Early Classification Of Time Series Research Articles

A Ranking-Based Cross-Entropy Loss for Early Classification of Time Series.

Early classification tasks aim to classify time series before observing full data. It is critical in time-sensitive applications such as early sepsis diagnosis in the intensive care unit (ICU). Early diagnosis can provide more opportunities for doctors to rescue lives. However, there are two conflicting goals in the early classification task-accuracy and earliness. Most existing methods try to find a balance between them by weighing one goal against the other. But we argue that a powerful early classifier should always make highly accurate predictions at any moment. The main obstacle is that the key features suitable for classification are not obvious in the early stage, resulting in the excessive overlap of time series distributions in different time stages. The indistinguishable distributions make it difficult for classifiers to recognize. To solve this problem, this article proposes a novel ranking-based cross-entropy () loss to jointly learn the feature of classes and the order of earliness from time series data. In this way, can help classifier to generate probability distributions of time series in different stages with more distinguishable boundary. Thus, the classification accuracy at each time step is finally improved. Besides, for the applicability of the method, we also accelerate the training process by focusing the learning process on high-ranking samples. Experiments on three real-world datasets show that our method can perform classification more accurately than all baselines at all moments.

Snippet Policy Network V2: Knee-Guided Neuroevolution for Multi-Lead ECG Early Classification.

Early time series classification predicts the class label of a given time series before it is completely observed. In time-critical applications, such as arrhythmia monitoring in ICU, early treatment contributes to the patient's fast recovery, and early warning could even save lives. Hence, in these cases, it is worthy of trading, to some extent, classification accuracy in favor of earlier decisions when the time series data are collected over time. In this article, we propose a novel deep reinforcement learning-based framework, snippet policy network V2 (SPN-V2), for long and varied-length multi-lead electrocardiogram (ECG) early classification. The proposed SNP-V2 contains two main components: snippet representation learning (SRL) and early classification timing learning (ECTL). The SRL is proposed to encode inner-snippet spatial correlations and inter-snippet temporal correlations into the hidden representations of the subsegment (snippet) of the input ECG. ECTL aims to learn a decision agent to classify the time series early and accurately. To optimize the proposed framework, we design a novel knee-guided neuroevolution algorithm (KGNA) to solve cardiovascular diseases' early classification problem, automatically optimizing the proposed SPN-V2 regarding the tradeoff between accuracy and earliness. In addition, we conduct a series of experiments on two real-world ECG datasets. The experimental results show the superiority of the proposed algorithm over the state-of-the-art competing methods.

Second-order Confidence Network for Early Classification of Time Series

Time series data are ubiquitous in a variety of disciplines. Early classification of time series, which aims to predict the class label of a time series as early and accurately as possible, is a significant but challenging task in many time-sensitive applications. Existing approaches mainly utilize heuristic stopping rules to capture stopping signals from the prediction results of time series classifiers. However, heuristic stopping rules can only capture obvious stopping signals, which makes these approaches give either correct but late predictions or early but incorrect predictions. To tackle the problem, we propose a novel second-order confidence network for early classification of time series, which can automatically learn to capture implicit stopping signals in early time series in a unified framework. The proposed model leverages deep neural models to capture temporal patterns and outputs second-order confidence to reflect the implicit stopping signals. Specifically, our model exploits the data not only from a time step but also from the probability sequence to capture stopping signals. By combining stopping signals from the classifier output and the second-order confidence, we design a more robust trigger to decide whether or not to request more observations from future time steps. Experimental results show that our approach can achieve superior results in early classification compared to state-of-the-art approaches.

CALIMERA: A new early time series classification method

Early time series classification is a variant of the time series classification task, in which a label must be assigned to the incoming time series as quickly as possible without necessarily screening through the whole sequence. It needs to be realized on the algorithmic level by fusing a decision-making method that detects the right moment to stop and a classifier that assigns a class label. The contribution addressed in this paper is twofold. Firstly, we present a new method for finding the best moment to perform an action (terminate/continue). Secondly, we propose a new learning scheme using classifier calibration to estimate classification accuracy. The new approach, called CALIMERA, is formalized as a cost minimization problem. Using two benchmark methodologies for early time series classification, we have shown that the proposed model achieves better results than the current state-of-the-art. Two most serious competitors of CALIMERA are ECONOMY and TEASER. The empirical comparison showed that the new method achieved a higher accuracy than TEASER for 35 out of 45 datasets and it outperformed ECONOMY in 20 out of 34 datasets.

End-to-end learned early classification of time series for in-season crop type mapping

Remote sensing satellites capture the cyclic dynamics of our Planet in regular time intervals recorded in satellite time series data. End-to-end trained deep learning models use this time series data to make predictions at a large scale, for instance, to produce up-to-date crop cover maps. Most time series classification approaches focus on the accuracy of predictions. However, the earliness of the prediction is also of great importance since coming to an early decision can make a crucial difference in time-sensitive applications.In this work, we present an End-to-End Learned Early Classification of Time Series (ELECTS) model that estimates a classification score and a probability of whether sufficient data has been observed to come to an early and still accurate decision. ELECTS is modular: any deep time series classification model can adopt the ELECTS conceptual idea by adding a second prediction head that outputs a probability of stopping the classification. The ELECTS loss function then optimizes the overall model on a balanced objective of earliness and accuracy. Our experiments on four crop classification datasets from Europe and Africa show that ELECTS allows reaching state-of-the-art accuracy while reducing the quantity of data massively to be downloaded, stored, and processed. The source code is available at https://github.com/marccoru/elects.

Open challenges for Machine Learning based Early Decision-Making research

More and more applications require early decisions, i.e. taken as soon as possible from partially observed data. However, the later a decision is made, the more its accuracy tends to improve, since the description of the problem to hand is enriched over time. Such a compromise between the earliness and the accuracy of decisions has been particularly studied in the field of Early Time Series Classification. This paper introduces a more general problem, called Machine Learning based Early Decision Making (ML-EDM), which consists in optimizing the decision times of models in a wide range of settings where data is collected over time. After defining the ML-EDM problem, ten challenges are identified and proposed to the scientific community to further research in this area. These challenges open important application perspectives, discussed in this paper.

Technology investigation on time series classification and prediction.

Time series appear in many scientific fields and are an important type of data. The use of time series analysis techniques is an essential means of discovering the knowledge hidden in this type of data. In recent years, many scholars have achieved fruitful results in the study of time series. A statistical analysis of 120,000 literatures published between 2017 and 2021 reveals that the topical research about time series is mostly focused on their classification and prediction. Therefore, in this study, we focus on analyzing the technical development routes of time series classification and prediction algorithms. 87 literatures with high relevance and high citation are selected for analysis, aiming to provide a more comprehensive reference base for interested researchers. For time series classification, it is divided into supervised methods, semi-supervised methods, and early classification of time series, which are key extensions of time series classification tasks. For time series prediction, from classical statistical methods, to neural network methods, and then to fuzzy modeling and transfer learning methods, the performance and applications of these different methods are discussed. We hope this article can help aid the understanding of the current development status and discover possible future research directions, such as exploring interpretability of time series analysis and online learning modeling.

Data-Driven Fault Diagnosis in a Complex Hydraulic System based on Early Classification

In this paper, an early time-series classification (ETSC) algorithm is applied to support fault diagnosis in a complex hydraulic system (HS) with several interconnected components. The proposed technique aims at early classifying the state of the system while keeping the loss of classification inaccuracy at the minimum level. In contrast to baseline models that detect the eventual faults at the end of each working cycle, the ETSC model can diagnose any fault type of the HS components before observing the entire working cycle. Indeed, the early classification model successfully achieves a trade-off between the accuracy and the earliness criterion. Experimental results on a realistic HS dataset from the related literature show that the ETSC method can effectively identify different fault types with a higher accuracy and earlier compared to baseline methodologies.

Crop Type Mapping from Optical and Radar Time Series Using Attention-Based Deep Learning

Crop maps are key inputs for crop inventory production and yield estimation and can inform the implementation of effective farm management practices. Producing these maps at detailed scales requires exhaustive field surveys that can be laborious, time-consuming, and expensive to replicate. With a growing archive of remote sensing data, there are enormous opportunities to exploit dense satellite image time series (SITS), temporal sequences of images over the same area. Generally, crop type mapping relies on single-sensor inputs and is solved with the help of traditional learning algorithms such as random forests or support vector machines. Nowadays, deep learning techniques have brought significant improvements by leveraging information in both spatial and temporal dimensions, which are relevant in crop studies. The concurrent availability of Sentinel-1 (synthetic aperture radar) and Sentinel-2 (optical) data offers a great opportunity to utilize them jointly; however, optimizing their synergy has been understudied with deep learning techniques. In this work, we analyze and compare three fusion strategies (input, layer, and decision levels) to identify the best strategy that optimizes optical-radar classification performance. They are applied to a recent architecture, notably, the pixel-set encoder–temporal attention encoder (PSE-TAE) developed specifically for object-based classification of SITS and based on self-attention mechanisms. Experiments are carried out in Brittany, in the northwest of France, with Sentinel-1 and Sentinel-2 time series. Input and layer-level fusion competitively achieved the best overall F-score surpassing decision-level fusion by 2%. On a per-class basis, decision-level fusion increased the accuracy of dominant classes, whereas layer-level fusion improves up to 13% for minority classes. Against single-sensor baseline, multi-sensor fusion strategies identified crop types more accurately: for example, input-level outperformed Sentinel-2 and Sentinel-1 by 3% and 9% in F-score, respectively. We have also conducted experiments that showed the importance of fusion for early time series classification and under high cloud cover condition.

Survey of early time series classification methods

Survey of early time series classification methods

Early classification of time series based on trend segmentation and optimization cost function

Early classification of time series based on trend segmentation and optimization cost function

MultiETSC: automated machine learning for early time series classification

Early time series classification (EarlyTSC) involves the prediction of a class label based on partial observation of a given time series. Most EarlyTSC algorithms consider the trade-off between accuracy and earliness as two competing objectives, using a single dedicated hyperparameter. To obtain insights into this trade-off requires finding a set of non-dominated (Pareto efficient) classifiers. So far, this has been approached through manual hyperparameter tuning. Since the trade-off hyperparameters only provide indirect control over the earliness-accuracy trade-off, manual tuning is tedious and tends to result in many sub-optimal hyperparameter settings. This complicates the search for optimal hyperparameter settings and forms a hurdle for the application of EarlyTSC to real-world problems. To address these issues, we propose an automated approach to hyperparameter tuning and algorithm selection for EarlyTSC, building on developments in the fast-moving research area known as automated machine learning (AutoML). To deal with the challenging task of optimising two conflicting objectives in early time series classification, we propose MultiETSC, a system for multi-objective algorithm selection and hyperparameter optimisation (MO-CASH) for EarlyTSC. MultiETSC can potentially leverage any existing or future EarlyTSC algorithm and produces a set of Pareto optimal algorithm configurations from which a user can choose a posteriori. As an additional benefit, our proposed framework can incorporate and leverage time-series classification algorithms not originally designed for EarlyTSC for improving performance on EarlyTSC; we demonstrate this property using a newly defined, “naïve” fixed-time algorithm. In an extensive empirical evaluation of our new approach on a benchmark of 115 data sets, we show that MultiETSC performs substantially better than baseline methods, ranking highest (avg. rank 1.98) compared to conceptually simpler single-algorithm (2.98) and single-objective alternatives (4.36).

Early classification of time series

An increasing number of applications require to recognize the class of an incoming time series as quickly as possible without unduly compromising the accuracy of the prediction. In this paper, we put forward a new optimization criterion which takes into account both the cost of misclassification and the cost of delaying the decision. Based on this optimization criterion, we derived a family of non-myopic algorithms which try to anticipate the expected future gain in information in balance with the cost of waiting. In one class of algorithms, unsupervised-based, the expectations use the clustering of time series, while in a second class, supervised-based, time series are grouped according to the confidence level of the classifier used to label them. Extensive experiments carried out on real datasets using a large range of delay cost functions show that the presented algorithms are able to solve the earliness vs. accuracy trade-off, with the supervised partition based approaches faring better than the unsupervised partition based ones. In addition, all these methods perform better in a wide variety of conditions than a state of the art method based on a myopic strategy which is recognized as being very competitive. Furthermore, our experiments show that the non-myopic feature of the proposed approaches explains in large part the obtained performances.

When is Early Classification of Time Series Meaningful

Since its introduction two decades ago, there has been increasing interest in the problem of early classification of time series. This problem generalizes classic time series classification to ask if we can classify a time series subsequence with sufficient accuracy and confidence after seeing only some prefix of a target pattern. The idea is that the earlier classification would allow us to take immediate action, in a domain in which some practical interventions are possible. For example, that intervention might be sounding an alarm or applying the brakes in an automobile. In this work, we make a surprising claim. In spite of the fact that there are dozens of papers on early classification of time series, it is not clear that any of them could ever work in a real-world setting. The problem is not with the algorithms per se but with the vague and underspecified problem description. Essentially all algorithms make implicit and unwarranted assumptions about the problem that will ensure that they will be plagued by false positives and false negatives even if their results suggested that they could obtain near-perfect results. We will explain our findings with novel insights and experiments and offer recommendations to the community.

Approaches and Applications of Early Classification of Time Series: A Review

Early classification of time series has been extensively studied for minimizing class prediction delay in time-sensitive applications such as healthcare and finance. A primary task of an early classification approach is to classify an incomplete time series as soon as possible with some desired level of accuracy. Recent years have witnessed several approaches for early classification of time series. As most of the approaches have solved the early classification problem with different aspects, it becomes very important to make a thorough review of the existing solutions to know the current status of the area. These solutions have demonstrated reasonable performance in a wide range of applications including human activity recognition, gene expression based health diagnostic, industrial monitoring, and so on. In this paper, we present a systematic review of current literature on early classification approaches for both univariate and multivariate time series. We divide various existing approaches into four exclusive categories based on their proposed solution strategies. The four categories include prefix based, shapelet based, model based, and miscellaneous approaches. The authors also discuss the applications of early classification in many areas including industrial monitoring, intelligent transportation, and medical. Finally, we provide a quick summary of the current literature with future research directions.

Development of Indicator of Data Sufficiency for Feature-based Early Time Series Classification with Applications of Bearing Fault Diagnosis

Diagnosis of bearing faults is crucial in various industries. Time series classification (TSC) assigns each time series to one of a set of pre-defined classes, such as normal and fault, and has been regarded as an appropriate approach for bearing fault diagnosis. Considering late and inaccurate fault diagnosis may have a significant impact on maintenance costs, it is important to classify bearing signals as early and accurately as possible. TSC, however, has a major limitation, which is that a time series cannot be classified until the entire series is collected, implying that a fault cannot be diagnosed using TSC in advance. Therefore, it is important to classify a partially collected time series for early time series classification (ESTC), which is a TSC that considers both accuracy and earliness. Feature-based TSCs can handle this, but the problem is to determine whether a partially collected time series is enough for a decision that is still unsolved. Motivated by this, we propose an indicator of data sufficiency to determine whether a feature-based fault detection classifier can start classifying partially collected signals in order to diagnose bearing faults as early and accurately as possible. The indicator is trained based on the cosine similarity between signals that were collected fully and partially as input to the classifier. In addition, a parameter setting method for efficiently training the indicator is also proposed. The results of experiments using four benchmark datasets verified that the proposed indicator increased both accuracy and earliness compared with the previous time series classification method and general time series classification.

TEASER: early and accurate time series classification

Early time series classification (eTSC) is the problem of classifying a time series after as few measurements as possible with the highest possible accuracy. The most critical issue of any eTSC method is to decide when enough data of a time series has been seen to take a decision: Waiting for more data points usually makes the classification problem easier but delays the time in which a classification is made; in contrast, earlier classification has to cope with less input data, often leading to inferior accuracy. The state-of-the-art eTSC methods compute a fixed optimal decision time assuming that every times series has the same defined start time (like turning on a machine). However, in many real-life applications measurements start at arbitrary times (like measuring heartbeats of a patient), implying that the best time for taking a decision varies widely between time series. We present TEASER, a novel algorithm that models eTSC as a two-tier classification problem: In the first tier, a classifier periodically assesses the incoming time series to compute class probabilities. However, these class probabilities are only used as output label if a second-tier classifier decides that the predicted label is reliable enough, which can happen after a different number of measurements. In an evaluation using 45 benchmark datasets, TEASER is two to three times earlier at predictions than its competitors while reaching the same or an even higher classification accuracy. We further show TEASER’s superior performance using real-life use cases, namely energy monitoring, and gait detection.

Efficient genetic algorithm for feature selection for early time series classification

This paper addresses a multi-objective feature selection problem for early time series classification. Previous research has focused on how many features to consider for a classifier, but has not considered the starting time of classification, which is also important for early classification. Motivated by this, we developed a mathematical model for which the objectives are to maximize classification performance and minimize the starting time and execution time of classification. We designed an efficient genetic algorithm to generate solutions with high probability. In experiment, we compared the proposed algorithm and general genetic algorithm under various experimental settings. From the experiment, we verified that the proposed algorithm can find a better feature set in terms of classification performance, starting time and execution time of classification than feature set found by general genetic algorithm.

Corrections to “An Effective Confidence-Based Early Classification of Time Series”

Corrections to “An Effective Confidence-Based Early Classification of Time Series”

Early classification of time series using multi-objective optimization techniques

In early classification of time series the objective is to build models which are able to make class-predictions for time series as accurately and as early as possible, when only a part of the series is available. It is logical to think that accuracy and earliness are conflicting objectives, since the more we wait, more data points from the series are available, and it is easier to make accurate class-predictions. Considering this, the problem can be very naturally formulated as a multi-objective optimization problem, and solved as such. However, the solutions proposed in the literature up to now, reduce the problem into a single-objective problem by combining both objectives somehow. In this paper, we present a novel multi-objective formulation of the problem of early classification, and we design a solution using multi-objective optimization techniques. This method will provide a variety of solutions which find different trade-offs between both objectives, allowing the user to select the most suitable solution a-posteriori, depending on the accuracy and earliness requirements of the problem at hand. To prove the usefulness of our proposal, we carry out an extensive experimentation process using 45 benchmark databases and we present a case study in the financial domain.