Articles
<![CDATA[Rancang Bangun Prototype Ciri Citra Kulit Luar Kayu Tanaman Karet menggunakan Metode Virtual Center Of Gravity ]]>
<![CDATA[Arief Bramanto Wicaksono Putra]]>;
<![CDATA[Sholeh Hadi Pramono]]>;
<![CDATA[Agus Naba]]>
<![CDATA[ Jurnal EECCIS Vol 8, No 1 (2014) ]]>
Publisher : <![CDATA[Fakultas Teknik, Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (638.574 KB)
<![CDATA[Citra dijital kulit kayu tanaman karet memiliki tingkat kerapatan intensitas yang tinggi. Pola suatu citra dapat dikenali melalui proses analisis ciri. Ekstraksi ciri yang merupakan salah satu proses analisis ciri pada penelitian ini mengunakan metode Virtual Center Of Gravity (VCG) dengan segmentasi citra berbasis warna abu-abu (Gray Base) dan warna hitam putih (Contour Base). Prototype ciri yang dibangun berasal dari 3 (tiga) data citra yang telah melalui proses pemilihan data terbaik (best sample selection) sebagai proses pelatihan dengan menggunakan tenik coefficient correlation. Keputusan yang diharapkan adalah sebuah model klasifikasi usia produktifitas tanaman karet dengan menguji berbagai data citra uji terhadap prototype ciri dengan menggunakan pengukuran kemiripan dan jarak (similiarity measurement). Performance dari pengujian ini menggunakan pengukuran tingkat kesalahan (error analysis rate) dan pengukuran keberhasilan penentuan klasifikasi (Accuracy). Hasil penelitian ini menunjukkan bahwa dari maksimal 18 data pengujian yang terbagi menjadi maksimal 6 data valid image dan 12 data forgery image, dengan variasi pengujian sebanyak 5 kali pada setiap kategori diperoleh tingkat Accuracy terendah sebesar 77.78% dan tertinggi sebesar 85.19%.Kata Kunci — Performance, Prototype ciri, Segmentation Gray Base & Contour Base, Similarity measurement, Virtual Center of Grafity.]]>
<![CDATA[Penerapan Metode Hybrid Fuzzy C-Means dan Particle Swarm Optimization (FCM - PSO) E untuk Segmentasi Citra Geografis ]]>
<![CDATA[Herditomo Herditomo]]>;
<![CDATA[Sunaryo Sunaryo]]>;
<![CDATA[Agus Naba]]>
<![CDATA[ Jurnal EECCIS Vol 8, No 1 (2014) ]]>
Publisher : <![CDATA[Fakultas Teknik, Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (524.931 KB)
<![CDATA[Beberapa lapisan dari Sistem Informasi Geografis (SIG) bisa dibedakan oleh mata telanjang dari sebuah citra satelit namun pasti akan melelahkan jika mengamati citra begitu banyak. Penelitian ini dilakukan untuk melakukan otomasi pengamatan dengan metode segmentasi. Metode segmentasi yang diusulkan adalah Hybrid Fuzzy C-Means – Particle Swarm Optimization (FCM-PSO). Hasil penelitian menunjukkan FCM-PSO lebih unggul dari FCM biasa sekalipun dengan kelemahan waktu eksekusi yang lebih panjang.Kata Kunci—FCM, PSO, Segmentasi, SIG]]>
<![CDATA[Bayesian Network Expert System for Early Diagnosis of Heart Diseases ]]>
<![CDATA[Mohamad Saad A.Sawa]]>;
<![CDATA[Agus Naba]]>;
<![CDATA[Harry Soekotjo Dachlan]]>
<![CDATA[ Jurnal EECCIS Vol 7, No 2 (2013) ]]>
Publisher : <![CDATA[Fakultas Teknik, Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (760.933 KB)
<![CDATA[Heart disease is a deadly disease in the world. Some countries that have a high risk of death are America, Australia and England. It is difficult for a person do a medical checkup not only because of the financial matter but also because they don't care about it. This study is to help people on early diagnose to the risk of heart disease. Expert System is used as the basis of this study which is using Bayesian Network algorithms with datasets from previous studies conducted in Europe. The objective of this research are (1) to design knowledge base, inference engine with Bayesian network for early diagnose of heart diseases, (2) to develop web-based system that help people to get early diagnose of risk heart disease. This study was conducted by the help of a heart disease specialist and internist that helps validate the dataset and the results of research through application testing detection of heart disease risk. This result is consistent with the analysis that can be used by physicians and public.Index Terms—expert system, Bayesian network, heart disease, early diagnose.]]>
<![CDATA[Peramalan Beban Jangka Panjang Sistem Kelistrikan Kota Palu Menggunakan Metode K Logika Fuzzy ]]>
<![CDATA[Maryantho Masarrang]]>;
<![CDATA[Erni Yudaningtyas]]>;
<![CDATA[Agus Naba]]>
<![CDATA[ Jurnal EECCIS Vol 9, No 1 (2015) ]]>
Publisher : <![CDATA[Fakultas Teknik, Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (452.374 KB)
<![CDATA[Long-term load forecasting is intended to estimate the electrical load on an annual time period. It has an important role in the real control and security functions of an energy management system. This study is focused on designing long-term load forecasting in Palu electrical systems by using mamdani fuzzy logic method. The process of long term load forecasting is done by providings inputs; the number of customers, PDRB, and the power used for residences, businesses and public load at the previous year into the fuzzy logic system so that it is produced an output: the power used for the next year. The shows that mamdani fuzzy logic provide high level accuracy of forecasting and very small value of MSE.Index Terms:- fuzzy logic, MSE value, number of consumers, PDRB, the power used]]>
<![CDATA[Analisis Jarak Microphone Array dengan Teknik Pemrosesan Sinyal Fast Fourier Transform Beamforming ]]>
<![CDATA[Moh. Fausi]]>;
<![CDATA[Agus Naba]]>;
<![CDATA[Djoko Santjojo]]>
<![CDATA[ Jurnal EECCIS Vol 9, No 1 (2015) ]]>
Publisher : <![CDATA[Fakultas Teknik, Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (503.721 KB)
<![CDATA[The main problem in the application of the sound source detection is to estimate the angle of the wave or called as Direction Of Arrival (DOA) of Planewave. The method commonly to overcome the problem to utilize the sensor array by the data processing technique such as a beamforming technique. In this research was done by DOA estimation that used technique Fast Fourier Trasnfrom (FFT) beamformer with sensor configuration by Uniform Linear Array (ULA). The analysis has been to determine the distance of the array microphone that has DOA estimation with high accuration to the real source posisition. Based on the variation of distance of array microphone tested, shown the 6 cm is the bes distance which has the most dominant DOA estimation results with high accuracyKeywords : DOA , FFT Beamforming , Array sensor , ULA]]>
<![CDATA[Game Chicken Roll dengan Menggunakan Metode Forward Chaining ]]>
<![CDATA[Yogie Susdyastama Putra]]>;
<![CDATA[M. Aziz Muslim]]>;
<![CDATA[Agus Naba]]>
<![CDATA[ Jurnal EECCIS Vol 7, No 1 (2013) ]]>
Publisher : <![CDATA[Fakultas Teknik, Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (616.361 KB)
<![CDATA[Metode forward chaining pada umumnya digunakan untuk sistem pendukung keputusan dan sistem pakar. Penelitian ini menggunakan algoritma forward chaining, khususnya untuk proses review dan untuk menentukan apakah seorang pemain game layak melanjutkan ke level berikutnya. Algoritma forward chaining adalah algoritma yang berbasiskan pada fakta-fakta atau premise yang ada sehingga menghasilkan sebuah kesimpulan atau konsekuen. Hasil pengujian menunjukkan bahwa nilai validitas mencapai 100%. Hasil didapat dari komparasi data antara rules dan hasil pengujian yang didapat saat bermain game.Kata Kunci : Game, Chicken Roll, Forward Chaining, Sistem Pakar, Sistem Pendukung Keputusan.]]>
<![CDATA[Klasifikasi Kendaraan Menggunakan Gaussian Mixture Model (GMM) dan Fuzzy Cluster K Means (FCM) ]]>
<![CDATA[Fitroh Amaluddin]]>;
<![CDATA[M. Aziz Muslim]]>;
<![CDATA[Agus Naba]]>
<![CDATA[ Jurnal EECCIS Vol 9, No 1 (2015) ]]>
Publisher : <![CDATA[Fakultas Teknik, Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (748.876 KB)
<![CDATA[This paper describes how to record a moving object and save as new video files (* .avi), then filtering the moving objects (Vehicles) by using a Gaussian Mixture Model (GMM) with 2 types of distribution, i.e. Bacground and Foreground distribution. The shape of the foreground distribution is filtered by morphological operations and segmented by using Bit Large Object (BLOB) Segmentation to get the vehicle dimensions. Feature extraction results of these vehicles, will be used as data cluster for vehicles classification by using Fuzzy Cluster Means (FCM). Resulting experiments show good results with 91.3% of accuracy rate.Index Terms—GMM, BLOB, FCM, Classification.]]>
<![CDATA[Optimal Control Design of Eco-Friendly Power Generators Using Wind Power ]]>
<![CDATA[Ahmad Nadhir]]>;
<![CDATA[Agus Naba]]>
<![CDATA[ Natural B, Journal of Health and Environmental Sciences Vol 1, No 4 (2012) ]]>
Publisher : <![CDATA[Natural B, Journal of Health and Environmental Sciences ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (59.557 KB)
|
DOI: 10.21776/ub.natural-b.2012.001.04.3
<![CDATA[Two optimal control methods based on fuzzy inference system (FIS) for maximizing extraction of energy in wind energy conversion system (WECS) is already presented. An MPPTFIS is a first optimal control method using maximum power point tracking approach and fuzzy system. The objective of MPPTFIS is to make zero value change rate of power and rotor speed. A control system will drive an actuator to increasing or decreasing the generator speed depend on the measurement rate of power and rotor speed. An optimal of WECS can be achieved by carried through the rate of power and rotor speed that operating near optimal point. The second optimal control method is proposed by using adaptive neuro fuzzy inference system (ANFIS) to finding model of power curve that will be applied for design of linear control feedback (LCANFIS). The advantage of LCANFIS than MPPTFIS is only one parameter measusrement needed: wind speed. MPPTFIS and LCANFIS could maximize extraction of the wind energy that verified by a power coefficient Cp stay at its maximum almost all the time and an actual power line close to a maximum power extraction (MPE) line reference during simulation process using a same of wind profile. ]]>
<![CDATA[Adaptive Control with Approximated Policy Search Approach ]]>
<![CDATA[Agus Naba]]>
<![CDATA[ Journal of Engineering and Technological Sciences Vol. 42 No. 1 (2010) ]]>
Publisher : <![CDATA[Institute for Research and Community Services, Institut Teknologi Bandung ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.5614/itbj.eng.sci.2010.42.1.2
<![CDATA[Most of existing adaptive control schemes are designed to minimize error between plant state and goal state despite the fact that executing actions that are predicted to result in smaller errors only can mislead to non-goal states. We develop an adaptive control scheme that involves manipulating a controller of a general type to improve its performance as measured by an evaluation function. The developed method is closely related to a theory of Reinforcement Learning (RL) but imposes a practical assumption made for faster learning. We assume that a value function of RL can be approximated by a function of Euclidean distance from a goal state and an action executed at the state. And, we propose to use it for the gradient search as an evaluation function. Simulation results provided through application of the proposed scheme to a pole -balancing problem using a linear state feedback controller and fuzzy controller verify the scheme's efficacy.]]>
<![CDATA[Evaluation-Function-based Model-free Adaptive Fuzzy Control ]]>
<![CDATA[Agus Naba]]>
<![CDATA[ Journal of Engineering and Technological Sciences Vol. 48 No. 6 (2016) ]]>
Publisher : <![CDATA[Institute for Research and Community Services, Institut Teknologi Bandung ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.5614/j.eng.technol.sci.2016.48.6.4
<![CDATA[Designs of adaptive fuzzy controllers (AFC) are commonly based on the Lyapunov approach, which requires a known model of the controlled plant. They need to consider a Lyapunov function candidate as an evaluation function to be minimized. In this study these drawbacks were handled by designing a model-free adaptive fuzzy controller (MFAFC) using an approximate evaluation function defined in terms of the current state, the next state, and the control action. MFAFC considers the approximate evaluation function as an evaluative control performance measure similar to the state-action value function in reinforcement learning. The simulation results of applying MFAFC to the inverted pendulum benchmark veriï¬ed the proposed scheme's efficacy.]]>
