Pranav Chippalkatti

@mituniversity.ac.in

Assistant Professor , Computer Science and Engineering
MIT Arts, Design and Technology University

Pranav Chippalkatti


               Download Compact PDF  
https://researchid.co/ppc8051

RESEARCH INTERESTS

Embedded Systems, Microcontrollers and Microprocessor, Image Processing, C, C++, Object Oriented Programming
13

Scopus Publications

Scopus Publications

  • Comparative analysis of deep learning models for semantic segmentation and classification on high-resolution aerial imagery
    Pranav Pradip Chippalkatti, Pournima Natraj Sutar, Saloni Uday Deshmukh, Raju Prakash Gurav, Atharva Rajendra Kanchan
    Connecting Intelligence Trends in Computation and Data Communication, 2026
    High-resolution aerial imagery plays a vital role in areas like urban planning, environmental monitoring, and guiding autonomous systems. However, achieving precise segmentation of these images is challenging due to variations in object sizes, uneven class distribution, and intricate boundaries. In this work, we evaluate the real-time segmentation performance of four distinct deep learning architectures such as U-Net, DeepLabV3+, ResNet-50, and EfficientNet-B4 on the Semantic Drone Dataset. To enhance robustness and training stability, we applied Albumentations-based data augmentation along with the OneCycleLR learning rate scheduler. Performance was measured using metrics including mean Intersection over Union (mIoU), precision, recall, and processing speed (FPS). Among the tested models, EfficientNet-B4 produced the highest scores, attaining an mIoU value of 0.6123 and a speed of 705.48 FPS, making it well-suited for real-time drone applications. ResNet-50 provided a strong accuracy–efficiency balance, while U-Net and DeepLabV3+ presented trade-offs between detail preservation and processing speed. Overall, this study offers a practical performance comparison that addresses both precision and real-time viability for aerial segmentation in real-world scenarios.
  • Exploring nusselt number and friction factor correlations for sphere-shaped roughness elements on the absorber to enhance solar air heater efficiency
    Rajesh Maharudra Patil, N. Madhukeshwara, Swagat Madhav Karve, Pranav Chippalkatti, Somnath B. Thigale
    Experimental Heat Transfer, 2025
    This investigation is conducted to analyze the artificial surface roughness influence on the heat flow and friction characteristics within the ducts of solar air heaters (SAHs). This research aims to investigate the consequences of applying spherical-shaped surface roughness to the absorber in a linear and staggered manner with the intention of enhancing the heat transfer efficiency. The utilization of roughness elements in the shape of spheres is aimed at augmenting the heat transfer characteristics; however, it is crucial to acknowledge that this enhancement is concomitant with an elevation in pumping power due to heightened friction. An experimental campaign encom- passes a diverse set of operational and device parameters. These parameters include the Reynolds number (Re), which varies from 3,000 to 8,000. Additionally, the roughness pitch-to-height ratio (p/h) ranges from 10 to 20, while the roughness gap-to-height ratio (w/h) ranges from 4 to 8. Throughout the trials, a constant value of 0.06 is maintained for the roughness height-to-hydraulic diameter ratio (h/D) and an amount of 5 is maintained for the duct width-to-height ratio (W/H). The outcomes of this study indicate a considerable increase in the Nusselt number, ranging from 50.47% to 69.51%, concurrently with a substantial rise in the friction factor, ranging from 27.76% to 144.75%, when compared to designs using a smooth absorber surface in the context of SAHs. By utilizing the experimental data, relationships between the friction factor and the Nusselt number are established based on the artificial roughness parameters and the operating conditions. The current study’s findings significantly advance our knowledge of and ability to improve SAH systems’ heat transfer and friction characteristics. Thus, this investigation improves our understanding of these systems operational behavior in many situations.
  • Detection of Knee Osteoarthritis from Magnetic Resonance Imaging Using a 3-D Independent Component Analysis Method in Machine Learning
    Swagat Karve, Tanuja Satish Dhope, Rajesh Kaushal, Naveen Kumar, Pranav Chippalkatti, Akshay Jadhav
    Communications in Computer and Information Science, 2025
  • SLODS: Real-time smart lane detection and object detection system
    Applied Data Science and Smart Systems, 2024
  • Mathematical Modeling and Designing of a Novel Improvised Cooperative Balancing Routing (CBR) Protocol to Enhance the Lifetime of WSNS using Load Balancing Concepts
    Swagat M Karve
    Panamerican Mathematical Journal, 2023
    In this paper, the design & development of a novel cooperative balancing routing (CBR) protocol to enhance the lifetime of WSNs using load balancing concepts by decreasing the energy consumption during the data exchanges is presented in the respective section. The main objective of the research work presented in this paper is to present an improvised version of the CBR that computes the routing path by using cooperative mechanisms using the concept of load balancing. This paper also demonstrates the various results obtained for all the test cases along with the necessary observations and explanations in the form of discussions and diagrammatic representations. The paper finally concludes with the overall conclusions of the CBR work.
  • Development and Mathematical Formulation of Secured Memory Efficient Cloning Detection Protocol in WSNs using RSA Algorithm
    Pranav P Chippalkatti
    Panamerican Mathematical Journal, 2023
    This paper is related to the developing an improvised of secured memory efficient cloning detection protocol in WSNs using RSA Algorithm and is used for efficient transfer of data packets with security. NS2 is used as the simulation tool to simulate the outputs. The main aim or objective of the proposed work presented in this paper is to develop a secured memory efficient cloning detection protocol in the mobile adhoc wireless sensor networks. The simulation results shows the effectivity of the methodology that is being proposed by us.
  • IOT Based Baby Incubator for Clinic
    Pravin Kshirsgar, Varsha More, Vaibhav Hendre, Pranav Chippalkatti, Krishan Paliwal
    Lecture Notes in Electrical Engineering, 2020
  • A Review on IOT Based Health Care Monitoring System
    Pravin Kshirsagar, Akshay Pote, K. K. Paliwal, Vaibhav Hendre, Pranav Chippalkatti, Nikhil Dhabekar
    Lecture Notes in Electrical Engineering, 2020
  • Design and Implementation of Adaptive Headlight Control System Using CAN-LIN Protocols
    Vrushali D. Ichake, Pranav Chipalkatti, Ganesh Kadam
    Lecture Notes on Data Engineering and Communications Technologies, 2019
  • I-SPARK: IoT Based Smart Parking System
    Pranav Chippalkatti, Ganesh Kadam, Vrushali Ichake
    2018 International Conference on Advances in Communication and Computing Technology Icacct 2018, 2018
    TRAFFIC a direct or an indirect outcome of many minor issues has been creating havoc for an individual especially in urban areas. This paper proposes an architecture that introduces an efficient and eminent; rather a smart way to resolve the small module that actually counts i.e. Parking Area. We design a system so as to eliminate the time wastage and irrelevant frustration faced by the drivers based on IoT for real time monitoring of the empty slots for car parking from anywhere using a webpage or a mobile app; IoT the emerging research domain is the heart of the proposed system.
  • Configuration of FPGA Through Internal Configuration Access Port
    Asha Jadhav, Pravin N. Matte, Pranav Chippalkatti
    Proceedings of the 2nd International Conference on Computing Methodologies and Communication Iccmc 2018, 2018
  • Optimum spread for generalized regression neural network using particle swarm intelligence
    Journal of Advanced Research in Dynamical and Control Systems, 2018
  • Performance optimization of neural network using GA incorporated PSO
    Journal of Advanced Research in Dynamical and Control Systems, 2018