Articles
52 Documents
Search results for
, issue
"Vol 11, No 3: September 2018"
:
52 Documents
clear
Enhancing Similarity Distances Using Mandatory and Optional for Early Fault Detection
Safwan Abd Razak;
Mohd Adham Isa;
Dayang N.A Jawawi
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i3.pp1194-1203
Software Product Line (SPL) describes procedures, techniques, and tools in software engineering by using a common method of production for producing a group of software systems that identical from a shared set of software assets. In SPL, the similarity-based prioritization can resemble combinatorial interaction testing in scalable and efficient way by choosing and prioritize configurations that most dissimilar. However, the similarity distances in SPL still not so much cover the basic detail of feature models which are the notations. Plus, the configurations always have been prioritized based on domain knowledge but not much attention has been paid to feature model notations. In this paper, we proposed the usage of mandatory and optional notations for similarity distances. The objective is to improve the average percentage of faults detected (APFD). We investigate four different distances and make modifications on the distances to increase APFD value. These modifications are the inclusion of mandatory and optional notations with the similarity distances. The results are the APFD values for all the similarity distances including the original and modified similarity distances. Overall, the results shown that by subtracting the optional notation value can increase the APFD by 3.71% from the original similarity distance.
Study of Load Optimization and Performance Issues in Cloud
Madhina D Banu;
Aranganathan Aranganathan
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i3.pp1035-1041
“Nowadays, cloud computing is the latest computing platform which is feasible to the user for computation and unlimited storage and data transmission with minimal cost and time in a cloud environment during the internet. The load balancing is important criteria of cloud environment that avoid same nodes overloaded and others are idle. Ultimately load balancing can enhance the QoS parameters including make span, cost and resource utilization. To optimize the load, the existing load optimization approach is properly utilized federation mechanisms, which offers physical resources based on demand to maintain the cloud application efficiency. However, the technique failed to optimize load where part of the servers suffering from heavy load after an execution of the application. In the current scenario, several systems are facing same kinds of problem which is the biggest cause to increase the virtual machine (VM) cost. Current systems still have a time delay, request-response process error from data center side in cloud environments. To overcome these issues, the research study studies all related technique for cloud performance optimization and load balancing issues. The main framework objective is to offer an effective solution to store/search/transmit/ data with minimal cost and time without compromising the QoS constraints. The study represents different policies and cloud-specific strategies to enhance the performance of cloud application with minimal cost and time. The research study is also planning to find out an effective solution for traffic, data congestion and media streaming issues in a cloud environment.
Matchmaking Problems in MOBA Games
Muhammad Farrel Pramono;
Kevin Renalda;
Dedy Prasetya Kristiadi;
Harco Leslie Hendric Spits Warnars;
Worapan Kusakunniran
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i3.pp908-917
MOBA is a popular genre that requires teamwork to achieve victory. A close and tight match is what make MOBA fun to play and increase its user satisfaction, but some factor may ruin the matchmaking and create unbalanced match between the two team. Those problems factors are high latency, players with bad attitude, and players doing unfamiliar role. We use DOTA 2 as our case study. Then we compare the DOTA 2 matchmaking system in other sector to make comparison. Lastly, we discuss about solution to solve MOBA matchmaking problem such as displaying live information about online players, players searching for games, servers online and ETA for gaming to start. In addition, we proposed new variable to be considered in the matchmaking system, which are Preferences Role, player’s chosen preferences role will be considered while the system set up the game to minimize the number of unbalanced games in MOBA.
Forecasting Drought Using Modified Empirical Wavelet Transform-ARIMA with Fuzzy C-Means Clustering
Muhammad Akram Shaari;
Ruhaidah Samsudin;
Ani Shabri Ilman
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i3.pp1152-1161
Drought forecasting is important in preparing for drought and its mitigation plan. This study focuses on the investigating the performance of Auto Regressive Integrated Moving Average (ARIMA) and Empirical Wavelet Transform (EWT)-ARIMA based on clustering analysis in forecasting drought using Standard Precipitation Index (SPI). Daily rainfall data from Arau, Perlis from 1956 to 2008 was used in this study. SPI data of 3, 6, 9, 12 and 24 months were then calculated using the rainfall data. EWT is employed to decompose the time series into several finite modes. The EWT is used to create Intrinsic Mode Functions (IMF) which are used to create ARIMA models. Fuzzy c-means clustering is used on the instantaneous frequency given by Hilbert Transform of the IMF to create several clusters. The objective of this study is to compare the effectiveness of the methods in accurately forecasting drought in Arau, Malaysia. It was found that the proposed model performed better compared to ARIMA and EWT-ARIMA.
Performance Improvement of MIMO-OSTBC System with BCH-TURBO Code In Rayleigh Fading Channel
SOFI Naima;
FATIMA Debbat;
Fethi Tarik Bendimerad
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i3.pp898-907
Recently, OSTBCs has become a widespread technique for signal transmission over wireless channels because of their diversity gain, but there are not designed to achieve an additional coding gain. Hence, OSTBCs must be concatenated with an external code which allows a significant coding gain.FEC (forward error correction) is a technique used for detecting and possibly correcting errors that can occur when messages are transmitted through a digital communication system, also for rendering the information more reliable. Thus, with staffing these coding techniques that are able to reach Shannon limits, in MIMO systems, better performances can be achieved by taking advantages of diversity and coding gains. The objective of this paper is to compare different FEC codes in Rayleigh fading channel and propose an appropriate code for MIMO-OSTBC systems. The simulation results reveal the performance of the proposed model
Survey On The Role Of IoT In Intelligent Transportation System
Varun Chand H;
Karthikeyan J
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i3.pp936-941
Precise and appropriate traffic related data allows travellers to choose suitable travelling modes, travelling paths, and departure time, which is crucial for the success of Intelligent Transportation System (ITS). With the growth of vehicles, the rate of pollution and consumption of fuel has increased, it also creates traffic congestions. For the recent years there has been a rapid growth in technology, which can be explored to solve traffic issues. However, depending upon the available technologies each countries ITS research area may be different. The objective of this literature review is to integrate ITS with internet of things and it also discusses the prospect of clustering, controller system, location identification and resource privacy in ITS.
A Novel Approach for Efficient Training of Deep Neural Networks
D.T.V. Dharmajee Rao;
K.V. Ramana
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i3.pp954-961
Deep Neural Network training algorithms consumes long training time, especially when the number of hidden layers and nodes is large. Matrix multiplication is the key operation carried out at every node of each layer for several hundreds of thousands of times during the training of Deep Neural Network. Blocking is a well-proven optimization technique to improve the performance of matrix multiplication. Blocked Matrix multiplication algorithms can easily be parallelized to accelerate the performance further. This paper proposes a novel approach of implementing Parallel Blocked Matrix multiplication algorithms to reduce the long training time. The proposed approach was implemented using a parallel programming model OpenMP with collapse() clause for the multiplication of input and weight matrices of Backpropagation and Boltzmann Machine Algorithms for training Deep Neural Network and tested on multi-core processor system. Experimental results showed that the proposed approach achieved approximately two times speedup than classic algorithms.
Automated Detection of Microaneurysmsusing Probabilistic Cascaded Neural Network
Jeyapriya J;
K S Umadevi;
R Jagadeesh Kannan
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i3.pp1083-1093
The diagnosing features for Diabetic Retinopathy (DR) comprises of features occurring in and around the regions of blood vessel zone which will result into exudes, hemorrhages, microaneurysms and generation of textures on the albumen region of eye balls. In this study we presenta probabilistic convolution neural network based algorithms, utilized for the extraction of such features from the retinal images of patient’s eyeballs. The classifications proficiency of various DR systems is tabulated and examined. The majority of the reported systems are profoundly advanced regarding the analyzed fundus images is catching up to the human ophthalmologist’s characterization capacities.
Homotopy Analysis Method for the First Order Fuzzy Volterra-Fredholm Integro-differential Equations
Ahmed A. Hamoud;
Kirtiwant P. Ghadle
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i3.pp857-867
A fuzzy Volterra-Fredholm integro-differential equation (FVFIDE) in a parametric case is converted to its related crisp case. We use homotopy analysis method to find the approximate solution of this system and hence obtain an approximation for the fuzzy solution of the FVFIDE. This paper discusses existence and uniqueness results and convergence of the proposed method.
An Efficient Approach to Detecting Missing Tags in RFID Data Stream
Nur’Aifaa Zainudin;
Hairulnizam Mahdin;
Deden Witarsyah;
Mokhairi Makhtar;
Mohd Izuan Hafez Ninggal;
Zirawani Baharum
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i3.pp1204-1213
RFID technology is a Radio frequency identification system that provides a reader reading the data item from its tag. Nowadays, RFID system has rapidly become more common in our life because of its autonomous advantages compared to the traditional barcode. It can detect hundreds of tagged items automatically at a time. However, in RFID, missing tag detection can occur due to signal collisions and interferences. It will cause the system to report incorrect tag’s count due to an incorrect number of tags being detected. The consequences of this problem can be enormous to business, as it will cause incorrect business decisions to be made. Thus, a Missing Tag Detection Algorithm (MTDA) is proposed to solve the missing tag detection problem. There are many other existing approaches has been proposed including Window Sub-range Transition Detection (WSTD), Efficient Missing-Tag Detection Protocol (EMD) and Multi-hashing based Missing Tag Identification (MMTI) protocol. The result from experiments shows that our proposed approach performs better than the other in terms of execution time and reliability.