Search

This paper contributes multivariate versions of seven commonly used elastic similarity and distance measures for time series data analytics. Elastic similarity and distance measures can compensate for misalignments in the time axis of time series data. We adapt two existing strategies used in a multivariate version of the well-known Dynamic Time Warping (DTW), namely, Independent and Dependent DTW, to these seven measures. While these measures can be applied to various time series analysis tasks, we demonstrate their utility on multivariate time series classification using the nearest neighbor classifier. On 23 well-known datasets, we demonstrate that each of the measures but one achieves the highest accuracy relative to others on at least one dataset, supporting the value of developing a suite of multivariate similarity and distance measures. We also demonstrate that there are datasets for which either the dependent versions of all measures are more accurate than their independent counterparts or vice versa. In addition, we also construct a nearest neighbor-based ensemble of the measures and show that it is competitive to other state-of-the-art single-strategy multivariate time series classifiers. [ABSTRACT FROM AUTHOR]

Land cover maps are a vital input variable to many types of environmental research and management. While they can be produced automatically by machine learning techniques, these techniques require substantial training data to achieve high levels of accuracy, which are not always available. One technique researchers use when labelled training data are scarce is domain adaptation (DA)—where data from an alternate region, known as the source domain, are used to train a classifier and this model is adapted to map the study region, or target domain. The scenario we address in this paper is known as semi-supervised DA, where some labelled samples are available in the target domain. In this paper we present Sourcerer, a Bayesian-inspired, deep learning-based, semi-supervised DA technique for producing land cover maps from satellite image time series (SITS) data. The technique takes a convolutional neural network trained on a source domain and then trains further on the available target domain with a novel regularizer applied to the model weights. The regularizer adjusts the degree to which the model is modified to fit the target data, limiting the degree of change when the target data are few in number and increasing it as target data quantity increases. Our experiments on Sentinel-2 time series images compare Sourcerer with two state-of-the-art semi-supervised domain adaptation techniques and four baseline models. We show that on two different source-target domain pairings Sourcerer outperforms all other methods for any quantity of labelled target data available. In fact, the results on the more difficult target domain show that the starting accuracy of Sourcerer (when no labelled target data are available), 74.2%, is greater than the next-best state-of-the-art method trained on 20,000 labelled target instances. [ABSTRACT FROM AUTHOR]

This paper studies time series extrinsic regression (TSER): a regression task of which the aim is to learn the relationship between a time series and a continuous scalar variable; a task closely related to time series classification (TSC), which aims to learn the relationship between a time series and a categorical class label. This task generalizes time series forecasting, relaxing the requirement that the value predicted be a future value of the input series or primarily depend on more recent values. In this paper, we motivate and study this task, and benchmark existing solutions and adaptations of TSC algorithms on a novel archive of 19 TSER datasets which we have assembled. Our results show that the state-of-the-art TSC algorithm Rocket, when adapted for regression, achieves the highest overall accuracy compared to adaptations of other TSC algorithms and state-of-the-art machine learning (ML) algorithms such as XGBoost, Random Forest and Support Vector Regression. More importantly, we show that much research is needed in this field to improve the accuracy of ML models. We also find evidence that further research has excellent prospects of improving upon these straightforward baselines. [ABSTRACT FROM AUTHOR]

This paper brings deep learning at the forefront of research into time series classification (TSC). TSC is the area of machine learning tasked with the categorization (or labelling) of time series. The last few decades of work in this area have led to significant progress in the accuracy of classifiers, with the state of the art now represented by the HIVE-COTE algorithm. While extremely accurate, HIVE-COTE cannot be applied to many real-world datasets because of its high training time complexity in O (N 2 · T 4) for a dataset with N time series of length T. For example, it takes HIVE-COTE more than 8 days to learn from a small dataset with N = 1500 time series of short length T = 46 . Meanwhile deep learning has received enormous attention because of its high accuracy and scalability. Recent approaches to deep learning for TSC have been scalable, but less accurate than HIVE-COTE. We introduce InceptionTime—an ensemble of deep Convolutional Neural Network models, inspired by the Inception-v4 architecture. Our experiments show that InceptionTime is on par with HIVE-COTE in terms of accuracy while being much more scalable: not only can it learn from 1500 time series in one hour but it can also learn from 8M time series in 13 h, a quantity of data that is fully out of reach of HIVE-COTE. [ABSTRACT FROM AUTHOR]

Most methods for time series classification that attain state-of-the-art accuracy have high computational complexity, requiring significant training time even for smaller datasets, and are intractable for larger datasets. Additionally, many existing methods focus on a single type of feature such as shape or frequency. Building on the recent success of convolutional neural networks for time series classification, we show that simple linear classifiers using random convolutional kernels achieve state-of-the-art accuracy with a fraction of the computational expense of existing methods. Using this method, it is possible to train and test a classifier on all 85 'bake off' datasets in the UCR archive in < 2 h , and it is possible to train a classifier on a large dataset of more than one million time series in approximately 1 h. [ABSTRACT FROM AUTHOR]

Time Series Classification (TSC) has seen enormous progress over the last two decades. HIVE-COTE (Hierarchical Vote Collective of Transformation-based Ensembles) is the current state of the art in terms of classification accuracy. HIVE-COTE recognizes that time series data are a specific data type for which the traditional attribute-value representation, used predominantly in machine learning, fails to provide a relevant representation. HIVE-COTE combines multiple types of classifiers: each extracting information about a specific aspect of a time series, be it in the time domain, frequency domain or summarization of intervals within the series. However, HIVE-COTE (and its predecessor, FLAT-COTE) is often infeasible to run on even modest amounts of data. For instance, training HIVE-COTE on a dataset with only 1500 time series can require 8 days of CPU time. It has polynomial runtime with respect to the training set size, so this problem compounds as data quantity increases. We propose a novel TSC algorithm, TS-CHIEF (Time Series Combination of Heterogeneous and Integrated Embedding Forest), which rivals HIVE-COTE in accuracy but requires only a fraction of the runtime. TS-CHIEF constructs an ensemble classifier that integrates the most effective embeddings of time series that research has developed in the last decade. It uses tree-structured classifiers to do so efficiently. We assess TS-CHIEF on 85 datasets of the University of California Riverside (UCR) archive, where it achieves state-of-the-art accuracy with scalability and efficiency. We demonstrate that TS-CHIEF can be trained on 130 k time series in 2 days, a data quantity that is beyond the reach of any TSC algorithm with comparable accuracy. [ABSTRACT FROM AUTHOR]

In recent years, many new ensemble-based time series classification (TSC) algorithms have been proposed. Each of them is significantly more accurate than their predecessors. The Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) is currently the most accurate TSC algorithm when assessed on the UCR repository. It is a meta-ensemble of 5 state-of-the-art ensemble-based classifiers. The time complexity of HIVE-COTE—particularly for training—is prohibitive for most datasets. There is thus a critical need to speed up the classifiers that compose HIVE-COTE. This paper focuses on speeding up one of its components: Ensembles of Elastic Distances (EE), which is the classifier that leverages on the decades of research into the development of time-dedicated measures. Training EE can be prohibitive for many datasets. For example, it takes a month on the ElectricDevices dataset with 9000 instances. This is because EE needs to cross-validate the hyper-parameters used for the 11 similarity measures it encompasses. In this work, Fast Ensembles of Elastic Distances is proposed to train EE faster. There are two versions to it. The exact version makes it possible to train EE 10 times faster. The approximate version is 40 times faster than EE without significantly impacting the classification accuracy. This translates to being able to train EE on ElectricDevices in 13 h. [ABSTRACT FROM AUTHOR]

Research into the classification of time series has made enormous progress in the last decade. The UCR time series archive has played a significant role in challenging and guiding the development of new learners for time series classification. The largest dataset in the UCR archive holds 10,000 time series only; which may explain why the primary research focus has been on creating algorithms that have high accuracy on relatively small datasets. This paper introduces Proximity Forest, an algorithm that learns accurate models from datasets with millions of time series, and classifies a time series in milliseconds. The models are ensembles of highly randomized Proximity Trees. Whereas conventional decision trees branch on attribute values (and usually perform poorly on time series), Proximity Trees branch on the proximity of time series to one exemplar time series or another; allowing us to leverage the decades of work into developing relevant measures for time series. Proximity Forest gains both efficiency and accuracy by stochastic selection of both exemplars and similarity measures. Our work is motivated by recent time series applications that provide orders of magnitude more time series than the UCR benchmarks. Our experiments demonstrate that Proximity Forest is highly competitive on the UCR archive: it ranks among the most accurate classifiers while being significantly faster. We demonstrate on a 1M time series Earth observation dataset that Proximity Forest retains this accuracy on datasets that are many orders of magnitude greater than those in the UCR repository, while learning its models at least 100,000 times faster than current state-of-the-art models Elastic Ensemble and COTE. [ABSTRACT FROM AUTHOR]

Dynamic Time Warping (DTW) is a highly competitive distance measure for most time series data mining problems. Obtaining the best performance from DTW requires setting its only parameter, the maximum amount of warping (w). In the supervised case with ample data, w is typically set by cross-validation in the training stage. However, this method is likely to yield suboptimal results for small training sets. For the unsupervised case, learning via cross-validation is not possible because we do not have access to labeled data. Many practitioners have thus resorted to assuming that “the larger the better”, and they use the largest value of w permitted by the computational resources. However, as we will show, in most circumstances, this is a naïve approach that produces inferior clusterings. Moreover, the best warping window width is generally non-transferable between the two tasks, i.e., for a single dataset, practitioners cannot simply apply the best w learned for classification on clustering or vice versa. In addition, we will demonstrate that the appropriate amount of warping not only depends on the data structure, but also on the dataset size. Thus, even if a practitioner knows the best setting for a given dataset, they will likely be at a lost if they apply that setting on a bigger size version of that data. All these issues seem largely unknown or at least unappreciated in the community. In this work, we demonstrate the importance of setting DTW’s warping window width correctly, and we also propose novel methods to learn this parameter in both supervised and unsupervised settings. The algorithms we propose to learn w can produce significant improvements in classification accuracy and clustering quality. We demonstrate the correctness of our novel observations and the utility of our ideas by testing them with more than one hundred publicly available datasets. Our forceful results allow us to make a perhaps unexpected claim; an underappreciated “low hanging fruit” in optimizing DTW’s performance can produce improvements that make it an even stronger baseline, closing most or all the improvement gap of the more sophisticated methods proposed in recent years. [ABSTRACT FROM AUTHOR]

This article introduces a new methodology dedicated to classify the evolutions of urban blocks extracted from spatiotemporal topographic databases where an urban block is defined as the smallest area that is surrounded by communication network (roads, railways, . . .). To achieve that, an ascendant hierarchical clustering is applied to sequences of urban block states (i.e., sequences of class labels to which the block belongs to at each date). The principal originality of this approach is to use a distance measure based on DTW (Dynamic Time Warping) which is able to apprehend temporal behaviors (mainly time lags in dates corresponding to a change of state) and which takes into account the semantic proximity between the different kinds of urban blocks. Several experiments have been carried out on areas in the city of Strasbourg (France). First results are relevant and highlight realistic urban dynamics. [ABSTRACT FROM AUTHOR]

A concerted research effort over the past two decades has heralded significant improvements in both the efficiency and effectiveness of time series classification. The consensus that has emerged in the community is that the best solution is a surprisingly simple one. In virtually all domains, the most accurate classifier is the nearest neighbor algorithm with dynamic time warping as the distance measure. The time complexity of dynamic time warping means that successful deployments on resource-constrained devices remain elusive. Moreover, the recent explosion of interest in wearable computing devices, which typically have limited computational resources, has greatly increased the need for very efficient classification algorithms. A classic technique to obtain the benefits of the nearest neighbor algorithm, without inheriting its undesirable time and space complexity, is to use the nearest centroid algorithm. Unfortunately, the unique properties of (most) time series data mean that the centroid typically does not resemble any of the instances, an unintuitive and underappreciated fact. In this paper we demonstrate that we can exploit a recent result by Petitjean et al. to allow meaningful averaging of 'warped' time series, which then allows us to create super-efficient nearest 'centroid' classifiers that are at least as accurate as their more computationally challenged nearest neighbor relatives. We demonstrate empirically the utility of our approach by comparing it to all the appropriate strawmen algorithms on the ubiquitous UCR Benchmarks and with a case study in supporting insect classification on resource-constrained sensors. [ABSTRACT FROM AUTHOR]

Abstract: Satellite image time series (SITS) analysis is an important domain with various applications in land study. In the coming years, both high temporal and high spatial resolution SITS will become available. In the classical methodologies, SITS are studied by analyzing the radiometric evolution of the pixels with time. When dealing with high spatial resolution images, object-based approaches are generally used in order to exploit the spatial relationships of the data. However, these approaches require a segmentation step to provide contextual information about the pixels. Even if the segmentation of single images is widely studied, its generalization to series of images remains an open-issue. This article aims at providing both temporal and spatial analysis of SITS. We propose first segmenting each image of the series, and then using these segmentations in order to characterize each pixel of the data with a spatial dimension (i.e., with contextual information). Providing spatially characterized pixels, pixel-based temporal analysis can be performed. Experiments carried out with this methodology show the relevance of this approach and the significance of the resulting extracted patterns in the context of the analysis of SITS. [Copyright &y& Elsevier]

Satellite Image Time Series are becoming increasingly available and will continue to do so in the coming years thanks to the launch of space missions which aim at providing a coverage of the Earth every few days with high spatial resolution. In the case of optical imagery, it will be possible to produce land use and cover change maps with detailed nomenclatures. However, due to meteorological phenomena, such as clouds, these time series will become irregular in terms of temporal sampling, and one will need to compare time series with different lengths. In this paper, we present an approach to image time series analysis which is able to deal with irregularly sampled series and which also allows the comparison of pairs of time series where each element of the pair has a different number of samples. We present the dynamic time warping from a theoretical point of view and illustrate its capabilities with two applications to real-time series. [ABSTRACT FROM PUBLISHER]

Satellite Image Time Series (SITS) provide us with precious information on land cover evolution. By studying these series of images we can both understand the changes of specific areas and discover global phenomena that spread over larger areas. Changes that can occur throughout the sensing time can spread over very long periods and may have different start time and end time depending on the location, which complicates the mining and the analysis of series of images. This work focuses on frequent sequential pattern mining (FSPM) methods, since this family of methods fits the above-mentioned issues. This family of methods consists of finding the most frequent evolution behaviors, and is actually able to extract long-term changes as well as short term ones, whenever the change may start and end. However, applying FSPM methods to SITS implies confronting two main challenges, related to the characteristics of SITS and the domain's constraints. First, satellite images associate multiple measures with a single pixel (the radiometric levels of different wavelengths corresponding to infra-red, red, etc.), which makes the search space multi-dimensional and thus requires specific mining algorithms. Furthermore, the non evolving regions, which are the vast majority and overwhelm the evolving ones, challenge the discovery of these patterns. We propose a SITS mining framework that enables discovery of these patterns despite these constraints and characteristics. Our proposal is inspired from FSPM and provides a relevant visualization principle. Experiments carried out on 35 images sensed over 20 years show the proposed approach makes it possible to extract relevant evolution behaviors. [ABSTRACT FROM AUTHOR]

• Four novel and effective lower bounds for Dynamic Time Warping that have linear complexity. • Provide substantial speed-up for nearest neighbor time series search. • Useful under a wide variety of different types of nearest neighbour search. Dynamic Time Warping (DTW) is a popular similarity measure for aligning and comparing time series. Due to DTW 's high computation time, lower bounds are often employed to screen poor matches. Many alternative lower bounds have been proposed, providing a range of different trade-offs between tightness and computational efficiency. LB _ KEOGH provides a useful trade-off in many applications. Two recent lower bounds, LB _ IMPROVED and LB _ ENHANCED , are substantially tighter than LB _ KEOGH. All three have the same worst case computational complexity—linear with respect to series length and constant with respect to window size. We present four new DTW lower bounds in the same complexity class. LB _ PETITJEAN is substantially tighter than LB _ IMPROVED , with only modest additional computational overhead. LB _ WEBB is more efficient than LB _ IMPROVED , while often providing a tighter bound. LB _ WEBB is always tighter than LB _ KEOGH. The parameter free LB _ WEBB is usually tighter than LB _ ENHANCED. A parameterized variant, LB_Webb_Enhanced , is always tighter than LB _ ENHANCED. A further variant, LB _ WEBB * , is useful for some constrained distance functions. In extensive experiments, LB _ WEBB proves to be very effective for nearest neighbor search. [ABSTRACT FROM AUTHOR]

Latest remote sensing sensors are capable of acquiring high spatial and spectral Satellite Image Time Series (SITS) of the world. These image series are a key component of classification systems that aim at obtaining up-to-date and accurate land cover maps of the Earth's surfaces. More specifically, current SITS combine high temporal, spectral and spatial resolutions, which makes it possible to closely monitor vegetation dynamics. Although traditional classification algorithms, such as Random Forest (RF), have been successfully applied to create land cover maps from SITS, these algorithms do not make the most of the temporal domain. This paper proposes a comprehensive study of Temporal Convolutional Neural Networks (TempCNNs), a deep learning approach which applies convolutions in the temporal dimension in order to automatically learn temporal (and spectral) features. The goal of this paper is to quantitatively and qualitatively evaluate the contribution of TempCNNs for SITS classification, as compared to RF and Recurrent Neural Networks (RNNs) —a standard deep learning approach that is particularly suited to temporal data. We carry out experiments on Formosat-2 scene with 46 images and one million labelled time series. The experimental results show that TempCNNs are more accurate than the current state of the art for SITS classification. We provide some general guidelines on the network architecture, common regularization mechanisms, and hyper-parameter values such as batch size; we also draw out some differences with standard results in computer vision (e.g., about pooling layers). Finally, we assess the visual quality of the land cover maps produced by TempCNNs. [ABSTRACT FROM AUTHOR]

Live fuel moisture content (LFMC) is an essential variable to model fire danger and behaviour. This paper presents the first application of deep learning to LFMC estimation based on the historical LFMC ground samples of the Globe-LFMC database, as a step towards operational daily LFMC mapping in the Contiguous United States (CONUS). One-year MODerate resolution Imaging Spectroradiometer (MODIS) time series preceding each LFMC sample were extracted as the primary data source for training. The proposed temporal convolutional neural network for LFMC (TempCNN-LFMC) comprises three 1-D convolutional layers that learn the multi-scale temporal dynamics (features) of one-year MODIS time series specific to LFMC estimation. The learned features, together with a few auxiliary variables (e.g., digital elevation model), are then passed to three fully connected layers to extract the non-linear relationships with LFMC. In the primary training and validation scenario, the neural network was trained using samples from 2002 to 2013 and then adopted to estimating the LFMC from 2014 to 2018, achieving an overall root mean square error (RMSE) of 25.57% and a correlation coefficient (R) of 0.74. Good consistency on spatial patterns and temporal trends of accuracy was observed. The trained model achieved a similar RMSE of 25.98%, 25.20% and 25.93% for forest, shrubland, and grassland, respectively, without requiring prior information on the vegetation type. [ABSTRACT FROM AUTHOR]