Precision agriculture is revolutionizing the agricultural sector by integrating advanced technologies to enhance productivity and sustainability. In aquaculture, precision agriculture can significantly improve fish farming practices through precise monitoring and data-driven decision-making, addressing challenges such as optimizing resource usage and improving fish health. This paper presents the development and implementation of an IoT-based Fish Recommendation System designed to optimize aquaculture practices through a mobile application. This system uses different sensors for extracting data continuously regarding temperature, PH and Turbidity etc. These parameters can be analysed in real-time to help fish farmers make decisions on when or how much the system should feed and aerate, and what approach of water treatment is best for their fishes. This information is stored to create individual datasets, offering researchers valuable insights into optimal conditions for each fish species. This can enhance their survival rates and promote growth. In this study, we evaluate a series of machine learning algorithms for their ability to predict the optimal fish species based on water quality parameters. Among these algorithms, Random Forest demonstrated superior performance, achieving an accuracy of 92.5%, precision of 93%, recall of 93%, and F1-score of 92%. These findings highlight the effectiveness of our approach in integrating machine learning with IoT for precise aquaculture management. Implemented through a user-friendly mobile application, our system enhances accessibility and usability for fish farmers.

To improve surveillance, the proposed patrolling security system employs autonomous mobile robots outfitted with low-cost night vision cameras. Regular patrols, which are essential for discouraging criminal behavior, are typically conducted by security or law enforcement officers with the use of pricey CCTV equipment. The goal of using autonomous robots is to save expenses while enhancing the quality of patrols in particular regions. Using a night vision camera, the late-night guarding robot detects human movement within its assigned zone while following a random path. Its obstacle-detecting sensors help to prevent crashes and guarantee secure navigation. The robot records incidences, takes pictures with its mounted camera, and carefully scans regions for probable incursions. It then sends the data to the user as quickly as it can. This project's primary goal is to draw attention to suspicious activity in hidden areas. 

Smart Vehicle Accident Prevention System is an innovative solution aimed at enhancing road safety and reducing the occurrence of accidents. Leveraging the Internet of Things (IoT) technology, this system combines real-time data acquisition, analysis, and intelligent decision-making algorithms to provide an effective accident prevention mechanism. The Vehicle Accident Prevention System is a com-prehensive project that aims to enhance road safety by utilizing Arduino microcontrollers and various sensors, including an alcohol sensor, temperature sensor, IR sensor and ultrasonic sensor. This report provides a detailed overview of the system’s design, implementation, and functionality.