Articles
9,226 Documents
Ensemble deep learning for tuberculosis detection
Mohd Hanafi Ahmad Hijazi;
Leong Qi Yang;
Rayner Alfred;
Hairulnizam Mahdin;
Razali Yaakob
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 2: February 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i2.pp1014-1020
Tuberculosis (TB) is one of the deadliest infectious disease in the world. TB is caused by a type of tubercle bacillus called Mycobacterium Tuberculosis. Early detection of TB is pivotal to decrease the morbidity and mortality. TB is diagnosed by using the chest x-ray and a sputum test. Challenges for radiologists are to avoid confused and misdiagnose TB and lung cancer because they mimic each other. Semi-automated TB detection using machine learning found in the literature requires identification of objects of interest. The similarity of tissues, veins and small nodules presenting the image at the initial stage may hamper the detection. In this paper, an approach to detect TB, that does not require segmentation of objects of interest, based on ensemble deep learning, is presented. Evaluation on publicly available datasets show that the proposed approach produced a model that recorded the best accuracy, sensitivity and specificity of 91.0%, 89.6% and 90.7% respectively.
Transient Stability Analysis of Grid-connected Wind Turbines with Time Domain Simulation
Hongwei Li;
Haiying Dong;
Shuaibing Li;
Linxin Cao
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
With an ever-increasing pentration of wind power into power system, the influence to overall system behavior and stability becomes obviously. Therefore, it is so necessary to require wind turbines have good grid adaptability. This paper investigates the effect ofdirectly grid-connectedfront-end speed controlled wind turbines (FSCWT) on transient stability of power system.For this purpose, a voltage based synchronous generator model is used and the drive train model with WinDriver is built. By using a fast excitation control of FSCWT exciter, the FSCWT wind turbines can successfully ride through grid fault and have no problem of angular stability when connected to grid. Simulation studies are carried out to demonstrate and compare the transient performance of the IEEE 5-machine 14-bus system with FSCWT replace by double fed induction generators (DFIG) during a three phase fault. Results show that a better transient stability performance is achieved with an intergration of FSCWT in comparsion with DFIG, which can even bring some benefits on power system transient performance and stability.DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3331
Simulation and Implementation of Multiple Unipolar Stepper Motor Position Control in the Three Stepping Modes using Microcontroller
Ayman Y. Yousef;
M. H. Mostafa
Indonesian Journal of Electrical Engineering and Computer Science Vol 4, No 1: October 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v4.i1.pp29-40
This paper presents a multiple unipolar stepper motor position control system using microcontroller (MCU) in anticlockwise and clockwise directions. The open loop controller of the implemented position control system for the three stepping modes of operation has been designed and developed with three stepper motors and without position feedback. The MCU is programmed using flowcode software package to generate the pulse signals with the desired stepping sequences and step angles. These pulse signals are necessary to drive the three stepper motors in the three drive modes (wave-step, full-step, and Half-step) according to the control algorithm. Three devices of 8 Channel Darlington Driver (chip ULN2803) are used to drive the three stepper motors and provide them with the sufficient current. The position control system has been simulated using proteus design suite software package and the controller has been implemented using low cost PIC16F877A (MCU). A reliable and accurate position control of the stepper motor is achieved by this position control system.
Security Authentication for Student Cards’ Biometric Recognition Using Viola-Jones Algorithm
S. Ibrahim;
K.R. Jamaluddin;
K.A.F.A. Samah
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 1: July 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i1.pp241-247
The unauthorized access to the university entrance could be gained by only flashing a student card. This unsecure situation shows the loophole of security authentication in a university. In order to overcome this, a biometric recognition could be the most suitable candidate as it varies uniquely from one person to another. A study on student cards’ biometric recognition using Viola-Jones algorithm is presented as it is proven as a powerful algorithm in terms of superb detection rates and speed. It is done by comparing the facial structures and features between the student card’s image and the card holder image, thus determining the similarity. The recognition performance is evaluated based on the percentage of similarity using 100 testing images of 50 students. The observation on results obtained the effectiveness of the Viola-Jones features in student cards’ biometric recognition rate.
PV system reactive power coordination with ULTC & shunt capacitors using grey wolf optimizer algorithm
Mogaligunta Sankaraiah;
S Suresh Reddy;
M Vijaya Kumar
Indonesian Journal of Electrical Engineering and Computer Science Vol 19, No 1: July 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v19.i1.pp1-10
The presence of PV systems increases rapidly in distribution systems to improve reliability and quality of supply. This will influence the performance of under load tap changing (ULTC) transformer and related reactive power devices. Therefore, many researchers are working on this area. This paper main objective is to reduce switching operations of reactive power devices (ULTC and Shunt capacitors) together with system power loss. Distribution system load and solar system power will predict one day in advance and grey wolf optimizer (GWO) algorithm proposed to solve the objective function. Reactive power of solar system is coordinated together with ULTC and shunt capacitors (SCs) with the aid of forecasted load. Distribution system losses and switching operations of ULTC and SCs converted into objective function in terms of cost. The proposed method is applied on practical 10KV system and the results are compared with conventional and particle swarm optimization (PSO) methods considering grid conditions.
Joint Optimization of Sensing Time and Fusion Rules for Cognitive Radios
Yang Liu;
Ying Cui;
Ou Li
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 4: April 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
In Cognitive Radios, sensing-time and fusion rules affect the performance of spectrum sensing when cooperative sensing is applied. Besides, the more unlicensed users are involved in cooperative sensing, the higher spectrum utilization the channel can achieve, while from the unlicensed users’ perspective, the lower average throughput the unlicensed users can obtain. In this paper, we explore the issue on the sensing-time and the fusion rules to optimize the average throughput of the unlicensed users under the constraint that the licensed users are sufficiently protected. At first, we formulate this issue as an optimization problem, and showed the unimodal characteristics of the unlicensed users’ average throughput as a function of the sensing-time and the fusion parameter. Then a numerical optimization algorithm is proposed to obtain the optimal solution. At last, by theoretical analysis and performance comparisons we derived the optimal fusion rule selection scheme under different scenarios. Computer simulations show that significant improvement in the average throughput of unlicensed users is achieved when the sensing-time and the fusion rule are jointly optimized. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4793
Flight-Path Tracking Control of an Aircraft Using Backstepping Controller
Labane Chrif;
Zemalache Meguenni Kada;
Tahar Mohamed
Indonesian Journal of Electrical Engineering and Computer Science Vol 15, No 2: August 2015
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v15.i2.pp270-276
For transportation aircraft, the primary control objective for an autopilot system engaged during approach and landing is relative to the flight path tracking on the basis of highly simplified linear models of flight dynamics. The dynamics governing the flight path of an aircraft are in general highly nonlinear and involve complex physics for which no accurate models are available. In this paper a nonlinear model describing the longitudinal equations of motion in strick feedback form is derived. Backstepping is utilized for the construction of a globally stabilizing controller with a number of free parameters. It is implemented a controller with an internal loop controls involving the pitch rate of the aircraft and an external loop which includes angle of attack, path angle and pitch angle. Finally, nonlinear simulation results for a longitudinal model of a transportation aircraft are displayed and discussed.
Research on Nuclear Channel Head CAD System
Tian Chen;
Zhonghai Yu
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 8: December 2012
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
To enable the designers to design and modify model of nuclear channel head quickly and easily, we constructed the CAD system of the nuclear channel head. At first, we analyzed the geometric characteristics of nuclear channel, established of feature control parameter set and the parametric model of nuclear channel head. Secondly, other parameters related to the solid modeling are described through the parameter control set. Thus, the feature solid modeling of head shell surface, nozzle and boss are programmed. Finally, it is proved that the method and development strategy of parametric CAD system is effective by using automatic design example of nuclear channel head which is developed through CAD system of nuclear channel head. DOI: http://dx.doi.org/10.11591/telkomnika.v10i8.1689
An Architecture to Implement Event-Driven Web Monitoring Systems
Gao Ying;
Mu Lei;
Hao Zhonghu;
Zheng Weiyang
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Traditional monitoring systems are based on C/S mode because desktop software still has inherent advantages though desktop software is replaced by web applications rapidly in many fields. Meanwhile, traditional monitoring systems use relational database as data source, however, relational database lacks the ability to process influx of queries per second. In this paper, we will do an in-depth research to design an architecture to implement event-driven web monitoring systems. DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.3466
Spatial distribution pattern of Tarsius Lariang in lore lindu national park
Abdul Rosyid;
Yanto Santosa;
I Nengah Surati Jaya;
M. Bismark;
Agus P. Kartono
Indonesian Journal of Electrical Engineering and Computer Science Vol 13, No 2: February 2019
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v13.i2.pp606-614
Tarsius lariang (T. lariang) is an endemic species in Lore Lindu National Park (LLNP). Available information regarding T. lariang is limited to only morphological, anatomical, cytogenetic, and voices issues. Knowledge for its geospatial characteristics such as spatial preferences and spatial distribution is rare. The main objective of this study is to identify the spatial distribution pattern of T. lariang in LLNP. An additional objective is to identify the environmental factors affecting its spatial distribution patterns. Field observation for distribution pattern was done at the observation plot that were using systematic sampling with random start. Furthermore, the density estimation in each point was calculated using Triangle Count and Concentration Count method, while insect abundance was estimated using light traps sample data. Finally, spatial pattern was estimated using nearest neighbor index, while the environmental affecting factors were identified by using spatial analysis and correlation analyses. From 45 observation points, the T. lariang distribution pattern was clumped. It is also recognized that the significant factors affecting the spatial distribution were insect abundance, proximity from the commercially utilized land, and land surface temperature.