Related Experiment Video
Updated: Jul 19, 2025
06:19
Low-Cost Automated Flight Intercept Trap for the Temporal Sub-Sampling of Flying Insects Attracted to Artificial Light at Night
Published on: December 29, 2021
2.6K
A Lightweight Fault-Detection Scheme for Resource-Constrained Solar Insecticidal Lamp IoTs
Xing Yang1, Lei Shu2,3, Kailiang Li2
1College of Engineering, Nanjing Agricultural University, Nanjing 210031, China.
Sensors (Basel, Switzerland)
|August 12, 2023
Summary
A new lightweight fault-detection scheme for Solar Insecticidal Lamp Internet of Things (SIL-IoTs) enhances agricultural pest monitoring. This energy-efficient method ensures system dependability with minimal resource usage.
Area of Science:
- Agricultural technology
- Internet of Things (IoT)
- Sensor networks
Background:
- Solar Insecticidal Lamp Internet of Things (SIL-IoTs) are vital for pest management.
- System failures due to environmental factors and device aging can degrade SIL-IoTs performance.
- Dependability and safety are critical for effective pest monitoring and prediction.
Purpose of the Study:
- To propose a sensor-level lightweight fault-detection scheme for SIL-IoTs.
- To address constraints of computational resources and energy in agricultural settings.
- To enhance the reliability and safety of SIL-IoTs for pest control.
Main Methods:
- Developed a distributed fault-detection method analyzing fault characteristics.
- Utilized operation condition differences, interval number residuals, and feature residuals.
- Implemented a sensor-level scheme considering resource limitations.
Main Results:
- Achieved an average F1-score of 95.59% in experimental validation.
- Demonstrated minimal resource consumption: 0.27% additional power, 0.9% RAM, 3.1% Flash.
- Confirmed the effectiveness of the proposed fault-detection scheme.
Conclusions:
- The proposed fault-detection method is lightweight and energy-efficient for SIL-IoTs.
- This scheme enhances the dependability and safety of agricultural IoT devices.
- Enables more reliable pest monitoring, prediction, and prevention systems.
