011883   Thyagarajan K;Chinnaiyan R (Computer Science Dep, AVC College (Autonomous), Mannmpandal - Mayiladuthurai, Nagappattinam District-609 305) : Genetic programming for soft computing. Karpagam J Comput Sci 2008, 2(3), 615-19.

This paper is dealt with the basics of genetic programming. The Genetic Programming (GP) is an important tool to evolve computer programs. An automatic programming has been the goal of scientists and engineers for a number of decades. Scientists would like to give the computer a problem and ask the computer to build a program to solve it. Genetic programming shows the most potential ways that automatically write computer programs for solving complex problems in computer science. Genetic Programming plays a vital role in future soft computing since it gives consistent solutions.

2 illus, 14 ref

011882   Thakur G S;Jain R C (Computer Appilications Dep, Samrat Ashok Technological Institute, Vidisha, Madhya Pradesh) : Document classification approach based on linear combination. Karpagam J Comput Sci 2008, 2(2), 503-7.

Developeds an algebraic approach for document classification. This is the most accurate, efficient, and scalable classification approach that addresses the special challenges of document classification. Algebraic approach is a new document classification method comparatively more efficient and accurate. So for, no research was conducted using this concept for Document classification. Our experiments indicate that the accuracy of existing method increase by using algebraic approach. The final goal is achieving high performance and eventually increasing classification accuracy.

14 ref

011881   Sushmera M;Muneeswaran K (IT Dep, Mepco Schlenk Engineering College, Virudhnagar, Tamilnadu-626 005, Email: gayathri_nice2004@yahoo.co.in) : KDEH based image retrieval using invariant features. Karpagam J Comput Sci 2008, 2(2), 521-9.

Image Retrieval scheme represents images on the basis of histograms derived from photometric color features. The main objective of this research is to apply Kernel Density Estimation function on Histogram (KDEH), to retrieve images from large collection of image database by characterizing the contents. The retrieval process is performed based on the content of images, and more precisely on a low - level visual features based method such as color and shape. In this approach, the system extracts the color features in two color spaces namely RGB and HSV. The similarity measure between two color histograms are computed by Histogram Intersection Distance (HID) and their retrieval performances are compared based on precision and recall techniques. Various edge detection methods like gradient-based edge detection and signature-based edge detection for shape feature have been proposed to detect the arbitrary objects in an image. Finally, the KDEH method is compared with a Traditional Histogram (TH) approach by varying the histogram bins with for different testing and training samples. It has been experimented that extracting the KDEH based color feature histogram provides improved results in terms of retrieval accuracy for the kind of images, which are enriched with color characteristics and the shape features perform well for the images with structural characteristics.

5 illus, 4 tables, 15 ref

011880   Subban R;Nallaperumal K (Centre for Information Technology and Engineering, Manonmaniam Sundaranar Univ, Tirunelveli-627 012, Email: subban_ravi@yahoo.co.in) : Face detection in color images using pixel-based skin color detection techniques. Karpagam J Comput Sci 2008, 2(6), 820-32.

The selection of the best color space for skin detection in color images is important in many computer vision areas and this paper presents a comparative study on the pixel-based skin color detection techniques. Three main issues of the face detection are the selection of the best color space, skin color pixel classification algorithm and face detection algorithm. A large set of XM2VTS face database is used to examine whether the selection of color space can enhance the compactness of the skin class and discriminability between skin and non-skin class in thirteen color spaces, six different skin color pixel classification algorithms and one face detection algorithm. The results show that 1) the selection of the color space can improve the skin classification performance 2) the segmentation performance degrades only when chrominance information is used for classification 3) Bayesian classifier is found to perform better as compared to other classification algorithms, like Gaussian classifiers. Piece-wise linear decision boundary classifier algorithm outperforms all the other skin classification algorithms when used for images with good illumination conditions. The template matching technique is used to mark the face region in the image.

3 illus, 2 tables, 19 ref

011879   Shankar P (NO, Indian Institute of Science, Bangalore-560 012, Email: priti@csa.iisc.ernet.in) : Evolution of compilers. Resonance 2007, 12(8), 8-26.

The term compiler was coined in the late forties, by Grace Murray Hopper, a pioneer who rose to the challenges of programming the first computers. The problem of translation from a source language into a target language was viewed as a 'compilation' of a sequence of machine language subprograms selected from a library. Article briefly trace the evolution of compilers from their beginnings as huge sprawling algorithms in the early fifties, to their current elegant, phase ordered forms.

4 illus, 2 ref

011878   Sathyanarayana B (Computer Science & Technology Dep, S.K. Univ, Anantapur, Andhra Pradesh, Email: bachalasatya@yahoo.com) : Edge loading algorithms for De Bruijn and modified De Bruijn graphs and their performance analysis in lightwave networks. Karpagam J Comput Sci 2008, 2(2), 547-53.

Proposes edge-loading algorithms for the De Bruijn graphs and Modified De Bruijn graphs, which are logical topologies for multihop light wave networks. For a given in-degree, out-degree and average number of hops between nodes in a network, the edge loading algorithms for Modified De Bruijn graphs has shown smaller average edge loading, better network utilization than that of De Bruijn graphs. Results for De Bruijn and Modified De Bruijn graphs are computed for different values of 'A' (degree) and 'd' (diameter) are presented.

2 tables, 11 ref

011877   Ramaraj E;Gokulakrishnan R;Rameshkumar K (Computer Centre, Alagappa Univ, Karaikudi, Email: dr_ramaraj@yahoo.co.in ) : Association rule based closed frequent item set algorithm (CFIA) for chess dataset. Karpagam J Comput Sci 2008, 2(6), 804-12.

Taxonomy over the items in database can be more initiative and informative in the area of knowledge discovery. Association Rule Mining (ARM) focuses on finding a set of all subsets of items called item sets. This paper proposes a new approach for closed item sets using association rules. A smaller set of closed item sets can be a substitute of a larger item set. A new algorithm to mine a set of closed frequent item set called CFIA is presented as a part of this paper. The CFIA algorithm outperforms the traditional approaches of mining frequent item sets especially when the item sets intensity is dense in the database or when there are complicated permutations, probability of occurrences like Chess datasets.

13 ref

011876   Pongiannan R K;Yadaiah N (Information Technology Dep, Karpagam College of Engineering, Coimbatore-641 032, Email: pongiannan-rk@yahoo.co.in) : FPGA applications in DC - AC converters : a single chip implementation of spwm and SVPWM modulators. Karpagam J Comput Sci 2008, 2(3), 620-33.

In the past decade, the development in the field of FPGA has found a lot of applications in electrical power conversion applications. The SPWM and SVPWM are the most commonly used PWM schemes in the three phase inverters due to their advantages. This paper presents single chip implementation of two commonly used PWM schemes such as SPWM and SVPWM in a single FPGA using Q-format data representation. It also provides the guidelines and quick references for practicing engineers and researchers in the field of FPGA based development to select the suitable digital controller based on the switching frequency, speed of the algorithm and single chip applications.

7 illus, 52 ref

011875   Patil J B;Pawar B V (Computer Engineering Dep, R.C. Patel Institute of Technology, Shirpur, Maharashtra, Email: jbpatil@hotmail.com) : Trace driven simulation of GDSFno. and existing caching algorithms for internet web servers. Karpagam J Comput Sci 2008, 2(3), 573-83.

Web caching is used to improve the performance of the Internet Web servers. Document caching is used to reduce the time it takes Web server to respond to client requests by keeping and reusing Web objects that are likely to be used in the near future in the main memory of the Web server, and by reducing the volume of data transfer between Web server and secondary storage. The heart of a caching system is its page replacement policy, which needs to make good replacement decisions when its cache is full and a new document needs to be stored. The latest and most popular replacement policies like GDSF use the file size, access frequency, and age in the decision process. The effectiveness of any replacement policy can be evaluated using two metrics: hit ratio (HR) and byte hit ratio (BHR). There is always a trade-off between HR and BHR [1]. In this paper, using three different Web server logs, we use trace driven analysis to evaluate the effects of different replacement policies on the performance of a Web server. We propose a modification of GDSF policy, GDSFNo, which allows augmenting or weakening the impact of size or frequency or both on HR and BHR. simulation results show that proposed replacement

8 illus, 12 ref

011874   Nalayini N;Wahida Banu R S D (Electronics & Communication Engg Dep, Govt. College of Engg, Salem, Email: sandeep_nalayini@yahoo.com) : Design methodology of a controller to predict the uncertain cardiac arrest using fuzzy logic approach. Karpagam J Comput Sci 2008, 2(2), 563-71.

The main objective of design methodology of a controller for forecasting cardiac arrest using fuzzy logic approach is to provide the prediction of period of life time for the patients affected by sudden death due to cardiac arrest. In this paper, the controllable risk factors "blood pressure, cholesterol, diabetic, obesity" are taken as inputs for the fuzzy logic controller and "the period of life time" is the output. The input triangular membership functions are Low, Normal, High, Very High. The output triangular membership functions are Very Short, Short, Medium, Long, Very Long. As the rate of mortality increases due to the uncertain, unexpected and sudden arrest of cardio vascular system, a Fuzzy Logic Controller is designed to perform optimal control on high risk controllable risk factors. Fuzzy Logic is used to incorporate the available knowledge into intelligent control system, based on the clinical observations, medical diagnosis, and the expert's knowledge. The controller is validated with the captured data as a tracking system with accuracy and robustness. Also, a basic design of a logic circuit is developed to devise a device for test and implementation as a further enhancement.

4 illus, 4 tables, 28 ref

011873   Mukund M (NO, Chennai Mathematical Institute, H1, SIPCOT IT Park, Padur PO, Siruseri-603 103, Email: madhavan@cmi.ac.in) : Taste of functional programming-1. Resonance 2007, 12(8), 27-48.

Functional programming has its roots in Alonzo Church's lambda calculus. A functional program is a collection of functions that work together to transform data. Though Lisp brought functional programming to public attention in the 1950s, it was John Backus's 1977 Turing Award lecture criticizing the limitations of imperative programming languages that led to a resurgence of interest in this field. The 1970s and 1980s saw a number of advances, leading to the development of the language Haskell, which carefully combined ideas from many earlier languages. Arti-cle, explores some basic notions of functional programming via Haskell.

ref

011872   Marimuthu A;Shanmugam A (Computer Science, Govt. Arts College, Coimbatore-641 018, Email: mmuthu2005@yahoo.com) : Model for ad hoc mobile networks using cluster-based intrusion detection technique. Karpagam J Comput Sci 2008, 2(6), 786-794.

The ad hoc networks are vulnerable to attacks due to distributed nature and lack of infrastructure. Intrusion detection systems (IDS) provide audit and monitoring capabilities that offer the local security to a node and help to perceive the specific trust level of other nodes. The clustering protocols can be taken as an additional advantage in these processing constrained networks to collaboratively detect intrusions with less power usage and minimal overhead. Existing clustering protocols are not suitable for intrusion detection purposes, because they are linked with the routes. The route establishment and route renewal affects the clusters and as a consequence, the processing and traffic overhead increases due to instability of clusters. The ad hoc networks are battery and power constraint, and therefore a trusted monitoring node should be available to detect and respond against intrusions in time. This can be achieved only if the clusters are stable for a long period of time. If the clusters are regularly changed due to routes, the intrusion detection will not prove to be effective. Therefore, a generalized clustering algorithm has been proposed that can run on top of any routing protocol and can monitor the intrusions constantly irrespective of the routes. The proposed simplified clustering scheme has been used to detect intrusions, resulting in high detection rates and low processing and memory overhead irrespective of the routes, connections, traffic types and mobility of nodes in the network.

2 illus, 5 tables, 12 ref

011871   Manimegalai P;Sathyabama R;Annadurai S (Electronics and Communication Engineering Dep, Karpagam College of Engineering, Coimbatore-641 032, Email: mega_shanthi@rediffmail.com) : Object detection using dual lifting. Karpagam J Comput Sci 2008, 2(2), 530-36.

Pereides an approach to extend the functionality and application fields of adaptive lifting. An adaptive lifting scheme is used for detecting user-selected objects in a sequence of images. In this algorithm, first a set of object features in the wavelet transform domain is selected and then an adaptive transform is built using the selected features. The adaptive transform is constructed based on adaptive prediction in a lifting scheme procedure. Adaptive prediction is performed such that, the large coefficients in the high-pass component of the non-adaptive transform vanishes in the high-pass component of the adaptive transform. Finally, both the non-adaptive and adaptive transforms are applied to a given test image and the transform domain coefficients are compared for detecting the object of interest.

10 ref

011870   Madhavi S;Ramesh Babu I (CSE Dep, PVP Siddhartha Institute of Technology, Jawaharlal Nehru Technological Univ, Andhra Pradesh) : Adaptive broadcast scheduling in mobile adhoc networks. Karpagam J Comput Sci 2008, 2(3), 593-600.

The topology of the Mobile Ad Hoc network changes dynamically. The initial slot assignments may cause interferences among the nodes while transmitting. Many heuristics methods have proposed in [1] - [19]. In this paper, describes an adaptive distributed broadcast scheduling for spatial time division multiple accesses in mobile ad hoc networks that computes the slot assignments according to the changes in the topology like new node joining / leaving the network. No central node has maintained to calculate such schedules. Each node gathers information from its local neighborhood to reconstruct the slot assignments.

5 illus, 19 ref

011869   Kumar S;Mishra R B (Computer Engineering Dep, Institute of Technology, Banaras Hindu Univ, (IT-BHU), Varanasi-221 005, Email: sandeep.garg.cse06@itbhu.ac.in) : Semantic web service composition. IETE Tech Rev 2008, 25(3), 105-121.

The research community of Web, presently is working to generate its next generation i.e. Semantic Web. They are moving towards automation of the retrieval and processing of web contents. The systems based on the semantic web require performing various processes like discovery, selection, composition, orchestration, monitoring etc. on services provided by it for satisfying client needs. Concentrates semantic web service composition techniques. The work deals with exploring different type of composition techniques, categorization of them, and comparing them based on some of their properties like process, reasoners & languages involved, interface etc.

3 illus, 2 tables, 36 ref

011868   Kulkarni S A;Raghavendra Rao G (Computer Science and Engineering Dep, GIT, Udyambag, Belgaum-590 008, Email: sakulkarni@git.edu) : Mobility and energy-based performance analysis of temporally ordered routing algorithm for ad hoc wireless network. IETE Tech Rev 2008, 25(4), 222-7.

Mobile ad hoc network consists of nodes that move arbitrarily and form dynamic topologies. The distributed nature of the networks and their link stability pose critical challenges in the design of routing protocols for them. Also, the lifetime of individual nodes in MANET is dependent on their battery power. This is critically important as the failure of battery resources may severely affect the communication capabilities of the node. Temporally ordered routing protocol (TORA) is a highly adaptive, loop-free, and distributed routing algorithm for mobile ad hoc networks (MANET). The protocol emphasizes on stable routes, with multi-path. Proposes to investigate TORA under different mobility patterns and mobility models. Mmodel TORA for its energy consumption capabilities, and extend the analysis for TCP and UDP-based traffic models.

1 illus, 1 table, 13 ref

011867   Kiran Sree P;Ramesh Babu I;Usha Devi N S S S N (C.S.E. Dep, S.R.K.I.T., Vijayawada, Email: profkiran@yahoo.com) : Non linear cellular automata in improving the quality of clustering for medical image processing. Karpagam J Comput Sci 2008, 2(6), 795-803.

Clustering can be applied to medical image processing on the grounds of its potential improved effectiveness over conventional image search. Clustering is a mostly unsupervised procedure and the majority of the clustering algorithms depend on certain assumptions in order to define the subgroups present in a data set A clustering quality measure is a function that, given a data set and its partition into clusters, returns a non-negative real number representing the quality of that clustering. Moreover, they may behave in a different way depending on the features of the data set and the input parameters values. Therefore, in most applications the resulting clustering scheme requires some sort of evaluation as regards its validity. The quality of clustering can be enhanced by using a Cellular Automata Classifier for medical image processing. In this paper we take the view that if cellular automata with clustering is applied to search results, then it has the potential to increase the retrieval effectiveness compared both to that of static clustering and of conventional image search. We conducted a number of experiments using five image collections and four hierarchic clustering methods. Our results show that the effectiveness of query-specific clustering with cellular automata is indeed higher, and suggest that there is scope for its application to medical image processing.

ref

011866   Khan R A;Mustafa K (IT Dep, Babasaheb Bhimrao Ambedkar Univ, Lucknow, Uttar Pradesh, Email: khanraees@yahoo.com ) : Managing software risk a lifecycle approach. Karpagam J Comput Sci 2008, 2(6), 841-51.

The major objectives of software risk management includes identifying, addressing, and eliminating potential elements of risk before they become either threats to successful software operation or major sources of software rework. In order to develop risk free software, it appears to be worthwhile to incorporate risk management within the development process as part of project management. A process of risk management consisting of six phases including identification, analysis, prioritization, planning, resolving and monitoring has been introduced in this paper. In order to prevent project runaways, meet deadlines, stay within the project's budget, and simultaneously maintain the product's high quality standards, it is essential to timely identify, analyze and mitigate risks associated with each and every phase of software development life cycle. For that, a framework has been proposed to integrate risk within the development life cycle.

10 tables, 15 ref

011865   Karthikeyan S (Computer Science, Karpagam Arts and Science College, Autonomous, Coimbatore-21) : Extended MD5 (ExMD5) hashing algorithm for better data integrity. Karpagam J Comput Sci 2008, 2(3), 584-92.

Recent developments in scientific and engineering applications communication are playing a major role in online transactions. All the transactions across the globe are shared by network. The integrity ensures that only authorized parties are able to modify the transmitted information. Modification includes writing, changing, changing status and delaying or replaying transmitted messages. The Message Digest functions MD4 and MD5 provide one-way function integrity in the form of octets, 32-bit and 64 bit words respectively. The extended MD5 (ExMDS) was designed to be somewhat more conservative than MD5 in terms of being more concerned with security. An extended MD5 hashing algorithm that follows five passes than MD5, which follows only four passes. In the proposed approach, the message is processed in 512-bit blocks and the message digest is a 128-bit quantity. Each stage consists of computing function based on the 512-bit message chunk and the message digest to produce a new intermediate value. The value of the message digest is the result of the output of the final block of the message. An extended MD5 hashing provides the better data integrity and the resulted values are compared against existing hashing algorithms such as MD4 and MD5 algorithms.

4 illus, 2 tables, 17 ref

011864   Indumathi G;Ebenezer Gifta Angelin S (E.C.E. Dep, Mepco Schlenk Engg. College, Sivakasi) : Cross layer analysis and design with prescribed Qos using adaptive modulation and coding. Karpagam J Comput Sci 2008, 2(3), 634-8.

In this frame work, a cross layer model which combines Adaptive Modulation and Coding (AMC) at the Physical Layer with admission policy in the Data Link Layer over adaptive wireless links is proposed to maximize the throughput. The proposed cross layer model analysis performance is done by taking into account the QoS parameters such as packet error rate (PER), delay and throughput. The control policy and AMC employed in this analysis possess reduced complexity. By applying admission policy at the Data Link Layer and AMC at the Physical Layer, the throughput is maximized thereby reduce the Packet Error Rate (PER) and delay.

5 illus, 1 table

011863   Gupta V;Lehal G S (University Institute of Engineering & Technology, Panjab Univ, Chandigarh, Email: vishal_gupta100@yahoo.co.in) : Proposed architecture for Punjabi language question answering using text mining. Karpagam J Comput Sci 2008, 2(2), 554-62.

Proposes an approach for Punjabi language web question answering using text mining. Text Mining is a technique for automatically discovering knowledge from unstructured text documents. Traditional search engines like Google, give us only the correct links to web pages. These search engines will not produce the useful answers, but will only give useful links. Our proposed method will give you, the correctly ranked answers of questions typed by you. This architecture is very helpful for people of Punjab. Now they have not to waste their too much time in exploring the web links returned by google, but our system will directly produce the ranked answers of question. Good ranked answers are more relevant than lower ranked answers. Proposes this architecture for Punjabi language text.

18 ref

011862   Gunasekaran R;Divya V P;Sharanya S;Rhymend Uthariaraj V (Information Technology Dep, Anna Univ, Chennai-600 044, Email: gunamit@annauniv.edu) : Packet dropping alleviation in mobile ad hoc networks by power saving AODV. Karpagam J Comput Sci 2008, 2(6), 833-40.

In a mobile ad hoc network every node acts as a router for its neighbor. The existing routing protocols assume that the all the nodes will fully participate in the transmission of packets. Though usually a waiting time is allotted for each participating node to send its data, some nodes, however, behave maliciously, by dropping the packets. This paper aims at developing an algorithm to detect misbehaving nodes and prevent such misbehavior by incorporating promiscuous properties in AODV. The new routing algorithm extensions presented in this paper make it possible to detect and isolate misbehaving nodes with energy saving mechanism, thus making it unattractive to deny cooperation. In the presented scheme, trust relationships and routing decisions are made based on experienced, observed, or reported routing and forwarding behavior of other nodes.

7 illus, 11 ref

011861   Garg D;Narahari Y;Gujar S (IBM India Research Laboratory, , Bangalore-560 071, Email: dingarg2@in.ibm.com) : Foundations of mechanism design: a tutorial II-Advanced concepts and results. Sadhana 2008, 33(2), 131-74.

Mechanism design, an important tool in microeconomics, has found widespread applications in modelling and solving decentralized design problems in many branches of engineering, notably computer science, electronic commerce, and network economics. In the first part of this tutorial on mechanism design (Garg et al 2008), we looked into the key notions and classical results in mechanism design theory. In the current part of the tutorial, we build upon the first part and undertake a study of several other key issues in mechanism design theory.

1 illus, 5 tables, 57 ref

011860   Garg D;Narahari T;Gujar S (NO, IBM India Research Laboratory, Bangalore-560 071, Email: dingarg2@in.ibm.com) : Foundations of mechanism design: a tutorial I-Key concepts and classical results. Sadhana 2008, 33(2), 83-130.

Mechanism design, an important tool in microeconomics, has found widespread applications in modelling and solving decentralized design problems in many branches of engineering, notably computer science, electronic commerce, and network economics. Mechanism design is concerned with settings where a social planner faces the problem of aggregating the announced preferences of multiple agents into a collective decision when the agents exhibit strategic behaviour. The objective of this paper is to provide a tutorial introduction to the foundations and key results in mechanism design theory. The paper is in two parts. Part 1 focuses on basic concepts and classical results which form the foundation of mechanism design theory. Part 2 presents key advanced concepts and deeper results in mechanism design.

11 illus, 78 ref

011859   Dutta A;Kar A;Chatterji B N (Computer Science and Engineering Dep, Birla Institute of Technology, Mesra, Kolkata Extension Centre, Southend Conclave, 1582, Rajdanga Main Road, Kolkata-700 107, Email: adutta@bitmesra.ac.in) : Corner detection algorithms for digital images in last three decades. IETE Tech Rev 2008, 25(3), 123-133.

Corner detection is an important step in many computer vision applications. A large number of corner detection algorithms were already developed. An exhaustive review of the existing corner detection algorithms is, therefore, invaluable for the researchers working in this area. Few reviews are given on this area. Most reviewers classified corner detectors into two categories -boundary-based and intensity-based. Some reviewers classified the algorithms into two groups - template-based and geometry-based. Though we follow the first classification, still we feel that there is a requirement of further subdivision. So, we subdivide each categoryis & ubdivided into further two subcategories - spatial-domain and transform-domain. Reviews a total of 114 corner detection algorithms developed from 1977 to 2006, classified them in each of the four categories and found that most of the works have been done in spatial domain only as compared to transform domain approaches.

1 illus, 120 ref

011858   Dhandra B V;Hangarge M (P.G. Dep of Studies and Research in Computer Science, Gulbarga Univ Gulbarga, Karnataka, Email: dhandra_b_v@yahoo.co.in) : Global + local (Glocal) features based script identification system for Indian multi-script documents. Karpagam J Comput Sci 2008, 2(2), 509-20.

The problem of determining the script of the text present in multi-script documents is one of the important steps as a precursor to Optical Character Recognition (OCR). In this paper, the word level script identification in bilingual or multilingual documents based on global and local features is reported. Initially, the identification of the script of words using morphological filters (global features) and regional descriptors (local features) in a biscript scenario is considered. In the later stage, the problem is extended across tri-script to five-script scenarios. The words of different scripts are classified using K nearest neighbour algorithm with five fold cross validation on a large dataset of 27,500 word images. The proposed algorithm achieves an average accuracy of more than 94.78 and is robust for noise, word length, font styles, and sizes.

7 illus, 7 tables, 26 ref

011857   Chopade N B;Ghatol A A (Electronics and Telecommunication Engineering Dep, SSGM College of Engineering, Shegaon-444 203, Email: nbchopade@gmail.com) : SPIHT: highly efficient technique for image transmission and coding. IETE Tech Rev 2008, 25(3), 135-141.

Uncompressed multimedia data (graphics, audio and video) requires considerable storage and transmission bandwidth. A fundamental goal of data compression is to reduce the bit rate for transmission or storage while maintaining acceptable quality. Image coding and compression technique, converts an image that requires low memory storages space, smaller bandwidth for transmission, high PSNR with acceptable image quality. Presents wavelet based coding algorithm SPIHT to encode and compress an image data. The coding and decoding process is comparatively fast. The numerical results obtained using MATLAB shows that the output image has high value of PSNR with good compression ratio for low bit rate.

6 illus, 1 table, 8 ref

011856   Bhuvaneswari V;Nusrath A (School of Computer Science and Engineering, Bharathiar Univ, Bharathiar, Email: bhuvanes.v@yahoo.com) : Analysis of bayesian and nonbayesian functions for motif detection using genetic algorithm. Karpagam J Comput Sci 2008, 2(6), 775-85.

A motif, in the context of biological sequence analysis, is a consensus pattern of DNA bases or amino acids which accurately captures a conserved feature common to a group of DNA or protein sequences. Finding motif-patterns of conserved residues-within nucleotide and protein sequence is a key part of understanding function and regulation within biological system. Computational motif discovery has been used with some success in simple organisms like yeast. However, when moves to higher organisms with more complex genomes, more sensitive methods are needed. Genetic Algorithm is an efficient method for detecting motifs, since it has greater freedom of movement between different configurations than simpler algorithms. This paper analyses the genetic algorithm method for the detection of motifs by using Bayesian and NonBayesian functions as fitness function and compares it with the other existing tools.

ref

011855   Arthi K;Tamilarasi A (NO, Karpagam College of Engineering, Coimbatore, Email: sek_art@rediffmail.com) : Approach to diagnose neurological disorder using neuro fuzzy model. Karpagam J Comput Sci 2008, 2(3), 601-7.

The major problem in medical field is todiagnose disease. Human beings always make mistakes and because of their limitation, diagnosis would give the major issue of human expertise. One of the most important problems of medical diagnosis, in general is the subjectivity of the specialist. It can be noted, in particular in pattern recognition activities, that the experience of the professional is closely related to the final diagnosis. This is due to the fact that the result does not depend on a systematized solution but on the interpretation of the input symptoms from the patient. Almost all the physicians are challenged by the task of learning to predict. Hence, there is a need to solve the problem of deducing certain diseases or formulating a treatment based on more or less specified observations and knowledge. Here, a neuro fuzzy model is designed for diagnosis of Autistic Spectrum disorders which is a type of neurological disorder is proposed in this paper. The symptoms and signs are gathered and definitions of fuzzy membership values are defined. Feed forward multi layer network accepts those input fuzzy values and it is trained using back propagation training algorithm. Finally, the fruition of this process is compared with the expertise to know its performance.

2 illus, 1 table, 20 ref

010823   Vijaya Kumar V;Sunitha K V N (School of Information Technology, Jawaharlal Technology Univ, Hyderabad) : Redundancy elimination using hash based value numbering. J Instn Engrs-Pt CP 2007, 88(Nov), 43-5.

Redundancy elimination is a code optimization technique with a long history of literature and implementation. In practice, its effectiveness depends on issues of assigning a new index numbers and code shape. Shows that hash based value numbering can increase the effectiveness of redundancy elimination. As part of the work, a new algorithm in two passes has been introduced which assigns value numbering in first pass and the redundancy elimination in second pass.

2 ref

010822   Rihani V;Bandlish A;Singh V;Soni V;Aggarwal V (Electronics and Electrical Communication Engineering Dep, Punjab Engineering College, Chandigarh-160 012) : Hybrid protocol for local area networks. J Instn Engrs-Pt CP 2007, 88(Nov), 13-16.

Proposes a technique to efficiently transmit data in a local area network (LAN), overcoming the effect of instabilities in the random access techniques such as ethernet, and the delays in the fixed assignment schemes, such as token bus. This hybrid protocol aims at improving the efficiency-delay characteristics of data transfer in the LAN under variable load conditions. The protocol has been tested and the results are presented. The network hardware has been designed, used and the hybrid protocol is shown to provide a better network performance when compared individually to the ethernet and token bus protocols.

2 illus, 9 ref

010821   Rawtani L (Computer Science and Information Technology Dep, Maulana Azad National Institute of Technology, Bhopal-462 007) : Efficient technique for spam filtering of E-mail. J Instn Engrs-Pt CP 2007, 88(Nov), 23-7.

Spam (unsolicited bulk e-mail) has become a serious problem. Common approaches to deal with the problem are whitelist, blacklist, password, challenge-response, Bayesian filtering etc. A new approach is suggested for dealing with the problem of spam. It is a combination of whitelist, blacklist, Bayesian and challenge-response approaches. While the advantages of these four techniques get combined, the disadvantages of any one approach are countered by the other. If the value of spam probability (P) of the e-mail is greater than higher threshold value, it is classified as spam, if it is less than lower threshold value, it is classified as non -spam. If value of Pis between the two threshold values, it is placed in grey box. E-mail in grey box is subjected to confirmatory test in the form of challenge-response approach, to decide whether it is spam or non -spam. This avoids false negatives and false positives encountered in two class Bayesian classification. Determination of spam probability is quite a lengthy process. In the present method, the e-mails received from senders in blacklist and white list are directly classified as spam and non -spam, respectively. Similarly, the e-mail which is a proper response to an already sent challenge, is classified as non -spam. Only the remaining e -mails are subjected to Bayesian analysis. This makes the classification fast.

3 illus, 2 tables, 10 ref

010820   Mitra A;Ray B K (Computer Applications Dep, VIT, Vellore-632 014) : GSM-free scheme for location management. J Instn Engrs-Pt CP 2007, 88(Nov), 9-12.

Proposes a scheme for location management and location updating without using the GSM facility. A model based on broadcasting is proposed to find out the nodes adjacent to each other. The model is efficient when the number of adjacent nodes are not too many. The algorithm selects one among the list of adjacent nodes randomly for forwarding packets. The performance of this model has been evaluated through simulation and found to be satisfactory.

4 illus, 1 table, 5 ref

010819   Mala K;Sadasivam V (Computer Science and Engineering Dep, Mepco Schlenk Engineering Colleg, M S Univ, Tirunelveli-627 012) : Comparison of sequential feature selection algorithms for liver tumout characterization. J Instn Engrs-Pt CP 2008, 88(May), 3-7.

A comparative study of sequential feature selection algorithms for the problem of liver tumour characterisation has been discussed in this paper. The feature extraction algorithm extract biorthogonal wavelet based second order statistical texture features from the tumour region identified by the radiologist using computed tomography (CT) abdominal images. Then, the feature set is optimized by various sequential feature selection algorithms like sequential forward search (SFS). sequential backward search (SBS) and sequential forward floating search (SFFS). Classification performance is evaluated by probabilistic neural network (PNN) based on the classification of tumour region as benign or malignant tumour. Results show that, features optimized by SFS and SFFS give maximum classification performance for the selected problem. Thus. the cost of the classifier is reduced using the selected feature subset.

2 tables, 20 ref

010818   Kole A;Mandal A K (Electronics and Communication Engineering Dep, Institute of Technology and Marine Engineering, Jinga, South 24 Parganas-743 368) : Neual network based predictive control of non-linear process with fast optimization algorithm. J Instn Engrs-Pt CP 2008, 88(May), 32-7.

A neural network based predictive controller has been designed to govern the dynamics of a magnetic ball suspension system (MAGLEV). It is a highly non -linear and unstable process, therefore, a non -linear prediction method is adopted in a predictive control strategy. Advantages of neural network for non-linear process modelling and control have been investigated and a multi-layer perceptron (MLP) neural network based predictor scheme has been designed, trained and tested for this system. The dynamics of the plant is identified using a three layer perceptron neural network. A fast convergence minimization algorithm, CSRCHCHA using the method of Charalambous is employed in optimization of the control scheme to reduce the computation time and memory. Suitable non-linear function has been used for training the neural network. The predictive control strategy based on the neural network model of the plant is then applied to achieve tracking of the output of the plant. Simulation results demonstrate the effectiveness and superiority of the control strategy and the fast learning algorithm for non-linearprocesses. Comparison of the performance with PID control has also been presented.

5 illus, 1 table, 11 ref

010817   Dudul S V (Applied Electronics Dep, Amravati Univ, Amravati-444 602) : Identification of a steam generator using focused time lagged recurrent neural network model with gamma memory. J Instn Engrs-Pt CP 2007, 88(Nov), 32-6.

Investigates the identification of a typical steam generator, which shows very rich non -linear dynamics using a focused time lagged recurrent (FTLR) neural network (NN). It appears from the literature review that an optimal NN model for the identification of such a highly non -linear complex dynamical system is not currently available. This paper compares the performance of two NN configurations, namely a well known MLP NN and the proposed FTLRNN. A standard static back propagation algorithm with momentum term has been used for both the models. It is shown that the estimated dynamic NN model comprising of a gamma memory (GM) filter followed by a MLP NN clearly outperforms the static MLP NN in NMSE, correlation coefficients and regression characteristics on the cross-validation (CV) as well as testing datasets. In addition, the outputs of the proposed FTLRNN model reasonably follow the desired outputs of the steam generator system for the testing and CV exemplars. This also means that most of the information about the rich non -linear dynamics of the system has been extracted satisfactorily from the training dataset and that the proposed model approximates the given system with pragmatic accuracy. It has been shown that the proposed FTLRNN model has a remarkable system identification capability for the problem considered in this paper.

2 illus, 4 tables, 9 ref

010816   Dethe C G;Wakde D G (NO, Priyadarshini College of Engineering and Technology, Nagpur-440 022) : Network traffic measurements and traffic models. J Instn Engrs-Pt CP 2007, 88(Nov), 37-42.

Data traffic measurements are essential parts to validate the assumptions made in analytical models of the networks. Any model cannot be accurate if the assumptions do not reflect the reality. In order to reach to some conclusion about packet process, a survey of traffic measurement studies has been made for LAN as well as WAN networks. This survey has lead to some important characteristics like long range dependence and hence self-similarity (fractal beha viour) observed in LAN as well as WAN traffic. Thus, it has put questions about validity of previous simple models like Poisson models to capture correlations (long range dependence) present in packet process over wide range of time scale. It is also observed that to model changed dynamics of packet process, models like fractional Gaussian noise, FARIMA, multiplexing ON/OFF sources with ON and OFF periods having heavy tailed distribution, M/G etc. are suggested. Further, attempts are on to come up with structural models instead of black box techniques, which will account for physical reasons for fractal nature of packet process.

^iia6 illus, 24 ref

010815   Balkrishan;Singh A P (NO, Yadavindra College of Engineering, Talwandi Saboo, Bhatinda) : Java implementation of least significant bit embedding for hiding data. J Instn Engrs-Pt CP 2008, 88(May), 28-31.

Reports on Java implementation of the least significant bit (LSB) embedding for hiding messages in high-colour-depth digital images. The results reported in the present work indicate that even when presented with the original cover image, it is not possible to identify the stego-image from the original. The proposed algorithm implemented in Java presents an effective method to achieve least significant bit embedding for the successful hiding of a given test in a digital image. The present technique is an useful alternative for secure transmission of sensitive data over the internet without prying-eyes being able to tell whether a message is being transported. The results are quite promising and noticeable.

4 illus, 10 ref

009801   Goyal P;Behera L;McGinnity T M (Electrical Engineering Dep, Indian Institute of Technology, Kanpur, Email: Ibehera@iitk.ac.in) : Application of Bayesian framework in natural language understanding. IETE Tech Rev 2008, 25(5), 251-69.

A natural language understanding (NLU) system has to handle a large amount of data. A graphical model serves as an advantageous tool for data analysis encoding the dependencies among variables and learning causal relationships. Over the last two decades, the Bayesian network has become a popular representation for encoding uncertain expert knowledge in expert systems. It is an ideal representation for combining prior knowledge; it avoids overfitting of data. Efficient algorithms have been developed for learning Bayesian networks from data, allowing Bayesian networks to be applied to a wide category of problems. A comprehensive and state-of the-art introduction to the application of Bayesian networks in different aspects of an NLU system, with emphasis on information retrieval, The extensions and variants of Bayesian networks applied to NLU problems have been described. Examples of application examples are given, in order to illustrate the use of Bayesian networks.

17 illus, 2 tables, 74 ref

007959   Zhang Y;Orgun M A;Lin W (Dep of Computing Change Program, Macquarie University Australian Taxat, , North ryde, NSW 2109, Austraoia Sydney, NSW 2000, australia, Email: yihao, mehmet@ics.mq.edu.au) : Unsupervised learning aided by clustering and local-global hierarchical analysis in knowledge exploration. J Digital Inf Mgmt 2007, 5(4), 237-45.

Unsupervised learning plays an important role in the knowledge exploration discovery. The basic task of unsupervised learning is to find latent variablesor relationships in a given dataset without any assumed regularities or patterns. In this paper we apply two advanced models, clustering analysis and hierarchial analysis to accomplish unsupervised learning. K-Means clustering presents its strength in large scale clustering. The original data can be preprocessed and the potential variables are targeted. Correlations among these variables are targeted. Correlations among these variables are explored in the subsequent sets by Local Global Hierarchial Analysis (LGHA) assisted by three main steps. In the first step, we use a structural approach to find qualititative patterns from the given variables. Then, the second step applies a quantitative based algorithm to find quantitative patterns from those variables. The and last step generated global hybrid patterns by combining the local patterns obtained from the first two steps based on a certain criterion. Both of the K-Means and Local Global Hierarchial Analysis (LGHA) models are applied in experiments with real world longitutional medical datasets.

2 illus, 8 tables, 25 ref

007958   Tripathi A K;Ratneshwer;Gupta M (Dep of computer Engineering, Institute of Technology, Banaras Hindu University, Varanasi-221 005, Email: anilkt@bhu.ac.in) : Need to redefine the testing process for component based software. Int J Inf Comput Sci 2007, 10(1), 53-63.

Importance of software testingand its implications with respect to software quality cannot be overemphasized. Testing process of Component Based Software has its own challenges, because it development process, system life cycle, coding style etc. are very different from traditional software development. The testing methods must be looked into a fresh to consider problems and possibilities of their applicability may call for redefinition. In CBSE, there will be parallel testing process; one for testing an individual component and other is testing of a Component Based System. Adding of components in system at run time, unavailability of component's source code, modification affect of component on whole system etc. leads the requirement of new testing requirements. These newer issues need to be addressed for any testing methodology of CBSE. The proposed research work aims at identifying software testing process and concepts that need redefinition in the context of CBSE. The idea is to evaluate whether the testing methodologies for conventional software development can be used for CBSE or there is a need to propse and develop newer methodologies for the purpose. The issues related to software testing are important because the slow rate the practive of CBSE may be result of the use of the software testing practices meant for non CBSE based software development.

10 ref

007957   Sumeet Singh;Gill N;Singh M P (Computer Engineering, Government Polytechnic, Sonipat-131 001 (Haryana), Email: sumeet gill 123@rediffmail.com) : Prediction of missed part of password security in windows 9X environment using feed forward artificial. Int J Inf Comput Sci 2007, 10(1), 21-32.

Alternate much secure technique for password security is provided in windows9x environment for generating the encrypted passwords fr any given input password on the basis of proper training of a feedforward neural network by using the Back Propagation learning Algorithm of Artificial Neural Network. Network uses the mapping technique to generate new encrypted passwork on the basis of previous training of the network based on encryption algorithm of Window's. The training is made on the basis of how the encryption algorithm, used by the Win9xforms the encrypted passwords for the given test input passwords. The network captures a mapping function for which the training has been provided and generates new encrypted passwords for any given input password, thereby eliminating the use of encryption algorithm. The importance of this technique is that encrypted passwords are not stored in any file but in parameters of Network and hence more secure. It can also predict the encrypted form of the number, which the user has been lost/missed by the user as a part of complete code.

4 illus, 8 ref

007956   Shah G A;Rathore T S (Electronics & Telecommunication Dep SFIT, , Borivil, Mumbai, Email: gautamshah@ieee.org) : Design, Development and applications of PC-based process control trainer for automation. IETE Tech Rev 2008, 25(1), 29-37.

Initially, Process Control was typically done in the analog domain using continuous-time signals with analog systems. However, as the complexity of the control function increased, it became very costly, and, at times, unfeasible to use only analog elements. The rapid evolution of digital computers caused a major shift to digital technologies, and led to the control action being done in the digital domain using discrete-time signals with digital systems. The main motive behind designing and developing the PC-Based Process Control Trainer (PCT) for automation is to have a system which is versatile, easy to use, interactive, intelligent, and quickly developed. Physical variables like temperature, fluid flow and levels at various points in the system are monitored and control action is provided to various heaters, stirrers, valves and pumps. One utilizes LABTECH's LT/CONTROL software package which reads the inputs from the standard data acquisition and control add-on cards. It performs various calculations as per the requirement and the results are used in the control strategy. It provides real-time data logging, data storage and real-time display control panel for the user interface with multiple display screens to view the system. The PCT is built, tested and found to work satisfactorily. About twenty experiments are set up and performed on it. These check various devices in the system, help in studying various types of control actions and automate the trainer for particular processes. The PCT has varied applications for automation. On the educational front, it can be used as a basic control laboratory. New experimental setups can be configured to study open loop and closed loop control systems for temperature, flow and level control. Automation of different processes with a choice of control actions can be done. From the industrial point of view, it provides an insight to industrial control; prototypes of process control systems can be built and used as a stepping stone to change the present manual or semi-automatic control to complete automation.

5 illus, 1 table, 15 ref

007955   Ram Kumar;Ramesh Kumar (Ashwani Kush Deartment of Comuter Sci and Appl, Kurukshetra University, Kurukshetra) : Security issues for wireless network. Int J Inf Comput Sci 2007, 10(1), 42-51.

Over recent years, wireless technology has enjoyed tremendous growth. wireless communication now reaches or is capable of eaching virtually every nook and corner on the earth. People exchange information everyday using wireless communication products. Wireless communications do not rely on any fixed infrastructure. Due to the open nature of wireless networks and their inherent lack of infrastructure, security exposures can be an impediment to basic network operation. The counter measures should be included in network function for early stage of their design, which at times becomes difficult to implement. This paper describes the challenges faced in wireless network security and issues related to the security of wireless networks. As security requirement and their implication vary, general security architecture for wireless network is very difficult and a more hybrid approach is the need of the hour. Some solutions to the secutity needs of the wireless medium have been suggested.

10 illus, 1 table, 12 ref

007954   Cuzzocrea A (ICAR Institute & DEIS Dep, University of Calabria, Italy, Email: cuzzocrea@si.deis.unical.it) : Querying unstructured and structured peer-to-peer networks: models, issues, algorithms. J Digital Inf Mgmt 2007, 5(4), 201-10.

Peer-to-Peer (P2P) networks are defined as a collection of peers that expose client/server functionalities simultaneously, P2P systems, built on top of P2P networks, support information sharing primitives and lookup mechanisms of data objects located on peers. It has been demonstrated that the P2P paradigm is able to efficiently capture models and, above all, dynamics of modern applications, beyond limitations of conventional produce/consumer paradigms. Traditionally, P2P primitives and mechanisms have been implemented by means of keyword-based search and matching operations. Modern P2P system require more complex query functionalities, beyond capabilities of DBMS-inspired models and algorithms. As a consequence, the issue of efficiently querying the under-ling P2P network is gaining momentum in the research community. Indeed, querying P2P networks, which can be in the unstructure and structure modes, plays a critical role in next-generation P2P systems, as its performance heavily affect the efficiency of the overall system. Starting from these considerations, in this paper we propose a survey on models, issues and algorithms for querying unstructured and structured P2P systems. We also put in evidence similarities and differences of state-of-the-art proposals appearing in literature, with critical discussion, and we provide a rigorous taxonomy of P2P query strategies. Finally, we complete our analytical contribution via highlighting future directions in this research field.

1 illus, 1 table, 55 ref

007953   Chauhan R K;Parveen Kumar;Dalai O S (Dep of Computer Sc & Applications, Kurukshetra University, Kurukshetra-136 119]) : Checkpointing and mobile distributed computing systems. Int J Inf Comput Sci 2007, 10(1), 13-20.

Mobile hosts are increasingly becoming common in distributed systems due to their availability, cost, and mobile connectivity. A host that can move while retaining its network connections is a Mobile Host. The existence of mobile nodes in a distributed system introduces new issues that need proper handling while designing a checkpointing algorithm for such systems. These issues are mobility, disconnection, finite power source, vulnerable to physical damage, lack of stable storage etc. Checkpointing is an efficients way of implementing fault tolerance in distributed systems. A checkpoint is a local state of a process saved on stable storage. In a distributed system, since the processes in the system do not share memory, a global state of the system is defined as a set of local states, one from each process. The state of channels corresponding to a global state is the set of messages sent but not yet received. In this paper, we study the system model of mobile distributed system and also introduce the concept of checkpointing and its categorization.

19 ref

007952   Bruno G;Garza P;Quintarelli E;Rossato R (Dipartimento di Automatica e Informatica - Politecnico di Torino, , Italy, Email: giulia.bruno.@polito.it) : Anomaly detection through quasi-functional dependency analysis. J Digital Inf Mgmt 2007, 5(4), 191-200.

Attention on the analysis of anomaly detection in databases is focused. Proposed a method, based on data mining algorithms, which allows one to infer the "normal behavior" of objects, by extracting frequent "rules" from a given dataset. These rules are described in the form of quasi-functional dependencies and mined from the dataset by using association rules. Our approach allows us to consequently analyze anomalies with respect to the previously inferred dependencies: given a quasi-functional dependency, it is possible to discover the related anomalies by querying either the original database or the association rules previously stored. By further investigating the nature of such anomalies, we can either derive the presence of erroneous data or highlight novel information which represents significant exceptions of frequent rules. Our method is independent of the considered database and directly infers rules from the data. The applicability of the proposed approach is validated through a set of experiments on XML databases, whose results are here reported.

2 illus, 13 tables, 23 ref

007951   Baltzer O;Rau Chaplin A; (Faculty of Computer Science, Dalhousie UNiversity, Halifax, NS, Canada, Email: obaltzer,Zeh N@cs.dal.ca) : Storage and indexing of relational OLAP views with mixed categorical and continuous dimensions. J Digital Inf Mgmt 2007, 5(4), 180-90.

Due to the widespread adoptation of location-based services and other spatial applications, data warehouses that store spatial information are becoming increasingly prevalent. Consequently, it is becoming important to extend the standard OLAP paradigm with features that support spatial analysis and aggregation. While traditional OLAP systems are limited to data characterized by strictly categorical feature dimensions, Spatial OLAP systems must provide support for both categorical and spatial feature dimensions. Such spatial feature dimensions are typically represented by continuous data values. In this paper we propose a technique for representing and indexing relational OLAP views with mixed categorical and continuous data. Our method builds on top of an established mechanism for standard OLAP and exploits characteristic properties of space-filling curves. It allows us to effectively represent and index mixed categorical and continuous data, while dynamically adapting to changes in dimension cardinality during updates. We have implemented the proposed storage and indexing methods and evaluated their build, update, and query times using both synthetic and real datasets. Our experiments show that the proposed methods based on Hilbert curves of dynamic resolutions offers significant performance advantages especially for view updates.

12 illus, 34 ref

007950   Ashok Kumar;Bansal N;Singla S;Sharma P C (Dep of Computer Sciences, Kurukshtra University, Kurukshetra) : Applications of computers in pharmacokinetic studies. Int J Inf Comput Sci 2007, 10(1), 64-74.

Pharmacokinetics is the quantitative study of drugs movement in, through and out of the body. Intensity of response is related to concentration of the drug at the site of action, which in turn is dependent on its pharmacokinetic properties. Computer technology has greatly accelerated the development of pharmacokinetics in recent years, contributing to an easier solution of complicated phasrmacokinetic equations and rapid modeling of pharmacokinetic processes. Comuter applications are also applied in the development of experimental study design, statistical data treatment, data manipulation, graphical representation of data pharmacokinetics models simulation and projection of prediction of drug actions. Computer models provide a valuable tool for the reduction in number of animal and human experiments/trials by careful planning and interpretation of these experiments when studying targeted pharmacokinetic parameters. They are helpful for evaluating changes in application protocols and of delivery systems for targeted site drug delivery and for extrapolating the results from animal studies to humans.

12 ref

007949   Altarawneh M S;Khor L C;Woo W L;Dlay S S (School of Electrical, Electronic and computer Engineering, University of Newcastle, Newcastle upon tyne, NE1 7 RU, United Kingdom, Email: mokhled.al-tarawneh@ncl.ac.uk) : Non reference fingerprint image validity via statistical weight calculation. J Digital Inf Mgmt 2007, 5(4), 220-4.

Validity check algorith (VCA) is prepared. The VCA is applied to the base image element statistical weight calculation because the image element statistical weight calculation because the image element (pixel) describes an image object with the contrast, brightness, clarity and noising attributes. Our algorithm depends on fingerprint object segmentation, background subtraction, total image thresholding and pixel weight calculation. A VTC2000DB1_B, TIMA databases was used to evaluate the VCA and it has been compared with NIST fingerprint image quality results. Correlation results indicate that the proposed algorithm is feasible in detecting low quality as well as non-fingerprint images.

3 illus, 2 tables, 11 ref