Articles
65 Documents
Search results for
, issue
"Vol 17, No 1: January 2020"
:
65 Documents
clear
Electrocardiogram profiling of myocardial infarction history using MLP and HMLP networks
Fatin Syahirah Ab Gani;
Mohd Khairi Nordin;
Ahmad Ihsan Mohd Yassin;
Idnin Pasya Ibrahim;
Megat Syahirul Amin Megat Ali
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 1: January 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i1.pp183-190
Narrowing of coronary arteries caused by cholesterol deposits deprives heart tissues of oxygen. In prolonged conditions, these will result in myocardium infarction. The presence of damage tissues modifies the normal sinus rhythm and this can be detected using electrocardiogram (ECG). Hence, this paper characterized history of myocardial infarction from survivors using QRS power ratio features from the ECG. Subsequent profiling is performed using multilayered perceptron (MLP) and hybrid multilayered perceptron (HMLP) networks. ECG with history of anterior and inferior infarctions, along with healthy controls is obtained from PTB Diagnostic ECG Database. The signal is initially pre-processed and the power ratio features are extracted for low- and mid-frequency components. The features are then used as input vector to the MLP and HMLP networks. The optimized MLP has attained accuracies of 99.2% for training and 98.0% for testing. Meanwhile, the optimized HMLP managed to achieve accuracies of 99.4% for training and 97.8% for testing. Despite the similarities in network performance, MLP provides a better alternative due to the reduced computational requirements by as much as 30%.
Generating images of partial face using landmark based k-nearest neighbor
Israa Hadi;
Alyaa Mahdi
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 1: January 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i1.pp420-428
One of the most common approaches to address the partial face recognition challenge is to crop the full face image into segments. The problem is how the full face image must be cropped in a uniform way to generate informative segments. The un-blindly strategy was applied in this paper to generate informative segments, it depends on localizing the facial landmarks and selecting the more informative facial points as a key points, as more as the k-nearest neighbor concept was explored to select the k nearest landmark points to the key points. Two landmark localization techniques were experimented, the suitable technique resulted in segments which are overlapped due to the supervised clustering technique that explored in this paper to cover important biometric face regions, not repeated and covered most probabilities in which it is possible to distinguish the query face from the available part of it.
Voltage disturbance mitigation in Iraq's low voltage distribution system
Jamal Abdul-Kareem Mohammed;
Arkan Ahmed Hussein;
sahar R. Al-Sakini
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 1: January 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i1.pp47-60
Power distribution network in Iraq still suffers from significant problems regarding electricity distribution level. The most important problem is the disturbances that are occurring on lines voltages, which in turn, will negatively affect sensitive loads they feed on. Protection of these loads could be achieved efficiently and economically using the dynamic voltage restorer DVR when installed between the voltage source and load to inject required compensation voltage to the network during the disturbances period. The DVR mitigates these disturbances via restoring the load voltage to a pre-fault value within a few milliseconds. To control the DVR work, dq0 transformation concept and PID method with sinusoidal pulse-width modulation SPWM based converter had been used to correct the disturbances and thus enhance the power quality of the distribution network. The DVR performance was tested by MATLAB/Simulink with all kinds of expected voltage disturbances and results investigated the effectiveness of the proposed method.
Smart insects repeller
Suzi Seroja Sarnin;
Nur Jumaatul Hidayati Binti Mohammad;
Nani Fadzlina Naim;
Norsuzila Ya’acob;
Azlina Idris;
Wan Norsyafizan Wan Mohamad;
Mohd Nor Md Tan
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 1: January 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i1.pp205-212
One of the key issues for those involved in farming and greenhouse is the use of pesticides. In a recent headline, there has been an epidemic of insect infestation that has destroyed 211 hectares of rice plants. These concerns have led to the discussion of possible over-use of pesticides that are not just killing dangerous pests, but also other animals that help combat the pest. In order to overcome the problem, a research was conducted by introducing a smart insect killer. In this developing project, Pyroelectric (PIR) sensor will be using as a motion detector towards insects. This sensor plays a role to transmit the signal for action in taking care of the plant. The IR sensors will install around the plant, so that it has good range to detect any motion. As a result, suitable chemical spray will trigger to repel these insects. A light emitting diode as an indicator of functional to the system. "Smart Insect Repeller" will work when certain pests are detected and this will reduce the use of poisons and the quality of the crop will be preserved due to the use of minimal poisons.
Fault isolation technique for decentralized survivable communication network systems via regions and paths
Nethravathi B;
Kamalesh V N
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 1: January 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i1.pp533-542
The rapid continuous growth of communication networks in size, complexity and dependencies, makes them extremely challenging to maintain the survivability of the complete large network. The complexity may be due to advance voice and video services like IP TVs, IP telephony, video streaming which demands high reliability and survivability. Network management has become a great challenge as Faults are expected only in these complex networks. Once a failure is detected, the next step in the diagnosis is fault isolation which locates the source of that failure. The necessitate of decentralized diagnosis is justified by various applications, like spacecrafts. This article presents model based fault isolation technique using a graph theoretical concepts, regions and paths for decentralized communication networks.
Electromagnetic radiation of human body before and after intense exercise
R.S.S.A. Kadir;
Zunairah Hj Murat;
Nizaar Suhairy Bin Johari
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 1: January 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i1.pp141-147
This paper investigates the electromagnetic radiation (EMR) of the human body before and after intense exercise. The intensity of exercise refers to the rate or the effort at which the activity is being performed. 30 healthy students participated in this research. The data were collected at the specific point of the human body by using a frequency detector. The reading of the frequency was taken 5 times at each point at the same location; hence, the average value is calculated for data analysis. This frequency measurement is recorded two times which is before and after intense exercise with a consistence protocol for all participants. The collected data is analyzed by using MATLAB programming tool which converts the data frequency into 15 colours of bio-energies which symbolizes different energy field score. The score represents the health level of the samples at specific point. From the analysis, higher frequency of EMR is detected after intense exercise compared to before intense exercise. There is also a significant change in the physical health score categories. This indicates that the intense exercise influences the body EMR radiation frequencies.
Effect of increasing the network capacity using device-to-device technology for next generation networks
Aws Zuheer Yonis
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 1: January 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i1.pp303-309
Device-to-device (D2D) communication is one of the key technologies in the fifth generation of wireless communication systems, which is defined as direct communication between two mobile users without traversing the base station D2D communication plays an increasingly important role and which improves communication capability and reduces communication delay and power consumption. D2D communication that enables direct communication between nearby mobiles is an exciting and innovative feature of next-generation cellular networks. In order to meet the rising subscriber demands and provide them satisfactory services, D2D communication is being looked upon as an emerging technology of the next generation networks.
Design and development of activity attendance monitoring system based on RFID
Ray Adderley Jm Gining;
S.S.M. Fauzi;
I.M. Ayub;
M.N.F. Jamaluddin;
Ira Puspitasari;
Okfalisa Okfalisa
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 1: January 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i1.pp500-507
Attending activities organized by the university or institution is one of the important criteria that must be fulfilled by students for multiple purposes. Whether it is by attending classes, or any other activities, the main concern is focused on the process of recording students’ attendance. The use of a paper-based manual system to record students’ attendance is still being widely used due to the lack of an e-management system. These approaches have a lot of disadvantages due to the nature of the paper which is a fragile material - also an expensive cost to procure and produce. This paper, relying on Radio Frequency Identification (RFID), designed and developed an electronic system known as Activity Attendance Monitoring System (AAMS) that utilizes readily available resource – student card, as the student identification when attending an activity. Results from the validation, execution and continuous test suggest that AAMS can be effectively implemented to monitor and record student’s attendance. The main contribution of the study is the design and development model that capable of monitoring students’ activity attendance in university activities context. Developers and researcher in the area can adopt the proposed design and development model in formulating a similar system in managing activity attendance.
Artificial neural network based technique for energy management prediction
N. Ab. Wahab;
Z. Mat Yasin;
N. A. Salim;
N. F. A. Aziz
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 1: January 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i1.pp94-101
The energy management of electrical machine is significant to ensure efficient power consumption. Mismanagement of energy consumption could give impact on low efficiency of energy consumption that leads to power wastage. This paper presents analysis of power consumption and electricity costing of the electrical machineries and equipment in High Voltage (HV) and Electrical Machine (EM) Laboratories at Faculty of Electrical Engineering (FKE), Universiti Teknologi MARA (UiTM) Shah Alam, Selangor, Malaysia. The electrical data are collected using Fluke Meter 1750. Based on the analysis, it is found that the estimated annually electricity cost for HV Laboratory and EM Laboratory are RM 392.00 and RM 3197.76 respectively. For prediction of energy consumption of the two laboratories, Artificial Neural Network (ANN) algorithm is applied as computational tool using feedforward network type. The results show that the ANN is successfully modelled to predict the energy consumption.
Hydraulically operated palm oil loader system design as fresh fruit bunch collector
S. Sarip;
M. A. Suhot;
H. M. Kaidi;
M. F. Mohd Noor;
S. Abdul Aziz;
N. A. Bani;
M. S. Noorazizi
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 1: January 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i1.pp228-236
Palm oil is one of the main agricultural contributors to Malaysia’s Gross Domestic Product (GDP). Although commercial palm oil plantations have flourished in Malaysia for decades, there is still room for improvement especially in minimizing manpower load and developing efficient machinery to improve the various processes involved in the palm oil industry from estate to the mills. This paper presents a modified towable backhoe to assist in the Fresh Fruit Bunch (FFB) collecting process as an effort to save time. The main objective of this study is to design a machine that can be used by smallholders of oil palm in order to help speed up the work process. With a boom extension and an innovative grabber, the pressure needed to operate the hydraulic system was analyzed to ensure the towable backhoe functioned effectively and fulfilled its objectives. From the calculations done, the maximum pressure that the system can supply is 31.28 MPa which is higher than the 11 MPa minimum required for the hydraulic system to operate.