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.

Many approaches have been proposed for early classification of time series in light of its significance in a wide range of applications including healthcare, transportation and finance. Until now, the early classification problem has been dealt with by considering only irrevocable decisions. This paper introduces a new problem called early and revocable time series classification, where the decision maker can revoke its earlier decisions based on the new available measurements. In order to formalize and tackle this problem, we propose a new cost-based framework and derive two new approaches from it. The first approach does not consider explicitly the cost of changing decision, while the second one does. Extensive experiments are conducted to evaluate these approaches on a large benchmark of real datasets. The empirical results obtained convincingly show (i ) that the ability of revoking decisions significantly improves performance over the irrevocable regime, and (ii ) that taking into account the cost of changing decision brings even better results in general.