Contact Email

IAES International Journal of Artificial Intelligence (IJ-AI)



IAES International Journal of Artificial Intelligence (IJ-AI), ISSN/e-ISSN 2089-4872/2252-8938 publishes articles in the field of artificial intelligence (AI). The scope covers all artificial intelligence (AI) and machine learning (ML) areas and theirs applications in the following topics: neural networks; fuzzy logic; simulated biological evolution algorithms (like genetic algorithm, ant colony optimization, etc); reasoning and evolution; intelligence applications; computer vision and speech understanding; multimedia and cognitive informatics, data mining and machine learning tools, heuristic and AI planning strategies and tools, computational theories of learning; technology and computing (like particle swarm optimization); intelligent system architectures; knowledge representation; bioinformatics; natural language processing; multiagent systems; supervised learning; unsupervised learning; deep learning; big data and AI approaches; reinforcement learning; and learning with generative adversarial networks; etc

Ilamathi P, V. Selladurai, K. Balamurugan,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 1: March 2012 , pp. 11-18

A predictive modelling of nitrogen oxides emission from a 210 MW coal fired thermal power plant with combustion parameter optimization is proposed. The oxygen concentration in flue gas, coal properties, coal flow, boiler load, air distribution scheme, flue gas outlet temperature and nozzle tilt were studied. The parametric field experiment data were used to build artificial neural network (ANN). The coal combustion parameters were used as inputs and nitrogen oxides as output of the model. The predicted values of the ANN model for full load condition were verified with the actual values. The optimum level of input operating conditions for low nitrogen oxides emission was determined by simulated annealing (SA) approach. The result indicates that the combined approach could be used for reducing nitrogen oxides emission.DOI:

Nader Jamali Soufi Amlashi,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 1: March 2012 , pp. 31-44

This paper was written to demonstrate importance of a fuzzy logic controller in act over conventional methods with the help of an experimental model. Also, an efficient simulation model for fuzzy logic controlled DC motor drives using Matlab/Simulink is presented. The design and real-time implementation on a microcontroller presented. The scope of this paper is to apply direct digital control technique in position control system. Two types of controller namely PID and fuzzy logic controller will be used to control the output response. The performance of the designed fuzzy and classic PID position controllers for DC motor is compared and investigated. Digital signal Microcontroller ATMega16 is also tested to control the position of DC motor. Finally, the result shows that the fuzzy logic approach has minimum overshoot, and minimum transient and steady state parameters, which shows the more effectiveness and efficiency of FLC than conventional PID model to control the position of the motor. Conventional controllers have poorer performances due to the non-linear features of DC motors like saturation and friction.DOI:

Kumaran Kumar. J, Kailas A,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 1: March 2012 , pp. 25-30

In this paper, the prediction of future stock close price of SENSEX & NSE stock exchange is found using the proposed Hybrid ANN model of Functional Link Fuzzy Logic Neural Model. The historic raw data’s of SENSEX & NSE stock exchange has been pre-processed to the range of (0 to 1). After pre-processing the inputs and forwarded to functional expansion function to perform neural operation. The activation function of neuron has fuzzy sets in order to show the future close price range of SENSEX & NSE stock exchange. The model is trained with the pre-processed historic data’s of stock exchange and the prediction rate (Performance & Error rate) of the Proposed Hybrid ANN model of Functional Link Fuzzy Logic Neural Model is calculated at the testing phase using the performance metrics (MAPE & RMSE).DOI:

Sumit Goyal, Gyanendra Kumar Goyal,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 1: March 2012 , pp. 19-24

Cascade multilayer artificial neural network (ANN) models were developed for estimating the shelf life of processed cheese stored at 7-8oC.Mean square error , root mean square error,coefficient of determination and nash - sutcliffo coefficient were applied in order to compare the prediction ability of the developed models.The developed model with a combination of 5à16à16à1 showed excellent agreement between the actual and the predicted data , thus confirming that multilayer cascade models are good in estimating the shelf life of processed cheese.DOI:

H. Omranpour, M. Ebadzadeh, S. Shiry, S. Barzegar,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 1: March 2012 , pp. 1-10

In this paper, a technical approach to particle swarm optimization method is presented. The main idea of the paper is based on local extremum escape. A new definition has been called the worst position. With this definition, convergence and trapping in extremumlocal be prevented and more space will be searched. In many cases of optimization problems, we do not know the range that answer is that.In the results of examine on the benchmark functions have been observed that when initialization is not in the range of the answer, the other known methods are trapped in local extremum. The method presented is capable of running through it and the results have been achieved with higher accuracy.DOI:

Farhad Gorbanzadeh, Ali Asghar Pourhaji Kazem,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 2: June 2012 , pp. 54-62

Nowadays, since grid has been turned to commercialization, using economic methods such as auction methods are appropriate for resource allocation because of their decentralized nature. Combinatorial double auction has emerged as a major model in the economy and is a good approach for resource allocation in which participants of grid, give their requests once to the combination of resources instead of giving them to different resources multiple times. One problem with the combinatorial double auction is the efficient allocation of resources to derive the maximum benefit. This problem is known as winner determination problem (WDP) and is an NP-hard problem. So far, many methods have been proposed to solve this problem and genetic algorithm is one of the best ones. In this paper, two types of hybrid genetic algorithms were presented to improve the efficiency of genetic algorithm for solving the winner determination problem. The results showed that the proposed algorithms had good efficiency and led to better answers. DOI:

SeyedElyar Hashemseresht, Ali Asghar Pourhaji Kazem,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 2: June 2012 , pp. 45-53

Nowadays, with the increasing variety of computer systems, resource discovery in the Grid environment has been very important due to their applications; thus, offering optimal and dynamic algorithms for discovering resources in which users need a short period is an important task in grid environments.One of the methods used in resource discovery in grid is to use routing tables RDV (resource distance vector) in which the resources are based on certain criteria clustering and the clusters form a graph. In this way, some information about the resources is stored in RDV tables. Due to the environmental cycle in the graph, there are some problems; for example there are multiple paths to resources, most of which are repeated. Also, in large environments, due to the existence of many neighbors, updating the graph is time-consuming. In this paper, the structure of RDV was presented as a binary tree and these two methods (RDV graph-algorithm and RDVBT) were compared. Simulation results showed that, as a result of converting the structure to a binary tree, much better results were obtained for routing time, table updating time and number of successful requests; also the number of unsuccessful requests was reduced.DOI: 

Ragavan Saravanan,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 2: June 2012 , pp. 73-78

This paper describes how we design a lighting control system including hardware and software. Hardware includes Dimmer with relays Bulb light sensing circuit, control circuit, and 8255 expanding I/O circuit, PC, and bulb.   Sensing circuit uses photo-resistance component to sense the environmental light and then transmit the signal of the lightness to the computer through an 8-bit A/D converter 0804.  The control circuit applies reed relay in digital control way to adjust the variable resistor value of the traditional dimmer.  Software incorporates LABVIEW graph- ical programming language and MATLAB Fuzzy Logic Toolbox to design the light fuzzy controller.  The rule-base of the fuzzy logic controller either for the single input single output (SISO) system or the double inputs single output (DISO) system is developed and compared based on the op- eration of the bulb and the light sensor.  The control system can dim the bulb automatically according to the environmental light.   It can be applied to many fields such as control of streetlights and lighting control of car’s headlights and it is possible to save energy by dimming the bulb.  Experimental results show that the fuzzy controller with the DISO system can make bulb response faster than with the SISO system under sudden change of environmental light.DOI:

Adnan Tawafan, Marizan Bin Sulaiman, Zulkifilie Bin Ibrahim,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 2: June 2012 , pp. 63-72

High impedance fault (HIF) is abnormal event on electric power distribution feeder which does not draw enough fault current to be detected by conventional protective devices. The algorithm for HIF detection based on the amplitude ratio of second and odd harmonics to fundamental is presented. This paper proposes an intelligent algorithm using an adaptive neural- Takagi Sugeno-Kang (TSK) fuzzy modeling approach based on subtractive clustering to detect high impedance fault. It is integrating the learning capabilities of neural network to the fuzzy logic system robustness in the sense that fuzzy logic concepts are embedded in the network structure. It also provides a natural framework for combining both numerical information in the form of input/output pairs and linguistic information in the form of IF–THEN rules in a uniform fashion. Fast Fourier Transformation (FFT) is used to extract the features of the fault signal and other power system events. The effect of capacitor banks switching, non-linear load current, no-load line switching and other normal event on distribution feeder harmonics is discussed. HIF and other operation event data were obtained by simulation of a 13.8 kV distribution feeder using PSCAD. The results show that the proposed algorithm can distinguish successfully HIFs from other events in distribution power systemDOI:

Nazario D. Ramirez-Beltran, Joan Manuel Castro, Harry Rodriguez,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 2: June 2012 , pp. 91-102

The projection algorithm to classify tissues with a large number of genes and a small number of microarrays is proposed.The algorithm is based on the angle formed by two vectors in the n-dimensional space, and takes advantages of the geometrical projection principle.The properties of known tissues can be used to train the algorithm and distinguish between the cancer and normal gene expressions.The gene’s percentiles from an independent data set can be used to create a third vector, which is projected into the previously trained vectors to classify the third vector in one of the two populations, cancer or normal population.The proposed algorithm was implemented to detect cervical cancer in a microarray data set, which contains 8 normal and 25 cancerous tissues, which were randomly selected one thousand of times using a combinatory strategy.The algorithm was compared with three existing algorithms that have been used to solve the microarray classification problem: Fisher discriminate function, logistic regression, and artificial neural networks.Results show that the proposed algorithm outperformed the selected algorithmsDOI:

Mortaza Abbaszadeh, Saeed Saeedvand, Hamid Asbagi Mayani,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 2: June 2012 , pp. 79-90

Scheduling problem is one of the Non-deterministic Polynomial (NP) problems. This means that using a normal algorithm to solve NP problems is so time-consuming a process (it may take months or even years with available equipment), and thus such an algorithm is regarded as an impracticable way of dealing with NP problems. The method of Memetic Algorithm presented in this paper is different from other available algorithms. In this algorithm the problem of a university class Scheduling is solved through applying a new chromosome structure, modifying the normal genetic methods and adding a local search, which is claimed to considerably improve the solution. We included the teacher, class and course information with their maximal constraints in the proposed algorithm, and it produced an optimized scheduling table for a weekly program of the university after creating the initial population of chromosomes and running genetic operators. The results of the study show a high efficiency for the proposed algorithm compared with other algorithms considering maximum Constraints.DOI:

Vaibhav Godbole,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 3: September 2012 , pp. 103-111

In order to gather information more efficiently, wireless sensor networks are partitioned into clusters. The most of the proposed clustering algorithms do not consider the location of the base station. This situation causes hot spots problem in multi-hop wireless sensor networks. In this paper, we analyze a fuzzy clustering algorithm which aims to prolong the lifetime of wireless sensor networks. This algorithm adjusts the cluster-head radius considering the residual energy and the distance to the base station parameters of the sensor nodes. This helps decreasing the intra-cluster work of the sensor nodes which are closer to the base station or have lower battery level. In this paper fuzzy logic is utilized for handling the uncertainties in cluster-head radius estimation. We compare this algorithm with LEACH according to first node dies, half of the nodes alive and energy-efficiency metrics. Our simulation results show that the fuzzy clustering approach performs better than LEACH. Therefore, the fuzzy clustering algorithm is a stable and energyefficient clustering algorithm.DOI:

Endro Yulianto, Adhi Susanto, Thomas Sri Widodo, Samekto Wibowo,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 3: September 2012 , pp. 139-148

Brain Computer Interface (BCI) refers to a system designed to translate the brain signal in controlling a computer application.  The most widely used brain signal is electroencephalograph (EEG) for using the non-invasive method, and having a quite good resolution and relatively affordable equipments. This research purposively is to obtain the characteristics of EEG signals using the motor movement of “turn right” and “turn left” that is by moving the simulation of steering wheel. The characteristic of signal obtained is subsequently used as a reference to create a new type of wavelet for classification. The signal processing, including a 4 – 20 Hz bandpass filter, signal segmentation in 1 to 2 seconds after stimuli and signal correlation,  is used to obtain the characteristic of EEG signal; namely Event–Related Synchronization /Desynchronization (ERS/ERD). The result of test data classification to two new types of wavelet shows that each volunteer has a higher correlation value towards the new type of wavelet that has been designed with various wavelet scales for each individuals.DOI:

Vimal Nayak, Haresh A. Suthar, Jagrut Gadit,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 3: September 2012 , pp. 112-120

Evolutionary algorithm is a stochastic search method that mimics the natural biological evolution and the social behavior of species. Artificial bee colony algorithm is also a kind of evolutionary algorithm which was proposed by Dervis karaboga in 2005.Such algorithms have been developed to arrive at near-optimum solutions of multimodal optimization problems, which may not be possible with traditional algorithms. This paper describes implementation of ABC algorithm on complex benchmark functions like rastrigin, rosenbrock; sphere and schwefel the analysis of the performance of ABC algorithm were compared for the optimization of above benchmark functions with Partical Swarm Optimization (PSO). The ABC algorithm was successfully implemented in software tool ‘c’.DOI:

Ouadfel Salima, Abdelmalik Taleb-Ahmed, Batouche Mohamed,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 3: September 2012 , pp. 149-160

Fuzzy c-means algorithm (FCM) is one of the most used clustering methods for image segmentation. However, the conventional FCM algorithm presents some limits like its sensitivity to the noise because it does not take into consideration contextual information and its convergence to local minimum since it is based on a gradient descent method. In this paper, we present a new spatial fuzzy clustering algorithm optimized by the Artificial Bee Colony (ABC) algorithm. ABC-SFCM has two major characteristics. First it tackles better noisy image segmentation by making use of the spatial local information into the membership function. Secondly, it improves the global performance by taking advantages of the global search capability of ABC. Experiments with synthetic and real images show that ABC-SFCM is robust to noise compared to other methods.DOI:

Tariq Mahmood, M. Shahid Farid,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 4: December 2012 , pp. 193-200

Task scheduling problems are involved in almost every field of life from industry, where scheduling of employees on different machines with different shifts with respect to various constraints, to universities where scheduling involved in time tabling of classes and faculty, in examination scheduling, laboratory scheduling, staff scheduling and so on. Scheduling problem involves scheduling of different resources under various constraints to attain optimal results. In this paper we present a multi-agent based solution to Task Scheduling Problem (TSP) in university environment. It involves two main scheduling  problmes; first, time tabling probelm (TTP) and second  examination scheduling problem (ESP). In time tabling problem, a time table of classes is consturcted subject to different constraints; like rooms, subjects, teachers, degrees and semester with in a degree program. in examination scheduling problem is central to scheduling issue to every university. In ESP, the schedule of the examination of different courses of different degrees invigilated by different faculty members each with his/her availability constraints, is carried out. The problem is even worse when students of different degrees takes a shared course and when there are add-drops students in a course. In this case, the complexity of the scheduling problem doubles, now scheduling has to done with respect to the constraints of faculty, degree and also to  decrease the number of clashes in examination. An agent based solution to TSP is proposed in this paper which is also implemented and tested over different scenarios and optimal results are achieved in negligible amount of time.DOI:

Rajashree Sasamal, Rabindra Kumar Shial,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 4: December 2012 , pp. 182-192

Granular Computing is not only a computing model for computer centered problem solving, but also a thinking model for human centered problem solving.Some authors have presented the structure of such kind models and investigated various perspectives of granular computing from different application  point of views.  In this paper we discuss the archeitectue of Granular computing  models, strategies, and applications. Especially, the perspectives of granular computing in various aspects as data mining and  phases of software engineering are presented, including recquirement specification system analysis and design, algorithm design,structured programming,software tesing.AI is used for measuring the three perspective  of Granular Computing model. Here we have discovered the patterns in sequence of events has been an area  of active research in AI. However, the focus in this body of work is on discovering the rule underlying the generation of a given sequence in order to be able to predict a plausible sequence continuation ( the rule to predict what number will come next, given a sequence of numbers).DOI:

Zahra Pooranian, Mohammad Shojafar, Bahman Javadi,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 4: December 2012 , pp. 171-181

The inherent dynamicity in grid computing has made it extremely difficult to come up with near-optimal solutions to efficiently schedule tasks in grids. Task Scheduling plays crucial role in Grid computing. It is a challengeable issue among scientists to achieve better results especially in makespan based on various AI methods. Nowadays, non deterministic algorithms provide better results for these tasks. In this study the task scheduling problem in Grid computing environments has been addressed. In this paper, Queen Bee Algorithm is used for resolving scheduling problem and the obtained results are compared with several Meta–heuristic Algorithms which are developed to solve the problem. As it illustrated, queen bee algorithm is declined considerably makespan and execution time parameters rather than others in different states.DOI:

Sameerchand Pudaruth, Bibi Feenaz Bhaukaurally, Mohammad Haydar Ally Didorally,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 4: December 2012 , pp. 201-213

In this paper, we give an overview of how Sega lyrics, in Mauritian Creole language, are being written by Mauritian Lyricists and a tool which has been developed to automatically generate Sega lyrics. Research shows that song writing is not always an easy task. Someone cannot be told exactly how to write lyrics, but that does not mean there are not ways in which he/she can learn to do it better. In-depth analysis has been carried out on Natural Language Processing, Text Mining, Machine Learning and existing Sega lyrics to consolidate the foundation of the project. Interviews have been done with a domain expert to learn the process of conventional song writing. Thus a tool, Paroles Sega Morisien, was developed. Paroles Sega Morisien enables users to generate Sega lyrics from randomly selected Mauritian Creole keywords. It is the first time that such a tool has been developed. An evaluation, consisting of a comparability study, was carried out to compare existing lyrics against lyrics generated by the tool. The result obtained was favorable.DOI:

Abeer Mohamed El-korany, Salma Mokhtar Khatab,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 3: September 2012 , pp. 127-138

Knowledge sharing is vital in collaborative work environments.People working in the same environment aid better communication due to sharing information and resources within a contextual knowledge structure constructed based on their scope. Social networks play important role in our daily live as it enables people to communicate, and share information. The main idea of social network is to represent a group of users joined by some kind of voluntary relation without considering any preference. This paper proposes a social recommender system that follows user’s preferences to provide recommendation based on the similarity among users participating in the social network. Ontology is used to define and estimate similarity between users and accordingly being able to connect different stakeholders working in the community field such as social associations and volunteers.This approach is based on integration of major characteristics of content-based and collaborative filtering techniques. Ontology plays a central role in this system since it is used to store and maintain the dynamic profiles of the users which is essential for interaction and connection of appropriate knowledge flow and transaction.DOI:

D. Sridhar, I. V. Murali Krishna,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 4: December 2012 , pp. 161-170

In this paper, a new Face Recognition method based on Two Dimensional Discrete Cosine Transform with Linear Discriminant Analysis (LDA) and K Nearest neighbours (KNN) classifier is proposed. This method consists of three steps, i) Transformation of images from special to frequency domain using Two dimensional discrete cosine transform ii) Feature extraction using Linear Discriminant Analysis and iii) classification using K Nearest Neighbour  classifier. Linear Disceminant Analysis searches the directions for maximum discrimination of classes in addition to dimensionality reduction. Combination of Two Dimensional   Discrete Cosine transform and Linear Discriminant Analysis is used for improving the capability of Linear Discriminant Analysis when few samples of images are available. K Nearest Neighbour classifier gives fast and accurate classification of face images that makes this method useful in online applications. Evaluation was performed on two face data bases. First database of 400 face images from AT&T face database, and the second database of thirteen students are taken. The proposed method gives fast and better recognition rate when compared to other classifiers. The main advantage of this method is its high speed processing capability and low  computational requirements in terms of both speed and memory utilizations.DOI:

Urvashi Rahul Saxena, S.P Singh,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 3: September 2012 , pp. 121-126

Multi-Party Security System is an improvised version of various security systems available using Artificial Neural Networks (ANN’s) as an Intelligent Agent for Intrusion Detection. This Paper focuses how inputs can be preserved to serve as a measure for securing communication protocol between two parties using privacy protocols at the hidden layer of Multi-layer Perceptron model. Various neural network structures are observed for evaluating the optimal network considering the number of hidden layers. Results depict that the generated system is capable of classifying records with about 90% of accuracy when two hidden layers are engulfed and the accuracy reduces to 87% with one hidden layer under observation.DOI:

Anis Charrada,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 1, No 4: December 2012 , pp. 214-224

In this paper, we propose a robust highly selective nonlinear channel estimator for Multiple -Input Multiple-Output (MIMO) Orthogonal Frequency Division Multiplexing (OFDM) system using complex Support Vector Machines Regression (SVR) and applied to Long Term Evolution (LTE) downlink under high mobility conditions .The new method uses the information provided by the pilot signals to estimate the total frequency response of the channel in two phases: learning phase and estimation phase. The estimation algorithm makes use of the reference signals to estimate the total frequency response of the highly selective multipath channel in the presence of non-Gaussian impulse noise interfering with pilot signals. Thus, the algorithm maps trained data into a high dimensional feature space and uses the Structural Risk Minimization (SRM) principle to carry out the regression estimation for the frequency response function of the highly selective channel. The simulations show the effectiveness of the proposed method which has good performance and high precision to track the variations of the fading channels compared to the conventional LS method and it is robust under high mobility conditions.DOI:

Jayamala Kumar Patil, Raj Kumar,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 1: March 2013 , pp. 36-42

This paper  presents a Content Based Image Retrieval (CBIR)method for plant leaf image retrieval, intended for identification of leaf diseases. We  used color features to extract the contents of leaf images. The color features are extracted using first three color moments.  For similarity measurement median value of moment feature vectors is used. The method is studied for three different color spaces i.e. RGB, HSV & YCbCr. The experimental result shows that HSV color space provides better results for plant leaf disease retrieval.DOI:

Omar Benarchid, Naoufal Raissouni,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 1: March 2013 , pp. 43-50

Many fields of artificial intelligence have been developed such as computational intelligence and machine learning involving neural networks, fuzzy systems, genetic algorithms, intelligent agents and Support Vector Machines (SVM). SVM is a machine learning methodology with great results in image classification. In this paper, we present the potential of SVMs to automatically extract buildings in suburban area using Very High Resolution Satellite (VHRS) images. To achieve this goal, we use object based approach: Segmentation before classification in order to create meaningful image objects using color features. In the first step, we form objects with the aid of mean shift clustering algorithm. Then, SVM classifier was used to extract buildings. The proposed method has been applied on a suburban area in Tetuan city (Morocco) and 83.76% of existing buildings have been extracted by only using color features. This result can be improved by adding other features (e.g., spectral, texture, morphology and context).DOI:

Fakir Mohamed Fakir,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 1: March 2013 , pp. 20-26

In this work we present a method for the recognition of Arabic printed script. The major problem of the automatic reading of cursive writing is a segmentation of script to isolate characters. The recognition process consists of four phases: Preprocessing, segmentation, feature extraction and the recognition.In the preprocessing, the image is scanned and smoothed. The correction of skew lines is done by using Hough transform . In the second phase, the text is segmented into lines, words or parts of words and each word into characters based on the principle of projection of the histogram. Features such as:  density, profile, Hu moments and histogram are used to classifier the characters based on the Neural network.DOI: 

Ravi kumar Venkatesh,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 1: March 2013 , pp. 27-35

In a common law system and in a country like India, decisions made by judges are significant sources of application and understanding of law. Online access to the Indian Legal Judgments in the digital form creates an opportunities and challenges to the both legal community and information technology researchers. This necessitates organizing, analyzing, retrieving relevant judgment and presenting it in a useful manner to the legal community for quick understanding and for taking necessary decision pertaining to a present case. In this paper we propose an approach to cluster legal judgments based on the topics obtained from hierarchical Latent Dirichlet Allocation (hLDA) using similarity measure between topics and documents and to find the summarization of each document using the same topics. The developed topic based clustering model is capable of grouping the legal judgments into different clusters and to generate summarization in effective manner compare to our previous [1] approach.DOI:

Nazri Mohd Nawi,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 1: March 2013 , pp. 7-19

The diagnosis of defective castings has always been a centre of attention in the manufacturing industry. This is mainly because the cause and effect relationship in a casting process is complex and non-linear. Furthermore, a large number of parameters are needed to be coordinated with each other in an optimal way to minimise the occurrence of defective castings. An intelligent diagnosis system is needed to diagnose effectively the causal representation and also justify its diagnosis. A previous method, known as the Knowledge Hyper-surface method which used Lagrange Interpolation polynomials has gained more popularity in learning cause and effect analysis in casting processes. The current method show that the belief value of the occurrence of cause with respect to the change in the belief value in the occurrence of effect can be modeled by linear, quadratic or cubic relationships and the method retained the advantages of neural networks and overcomes their limitations in learning the input-output mapping function in the presence of noisy, limited and sparse data. However, the methodology was unable to model exponential increase/decrease in belief values in cause and effect relationships. This paper proposed an enhancement to the current Knowledge Hyper-surface method by introducing midpoints in the existing shape formulation which further constrains the shape of the Knowledge hyper-surfaces to model an exponential rise in belief values but without exposing the dataset to the limitations of ‘over fitting’. The ability of the proposed method to capture the exponential change in the belief variation of the cause when the belief in the effect is at its minimum is compared to the current method on real casting data.DOI:

Driss Naji, Fakir Mohamed Fakir, O. Bencharef, B. Bouikhalene, A. Razouk,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 1: March 2013 , pp. 1-6

In this paper, we present a new approach to object to recognition based on the combination of Zernike moments, descriptors Gist and PCA pair wise applied to color images. The recognition of objects are based on two approaches of classification the first use neural networks (NN) for learning stage and gratitude as well to the Support Vector Machines (SVM). The experimental results showed that the recognition by SVM is better than NN. We illustrate the proposed method on color images, including objects from the database COIL-100.DOI:

Mohammad Sarvi, Masoud Safari,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 2: June 2013 , pp. 81-89

The batteries models found in the literature are based mainly on mathematical descriptions of physical, chemical, and electrochemical properties which are difficult to determine. This paper presents new fuzzy based model for Nickel Cadmium (Ni-Cd) batteries. The main advantage of the proposed models is that, the proposed model is able to predict battery output voltage without knowledge of numerous factors. Inputs of the proposed model are battery current and state of charge while battery voltage is selected as the output. To check the accuracy of the proposed models, simulations results are compared with the measured battery data at different charge current as well as many other battery models for a 7Ah, size F, Ni-Cd battery. Simulated shows good agreements with measured data. The advantage of fuzzy model is that for modeling by fuzzy method experimental data isn’t needed. The proposed models can apply for modeling of other batteries types.DOI:

Soe Lai Phyue,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 3: September 2013 , pp. 107-116

A knowledge resource is the central repository of data for all Natural Language Processing (NLP) applications and development of NLP applications mostly depend on coverage of knowledge resources. The multipurpose Myanmar Language Lexico-conceptual Knowledge Resource (ML2KR) and Myanmar function tagged corpus were developed as initial resources by using semiautomatic approach. ML2KR consists of Myanmar WordNet, Myanmar English bilingual computational lexicon and morphological processor. Myanmar language is morphologically rich and agglutinative language. Therefore, it is usually required to segment Myanmar texts prior to further processing. Segmentation has two main problems, word ambiguity that more than one meaning and unknown word occurrence that a word does not have in the lexicon. In this paper, we address on the unknown word occurrence issue. To detect the new unrestricted character patterns of words, character based parsing syntax analyzer is built by using Context Free Grammar (CFG). Firstly, unknown words are considered as a Name by Name Entity Recognition with forward and backward rule based approach. If the name does not agree with syntax analyzer, all possible unknown words are verified to update the lexicon and Myanmar WordNet.DOI:

Hoda Waguih,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 2: June 2013 , pp. 99-106

Denial of Service (DoS) attacks constitutes one of the major threats and among the hardest security problems currently facing computer networks and particularly the Internet. A DoS attack can easily exhausts the computing and communication resources of its victim within a short period of time. Because of the seriousness of the problem many defense mechanisms have been proposed to fight these attacks. In this paper, we propose an approach that detects DoS attacks using data mining classification techniques. The approach is based on classifying “normal” traffic against “abnormal” traffic in the sense of DoS attacks. The paper investigates and evaluates the performance of J48 decision tree algorithm for the detection of DoS attacks and compares it with two rule based algorithms, namely OneR and Decision table. The selected algorithms were tested with benchmark 1998 DARPA Intrusion Detection data. Our research results show that both Decision tree and rule based classifiers deliver highly accurate results – greater than 99% accuracy – and exhibit high level of overall performance.DOI:

Reza Ghasemi,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 2: June 2013 , pp. 59-72

Designing a stable fuzzy controller for a class of generalized flow shop systems is addressed in this paper based on max-plus algebra. The proposed controller is multi-input single-output. Robustness against uncertainties in the service times, stabilizing the closed loop system and withholding the blocking effect are the main properties of the proposed controller. An illustrative example is given to show the effectiveness of the proposed method.DOI:

Hardiansyah Hardiansyah,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 2: June 2013 , pp. 90-98

In practical cases, the fuel cost of generators can be represented as a quadratic function of real power generation and satisfied constraints for minimizing of fuel cost. Artificial Bee Colony (ABC) algorithm is used for the optimization of active power dispatch of generating units. The proposed method is able to determine, the output power generation for all of the power generation units, so that the total cost is minimized. Simulation and analysis of economic load dispatch using Artificial Bee Colony (ABC) algorithm is proposed. The obtained results are compared with the conventional method, genetic algorithm (GA) and shows that the ABC algorithm approach is more feasible and efficient for finding minimum cost.DOI:

Reza Ghasemi,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 2: June 2013 , pp. 73-80

Fuzzy adaptive controller is developed for HIV infection in which functions of the system are unknown. A non-affine nonlinear system is considered for the HIV infection dynamic model. The merits of the proposed method is as the stability of the closed-loop system (HIV + Controller), the convergence of the infected cells concentration rates to zero and the boundedness of the internal signal and infected cell concentration. The simulation results show the promising performance of the proposed method.DOI:

Muhammad Arif, Sultan Daud, Saleh Basalamah,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 2: June 2013 , pp. 51-58

In this paper, we have proposed a framework to count the moving person in the video automatically in a very dense crowd situation. Median filter is used to segment the foreground from the background and blob analysis is done to count the people in the current frame. Optimization of different parameters is done by using genetic algorithm. This framework is used to count the people in the video recorded in the mattaf area where different crowd densities can be observed. An overall people counting accuracy of more than 96% is obtained.DOI:

Mostafa Nemati, Reza Salimi, Navid Bazrkar,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 3: September 2013 , pp. 143-150

In this paper a swarms algorithms, for optimization problem is proposed. This algorithm is inspired of black holes. A black hole is a region of space-time whose gravitational field is so strong that nothing which enters it, not even light, can escape. Every black hole has mass, and charge.  In this Algorithm we suppose each solution of problem as a black hole and use of gravity force for global search and electrical force for local search. The proposed method is verified using several benchmark problems commonly used in the area of optimization. The experimental results on different benchmarks indicate that the performance of the proposed algorithm is better than    PSO (Particle Swarms Optimization), AFS (Artifitial Fish Swarm Algorithm) and RBH-PSO (random black hole particle swarm optimization Algorithm).DOI:

Toyin Enikuomehin, J S Sadiku,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 3: September 2013 , pp. 136-142

This paper continues the advancement of models proposed for Information Retrieval by understanding that, the Information Retrieval task continues to draw attention as the information repositories increase. Knowing that Natural Language presentation of user’s information need help to reduce the complexity of the search process, we propose the use of a well defined Significant Indicator, which uses the relevance index of terms derived from the position of the text, to perform retrieval. This is achieved by initiating a text wrapping process such that document representation in space could algebraically be measured and assigned appropriate function as similarity ratio for Query and Document. Benchmark tools for Information Retrieval were followed and experiment performed using TREC classified data implemented with TRECEVAL shows better performance against some baseline models. The paper suggests further research in the direction of the Significant Indicator as a method for large search space reductionDOI:

Hesham Ahmed Hassan, Hazem Mokhtar El-Bakry, Hamada Gaber Abd Allah,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 3: September 2013 , pp. 117-124

This paper presents a Multi-criteria spatial decision support system (MC-SDSS) as a tool for decision making and planning. MC-SDSS can be used to assess different criteria with different weights. We believe that such tool can be utilized to help policy/decision makers to improve animal production in Egypt. MC-SDSS facilitates the integration of the exploration and evaluation phases of the decision-making process in a transparent and interactive system that allows policy/decision makers to carry out the analyses without advanced geographical information system (GIS) or multiple criteria decision analysis (MCDA) training. We use weighted overlay method to support data spatial analysis, and then visualize and analyze different factors such as "Diseases", "Climate", "Veterinary care" and "Economical factors" which affect the animal production in Egypt. Policy/Decision makers can change their weights and parameters with this tool for their different study areas. Moreover they can use final suitability maps from this tool.DOI:

Reza Ghasemi,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 3: September 2013 , pp. 125-135

Designing observer based decentralized fuzzy adaptive controller is discussed for a class of large scale non-canonical nonlinear systems with unknown functions of the subsystems in this paper. The On-line adaptation of the controller and the observer parameters, boundedness of the output and the observer errors, robustness against external disturbance are the advantages of the proposed method. The simulation results show the promising performance of the proposed method.DOI:

Boutheina Jlifi, Zina Elguedria, Khaled Ghedira,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 4: December 2013 , pp. 187-197

The Bomber Problem BP can be considered as a discrete time model in which a bomber must survive for t epochs before reaching the target where it will drop its bombs. The Bomber problem is unsolved despite his appearance date since the 1960s. It is classified in the heading of research problems unsolved by Richard Weber. In fact, it can be classified as an NP-hard combinatorial optimization problem. Multi-agent simulation is for a long time privileged for modeling and experimentation of complex systems. This term includes concepts as diverse as strategic decision support or staff training. In this paper, we explore the challenge of simulating a system as complex as the Bomber problem with a MAS approach. Particularly, we demonstrate that Coalition forming in a MAS, models and simulates the collective resolution of the Bomber Problem within a dynamic agent organization in an efficient way. We illustrate our discussion with developed simulation results. DOI:

Mostafa Nemati, Navid Bazrkar, Reza Salimi, Behdad Moshref,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 4: December 2013 , pp. 173-178

In this paper we Using Black Holes Algorithm in Discrete Space by Nearest Integer Function. Black holes algorithm is a Swarm Algorithm inspired of Black Holes for Optimization Problems. We suppose each solution of problem as an integer black hole and after calculating the gravity and electrical forces use Nearest Integer Function. The experimental results on different benchmarks show that the performance of the proposed algorithm is better than    PSO (Binary Particle Swarms Optimization), and GA (Genetic Algorithm).DOI:

Abdel-Rahman Hedar,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 4: December 2013 , pp. 179-186

The minimum edge dominating set (MEDS) is one of the fundamental covering problems ingraph theory, which finds many practical applications in diverse domains. In this paper, wepropose a meta-heuristic approach based on genetic algorithm and local search to solve theMEDS problem. Therefore, the proposed method is considered as a memetic search algorithmwhich is called Memetic Algorithm for minimum edge dominating set (MAMEDS). Inthe MAMEDS method, a new fitness function is invoked to effectively measure the solutionqualities. The search process in the proposed method uses intensification schemes besidethe main genetic search operations in order to achieve faster performance. The experimentalresults proves that the proposed method is promising in solving the MEDS problem.DOI:

Mohamad Reza Rahimi Khoygani, Reza Ghasemi, Davoud Sanaei,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 4: December 2013 , pp. 159-168

Designing proportional integral derivative (PID), Linear Quadratic Regulator (LQR), Fuzzy Logic Controller (FLC) and Self-Tuning Fuzzy PID (STFP) controller is used for nonlinear pendulum dynamic system in this paper.The promising performance of the proposed controllers investigates in simulation. The effectiveness, robustness against noise and the comparison of the controller methods for Nonlinear Pendulum Dynamical System are delivered in this paper.DOI:

Mahil J, T. Sree Renga Raja,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 4: December 2013 , pp. 169-172

This paper proposed a hybrid neural network Back propagation (BP) algorithm optimized by Genetic Algorithm (GA) for the diminution of the fundamental electromagnetic interferences in Incubators. Gradient based techniques have been proposed in the past for the elimination of incubator noise but they are susceptible to local minima problem. Genetic algorithms are a class of optimization procedure which is good at examining an intelligent way for selecting the number of hidden layer neurons, learning rate and momentum constant of the Artificial Neural Network (ANN) to find values close to the global minimum. The result analysis shows that the proposed approach shows good performance in cancelling the ECG interference over other conventional approaches.DOI:

Seyed Mojtaba Saif, Mehdi Sarikhani, Fahime Ebrahimi,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 2, No 4: December 2013 , pp. 151-158

Nowadays expert system, being used in various fields has received a great deal of attention. Auditing is one such field, along with determining the audit opinion type. An expert system consists of a knowledge database and an inference engine. The objective of this research is to make an expert system that will be of help to auditors in predicting and determining the different types of audit reports. The expert system receives data or knowledge from financial reports and determines the types of audit opinions by using an artificial neural network and a decision tree as an inference engine. An expert system should able to explain the solution, but presenting the reason for the results obtained with a neural network is difficult.  This study attempts to provide a method that will present simple and understandable reasons for the results obtained with neural networks.DOI:

Minakshi Sharma, Saourabh Mukherjee,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 3, No 1: March 2014 , pp. 16-23

Imaging plays an important role in medical field like medical diagnosis, treatment planning and patient follow up. Image segmentation is the backbone process to accomplish these tasks by dividing an image in to meaningful parts which share similar properties.  Medical Resonance Imaging (MRI) is primary diagnostic technique to do image segmentation. There are several techniques proposed for image segmentation of different parts of body like Region growing, Thresholding, Clustering methods and Soft computing techniques  (Fuzzy Logic, Neural Network, Genetic Algorithm).The proposed research work uses Grey level Co-occurrence Matrix (GLCM) for texture feature extraction, ANFIS(Adaptive Network Fuzzy inference System) plus  Genetic Algorithm for feature selection and FCM(Fuzzy C-Means) for segmentation of  Astrocytoma (Brain Tumor) with all four Grades. The comparative study between FCM, FCM plus K-mean, Genetic Algorithm, ANFIS and proposed technique shows improved Accuracy, Sensitivity and Specificity.

Farzin Piltan, Mansour Bazregar, Marzieh Kamgari, Mojdeh Piran, Mehdi Akbari,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 3, No 1: March 2014 , pp. 36-48

In this research, manage the Internal Combustion (IC) engine modeling and a multi-input-multi-output artificial intelligence baseline chattering free sliding mode methodology scheme is developed with guaranteed stability to simultaneously control fuel ratios to desired levels under various air flow disturbances by regulating the mass flow rates of engine PFI and DI injection systems. Nevertheless, developing a small model, for specific controller design purposes, can be done and then validated on a larger, more complicated model. Analytical dynamic nonlinear modeling of internal combustion engine is carried out using elegant Euler-Lagrange method compromising accuracy and complexity. The fuzzy inference baseline sliding methodology performance was compared with a well-tuned baseline multi-loop PID controller through MATLAB simulations and showed improvements, where MATLAB simulations were conducted to validate the feasibility of utilizing the developed controller and state estimator for automotive engines. The proposed tracking method is designed to optimally track the desired FR by minimizing the error between the trapped in-cylinder mass and the product of the desired FR and fuel mass over a given time interval.

Mostafa Nemati, Reza Salimi, Behdad Moshref,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 3, No 1: March 2014 , pp. 49-55

In this paper fuzzy version for black holes algorithm is proposed. The main idea of this article is based upon this principle that we should consider the distance between two black holes for calculating gravitational force (global search) and electrical force (local search). For this purpose, we have suggested Fuzzy distance notion. In this proposed idea, for calculating two forces, FQ and FG, considering the distance between black holes, we have defined a Fuzzy function, which receives distance value and depending on this value being low or high, produces a membership degree for gravitational and electrical constants to be used in the formulas related to the calculation of FG and FQ. The proposed method is verified using several benchmark problems used in the area of optimization. The experimental results on different benchmarks show that the performance of the proposed algorithm is better than basic BLA (Black holes Algorithm) and FPSO (fuzzy Particle Swarms Optimization).

Morcous M. Yassa, Hesham A. Hassan, Fatma A. Omara,

IAES International Journal of Artificial Intelligence (IJ-AI), Vol 3, No 1: March 2014 , pp. 1-6

Business Opportunity (BO) needs business collaboration and rapid distributed solution. Legacy systems are not enough to cope with it and there is a need to create Dynamic Virtual Organizations (DVO). While ecosystems have no agree in this area of business markets, some earlier DVO work used ecosystems to handle BO. The main objective of this paper is to show how CommonKADS knowledge engineering methodology is used to model DVO; life cycle, identification, and formation. Towards this objective, different perspectives used to analyze Collaboration Network Organization (CNO) have been discussed. Also, four more perspectives (CNO boundary fixing, organizational behavior, CNO federation modeling, and external environments) have been suggested to obtain what we called a Federated CNO Model (FCNOM). We believe that according to the work in this paper, the negotiations within CNO components during its life cycle will be minimized, the DVO configuration automation will be support, and more harmonization between CNO partners will be accomplished.



ipmuGoDigital Library

Copyright © 2021 IpmuGo Digital Library.

All Right Reserved


Help Center

Privacy Policy

Terms of Service