Rachmat Gernowo
Fakultas Sains dan Matematika, Universitas Diponegoro

Published : 9 Documents
Articles

Found 9 Documents
Search

SISTEM PAKAR IDENTIFIKASI MODALITAS BELAJAR SISWA DENGAN IMPLEMENTASI ALGORITMA C4.5 Soewono, Rachmawati; Gernowo, Rachmat; Sasongko, Priyo Sidik
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 4, No 1 (2014): Volume 4 Nomor 1 Tahun 2014
Publisher : Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1984.46 KB) | DOI: 10.21456/vol4iss1pp20-27

Abstract

C4.5 Algorithm is one of the classification technique in machine learning which is used in data mining process by build a decision tree which is represent in the rules. The aims of classification technique in data mining is to recognize the regularity of the pattern and the relation in a huge dataset by historical data collection. Students? modalities measurement which is done by the questionnaire is produce historical data which is potentially to be processed to generate the classification that can be converted in rules. The expert acquisition and the C4.5 algorithm classification rules are used as knowledge base in the expert system. Therefore this research is done to build an expert system of the student?s modalities identification by implementing C4.5 algorithm that can produce seven categories of modalities classification, they are : visual, auditory, kinesthetic, visual-auditory, visual-kinesthetic, auditory-kinesthetic and visual-auditory-kinesthetic which has good in accuracy. The accuracy of the C4.5 algorithm classification and the expert system testing prediction is 80%. Keywords : Expert system; Decision tree; C4.5 Algorithm; Modalities.  
METODE JARINGAN SYARAF TIRUAN UNTUK PREDIKSI PERFORMA MAHASISWA PADA PEMBELAJARAN BERBASIS PROBLEM BASED LEARNING (PBL) Badieah, Badieah; Gernowo, Rachmat; Surarso, Bayu
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 6, No 1 (2016): Volume 6 Nomor 1 Tahun 2016
Publisher : Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (837.567 KB) | DOI: 10.21456/vol6iss1pp46-58

Abstract

In order to improve academic quality in higher education, students? performance evaluation is becoming important. To prevent increasing failure rate in the course, we need a system that is capable of predicting student?s performance in the end of the course. The research used several factors that are considered to affect students' performance on Problem Based Learning (PBL), such as students? demography, students? prior knowledge and group heterogeneity.  The method used in the study was Artificial Neural Network (ANN) with backpropagation training algorithm. Total 8 neurons were used as inputs for ANN which were obtained from gender variable (2 neurons), age variable (1 neuron), students? average knowledge variable (1 neuron), students? average skill variable (1 neuron) and group heterogeneity variable (3 neurons). Several different ANN architecture were tested in the study using 2, 7 and 12 hidden neurons respectively. Each architecture was trained using various different training parameters in order to find the best ANN architecture. Dataset used  in the research were obtained from Academic Information System in Faculty of Dentistry Unissula which contained Adult and Elderly Diseases Course?s participants from year 2009 to 2013. The ANN output were numeric values which represented students? performance in Adult and Elderly Diseases Course. The output of this study is a system that is able to predict the student performance in block course. The result shows that using 7 hidden neurons in the network combining with 0.5 ,0.1 and  9000 for learning rate, momentum and epoch respectively, were the best ANN architechture and parameters in the study. The MSE obtained from validation test was 0,011926 with correlation coefficient (R) 0,796879. The prediction system are expected to help faculty and academic evaluation team to conduct actions to improve student?s academic performance and prevent them from failure in the course. 
METODE QUALITY FUNCTION DEPLOYMENT DAN FUZZY TOPSIS UNTUK SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN PERUSAHAAN PENYEDIA JASA INTERNET Prasongko, Novianto Dwi; Gernowo, Rachmat
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 5, No 2 (2015): Volume 5 Nomor 2 Tahun 2015
Publisher : Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (670.716 KB) | DOI: 10.21456/vol5iss2pp137-144

Abstract

Internet Service Provider (ISP) is a company or business organization that provides access to intenet and services related for individual consumer or companies. There are many ISP in Indonesia recently, and they have almost the same product to offered. This problem makes internet service provider selection become a major issue. Decision support system can be used to recommend the best ISP company based on need. The aim of this research is to used Quality Function Deployment with Fuzzy TOPSIS sequentially to select the best ISP company as needed, and implemented in decision support system for internet service provider selection. Quality Function Deployment and Fuzzy TOPSIS methods used to evaluate, and then recommend the ISP company by ranked. Quality Function Deployment method used to find out customers requirements about internet network, the weighting of the criteria and the assessment of each ISP company. Fuzzy TOPSIS used to rank ISP company. These two methods produce consistent ratings when sensitivity analysis is performed for fuzzy and crisp value. These two methods make decision support system result can be trusted.  
MODEL EVALUASI IKLIM MARITIM TROPIS BERBASIS SISTEM INFERENSI FUZZY JARINGAN SARAF ADAPTIF Gernowo, Rachmat; Sugianto, Denny N
ILMU KELAUTAN: Indonesian Journal of Marine Sciences Vol 9, No 2 (2004): Jurnal Ilmu Kelautan
Publisher : Marine Science Department Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (146.392 KB) | DOI: 10.14710/ik.ijms.9.2.115-119

Abstract

Telah dilakukan studi model prediksi iklim maritim tropis berdasarkan data curah hujan (khususnya Pantai Pulau Jawa) dengan model sistem Inferensi Fuzzy jaringan saraf adaptif ( ANFIS), untuk pengolahan data curah hujan dalam kurun waktu 10 tahun (tahun 1988 ? 1998) sebagai data historis pada proses pembelajaran. Perangkat lunak yang dimanfaatkan antara lain ANFIS dari sistem fuzzy. Hasil yang diperoleh, dengan sistem fuzzy menunjukan jangkauan estimasi untuk seluruh daerah penelitian diperoleh sebesar 89,51 % untuk pengolahan dengan anfis. Variabilitas curah hujan, khususnya daerah pengamatan pantai pulau Jawa menunjukan pola curah hujan monsunal yaitu curah hujan tertinggi ada pada awal dan akhir pentad dan mulai menurunhingga pertengahan pentad.Kata kunci : Prediksi, Iklim maritim tropis, ANFISStudy of tropical maritim climate base rainfall-data prediction modeling has been done by using ANFIS model. As history data (Coastal of Java Island in particular) in learning process was taken from 10 years period (from 1988 to 1998). The ANFIS software was applied in the analysis. The ANFIS processing result show of estimation, with average estimation of the all experiment zone are 89,51 % by ANFIS processing. Rainfall variability of the ANFIS modeling processing with the special in Coastal of Java Island shows the monsoon rainfall pattern that reach top level at the first and final pentad and decrease until the middle pentad.Key words : Prediction, Tropical maritim climate, ANFIS.
MODEL SERVQUAL RULE BASE ASEAN UNIVERSITY NETWORK UNTUK PENILAIAN KUALITAS PROGRAM STUDI Wijayanti, Esti; Farikhin, Farikhin; Gernowo, Rachmat
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 6, No 1 (2016): Volume 6 Nomor 1 Tahun 2016
Publisher : Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1076.224 KB) | DOI: 10.21456/vol6iss1pp59-65

Abstract

As well known that AUN (Asean University Network.AUN) and ABET (Accreditation Boardb for Enginnering and Technology) are non-profit organitatinon which have. AUN (Asean University Network) were using variable with refer to AUN?s criteria?s there consist of fifteen which are: Expected Learning Outcomes, Programme Specification, Programme Structure and Content, Teaching and Learning Strategy, Student Assessment, Academic Staff Quality, Support Staff Quality, Student Quality, Student Advice and Support, Facilities and Infrastructure, Quality Assurance of Teaching/Learning Process, Staff Development Activities, Stakeholders Feedback, Output, Stakeholders Satisfaction,and adopted score's scale 7. In there here, we discuss the fifteen AUN?s of AUN in the criterias. There servqual of as can be into five dimensions, assurance, empathy, responsive, reliability and facilty in order to make the assessment's process easier. This research outcome indicated that this proposed method can be used to evaluate an education program. The validation result by using AUN's data and the analysis of servqual rule base Asean University Network almost have the same pattern with correlation value is 0,985 and this is can be accepted because its validity have reach 97%.
EVALUASI HUMAN MACHINE INTERFACE MENGGUNAKAN KRITERIA USABILITY PADA SISTEM E-LEARNING PERGURUAN TINGGI Qashlim, Akhmad; Prahasto, Toni; Gernowo, Rachmat
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 4, No 2 (2014): Volume 4 Nomor 2 Tahun 2014
Publisher : Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2931.619 KB) | DOI: 10.21456/vol4iss2pp96-107

Abstract

Integration HMI with usability in user interface design process is a standart of the success of a website. The design process is done through the approach to the end user to find a problem solution of human machine interface phenomena. It can also generate the maximum level of satisfaction and success of implementation of the website. The purpose of this research is to evaluate HMI using usabilitycriteria to know the application of HMI concept in e-learning and provide proposals for improvements to the HMI. Questionnaire Data were processed using a descriptive analysis and methods of CFA to know the variables that are weakest and which indicators have an important role in shaping the research variables. Evaluation results indicate the application concept of HMI in the e-learning had been done but not the maximum. Data analysis of the results obtained that the main problem lies in the accessibility criteria in the meantime indicator latent variables from forming error prevention, learnability, memorability, visibility and accessibility of influential factor loading values indicated significantly (unidimensionalitas) in shaping the criteria of latent variables in first-order CFA. The end result of this research is the proposal of improvement as a HMI solution in the form of principles and technicsuser interface design. This solution is focused on the development of standards for the quality of the interface in e-learning systems and not on the digital learning content presented on the e-learning system. Keywords: Descriptive analisis; Human machine interface; Usability; Confirmatory factor analisys; Elearning
PENGGUNAAN ALGORITMA CART UNTUK PEMILIHAN BINGKAI KACAMATA DENGAN PENERAPAN MODEL MORFOLOGI INDEKS WAJAH UNTUK IDENTIFIKASI BENTUK WAJAH Retno Hapsari, Angga Ayu; Gernowo, Rachmat; Widodo, Catur Edi
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 10, No 1 (2020): Volume 10 Nomor 1 Tahun 2020
Publisher : Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1090.936 KB) | DOI: 10.21456/vol10iss1pp1-9

Abstract

The large variety of frame shapes and sizes make it difficult for consumers to choose which one suits their face. The absence of a standard frame style guide between face types against the eyeglass frame complicates the selection of eyeglass frames. The application of the Zen principle (balance) in the selection of the right frame expected to be a consideration in choosing eyeglass frame. Various forms of eyeglass frames that look like a square, round and oval make the Zen principle difficult to apply, so machine learning is needed to be able to create eyeglass frames selection system. Face shape identification help to determine eyeglass frames. Face shape identification is done based on the morphological facial index by calculating face length and width. The decision tree CART algorithm is chosen as a method for selecting eyeglass frames. The study uses 109 face data that have been selected by the optical, from 109 data divided into two parts, 100 training data, and 9 test data. The prediction system produces an accuracy value of 93% at max depth 6 for reading glasses and 91% for sunglasses. The implementation of the CART algorithm is proven to be able to predict the selection of eyeglass frames using morphological attributes of face index.
IMPLEMENTASI METODE PROMETHEE DAN BORDA DALAM SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN LOKASI PEMBUKAAN CABANG BARU BANK Apriliani, Dyah; Adi, Kusworo; Gernowo, Rachmat
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 5, No 2 (2015): Volume 5 Nomor 2 Tahun 2015
Publisher : Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (710.309 KB) | DOI: 10.21456/vol5iss2pp145-150

Abstract

The selection of a new branch bank location is crucial to the success of the bank in the future. The object of this research is BMT Muamalat. PROMETHEE method is used to manage individual decision of each decision makers, while Borda method is used to manage group decisions of PROMETHEE method in ranking the results. The use of these two methods is one solution to produce a more objective group decision. Ranked of alternative location have appropriated with the opening rules of the new branches of BMT Muamalat. As for the variables in this study are criminality, facilities and infrastructures, per capita income, economic growth, population, and the number of competitors around the alternative location of a new branch. The results of this research is Banyuputih as the best alternative location.  
MODEL HEURISTIC TIME INVARIANT FUZZY TIME SERIES DAN REGRESI UNTUK PREDIKSI LABA DAN ANALISIS VARIABEL YANG MEMPENGARUHI Admirani, Ica; Gernowo, Rachmat; Suryono, Suryono
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 6, No 2 (2016): Volume 6 Nomor 2 Tahun 2016
Publisher : Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (980.47 KB) | DOI: 10.21456/vol6iss2pp144-153

Abstract

Model of prediction with fuzzy time series method has ability to capture the pattern of past data to predict the fu ture of data does not need a complicated system, making it easier to use. The research aims to built prediction system using model of  heuristic time invariant fuzzy time series and multiple linear regression to predict profit and analysis of variables that affect profit. Profit forecasting aims to determine the company's prospects in the future in order to remain exist in doing its business. The variables that use in the modelling are profit as the dependent variable, and sales, cost of goods sold, general and administrative expenses, selling and marketing expenses and interest income as the indepent variables. Profit forecasting modelling begins by defining universe of discourse and interval actual data of profit, then determine fuzzy set and actual data fuzzified. Furthermore, fuzzy logical relationship and fuzzy logical relationships group to fuzzified data. The prediction process consist of two prediction phase there are training phase aimed to determine trend predictor and testing phase to determine prediction results. By using 24 profit data samples resulted prediction error by using Mean Absolute Percentage Error is 11,64% and added 13 data for testing obtained prediction error is 22,27%.  In analysis of variables that affect profit is known that sales variable most effect on profit than other variables with a regression coefficient 0.976.