Study of intelligent home environment system based on big data and improved k-means algorithm

Area of Science:

• Embedded Systems
• Environmental Monitoring
• Artificial Intelligence

Background:

• Traditional home environment monitoring systems suffer from low acquisition frequency and poor real-time performance.
• Existing systems often lack adaptive capabilities and feedback mechanisms for optimal user comfort.
• The STC12C5A MCU-based embedded operating system addresses these limitations in smart home technology.

Purpose of the Study:

• To develop an embedded system for real-time monitoring and control of the home environment.
• To improve system performance by addressing issues of low acquisition frequency, poor real-time response, and lack of adaptation.
• To achieve efficient collaboration and stable operation between hardware and software components.

Main Methods:

• Utilized an embedded operating system based on the STC12C5A MCU.
• Implemented a Kalman filter and an improved k-means algorithm for big data analysis.
• Employed a BP neural network for processing environmental data.
• Designed an independent monitoring mechanism and feedback adjustment system.

Main Results:

• The system demonstrated high acquisition accuracy and fast response speeds.
• Achieved good reliability performance, indicating robust operation.
• Showcased effective real-time and adaptive capabilities for environmental control.
• Successfully identified optimal living environment parameters for user comfort.

Conclusions:

• The developed embedded system effectively enhances real-time monitoring and control of home environments.
• The integration of Kalman filter, k-means, and BP neural network provides accurate and adaptive environmental parameter optimization.
• The system's independent monitoring and feedback mechanisms ensure stable and efficient operation, leading to improved user comfort and satisfaction.