K P Soman

Plug-ins for GNU Radio Companion

This paper gives an insight on how to develop plug-ins (signal processing blocks) for GNU Radio Companion. GRC is on the monitoring computer and does bulk of the signal processing before transmission and after reception. The coding done in order to develop any block is discussed. A block that performs Huffman coding has been built. Huffman coding is a coding technique that gives a prefix code. A block that performs convolution coding at any desired rate using any generator polynomial has also been built. Both Huffman and Convolution coding are done on data stored in file sources by these blocks. This paper thus describes the ease of signal processing that can be attained by developing blocks in demand by changing the C++ and PYTHON codes of the HOWTO package. Being an open source it is available to all, is highly cost effective and is a field with great potential.

Computational thinking leads to computational learning: Flipped class room experiments in linear algebra

The latest concept evolving in pedagogy is flipped class room where class room is utilized for active learning by students with their peers and faculty. This necessitates development of new syllabus and pedagogy for each subject for class room activities. This paper attempt to propose spreadsheet based experiments in linear algebra that can be used to learn many abstract concepts that are very important for mastering many engineering disciplines. There is vast amount of evidence showing that the computational experiments support active learning and develop exploratory and inventive skill of students.

A synchronised tree adjoining Grammar for English to Tamil Machine Translation

Tree adjoining Grammar (TAG) is a rich formalism for capturing syntax and some limited semantics of Natural languages. The XTAG project has contributed a very comprehensive TAG for English Language. Although TAGs have been proposed nearly 40 years ago by Joshi et al, 1975, their usage and application in the Indian Languages have been very rare, predominantly due to their complexity and lack of resources. In this paper we discuss a new TAG system and methodology of development for Tamil Language that can be extended for other Indian languages. The trees are developed synchronously with a minimalistic grammar obtained by careful pruning of XTAG English Grammar. We also apply Chomskian minimalism on these TAG trees, so as to make them simple and easily parsable. Furthermore we have also developed a parser that can parse simple sentences using the above mentioned grammar, and generating a TAG derivation that can be used for dependency resolution. Due to the synchronous nature of these TAG pairs they can be readily adapted for Formalism based Machine Translation (MT) from English to Tamil and vice versa.

Multicast WebSDR implementation using RTL-SDR

The advent of internet provides better solution for many real time problems mainly audio streaming. Fast development in internet provides the pathway for accessing audio signals of the remote place. Software Defined Radio creates the platform of WebSDR, which provides the solution of online audio streaming. WebSDR allows many users to tune and listen simultaneously via internet. So far in the Indian sub-continent, there is no service of WebSDR server. In this paper, WebSDR server is created on Linux platform. This audio streaming platform helps in solving social problems during the course of disaster and flood. This server is created using RTL - SDR 2832U as the hardware platform which receives signals via a newly modeled omni directional antenna. Initially, the server is designed for 20 MHz bandwidth with the operating frequency of 90 MHz.

Hyperspectral image denoising using legendre Fenchel Transformation for improved Multinomial Logistic Regression based classification

The abundant spectral and spatial information in the hyperspectral images (HSI) are largely used in the field of remote sensing. Though there are highly sophisticated sensors to capture the hyperspectral imagery, they suffer from issues like hyperspectral noise and spectral mixing. The major challenges encountered in this field, demands the use of preprocessing techniques prior to hyperspectral image analysis. In this paper, we discuss the effective role of denoising by Legendre Fenchel Transformation (LFT) as a preprocessing method to improve the classification accuracy. Experimental time analysis shows that the computational efficiency of the proposed method is highly effective when compared with the existing preprocessing methods. LFT is based on the concept of duality which makes it a fast and reliable denoising strategy to effectively reduce the noise present in each band of the hyperspectral imagery, without losing much of the edge information. The denoising is performed on standard AVIRIS Indian Pines dataset. The performance of LFT denoising is evaluated by analysing the classification accuracy assessment measures. The denoised image is subjected to hyperspectral image classification using Multinomial Logistic Regression which learns the posterior probability distributions of each class. The potential of the proposed method is proved by the mean classification accuracy obtained experimentally without any post processing technique (94.4%), which is better when compared with the accuracies acquired by existing preprocessing techniques like Total Variation denoising and wavelet based denoising.

Hyperspectral image classification using Random Kitchen Sink and Regularized Least Squares

Kernel machines has gained considerable attention in the field of remote sensing for solving machine learning tasks, particularly in classification. Despite the fact that, kernel based methods produce comparatively better performance than traditional learning approaches, they are computationally expensive and requires large memory storage. In recent years, the concept of random features was introduced in kernel machines to solve this problem. This paper presents a new framework for hyperspectral image classification using Random Kitchen Sink (RKS) and Regularized Least Squares (RLS) classifier. The study shows that randomized features are economically powerful tool for hyperspectral image classification which produces significant improvement in classification accuracy. The proposed approach is tested on two standard hyperspectral datasets namely, Salinas-A and Indian Pines subset scene acquired by Airborne Visible Infrared Imaging Spectrometer (AVIRIS) sensor. A statistical comparison of the accuracies obtained on standard hyperspectral data with and without using Random Kitchen Sink algorithm for Regularized Least Squares classifier is analysed to show the effectiveness of the proposed method. The experimental results shows that the proposed method leads to improvement in Overall Accuracy from 85.12% to 98.58% and Kappa Coefficient from 0.8154 to 0.9822 for Salinas-A data scene. The analysis of Indian Pines subset scene shows that the proposed work results in significant improvement in Overall Accuracy from 62.76% to 93.79% and Kappa Coefficient from 0.5061 to 0.9160. The result analysis proves that random features of hyperspectral data as input to a standard linear classifier without the aid of any preprocessing produces better classification accuracy.