Welcome to Journal of Theoretical and Applied Information Technology

Author:

Source:

Abstract

Soft Computing Model always composed of Fuzzy logic, Neural Network, Genetic algorithm etc. Most of the time, these three components are combine in different ways to form model. Fuzzy- Neuro Model, Neuro- GA model, Fuzzy- Neuro- GA model etc. All this combination is widely used in prediction of time series data. If in a time series data, initial change are observed during some time interval, the final value of this data must be predicted. In this paper, an effort has been made to use soft computing approaches for predicting a final product of a time series data. The data is taken from a statistical survey has been conducted by a group of certain agricultural personnel on different mustard plant under the supervision of Prof. Dilip dey, Bidhan Chandra Krishi Viswavidayalay West Bengal, India. In this paper, the models of soft computing using neural network based on fuzzy input and genetic algorithm have been tested on same data and based on error analysis (calculation of average error) a suitable model is predicted for this data.

Author:

Source:

Abstract

The paper represents a genetic algorithm (GA) solution to the unit commitment problem for power generation in thermal power plant. GAs are general optimization techniques based on principles inspired from the biological evolution, using metaphors of mechanism such as natural selection, genetic recombination and survival of the fittest. A simple GA implementation using the standard crossover and mutation operators could locate near optimal solution.
To solve the problem a two layer approach is used, the first layer uses a genetic algorithm to decide the on/off status of the units, and the second layer uses a non linear programming formulation solved by Lagrangian relaxation to perform the economic dispatch while meeting all plant and system constraints. In order to save the execution time the economic dispatch is only performed if the given unit commitment schedule is able to meet the load balance, energy and begin/end level constraints. The simulation results reveal that the features of easy implementation, convergence within an acceptable execution time, and highly optimal solution in solving the unit commitment problem can be achieved.
 

Author:

Amandeep Dhir, Abhinav Arya

Source:

Abstract

This paper is based on the plagiarism detection in natural languages. We tried to put light on various forms of plagiarism, their detection principles. We have developed an efficient plagiarism detection mechanism and we have tested this mechanism for various input data and it has shown considerable output. Our purposed plagiarism detector is different from the already available plagiarism tools. We have also compared our plagiarism detection mechanism with the other tools which have already been developed. Challenges faced during the plagiarism detection are discussed with their purposed solutions.

Author:

Source:

Abstract

Character recognition is the important area in image processing and pattern recognition fields. Handwritten character recognition has received extensive attention in academic and production fields. The recognition system can be either on-line or off-line. Off-line handwriting recognition is the subfield of optical character recognition. India is a multi-lingual and multi-script country, where eighteen official scripts are accepted and have over hundred regional languages. In this paper we propose Zone centroid and Image centroid based Distance metric feature extraction system. The character centroid is computed and the image (character/numeral) is further divided in to n equal zones. Average distance from the character centroid to the each pixel present in the zone is computed. Similarly zone centroid is computed and average distance from the zone centroid to each pixel present in the zone is computed. We repeated this procedure for all the zones/grids/boxes present in the numeral image. There could be some zones that are empty, and then the value of that particular zone image value in the feature vector is zero. Finally 2*n such features are extracted. Nearest neighbor and Feed forward back propagation neural network classifiers are used for subsequent classification and recognition purpose. We obtained 99 %, 99%, 96% and 95 % recognition rate for Kannada, Telugu, Tamil and Malayalam numerals respectively.

Author:

Source:

Abstract

Web applications are nowadays at the heart of the business world. All corporate companies and big institutions have very busy e-commerce web sites that host a major part of their businesses. With this great emergence of web applications, techniques for maintaining their high quality attributes should be developed and exercised. Moreover, the quick evolution of web technology and the high user demands made web applications subject to rapid maintenance and change, which require the development of efficient regression testing techniques. The current testing efforts documented in research deal with a specific part of a web application. While some papers model and test the server side programs of the application, others model and analyze the navigation between pages as seen by the user, and yet others deal with analyzing the architectural environment of the web application. Motivated by the fact that there is no single model to represent the entire web application, and to model it from different perspectives at the same time, we propose a single analysis model with it testing techniques which models and tests the three poles of the web application: the client side pages navigated by the user, the server side programs executed at runtime, and the architectural environment hosting the application. Having discovered, as well, that there is no automated black box regression testing technique, we also propose a methodology and algorithm to create a tool capable of applying black box regression testing automatically.

Author:

Source:

Abstract

This paper deals with BDH technique, which is used to the compression of digital images. In BDH technique, Huffman coding[6] and Difference coding[7] with Binary Plane Technique[1] are combined. The BDH technique is compared with Binary Plane Technique and JPEG[4]. Experimental results show that BDH improves compression rate compared to Binary Plane Technique[1]. The same algorithm can be extended to color images.

Author:

Source:

Abstract

In this paper a new robust load frequency controller for two area interconnected power system is presented to quench the deviations in frequency and tie line power due to different load disturbances. The dynamic model of the interconnected power system is developed without the integral control. The area control error is also not included. The frequency and derivatives are zero under normal operation and after the disturbance effects are died. Then the problem is restructured as the problem of state transfer from the initial steady state to final steady state without oscillations in less time. The Genetic algorithm (GA) controller designed here consists of two crisp inputs namely deviation of frequency and the other is derivative of frequency deviation. The output of the Genetic algorithm controller is the control input to each area. The studies power system is subjected to a wide range of load disturbances to validate the effective ness of the proposed Genetic algorithm controller. The simulated results are obtained for different configurations of the Genetic algorithm controller like placing in area 1 only and placing area 1 and area 2 for different options of load variations. The digital results prove the present Genetic algorithm controller over the other control studies presented in earlier work in terms of fast response (dead beat response for certain configuration of Genetic algorithm controller) with very less undershoots and negligible overshoot with having small state transfer time to reach the final steady state with zero frequency.

Author:

Source:

Abstract

The main problem in the guidance of Autonomous Mobile Robots is obstacle avoidance in unknown environment. This paper presents a novel technique for path fixing for obstacle avoidance using a framework of cellular logic. The images of the unknown environment obtained from local perception devices are scanned by an array of neighbourhood windows and processed by the techniques of contouring, skeletonizing and centroid determination. High risk regions and low risk regions are considered for nearby and distant obstacles. A framework of cellular logic is used to determine the probability of collision. The various possibilities are classified into equally likely classes. The optimal path is the one that has the common probability of collisions. The mission direction is accordingly fixed instantaneously to meet the challenge of obstacle avoidance.

Author:

Source:

Abstract

Research on software architecture from different perspectives has been done for several years. However, Architectural Knowledge (AK), a relatively new field, has gained its increasing interest among the community. On this regard, various topics devoted to architectural knowledge, such as reusing, sharing, managing and communicating are being studied. Among them, AK sharing brings new effective
challenges and issues not present when studying other topics in architectural knowledge. Therefore, this paper surveys the current research on AK sharing (pertaining to software architecture), the approaches, models that are being proposed, and issues that arise when sharing different AKs by different parties. By making survey on AK sharing approaches, a better understanding of these approaches and issues related in this area is provided so that it can be a penetrative resource for a fast training and educating in this area of SE. In addition, conclusion about current state of research in this area and future trends for AK sharing is identified.

Author:

Source:

Abstract

Business Processes in Service Oriented Architecture (SOA) are run using an orchestrate engine. The point here is that running a huge number of business processes under a centralized orchestrate engine result in degrading of run-time environment abilities. Apart from this, running clustered orchestrate engines as an alternative way to obviate centralized orchestrate engine problems is not a final solution. On the other hand, there exist many researches focusing on decomposing or segmentation of business processes in run-time some of which attempts to decompose a business process to its building activities, while others break business process parts to sub flows or segments. Decomposing of a business process to its building activities will lead to a large number of activity agents in run time and it subsequently leads to more resource consumption and run-time system degradation. Segmentation, though, is useful however there are no criteria for business process segmentation commensurate with run-time environment requirements. In this paper, we introduce an intelligent process distribution method to firstly) increase business process adaptability with run-time environment, secondly) choose the best granularity for segments as well as encapsulating them in agents and thirdly) decrease resource consumption due to reduced number of agents and messages. We also prove the correctness of our method mathematically.

Author:

Source:

Abstract

Through this paper, two prominent methods for detection and classification of power quality disturbance are proposed. The first one, based on the statistical analysis of adaptive decomposition signals is proposed, the second one is a new technique for detecting and characterizing disturbances in power systems based on wavelet transforms. The voltage signal under investigation is often corrupted by noises, therefore the signal is first de-noised and then wavelet transform is applied. Using the first detail wavelet coefficients, voltage disturbance is detected and its duration is determined. The combination of an adaptive prediction filter based sub-band decomposition structure with a rule based histogram analysis block produce successful detection and classification results on our real life power system transient data. In this paper, voltage swell is considered for comparing both approaches. Proposed scheme is implemented using MATLAB(7.0.1), Simulink, DSP and Wavelet toolboxes.

TIME SERIES MODELING USING ARTIFICIAL NEURAL NETWORKS

Author:

P.Ram Kumar , M.V.Ramana Murthy , D.Eashwar , M.Venkatdas

Source:

Abstract

An Artificial Intelligent technique exists in human brain for observation Of  behavior of neurons in human brain. A neural network achieves the intelligent results by using massively parallel computations rather than by using rules or other logical structures. A set of elements begins by being randomly connected. Then network is trained to recognize a pattern by strengthening signals that lead to appropriate results and weakening incorrect or inefficient signals. An Artificial Neural Network(ANN) has procedural rules or formulas for only what kinds of input data the neural network can use to make an association with desired output. The approach of ANN has several advantages over conventional statistical and
deterministic` approaches. One of the most important algorithms of ANN is “Back Propogation Algorithm”(BPA) which learns by computing an error signal and than propogating the error backword throw the network. The BPA method is applied to statistical model(ARIMA) to test its efficiency and then applied to some actual geophysical data. The result of the analysis shows that the ANN is fast and efficient method for simulating/modeling large amount of data.

Augmenting Experience Reports with Lightweight Postmortem Reviews for Software Development

Author:

D.V. Chandra Shekar, J.N. Bhargava, B.V.H.KAMESWARA SASTRY

Source:

Abstract

 The paper is no longer available as it is copied from "Augmenting Experience Reports with Lightweight Postmortem Reviews for Software Development" Lecture Notes in Computer Science volume 2188, in 2001 Springer.

JATIT has a strong policy against plagiarism and does not tolerate any such case of polluting academic literature,. this is also circulated in agreemnet from authors submits before paper is subjected to blind review. This is for intimation only and  entry will be removed after 7days.