Prasannata Bhange

Expertise in developing advanced signal processing algorithms for real-time solutions, includes nonlinear dynamics, statistical analysis, AI/ML techniques, data analytics, and Non-Destructive Testing (NDT). Skilled in predictive modeling, embedded systems with hands-on experience on FGPA boards. Demonstrated research capabilities through a Suzuki Foundation-supported internship at Shizuoka University, Japan.

Android Implementation on Zynq UltraScale + MPSoC (ZCU102) platform Targeting Drone Navigation Applications, Implemented an Android-based system on the Zynq UltraScale + MPSoC (ZCU102) platform for drone navigation applications. ADC of FRDM Kl25z Board interfaced to demonstrate the analog signals, An ADC was interfaced to the FRDM KL25Z board to read analog signals from an LM35 temperature sensor. Interfacing LCD with Nexys 4 Artix-7 Board, Successfully interfaced an LCD with the Nexys 4 Artix-7 FPGA board. Implementation of Image Compression Algorithm using DCT, Implemented an image compression algorithm in MATLAB that employed the Discrete Cosine Transform (DCT). Machine learning based method for computing the water content in the soil, Designed a simulated environment in Simcenter Magnet software to model soil water saturation. Developed an object detection model tailored for a custom college campus dataset, Developed an object detection model suitable for a customized dataset from a college campus.

Painting, Photography, Actively coordinated technical events, Won medals, certificates and titles in group dance competition, drawing, quiz and elocution competitions, Fashion Show in high school, collegiate and intercollegiate level.

• https://scholar.google.com/citations?hl=en&user=Q1pNkgEAAAAJ
• Phase space reconstruction based real time fatigue crack growth estimation for structural health monitoring ships., IEEE LASCAS, Chile, 2022
• Real-time fatigue crack growth rate estimation methodology for structural health monitoring of ships., IEEE Sensors Journal, 22, 20, 19729-19738, 2022
• FCNet: Deep Learning Architecture for Classification of Fatigue and Corrosion Acoustic Emission Signal., IEEE NEWCAS, Canada, 2022
• Phase Space Reconstruction Based Methodology For Real Time Impact Assessment of Corrosion On Structural Health of Ship Material Using In-situ Acoustic Emission Sensors., IEEE NEWCAS, Scotland, UK, 2023
• Phase Space Reconstruction based Methodology of Real Time Detection of Corrosion in Ship Steel using AE Sensors., IEEE IUS, Canada, 2023
• Hybrid Deep Neural Network with CNN and RNN alongside 1st order B-spline Differential-Based Methodology for Real Time Fatigue Crack Growth Rate Monitoring Using Only AE Sensors., IEEE IUS, Canada, 2023
• Customized Recurrent Neural Network Based Accurate Co-Planar Source Localization Methodology with Reduced Number of AE Sensors., IEEE IUS, Canada, 2023
• IR Thermography and RGB Combined Processing Methodology for Defects and Deformation Localization, IEEE ICECS, France, 2024, Accepted
• Design and Evaluation of Conventional and NN-Based Methods for Corrosion and Fatigue Growth Rate Prediction, IEEE ICECS, France, 2024, Accepted
• Wavelet Packet Decomposition-Based CNN for Classification of Fatigue and Corrosion Acoustic Emission Signal, Conference and exhibition on non-destructive evaluation, Chennai, Accepted