Senior Design Projects - Fall 2024 Showcase

Traditional radar systems face several limitations, including high costs, limited adaptability, and significant size constraints, which hinder their deployment in dynamic and evolving environments. These systems are often prone to noise interference and require costly hardware upgrades to enhance accuracy and functionality. To address these challenges, our project focuses on developing a cost-effective, adaptable, and lightweight radar system leveraging Software Defined Radio (SDR) technology. By utilizing the ADALM-PLUTO SDR—a compact, pocket-sized device with extendable antennas and extensive customization capabilities—our system enables flexible applications, such as compatibility with bistatic radar setups, offering a versatile and modern solution to the limitations of conventional radar systems.​ 

The Smart Instrumentation Boat is a cost effective and eco friendly solution poised at testing and research water quality samples in small bodies of water. 

Efficient spectrum management is crucial in today's telecommunications landscape, where multiple communication systems often operate within overlapping frequency bands. The project's primary objective is to develop and implement clustering machine learning models for spectrum sensing. This initiative is essential to enhance spectrum efficiency, ensuring optimal use of the available bandwidth and minimizing interference across different communication signals.

Spectrum sensing involves detecting the presence of different communication signals within a specified frequency range and distinguishing between them. Traditional methods often need help with accuracy and real-time responsiveness, particularly in environments with diverse and dynamic signal sources. The proposed solution uses advanced clustering algorithms to improve the differentiation and identification of various signals, enabling more efficient and reliable spectrum utilization.

A. Objectives

Implementing Machine Learning Models: Develop clustering algorithms to identify and differentiate between different communication signals within a given bandwidth.

Integration with Software-Defined Radio (SDR) Kits: SDR kits are used as transmitters and receivers to collect real-time signal data for analysis.

Evaluation of Spectrum Efficiency: Assess the performance of the clustering models in terms of spectrum efficiency, aiming to maximize the utilization of available spectrum resources without causing interference.

B. Constraints

The project must operate under the following constraints:

Hardware Limitations: Use of specific SDR kits with limited frequency ranges, such as 2.4 GHz for Wi-Fi bands, imposing constraints on the operational frequencies.

Ease of Deployment: The system must be designed for straightforward implementation and operation. It should be user-friendly and require minimal setup to encourage widespread adoption and integration into existing infrastructure.

Cost Efficiency: The system should have a high return on investment for stakeholders.

The outlined project objectives focus on developing and implementing clustering machine learning models tailored for spectrum sensing applications. By leveraging advanced clustering algorithms, we aim to accurately differentiate between diverse communication signals sharing the same frequency bands. Integration with Software-Defined Radio (SDR) kits as transmitters and receivers enables real-time data collection for robust signal analysis. Our primary goal is to evaluate the performance of these models in terms of spectrum efficiency, ensuring optimal utilization of available resources while minimizing interference. This strategic alignment sets the stage for detailed exploration and validation in controlled indoor environments, paving the way for potential deployment in diverse real-world settings. 

The Raspberry Pi Voice Assistant project aims to develop a cost-effective, scalable, and reliable voice-activated assistant designed for home automation and everyday use. By leveraging the Raspberry Pi platform, the project provides users with hands-free interaction through advanced speech recognition and natural language processing technologies.