Employed BPN to Multi-sensors Data Fusion for Environment Monitoring Services

The real-time system uses a back-propagation network (BPN) with associative memory for recognition and classification in multi-sensors data fusion. This study attempts to apply classification fusion technology to the real-time signals recognition of multi-sensors data in a wireless sensor networks (WSNs) system with a node–sink mobile network structure. These wireless sensor network systems include temperature, humidity, ultraviolet, and illumination four variable measurements for environment monitoring services (EMS). Remote engineers can manage the multi-sensors data fusion using the browser, and the WSNs system then classification the data fusion database via the Internet and mobile network. Moreover, the data fields of each sensor node contain the properties and specifications of that pattern, except in the case of engineering components. The database system approach significantly improves classification data fusion system capacity. The classification fusion system examined here employs parallel computing, which increases system data fusion rate. The classification fusion system used in this work is an Internet based node–sink mobile network structure. The final phase of the classification fusion system applies database BPN technology to processing data fusion, and can solve the problem of spurious states. The system considered here is implemented on the Yang-Fen Automation Electrical Engineering Company as a case study. The experiment is continued for 4 weeks, and engineers are also used to operating the web-based classification fusion system. Therefore, the cooperative plan described above is analyzed and discussed here. Finally, these papers propose the tradition methods compare with the innovative methods.