Root System Water Consumption Pattern Identification on Time Series Data.
Root System Water Consumption Pattern Identification on Time Series Data.
复制标题
DOI：
10.3390/s17061410
复制
发表时间：
2017-06-16
期刊：
影响因子：
--
通讯作者：
Pope C
中科院分区：
文献类型：
--
作者：
Figueroa M;Pope C
在农业中，土壤和气象传感器沿低功率网络使用来捕获数据，从而实现资源的最佳利用并将对环境的影响降至最低。本研究利用时间序列分析方法对土壤水分传感器数据进行离群点检测和模式识别，以识别灌溉和消耗模式，并改进土壤水分预测和灌溉系统。本研究将三种新算法与项目中现有的检测技术进行了比较，结果大大降低了检测到的误报数量。最好的结果是通过序列字符串比较(SSC)算法在测试集上的平均精度为0.872，大大提高了当前系统的0.348的精度。
In agriculture, soil and meteorological sensors are used along low power networks to capture data, which allows for optimal resource usage and minimizing environmental impact. This study uses time series analysis methods for outliers’ detection and pattern recognition on soil moisture sensor data to identify irrigation and consumption patterns and to improve a soil moisture prediction and irrigation system. This study compares three new algorithms with the current detection technique in the project; the results greatly decrease the number of false positives detected. The best result is obtained by the Series Strings Comparison (SSC) algorithm averaging a precision of 0.872 on the testing sets, vastly improving the current system’s 0.348 precision.