This project focuses on developing a plant growth monitoring system for space exploration missions using the ARM Cortex-M0 microcontroller core. The projects aim to develop a SOC based on ARM M0 core for interactive plant monitoring by interfacing AHB lite, GPIO, timers, and communication protocols such as UART, I2C, SPI, and co-processors.  This project also proposes two co-processors for interactive plant monitoring and control. One AI co-processor for classification and prediction of plant and environmental data.

This Project is to develop traffic light system that can reduce traffic congestion with the aid of counters for each lane and acts wisely with the intersection in real time based with a fixed time constrain, include both hardware and software requirements using SOC FPGA technology with fundamental specification for the Register Transfer Level (RTL).

Conventional healthcare is expensive and reliant on the physical presence of the patients. Continuous health monitoring tracks vital health parameters like heart rate, blood pressure, etc. While these work well in measuring the parameters, modern-day devices rely on the cloud to compute and interpret data. This results in an increase in data transfer between the device and the cloud, and if this connection breaks, there can be no interpretation of data. Hence, there is a need to shift the computation to the hardware, referred to as "Edge Computing".

The development of a Low-Cost and Low-Power Data Acquisition System(DAQs). The DAQs will be made up of end-terminal and a gateway. The end-terminal will be micro-controller-driven device built on a SoC FPGA technology with built-in capability for machine learning. The end-terminal will be able to transmit and receive data using the Low Power Wide Area Networking (LPWAN) communication protocol that functions on LoRA.LoRa is a wireless radio frequency technology that operates in a license-free radio frequency spectrum.

Advancements in electronics, wireless communications, and sensing technologies have made possible a multitude of smart sensing features in automotives. Integrating high-frequency sensors, digital signal processors and hardware accelerator engines on a single system on a chip (SoC) enhances sensing computation potential of radar sensors utilized in automotives.

We propose the A-Cube design methodology to create medical decision support on the edge. The design and implementation of an atrial fibrillation detector hardware core was selected as a proof-of-concept study. To facilitate the required atrial fibrillation functionality, we adopted an established AI model, based on Long Short-Term Memory (LSTM) technology for hardware implementation. The adaptation was done by varying design parameters such as data window and the number of LSTM units.

Battery storage systems are an important source for powering emerging clean energy applications. The Battery Management System (BMS) is a critical component of modern battery storage, essential for efficient system monitoring, reducing run-time failures, prolonging charge-discharge lifecycle, and preventing battery stress or catastrophic situations. The BMS performs functionalities such as data acquisition and monitoring, battery state estimation, cell equalization, and charge protection, making it computationally intensive to manage large scale battery storage.

The dynamic range processor is a DSP function which does as it says on the tin; it compresses the dynamic range of the incoming signal. This is used most commonly in the music industry for its effects on the perceived loudness of audio. It is also used extensively in hearing aids to compensate for the user’s reduced dynamic range of hearing. In this project a hardware accelerator is developed for the purpose of dynamic range compression of digital audio. This accelerator will be implemented in a mixed-signal infrastructure.

Autonomous mobile robots (AMRs) have been proven useful for smart factories and have the potential to revolutionize critical missions, such as disaster rescue. AMRs can perceive the environment, plan for assigned tasks, and act on the plan. Motion control is critical to the robot's action, which is accomplished through trajectory optimization to refine the robot's states using a physics model. However, the high computational complexity of trajectory optimization poses significant challenges for AMRs with limited power and computing resources.