在农业中使用机器学习和嵌入式系统进行智能火灾检测,以预防风险和提高可持续性
Abdennabi Morchid1, Abdennacer Elbasri2, Hassan Qjidaa3
1LIMAS Laboratory, Faculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah (SMBA) University, Fes, 30000, Morocco. Abdennabi.morchid@usmba.ac.ma.
Scientific reports
|February 17, 2026
概括
本研究介绍了使用Raspberry Pi和机器学习的农村地区的自主火灾检测系统. 随机森林模型在检测火灾危险方面取得了很高的准确性,提高了农业安全.
科学领域:
- 农业工程 农业工程
- 计算机科学 计算机科学
- 环境科学 环境科学
背景情况:
- 由于互联网连接和基础设施有限,传统的火灾监测系统在偏远地区往往缺乏有效性.
- 农业和农村环境中不断增加的火灾风险需要先进的,独立的监测解决方案.
- 实时危险检测和风险预测的需求对于保护自然资源和农场弹性至关重要.
研究的目的:
- 设计和实施可适应在互联网接入最小的地区的自主火灾检测系统.
- 通过机器学习算法提高火灾危险分类和预测准确度.
- 通过异常检测确保数据可靠性并验证系统性能.
主要方法:
- 使用Raspberry Pi 3 B+与烟雾和火焰传感器开发嵌入式系统.
- 机器学习 (ML) 算法的应用,特别是随机森林和物流回归,用于危险分类和异常检测.
- 使用混矩阵和五重分层交叉验证来评估模型性能.
主要成果:
- 随机森林模型表现出卓越的性能,平均准确度为0.9860 ± 0.0172,F1得分为0.9740 ± 0.0319,回忆率为0.9733 ± 0.0327.
- 后勤回归实现了0.9446 ± 0.0600的平均准确度,F1得分为0.9173 ± 0.0744,回忆率为0.9250 ± 0.0608.
- 异常检测技术成功识别并纠正了潜在的传感器测量错误,确保了数据完整性.
结论:
- 开发的自主系统为缺乏互联网的农村和农业地区提供了可靠和高效的火灾检测解决方案.
- 随机森林模型在分类火灾风险水平和确保及时发出警报方面非常有效,大大降低了农业火灾风险.
- 这项研究通过加强风险管理,促进可持续性和提高农场对自然灾害的抵抗力,为向智能农业的过渡做出了贡献.
相关概念视频
Steps in Outbreak Investigation
613
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
613
Key Elements for Plant Nutrition
24.5K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
24.5K
