Department of Electrical Engineering

Indian Institute of Technology Palakkad&nbsp;(IIT Palakkad or IIT PKD) is a public autonomous&nbsp;engineering&nbsp;and&nbsp;research&nbsp;institute located in&nbsp;Palakkad,&nbsp;Kerala. It was&nbsp;one of the five new&nbsp;IITs&nbsp;proposed in the&nbsp;2014 Union budget of India. The campus was inaugurated on 3 August 2015. The institute has 94 faculty, 978 students, and 63 non-teaching staffs.

IT Palakkad currently offers four-year Bachelor of Technology (B.Tech) and two years MS programmes in 8 different engineering disciplines including&nbsp;Computer Science, Electrical, Mechanical, Civil among others.

&nbsp;

IIT Palakkad

This article demonstrates the chip-less Wi-Fi system design, and its working mechanism is discussed. Many human activities involve interaction with passive objects, and one of the best solutions is introducing Wi-Fi systems. As data can be transferred through the wire and wirelessly, Wi-Fi would be the better choice to transfer data wirelessly. Here, a Wi-Fi touch detection system consists of an antenna, Wi-Fi resonator and combined tag to sense object-human interaction through chipless Wi-Fi tags. © 2022 IEEE.

World University root node

2022 IEEE Wireless Antenna and Microwave Symposium, WAMS 2022

Sensing Object-Human Interaction Through 4-Bit Spiral Resonator Based Passive Chipless WiFi Tags

The COVID-19 pandemic has highlighted the need for a tool to speed up triage in ultrasound scans and provide clinicians with fast access to relevant information. To this end, we propose a new unsupervised reinforcement learning (RL) framework with novel rewards to facilitate unsupervised learning by avoiding tedious and impractical manual labelling for summarizing ultrasound videos. The proposed framework is capable of delivering video summaries with classification labels and segmentations of key landmarks which enhances its utility as a triage tool in the emergency department (ED) and for use in telemedicine. Using an attention ensemble of encoders, the high dimensional image is projected into a low dimensional latent space in terms of: a) reduced distance with a normal or abnormal class (classifier encoder), b) following a topology of landmarks (segmentation encoder), and c) the distance or topology agnostic latent representation (autoencoders). The summarization network is implemented using a bi-directional long short term memory (Bi-LSTM) which utilizes the latent space representation from the encoder. Validation is performed on lung ultrasound (LUS), that typically represent potential use cases in telemedicine and ED triage acquired from different medical centers across geographies (India and Spain). The proposed approach trained and tested on 126 LUS videos showed high agreement with the ground truth with an average precision of over 80% and average F1 score of well over 44±1.7% . The approach resulted in an average reduction in storage space of 77% which can ease bandwidth and storage requirements in telemedicine.

IEEE Journal of Biomedical and Health Informatics

Unsupervised multi-latent space reinforcement learning framework for video summarization in ultrasound imaging

Diagnostic ultrasound imaging systems typically employ the traditional delay and sum (DAS) beamforming for image reconstruction because of its reduced complexity. But the limited contrast and resolution of DAS beamformed images makes it difficult for the detection of small lesions with a single non-steered plane wave insonification. To address these limitations, this paper demonstrates a novel beamforming technique named as beam multiply and sum (BMAS) for enhancement of contrast and lesion detectability with a non-steered plane wave insonification. The intensity linearity of BMAS is evaluated in-silico and the contrast is evaluated in-vitro and in-vivo. When compared to DAS, BMAS images for in-vitro datasets showed an improvement of 33%, 16.78% and 6.3% in lateral resolution, contrast ratio and contrast-to-noise ratio, respectively.

IEEE 19th International Symposium on Biomedical Imaging (ISBI)

Lesion Detectability and Contrast Enhancement with Beam Multiply and Sum Beamforming for Non-Steered Plane Wave Ultrasound Imaging

Underwater acoustical imaging is fast becoming a popular option for ocean exploration. However, it is very challenging and expensive to conduct elaborate experiments to validate the performance of algorithms developed for underwater imaging and array designing, which makes the simulation of underwater environment necessary. Besides acoustical imaging, any Sound Navigation and Ranging (SONAR) signal processing applications such as object detection, image enhancement and classification require a proper simulation tool which models the underwater scenario as realistic as possible. In this paper, we propose to use the k-Wave toolbox for modelling underwater target for acoustical 2D and 3D imaging. The accuracy of the data obtained from k-Wave is analysed by computing structural similarity index of the reconstructed 3D image with the reference 3D image.

k-Wave as a Modelling Tool for Underwater Acoustical Imaging

The need for summarizing long medical scan videos for automatic triage in Emergency Departments and transmission of the summarized videos for telemedicine has gained significance during the COVID-19 pandemic. However, supervised learning schemes for summarizing videos are infeasible as manual labeling of scans for large datasets is impractical by frontline clinicians. This work presents a methodology to summarize ultrasound videos using completely unsupervised learning schemes and is validated on Lung Ultrasound videos. A Convolutional Autoencoder and a Transformer decoder is trained in an unsupervised reinforcement learning setup i.e., without supervised labels in the whole workflow. Novel precision and recall computation for ultrasound videos is also presented employing which high Precision and F 1 scores of 64.36\% and 35.87\% with an average video compression rate of 78\% is obtained when validated against clinically annotated cases. Even though demonstrated using lung ultrasound videos, our approach can be readily extended to other imaging modalities.

RL Based Unsupervised Video Summarization Framework for Ultrasound Imaging

Digital delay and sum beamforming is the promising technique for underwater 3D acoustical imaging. Even though time domain delay and sum beamforming is widely used for medical ultrasound imaging, it is hardly used for underwater acoustical 3D imaging. The conventional narrowband transmit coupled with the computational complexity required for the implementation of interpolation filter is the major reason for that. However, with the increasing popularity of wideband and ultrawideband transmission for achieving high resolution imaging and with the availability of efficient software interpolation libraries in modern computing systems, the computational time required for frequency domain beamforming appears to be more than that of time domain beamforming. Thus, through this work, we have attempted to compare the frequency domain vs time domain delay and sum beamforming for wideband underwater 3D acoustical imaging. The simulation findings demonstrated that time domain DAS beamforming is faster, computationally effective, memory-efficient, and offers somewhat superior image quality.

A Comparison of Time Domain VS Frequency Domain Delay and Sum Beamforming for Underwater 3D Acoustical Imaging

Typically, an ultrasound <a href="https://www.sciencedirect.com/topics/medicine-and-dentistry/flow-imaging">flow imaging</a> system employs the conventional delay and sum (DAS) beamformer due to its inherent low complexity. But the conventional DAS technique offers poor contrast, low imaging resolution, and limited spatiotemporal sensitivity. This article attempts to improve the spatiotemporal sensitivity of the conventional flow imaging with a novel multiply and sum based nonlinear high-resolution (NLHR) beamforming approach. The major advantages of the proposed beamformer are the harmonic generation and the enhanced coherence in beamformed signals that improve the spatiotemporal sensitivity towards flow transients. We demonstrate the proposed beamformer for a directional cross-correlation as well as an autocorrelation based velocity estimator with simulated parabolic flow profiles of different velocities and flow directions, an in-vitro rotating disk dataset, and <a href="https://www.sciencedirect.com/topics/medicine-and-dentistry/pulsatile-flow">pulsatile flow</a> experiments. The sensitivity of NLHR beamforming towards the flow transients is validated in-vitro with a sudden reversal of flow direction and air bubble tracking experiments. The comparison between the time–frequency plots of DAS and NLHR beamforming indicates that the impulsive spatiotemporal changes induced by the flow of air bubbles are clearly characterized by nonlinear beamforming than that of DAS beamforming. Furthermore, better spatiotemporal velocity tracking of a single air bubble and a clear distinguishability between the tracking of two proximal air bubbles are observed in-vitro. Preliminary studies on the in-vivo carotid data also show comparable, if not better, results than that of the DAS algorithm. Detailed results for each test case in simulation, phantom, and in-vivo studies are available as movies with the supplementary material and online [<a href="https://www.youtube.com/playlist?list=PLiuuVhVNWBZSYikqhd20FsVr8NTKRlZ4F">Online Link</a>].

Computers in Biology and Medicine

A nonlinear beamforming for enhanced spatiotemporal sensitivity in high frame rate ultrasound flow imaging

Electrostatic MEMS actuators suffer from an instability called pull-in, wherein the movable electrode snaps onto the fixed electrode beyond a certain applied voltage. Thus, the entire allowed range is not utilized for stable operation. We propose pull-in free, low-voltage operation by using a cubic non-linear spring with a ferroelectric negative-capacitance hybrid MEMS actuator. We use a physics-based framework based on the energy landscape to illustrate the stability improvement. This framework uses energy-displacement and voltage-displacement plots for analysis. We predict that the actuator can operate in three distinct modes: (a) monostable, (b) bistable and (c) always-stable, based on the value of the cubic spring constant. We also estimate the threshold values of the cubic spring constant that demarcate the three modes of operation. By proper design of the cubic spring constant, we predict pull-in free, low-voltage operation of the hybrid actuator, as compared to the standalone MEMS actuator. The results obtained are in agreement with the numerical simulations.

IEEE Transactions on Electron Devices

Stable Deflection in Ferroelectric Negative-Capacitance Hybrid MEMS Actuator with Cubic Non-Linear Spring

Real-time monitoring of oscillation events provides enhanced wide-area situational awareness to the system operator. This article focuses on visualizing low frequency oscillatory modes, their detection, and classification following an event. The significant oscillatory modes present in the signal are extracted through a novel energy preserving, nonredundant “frequency partition based mode extraction (FPBME)” algorithm. These modes are analytically deduced and classified as governor mode, interarea mode, and local mode through a novel “energy based mode detection and classification (EBMDC)” algorithm. This article proposed method introduces the concept of “visualization” that is highly operator-friendly through the time domain plots of extracted modes.

IEEE Systems Journal

Enhanced Visualization and Characterization of Low Frequency Oscillations in Power System

Wide area measurement system (WAMS) based software solutions are getting integrated into the energy management system (EMS) of the smart grid. Angle difference monitoring is one of the most important use cases as far as WAMS base control room applications are concerned. The real-Time angular separation between the nodes provides information related to the stress of transmission corridor. To monitor angle differences across the power system a reference angle must be selected in the control room software solution. This article revisits the concept of reference angle selection techniques for wide area control room operation. Concepts of individual bus angle, a center of inertia angle and center of power angle-based reference angle selection techniques are explored and the most suitable technique for real-Time reference angle selection is suggested. © 2022 IEEE.