International Journal of Electrical and Computer Engineering
International Journal of Electrical and Computer Engineering (IJECE, ISSN: 2088-8708, a SCOPUS indexed Journal, SNIP: 1.001; SJR: 0.296; CiteScore: 0.99; SJR & CiteScore Q2 on both of the Electrical & Electronics Engineering, and Computer Science) is the official publication of the Institute of Advanced Engineering and Science (IAES). The journal is open to submission from scholars and experts in the wide areas of electrical, electronics, instrumentation, control, telecommunication and computer engineering from the global world.
Articles
90 Documents
Search results for
, issue
"Vol 6, No 6: December 2016"
:
90 Documents
clear
Software Reliability Using SPRT: Burr Type III Process Model
CH. Smitha;
R. Satya Prasad;
R. Kiran Kumar
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (703.738 KB)
|
DOI: 10.11591/ijece.v6i6.pp3060-3067
Increased dependence on software systems elicited the assessment of their reliability, a crucial task in software development. Effective tools and mechanisms are required to facilitate the assessment of software reliability. Classical approaches like hypothesis testing are significantly time consuming as the conclusion can only be drawn after collecting huge amounts of data. Statistical method such as Sequential Analysis can be applied to arrive at a decision quickly. This paper implemented Sequential Probability Ratio Test (SPRT) for Burr Type III model based on time domain data. For this, parameters were estimated using Maximum Likelihood Estimation to apply SPRT on five real time software failure datasets borrowed from different software projects. The results exemplify that the adopted model has given a rejection decision for the used datasets.
Performance Forecasting of Share Market using Machine Learning Techniques: A Review
Sachin Kamley;
Shailesh Jaloree;
R.S. Thakur
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (541.571 KB)
|
DOI: 10.11591/ijece.v6i6.pp3196-3204
Forecasting share performance becomes more challenging issue due to the enormous amount of valuable trading data stored in the stock database. Currently, existing forecasting methods are insufficient to analyze the share performance accurately. There are two main reasons for that: First, the study of existing forecasting methods is still insufficient to identify the most suitable methods for share price prediction. Second, the lack of investigations made on the factors affecting the share performance. In this regard, this study presents a systematic review of the last fifteen years on various machine learning techniques in order to analyze share performance accurately. The only objective of this study is to provide an overview of the machine learning techniques that have been used to forecast share performance. This paper also highlights a how the prediction algorithms can be used to identify the most important variables in a share market dataset. Finally, we could have succeeded to analyze share performance effectively. It could bring benefits and impacts to researchers, society, brokers and financial analysts.
Time Independent Signature Verification using Normalized Weighted Coefficients
Manas Singhal;
Manish Trikha;
Maitreyee Dutta
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (481.164 KB)
|
DOI: 10.11591/ijece.v6i6.pp2658-2664
Signature verification is one of the most widely accepted verification methods in use. The application of handwritten signatures includes the banker’s checks, the credit and debit cards issued by banks and various legal documents. The time factor plays an important role in the framing of signature of an individual person. Signatures can be classified as: offline signature verification and online signature verification. In this paper a time independent signature verification using normalized weighted coefficients is presented. If the signature defining parameters are updated regularly according to the weighted coefficients, then the performance of the system can be increased to a significant level. Results show that by taking normalized weighted coefficients the performance parameters, FAR and FRR, can be improved significantly.
The Contour Extraction of Cup in Fundus Images for Glaucoma Detection
Anindita Septiarini;
Hamdani Hamdani;
Dyna Marisa Khairina
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (880.959 KB)
|
DOI: 10.11591/ijece.v6i6.pp2797-2804
Glaucoma is the second leading cause of blindness in the world; therefore the detection of glaucoma is required. The detection of glaucoma is used to distinguish whether a patient's eye is normal or glaucoma. An expert observed the structure of the retina using fundus image to detect glaucoma. In this research, we propose feature extraction method based on cup area contour using fundus images to detect glaucoma. Our proposed method has been evaluated on 44 fundus images consisting of 23 normal and 21 glaucoma. The data is divided into two parts: firstly, used to the learning phase and secondly, used to the testing phase. In order to identify the fundus images including the class of normal or glaucoma, we applied Support Vector Machines (SVM) method. The performance of our method achieves the accuracy of 94.44%.
Trends In Task Allocation For Multicore System
Arun Kumar Sundar Rajan;
Shriram K Vasudevan;
Nirmala Devi M
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (876.375 KB)
|
DOI: 10.11591/ijece.v6i6.pp3018-3030
As the functionality in real-time embedded systems becoming complex, there has been a demand for higher computation capability, exploitation of parallelism and effective usage of the resources. Further, technological limitations in uniprocessor in terms of power consumption, instruction level parallelism reaching saturation, delay in access of memory blocks; directed towards emergence of multicore. Multicore design has its challenges as well. Increase in number cores has raised the demand for proper load distribution, parallelizing existing sequential codes, enabling effective communication and synchronization between cores, memory and I/O devices. This paper brings out the demand for effective load distribution with analyzes and discussion about the various task allocation techniques and algorithms associated with decentralized task scheduling technique for multicore systems. This paper also addresses on the multithreaded architecture, where parallel tasks are formulated from sequential code blocks and finally on the techniques to parallelize the sequential code block.
Collaboration Management System between the Device based on Machine Socialization
Han Kyung Kim;
In Shik Kang;
Wung Jun Kim;
Hoe Kyung Jung
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (596.929 KB)
|
DOI: 10.11591/ijece.v6i6.pp3148-3153
The basis of IoT is in the interconnection and communication between different devices to achieve common goals through internet. These devices are interconnected through a network which enables communication within these devices without any direct human intervention. But with such great potential, this technology reached a road-block due to incompatibility within various manufacturers of the same type of device and proprietary standards. I started this project with this problem in mind and I have created a brand and platform independent machine socialization device manager system. In this paper, to overcome the above mentioned problem, I have utilized micro controllers to connect to various existing device to solve the problem and propose a device to device communication with collaboration management. This technology is not restricted to usage in only the new network module enabled smart devices but also this can be used to operate the existing old (not smart) home appliances. Machine socialization was made possible with the use of XML, (an internet standard schema language) which we have used to gather device, task and relationship information of all the devices to show schema information.
Simulation and Performance Evaluation of Shunt Hybrid Power Filter for Power Quality Improvement Using PQ Theory
R. Balasubramanian;
S. Palani
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (589.936 KB)
|
DOI: 10.11591/ijece.v6i6.pp2603-2609
This work proposes the design of shunt hybrid filter using instantaneous power theory to improve the power quality and simulation has been carried out for 3 phase distribution system feeding different types of non linear loads. The proposed filter consists of parallel combination of 5th and 7th tuned selective harmonic elimination passive filters, which is connected in series with a small rating IGBTs based voltage source inverter. In this work, principle of compensation and filtering behavior of the system has been discussed in detail. Instantaneous real and reactive power theory based controller has been designed to estimate the reference current from the distorted current. In order to reduce the harmonics, generated reference currents are tracked by voltage source inverter using hysteresis band current controller. The performance of the hybrid scheme is evaluated for various nonlinear loads using Matlab/ Simulink tool. The detailed analysis has been carried out on harmonics reduction and DC bus voltage regulation and the simulation result ensures the feasibility of suggested control strategy. The proposed topology improves the filtering performance of the passive filter in hybrid scheme.
Real Time Weed Detection using a Boosted Cascade of Simple Features
Adil Tannouche;
Khalid Sbai;
Miloud Rahmoune;
Rachid Agounoun;
Abdelhai Rahmani;
Abdelali Rahmani
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (752.381 KB)
|
DOI: 10.11591/ijece.v6i6.pp2755-2765
Weed detection is a crucial issue in precision agriculture. In computer vision, variety of techniques are developed to detect, identify and locate weeds in different cultures. In this article, we present a real-time new weed detection method, through an embedded monocular vision. Our approach is based on the use of a cascade of discriminative classifiers formed by the Haar-like features. The quality of the results determines the validity of our approach, and opens the way to new horizons in weed detection.
Enhancing the Accuracy of Mobile Geo Targeting
Dmitry Sergeevich Silnov
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (398.11 KB)
|
DOI: 10.11591/ijece.v6i6.pp2887-2890
SMS advertising companies use mobile phone numbers to send its own content. Geo targeting can improve advertising possibilities. New approach of mobile numbers geo targeting discovered and used in Russia. That approach can be used not only in Russia, but its universal for any country. For Russian geo targeting used site avito.ru for attaching mobile to selected area in city.
Finding the Optimal Value for Threshold Cryptography on Cloud Computing
Weena Janratchakool;
Sirapat Boonkrong;
Sucha Smanchat
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (789.655 KB)
|
DOI: 10.11591/ijece.v6i6.pp2979-2988
The objective of using threshold cryptography on cloud environment is to protect the keys, which are the most important elements in cryptographic systems. Threshold cryptography works by dividing the private key to a number of shares, according to the number of virtual machines, then distributing them each share to each virtual machine. In order to generate the key back, not all the shares are needed. Howerver, the problem is that there has been no research attemping to find a suitable threshold value for key reconstruction. Therefore, this paper presented a guildline designed and implemented that can assist to choose such value. The experiment was setup using CloudSim to simulate cloud environment and collecting time taken in key distribution and key reconstruction process to achieve the optimal threshold value.