Articles

Chaotic Oscillationofa Three-bus Power System Model Using Elman Neural Network

Lontar Komputer Vol 3, No 2 (2012)
Publisher : Lontar Komputer

Show Abstract | Original Source | Check in Google Scholar

Abstract

Chaotic oscillation of power systems was deeply studied in this paper.By using a three-bus power system, route may cause chaotic behavior in power systems are evaluated, illustrated and discussed.Chaotic oscillationof power systems was modeled using Elman neural network because the Elman neural networkhas a simple form. Backpropagation algorithm with adaptive learning rate and momentum was proposed in this research. Performance of learning rate with momentum was better than learning rate without momentum. Chaoticbehaviors in a power system appeared due to the system operated in critical mode. A Chaotic behavior in power systems was detected by appearing a strange attractor (a chaotic attractor) in phase-plane trajectory.

Aplikasi Pengenalan Kata pada Huruf Braille dan Pelafalannya

Jurnal Teknik ITS Vol 2, No 2 (2013)
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM), ITS

Show Abstract | Original Source | Check in Google Scholar | Full PDF (443.83 KB)

Abstract

Penelitian dan karya dalam bidang optical character recognition terutama pengenalan karakter Braille, hingga saat ini masih jarang dilakukan dan pada umumnya penelitian yang telah ada untuk pengenalan huruf Braille masih berorientasi pada citra statis yang menggunakan scanner. Untuk mengubah lembaran Braille menjadi citra untuk dikenali sebagai karakter alphabet harus menggunakan alat scanner yang mahal, tidak portable, dan tidak praktis. Untuk menyederhanakan proses pengenalan huruf Braille tersebut perlu digunakan sistem pengenalan huruf Braille secara dinamis dengan kamera webcam atau kamera telpon genggam yang lebih murah dan lebih praktis. Tujuan utama dari pembuatan karya ini adalah untuk menyederhanakan proses pengenalan huruf Braille tersebut. Pengenalan huruf Braille secara dinamis ini menggunakan metode chain approximation untuk mendeteksi titik-titik Braille dan metode horizontal and vertical projection untuk pengelompokan posisi-posisi Braille menjadi karakter sesuai dengan aturan pembacaan huruf Braille yang berlaku. Hasil yang didapat dari proyek ini adalah sebuah program yang dapat bekerja untuk mengenali huruf Braille secara dinamis dengan menggunakan kamera webcam dengan tingkat akurasi sebesar 84% benar.

Application of Interval Type-2 Fuzzy Logic System in Short Term Load Forecasting on Special Days

IPTEK The Journal for Technology and Science Vol 22, No 2 (2011)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Original Source | Check in Google Scholar

Abstract

This paper presents the application of Interval Type-2 fuzzy logic systems (Interval Type-2 FLS) in short term load forecasting (STLF) on special days, study case in Bali Indonesia. Type-2 FLS is characterized by a concept called footprint of uncertainty (FOU) that provides the extra mathematical dimension that equips Type-2 FLS with the potential to outperform their Type-1 counterparts. While a Type-2 FLS has the capability to model more complex relationships, the output of a Type-2 fuzzy inference engine needs to be type-reduced. Type reduction is used by applying the Karnik-Mendel (KM) iterative algorithm. This type reduction maps the output of Type-2 FSs into Type-1 FSs then the defuzzification with centroid method converts that Type-1 reduced FSs into a number. The proposed method was tested with the actual load data of special days using 4 days peak load before special days and at the time of special day for the year 2002-2006. There are 20 items of special days in Bali that are used to be forecasted in the year 2005 and 2006 respectively. The test results showed an accurate forecasting with the mean average percentage error of 1.0335% and 1.5683% in the year 2005 and 2006 respectively.

A Comparison between Buck-Boost Inverter with and without Buffer Inductor

IPTEK The Journal for Technology and Science Vol 23, No 2 (2012)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Original Source | Check in Google Scholar

Abstract

The electric vehicle inverter requires an induction motor drive with a high output of voltage and current to reduce the number of batteries used and in turn reduce the vehicle’s weight. In this paper compared two single Phase BuckBoost Inverter (SPBBI), that is between the SPBBI conventional topology with SPBBI new topology uses a buffer inductor. The results of comparison are expected that the new inverter topology can strengthen the voltage greater than the conventional inverter topology. The inverter’s components of capacitor and inductor were reconfigured. The circuit was simulated for various carrier and signal frequencies with various load. The simulation results of the proposed topology compared with the simulation results of conventional topologies commonly used in a variety of frequency and load values. It is shown that the output voltage and current can be strengthened significantly, with a value of more than five times of the output voltage compared to the conventional inverter. The new inverter topology is useful to be implemented for the electric vehicle.

Minimum Constructive Back Propagation Neural Network Based on Fuzzy Logic for Pattern Recognition of Electronic Nose System

IPTEK The Journal for Technology and Science Vol 22, No 3 (2011)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Original Source | Check in Google Scholar

Abstract

Constructive Back Propagation Neural Network (CBPNN) is a kind of back propagation neural network trained with constructive algorithm. Training of CBPNN is mainly conducted by developing the network’s architecture which commonly done by adding a number of new neuron units on learning process. Training of the network usually implements fixed method to develop its structure gradually by adding new units constantly. Although this method is simple and able to create an adaptive network for data pattern complexity, but it is wasteful and inefficient for computing. New unit addition affects directly to the computational load of training, speed of convergence, and structure of the final neural network. While increases training load significantly, excessive addition of units also tends to generate a large size of final network. Moreover, addition pattern with small unit number tends to drop off the adaptability of the network and extends time of training. Therefore, there is important to design an adaptive structure development pattern for CBPNN in order to minimize computing load of training. This study proposes Fuzzy Logic (FL) algorithm to manage and develop structure of CBPNN. FL method was implemented on two models of CBPNN, i.e. designed with one and two hidden layers, used to recognize aroma patterns on an electronic nose system. The results showed that this method is effective to be applied due to its capability to minimize time of training, to reduce load of computational learning, and generate small size of network.

Data Mining Based Receiver Operating Characteristic (ROC) for Fault Detection and Diagnosis in Radial Distribution System

IPTEK The Journal for Technology and Science Vol 20, No 4 (2009)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Original Source | Check in Google Scholar

Abstract

This paper discusses data mining applications, especially the use of support vector machines to identify a fault in the 13 nodes radial distribution system of IEEE standard. The identification process was carried out with support vector machine (SVM). Prior to the identification process by SVM, feature extraction was carried out using wavelet transformation for signal decomposition and signal size reduction. To determine the performance of the identification, ROC (Receiver Operating Characteristic) analysis was used. Based on the curve formed by the ROC a fault in the radial distribution can be identified by SVM with “good” performance This is indicated by the value of the best cut-off point is 0.8 and area under the curve is 0.85854.

Automatic Segmentation of Impaired Joint Space Area for Osteoarthritis Knee on X-ray Image using Gabor Filter Based Morphology Process

IPTEK The Journal for Technology and Science Vol 22, No 3 (2011)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Original Source | Check in Google Scholar

Abstract

Segmentation is the first step in osteoarthritis classification. Manual selection is time-consuming, tedious, and expensive. The system is designed to help medical doctors to determine the region of interest of visual characteristics found in knee Osteoarthritis (OA). We propose a fully automatic method without human interaction to segment Junction Space Area (JSA) for OA classification on impaired x-ray image. In this proposed system, right and left knee detection is performed using using Contrast-Limited Adaptive Histogram Equalization (CLAHE) and template macthing. The row sum graph and moment methods are used to segment the junction space area of knee. Overall we evaluated 98 kneess of patients. Experimental results demonstrate an accuracy of the system of up to 100% for detection of both left and right knee and for junction space detection an accuracy 84.38% for the right knee and 85.42% for the left. The second experiment using gabor filter with parameter α=8, θ=0, Ψ=[0 Π/2], γ=0,8 and N=8 and row sum graph give an accuracy 92.63% for the right knee and 87.37% for the left. And the average time needs to process is 65.79 second. For obvious reasons we chose the results of the fourth to segment junction area in both right and the left knee.

New Algorithm for the Smoothing Speed Control of Induction Motor in Electric Car based on Self-Tuning Parameter PID-Fuzzy Logic

IPTEK The Journal for Technology and Science Vol 23, No 2 (2012)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Original Source | Check in Google Scholar

Abstract

Driving system of electric car for low speed has a performance of controller that is not easily set up on large span so it does not give a comfort to passengers. The study has been tested in the bumpy road conditions, by providing disturbances in the motor load, it is to describe the condition of the road. To improve the system performance, the speed and torque controller was applied using Field Oriented Control (FOC) method. In this method, On-Line Proportional Integral Derivative Fuzzy Logic Controller (PID-FLC) is used to give dynamic response to the change of speed and maximum torque on the electric car and this results the smooth movement on every change of car performance both in fast and slow movement when breaking action is taken. Optimization of membership functions in Fuzzy PID controller is required to obtain a new PID parameter values which is done in autotuning in any changes of the input or disturbance. PID parameter tuning in this case using the Ziegler-Nichols method based on frequency response. The mechanism is done by adjusting the PID parameters and the strengthening of the system output. The test results show that the controller Fuzzy Self-Tuning PID appropriate for Electric cars because they have a good response about 0.85% overshoot at to changes in speed and braking of electric cars.

Performance Fuzzy Logic Control to Minimize Output Voltage Ripple and Balanced Current Distribution of DC-DC Converters in Parallel Non-Identical

IPTEK The Journal for Technology and Science Vol 21, No 1 (2010)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Original Source | Check in Google Scholar

Abstract

Analysis of DC-DC converters are arranged in parallel with the inductor parameters which are different from what discussed in this paper. Buck DC-DC converter using non-identical model, that is different in the value of inductance which is L1 ≠ L2 ≠ L3. Research techniques are taken from the difference of current flows of each converter i.e. I1-I2 and I1- I3 and the reference current is I1. This current difference results are used as input controller. PID and Fuzzy Inference System with 5 gbell membership function are used as a controller. The results of this study indicate a significant system performance. Output voltage ripple is 10 mV with the total output current is 63.7 Ampere. Each DC-DC converter provides a current of contribution to the load 21.28 Ampere. The difference of the current distribution of each converter module range is 1mA - 4mA RMS (Root Mean Square) using PID control, while using Fuzzy Logic Control for differences in the distribution of current is 0.1 mA RMS and the output voltage is 48 volt. Fuzzy Logic Control performance has shown an improvement of control systems to reduce the output voltage ripple and the ability to share load current equally into each DC-DC converter.

Cyst and Tumor Lesion Segmentation on Dental Panoramic Images using Active Contour Models

IPTEK The Journal for Technology and Science Vol 22, No 3 (2011)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Original Source | Check in Google Scholar

Abstract

Active contours, or snakes, are computer-generated curves that move within images to find object boundaries. They are often used in computer vision and image analysis to detect and locate objects, and to describe their shape. Thus active contour can be used for object segmentation, especially the lesion in medical images. This paper presents the application of active contour models (Snakes) for the segmentation of lesions in dental panoramic image. The aim is to assist the clinical expert in locating potentially cyst or tumor cases for further analysis (e.g. classification of cyst or tumor lesion). In order to apply the snake formulation, color images were converted into gray images. Then, with correct parameters, we can create a snake that is attracted to edges or termination. Initializing contour, choosing parameter value and number of iteration affect the behaviour of the snake in a particular way. Using Receiver Pperating Characteristic (ROC), an average accuracy rate of 99.67 % is obtained. Examples of Snake segmentation results of lesions are presented.

Co-Authors -, Hindarto Adhi Dharma Wibawa, Adhi Dharma Adi Soeprijanto Agung Mega Iswara Agus Dharma Al Kindhi, Berlian Alamsyah Alamsyah Ardyono Priyadi Arham Arham, Arham Arif Muntasa Arifin Arifin Aryo Nugroho Atris Suyantohadi Bambang Suprianto Budi Setiyono Chastine Fatichah Dedid Cahya Happyanto Dian Retno Sawitri Diana Purwitasari Eka Dwi Nurcahya, Eka Dwi Eko Mulyanto Yuniarno Eko Setijadi Endang Setyati, Endang Evi Septiana Pane, Evi Septiana Fanani, Nurul Zainal Gunawan Gunawan Herlambang, Yodik Iwan Hidayatillah, Rumaisah I Ketut Eddy Purnama I Made Gede Sunarya I Made Ginarsa Ima Kurniastuti, Ima Imam Robandi Ingrid Nurtanio Iwan Setiawan Jamlaay, Marselin Joan Santoso Ketut Edi Purnama Khamid Khamid Kristian, Yosi Lie Jasa Lilik Anifah Margareta Rinastiti, Margareta Moch Hariadi Moch. Hariadi Mochamad Ashari Mochamad Hariadi Mochammad Facta Mochammad Hariadi Moh. Aries Syufagi Mohammad Arie Reza, Mohammad Arie Muhammad Ashari Muhammad Rivai Nasuha, Aris Nugroho, Supeno Mardi S. Nurul fadillah, Nurul Priambodo, Joko Prima Kristalina Purwadi Agus Darwito Putra, Darma Setiawan R Dimas Adityo Radi Radi Ratna Ika Putri Ratna Ika Putri, Ratna Rima Tri Wahyuningrum Rokhana, Rika Rumaksari, Atyanta. N. Ruri Suko Basuki, Ruri Suko Rusmono Yulianto Setiawan, Esther Irawati Siti Rochimah Soebagio Soebagio Soetiono, Agung Dewa Bagus Sooai, Adri Gabriel Surya Sumpeno Sutanto, Effendy Hadi Tita Karlita Tri Arief Sardjono Umi Laili Yuhana Wiratmoko Yuwono Yulianto Tejo Putranto, Yulianto Tejo Yuniarno, Eko M. Zakaria, Alamsyah Zaman, Lukman