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

27,404 Article Results

Elastic Bunch Graph Matching Based Face Recognition Under Varying Lighting, Pose, and Expression Conditions

10.11591/ijai.v3.i4.pp177-182
Farooq Ahmad Bhat , M. Arif Wani
In this paper performance of elastic bunch graph matching (EBGM) for face recognition under variation in facial expression, variation in lighting condition and variation in poses are given. In this approach faces are represented by labelled graphs. Experimental results of EBGM on ORL, Yale B and FERET datasets are provided. Strong and weak features of EBGM algorithm are discussed.
Volume: 3
Issue: 4
Page: 177-182
Publish at: 2016-08-20

Automatic Exudates Detection in Diabetic Retinopathy Images

10.11591/ijai.v5.i2.pp45-54
H. Faouzi , Mohamed Fakir
Diabetic Retinopathy (DR) refers to the presence of typical retinal micro vascular lesions in persons with diabetics. When the disease is at the early state, a prompt diagnosis may help in preventing irreversible damages to the diabetic eye. If the exudates are closer to macula, then the situation is critical. Early detection can potentially reduce the risk of blind.  This paper proposes tool for the early detection of Diabetic Retinopathy using edge detection, algorithm kmeans in segmentation phase, invariant moments (Hu and Affine) and descriptor GIST in extraction phase. In the recognition phase, neural network is adopted. All tests are applied on database DIARETDB1.
Volume: 5
Issue: 2
Page: 45-54
Publish at: 2016-08-20

Prediction of Daily Network Traffic based on Radial Basis Function Neural Network

10.11591/ijai.v3.i4.pp145-149
Haviluddin Haviluddin , Imam Tahyudin
This paper presents an approach for predicting daily network traffic using artificial neural networks (ANN), namely radial basis function neural network (RBFNN) method. The data is gained from 21 – 24 June 2013 (192 samples series data) in ICT Unit Universitas Mulawarman, East Kalimantan, Indonesia. The results of measurement are using statistical analysis, e.g. sum of square error (SSE), mean of square error (MSE), mean of percentage error (MPE), mean of absolute percentage error (MAPE), and mean of absolute deviation (MAD). The results show that values are the same, with different goals that have been set are 0.001, 0.002, and 0.003, and spread 200. The smallest MSE value indicates a good method for accuracy. Therefore, the RBFNN model illustrates the proposed best model to predict daily network traffic.
Volume: 3
Issue: 4
Page: 145-149
Publish at: 2016-08-20

Expert System for Decision Support Division of Inheritance According to Islamic Law

10.11591/ijai.v5.i3.pp89-94
Adi Fitra Andikos , Gunawan Ali , Wulan Andang Purnomo
Develop an expert system as supporting legacy property distribution of decision which based on the Islamic law. This expert system expected can help everyone who need distribution value of legacy property by using distribution method based on the Islamic law. The legacy property value which will be distributed is legacy property after taken by the will if it was. And debt, corpse of administration cost. The distribution result is an percentage value for each heir who have right to get the property legacy after distribution process. Determination of nominal value of legacy property will not be count in this system. The user system can obtain nominal value of distribution property by multiplying the distribution percentage with whole value of legacy property. The result that taken form this expert system is output as information of heir group who has right to the legacy, and percentage value for each heir who has right to get the legacy. The inference method that used in this expert system is Forward Chaining Method. The method that used for system analysis and designing is Data Flow Oriented method by using Data Flow Diagram (DFD) tool. The database design is using Entity-Relationship Diagram (E-R Diagram) relation model.
Volume: 5
Issue: 3
Page: 89-94
Publish at: 2016-08-20

Environment Detection and Path Planning Using the E-puck Robot

10.11591/ijra.v5i3.pp151-160
Muhammad Saleem Sumbal
Automatic path planning is one of the most challenging problems confronted by autonomous robots. Generating optimal paths for autonomous robots are some of the heavily studied subjects in mobile robotics applications. This paper documents the implementation of a path planning project using a mobile robot in a structured environment. The environment is detected through a camera and then a roadmap of the environment is built using some algorithms. Finally a graph search algorithm called A* is implemented that searches through the roadmap and finds an optimal path for robot to move from start position to goal position avoiding obstacles
Volume: 5
Issue: 3
Page: 151-160
Publish at: 2016-08-20

Classification of Power Quality Events Using Wavelet Analysis and Probabilistic Neural Network

10.11591/ijai.v5.i1.pp1-12
Pampa Sinha , Sudipta Debath , Swapan Kumar Goswami
Power quality studies have become an important issue due to widespread use of sensitive electronic equipment in power system. The sources of power quality degradation must be investigated in order to improve the power quality. Switching transients in power systems is a concern in studies of equipment insulation coordination. In this paper a wavelet based neural network has been implemented to classify the transients due to capacitor switching, motor switching, faults, converter and transformer switching. The detail reactive powers for these five transients are determined and a model which uses the detail reactive power as the input to the Probabilistic neural network (PNN) is set up to classify the above mentioned transients. The simulation has been executed for an 11kv distribution system. With the help of neural network classifier, the transient signals are effectively classified.
Volume: 5
Issue: 1
Page: 1-12
Publish at: 2016-08-20

Development of an Efficient Face Recognition System Based on Linear and Nonlinear Algorithms

10.11591/ijai.v5.i2.pp80-88
Araoluwa Simileolu Filani , Adebayo Olusola Adetunmbi
This paper presents appearance based methods for face recognition using linear and nonlinear techniques. The linear algorithms used are Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). The two nonlinear methods used are the Kernel Principal Components Analysis (KPCA) and Kernel Fisher Analysis (KFA). The linear dimensional reduction projection methods encode pattern information based on second order dependencies. The nonlinear methods are used to handle relationships among three or more pixels. In the final stage, Mahalinobis Cosine (MAHCOS) metric is used to define the similarity measure between two images after they have passed through the corresponding dimensional reduction techniques. The experiment showed that LDA and KFA have the highest performance of 93.33 % from the CMC and ROC results when used with Gabor wavelets. The overall result using 400 images of AT&T database showed that the performance of the linear and nonlinear algorithms can be affected by the number of classes of the images, preprocessing of images, and the number of face images of the test sets used for recognition.
Volume: 5
Issue: 2
Page: 80-88
Publish at: 2016-08-20

The Cheapest Shop Seeker : A New Algorithm For Optimization Problem in a Continous Space

10.11591/ijai.v5.i3.pp119-126
Peter Bamidele Shola
In this paper a population-based meta-heuristic algorithm for optimization problems in a continous space is presented.The algorithm,here called cheapest shop seeker is modeled after a group of shoppers seeking to identify the cheapest shop (among many available) for shopping. The  algorithm was tested on many benchmark functions with the result  compared with those from some other methods. The algorithm appears to  have a better  success  rate of hitting the global optimum point  of a function  and of the rate of convergence (in terms of the number of iterations required to reach the optimum  value) for some functions  in spite  of its simplicity.
Volume: 5
Issue: 3
Page: 119-126
Publish at: 2016-08-20

Natural Immune System Response As Complexe Adaptive System Using Learning Fuzzy Cognitive Maps

10.11591/ijai.v5.i3.pp95-104
Ahmed Tlili , Salim Chikhi
In the Natural Immune Systems NIS, adaptive and emergent behaviors result from the behaviors of each cell and their interactions with other cells and environment. Modeling and Simulating NIS requires aggregating these cognitive interactions between the individual cells and the environment. In last years the Fuzzy Cognitive Maps (FCM) has been shown to be a convenient tool for modeling, controlling and simulating complex systems. In this paper,  a new type of learning fuzzy cognitive maps (LFCM) have been proposed as an extension of traditional FCM for modeling complex adaptive system is described. Our approach is summarized in two major ideas: The first one is to increase the reinforcement learning capabilities of the FCM by using an adaptation of Q-learning technique and the second one is to foster diversity of concept's states within the FCM by adopting an IF-THEN rule based system. Through modeling and simulating response of natural immune system, we show the effectiveness of the proposed approach in modeling CASs.
Volume: 5
Issue: 3
Page: 95-104
Publish at: 2016-08-20

Effective Analysis of Lung Infection using Fuzzy Rules

10.11591/ijai.v5.i2.pp55-63
Navneet Walia , Harsukhpreet Singh , Anurag Sharma
Soft Computing is conglomerate of methodologies which works together and provides an ability to make a decision from reliable data or expert’s experience. Nowadays different types of soft computing techniques such as neural network, fuzzy logic, genetic algorithm and hybrid system are largely used in medical areas. In this paper, an algorithm for analysis of lung infection is presented. The main focus is to develop system architecture to find probable disease stage patient may have. Severity level of disease is determined by using rule base method. The algorithm uses an output of Rulebase entered by the user to determine a level of infection.Soft Computing is conglomerate of methodologies which works together and provides an ability to make decision from reliable data or expert’s experience. Nowadays different types of soft computing techniques such as neural network, fuzzy logic, genetic algorithm and hybrid system are largely used in medical areas. In this paper, algorithm for analysis of lung infection is presented. The main focus is to develop system architecture to find probable disease stage patient may have. Severity level of disease is determined by using rule base method. The algorithm uses output of Rulebase entered by user to determine level of infection.
Volume: 5
Issue: 2
Page: 55-63
Publish at: 2016-08-20

Artificial Intelligence a Threat

10.11591/ijai.v5.i3.pp117-118
Abhedya Saini
Research in AI has built upon the tools and techniques of many different disciplines.Study in the artificial intelligence has given rise to rapidly growing technology known as expert system. Rapid development in this field made human more dependent on this technology. More advancement will lead to side effects of that technology because after a certain point, everything is harmful.
Volume: 5
Issue: 3
Page: 117-118
Publish at: 2016-08-20

An SVD based Real Coded Genetic Algorithm for Graph Clustering

10.11591/ijai.v5.i2.pp64-71
Parthajit Roy , Jyotsna Kumar Mandal
This paper proposes a novel graph clustering model based on genetic algorithm using a random point bipartite graph. The model uses random points distributed uniformly in the data space and the measurement of distance from these points to the test points have been considered as proximity. Random points and test points create an adjacency matrix. To create a similarity matrix, correlation coefficients are computed from the given bipartite graph. The eigenvectors of the singular value decomposition of the weighted similarity matrix are considered and the same are passed to an elitist GA model for identifying the cluster centers. The model has been tasted with the standard datasets and the performance has been compared with existing standard algorithms.
Volume: 5
Issue: 2
Page: 64-71
Publish at: 2016-08-20

Rule Based and Expectation Maximization algorithm for Arabic-English Hybrid Machine Translation

10.11591/ijai.v5.i2.pp72-79
Arwa Hatem Alqudsi , Nazlia Omar , Rabha W. Ibrahim
It is practically impossible for pure machine translation approach to process all of translation problems; however, Rule Based Machine Translation and Statistical Machine translation (RBMT and SMT) use different architectures for performing translation task. Lexical analyser and syntactic analyser are solved by Rule Based and some amount of ambiguity is left to be solved by Expectation–Maximization (EM) algorithm, which is an iterative statistic algorithm for finding maximum likelihood. In this paper we have proposed an integrated Hybrid Machine Translation (HMT) system. The goal is to combine the best properties of each approach. Initially, Arabic text is keyed into RBMT; then the output will be edited by EM algorithm to generate the final translation of English text. As we have seen in previous works, the performance and enhancement of EM algorithm, the key of EM algorithm performance is the ability to accurately transform a frequency from one language to another. Results showing that, as proved by BLEU system, the proposed method can substantially outperform standard Rule Based approach and EM algorithm in terms of frequency and accuracy. The results of this study have been showed that the score of HMT system is higher than SMT system in all cases. When combining two approaches, HMT outperformed SMT in Bleu score.
Volume: 5
Issue: 2
Page: 72-79
Publish at: 2016-08-20

Design of Observer-Based Robust Power System Stabilizers

10.11591/ijece.v6i5.pp1956-1966
Hisham M. Soliman , Mahmoud Soliman
Power systems are subject to undesirable small oscillations that might grow to cause system shutdown and consequently great loss of national economy. The present manuscript  proposes two  designs for observer-based robust power system stabilizer (PSS) using Linear Matrix Inequality (LMI) approach to damp such oscillations. A model to describe power system dynamics for different loads is derived in the norm-bounded form. The first controller design is based on the derived model to achieve  robust stability against load variation. The design is based on a new Bilinear matrix inequality (BMI) condition. The BMI optimization  is solved interatively in terms of Linear Matrix Inequality (LMI) framework. The condition contains a symmetric positive definite full matrix to be obtained, rather than the commonly used block diagonal form. The difficulty in finding a feasible solution is thus alleviated. The resulting LMI is of small size, easy to solve. The second PSS design shifts the closed loop poles in a desired region so as to achieve a favorite  settling time and damping ratio via a non-iterative solution to a set of LMIs.  The approach provides a systematic way to design a robust output feedback PSS which  guarantees good dynamic performance for different loads. Simulation results based on single-machine and multi-machine power system models verify the ability of the proposed PSS to satisfy control objectives for a wide range of load conditions.
Volume: 6
Issue: 5
Page: 1956-1966
Publish at: 2016-08-11

Development of a Measuring Sensory System Based on LabVIEW for Determining Elastic Proprieties of Solid Materials

10.11591/ijece.v6i5.pp2096-2105
Zakaryae Ezzouine , Abdelrhani Nakheli
This article develops also a measure and prototype to allow the acquisition of real time data for display, analysis, control and storage with a proposed test program for determining the model parameters. The aim is to be able to measure, and apply moment to a specimen, and collect data from the resulting deformation in the material. At the same time, the reliability of this test system has been proved by precision analysis and data processing for a simple test validation (metal wire). The force-deformation curves of solids materials in this tensile test are measured accurately in real time, to obtain the values of solid materials mechanical property parameters, The minimal change in length of the test Specimen that can be resolved by this system is 1µm, which yields the sensitivity comprised between 10-4µm and 10-5 µm. Based on the experience that compressive tensile test have the smallest statistical scatter and that they are simplest to carry out. The measuring device can improve the measuring efficiency and accuracy distinctly while has advantages of simple configuration, low cost and high stability.
Volume: 6
Issue: 5
Page: 2096-2105
Publish at: 2016-08-11
1 2 3
...
1826 1827
Show 1467 of 1827

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