Articles

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

Filter Icon

Filters article

Years

FAQ Arrow
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

27,438 Article Results

Mammogram Analysis using League Championship Algorithm Optimized Ensembled FCRN Classifier

10.11591/ijeecs.v5.i2.pp451-461
Saraswathi D , Srinivasan E
An intelligent mammogram diagnosis system can be very helpful for radiologist in detecting the abnormalities earlier than typical screening techniques. This paper investigates a new classification approach for detection of breast abnormalities in digital mammograms using League Championship Algorithm Optimized Ensembled Fully Complex valued Relaxation Network (LCA-FCRN). The proposed algorithm is based on extracting curvelet fractal texture features from the mammograms and classifying the suspicious regions by applying a pattern classifier. The whole system includes steps for pre-processing, feature extraction, feature selection and classification to classify whether the given input mammogram image is normal or abnormal. The method is applied to MIAS database of 322 film mammograms. The performance of the CAD system is analysed using Receiver Operating Characteristic (ROC) curve. This curve indicates the trade-offs between sensitivity and specificity that is available from a diagnostic system, and thus describes the inherent discrimination capacity of the proposed system. The result shows that the area under the ROC curve of the proposed algorithm is 0.985 with a sensitivity of 98.1% and specificity of 92.105%. Experimental results demonstrate that the proposed method can form an effective CAD system, and achieve good classification accuracy.
Volume: 5
Issue: 2
Page: 451-461
Publish at: 2017-02-01

Effect of Measurement Factors on Photovoltaic Cell Parameters Extracting

10.11591/ijece.v7i1.pp50-57
El Hadi Chahid , Mohammed Idali Oumhand , M’barek Feddaoui , Mohammed Erritali , Abdessamad Malaoui
In this paper, we study the influence of external factors on the measurement for the current–voltage (I-V) characteristic of the photovoltaic cell. These factors are the size of the number of measurements, the range of the cell generated voltage and the influence of measures step and mode combination of photovoltaic cells (parallel, serial, or hybrid). The main extracted parameters solar cell are the photocurrent Iph, the reverse diode saturation current I0, the ideality factor of diode n, the series resistance Rs and the shunt resistance Rsh. A method for finding these parameters, according to the single-diode model, was developed by Newton-Raphson’s method using Matlab. To assess the accuracy of this method, measured and calculated I–V characteristics were compared with provided data by the manufacturer at standard test condition (STC). The measurement results showed that these parameters are highly dependent on these four factors.
Volume: 7
Issue: 1
Page: 50-57
Publish at: 2017-02-01

Identity Analysis of Egg Based on Digital and Thermal Imaging: Image Processing and Counting Object Concept

10.11591/ijece.v7i1.pp200-208
Sunardi Sunardi , Anton Yudhana , Shoffan Saifullah
This Research was conducted to analyze the identification of eggs. The research processes use two tools, namely thermal imaging camera and smartphone camera. The identification process was done by using Matlab prototype tools. The image has been acquired by means of proficiency level, then analyzed and applied several methods. Image acquisition results of thermal imaging camera are processed using morphological dilation and do the complement in black and white (BW). While the digital image uses the merger method of morphological dilation and opening, and it doesn't need to be complemented. Labeling process is done, and the process of determining centroid and bounding box. The process has been done and it can be applied for identifying of chicken eggs with the accuracy rate of 100%. There are different methods of both images is obtained area (pixels) which is equivalent to the difference is very small as 6 x 10-3.
Volume: 7
Issue: 1
Page: 200-208
Publish at: 2017-02-01

Selection of the Best Proposal using FAHP: Case of Procurement of IT Master Plan’s Realization

10.11591/ijece.v7i1.pp353-362
Amadou Diabagate , Abdellah Azmani , Mohamed El Harzli
IT master plan, which allows planning and managing the development of the computer systems, derives its importance in the central role of the computer systems in the functioning of organizations. This article focuses on the use of FAHP method for analysis and evaluation of tenders during the awarding of contracts of IT master plan’s realization. For those purposes, a painstaking work was realized for making an inventory of criteria and sub-criteria involved in the evaluation of tenders and for specifying the degrees of preference for each pair of criteria and sub-criteria. To find a provider for the IT master plan’s realization, organizations are increasingly using tendering as the mode of awarding contracts. This paper is an improvement of a previous published paper in which AHP method was used. The goals of this work are to make available to members of tenders committee a decision support tool for evaluating tenders of IT master plan’s realization and endow the organizations with effective IT master plans in order to increase their information systems’ performance.
Volume: 7
Issue: 1
Page: 353-362
Publish at: 2017-02-01

Optimized Active Learning for User’s Behavior Modelling based on Non-Intrusive Smartphone

10.11591/ijece.v7i1.pp505-512
Ika Kusumaning Putri , Deron Liang , Sholeh Hadi Pramono , Rahmadwati Rahmadwati
In order to protect the data in the smartphone, there is some protection mechanism that has been used. The current authentication uses PIN, password, and biometric-based method. These authentication methods are not sufficient due to convenience and security issue. Non-Intrusive authentication is more comfortable because it just collects user’s behavior to authenticate the user to the smartphone. Several non-intrusive authentication mechanisms were proposed but they do not care about the training sample that has a long data collection time. This paper propose a method to collect data more efficient using Optimized Active Learning. The Support Vector Machine (SVM) used to identify the effect of some small amount of training data. This proposed system has two main functionalities, to reduce the training data using optimized stop rule and maintain the Error Rate using modified model analysis to determine the training data that fit for each user. Finally, after we done the experiment, we conclude that our proposed system is better than Threshold-based Active Learning. The time required to collect the data can reduced to 41% from 17 to 10 minutes with the same Error Rate.
Volume: 7
Issue: 1
Page: 505-512
Publish at: 2017-02-01

Improving Efficiency of Power Systems by Demand Side Management Method

10.11591/ijece.v7i1.pp100-106
Tibbie Pon Symon V.A. , I. Jacob Ragland
In the smart grid infrastructure based power systems, it is necessary to consider the demand side management to enhance the energy reduction and system control. In many countries the resources are very less so the available resources have to be used in an efficient manner without any loss. The total loss cannot be avoided but it can be reduced. In the proposed system, the Particle Swarm Optimization (PSO) technique is used to distribute the power in the smart grid. Here, the grids are arranged in such a way that the losses in it are reduced. The load connected to the grid is rearranged according to their use. It uses a new and stochastic scheduling technique to handle the uncertainties in the power system. Solar and wind power are taken in account for twenty four hours and the values are given to the PSO algorithm. The   experiment was conducted by MATLAB and the results show that the efficiency level of wind and solar power systems was increased by an appreciable level. The proposed technique is compared with the normal system without using Demand Side Management (DSM) and it shows that the proposed system gives better results than the existing systems.
Volume: 7
Issue: 1
Page: 100-106
Publish at: 2017-02-01

Performance Evaluation of GaN based Thin Film Transistor using TCAD Simulation

10.11591/ijece.v7i1.pp144-151
Shashi Kant Dargar , J K Srivastava , Santosh Bharti , Abha Nyati
As reported in past decades, gallium nitride as one of the most capable compound semiconductor, GaN-based high-electron mobility transistors are the focus of intense research activities in the area of high power, high-speed, and high-temperature transistors. In this paper we present a design and simulation of the GaN based thin film transistor using sentaurus TCAD for the extracting the electrical performance. The resulting GaN TFTs exhibits good electrical performance in the simulated results, including, a threshold voltage of 12-15 V, an on/off current ratio of 6.5×107 ~8.3×108, and a sub-threshold slope of 0.44V/dec. Sentaurus TCAD simulations is the tool  which offers study of comprehensive behavior of semiconductor structures with ease. The simulation results of the TFT structure based on gallium nitride active channel have great prospective in the next-generation flat-panel display applications.
Volume: 7
Issue: 1
Page: 144-151
Publish at: 2017-02-01

Improving the Proactive Routing Protocol using Depth First Iterative Deepening Spanning Tree in Mobile Ad Hoc Network

10.11591/ijece.v7i1.pp316-323
Justin Sophia I , N. Rama
Owing to the wireless and mobility nature, nodes in a mobile ad hoc network are not within the transmission range. It needs to transfer data through the multi-intermediate nodes. Opportunistic data forwarding is an assuring solution to make use of the broadcast environment of wireless communication links. Due to absence of source routing capability with efficient proactive routing protocol, it is not widely used. To rectify the problem, we proposed memory and routing efficient proactive routing protocol using Depth-First Iterative-Deepening and hello messaging scheme.  This protocol can conserve the topology information in every node in the network. In experimental analysis and discussion, we implemented the proposed work using NS2 simulator tool and proved that the proposed technique is performed well in terms of average delay, buffer and throughput.
Volume: 7
Issue: 1
Page: 316-323
Publish at: 2017-02-01

GIS-MAP based Spatial Analysis of Rainfall Data of Andhra Pradesh and Telangana States Using R

10.11591/ijece.v7i1.pp460-468
Y. Jeevan Nagendra Kumar , T. V. Rajini Kanth
The rainfall conditions across wide geographical location and varied topographic conditions of India throw challenge to researchers and scientists in predicting rainfall effectively. India is Agriculture based country and it mainly depends on rainfall. Seasons in India are divided into four, which is winter in January and February, summer is from March to May, monsoon is from June to September and post monsoon is from October to December. India is Agriculture based country and it mainly depends on rainfall. It is very difficult to develop suitable rainfall patterns from the highly volatile weather conditions. In this Paper, it is proposed that Map based Spatial Analysis of rainfall data of Andhra Pradesh and Telangana states is made using R software apart from Hybrid Machine learning techniques. A Study will be made on rainfall patterns based on spatial locations. The Visual analytics were also made for effective study using statistical methods and Data Mining Techniques. This paper also introduced Spatial mining for effective retrieval of Remote sensed Data to deal with retrieval of information from the database and presents them in the form of map using R software.
Volume: 7
Issue: 1
Page: 460-468
Publish at: 2017-02-01

Modeling and Structure Optimization of Tapped Transformer

10.11591/ijece.v7i1.pp41-49
Abdelhadi Namoune , Azzedine Hamid , Rachid Taleb
In this paper, a simplified circuit model of the tapped transformer structure has been presented to extract the Geometric and technology parameters and offer better physical understanding. Moreover, the structure of planar transformer has been optimized by using changing the width and space of the primary coil, so as to enlarge the quality factor Q and high coupling coefficient K. To verify the results obtained by using these models, we have compared them with the results obtained by employing the MATLAB simulator. Very good agreement has been recorded for the effective primary inductance value, whereas the effective primary quality factor value has shown a somewhat larger deviation than the inductance.
Volume: 7
Issue: 1
Page: 41-49
Publish at: 2017-02-01

Recognition of Tomato Late Blight by using DWT and Component Analysis

10.11591/ijece.v7i1.pp194-199
Hiteshwari Sabrol , Satish Kumar
Plant disease recognition concept is one of the successful and important applications of image processing and able to provide accurate and useful information to timely prediction and control of plant diseases. In the study, the wavelet based features computed from RGB images of late blight infected images and healthy images. The extracted features submitted to Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA) and Independent Component Analysis performed (ICA) for reducing dimensions in feature data processing and classification. To recognize and classify late blight from healthy plant images are classified into two classes i.e.  late blight infected or healthy. The Euclidean Distance measure is used to compute the distance by these two classes of training and testing dataset for tomato late blight recognition and classification. Finally, the three-component analysis is compared for late blight recognition accuracy. The Kernel Principal Component Analysis (KPCA) yielded overall recognition accuracy with 96.4%.
Volume: 7
Issue: 1
Page: 194-199
Publish at: 2017-02-01

Novel Resonant Structure to Compact Partial H-Plane Band-Pass Waveguide Filter

10.11591/ijece.v7i1.pp266-270
Elahe Mohhamadi , Habib Ghorbaninejad
In this paper partial H-plane band-pass waveguide filter, utilizing a novel resonant structure comprising a metal window along with metal posts has been proposed to compact the filter size. The metal windows and posts have been implemented transversely in a partial H-plane waveguides, which have one-quarter cross section size compared to the conventional waveguides in the same frequency range. Partial H-plane band-pass waveguide filter with novel proposed resonant structures has considerably shorter longitudinal length compared to the conventional partial H-plane filters, so that they reduce both cross section size and the total length of the filter compared to conventional H-plane filters, in the same frequency range. In the presented design procedure, the size and shape of each metal window and metal posts has been determined by fitting the transfer function of the proposed resonant structure to that of a desired one, which is obtained from a suitable equivalent circuit model. The design process is based on optimization using electromagnetic simulator software, HFSS. A proposed partial H-plane band-pass filter has been designed and simulated to verify usefulness and performance of the design method.
Volume: 7
Issue: 1
Page: 266-270
Publish at: 2017-02-01

Streaming Big Data Analysis for Real-Time Sentiment based Targeted Advertising

10.11591/ijece.v7i1.pp402-407
Lekha R. Nair , Sujala D. Shetty , Siddhant Deepak Shetty
Big Data constituting from the information shared in the various social network sites have great relevance for research to be applied in diverse fields like marketing, politics, health or disaster management. Social network sites like Facebook and Twitter are now extensively used for conducting business, marketing products and services and collecting opinions and feedbacks regarding the same. Since data gathered from these sites regarding a product/brand are up-to-date and are mostly supplied voluntarily, it tends to be more realistic, massive and reflects the general public opinion. Its analysis on real time can lead to accurate insights and responding to the results sooner is undoubtedly advantageous than responding later.  In this paper, a cloud based system for real time targeted advertising based on tweet sentiment analysis is designed and implemented using the big data processing engine Apache Spark, utilizing its streaming library. Application is meant to promote cross selling and provide better customer support.
Volume: 7
Issue: 1
Page: 402-407
Publish at: 2017-02-01

An Improved Similarity Matching based Clustering Framework for Short and Sentence Level Text

10.11591/ijece.v7i1.pp551-558
M. John Basha , K.P. Kaliyamurthie
Text clustering plays a key role in navigation and browsing process. For an efficient text clustering, the large amount of information is grouped into meaningful clusters. Multiple text clustering techniques do not address the issues such as, high time and space complexity, inability to understand the relational and contextual attributes of the word, less robustness, risks related to privacy exposure, etc. To address these issues, an efficient text based clustering framework is proposed. The Reuters dataset is chosen as the input dataset. Once the input dataset is preprocessed, the similarity between the words are computed using the cosine similarity. The similarities between the components are compared and the vector data is created. From the vector data the clustering particle is computed. To optimize the clustering results, mutation is applied to the vector data. The performance the proposed text based clustering framework is analyzed using the metrics such as Mean Square Error (MSE), Peak Signal Noise Ratio (PSNR) and Processing time. From the experimental results, it is found that, the proposed text based clustering framework produced optimal MSE, PSNR and processing time when compared to the existing Fuzzy C-Means (FCM) and Pairwise Random Swap (PRS) methods.
Volume: 7
Issue: 1
Page: 551-558
Publish at: 2017-02-01

Study of Wind Turbine based Variable Reluctance Generator using Hybrid FEMM-MATLAB Modeling

10.11591/ijece.v7i1.pp1-11
Tariq Benamimour , Amar Bentounsi , Hind Djeghloud
Based on exhaustive review of the state of the art of the electric generators fitted to Wind Energy Conversion System (WECS), this study is focused on an innovative machine that is a Variable Reluctance Generator (VRG). Indeed, its simple and rugged structure (low cost), its high torque at low speed (gearless), its fault-tolerance (lowest maintenance), allow it to be a potential candidate for a small wind power application at variable wind speed. For better accuracy, a finite element model of a studied doubly salient VRG is developed using open source software FEMM to identify the electromagnetic characteristics such as linkage flux, torque or inductance versus rotor position and stator excitation. The obtained data are then transferred into  look-up tables of MATLAB/Simulink to perform various simulations. Performance of the proposed wind power system is analyzed for several parameters and results are discussed.
Volume: 7
Issue: 1
Page: 1-11
Publish at: 2017-02-01
Show 1429 of 1830

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