Hyper Spectral Anomaly Detection

Abstract

The HSA is a statistics based anomaly detection model. The model performs unsupervised anomaly detection, based on a datapoint's density and similarity within a dataset. Density and similarity data are encoded into an affinity matrix. The affinity matrix is evolved to summarize the data's structure on greater topographical scales within the data's function space. The set of evolved affinity matrices and an anomaly score vector are passed to a user defined penalized objective function. The penalized objective function of anomaly scores is then minimized. Data points where the absolute value of the z-scores of anomaly scores greater than a specified threshold are predicted as anomalies. A novel multi-filter feature has also been implemented. To reduce false positive rates, the multi-filter records the indexes of the HSA predictions. A new dataset and data loader are instantiated consisting of all the initial HSA predictions and non-anomalous data points in a 10% and 90% split respectively. The HSA is then run through this data set and a count of number of times a data point is predicted is kept. In this way the initial predictions may be compared with data spanning the entire dataset. After the multi-filter is complete, all datapoints will have an associated anomaly score, as well as a multi-filter prediction count to further filter the anomalous predictions.