Multi-scale streaming anomalies detection for time series
نویسنده
چکیده
In the class of streaming anomaly detection algorithms for univariate time series, the size of the sliding window over which various statistics are calculated is an important parameter. To address the anomalous variation in the scale of the pseudo-periodicity of time series, we define a streaming multi-scale anomaly score with a streaming PCA over a multi-scale lag-matrix. We define three methods of aggregation of the multi-scale anomaly scores. We evaluate their performance on Yahoo ! and Numenta dataset for unsupervised anomaly detection benchmark. To the best of authors’ knowledge, this is the first time a multi-scale streaming anomaly detection has been proposed and systematically studied.
منابع مشابه
Real-Time Anomaly Detection for Streaming Analytics
Much of the worlds data is streaming, time-series data, where anomalies give significant information in critical situations. Yet detecting anomalies in streaming data is a difficult task, requiring detectors to process data in real-time, and learn while simultaneously making predictions. We present a novel anomaly detection technique based on an on-line sequence memory algorithm called Hierarch...
متن کاملThermal anomalies detection before earthquake using three filters (Fourier, Wavelet and Logarithmic Differential Filter), A Case Study of two Earthquakes in Iran
Earthquake is one of the most destructive natural phenomena which has human and financial losses. The existence of an efficient prediction system and early warning system will be useful for reducing effects of destroying earthquake. In this research, the soil temperature time-series data, obtained from three meteorological station, using three filters (Fourier, Wavelet and Logarithmic Different...
متن کاملMining Approximate Top-K Subspace Anomalies in Multi-Dimensional Time-Series Data
Market analysis is a representative data analysis process with many applications. In such an analysis, critical numerical measures, such as profit and sales, fluctuate over time and form time-series data. Moreover, the time series data correspond to market segments, which are described by a set of attributes, such as age, gender, education, income level, and product-category, that form a multi-...
متن کاملPervasive white and colored noise removing from magnetotelluric time series
Magnetotellurics is an exploration method which is based on measurement of natural electric and magnetic fields of the Earth and is increasingly used in geological applications, petroleum industry, geothermal sources detection and crust and lithosphere studies. In this work, discrete wavelet transform of magnetotelluric signals was performed. Discrete wavelet transform decomposes signals into c...
متن کاملOnline Streaming Feature Selection Using Geometric Series of the Adjacency Matrix of Features
Feature Selection (FS) is an important pre-processing step in machine learning and data mining. All the traditional feature selection methods assume that the entire feature space is available from the beginning. However, online streaming features (OSF) are an integral part of many real-world applications. In OSF, the number of training examples is fixed while the number of features grows with t...
متن کامل