Research Highlight

De-Speckling of Synthetic Aperture Radar Using Discrete Fourier Transform

A novel technique is propounded, which uses Boxcar filter for reduction of speckle-noise whilst retaining the point targets, edges and texture with the inclusion of Discrete Fourier Transform (DFT) in the speckle reduction framework.

Sanjav Shitole, Vijal Jain, V. S. K. Vanama

Urban area classification with quad-pol L-band ALOS-2 SAR data: A case of Chennai city, India

The fully-polarimetric L-band ALOS-2 Synthetic Aperture Radar (SAR) data of the two land regions, having heterogeneous land uses, as high-rise high-density and medium-rise low-density of the Chennai city is used for rapid identification of the urban regions. A comparative assessment of the two supervised classification algorithms such as Wishart and Support Vector Machine (SVM) is presented to classify urban areas from non urban areas. The results of classification with the two classes as urban and non urban indicate that the SVM outperformed the Wishart supervised classification algorithm.

Dhanashri S. Kanade, Venkata Sai Krishna Vanama and Sanjay Shitole

Patent-Smart Barricades for traffic congestion reduction

This project proposes an electronic barricade system which will divert this one way traffic to the underutilized side of the road during peak hours. The barricade will move forward & backward for vehicles to change lanes. Diverting the traffic again depends on the frequency of the traffic on the reverse side, type of area where the vehicle wanted to reach(needs to have a smart electronics board for information), Type of local area (City or outside the city).

Ms Charushila and Dr Nema Shikha

Traffic prediction using IoT and Machine Learning

In this context, using an improved deep learning model, the complex interactions among roadways, transportation traffic, environmental elements, and traffic crashes have been explored. Once the real time traffic data is available an optimal traffic flow prediction model is created using optimized HMM framework, which directly predicts the corresponding traffic flow.

Ms Charushila and Dr Nema Shikha

Low Complexity IAOR Signal Detection for Uplink GSM - Massive MIMO Systems

In the MMSE detector, the computational complexity to calculate the inverse of the channel matrix is ​​very high. Low complexity and energy-efficient signal detection algorithm called Improved Accelerated over Relaxation (IAOR) is implemented for large-scale MIMO systems. The algorithm can iteratively detect the transmitted signal without the complicated inversion of the channel matrix.

Ms Seema H. and Dr Nema Shikha