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

28,428 Article Results

Wireless Sensor Node with Passive RFID for Indoor Monitoring System

10.11591/ijece.v7i3.pp1459-1466
Norsaidah Muhamad Nadzir , M.K.A. Rahim , F. Zubir , A. Zabri , H.A. Majid
This paper discusses the development of an indoor monitoring system based on passive radio frequency identification (RFID) system and Raspberry Pi 3. There are two algorithms designed for this project where the first is to link the RFID module to the Raspberry Pi 3, and the other one is to send the data obtained to a database over wireless network via UDOO Quad as a secondary router. The result is then displayed on a localhost generated using XAMPP. The objective of this project is to realize a monitoring system that incorporates different systems such as Raspberry Pi 3, UDOO Quad, and also RFID module by designing algorithms using Python and C programming language. Plus, the performance of the system is also analyzed using different type of antennas such as the Raspberry Pi 3 Antenna, monopole antenna, and a Yagi Uda antenna in terms of power received versus distance in both line of sight position and non-line of sight position. Finally, antenna that produces the best performance for line-of-sight (LOS) propagation is Yagi Uda antenna while monopole antenna is better when it comes to non-line-of-sight (NLOS) propagation.
Volume: 7
Issue: 3
Page: 1459-1466
Publish at: 2017-06-01

Impact of Distributed Generation on Voltage Profile in Radial Feeder

10.11591/ijeecs.v6.i3.pp583-590
Charles R. Sarimuthu , Vigna K. Ramachandaramurthy , H. Mokhlis , K.R. Agileswari
The use of distributed generation (DG) within distribution systems has increased for the last two decades due to worldwide increase in demand for electricity and governmental policy change from “conventional” energy to “green” energy. High levels of penetration of DG have many significant benefits but also come with many drawbacks such as voltage drop and power losses. This study presents the impact of DG at different locations in a distribution feeder in terms of the feeder voltage profile. A radial distribution system is simulated using PSCAD/EMTDC simulation software while changing the size and location of DG in the system. The obtained results are used for better understanding on the impact of DG on voltage profile in radial distribution feeder.
Volume: 6
Issue: 3
Page: 583-590
Publish at: 2017-06-01

A Novel Right Handed Circular Polarization Folded Reflectarray Antenna at 60 GHz

10.11591/ijece.v7i3.pp1580-1587
Mohd Fairus Mohd Yusoff , Ronan Sauleau , Zaharah Johari , Mohamad Kamal A. Rahim , Huda A. Majid
A novel right-handed circular polarization (RHCP) folded reflectarray antenna with optimized parameters is presented at 60GHz. The RHCP folded reflectarray antenna is designed using left handed circularly polarized selective surface (LHCPSS) Pierrot unit cell. Through simulation, it is shown that the antenna operates well at 60GHz. The maximum antenna directivity is 19dB with a reflection coefficient below -15dB. The radiation patterns showed good responses with side lobes level below -10dB. In addition, the best axial ratio at 60GHz is achieved as 0.75dB.
Volume: 7
Issue: 3
Page: 1580-1587
Publish at: 2017-06-01

Optimal Feature Selection Technique for Mel Frequency Cepstral Coefficient Feature Extraction in Classifying Infant Cry with Asphyxia

10.11591/ijeecs.v6.i3.pp646-655
A. Zabidi , W. Mansor , Khuan Y. Lee
Mel Frequency Cepstral Coefficient is an efficient feature representation method for extracting human-audible audio signals. However, its representation of features is large and redundant. Therefore, feature selection is required to select the optimal subset of Mel Frequency Cepstral Coefficient features. The performance of two types of feature selection techniques; Orthogonal Least Squares and F-ratio for selecting Mel Frequency Cepstral Coefficient features of infant cry with asphyxia was examined. OLS selects the feature subset based on their contribution to the reduction of error, while F-Ratio selects them according to their discriminative abilities. The feature selection techniques were combined with Multilayer Perceptron to distinguish between asphyxiated infant cry and normal cry signals. The performance of the feature selection methods was examined by analysing the Multilayer Perceptron classification accuracy resulted from the combination of the feature selection techniques and Multilayer Perceptron. The results indicate that Orthogonal Least Squares is the most suitable feature selection method in classifying infant cry with asphyxia since it produces the highest classification accuracy.
Volume: 6
Issue: 3
Page: 646-655
Publish at: 2017-06-01

Comparison of Accuracy Measures for RS Image Classification using SVM and ANN Classifiers

10.11591/ijece.v7i3.pp1180-1187
S.V.S. Prasad , T. Satya Savithri , Iyyanki V. Murali Krishna
The accurate land use land cover (LULC) classifications from satellite imagery are prominent for land use planning, climatic change detection and eco-environment monitoring. This paper investigates the accuracy and reliability of Support Vector Machine (SVM) classifier for classifying multi-spectral image of Hyderabad and its surroundings area and also compare its performance with Artificial Neural Network (ANN) classifier. In this paper, a hybrid technique which we refer to as Fuzzy Incorporated Hierarchical clustering has been proposed for clustering the multispectral satellite images into LULC sectors. The experimental results show that overall accuracies of LULC classification of the Hyderabad and its surroundings area are approximately 93.159% for SVM and 89.925% for ANN. The corresponding kappa coefficient values are 0.893 and 0.843. The classified results show that the SVM yields a very promising performance than the ANN in LULC classification of high resolution Landsat-8 satellite images.
Volume: 7
Issue: 3
Page: 1180-1187
Publish at: 2017-06-01

Evaluation of Feature Reduction using Principal Component Analysis and Sequential Pattern Matching for Manet

10.11591/ijece.v7i3.pp1228-1239
M. Reji , P.C. Kishore Raja , Bhagyalakshmi M
In Mobile Ad hoc Networks (MANETs) there are some security problems because of portability, element topology changes, and absence of any framework. In MANETs, it is of extraordinary significance to identify inconsistency and malignant conduct. With a specific end goal to recognize malignant assaults by means of interruption identification frameworks and dissect the information set, we have to choose some components. Thus, highlight determination assumes basic part in recognizing different assaults. In the writing, there are a few recommendations to choose such elements. For the most part, Principal Component Analysis (PCA) breaks down the information set and the chose highlights. In this paper, we have gathered a list of capabilities from some cutting edge works in the writing. Really, our reproduction demonstrates this list of capabilities identify inconsistency conduct more precise. Likewise, interestingly, we utilize PCA for investigating the information set. In contrast to PCA, our results show Sequential pattern mining (SPM) cannot be affected by outlier data within the network. The  normal and attack states are simulated and the results are analyzed using NS2 simulator.
Volume: 7
Issue: 3
Page: 1228-1239
Publish at: 2017-06-01

Portable Electrochemical Sensing System Attached to Smartphones and Its Incorporation with Paper-based Electrochemical Glucose Sensor

10.11591/ijece.v7i3.pp1423-1429
Takuya Fujimoto , Shogo Kawahara , Yukio Fuchigami , Shoji Shimokawa , Yosuke Nakamura , Kenichi Fukayama , Masao Kamahori , Shigeyasu Uno
This paper described the development of a small and low cost biosensor consisting of a smartphone-based electrochemical biosensor device and a paper-based biosensor. The device harvested power from the smartphone and transferred data through audio jack. We designed CMOS circuits including a power supply circuit, a potentiostat, and a ΔΣ modulator. The fabrication of a paper-based biosensor was simple: the three electrodes were directly drawn on chromatography paper using a carbon pencil. The paper-based biosensor was low cost, disposable, portable and friendly to the environment. The sensing system was designed to perform the chronoamperometry measurement, and the glucose concentration in a liquid specimen was detected. Results showed that the sensing system was capable of measuring the glucose concentration as precisely as expensive equipments.
Volume: 7
Issue: 3
Page: 1423-1429
Publish at: 2017-06-01

SAR Levels for Irradiation by a Crumpled 900 MHz Flexible Diamond Dipole

10.11591/ijece.v7i3.pp1546-1553
N. A. Elias , N. A. Samsuri , M. K. A. Rahim , C. J. Panagamuwa , W. Whittow
In this work, the antenna performance and Specific Absorption Rate (SAR) levels in a homogeneous phantom exposed to 900 MHz flexible diamond dipole antenna are investigated under different crumpling deformation conditions. The numerical simulations of the realistic complex two dimensional crumpling are performed by using Finite Integration Technique (FIT) which is applied in Computer Simulation Technology (CST) Microwave Studio. The validation of results with the industry standard DASY4 robot SAR measurement system is made possible with the use of homogenous phantom model. The 1 g, 10 g and point SAR are enhanced by 28.33 %, 36.75 % and 9.55 % respectively due to the antenna crumpling deformation. The short length ripple investigated in this paper shows the highest relative SAR increment.
Volume: 7
Issue: 3
Page: 1546-1553
Publish at: 2017-06-01

Wind Farm Management using Artificial Intelligent Techniques

10.11591/ijece.v7i3.pp1133-1144
Boualam Benlahbib , Farid Bouchafaa , Saad Mekhilef , Noureddine Bouarroudj
This paper presents a comparative study between genetic algorithm and particle swarm optimization methods to determine the optimal proportional–integral (PI) controller parameters for a wind farm management algorithm. This study primarily aims to develop a rapid and stable system by tuning the PI controller, thus providing excellent monitoring for a wind farm system. The wind farm management system supervises the active and reactive power of the wind farm by sending references to each wind generator. This management system ensures that all wind generators achieve their required references. Furthermore, the entire management is included in the normal controlling power set points of the wind farm as designed by a central control system. The performance management of this study is tested through MATLAB/Simulink simulation results for the wind farm based on three doublyfed induction generators
Volume: 7
Issue: 3
Page: 1133-1144
Publish at: 2017-06-01

A New Recognition Method for Visualizing Music Emotion

10.11591/ijece.v7i3.pp1246-1254
Van Loi Nguyen , Donglim Kim , Phi Van Ho , Younghwan Lim
This paper proposes an emotion detection method using a combination of dimensional approach and categorical approach. Thayer’s model is divided into discrete emotion sections based on the level of arousal and valence. The main objective of the method is to increase the number of detected emotions which is used for emotion visualization. To evaluate the suggested method, we conducted various experiments with supervised learning and feature selection strategies. We collected 300 music clips with emotions annotated by music experts. Two feature sets are employed to create two training models for arousal and valence dimensions of Thayer’s model. Finally, 36 music emotions are detected by proposed method. The results showed that the suggested algorithm achieved the highest accuracy when using RandomForest classifier with 70% and 57.3% for arousal and valence, respectively. These rates are better than previous studies.
Volume: 7
Issue: 3
Page: 1246-1254
Publish at: 2017-06-01

An Early Detection-Warning System to Identify Speed Breakers and Bumpy Roads using Sensors In Smartphones

10.11591/ijece.v7i3.pp1377-1384
Vamsee Krishna Kiran M , Vimalkumar K , Vinodhini R E , Archanaa R
Speed breakers and bumpy roads are a major threat to drivers that questions their safety. The mishap happens because of no sign boards indicating the speed breaker, poor visibility at night and road works that are often carried out with no proper signs of road deviations and also the negligence of the driver. All these factors put the life of the persons in vain causing damage to the vehicle as well as life. Also, bumpy roads have become a problem for cars with less ground clearance. The focus of the paper is on designing an early warning system detecting both speed breaker humps and bad road conditions. The approach used in this paper is a real-time solution and is developed as an android service that runs in the background and relies on Google Maps application in the smartphone. This service will throw an alert giving early warning if the user is approaching the speed breaker or a bumpy road. Apart from just giving an early alert to the user, it also provides the user with an alternative and a better route. The solution proposed in this work is a form of crowdsourcing where users share and get data, therefore making the system cost effective.
Volume: 7
Issue: 3
Page: 1377-1384
Publish at: 2017-06-01

Disaggregated Electricity Bill Base on Utilization factor and Time-of-use (ToU) Tariff

10.11591/ijece.v7i3.pp1498-1505
Nur Farahin Asa @ Esa , Md Pauzi Abdullah , Mohammad Yusri Hassan , Faridah Hussin
Time of Use tariff is introduced to motivate users to change their electricity usage pattern. Commonly the tariff is high during peak hours and relatively low during off peak hours, to encourage users to reduce consumption during peak hours or shift it to off-peak hours. This tariff scheme provides opportunities for building owners to reduce their electricity bill provided that their electricity usage patterns of various spaces in that building at every hour are known. In practice, the kWh meter installed by the utility can only provide the overall hourly electricity consumption pattern. To know the usage pattern of different spaces or rooms, separate individual meter need to be installed in each space/room, which is costly and impractical.  This paper presented the disaggregated electricity bill method based on user utilization factor and time of use (ToU) tariff. It estimates hourly electricity bill of each appliance at each space/room. Utilization factor is used to represent the electricity usage behavior of the occupants. The proposed method is applied on practical load profile data of a university building.
Volume: 7
Issue: 3
Page: 1498-1505
Publish at: 2017-06-01

An Optimized FPGA Implementation of CAN 2.0 Protocol Error Detection Circuitry

10.11591/ijeecs.v6.i3.pp602-614
Md Farukh Hashmi , Avinash G. Keskar
Controller Area Network is an ideal serial bus design suitable for modern embedded system based networks. It finds its use in most of critical applications, where error detection and subsequent treatment on error is a critical issue. CRC (Cyclic Redundancy Check) block was developed on FPGA in order to meet the needs for simple, low power and low cost wireless communication. This paper gives a short overview of CRC block in the Digital transmitter based on the CAN 2.0 protocols. CRC is the most preferred method of encoding because it provides very efficient protection against commonly occurring burst errors, and is easily implemented. This technique is also sometimes applied to data storage devices, such as a disk drive. In this paper a technique to model the error detection circuitry of CAN 2.0 protocols on reconfigurable platform have been discussed? The software simulation results are presented in the form of timing diagram.FPGA implementation results shows that the circuitry requires very small amount of digital hardware. The Purpose of the research is to diversify the design methods by using VHDL code entry through Modelsim 5.5e simulator and Xilinx ISE8.3i.The VHDL code is used to characterize the CRC block behavior which is then simulated, synthesized and successfully implemented on Sparten3 FPGA .Here, Simulation and Synthesized results are also presented to verify the functionality of the CRC -16 Block. The data rate of CRC block is 250 kbps .Estimated power consumption and maximum operating frequency of the circuitry is also provided.
Volume: 6
Issue: 3
Page: 602-614
Publish at: 2017-06-01

Modelling and Evaluation of Sequential Batch Reactor Using Artificial Neural Network

10.11591/ijece.v7i3.pp1620-1627
Norjannah Hazali , Norhaliza Abdul Wahab , Syahira Ibrahim
The main objective of wastewater treatment plant is to release safe effluent not only to human health but also to the natural environment. An aerobic granular sludge technology is used for nutrient removal of wastewater treatment process using sequential batch reactor system. The nature of the process is highly complex and nonlinear makes the prediction of biological treatment is difficult to achieve. To study the nonlinear dynamic of aerobic granular sludge, high temperature real data at 40˚C were used to model sequential batch reactor using artificial neural network. In this work, the radial basis function neural network for modelling of nutrient removal process was studied. The network was optimized with self-organizing radial basis function neural network which adjusted the network structure size during learning phase. Performance of both network were evaluated and compared and the simulation results showed that the best prediction of the model was given by self-organizing radial basis function neural network.
Volume: 7
Issue: 3
Page: 1620-1627
Publish at: 2017-06-01

Deep Machine Learning and Neural Networks: An Overview

10.11591/ijai.v6.i2.pp66-73
Chandrahas Mishra , D. L. Gupta
Deep learning is a technique of machine learning in artificial intelligence area. Deep learning in a refined "machine learning" algorithm that far surpasses a considerable lot of its forerunners in its capacities to perceive syllables and picture. Deep learning is as of now a greatly dynamic examination territory in machine learning and example acknowledgment society. It has increased colossal triumphs in an expansive zone of utilizations, for example, speech recognition, computer vision and natural language processing and numerous industry item. Neural network is used to implement the machine learning or to design intelligent machines. In this paper brief introduction to all machine learning paradigm and application area of deep machine learning and different types of neural networks with applications is discussed.
Volume: 6
Issue: 2
Page: 66-73
Publish at: 2017-06-01
1 2 3
...
1895 1896
Show 1461 of 1896

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