论文标题
通过非参数建模传感器统计的低功率无监督异常检测
Low Power Unsupervised Anomaly Detection by Non-Parametric Modeling of Sensor Statistics
论文作者
论文摘要
这项工作提出了AEGIS，这是一种通过检查传感器流统计数据的新型混合信号框架，用于实时异常检测。 AEGI使用基于内核密度估计（KDE）的非参数密度估计来生成传感器数据流的实时统计模型。传感器数据点的可能性估计值可以基于生成的统计模型来检测异常值。我们提出了CMOS Gilbert Gaussian基于细胞的设计，以实现KDE的高斯内核。对于离群检测，决策边界是根据内核标准偏差（$σ_{kernel} $）和似然阈值（$ p_ {thres} $）定义的。我们采用滑动窗口实时更新检测模型。我们使用从Yahoo提供的时间序列数据集来基准宙斯盾的性能。通过优化参数，例如滑动窗口的长度和可在宙斯盾中可以编程的决策阈值来实现高于0.87的F1得分。讨论的体系结构是使用45NM技术节点设计的，我们的方法平均消耗$ \ sim $ 75 $μ$ W功率，以2 MHz的采样速率，同时使用十个最近的Inlier样品进行密度估计。 \ textColor {red} {这项研究的全面已发表在IEEE TVLSI}
This work presents AEGIS, a novel mixed-signal framework for real-time anomaly detection by examining sensor stream statistics. AEGIS utilizes Kernel Density Estimation (KDE)-based non-parametric density estimation to generate a real-time statistical model of the sensor data stream. The likelihood estimate of the sensor data point can be obtained based on the generated statistical model to detect outliers. We present CMOS Gilbert Gaussian cell-based design to realize Gaussian kernels for KDE. For outlier detection, the decision boundary is defined in terms of kernel standard deviation ($σ_{Kernel}$) and likelihood threshold ($P_{Thres}$). We adopt a sliding window to update the detection model in real-time. We use time-series dataset provided from Yahoo to benchmark the performance of AEGIS. A f1-score higher than 0.87 is achieved by optimizing parameters such as length of the sliding window and decision thresholds which are programmable in AEGIS. Discussed architecture is designed using 45nm technology node and our approach on average consumes $\sim$75 $μ$W power at a sampling rate of 2 MHz while using ten recent inlier samples for density estimation. \textcolor{red}{Full-version of this research has been published at IEEE TVLSI}
