R. Venkatesh

A Hybrid model of Neural Network Approach for Speaker independent Word Recognition

Speech Recognition by computer is a process where speech signals are automatically converted into the corresponding sequence of words in text. When the training and testing conditions are not similar, statistical speech recognition algorithms suffer from severe degradation in recognition accuracy. So we depend on intelligent and recognizable sounds for common communications. In this research, word inputs are recognized by the system and executed in the form of text corresponding to the input word. In this paper, we propose a hybrid model by using a fully connected hidden layer between the input state nodes and the output. We have proposed a new objective function for the neural network using a combined framework of statistical and neural network based classifiers. We have used the hybrid model of Radial Basis Function and the Pattern Matching method. The system was trained by Indian English word consisting of 50 words uttered by 20 male speakers and 20 female speakers. The test samples comprised 30 words spoken by a different set of 20 male speakers and 20 female speakers. The recognition accuracy is found to be 91% which is well above the previous results.

Overview on Key Distribution Primitives in Wireless Sensor Network

Owing to the security requirements of wireless sensor network, the background of Wireless Sensor Network (WSN) is to be analyzed with different threats and attack models. Physical compromising of sensor nodes by an adversary is an emerging problem in sensor network and accordingly, it is necessary to provide an environment with efficient key management techniques due to resource constraints on sensor network. It is obvious to evaluate the efficiency of symmetric key management schemes for WSN, since it is not feasible to use traditional key management techniques such as asymmetric key cryptosystem and Key Distribution Center (KDC). This survey paper aims to report an extensive study on classification of pairwise key pre-distribution techniques. Further a smaller portion of analysis and security issues using pairwise key management is pronounced. Analysed results shows that polynomial pool based method have higher probability of communication by non-compromised nodes when compared with other schemes. The proposed survey effectively track the merits and demerits of different key predistribution schemes, also the communication overhead and memory overhead is reduced in polynomial pool based method during execution.

Robust estimation of incorrect data using relative correlation clustering technique in wireless sensor networks

Data inaccuracy is an important problem in wireless sensor networks, since the accuracy is affected by harsh environments and malicious nodes. The reason for this data inaccuracy is the improper identification of outliers. To detect exact outliers in the wireless sensor networks, we propose the relative correlation based clustering (RCC) technique with high data accuracy and low computational overhead. Identifying spatial, temporal correlation and attribute correlation is the first phase of the proposed algorithm. The second phase is optimal cluster formation and outlier classification based on two correlation levels. The inference of the proposed idea shows high outlier detection rate with different outlier corruption level. Moreover, our results when compared with previous approach taking the same data into consideration clearly outperform them, identifying high level of detection rate (99.87%) in the top-line with near to the ground false alarm rate.

Speaker independent speech recognition system based on phoneme identification

Speaker independent speech recognition is important for successful development of speech recognizers in most real world applications. While speaker dependent speech recognizers have achieved close to 100% accuracy, the speaker independent speech recognition systems have poor accuracy not exceeding 75%.In this paper, we describe a two-module speaker independent speech recognition system for all-Indian English speech. The first module performs phoneme recognition using two-level neural networks. The second module executes word recognition from the string of phonemes employing Hidden Markov Model. The system was trained by Indian English speech consisting of 3000 words uttered by 200 speakers. The test samples comprised 1000 words spoken by a different set of 50 speakers. The recognition accuracy is found to be 94% which is well above the previous results.

Implementation of biometrics based security system with integrated techniques

This paper deals with the design of an automated system for ration shop using fingerprint and e-card reader. The proposed system applies integrated security processing and introduces the verification chamber that analyses three categories of people like Above Poverty Line, Below Poverty Line and Antyodaya, which allows rights rendered to a right citizen. This system also involves authentication without passwords performing either bar code reading or finger print reading. The plotting technique is proposed to avoid fake fingerprint impressions. To distort the influence of reputed corrupters, a brand new algorithm is designed in such a manner that even the vendor is clueless of how the code is accessed. We perform automations such that machines maintain secrets. JavaScript implementations and hardware checking has been done for the analysis of encryption and decryption techniques. The systems usage is as easy as falling off a log and has no bar for the illiterates.

Peak: Power efficiency analysis for key distribution in Wireless Sensor Network

Secure Distributed Wireless Sensor Network (DWSN) is empowered by using an efficient key management technique. Battery powered sensor nodes faces precarious aspects during key distribution in order to reduce the energy consumption for the components of sensor nodes. Thus, implementing a key distribution algorithm should possess minimum power consumption. The proposed work steps towards greater heights by integrating power module with pairwise key establishment using group configuration methodology. We present an investigation of power consumption using STEM (Sparse Topology and Energy Management) protocol on sensor nodes (SNs) during the pairwise key establishment using graphical tools. Further memory utilization is reduced due to less number of keys generated from group configuration methodology. Analytical results of this PEAK (Power Efficiency Analysis for Key Distribution) show that energy efficiency is increased with sensor nodes while establishing pairwise key using group configuration when compared to existing key predistribution techniques.