Identification of unexpectedly high values in a time series is useful for epidemiologists, economists, and other social scientists interested in the effect of an exposure spike on an outcome variable. However, the best method to identify spikes in time series is not known. This paper aims to fill this gap by testing the performance of several spike detection methods in a simulation setting. We created simulations parameterized by monthly violence rates in nine California cities that represented different series features, and randomly inserted spikes into the series. We then compared the ability to detect spikes of the following methods: ARIMA modeling, Kalman filtering and smoothing, wavelet modeling with soft thresholding, and an iterative outlier detection method. We varied the magnitude of spikes from 10-50% of the mean rate over the study period and varied the number of spikes inserted from 1 to 10. We assessed performance of each method using sensitivity and specificity. The Kalman filtering and smoothing procedure had the best overall performance. We applied Kalman filtering and smoothing to the monthly violence rates in nine California cities and identified spikes in the rate over the 2005-2012 period.
The exact mechanisms leading to an earthquake are not fully understood and the space-time structural features are non-trivial. Previous studies suggest the seismicity of very low intensity earthquakes, known as micro-earthquakes, may contain information about the source process before major earthquakes, as they can quantify modifications to stress or strain across time that finally lead to a major earthquake. This work uses the history of seismic activity of micro-earthquakes to analyze the spatio-temporal statistical independence among the monitoring stations of a seismic network. Using point…
Modern well-performing approaches to neural decoding are based on machine learning models such as decision tree ensembles and deep neural networks. The wide range of algorithms that can be utilized to learn from neural spike trains, which are essentially time-series data, results in the need for diverse and challenging benchmarks for neural decoding, similar to the ones in the fields of computer vision and natural language processing. In this work, we propose a spike train classification benchmark, based on open-access neural activity datasets and consisting of several learning tasks such as s…
I propose a frequency domain adaptation of the Expectation Maximization (EM) algorithm to group a family of time series in classes of similar dynamic structure. It does this by viewing the magnitude of the discrete Fourier transform (DFT) of each signal (or power spectrum) as a probability density/mass function (pdf/pmf) on the unit circle: signals with similar dynamics have similar pdfs; distinct patterns have distinct pdfs. An advantage of this approach is that it does not rely on any parametric form of the dynamic structure, but can be used for non-parametric, robust and model-free classifi…
Reliable estimates of typical travel times allow road users to forward plan journeys to minimise travel time, potentially increasing overall system efficiency. On busy highways, however, congestion events can cause large, short-term spikes in travel time. These spikes make direct forecasting of travel time using standard time series models difficult on the timescales of hours to days that are relevant to forward planning. The problem is that some such spikes are caused by unpredictable incidents and should be filtered out, whereas others are caused by recurrent peaks in demand and should be fa…
A dynamic Boltzmann machine (DyBM) has been proposed as a model of a spiking neural network, and its learning rule of maximizing the log-likelihood of given time-series has been shown to exhibit key properties of spike-timing dependent plasticity (STDP), which had been postulated and experimentally confirmed in the field of neuroscience as a learning rule that refines the Hebbian rule. Here, we relax some of the constraints in the DyBM in a way that it becomes more suitable for computation and learning. We show that learning the DyBM can be considered as logistic regression for binary-valued t…
In this article there is no intention to repeat basic concepts about risk management, but we will try to define why often is usefull the time series analysis during the assessment of risks, and how is possible to compute a significative analysis using regression and autoregression. After some basic concepts about trend analysis, will be introduced some methods to identify peaks. This is often usefull when there is no need to use the full time series, because sometimes is more practical to focus only on the extremes. With a correct time series without not-anomalous data, the extremes time serie…
IBM Research - Tokyo（IBM研究院-东京）；IBM Japan, Ltd.（日本IBM有限公司）
We propose a particularly structured Boltzmann machine, which we refer to as a dynamic Boltzmann machine (DyBM), as a stochastic model of a multi-dimensional time-series. The DyBM can have infinitely many layers of units but allows exact and efficient inference and learning when its parameters have a proposed structure. This proposed structure is motivated by postulates and observations, from biological neural networks, that the synaptic weight is strengthened or weakened, depending on the timing of spikes (i.e., spike-timing dependent plasticity or STDP). We show that the learning rule of upd…
Neurons perform computations, and convey the results of those computations through the statistical structure of their output spike trains. Here we present a practical method, grounded in the information-theoretic analysis of prediction, for inferring a minimal representation of that structure and for characterizing its complexity. Starting from spike trains, our approach finds their causal state models (CSMs), the minimal hidden Markov models or stochastic automata capable of generating statistically identical time series. We then use these CSMs to objectively quantify both the generalizable s…
In this paper, we use convolutional neural networks to address the problem of model identification for autoregressive moving average time series models. We compare the performance of several neural network architectures, trained on simulated time series, with likelihood based methods, in particular the Akaike and Bayesian information criteria. We find that our neural networks can significantly outperform these likelihood based methods in terms of accuracy and, by orders of magnitude, in terms of speed.
Spiking neural networks (SNNs) offer a promising alternative to current artificial neural networks to enable low-power event-driven neuromorphic hardware. Spike-based neuromorphic applications require processing and extracting meaningful information from spatio-temporal data, represented as series of spike trains over time. In this paper, we propose a method to synthesize images from multiple modalities in a spike-based environment. We use spiking auto-encoders to convert image and audio inputs into compact spatio-temporal representations that is then decoded for image synthesis. For this, we …
Accurate labeling of phase connectivity in electrical distribution systems is important for maintenance and operations but is often erroneous or missing. In this paper, we present a process to identify which smart meters must be in the same phase using a hierarchical clustering method on voltage time series data. Instead of working with the time series data directly, we apply the Fourier transform to represent the data in their frequency domain, remove $98\%$ of the Fourier coefficients, and use the remaining coefficients to cluster the meters are in the same phase. Result of this process is v…
We address the problem of data-driven pattern identification and outlier detection in time series. To this end, we use singular value decomposition (SVD) which is a well-known technique to compute a low-rank approximation for an arbitrary matrix. By recasting the time series as a matrix it becomes possible to use SVD to highlight the underlying patterns and periodicities. This is done without the need for specifying user-defined parameters. From a data mining perspective, this opens up new ways of analyzing time series in a data-driven, bottom-up fashion. However, in order to get correct resul…
We study goodness-of-fit testing for non-causal autoregressive time series with non-Gaussian stable noise. To model time series exhibiting sharp spikes or occasional bursts of outlying observations, the exponent of the non-Gaussian stable variables is assumed to be less than two. Under such conditions, the innovation variables have no finite second moment. We proved that the sample autocorrelation functions of the trimmed residuals are asymptotically normal. Nonparametric tests are also investigated. The rank correlations of the residuals or the squared residuals are shown to be asymptotically…
A system identification approach to clustering vector autoregressive time series
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, China（华中科技大学人工智能与自动化学院）；School of Electrical Engineering and Telecommunications, UNSW Sydney, NSW, Australia（新南威尔士大学悉尼分校电子与电信工程学院）
Recent advances in AIoT technologies have led to an increasing popularity of utilizing machine learning algorithms to detect operational failures for cyber-physical systems (CPS). In its basic form, an anomaly detection module monitors the sensor measurements and actuator states from the physical plant, and detects anomalies in these measurements to identify abnormal operation status. Nevertheless, building effective anomaly detection models for CPS is rather challenging as the model has to accurately detect anomalies in presence of highly complicated system dynamics and unknown amount of sens…
University of California, Berkeley（加利福尼亚大学伯克利分校）；Amazon（亚马逊）
Linear dynamical systems are a fundamental and powerful parametric model class. However, identifying the parameters of a linear dynamical system is a venerable task, permitting provably efficient solutions only in special cases. This work shows that the eigenspectrum of unknown linear dynamics can be identified without full system identification. We analyze a computationally efficient and provably convergent algorithm to estimate the eigenvalues of the state-transition matrix in a linear dynamical system. When applied to time series clustering, our algorithm can efficiently cluster multi-dimen…
This paper presents an efficient approach for subsequence search in data streams. The problem consists in identifying coherent repetitions of a given reference time-series, eventually multi-variate, within a longer data stream. Dynamic Time Warping (DTW) is the metric most widely used to implement pattern query, but its computational complexity is a well-known issue. In this paper we present an approach aimed at learning a kernel able to approximate DTW to be used for efficiently analyse streaming data collected from wearable sensors, reducing the burden of computation. Contrary to kernel, DTW…
Interest in functional time series has spiked in the recent past with papers covering both methodology and applications being published at a much increased pace. This article contributes to the research in this area by proposing a new stationarity test for functional time series based on frequency domain methods. The proposed test statistics is based on joint dimension reduction via functional principal components analysis across the spectral density operators at all Fourier frequencies, explicitly allowing for frequency-dependent levels of truncation to adapt to the dynamics of the underlying…
Approaches to automated grouping in singular spectrum analysis are considered. A new method for the identification of periodic components is proposed. The possibilities of extensions to multivariate time series and images are discussed.
