Open AccessPosted Content
Time Series Anomaly Detection: Detection of Anomalous Drops with Limited Features and Sparse Examples in Noisy Periodic Data
TLDR
The goal is to utilize Machine Learning and statistical approaches to classify anomalous drops in periodic, but noisy, traffic patterns and found that using the intersection of the two anomaly detection methods proved to be an effective method of detecting anomalies on almost all of the models.Abstract:
Google uses continuous streams of data from industry partners in order to deliver accurate results to users. Unexpected drops in traffic can be an indication of an underlying issue and may be an early warning that remedial action may be necessary. Detecting such drops is non-trivial because streams are variable and noisy, with roughly regular spikes (in many different shapes) in traffic data. We investigated the question of whether or not we can predict anomalies in these data streams. Our goal is to utilize Machine Learning and statistical approaches to classify anomalous drops in periodic, but noisy, traffic patterns. Since we do not have a large body of labeled examples to directly apply supervised learning for anomaly classification, we approached the problem in two parts. First we used TensorFlow to train our various models including DNNs, RNNs, and LSTMs to perform regression and predict the expected value in the time series. Secondly we created anomaly detection rules that compared the actual values to predicted values. Since the problem requires finding sustained anomalies, rather than just short delays or momentary inactivity in the data, our two detection methods focused on continuous sections of activity rather than just single points. We tried multiple combinations of our models and rules and found that using the intersection of our two anomaly detection methods proved to be an effective method of detecting anomalies on almost all of our models. In the process we also found that not all data fell within our experimental assumptions, as one data stream had no periodicity, and therefore no time based model could predict it.read more
Citations
More filters
Posted Content
Deep Learning for Anomaly Detection: A Survey.
TL;DR: A structured and comprehensive overview of research methods in deep learning-based anomaly detection, grouped state-of-the-art research techniques into different categories based on the underlying assumptions and approach adopted.
Proceedings ArticleDOI
Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding
TL;DR: The effectiveness of Long Short-Term Memory networks, a type of Recurrent Neural Network, in overcoming issues using expert-labeled telemetry anomaly data from the Soil Moisture Active Passive (SMAP) satellite and the Mars Science Laboratory (MSL) rover, Curiosity is demonstrated.
Journal ArticleDOI
Anomaly Detection for IoT Time-Series Data: A Survey
TL;DR: A background on the challenges which may be encountered when applying anomaly detection techniques to IoT data is provided, with examples of applications for the IoT anomaly detection taken from the literature.
Journal ArticleDOI
Multi-head CNN–RNN for multi-time series anomaly detection: An industrial case study
TL;DR: This work proposes a deep learning based approach for supervised multi-time series anomaly detection that combines a Convolutional Neural Network and a Recurrent Neural Network in different ways and refers to this architecture as Multi-head CNN–RNN.
Proceedings ArticleDOI
Time-Series Anomaly Detection Service at Microsoft
Hansheng Ren,Bixiong Xu,Yujing Wang,Chao Yi,Congrui Huang,Xiaoyu Kou,Tony Xing,Mao Yang,Jie Tong,Qi Zhang +9 more
TL;DR: Wang et al. as mentioned in this paper proposed a novel algorithm based on Spectral Residual (SR) and Convolutional Neural Network (CNN) for time-series anomaly detection.
References
More filters
Journal ArticleDOI
Anomaly detection: A survey
TL;DR: This survey tries to provide a structured and comprehensive overview of the research on anomaly detection by grouping existing techniques into different categories based on the underlying approach adopted by each technique.
Proceedings Article
Recurrent neural network based language model
TL;DR: Results indicate that it is possible to obtain around 50% reduction of perplexity by using mixture of several RNN LMs, compared to a state of the art backoff language model.
Proceedings ArticleDOI
Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling
TL;DR: The first distributed training of LSTM RNNs using asynchronous stochastic gradient descent optimization on a large cluster of machines is introduced and it is shown that a two-layer deep LSTm RNN where each L STM layer has a linear recurrent projection layer can exceed state-of-the-art speech recognition performance.
Posted Content
Real-Time Anomaly Detection for Streaming Analytics
Subutai Ahmad,Scott Purdy +1 more
TL;DR: A novel anomaly detection technique based on an on-line sequence memory algorithm called Hierarchical Temporal Memory (HTM) is presented, which shows results from a live application that detects anomalies in financial metrics in real-time.
Deep Learning for Time Series Modeling CS 229 Final Project Report
TL;DR: This work sought to use deep learning architectures to predict energy loads across different network grid areas, using only time and temperature data from the Kaggle competition "Global Energy Forecasting Competition 2012 Load Forecasting" to focus on short term load forecasting.