1

Analysis of Spectral Unmixing to Extract the Pure Pixels using Endmembers Determination Algorithms
K. Nandhini, R. Porkodi

Abstract- - Over the past few decades linear mixing models shows a major contribution in a remote sensing field. At the time of data compilation, the linear mixing models ignore the scattering effects and secondary reflections also it expects the a priori in turn of topological and physical properties of the particular scene. In general LMM models for the spectral unmixing contain three major processes of steps which evolved in extracting the pure materials. The initial step is to calculate the number of endmembers, next step is to extract the pure spectral signature and last step is to calculate the abundance. This paper offers the view of background study in spectral unmixing. Experimented and analyzed the synthetic spectral data by applying three techniques called VCA, N-FindR and SISAL to extract the pure substances from the mixed pixel. The mean squared error for the VCA in both pure and non pure pixel assumptions are 0.00106 and computational time effort is 0.04 secs. VCA proves to be best when compared to other algorithms. Before determining the endmembers, SNR need to be estimated and HySime algorithm is used in this study to subspace the spectral data

2

Brain Tumor Exploration using Image Segmentation
M. Alamelumangai, M. Pushparani

Abstract- This paper defines about a brain tumor exploration using image segmentation. Brain tumor is a abnormal growth of tissue in human brain. It is a life threatening disease and its early detection is most important to save a life. A brief explanation about the cause and detection of brain tumor is discussed. The treatment and classification also presented in this paper. Image segmentation is a best method to detect the brain tumor from MRI image because it produced accurate results.

3

Two Level Text Data Encryption using DNA Cryptography
E. Vidhya, R. Rathipriya

Abstract- DNA Cryptography is one of new method in the cryptography research area. DNA can be used to encrypt the data in the form of storage and transmit and it also performs the computation. In DNA cryptography, the main role is to create a DNA sequence. The DNA sequence is created based on the information carrier and the biological technology. The main target of this paper is to increase the complexity of the DNA sequence. The main objective of this paper is to given the data in high security level. The proposed work of this paper is to provide two levels of security. The first level is to transform the plain text to an ASCII text with the shift key and then convert the text to a binary numbers. Apply the insertion method to binary numbers; convert the binary numbers to DNA sequence which is represented as cipher text. The receiver will apply the Insertion decryption method to cipher text the plaintext will appear. The Shannon entropy is used to measure the data compression and the time complexity is used to measure the execution time of the proposed work.

4

An Idiosyncratic Tool for Retrieving Legal Web Documents Using SSARC algorithm
V. Annapoorani/p>

Abstract- The practice of law necessarily involves a significant amount of research. In fact, the budding lawyers spend much of their work and time researching for the perfect information. Law and order is a field too vast, too varied and too detailed for any budding lawyer to keep all of it. Furthermore, the law is a living thing, it tends to change over time. Thus, in order to answer client's legal questions, lawyers typically conduct research into the laws affecting their clients. One of the most challenging problems is to incorporate domain knowledge in order to retrieve more relevant information from a collection based on a query given by the user.

5

Evolving Trends in Conversational Systems with Natural Language Processing
V. Sriguru, D. Francis Xavier Christopher

Abstract- Today, with digitization of everything, 80% of the data being created is unstructured. Audio, video, our social footprints, the data generated from conversations between customer service reps, tons of legal documents, and texts processed in financial sectors are examples of unstructured data stored in Big Data. Organizations are turning to natural language processing (NLP) technology to derive understanding from the myriad unstructured data available online, in call logs, and in other sources. In NLP, chatbots and intelligent automation are on the rise, enterprises should look at NLP infused chatbots to drive cost saving, operational efficiencies, and enhanced customer experiences throughout their businesses.