Anti-dermatophytic activity of Chrysosporium keratinophillum against species of the genera Trichophyton, Microsporum and Epidermophyton floccosum was tested in vitro. When C. keratinophillum and different species of dermatophytes were inoculated on Sabouraud's dextrose agar plates 2 cm apart, no antagonistic effect of C. keratinophillum on the mycelial growth of dermatophytes was observed. However, conidia production was not observed on the hyphae of Trichophyton rubrum, Trichophyton tonsurans and E. floccosum grown near C. keratinophillum. The secretory substances released by C. keratinophillum inhibited the growth of T. rubrum, T. tonsurans, Trichophyton mentagrophytes var. interdigitale and E. floccosum at a concentration of 2,000 microg ml(-1) when tested by broth dilution technique. No inhibition of the growth was observed for Microsporum gypseum and Microsporum nanum. The anti-fungal activity of secretory substances released by C. keratinophillum was recorded to be heat stable. Results of the present study suggest that the anti-dermatophytic activity of the secretory substances of C. keratinophillum on T. rubrum, T. mentagrophytes var. interdigitale, T. tonsurans and E. floccosum may be responsible in part, for the absence of these dermatophyte species in soil. Considering the global prevalence of C. keratinophillum in soil one may speculate that the anti-dermatophytic activity of C. keratinophillum is one of the early events for the evolutionary divergence of saprophytic archi-dermatophytes to obligate parasitic dermatophyte species.

No abstract

Phishing is a form of online fraud that aims to steal a user's sensitive information such as online banking passwords or credit card numbers. In this paper, we present a technique to quickly detect suspected email using Neural Network Pruning approach. The goal is to determine whether the email is suspected or legitimate. A Multilayer feedforward neural network with Pruning Strategy is used for Feature Extraction and extracted features are used for identifying email as phishing email. Pruning Strategy extracts important features which are playing a key role in identifying phishing mail which looks similar to a legitimate one. To verify the feasibility of the proposed approach experimental evaluation has been performed using a dataset composed of phishing emails along with legitimate emails. The experimental results are satisfactory in terms of false positives and false negatives. The results of conducted test indicated good identification rate with very short processing time.

A method has been proposed to classify handwritten Arabic numerals in its compressed form using partitioning approach, Leader algorithm and Neural network. Handwritten numerals are represented in a matrix form. Compressing the matrix representation by merging adjacent pair of rows using logical OR operation reduces its size in half. Considering each row as a partitioned portion, clusters are formed for same partition of same digit separately. Leaders of clusters of partitions are used to recognize the patterns by Divide and Conquer approach using proposed ensemble neural network. Experimental results show that the proposed method recognize the patterns accurately.

Abstract. In this paper an efficient method has been proposed to classify handwritten numerals using leader algorithm and Radial Basis Function network. Handwritten numerals are represented in matrix form and clusters with leaders are formed for each row of each digit separately. Every leader is with single target digit. Duplication patterns are avoided from the cluster leaders by combining those in a single pattern with target vectors having corresponding bits in on mode. Now resultant target vectors are with 10 bits corresponding to the number of digits considered for classification. Constructed leaders are trained using Radial Basis Function network. Experimental results show that the minimum number of patterns are enough for training compared to total patterns and it has been observed that convergency is fast during training. Also the number of resultant leaders after avoiding duplication patterns are less and the number of bits in each resultant pattern is 12.