Results 1  10
of
60
Fast Time Series Classification Using Numerosity Reduction
 In ICML’06
, 2006
"... Many algorithms have been proposed for the problem of time series classification. However, it is clear that onenearestneighbor with Dynamic Time Warping (DTW) distance is exceptionally difficult to beat. This approach has one weakness, however; it is computationally too demanding for many realtime ..."
Abstract

Cited by 65 (12 self)
 Add to MetaCart
(Show Context)
Many algorithms have been proposed for the problem of time series classification. However, it is clear that onenearestneighbor with Dynamic Time Warping (DTW) distance is exceptionally difficult to beat. This approach has one weakness, however; it is computationally too demanding for many realtime applications. One way to mitigate this problem is to speed up the DTW calculations. Nonetheless, there is a limit to how much this can help. In this work, we propose an additional technique, numerosity reduction, to speed up onenearestneighbor DTW. While the idea of numerosity reduction for nearestneighbor classifiers has a long history, we show here that we can leverage off an original observation about the relationship between dataset size and DTW constraints to produce an extremely compact dataset with little or no loss in accuracy. We test our ideas with a comprehensive set of experiments, and show that it can efficiently produce extremely fast accurate classifiers. 1.
R.P.W.: Building road sign classifiers using a trainable similarity measure
 Journal of Intelligent Transportations Systems
, 2006
"... Abstract—Deriving an informative data representation is an important prerequisite when designing roadsign classifiers. A frequently used strategy for roadsign classification is based on the normalized cross correlation similarity to class prototypes followed by the nearest neighbor classifier. Bec ..."
Abstract

Cited by 25 (1 self)
 Add to MetaCart
(Show Context)
Abstract—Deriving an informative data representation is an important prerequisite when designing roadsign classifiers. A frequently used strategy for roadsign classification is based on the normalized cross correlation similarity to class prototypes followed by the nearest neighbor classifier. Because of the global nature of the cross correlation similarity, this method suffers from presence of uninformative pixels (caused, e.g., by occlusions) and is computationally demanding. In this paper, a novel concept of a trainable similarity measure is introduced, which alleviates these shortcomings. The similarity is based on individual matches in a set of local image regions. The set of regions that are relevant for a particular similarity assessment is refined by the training process. It is illustrated on a set of experiments with roadsignclassification problems that the trainable similarity yields highperformance data representations and classifiers. Apart from a multiclass classification accuracy, nonsign rejection capability and computational demands in execution are also discussed. It appears that the trainable similarity representation alleviates some difficulties of other algorithms that are currently used in roadsign classification. Index Terms—Classifier system design, roadsign classification, similarity data representation.
Anytime classification using the nearest neighbor algorithm with applications to stream mining
 IEEE International Conference on Data Mining (ICDM
, 2006
"... For many real world problems we must perform classification under widely varying amounts of computational resources. For example, if asked to classify an instance taken from a bursty stream, we may have from milliseconds to minutes to return a class prediction. For such problems an anytime algorithm ..."
Abstract

Cited by 23 (11 self)
 Add to MetaCart
(Show Context)
For many real world problems we must perform classification under widely varying amounts of computational resources. For example, if asked to classify an instance taken from a bursty stream, we may have from milliseconds to minutes to return a class prediction. For such problems an anytime algorithm may be especially useful. In this work we show how we can convert the ubiquitous nearest neighbor classifier into an anytime algorithm that can produce an instant classification, or if given the luxury of additional time, can utilize the extra time to increase classification accuracy. We demonstrate the utility of our approach with a comprehensive set of experiments on data from diverse domains.
Accelerating dynamic time warping subsequence search with GPUs and FPGAs
 in Proc. ICDM, 2010
"... Abstract—Many time series data mining problems require subsequence similarity search as a subroutine. While this can be performed with any distance measure, and dozens of distance measures have been proposed in the last decade, there is increasing evidence that Dynamic Time Warping (DTW) is the best ..."
Abstract

Cited by 17 (3 self)
 Add to MetaCart
(Show Context)
Abstract—Many time series data mining problems require subsequence similarity search as a subroutine. While this can be performed with any distance measure, and dozens of distance measures have been proposed in the last decade, there is increasing evidence that Dynamic Time Warping (DTW) is the best measure across a wide range of domains. Given DTW’s usefulness and ubiquity, there has been a large communitywide effort to mitigate its relative lethargy. Proposed speedup techniques include early abandoning strategies, lowerbound based pruning, indexing and embedding. In this work we argue that we are now close to exhausting all possible speedup from software, and that we must turn to hardwarebased solutions if we are to tackle the many problems that are currently untenable even with stateoftheart algorithms running on highend desktops. With this motivation, we investigate both GPU (Graphics Processing Unit) and FPGA (Field Programmable Gate Array) based acceleration of subsequence similarity search under the DTW measure. As we shall show, our novel algorithms allow GPUs, which are typically bundled with standard desktops, to achieve two orders of magnitude speedup. For problem domains which require even greater scale up, we show that FPGAs costing just a few thousand dollars can be used to produce four orders of magnitude speedup. We conduct detailed case studies on the classification of astronomical observations and similarity search in commercial agriculture, and demonstrate that our ideas allow us to tackle problems that would be simply untenable otherwise. Keywords time series; similarity search; dynamic time warping; FPGA; GPU; I.
A taxonomy and experimental study on prototype generation for nearest neighbor classification
 IEEE Trans. Syst., Man, Cybern. C, Appl. Rev
, 2012
"... Abstract—The nearest neighbor (NN) rule is one of the most successfully used techniques to resolve classification and pattern recognition tasks. Despite its high classification accuracy, this rule suffers from several shortcomings in time response, noise sensitivity, and high storage requirements. ..."
Abstract

Cited by 16 (4 self)
 Add to MetaCart
(Show Context)
Abstract—The nearest neighbor (NN) rule is one of the most successfully used techniques to resolve classification and pattern recognition tasks. Despite its high classification accuracy, this rule suffers from several shortcomings in time response, noise sensitivity, and high storage requirements. These weaknesses have been tackled by many different approaches, including a good and wellknown solution that we can find in the literature, which consists of the reduction of the data used for the classification rule (training data). Prototype reduction techniques can be divided into two different approaches, which are known as prototype selection and prototype generation (PG) or abstraction. The former process consists of choosing a subset of the original training data, whereas PG builds new artificial prototypes to increase the accuracy of the NN classification. In this paper, we provide a survey of PG methods specifically designed for the NN rule. From a theoretical point of view, we propose a taxonomy based on the main characteristics presented in them. Furthermore, from an empirical point of view, we conduct a wide experimental study that involves small and large datasets to measure their performance in terms of accuracy and reduction capabilities. The results are contrasted through nonparametrical statistical tests. Several remarks are made to understand which PG models are appropriate for application to different datasets. Index Terms—Classification, learning vector quantization (LVQ), nearest neighbor (NN), prototype generation (PG), taxonomy. I.
Distances and (indefinite) kernels for sets of objects
 In ICDM
, 2006
"... For various classification problems involving complex data, it is most natural to represent each training example as a set of vectors. While several distance measures for sets have been proposed, only a few kernels over these structures exist since it is difficult in general to design a positive sem ..."
Abstract

Cited by 15 (1 self)
 Add to MetaCart
For various classification problems involving complex data, it is most natural to represent each training example as a set of vectors. While several distance measures for sets have been proposed, only a few kernels over these structures exist since it is difficult in general to design a positive semidefinite (PSD) similarity function. The main disadvantage of most existing set kernels is that they are based on averaging, which might be inappropriate for problems where only specific elements of the two sets should determine the overall similarity. In this paper we propose a class of kernels for sets of vectors directly exploiting set distance measures and, hence, incorporating various semantics into set kernels and lending the power of regularization to learning in structural domains where natural distance functions exist. These kernels belong to two groups: (i) kernels in the proximity space induced by set distances and (ii) set distance substitution kernels (nonPSD in general). We report experimental results which show that our kernels compare favorably with kernels based on averaging and achieve results similar to other stateoftheart methods. At the same time our kernels bring systematically improvement over the naive way of exploiting distances. 1
Transforming strings to vector spaces using prototype selection
, 2006
"... Abstract. A common way of expressing string similarity in structural pattern recognition is the edit distance. It allows one to apply the kNN rule in order to classify a set of strings. However, compared to the wide range of elaborated classifiers known from statistical pattern recognition, this is ..."
Abstract

Cited by 14 (5 self)
 Add to MetaCart
(Show Context)
Abstract. A common way of expressing string similarity in structural pattern recognition is the edit distance. It allows one to apply the kNN rule in order to classify a set of strings. However, compared to the wide range of elaborated classifiers known from statistical pattern recognition, this is only a very basic method. In the present paper we propose a method for transforming strings into ndimensional real vector spaces based on prototype selection. This allows us to subsequently classify the transformed strings with more sophisticated classifiers, such as support vector machine and other kernel based methods. In a number of experiments, we show that the recognition rate can be significantly improved by means of this procedure. 1
Selecting vantage objects for similarity indexing
 International Conference on Pattern Recognition (ICPR) 2006, Hong Kong
"... To make similarity searching in multimedia databases practical, indexing has become a necessity. Vantage indexing is an indexing technique which maps a dissimilarity space onto a vector space such that each object is represented by a vector of dissimilarities to a small set ofm reference objects, ..."
Abstract

Cited by 11 (5 self)
 Add to MetaCart
(Show Context)
To make similarity searching in multimedia databases practical, indexing has become a necessity. Vantage indexing is an indexing technique which maps a dissimilarity space onto a vector space such that each object is represented by a vector of dissimilarities to a small set ofm reference objects, the vantage objects. Querying takes place within this vector space, reducing the number of distance calculations to m. The retrieval performance of a system based on this technique can be improved significantly through a proper choice of vantage objects. We propose a new technique for selecting vantage objects and present experimental results based on data sets of different modality. 1.
Time Series Classification under More Realistic Assumptions
"... Most literature on time series classification assumes that the beginning and ending points of the pattern of interest can be correctly identified, both during the training phase and later deployment. In this work, we argue that this assumption is unjustified, and this has in many cases led to unwarr ..."
Abstract

Cited by 10 (5 self)
 Add to MetaCart
(Show Context)
Most literature on time series classification assumes that the beginning and ending points of the pattern of interest can be correctly identified, both during the training phase and later deployment. In this work, we argue that this assumption is unjustified, and this has in many cases led to unwarranted optimism about the performance of the proposed algorithms. As we shall show, the task of correctly extracting individual gait cycles, heartbeats, gestures, behaviors, etc., is generally much more difficult than the task of actually classifying those patterns. We propose to mitigate this problem by introducing an alignmentfree time series classification framework. The framework requires only very weakly annotated data, such as “in this ten minutes of data, we see mostly normal heartbeats..., ” and by generalizing the classic machine learning idea of data editing to streaming/continuous data, allows us to build robust, fast and accurate classifiers. We demonstrate on several diverse realworld problems that beyond removing unwarranted assumptions and requiring essentially no human intervention, our framework is both significantly faster and significantly more accurate than current stateoftheart approaches. 1.