Recent News

  • Matrix enabled road distress classification system June 20, 2022

    udaya shankar

    The Department of Electronics and Communication Engineering is glad to announce that Dr V Udaya Sankar, Assistant Professor has published the patent (App no. 202141056542), ‘A system and method with Matrix enabled Road distress classification with reduced computational complexity and reduced memory requirements’, in collaboration with Dr Siva Sankar Yellampalli and Ms Gayathri Lakshmi Chinthakrindi.

    This work has applications related to visual inspection systems. While this research considers road crack detection application, the same can be extended to various applications such as leaf disease prediction, covid prediction etc. This invention provides an alternative approach instead of using traditional machine learning algorithms that has less computational complexity as opposed to deep neural networks that take more complex operations. This method will also lead to further research in matrix-based machine learning applications related to image processing and image classification.

    The research team is planning to collaborate with Efftronics Systems Pvt ltd. for PCB defect detection and discussions are initiated with some start-ups for visual inspection applications. Their future research plan is to look deeper into these algorithms in combination with some of the deep neural networks to reduce computational complexity. In addition, Dr Udaya Sankar is also looking forward to establishing his own start-up in the incubation centre soon.

    Abstract of the Research

    A method for image classification is provided, wherein, the pre-processed gray scale image is first sent to the feature extraction block, and the said feature extraction block considers every image as a matrix and computes the metrics for features, viz., 1) EMD distance which is popularly known as Wassertain distance/Earth movers distance and is computed with respect to block image and 2) Frobenius Norm which is the square root of the sum of the absolute squares of its elements and finally, 3) Condition Number, which measures the ratio of the maximum relative stretching to the maximum relative shrinking that matrix does to any non-zero vectors. This method is preferred over the existing methods due to the drastic reduction in computational complexities and, utilizing lesser memory. Also, with this method and system, the communicational complexities too are significantly reduced and also, and the results yielded are far more significantly accurate.

    Continue reading →

  • Research article accepted for IEEE conference IEMTRONICS 2022 June 4, 2022


    SRM University-AP preserves a research-empowered ecosystem stimulating its faculty and students to roll out original and discerning studies capable of making instrumental contributions aiming the scientific and societal progress. Making strides with impactful research publications and groundbreaking achievements, the institution has carved a niche for itself in the academic milieu. We are glad to present yet another success story of our research community that keeps bringing laurels to the institutions from far and wide.

    Dr Pradyut Kumar Sanki and his PhD scholar Bevara Vasudeva, from the Department of Electronics and Communications Engineering, along with a group of Computer Science and Engineering students: Medarametla Depthi Supriya, Devireddy Vignesh, Peram Bhanu Sai Harshath, and Sravya Kuchina have got their paper titled ‘’VLSI Implementation of a Real-Time Modified Decision-Based Algorithm for Impulse Noise Removal’’ accepted in the IEEE conference IEMTRONICS 2022. This publication is a part of the Capstone project contributed by the students.

    IEMTRONICS 2022 (International IOT, Electronics and Mechatronics Conference) is an international conclave that aims to bring together scholars from different backgrounds to disseminate inventive ideas in the fields of IOT, Electronics and Mechatronics. The conference will also promote an intense dialogue between academia and industry to bridge the gap between academic research, industry initiatives, and governmental policies. This is fostered by panel discussions, invited talks, and industry exhibits where academia and industry will mutually benefit from each other.

    Through the research paper, the team proposes a real-time impulse noise removal (RTINR) algorithm and its hardware architecture for denoising images corrupted with fixed valued impulse noise.

    Abstract of the Research

    A decision-based algorithm is modified in the proposed RTINR algorithm where the corrupted pixel is first detected and is restored with median or previous pixel value depending on the number of corrupted pixels in the image. The proposed RTINR architecture has been designed to reduce the hardware complexity as it requires 21 comparators, 4 adders, and 2 line buffers which in turn improve the execution time. The proposed architecture results better in qualitative and quantitative performance in comparison to different denoising schemes while evaluated based on the following parameters: PSNR, IEF, MSE, EKI, SSIM, FOM, and visual quality. The proposed architecture has been simulated using the XC7VX330T-FFG1761 VIRTEX7 FPGA device and the reported maximum post place and route frequency is 360.88 MHz. The proposed RTINR architecture is capable of denoising images of size 512 × 512 at 686 frames per second. The architecture has also been synthesized using UMC 90 nm technology where 103 mW power is consumed at a clock frequency of 100 MHz with a gate count of 2.3K (NAND2) including two memory buffers.

    Continue reading →
  • Network resource allocation for emergency management May 28, 2022

    The focus of the network keeps changing with every generation of communication technology. The 5G era is waiting for the next generation to bring a remarkable revolution in communication technologies. Applying various changes and modifying the drawbacks of 5G technology can help us to improve the features of the upcoming 6G. The Department of Electronics and Communication Engineering is delighted to inform you that the paper, “Network Resource Allocation for Emergency Management based on Closed Loop Analysis” has been published by Dr Udaya Sankar, Assistant Professor, and BTech students; Sai Jnaneswar J and VMVS Aditya, in “ ITU Journal on Future and Evolving Technologies – 2nd special issue on AI and machine learning solutions in 5G and future networks”.

    Abstract of the research

    paper publicationTelecommunication systems being a critical pillar of emergency management, intelligent deployment, and management of slices in an affected area, will help emergency responders. Techniques such as automated management of ML (machine learning) pipelines across the edge and emergency responder devices, usage of hierarchical closed-loops, and offloading inference tasks closer to the edge, can reduce latencies for first responders in case of emergencies. This paper describes the major findings of building a Proof of Concept (PoC) for network resource allocation for emergency management using a hierarchical autonomous artificial intelligence (AI)/ML-based closed-loops in the mobile network, which was organized by the Internal Telecommunication Union Focus Group on Autonomous Network (ITU FGAN). The background scenario for this PoC included the interaction between a higher closed-loop in the Operations Support System (OSS) and a lower closed-loop in RAN (Radio Access Network) to intelligently share RAN resources between the public and emergency responder slice. Representation of closed-loop “controllers” in a declarative fashion (Intent), triggering “imperative actions” in the “underlay” based on the intent, setup of a data pipeline between various components, and methods of “influencing” lower layer loops using specific logic/models, were some of the important aspects investigated by various teams. The main conclusions are summarised in this work, along with the significant observations and limitations from the PoC as well as future directions.

    Explanation of the research

    paper publicatioThis is a collaborative study where the researchers have developed and implemented a hierarchical closed-loop that autonomously handles an emergency case. This project contains several groups working on separate functions such as monitoring, computing, ML selection, and resource allocation. Some presented how the AI agents and the network can be adapted to assist mobile network users in Search, Diagnostic, and Rescue (SDAR) missions. Some integrated the implementation of the closed loops in O-RAN based software. The researcher’s role in this project is to generate the data which will be used for analysis and this gets integrated with another team. Rather than putting dummy data and analysing or creating and training a machine learning model, we use the Simu5g simulator which is library-based on OMNET++ framework to generate data, mainly resource allocation data. In Simu5g they configure the required network, set all the input parameters such as and simulate it for a specific duration of time. After simulation, the various results are obtained like SINR, throughput, resource block allocation, and many more. This data of the selected parameter results is converted into CSV files and handed over to the required for ML. This project blends all the chunks of work like monitoring, computing, ML selection, and resource combination, to facilitate network resource allocation for emergency management.

    Practical implementations of the research

    In this project, the researchers have gathered the simulated data and want to analyse it and apply machine learning algorithms to improve the condition of existing 5G networks. AI/ML model will help to analyse the data which helps in optimizing resource allocation. Optimization algorithms for resource allocation like Interference minimization, Throughput maximization, and many more. Optimising such parameters would be really helpful for the development of new generation networks.


    The paper was developed as part of a build-a-thon track, “ITU AI/ML in 5G Challenge: applying machine learning in communication networks” challenge. The researchers worked under the problem statement “ITU-ML5G-PS-014: Build-a-thon (PoC) Network resource allocation for emergency management based on closed-loop analysis”. This project is guided by Dr. V Udaya Sankar under AI-Designed Wireless (AIDW) Project Simulated network scenarios using simu5g for measuring resource allocation. This build-a-thon challenge was started on June 7, 2021 and ended on November 5, 2021. The research team was placed fifth among 12 teams who participated across the world in the “build a thon” track of the global challenge. While the overall challenge saw over 600 participants across more than 80 countries, the “build a thon” track was a unique coding challenge from ITU FG AN. The team worked on the simulation of the 5G system and corresponding analysis using Simu5G from ITU global partners. After the build-a-thon, the teams that have participated in the build-a-thon under the problem statement “ITU-ML5G-PS-014: Build-a-thon (PoC) Network resource allocation for emergency management based on closed-loop analysis” were collaboratively developed the journal from the observations and results that were made during this build-a-thon.

    The current research work focuses on the Implementation of a simulation environment to generate data for model training and testing purposes, and serve as a simulation underlay for testing. The simulations allow us to study various configurations and analyse them to optimize the allocations. For the later stages, various machine learning techniques can be applied for the data that was generated through simulation, and further, the comparison can be done for various machine learning techniques.

    Continue reading →
  • Department of ECE publish paper on Fourier holography May 27, 2022

    Fourier holography

    A paper titled “Sparse reconstruction for integral Fourier holography using Dictionary Learning method” has been published by Dr Inbarasan Muniraj, Dr Karthikeyan Elumalai and Dr Sunil Chinnadurai – Assistant Professors of Electronics and Communications Engineering at SRM University-AP, along with PhD students Lakshmi Kuruguntla and Vineela Chandra Dodda.

    The paper proposes reconstructing holograms from fewer data, thereby reducing the need for processing the complete hologram data, which is otherwise computationally expensive.

    Abstract: A simplified method was demonstrated to generate a hologram from multiple two-dimensional (2D) images. Sparse reconstruction was shown using the Sequential Generalised K-means (SGK) algorithm. It is shown that the proposed sparse reconstruction method provides a good hologram quality, in terms of peak signal-to-noise ratio, even under ~90% sparsity.

    The paper is written in collaboration with Professor John T Sheridan, Vice-Principal for Research & Innovation – College of Engineering & Architecture, Head of School of Electrical and Electronic Engineering, University College Dublin, Ireland.

    Holography has been shown useful for biomedical imaging, cryptography, data storage, and entertainment. The future plans of the research group include extending this approach to other holographic systems such as digital holography and holographic microscopy.

    Continue reading →
  • Dr Divya Chaturvedi steps up her research with SERB-POWER grant May 25, 2022

    dst serb grant

    Dr Divya Chaturvedi from the Department of Electronics and Communication Engineering has been awarded the SERB-POWER research grant that amounts to a total of 29 lakhs for a period of three years. The grant was sanctioned for her research titled “Development of Breast Cancer Detecting System Based on Microwave Antenna-Array-Sensors and its Implementation to Internet of Medical Things (IoMT)”.

    SERB- POWER (Promoting Opportunities for Women in Exploratory Research)  research grants is a scheme initiated by the Government of India with an aim to encourage emerging and eminent women researchers for individual-centric and competitive mode of research funding to undertake R&D activities in frontier areas of science and engineering.

    Her study on developing a breast cancer detection system has gained immense attention due to the global increase of the malady in recent decades. It has become the most common cancer diagnosed in women across all age groups. Despite the different tests such as Mammograms, ultrasound, and MRI available to diagnose the disease, there has been little considerable improvement in bringing down the caseload.

    Dr Divya’s research intends to develop an advanced detection technique based on Antenna-Array-Sensors and she is attempting to put it into implementation through the Internet of Medical Things (IoMT). Connecting the medical devices to healthcare IT systems through online computer networks will allow the easier and quicker detection of the defect. This may go down as a milestone achievement in the medical domain.

    The research grant will help in building better- equipped research lab with the most modern amenities and hiring more manpower to fulfil the project objectives. In the words of Dr Divya, “Better research facilities will aid the faculty in performing various experiments. They will save their travelling time to other universities for accessing research infrastructure. The students can also avail the advantage to intensify their research initiatives”. Through the project she envisions to establish a collaborative dedicated research group that will help in fulfilling the various objectives of the project.

    Continue reading →