An AI-Driven Secure Underwater Data Logging System Using Multi-Sensor Fusion For Predictive Monitoring

Abstract

Applications like oceanographic research, aquatic ecosystem management, and underwater data center operation rely on monitoring the environment in underwater locations. In this paper, an intelligent underwater data logging system based on AI techniques, consisting of multi-sensor data acquisition, security protection, and predictive data analysis, is proposed.

The proposed system involves several environmental parameters such as pressure, temperature and PH level that simulate the real time underwater environment. A continuous data logging system is in place, and the data is stored in a structured format. In order to increase the intelligence in the system, the anomaly detection model based on Isolation Forest is used to detect abnormal patterns and system failures.

Moreover, it has a security layer with symmetric encryption for data confidentiality and integrity between storage and transport. It additionally offers visualization options for time-series information and anomaly detection outcomes, making it possible for true-time monitoring and examination.

The results show that the proposed system can perform data logging, anomaly detection and secure data management. Combining Artificial Intelligence and IoT based monitoring system gives a scalable and reliable platform for intelligent underwater monitoring applications.