Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

29,905 Article Results

Chaotic immune symbiotic organisms search for SVC installation in voltage security control

10.11591/ijeecs.v16.i2.pp623-630
Mohamad Khairuzzaman Mohamad Zamani , Ismail Musirin , Saiful Izwan Suliman , Muhammad Murtadha Othman
Parallel with the urbanization of the world, energy demand in the world also increased. The increase in energy demand will require a power system to be operated near its stability limit. To mitigate the problem, Flexible Alternating Current Transmission System (FACTS) devices can be installed as a compensation scheme to improve voltage security in a power system. For an effective compensation, FACTS devices should be optimally allocated in a power system. Although optimization techniques can be implemented to optimally allocate these devices, problems have been reported which would affect the performance of the optimization techniques in terms of producing high quality solutions. This paper presents the implementation of Chaotic Immune Symbiotic Organisms Search for solving optimal Static VAr Compensator (SVC) allocation problem for voltage security control. The optimization is validated in IEEE 26-Bus Reliability Test System (RTS) realizes the capability of CISOS in solving the optimization problem. Comparative studies with respect to Particle Swarm Optimization (PSO) and Evolutionary Programming (EP) resulting in good agreement on the results and demonstrated superior performance of CISOS. Results of the study can be beneficial to power system community in terms of compensation planning prior to real world implementation.
Volume: 16
Issue: 2
Page: 623-630
Publish at: 2019-11-01

Artificial neural network and partial least square in predicting blood hemoglobin using near-infrared spectrum

10.11591/ijeecs.v16.i2.pp701-708
Mohd Nazrul Effendy Mohd Idrus , Kim Seng Chia
Predictive models is crucial in near-infrared (NIR) spectroscopic analysis. Partial least square - artificial neural network (PLS-ANN) is a hybrid method that may improve the performance of prediction in NIR spectroscopic analysis. This study investigates the advantage of PLS-ANN over the well-known modelling in spectroscopy analysis that is partial least square (PLS) and artificial neural network (ANN). The results show that ANN that coupled with first order SG derivatives achieved the best prediction with root mean square error of prediction (RMSEP) of 0.3517 gd/L and coefficient of determination ( ) of 0.9849 followed by PLS-ANN with RMSEP of 0.4368 gd/L and  of 0.9787, and PLS with RMSEP of 0.4669 gd/L and  of 0.9727. This suggests that the spectrum information may unable to be totally represented by the first few latent variables of PLS and a nonlinear model is crucial to model these nonlinear information in NIR spectroscopic analysis.
Volume: 16
Issue: 2
Page: 701-708
Publish at: 2019-11-01

Simulation hedge investment portfolios through options portfolio

10.11591/ijeecs.v16.i2.pp843-847
Miguel Jiménez-Gómez , Natalia Acevedo-Prins , Miguel David Rojas-López
This paper presents two hedging strategies with financial options to mitigate the market risk associated with the future purchase of investment portfolios that exhibit the same behavior as Colombia's COLCAP stock index. The first strategy consists in the purchase of a Call plain vanilla option and the second strategy in the purchase of a Call option and the sale of a Call option. The second strategy corresponds to a portfolio of options called Bull Call Spread. To determine the benefits of hedging and the best strategy, the Geometric Brownian Motion and Monte Carlo simulation is used. The results show that the two hedging strategies manage to mitigate market risk and the best strategy is the first one despite the fact that the Bull Call Spread strategy is lower cost.
Volume: 16
Issue: 2
Page: 843-847
Publish at: 2019-11-01

An adaptive gravitational search algorithm for global optimization

10.11591/ijeecs.v16.i2.pp724-729
Ying-Ying Koay , Jian-Ding Tan , Chin-Wai Lim , Siaw-Paw Koh , Sieh-Kiong Tiong , Kharudin Ali
Optimization algorithm has become one of the most studied branches in the fields of artificial intelligent and soft computing. Many powerful optimization algorithms with global search ability can be found in the literature. Gravitational Search Algorithm (GSA) is one of the relatively new population-based optimization algorithms. In this research, an Adaptive Gravitational Search Algorithm (AGSA) is proposed. The AGSA is enhanced with an adaptive search step local search mechanism. The adaptive search step begins the search with relatively larger step size, and automatically fine-tunes the step size as iterations go. This enhancement grants the algorithm a more powerful exploitation ability, which in turn grants solutions with higher accuracies. The proposed AGSA was tested in a test suit with several well-established optimization test functions. The results showed that the proposed AGSA out-performed other algorithms such as conventional GSA and Genetic Algorithm in the benchmarking of speed and accuracy. It can thus be concluded that the proposed AGSA performs well in solving local and global optimization problems. Applications of the AGSA to solve practical engineering optimization problems can be considered in the future.
Volume: 16
Issue: 2
Page: 724-729
Publish at: 2019-11-01

A secure group based authentication protocol for machine to machine communications in LTE-WLAN interworking architecture

10.11591/ijeecs.v16.i2.pp848-859
Mariya Ouaissa , Abdallah Rhattoy
Machine to Machine (M2M) communication has been used in applications such as telemetry, industry, automation and health. Support for a large number of devices has been considered an essential requirement in M2M communications. During this time, security is the most important challenge; M2M cannot access secure networks through effective authentication, all relevant M2M applications cannot be accepted. The challenge of M2M research is authentication by the group when a large number of M2M devices simultaneously accessing the network will cause severe authentication signaling congestion. The group based model under an M2M architecture, especially when the Machine Type Communication (MTC) devices belong to the non 3rd Generation Partnership Project (3GPP) network, will face a new challenge of access authentication. In this paper, we propose a group based authentication and key agreement protocol for machine type communications combining Elliptic Curve based Diffie-Hellman (ECDH) on the Extensible Authentication Protocol (EAP). Compared to EAP-AKA and other existing authentication protocols, our solution provides increased security against various malicious activities and better performance in terms of signaling overhead, bandwidth consumption and transmission cost.
Volume: 16
Issue: 2
Page: 848-859
Publish at: 2019-11-01

Detection of fault during power swing in test system interconnected with DG

10.11591/ijeecs.v16.i2.pp577-585
Nor Zulaily Mohamad , Ahmad Farid Abidin , Ismail Musirin
Distance relay is prone to mal-operate during power swing, thus most of modern distance relay design is equipped with power swing blocking scheme to block the operation during power swing and reset the blocking operation whenever a fault occurs during power swing. However, the detection of fault during power swing especially for high resistance fault possess a challenging task, therefore it may cause the unblocking function to vulnerable to operate. This paper presents the development of a detection scheme for detecting fault during power swing in test system interconnected with Distributed Generation (DG). In this study, the detection scheme is proposed based on S-Transform analysis on the distance relay input voltage signal. It is demonstrated that the proposed S-Transform detection based scheme can effectively detect various type of fault during power swing includes high resistance fault, as well as able to operate correctly even with the presence of DG in the test system.
Volume: 16
Issue: 2
Page: 577-585
Publish at: 2019-11-01

Analytics of stock market prices based on machine learning algorithms

10.11591/ijeecs.v16.i2.pp1050-1058
Puteri Hasya Damia Abd Samad , Sofianita Mutalib , Shuzlina Abdul-Rahman
This study focuses on the use of machine learning algorithms to analyse financial news on stock market prices. Stock market prediction is a challenging task because the market is known to be very volatile and dynamic. Investors face these kinds of problems as they do not properly understand which stock product to subscribe or when to sell the product with an optimum profit. Analyzing the information individually or manually is a tedious task as many aspects have to be considered. Five different companies from Bursa Malaysia namely CIMB, Sime Darby, Axiata, Maybank and Petronas were chosen in this study. Two sets of experiments were performed based on different data types. The first experiment employs textual data involving 6368 articles, extracted from financial news that have been classified into positive or negative using Support Vector Machine (SVM) algorithm. Bags of words and bags of combination words are extracted as the features for the first experiment. The second experiment employs the numeric data type extracted from historical data involving 5321 records to predict whether the stock price is going up (positive) or down (negative) using Random Forest algorithm. The Rain Forest algorithm gives better accuracy in comparison with SVM algorithm with 99% and 68% accuracy respectively. The results demonstrate the complexities of the textual-based data and demand better feature extraction technique.
Volume: 16
Issue: 2
Page: 1050-1058
Publish at: 2019-11-01

Numerical computation for solving fuzzy differential equations

10.11591/ijeecs.v16.i2.pp1026-1033
Fuziyah Ishak , Najihah Chaini
Fuzzy differential equations (FDEs) play important roles in modeling dynamic systems in science, economics and engineering. The modeling roles are important because most problems in nature are indistinct and uncertain. Numerical methods are needed to solve FDEs since it is difficult to obtain exact solutions. Many approaches have been studied and explored by previous researchers to solve FDEs numerically. Most FDEs are solved by adapting numerical solutions of ordinary differential equations. In this study, we propose the extended Trapezoidal method to solve first order initial value problems of FDEs. The computed results are compared to that of Euler and Trapezoidal methods in terms of errors in order to test the accuracy and validity of the proposed method. The results shown that the extended Trapezoidal method is more accurate in terms of absolute error. Since the extended Trapezoidal method has shown to be an efficient method to solve FDEs, this brings an idea for future researchers to explore and improve the existing numerical methods for solving more general FDEs.
Volume: 16
Issue: 2
Page: 1026-1033
Publish at: 2019-11-01

An optimization of facial feature point detection program by using several types of convolutional neural network

10.11591/ijeecs.v16.i2.pp827-834
Shyota Shindo , Takaaki Goto , Tadaaki Kirishima , Kensei Tsuchida
Detection of facial feature points is an important technique used for biometric authentication and facial expression estimation. A facial feature point is a local point indicating both ends of the eye, holes of the nose, and end points of the mouth in the face image. Many researches on face feature point detection have been done so far, but the accuracy of facial organ point detection is improving by the approach usingConvolutional Neural Network (CNN). However, CNN not only takes time to learn but also the neural network becomes a complicated model, so it is necessary to improve learning time and detection accuracy. In this research, the improvement of the detection accuracy of the learning speed is improved by increasing the convolution layer.
Volume: 16
Issue: 2
Page: 827-834
Publish at: 2019-11-01

Coordinated and optimal voltage control for voltage regulation using firefly algorithm

10.11591/ijeecs.v16.i2.pp568-576
Muhamad Najib Kamarudin , Tengku Juhana Tengku Hashim
The operation and control of electricity in distribution networks has faced great challenges as a large number of distributed generations (DGs) are integrated. Connection of distributed generations (DGs) in the distribution system offers advantages in terms of reducing distribution and transmission costs as well as encouraging the use of renewable energy sources. The power flow in the distribution systems is no longer moving in a single direction and this resulted the system to become as active distribution networks (ADN). One of the main problems in ADN is the voltage regulation issue which is to maintain the voltage to be within its permissible limits. Several methods of voltage control methods are available and focus is given in finding the optimal voltage control using artificial intelligence techniques. This paper presents an optimal and coordinated voltage control method while minimizing losses and voltage deviation of the network. The optimal and coordinated voltage control scheme is implemented on an IEEE 13 bus distribution network for loss and voltage deviation minimization in the networks. Firefly Algorithm (FA) which is a known heuristic optimization technique for finding the optimal solution is used in this work. The results are compared with another optimization method known as Backtracking Search Algorithm (BSA) for identifying the best setting for solving the voltage regulation problem. In order to solve the multi-objective optimization issue, the MATPOWER load flow simulation is integrated in the MATLAB environment with the optimization algorithm.
Volume: 16
Issue: 2
Page: 568-576
Publish at: 2019-11-01

A comparative study on dimensionality reduction between principal component analysis and k-means clustering

10.11591/ijeecs.v16.i2.pp752-758
Norsyela Muhammad Noor Mathivanan , Nor Azura Md.Ghani , Roziah Mohd Janor
The curse of dimensionality and the empty space phenomenon emerged as a critical problem in text classification. One way of dealing with this problem is applying a feature selection technique before performing a classification model. This technique helps to reduce the time complexity and sometimes increase the classification accuracy. This study introduces a feature selection technique using K-Means clustering to overcome the weaknesses of traditional feature selection technique such as principal component analysis (PCA) that require a lot of time to transform all the inputs data. This proposed technique decides on features to retain based on the significance value of each feature in a cluster. This study found that k-means clustering helps to increase the efficiency of KNN model for a large data set while KNN model without feature selection technique is suitable for a small data set. A comparison between K-Means clustering and PCA as a feature selection technique shows that proposed technique is better than PCA especially in term of computation time. Hence, k-means clustering is found to be helpful in reducing the data dimensionality with less time complexity compared to PCA without affecting the accuracy of KNN model for a high frequency data.
Volume: 16
Issue: 2
Page: 752-758
Publish at: 2019-11-01

Computational study of flow around a NACA 0012 by using Roe FVM scheme and davis-yee TVD scheme

10.11591/ijeecs.v16.i2.pp1018-1025
Fatimah Yusop , Zamri Omar , Bambang Basuno , Nik Normunira Mat Hassan
Currently CFD had been considered as an important tool for solving engineering problems. The application of CFD had been used intensively in aircraft industries in design a new aircraft or in the effort of improvement on the exiting aircraft. In term of CFD computer code, the CFD code differs with any others may due to the difference in the numerical scheme have been used. Therefore, the present work presents the comparison result between two developed computer codes with ANSYS-FLUENT software to the case of transonic steady flow past through airfoil NACA 0012. The first computer code used a finite difference method with numerical scheme according to Davis-Yee TVD scheme. Meanwhile, the second computer code used a Roe’s cell centre finite volume scheme. The flow analysis is carried out at two Mach number, M (0.65 & 0.8). Each Mach number applied to two different angles of attacks (0° & 5°).  The flow domain discretized by use of C-topology with 193x63 grid points. The comparison in term of the pressure coefficient, along the airfoil surface are presented. From the result, indicated that developed computer code is able to capture the presence of shock wave in the flow field.
Volume: 16
Issue: 2
Page: 1018-1025
Publish at: 2019-11-01

Clonal evolutionary particle swarm optimization for congestion management and compensation scheme in power system

10.11591/ijeecs.v16.i2.pp591-598
N. Z. Mohd Ali , I. Musirin , H. Mohamad
This paper presents computational intelligence-based technique for congestion management and compensation scheme in power systems. Firstly, a new model termed as Integrated Multilayer Artificial Neural Networks (IMLANNs) is developed to predict congested line and voltage stability index separately. Consequently, a new optimization technique termed as Clonal Evolutionary Particle Swarm Optimization (CEPSO) was developed. CEPSO is initially used to optimize the location and sizing of FACTS devices for compensation scheme. In this study, Static VAR Compensator (SVC) and Thyristor Control Static Compensator (TCSC) are the two chosen Flexible AC Transmission System (FACTS) devices used in this compensation scheme. Comparative studies have been conducted between the proposed CEPSO and traditional Particle Swarm Optimization (PSO). Results obtained by the developed IMLANNs demonstrated high accuracy with respect to the targeted output. Consequently, the proposed CEPSO implemented for single objective in single unit of SVC and TCSC has resulted superior results as compared to the traditional PSO in terms of achieving loss reduction and voltage profile improvement.
Volume: 16
Issue: 2
Page: 591-598
Publish at: 2019-11-01

Analysis of landslide hazard mapping of penang island malaysia using bivariate statistical methods

10.11591/ijeecs.v16.i2.pp781-786
Ilyas A Huqqani , Lea Tien Tay , Junita Mohamad Saleh
Landslide is one of the disasters which cause property damages, infrastructure destruction, injury and death. This paper presents the analysis of landslide hazard mapping of Penang Island Malaysia using bivariate statistical methods. Bivariate statistical methods are simple approach which are capable to produce good results in short computational time. In this study, three bivariate statistical methods, i.e. Frequency Ratio (FR), Information Value (IV) and Modified Information Value (MIV) are used to generate the landslide hazard maps of Penang Island. These bivariate statistical methods are computed using MATLAB tool. Landslide hazard map is categorized into 4 levels of hazard. The accuracy of each method and effectiveness in predicating landslides are validated and determined by using Receiver of Characteristics curve. The accuracies of FR, IV and MIV methods are 79.58%, 79.14% and 79.37% respectively.
Volume: 16
Issue: 2
Page: 781-786
Publish at: 2019-11-01

Spectrum sensing in single channel and multi-channel cognitive radio networks

10.11591/ijeecs.v16.i2.pp812-817
Amira Osama Hashesh , Heba A.Tag El-Dien , Ahmad A.Aziz El-Banna , Adly Tag El-Din
Sensing the existence or absence of primary user is the major chore of cognitive radio networks. Nevertheless, Spectrum sensing is the core process of cognitive radio and with target to find idle channels.Various detection techniques exist, however, energy detection is considered as the most used detector because of its lower computational cost. In this paper, we proposed a study of throughput for a cognitive radio system. We had two scenarios, in the first scenario; a study of throughput against probability of false alarm was done; where, only one channel is sensed, to maximize the individual channel throughput. In the second scenario, multi-channel is sensed to maximize the overall system capacity. In addition, different number of channels is considered with different sensing times and at different throughput costs.The performance of the network has been investigated in terms of maximum throughput for optimal number of CR channels.      
Volume: 16
Issue: 2
Page: 812-817
Publish at: 2019-11-01
1 2 3
...
1993 1994
Show 1229 of 1994

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration