Renu Dhir

A Frequent Concepts Based Document Clustering Algorithm

This paper presents a novel technique of document clustering based on frequent concepts. The proposed technique, FCDC (Frequent Concepts based document clustering), a clustering algorithm works with frequent concepts rather than frequent items used in traditional text mining techniques. Many well known clustering algorithms deal with documents as bag of words and ignore the important relationships between words like synonyms. the proposed FCDC algorithm utilizes the semantic relationship between words to create concepts. It exploits the WordNet ontology in turn to create low dimensional feature vector which allows us to develop a efficient clustering algorithm. It uses a hierarchical approach to cluster text documents having common concepts. FCDC found more accurate, scalable and effective when compared with existing clustering algorithms like Bisecting K-means , UPGMA and FIHC.

Script Identification of Pre-segmented Multi-font Characters and Digits

Character recognition problems of distinct scripts have their own script specific characteristics. The state-of-art optical character recognition systems use different methodolgies, to recognize different script characters, which are most effective for the corresponding script. The identificaton of the script of the individual character has not brought much attention between researchers, most of the script identification work is on document, line and word level. In this multilingual/multiscript world presence of different script characters in a single document is very common. We here propose a system to encounter such adverse situation in context of English and Gurumukhi Script. Experiments on multifont and multisized characters with Gabor features based on directional frequency and Gradient features based on gradient information of an individual character to identify it as Gurumukhi or English and also as character or numeral are reported here. Treating it as four class classification problem, multi-class Support Vector Machine(One Vs One) has been used for classification. We got promising results with both types of features. The average identification rates obtained with Gabor and Gradient features are 98.9% and 99.45% respectively.

A range free skew detection technique for digitized Gurmukhi script documents

In this paper, a range free skew detection technique for machine printed Gurmukhi documents is presented. This approach can easily be extended to other Indian language scripts such as Devnagri and Bakngla. Most characters in these scripts have horizontal lines at the top called headlines. The characters forming a word are joined at the top by headlines, so that the word appears as one single component with a headline. The ratio of pixel density above and below the headline of any word in Gurmukhi script is always less than 1. These inherent characteristics of the script have been employed and a new algorithm based on the projection profile method has been devised. By inspecting horizontal and vertical projections at different angles in range [0/spl deg/, 90/spl deg/], the skew angle of the document in range [-180/spl deg/, 180/spl deg/] can be determined. Thus this approach is not limited to any range of skew angle and skewness in any document with orientation portrait or landscape and placed at any angle can easily be detected and removed.

Performance Comparison of Devanagari Handwritten Numerals Recognition

In this paper an automatic recognition system for isolated Handwritten Devanagari Numerals is proposed and compared the recognition rate with different classifier. We presented a feature extraction technique based on recursive subdivision of the character image so that the resulting sub images at each iteration have balanced numbers of foreground pixels as possible. Database, provided by Indian Statistical Institute, Kolkata, have 22547 grey scale images written by 1049 persons and obtained 98.98% highest accuracy with SVM classifier. Results are compared with KNN and Quadratic classifier.

Cryptanalysis and Performance Evaluation of Enhanced Threshold Proxy Signature Scheme Based on RSA for Known Signers

In these days there are plenty of signature schemes such as the threshold proxy signature scheme (Kumar and Verma 2010). The network is a shared medium so that the weakness security attacks such as eavesdropping, replay attack, and modification attack. Thus, we have to establish a common key for encrypting/decrypting our communications over an insecure network. In this scheme, a threshold proxy signature scheme based on RSA, any or more proxy signers can cooperatively generate a proxy signature while or fewer of them cannot do it. The threshold proxy signature scheme uses the RSA cryptosystem to generate the private and the public key of the signers (Rivest et al., 1978). Comparison is done on the basis of time complexity, space complexity, and communication overhead. We compare the performance of four schemes (Hwang et al. (2003), Kuo and Chen (2005), Yong-Jun et al. (2007), and Li et al. (2007), with the performance of a scheme that has been proposed earlier by the authors of this paper. In the proposed scheme, both the combiner and the secret share holder can verify the correctness of the information that they are receiving from each other. Therefore, the enhanced threshold proxy signature scheme is secure and efficient against notorious conspiracy attacks.

Recognition of Devanagari Handwritten Numerals using Gradient Features and SVM

Recognition of Indian languages is a challenging problem. In Optical Character Recognition (OCR), acharacter or symbol to be recognized can be machine printed or handwritten characters/numerals. Several approaches in the past have been proposed that deal with problem of recognition of numerals/character depending on the type of feature extracted and way of extracting them. In this paper also a recognition system for isolated Handwritten Devanagari Numerals has been proposed. The proposed system is based on the division of sample image into sub-blocks and then in each sub-block Strength of Gradient is accumulated in 8 standard directions in which Gradient Direction is decomposed resulting in a feature vector with dimensionality of 200. Support Vector Machine (SVM) is used for classification. Accuracy of 99.60% has been obtained by using standard dataset provided by ISI (Indian Statistical Institute) Kolkata. General Terms Pattern Recognition, Indian Scripts, Optical Character Recognition.

Bandwidth Delay Quality Parameter Based Multicast Congestion Control

Computer network is an important phenomenon for digital information world. Computer network having the various problem due to more demand such as congestion control security, reliability, scalability, fairness etc. Multicast service helps computer network to flow information from one end to another end. In this paper, we provide BDQP approach to minimize the congestion control. NS-2 result shows, BDQP congestion control scheme minimizes the congestion and provides better network performance to provide more quality data.

Opinion mining of news headlines using SentiWordNet

Opinion Mining (also known as “Sentiment Analysis”) is an area of text classification which continuously gives its contribution in research field. The main objective of Opinion mining is Sentiment Classification i.e. to classify the opinion into positive or negative classes. SentiWordNet is an opinion lexicon derived from the WordNet database where each term is associated with some numerical scores indicating positive and negative sentiment information. Up until recently most researchers presented opinion mining of online user generated data like reviews, blogs, comments, articles etc. Opinion mining for offline user generated data like newspaper is unconcerned so far despite the fact that it is also explored by many users. As a first step, this paper present opinion mining for newspaper headlines using SentiWordNet. Further, most of the researchers implement the opinion mining by separating out the adverb-adjective combination present in the statements or classifying the verbs of statements. On the other hand, in this paper we analyze each and every word in the News headline whether it is a noun, verb, adverb, adjective or any other part-of-speech. During experiment, python packages are used to classify words. Then SentiWordNet 3.0 is used to identify the positive and negative score of each word thus evaluating the total positive/negative impact in that news headline.

Software Architecture Recovery using Genetic Black Hole Algorithm

Software clustering is a technique that is used to manage a software system by partitioning it into smaller subsystems containing highly related modules. Search-based software clustering techniques are found to be beneficial in effective partitioning of software systems. In this paper, we propose a search-based technique that is based on a combination of a nature-inspired black-hole algorithm and a genetic algorithm for software clustering. In order to evaluate the success of this approach, it has been applied to some real-world software systems. It is observed that this approach deduces a structure similar to the original architecture of the software system concerned.

Analysis and Design of Protocol for Enhanced Threshold Proxy Signature Scheme Based on RSA for Known Signers

Many threshold proxy signature schemes are proposed in which the t out of n threshold schemes are deployed; but they still lack the property of security. In this research paper, secret sharing proxy signature could permit the shares of designated signers, called proxy signers, renew their own proxy shares periodically without changing the secret. In particular, our scheme applies the (t, n) threshold proxy signature scheme and allows any t or more then t signers to form a designated group from n proxy signers to sign messages on behalf of the original signer. In the proposed scheme, furthermore, a proxy signer can recover his/her own share from t other proxy shares without revealing any information about other proxy shares. Unless more than t other proxy signers cooperate and collude, the secret share algorithm is always secure. We compare the performance of four schemes: Hwang et al., Wen et al., Geng et al. and Fengying et al. with the performance of a scheme that has been proposed by the authors of this article earlier. In the proposed scheme, both the combiner and the secret share holder can verify the correctness of the information that they are receiving from each other. Therefore, the enhanced threshold proxy signature scheme is secure and efficient against notorious conspiracy attacks.