Pardhu Thottempudi

@bvrithyderabad.edu.in

Assistant Professor, Department of Electronics and Communications Engineering
BVRIT HYDERABAD College Of Engineering For Women

Pardhu Thottempudi


                           Download Compact PDF  
https://researchid.co/pardhu.t
Pardhu Thottempudi became a member (M) of IEEE in 2015. Pardhu was born in Luxettipet village in Adilabad district in Telangana state, India. He completed Batchelor’s degree B.tech in the stream of electronics and communication engineering in 2011 from MLR Institute of Technology, Hyderabad, India. He has done his master’s degree M.Tech in embedded systems from Vignan’s University, Vadlamudi in 2013. He is pursuing Ph.D in the stream of RADAR signal processing from VIT University His Research Includes Human Motion Analysis Behind walls using Optimized Deep Learning Algorithms. His major fields of interests include Digital Signal Processing, RADAR communications, embedded systems, and implementation of signal processing on applications in FPGA. He is working as assistant professor of department of Electronics and Communication Engineering in BVRIT HYDERABAD College of Engineering for Women, Hyderabad, India since 2023.

EDUCATION

VIT University, VELLORE- Thesis Submitted (2023)
M.Tech- Vignan University, Vadlamudi- 2013
B.Tech- MLRIT, Hyderabad- 2011
Intermediate-2011
Tenth-2005

RESEARCH, TEACHING, or OTHER INTERESTS

Signal Processing, Artificial Intelligence, Communication
42

Scopus Publications

Scopus Publications

  • Smart Agriculture: Crop Prediction, Fertilizer Recommendation and Water Requirement using Machine Learning
    Ch.Rajendra Prasad, Yalabaka Srikanth, Ramu Moola, Srinivas Samala, P. Ramchandar Rao, Thottempudi Pardhu
    Proceedings of the 2026 International Conference on AI Driven Smart Systems and Ubiquitous Computing Icauc 2026, 2026
    Smart agriculture has an important role to play to help enhance the productivity of crops and make the most of agricultural assets using machine learning techniques. This paper is designed to present an integrated system of smart agriculture that focuses on three key components of the system namely: prediction of crops, recommending fertilizers, and estimating water requirements of crops. The proposed system takes historical data on crop harvests, soil nutrient content and climatic situation and uses it as an analysis tool to forecast the best crops to be grown in a certain area. On the basis of soil nutrient deficiencies and based on crop-specific rate, suitable fertilizer types and quantities are recommended for the balanced management of nutrients. In addition, the system estimates water requirements of the crop in liters per hectare taking into account environmental factors such as temperature, humidity, soil moisture, crop type and weather conditions. Multiple machine learning algorithms, such as Decision Tree, Random Forest, Naive Bayes and K-Nearest Neighbors are implemented and tested for performance comparison Experimental results show that Random Forest algorithm has better accuracy and stability in all the modules. The proposed approach is in favor of precision agriculture, thanks to decision making, better use of resources and sustainable practices in farming especially during climate changes and/or resource scarcity.
  • Dynamic multi-modal attention network for robust and real-time through-wall human activity recognition
    Pardhu Thottempudi, Vijay Kumar, Rajkishor Kumar
    Results in Engineering, 2025
    Through-wall human activity recognition (TW-HAR) has emerged as a critical area of research due to its applications in healthcare, surveillance, and emergency response. Conventional approaches relying on single-modality data, such as radar or WiFi, often face challenges in complex environments, including noise, variability in sensor placement, and environmental obstructions. These limitations are further exacerbated by factors such as signal attenuation and scattering caused by diverse wall materials (e.g., concrete, brick, drywall), misalignment between sensors and human subjects, and dynamic noise conditions, all of which significantly degrade recognition performance. This paper presents a novel Dynamic Multi-Modal Attention Network (DMAN) that integrates data from Radar, WiFi, and Acoustic sensors to achieve robust and accurate human activity recognition. The proposed framework employs a hybrid Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) architecture, which effectively captures spatial and temporal features from multi-modal data. A dynamic attention mechanism is incorporated to prioritize critical modality-specific features, mitigating the effects of noise and redundancy. Comprehensive evaluations based on standard metrics—including accuracy, precision, recall, and F1-score—demonstrate that the proposed DMAN significantly outperforms state-of-the-art methods. The system achieved an average accuracy of 96.9% across six distinct activity classes: walking, running, sitting, standing, falling, and empty room scenarios. Furthermore, the system maintains high robustness under challenging conditions such as varying wall materials and sensor misalignments, with a low inference time of 2.8 seconds per sample, making it suitable for real-time applications. This work establishes the DMAN as a scalable and reliable solution for TW-HAR, addressing key limitations of existing methods. Future research directions include exploring additional sensor modalities and enhancing computational efficiency for broader deployment in smart environments and real-time monitoring scenarios. • Introduces a Dynamic Multi-Modal Attention Network (DMAN) for TW-HAR. • Fuses Radar, WiFi, and Acoustic data for robust through-wall detection. • CNN-BiLSTM with dynamic attention enables spatial-temporal learning. • Achieves 96.9% accuracy with low inference time for real-time use. • Scalable solution for healthcare and security monitoring scenarios.
  • Digital health resilience: IoT solutions in pandemic response and future healthcare scenarios
    Pardhu Thottempudi, Reddy Madhavi Konduru, Hima Bindu Valiveti, Swaraja Kuraparthi, Vijay Kumar
    Discover Sustainability, 2025
    This article explores the Internet of Things (IoT), an innovative technical advancement that utilizes the capabilities of billions of sensors across various applications. Sensors are critical to the IoT environment as they collect crucial data for complex analysis. The emergence of the Internet of Things (IoT) and its accompanying sensor technology has significant implications for various fields, including smart urban planning, advanced agriculture, online education, and healthcare. The Internet of Things (IoT) has played a crucial role in tackling worldwide health challenges, notably in the healthcare sector, with a particular emphasis on the recent COVID-19 pandemic. The epidemic has heightened the need for digital and home-based healthcare solutions. The Internet of Things (IoT) enhances healthcare services by providing precise patient monitoring over a unified digital network. This article examines the various uses, technical intricacies, and difficulties that exist in the healthcare field. A thorough investigation was conducted using reputable databases such as Google Scholar, Elsevier, PubMed, ACM, ResearchGate, Scopus, and Springer. Relevant keywords directed the search. The narrative highlights and emphasizes the significant impact of IoT on healthcare, explicitly identifying prospective research areas for doctors, scholars, and researchers to overcome obstacles in the field. As anticipated, the Internet of Things (IoT) serves as a guiding light for improved healthcare delivery. The Survey demonstrates that combining IoT with cutting-edge technology enhances computing capacities, emphasizing IoT’s widespread, advantageous, and extensive nature. To summarise, this discussion examines future difficulties and provides valuable solutions to strengthen the healthcare infrastructure led by the Internet of Things (IoT) during the COVID-19 crisis and future health catastrophes.
  • Transfer learning-enhanced CNN model for integrative ultrasound and biomarker-based diagnosis of polycystic ovarian disease
    M. Shanmuga Sundari, N. Venkata Sailaja, D. Swapna, Sireesha Vikkurty, Vijaya Chandra Jadala, Kbks Durga, Pardhu Thottempudi
    Scientific Reports, 2025
    Polycystic Ovarian Disease (PCOD), also known as Polycystic Ovary Syndrome (PCOS), is a prevalent hormonal and metabolic condition primarily affecting women of reproductive age worldwide. It is typically marked by disrupted ovulation, an increase in circulating androgen hormones, and the presence of multiple small ovarian follicles, which collectively result in menstrual irregularities, infertility challenges, and associated metabolic disturbances. This study presents an automated diagnostic framework for PCOD detection from transvaginal ultrasound images, leveraging an Enhanced [Formula: see text] convolutional neural network architecture. The model incorporates attention mechanisms, batch normalization, and dropout regularization to improve feature learning and generalization. Bayesian Optimization was employed to fine-tune critical hyperparameters, including learning rate, batch size, and dropout rate, ensuring optimal model performance. The proposed system was trained and validated on a curated ovarian ultrasound image dataset, applying data augmentation and SMOTE techniques to address class imbalance. Experimental evaluation demonstrated that the Enhanced [Formula: see text] model achieved a classification accuracy of 94.8%, sensitivity of 93.2%, specificity of 95.5%, precision of 94.0%, and an F1-score of 93.6% on the independent test set. Interpretability was enhanced through Grad-CAM visualization, which effectively localized diagnostically significant regions within the ultrasound images, corroborating clinical findings. These results highlight the potential of the proposed deep learning-based framework to serve as a reliable, scalable, and interpretable decision-support tool for PCOD diagnosis, offering improved diagnostic consistency and reducing operator dependency in clinical workflows.
  • Resilient object detection for autonomous vehicles: Integrating deep learning and sensor fusion in adverse conditions
    Pardhu Thottempudi, Asral Bin Bahari Jambek, Vijay Kumar, Biswaranjan Acharya, Fernando Moreira
    Engineering Applications of Artificial Intelligence, 2025
  • Examining the utilization and impact of active learning strategies in modern pedagogical practices
    Pardhu Thottempudi, Vijay Kumar, Nagesh Deevi
    Development of Self Awareness and Wellbeing Global Learning Challenges in A Shifting Society, 2025
    This study delves into the usage and results of active learning methodologies in modern educational systems, exploring techniques such as cooperative learning, inverted classroom settings, problem-oriented, and hands-on learning. The research aims to elucidate the frequency of these methodologies, their efficiency in amplifying student participation and learning achievements, and the difficulties encountered during their execution. The data was collected through a hybrid approach, fusing quantitative studies conducted in various classrooms with qualitative teacher interviews. Initial outcomes indicate that, when aptly applied, active learning approaches can stimulate increased student involvement and boost academic performance. Nonetheless, several obstacles, such as insufficient educator preparation and resource limitations, hinder their broad-scale application. The study emphasizes the need for a calculated strategy to incorporate active learning methodologies into teaching practices to cultivate a more engaging and efficient learning environment.
  • Impact of ChatGPT on the Indian Educational System: An Academic Study
    Thottempudi Pardhu, S. L. Aruna Rao
    Lecture Notes in Networks and Systems, 2025
  • Design and Simulation on Chip Fractal Inductor for Sub–THz Applications
    Nagesh Deevi, Dileep Reddy Bolla, Thottempudi Pardhu, Ravuri Viswanatham, MV. Subbarao
    Lecture Notes in Electrical Engineering, 2025
  • Enhanced Fingerprint Recognition System Using Minutiae-Based Analysis and FFT-Based Feature Extraction
    Pardhu Thottempudi, Vijay Kumar, Raenu A-L Kolandaisamy, N. Venkatesh, Deepthi Adduri, Prudhvila S, Haritha J, Sindhu N
    7th International Conference on Energy Power and Environment Icepe 2025, 2025
    Fingerprint recognition is a widely adopted biometric authentication technique due to the uniqueness and permanence of fingerprint patterns. This paper presents a fingerprint recognition system developed using MATLAB, incorporating an interactive graphical user interface (GUI) and advanced image processing techniques. The system employs histogram equalization for contrast enhancement, Fast Fourier Transform (FFT)-based enhancement for ridge structure clarity, and minutiae-based feature extraction for precise fingerprint identification. The preprocessing steps, including region of interest (ROI) extraction, thinning, and noise removal (H-breaks and spikes), optimize the feature representation for improved matching accuracy. The minutiae-based matching algorithm detects ridge endings and bifurcations, ensuring robust authentication. The experimental results demonstrate the system's effectiveness in enhancing fingerprint image quality and feature extraction accuracy, leading to high matching precision. The system achieves reliable performance across varying fingerprint quality levels, confirming its suitability for biometric authentication applications. Future work aims to integrate deep learning models and multimodal biometric approaches to further enhance recognition accuracy and system adaptability.
  • Advanced diabetes prediction: A comprehensive analysis of machine learning and deep learning techniques
    Decision Support System for Diabetes Healthcare Advancements and Applications, 2024
  • Deep Kronecker LeNet for human motion classification with feature extraction
    Thottempudi Pardhu, Vijay Kumar, Kalyan C. Durbhakula
    Scientific Reports, 2024
  • High-Performance Real-Time Human Activity Recognition Using Machine Learning
    Pardhu Thottempudi, Biswaranjan Acharya, Fernando Moreira
    Mathematics, 2024
  • Enhanced Classification of Human Fall and Sit Motions Using Ultra-Wideband Radar and Hidden Markov Models
    Thottempudi Pardhu, Vijay Kumar, Andreas Kanavos, Vassilis C. Gerogiannis, Biswaranjan Acharya
    Mathematics, 2024
  • The role of IoT in modern healthcare: Innovations and challenges in pandemic era
    Pardhu Thottempudi, Vijay Kumar
    Technologies for Sustainable Healthcare Development, 2024
  • Hand gesture recognition in real time
    Thottempudi Pardhu, Nagesh Deevi, N. Srinivasa Rao
    Aip Conference Proceedings, 2024
  • Revolutionizing wireless communication: A comprehensive study on modern antenna technologies
    Pardhu Thottempudi, Vijay Kumar
    Radar and RF Front End System Designs for Wireless Systems, 2024
  • EEG Artifact Removal Strategies for BCI Applications: A Survey
    Pardhu Thottempudi, Vijay Kumar, Nagesh Deevi
    Majlesi Journal of Electrical Engineering, 2024
  • Advancements in UWB-Based Human Motion Detection Through Wall: A Comprehensive Analysis
    Thottempudi Pardhu, Vijay Kumar, Praveen Kumar, Nagesh Deevi
    IEEE Access, 2024
  • Precision Lunar Landscape Unveiled with Terrain Mapping and Advanced Techniques
    Thottempudi Pardhu, Hemasree Jonnalagadda, Vijay Kumar, P. Sreeja, P. Bhavana, Ch. Sharon Rose, N. Venkatesh
    Icepe 2024 6th International Conference on Energy Power and Environment Towards Indigenous Energy Utilization, 2024
  • Human motion classification using Impulse Radio Ultra Wide Band through-wall RADAR model
    Thottempudi Pardhu, Vijay Kumar
    Multimedia Tools and Applications, 2023
  • Leveraging IoT and machine learning for improved health prediction systems
    Pardhu Thottempudi
    Sustainable Science and Intelligent Technologies for Societal Development, 2023
  • Face detection and recognition through live stream
    Pardhu Thottempudi
    Sustainable Science and Intelligent Technologies for Societal Development, 2023
  • Extraction and Matching of Fingerprint Features
    Pardhu Thottempudi, Nagesh Deevi
    Intelligent Engineering Applications and Applied Sciences for Sustainability, 2023
  • Remote health prediction system: A machine learning-based approach
    Pardhu Thottempudi, Nagesh Deevi, Amy Prasanna T., Srinivasarao N., Mahesh Babu Katta
    Multi Disciplinary Applications of Fog Computing Responsiveness in Real Time, 2023
  • Self-adaptive TLC using verilog HDL
    D. V. S. Chandrababu, Pardhu Thottempudi, Ch. Babaiah, G. Koushik
    Aip Conference Proceedings, 2023
  • Design and implementation of automatic hand sanitizer dispenser using Arduino and ultrasonic sensor
    D. V. S. Chandrababu, Pardhu Thottempudi, Ch. Babaiah, G. Koushik
    Aip Conference Proceedings, 2023
  • Recognition of Moving Human Targets by Through the Wall Imaging RADAR Using RAMA and SIA Algorithms
    Pardhu Thottempudi, Venkata Surya Chandra Babu Dasari, Venkata Surya Prasad Sista
    Lecture Notes in Networks and Systems, 2022
  • A General Regression Neural Network based Blurred Image Restoration
    Sreedhar Kollem, Katta Ramalinga Reddy, Sreejith S, Ch Rajendra Prasad, Srinivas Samala, Thottempudi Pardhu
    4th International Conference on Emerging Research in Electronics Computer Science and Technology Icerect 2022, 2022
  • Experimental study of through the wall imaging for the detection of vital life signs using SFWR
    Pardhu Thottempudi, Vijay Kumar
    Indonesian Journal of Electrical Engineering and Computer Science, 2021
  • Novel implementations of clutter and target discrimination using threshold skewness method
    Thottempudi Pardhu, Vijay Kumar
    Traitement Du Signal, 2021
  • Design methodology to check the quality of the image in a mobile environment - State of the art
    K Jyothi, Thottempudi Pardhu, R Karthik, T S Arulananth
    Proceedings of the International Conference on Intelligent Sustainable Systems Iciss 2017, 2018
  • An investigation on human identification behind the wall
    Journal of Advanced Research in Dynamical and Control Systems, 2018
  • Seperation of music and voice based on repeating pattern
    International Journal of Civil Engineering and Technology, 2017
  • Implementation of automatic test equipment for line replaceable units of active phased array radar
    International Journal of Mechanical Engineering and Technology, 2017
  • ATE for active phased array radar-Mini review
    International Journal of Mechanical Engineering and Technology, 2017
  • Digital image watermarking in frequency domain
    Thottempudi Pardhu, Bhaskara Rao Perli
    International Conference on Communication and Signal Processing Iccsp 2016, 2016
  • Design of ultra low power multipliers using hybrid adders
    Thottempudi Pardhu, N.Alekhya Reddy
    2015 International Conference on Communication and Signal Processing Iccsp 2015, 2015
  • Reduction of clutter using TWI ultra wideband imaging
    Thottempudi Pardhu, Vijay Kumar
    International Journal of Ultra Wideband Communications and Systems, 2015
  • Design and simulation of digital frequency meter using VHDL
    Thottempudi Pardhu, Sunkara Harshitha
    International Conference on Communication and Signal Processing Iccsp 2014 Proceedings, 2014
  • A low power flash ADC with Wallace tree encoder
    Thottempudi Pardhu, S. Manusha, Katakam Sirisha
    IFIP International Conference on Wireless and Optical Communications Networks Wocn, 2014
  • Novel characterization and generation of radar volume clutter using FPGA
    International Journal of Applied Engineering Research, 2014
  • Generation and validation of Gaussian noise using random sequence
    Thottempudi Pardhu, Usha Rani Nelakuditi, Suresh Pampana
    2014 International Conference on Electronics and Communication Systems Icecs 2014, 2014

RESEARCH OUTPUTS (PATENTS, SOFTWARE, PUBLICATIONS, PRODUCTS)

1.Power Efficient Compressor Using Full Adder Circuit
Inventor: Thottempudi Pardhu
Status: Published on 29/08/2014 pp:60
Application Number:3975/CHE/2014

2. WEED IDENTIFYING ROVER
Inventor: Thottempudi Pardhu
Status: Issued06/10/2021
Design Number: 347292-001

3.ARTIFICIAL INTELLIGENCE BASED HUMANOID ROBOT FOR SURVILLANCE AND SECURITY
Inventor: Thottempudi Pardhu
Status: Case is Amended with Controller
Application Number:377792-001

4.VARIABLE RATING ACCUMULATOR CHARGING STATION WITH TOOLS BOX
Inventor: Thottempudi Pardhu
Status: Granted
Design Number:6270282 (UK Design Patent)

5.DESIGN OF SENTRY ROBOT FOR SURVEILLANCE AND SECURITY
Inventor: Thottempudi Pardhu
Status: Granted
Design Number:6272417 (UK Design Patent)