA-RBF. PCA serves to reduce the input dimension of RBF. This dimension of input is known as the principal component (PC). PC determination process is done using PCA method combined with SVD. Furthermore, the PC is used as a new input to the RBF and a clustering process is performed on the PC using the K-means method for the initialization of the RBF center. Inisisalisasi center is the first step RBF in classification. The classification process in RBF consists of two processes namely training and testing. The result of this research is the SVD process on PCA to reduce the dimension of input data consisting of the process of determining the right singular matrix (V) ie calculating the ATA matrix, finding the eigenvalues (λ) and eigenvectors of the ATA matrix, conducting Gram-Schmidt and normalization , and the process of forming Principal Component (PC) is by multiplying the matrix of training data with right singular matrix (V), so that PC is used as new input to RBF. In this research is given example of classification data that is Landsat satellite data. After repeating 30 times the average success of classification in Landsat training data is 79,889% with mean error 20,111%, while for data testing Landsat obtained average success equal to 93,333% with error percentage is 6,667%.
PENGGUNAAN JUMAN & HOQUE METHOD (JHM) PADA PENENTUAN SOLUSI AWAL MASALAH TRANSPORTASI Andry Nor Indrawan; Pardi Affandi; oni Soesanto
EPSILON: JURNAL MATEMATIKA MURNI DAN TERAPAN Vol. 15(1), 2021
Publisher : Mathematics Study Program, Faculty of Mathematics and Natural Sciences, Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (576.108 KB) | DOI: 10.20527/epsilon.v15i1.2876

Abstract

Transportation problems are related to the efficient process of distributing goods by a company or industry. The purpose of solving transportation problems is to minimize the costs incurred in the process of distributing goods from several sources (supply) to several destinations (demand). One way to solve transportation problems is to find an initial feasible solution, continued by finding the optimal solution. This research was done by finding an initial feasible solution using the JHM (Juman & Hoque Method) for both the case of solving balanced transportation problems and unbalanced transportation problems. The method has the characteristic in the initial allocation process starting at the cell with the smallest cost in each column as much as the quantity of each demand. In addition, identification of whether the row if occupied or not was done based on the allocation for each row to the quantity of each inventory. This research aimed to explain about solving transportation problems by determining the initial feasible solution using JHM and performing optimality test using potential method. The methods of this research was to identify categories of transportation problems, determine the initial solution using JHM, and test the optimality using potential method. Based on the results of this research, JHM model may be used to solve transportation problems. In the steps of JHM there are explanations of some theorem regarding the selection of the column and row which will be the first to be processed to determine the value of intial solution of transportation problems. The initial solution by using JHM tends to approach the value of optimal solution after test of optimality was done by using the potential method.
MULTI OBJECTIVE FUZZY LINEAR PROGRAMMING Muhammad Mefta Eryshady; Oni Soesanto; Muhammad Ahsar Karim
EPSILON: JURNAL MATEMATIKA MURNI DAN TERAPAN Vol 8, No 1 (2014): JURNAL EPSILON VOLUME 8 NOMOR 1
Publisher : Mathematics Study Program, Faculty of Mathematics and Natural Sciences, Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (167.233 KB) | DOI: 10.20527/epsilon.v8i1.104

Abstract

Linear programming is a general model that can be used in problem solving the allocation problem of limited resources optimally. The mathematics model of linear programming consists of two function: objective function and constraint function. Based on the number of objective functions, linear programming is divided into two types: Single Objective Linear Programming and Multi-Objective Linear Programming. Multi Objective Linear Programming which values are defined in the scope of fuzzy is called Multi Objective Fuzzy Linear Programming. To find the optimal solution of the problem, firstly it is divided into a linear program with single objective and solved using the simplex method. This research was carried out by using a literature study. The results of this study indicate that the optimal solution of Multi Objective Fuzzy Linear Programming will be decision variable ()x, that are: 12,,...,nxxx which its values if they are substituted into the constraint function, the results will be consistent with the limits of specified| resources, as well as if they are substituted into the objective function, then it will be obtained the optimal solution of all expected purposes.
PENENTUAN LOKASI TERBAIK LINGKUNGAN PERUMAHAN DI PERKOTAAN DENGAN PENDEKATAN FUZZY Siti Sulistiani; Oni Soesanto; Mohammad Mahfuzh Shiddiq
EPSILON: JURNAL MATEMATIKA MURNI DAN TERAPAN Vol 8, No 1 (2014): JURNAL EPSILON VOLUME 8 NOMOR 1
Publisher : Mathematics Study Program, Faculty of Mathematics and Natural Sciences, Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (255.537 KB) | DOI: 10.20527/epsilon.v8i1.105

Abstract

Fuzzy logic provides a solution to the problem of uncertainty, because in real life often encountered things that are uncertain or vague and sometimes difficult to resolve firmly. Fuzzy logic is able to overcome the uncertainty in real-life cases. One is the problem of determining the right location to create a particular facility such as a residential neighborhood, where there are several factors to consider and sometimes difficult to decide firmly. To make a multi-criteria decision, there are several methods that can be used. But in this research that will be used is one method of Fuzzy Analytical Hierarchy Process (FAHP) is Method Extent Analysis Chang (1996). The purpose of this research is to determine optimal location of an urban housing environment by using Extent Analysis Chang Method. The decision-making process is carried out with the steps contained in Ext's Analysis (1996) method sequentially starting from criteria, sub criteria and alternatives. The final decision is made by ranking the normalized vector weighting of all criteria and sub criteria. Location A was chosen as the optimal location, because it has the highest ranking weighting that is 0.330.
Co-Authors Abdul Hakim Maulana Andi Farmadi Andry Nor Indrawan Arfan Eko Fahrudin Arief Rahmad Maulana Akbar Azidi Irwan Bambang Sugiyanto Sugiyanto Dewi Sri Susanti Dodon Turianto Nugrahadi Fairudz Shahura Fatma Indriani Hayqal Hazmi Qastari Hayqal Mochamad Arief Soendjoto Mohammad Mahfuzh Shiddiq Muhammad Ahsar Karim Muhammad Mahfuzh Shiddiq Muhammad Mefta Eryshady Nurul Dasima Astuti Oktarini Oktarini Pamona Dwi Rahayu Paola Anna Elena Bianchi Paola Bianchi Pardi Affandi Rahmad Eko Sanjaya Rahmat Rahmat Yunus Rahmat Yunus Raifa Azizia Mustaqima Rani Sasmita Siti Sulistiani Sri Elina Herni Yulianti Susilo, Tanto Budi Thresye Thresye Yuana Sukmawaty Yuniardi Wahyu Nugraha Yuyun Hidayat