Hybrid intelligence nano-enriched sensing and management system for efficient water-quality monitoring

This paper presents a comprehensive water-quality monitoring system that employs a smart network management, Nano-enriched sensing framework, and intelligent and efficient data analysis and forwarding protocols for smart and system-aware decision making. The presented system comprises two main subsystems, a data sensing and forwarding subsystem (DSFS), and Operation Management subsystem (OMS). The OMS operates based on real-time learned patterns and rules of system operations projected from the DSFS to manage the entire network of sensors. For the communication framework within the designed system, we propose a Hybrid Intelligence (HI) scheme for efficient data classification and forwarding processes. The scheme integrates a machine learning algorithm, Fuzzy logic and weighted decision trees. The proposed methodology depends on profiling raw data readings, generated from a set of optical nano-sensors, as profiles of attribute value pairs. Then, data patterns are learnt adopting association rule learning algorithm clarifying the most frequent attributes and their related values. According to the discovered sets of attributes, a set of Fuzzy membership functions are directed to produce a discrete sample space and a specific membership class for each attribute based on its value. Based on information theory concepts and calculated attribute-dependent entropies and information gains, weighted decision trees are built to help take decisions of data forwarding and to generate long-term rules. As a case study, we conduct a set of simulation scenarios for detecting and forwarding data related to water quality levels. Simulation results show the efficiency of the proposed HI-based methodology at learning different water quality classes.