Romain Tavenard

1d-SAX: A Novel Symbolic Representation for Time Series

SAX Symbolic Aggregate approXimation is one of the main symbolization techniques for time series. A well-known limitation of SAX is that trends are not taken into account in the symbolization. This paper proposes 1d-SAX a method to represent a time series as a sequence of symbols that each contain information about the average and the trend of the series on a segment. We compare the efficiency of SAX and 1d-SAX in terms of goodness-of-fit, retrieval and classification performance for querying a time series database with an asymmetric scheme. The results show that 1d-SAX improves performance using equal quantity of information, especially when the compression rate increases.

Clustering flood events from water quality time-series using Latent Dirichlet Allocation model

To improve hydro-chemical modeling and forecasting, there is a need to better understand flood-induced variability in water chemistry and the processes controlling it in watersheds. In the literature, assumptions are often made, for instance, that stream chemistry reacts differently to rainfall events depending on the season; however, methods to verify such assumptions are not well developed. Often, few floods are studied at a time and chemicals are used as tracers. Grouping similar events from large multivariate datasets using principal component analysis and clustering methods helps to explain hydrological processes; however, these methods currently have some limits (definition of flood descriptors, linear assumption, for instance). Most clustering methods have been used in the context of regionalization, focusing more on mapping results than on understanding processes. In this study, we extracted flood patterns using the probabilistic Latent Dirichlet Allocation (LDA) model, its first use in hydrology, to our knowledge. The LDA method allows multivariate temporal datasets to be considered without having to define explanatory factors beforehand or select representative floods. We analyzed a multivariate dataset from a long-term observatory (Kervidy-Naizin, western France) containing data for four solutes monitored daily for 12 years: nitrate, chloride, dissolved organic carbon, and sulfate. The LDA method extracted four different patterns that were distributed by season. Each pattern can be explained by seasonal hydrological processes. Hydro-meteorological parameters help explain the processes leading to these patterns, which increases understanding of flood-induced variability in water quality. Thus, the LDA method appears useful for analyzing long-term datasets.

Identifying seasonal patterns of phosphorus storm dynamics with dynamic time warping

Phosphorus (P) transfer during storm events represents a significant part of annual P loads in streams and contributes to eutrophication in downstream water bodies. To improve understanding of P storm dynamics, automated or semiautomated methods are needed to extract meaningful information from ever-growing water quality measurement data sets. In this paper, seasonal patterns of P storm dynamics are identified in two contrasting watersheds (arable and grassland) through Dynamic Time Warping (DTW) combined with k-means clustering. DTW was used to align discharge time series of different lengths and with differences in phase, which allowed robust application of a k-means clustering algorithm on rescaled P time series. In the arable watershed, the main storm pattern identified from autumn to winter displayed distinct export dynamics for particulate and dissolved P, which suggests independent transport mechanisms for both P forms. Conversely, the main storm pattern identified in spring displayed synchronized export of particulate and dissolved P. In the grassland watershed, the occurrence of synchronized export of dissolved and particulate P forms was not related to the season, but rather to the amplitude of storm events. Differences between the seasonal distributions of the patterns identified for the two watersheds were interpreted in terms of P sources and transport pathways. The DTW-based clustering algorithm used in this study proved useful for identifying common patterns in water quality time series and for isolating unusual events. It will open new possibilities for interpreting the high-frequency and multiparameter water quality time series that are currently acquired worldwide.

Time-sensitive topic models for action recognition in videos

In this paper, we postulate that temporal information is important for action recognition in videos. Keeping temporal information, videos are represented as word×time documents. We propose to use time-sensitive probabilistic topic models and we extend them for the context of supervised learning. Our time-sensitive approach is compared to both PLSA and Bag-of-Words. Our approach is shown to both capture semantics from data and yield classification performance comparable to other methods, outperforming them when the amount of training data is low.

Improving the efficiency of traditional DTW accelerators

Dynamic time warping (DTW) is the most popular approach for evaluating the similarity of time series, but its computation is costly. Therefore, simple functions lower bounding DTW distances have been designed, accelerating searches by quickly pruning sequences that could not possibly be best matches. The tighter the bounds, the more they prune and the better the performance. Designing new functions that are even tighter is difficult because their computation is likely to become complex, canceling the benefits of their pruning. It is possible, however, to design simple functions with a higher pruning power by relaxing the no false dismissal assumption, resulting in approximate lower bound functions. This paper describes how very popular approaches accelerating DTW such as

Identifying seasonal patterns of phosphorus storm dynamics with dynamic time warping: CLUSTERING STORM EVENTS WITH DTW

text {LB}_text {Keogh}{}

Next step for Big Data Infrastructure and Analytics for the Surveillance of the Maritime Traffic from AIS \& Sentinel Satellite Data Streams

LB_Keogh and