Automatic Speech Emotion Recognition (SER) is a current research topic in the field of Human Computer Interaction (HCI) with wide range of applications. The speech features such as, Mel Frequency cepstrum coefficients (MFCC) and Mel Energy Spectrum Dynamic Coefficients (MEDC) are extracted from speech utterance. The Support Vector Machine (SVM) is used as classifier to classify different emotional states such as anger, happiness, sadness, neutral, fear, from Berlin emotional database. The LIBSVM is used for classification of emotions. It gives 93.75% classification accuracy for Gender independent case 94.73% for male and 100% for female speech..

Security is one of the major concerns in communication networks and other online Internet based services, which are becoming pervasive in all kinds of domains like business, government, and society. Network security involves activities that all organizations, enterprises, and institutions undertake to protect the value and usability of their assets and to maintain the integrity and continuity of operations that are performed at their end. Network security exists on all the different layers of an OSI model, Application-level web security comes at the application layer and it refers to vulnerabilities inherent in the code of a web-application itself irrespective of the technologies in which it is implemented. Security in web applications is becoming very important because of the real time transactions that are required over the internet these days. Various attacks are carried out on the web applications and behind every attack; there is vulnerability of some types or the other. Now-a-days application-level vulnerabilities have been exploited with serious consequences: E-commerce sites are tricked by attackers and they lead into shipping goods for no charge, usernames and passwords have been cracked, and confidential and important credentials of users have been leaked. SQL Injection attacks and Cross-Site Scripting attacks are the two most common attacks on web application. Proposed method is a new policy based Proxy Agent, which classifies the request as a scripted request, or query based request, and then, detects the respective type of attack, if any in the request. This method detects both SQL injection attack as well as the Cross-Site Scripting attacks.

No abstract

Language transliteration is one of the important areas in NLP. Transliteration is very useful for converting the named entities (NEs) written in one script to another script in NLP applications like Cross Lingual Information Retrieval (CLIR), Multilingual Voice Chat Applications and Real Time Machine Translation (MT). The most important requirement of Transliteration system is to preserve the phonetic properties of source language after the transliteration in target language. In this paper, we have proposed the named entity transliteration for Hindi to English and Marathi to English language pairs using Support Vector Machine (SVM). In the proposed approach, the source named entity is segmented into transliteration units; hence transliteration problem can be viewed as sequence labeling problem. The classification of phonetic units is done by using the polynomial kernel function of Support Vector Machine (SVM). Proposed approach uses phonetic of the source language and n-gram as two features for transliteration.

This paper provide the way of finding the legitimacy of a packet by analyzing the number of hops that packet gone through before reaching at the destination. Problem with IP packet is that the contents of the packet can be changed easily. This is called IP spoofing, which is being very much used in Distributed Denialof-Service (DDoS) attacks. they are very hard to detect, there is no comprehensive solution.But attacker cannot control hop count. Since after sending the packet, he can not tamper TTL field, which is modified by every hop. By generating an IP to Hop-Count mapping table and inspecting it, spoofed packets can be identified. It is called HCF (Hop Count Filter). It is used to classify legitimate and spoofed packets with little collateral damage. HCF causes delay in critical path of packet processing in the kernel because of enormous IP2HC mapping table. This overhead is reduced by identifying the attackers in learning state and then drop spoofed packets in filtering state. It is implemented in the Linux kernel so as to reduce the CPU overhead in terms of interrupts which saves the resources.