Comparison of Statistical and Semantic Similarity Techniques for Paraphrase Identification

This paper compares statistical technique of paraphrase identification to semantic technique of paraphrase identification. The statistical techniques used for comparison are word set and word-order based methods where as the semantic technique used is the WordNet similarity matrix method described by Stevenson and Fernando in [3].

Techniques to Improve the word alignments in Statistical Machine Translation from English to Malayalam

In Statistical Machine Translation from English to Malayalam, an unseen English sentence is translated into its equivalent Malayalam translation using statistical models like translation model, language model and a decoder. A parallel corpus of English-Malayalam is used in the training phase. Word to word alignments has to be set up among the sentence pairs of the source and target language before subjecting them for training. This paper is deals with the techniques which can be adopted for improving the alignment model of SMT. Incorporating the parts of speech information into the bilingual corpus has eliminated many of the insignificant alignments. Also identifying the name entities and cognates present in the sentence pairs has proved to be advantageous while setting up the alignments. Moreover, reduction of the unwanted alignments has brought in better training results. Experiments conducted on a sample corpus have generated reasonably good Malayalam translations and the results are verified with F measure, BLEU and WER evaluation metrics

Significance Of Classification Techniques In Prediction Of Learning Disabilities

The aim of this study is to show the importance of two classification techniques, viz. decision tree and clustering, in prediction of learning disabilities (LD) of school-age children. LDs affect about 10 percent of all children enrolled in schools. The problems of children with specific learning disabilities have been a cause of concern to parents and teachers for some time. Decision trees and clustering are powerful and popular tools used for classification and prediction in Data mining. Different rules extracted from the decision tree are used for prediction of learning disabilities. Clustering is the assignment of a set of observations into subsets, called clusters, which are useful in finding the different signs and symptoms (attributes) present in the LD affected child. In this paper, J48 algorithm is used for constructing the decision tree and K-means algorithm is used for creating the clusters. By applying these classification techniques, LD in any child can be identified

Pattern Analysis Techniques for the Recognition of Unconstrained Handwritten Malayalam Character Images

The objective of the study is to develop a hand written character recognition system that could recognisze all the characters in the mordern script of malayalam language at a high recognition rate

Faster techniques to evolve wavelet coefficients for better fingerprint image compression

In this article, techniques have been presented for faster evolution of wavelet lifting coefficients for fingerprint image compression (FIC). In addition to increasing the computational speed by 81.35%, the coefficients performed much better than the reported coefficients in literature. Generally, full-size images are used for evolving wavelet coefficients, which is time consuming. To overcome this, in this work, wavelets were evolved with resized, cropped, resized-average and cropped-average images. On comparing the peak- signal-to-noise-ratios (PSNR) offered by the evolved wavelets, it was found that the cropped images excelled the resized images and is in par with the results reported till date. Wavelet lifting coefficients evolved from an average of four 256 256 centre-cropped images took less than 1/5th the evolution time reported in literature. It produced an improvement of 1.009 dB in average PSNR. Improvement in average PSNR was observed for other compression ratios (CR) and degraded images as well. The proposed technique gave better PSNR for various bit rates, with set partitioning in hierarchical trees (SPIHT) coder. These coefficients performed well with other fingerprint databases as well.

Development of Hierarchical Clustering Techniques for Gridded Data from Mixed Data Sequences

Knowledge discovery in databases is the non-trivial process of identifying valid, novel potentially useful and ultimately understandable patterns from data. The term Data mining refers to the process which does the exploratory analysis on the data and builds some model on the data. To infer patterns from data, data mining involves different approaches like association rule mining, classification techniques or clustering techniques. Among the many data mining techniques, clustering plays a major role, since it helps to group the related data for assessing properties and drawing conclusions. Most of the clustering algorithms act on a dataset with uniform format, since the similarity or dissimilarity between the data points is a significant factor in finding out the clusters. If a dataset consists of mixed attributes, i.e. a combination of numerical and categorical variables, a preferred approach is to convert different formats into a uniform format. The research study explores the various techniques to convert the mixed data sets to a numerical equivalent, so as to make it equipped for applying the statistical and similar algorithms. The results of clustering mixed category data after conversion to numeric data type have been demonstrated using a crime data set. The thesis also proposes an extension to the well known algorithm for handling mixed data types, to deal with data sets having only categorical data. The proposed conversion has been validated on a data set corresponding to breast cancer. Moreover, another issue with the clustering process is the visualization of output. Different geometric techniques like scatter plot, or projection plots are available, but none of the techniques display the result projecting the whole database but rather demonstrate attribute-pair wise analysis

Automatic Segmentation Framework for Primary Tumors From Brain MRIs Using Morphological Filtering Techniques

This paper describes a novel framework for automatic segmentation of primary tumors and its boundary from brain MRIs using morphological filtering techniques. This method uses T2 weighted and T1 FLAIR images. This approach is very simple, more accurate and less time consuming than existing methods. This method is tested by fifty patients of different tumor types, shapes, image intensities, sizes and produced better results. The results were validated with ground truth images by the radiologist. Segmentation of the tumor and boundary detection is important because it can be used for surgical planning, treatment planning, textural analysis, 3-Dimensional modeling and volumetric analysis

Habitat ecology and food and feeding of the herring bow crab Varuna litterata (Fabricius, 1798) of Cochin backwaters, Kerala, India

Habitat ecology and food and feeding of the herring bow crab, Varuna litterata of Cochin Backwaters, Kerala, India were investigated for a period of one year (April 2011-March 2012). Among the 15 stations surveyed, the crabs were found to occur only in 4 stations, which had a close proximity to the sea. Sediment analysis of the stations revealed that the substratum of these stations is sandy in nature and is rich in organic carbon content (0.79% to 1.07%). These estuarine crabs is euryhaline and are found to be distributed in areas with a sandy substratum, higher organic carbon content and more tidal influx. The stomach contents analysis of crabs examined showed that their diet included crustacean remains, plants, sand and debris, fishes, miscellaneous group and unidentified matter. In adults and sub-adults, crustaceans formed the dominant food group, while in juveniles, sand and debris formed the dominant group. From the present study, V. litterata was found to be a predatory omnivore capable of ingesting both animal and plant tissues

Development of Directionally Adaptive Techniques for Single Image Super-Resolution

Super Resolution problem is an inverse problem and refers to the process of producing a High resolution (HR) image, making use of one or more Low Resolution (LR) observations. It includes up sampling the image, thereby, increasing the maximum spatial frequency and removing degradations that arise during the image capture namely aliasing and blurring. The work presented in this thesis is based on learning based single image super-resolution. In learning based super-resolution algorithms, a training set or database of available HR images are used to construct the HR image of an image captured using a LR camera. In the training set, images are stored as patches or coefficients of feature representations like wavelet transform, DCT, etc. Single frame image super-resolution can be used in applications where database of HR images are available. The advantage of this method is that by skilfully creating a database of suitable training images, one can improve the quality of the super-resolved image. A new super resolution method based on wavelet transform is developed and it is better than conventional wavelet transform based methods and standard interpolation methods. Super-resolution techniques based on skewed anisotropic transform called directionlet transform are developed to convert a low resolution image which is of small size into a high resolution image of large size. Super-resolution algorithm not only increases the size, but also reduces the degradations occurred during the process of capturing image. This method outperforms the standard interpolation methods and the wavelet methods, both visually and in terms of SNR values. Artifacts like aliasing and ringing effects are also eliminated in this method. The super-resolution methods are implemented using, both critically sampled and over sampled directionlets. The conventional directionlet transform is computationally complex. Hence lifting scheme is used for implementation of directionlets. The new single image super-resolution method based on lifting scheme reduces computational complexity and thereby reduces computation time. The quality of the super resolved image depends on the type of wavelet basis used. A study is conducted to find the effect of different wavelets on the single image super-resolution method. Finally this new method implemented on grey images is extended to colour images and noisy images

Development of 2-D MRT based Image Compression Techniques

The thesis explores the area of still image compression. The image compression techniques can be broadly classified into lossless and lossy compression. The most common lossy compression techniques are based on Transform coding, Vector Quantization and Fractals. Transform coding is the simplest of the above and generally employs reversible transforms like, DCT, DWT, etc. Mapped Real Transform (MRT) is an evolving integer transform, based on real additions alone. The present research work aims at developing new image compression techniques based on MRT. Most of the transform coding techniques employ fixed block size image segmentation, usually 8×8. Hence, a fixed block size transform coding is implemented using MRT and the merits and demerits are analyzed for both 8×8 and 4×4 blocks. The N2 unique MRT coefficients, for each block, are computed using templates. Considering the merits and demerits of fixed block size transform coding techniques, a hybrid form of these techniques is implemented to improve the performance of compression. The performance of the hybrid coder is found to be better compared to the fixed block size coders. Thus, if the block size is made adaptive, the performance can be further improved. In adaptive block size coding, the block size may vary from the size of the image to 2×2. Hence, the computation of MRT using templates is impractical due to memory requirements. So, an adaptive transform coder based on Unique MRT (UMRT), a compact form of MRT, is implemented to get better performance in terms of PSNR and HVS The suitability of MRT in vector quantization of images is then experimented. The UMRT based Classified Vector Quantization (CVQ) is implemented subsequently. The edges in the images are identified and classified by employing a UMRT based criteria. Based on the above experiments, a new technique named “MRT based Adaptive Transform Coder with Classified Vector Quantization (MATC-CVQ)”is developed. Its performance is evaluated and compared against existing techniques. A comparison with standard JPEG & the well-known Shapiro’s Embedded Zero-tree Wavelet (EZW) is done and found that the proposed technique gives better performance for majority of images

A study of the techniques of the Hindi drama: Post Prasad Period (1935 - 1965)

HINDI

Spatially Adaptive Image Denoising Techniques Using Directionlets

The aim of the thesis was to design and develop spatially adaptive denoising techniques with edge and feature preservation, for images corrupted with additive white Gaussian noise and SAR images affected with speckle noise. Image denoising is a well researched topic. It has found multifaceted applications in our day to day life. Image denoising based on multi resolution analysis using wavelet transform has received considerable attention in recent years. The directionlet based denoising schemes presented in this thesis are effective in preserving the image specific features like edges and contours in denoising. Scope of this research is still open in areas like further optimization in terms of speed and extension of the techniques to other related areas like colour and video image denoising. Such studies would further augment the practical use of these techniques.

Studies on nitrifying microorganisms in Cochin Estuary and adjacent coastal waters

This thesis entitled “Studies on Nitrifying Microorganisms in Cochin Estuary and Adjacent Coastal Waters” reports for the first time the spatial andtemporal variations in the abundance and activity of nitrifiers (Ammonia oxidizingbacteria-AOB; Nitrite oxidizing bacteria- NOB and Ammonia oxidizing archaea-AOA) from the Cochin Estuary (CE), a monsoon driven, nutrient rich tropicalestuary along the southwest coast of India. To fulfil the above objectives, field observations were carried out for aperiod of one year (2011) in the CE. Surface (1 m below surface) and near-bottomwater samples were collected from four locations (stations 1 to 3 in estuary and 4 in coastal region), covering pre-monsoon, monsoon and post-monsoon seasons. Station 1 is a low saline station (salinity range 0-10) with high freshwater influx While stations 2 and 3 are intermediately saline stations (salinity ranges 10-25). Station 4 is located ~20 km away from station 3 with least influence of fresh water and is considered as high saline (salinity range 25- 35) station. Ambient physicochemical parameters like temperature, pH, salinity, dissolved oxygen (DO), Ammonium, nitrite, nitrate, phosphate and silicate of surface and bottom waters were measured using standard techniques. Abundance of Eubacteria, total Archaea and ammonia and nitrite oxidizing bacteria (AOB and NOB) were quantified using Fluorescent in situ Hybridization (FISH) with oligonucleotide probes labeled withCy3. Community structure of AOB and AOA was studied using PCR Denaturing Gradient Gel Electrophoresis (DGGE) technique. PCR products were cloned and sequenced to determine approximate phylogenetic affiliations. Nitrification rate in the water samples were analyzed using chemical NaClO3 (inhibitor of nitrite oxidation), and ATU (inhibitor of ammonium oxidation). Contribution of AOA and AOB in ammonia oxidation process was measured based on the recovered ammonia oxidation rate. The contribution of AOB and AOA were analyzed after inhibiting the activities of AOB and AOA separately using specific protein inhibitors. To understand the factors influencing or controlling nitrification, various statistical tools were used viz. Karl Pearson’s correlation (to find out the relationship between environmental parameters, bacterial abundance and activity), three-way ANOVA (to find out the significant variation between observations), Canonical Discriminant Analysis (CDA) (for the discrimination of stations based on observations), Multivariate statistics, Principal components analysis (PCA) and Step up multiple regression model (SMRM) (First order interaction effects were applied to determine the significantly contributing biological and environmental parameters to the numerical abundance of nitrifiers). In the CE, nitrification is modulated by the complex interplay between different nitrifiers and environmental variables which in turn is dictated by various hydrodynamic characteristics like fresh water discharge and seawater influx brought in by river water discharge and flushing. AOB in the CE are more adapted to varying environmental conditions compared to AOA though the diversity of AOA is higher than AOB. The abundance and seasonality of AOB and NOB is influenced by the concentration of ammonia in the water column. AOB are the major players in modulating ammonia oxidation process in the water column of CE. The distribution pattern and seasonality of AOB and NOB in the CE suggest that these organisms coexist, and are responsible for modulating the entire nitrification process in the estuary. This process is fuelled by the cross feeding among different nitrifiers, which in turn is dictated by nutrient levels especially ammonia. Though nitrification modulates the increasing anthropogenic ammonia concentration the anthropogenic inputs have to be controlled to prevent eutrophication and associated environmental changes.