Showing papers on "Dynamic time warping published in 2011"

Driving style recognition using a smartphone as a sensor platform

Abstract: Driving style can characteristically be divided into two categories: “typical” (non-aggressive) and aggressive. Understanding and recognizing driving events that fall into these categories can aid in vehicle safety systems. Potentially-aggressive driving behavior is currently a leading cause of traffic fatalities in the United States. More often than not, drivers are unaware that they commit potentially-aggressive actions daily. To increase awareness and promote driver safety, we are proposing a novel system that uses Dynamic Time Warping (DTW) and smartphone based sensor-fusion (accelerometer, gyroscope, magnetometer, GPS, video) to detect, recognize and record these actions without external processing. Our system differs from past driving pattern recognition research by fusing related inter-axial data from multiple sensors into a single classifier. It also utilizes Euler representation of device attitude (also based on fused data) to aid in classification. All processing is done completely on the smartphone.

View-Independent Action Recognition from Temporal Self-Similarities

Abstract: This paper addresses recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such measures across views. Building upon this key observation, we develop an action descriptor that captures the structure of temporal similarities and dissimilarities within an action sequence. Despite this temporal self-similarity descriptor not being strictly view-invariant, we provide intuition and experimental validation demonstrating its high stability under view changes. Self-similarity descriptors are also shown to be stable under performance variations within a class of actions when individual speed fluctuations are ignored. If required, such fluctuations between two different instances of the same action class can be explicitly recovered with dynamic time warping, as will be demonstrated, to achieve cross-view action synchronization. More central to the current work, temporal ordering of local self-similarity descriptors can simply be ignored within a bag-of-features type of approach. Sufficient action discrimination is still retained in this way to build a view-independent action recognition system. Interestingly, self-similarities computed from different image features possess similar properties and can be used in a complementary fashion. Our method is simple and requires neither structure recovery nor multiview correspondence estimation. Instead, it relies on weak geometric properties and combines them with machine learning for efficient cross-view action recognition. The method is validated on three public data sets. It has similar or superior performance compared to related methods and it performs well even in extreme conditions, such as when recognizing actions from top views while using side views only for training.

Fast Global Alignment Kernels

Abstract: We propose novel approaches to cast the widely-used family of Dynamic Time Warping (DTW) distances and similarities as positive definite kernels for time series. To this effect, we provide new theoretical insights on the family of Global Alignment kernels introduced by Cuturi et al. (2007) and propose alternative kernels which are both positive definite and faster to compute. We provide experimental evidence that these alternatives are both faster and more efficient in classification tasks than other kernels based on the DTW formalism.

Efficient spoken term discovery using randomized algorithms

Abstract: Spoken term discovery is the task of automatically identifying words and phrases in speech data by searching for long repeated acoustic patterns. Initial solutions relied on exhaustive dynamic time warping-based searches across the entire similarity matrix, a method whose scalability is ultimately limited by the O(n2) nature of the search space. Recent strategies have attempted to improve search efficiency by using either unsupervised or mismatched-language acoustic models to reduce the complexity of the feature representation. Taking a completely different approach, this paper investigates the use of randomized algorithms that operate directly on the raw acoustic features to produce sparse approximate similarity matrices in O(n) space and O(n log n) time. We demonstrate these techniques facilitate spoken term discovery performance capable of outperforming a model-based strategy in the zero resource setting.

Human action recognition using Dynamic Time Warping

Abstract: Human action recognition is gaining interest from many computer vision researchers because of its wide variety of potential applications. For instance: surveillance, advanced human computer interaction, content-based video retrieval, or athletic performance analysis. In this research, we focus to recognize some human actions such as waving, punching, clapping, etc. We choose exemplar-based sequential single-layered approach using Dynamic Time Warping (DTW) because of its robustness against variation in speed or style in performing action. For improving recognition rate, we perform body part tracking using depth camera to recover human joints body part information in 3D real world coordinate system. We build our feature vector from joint orientation along time series that invariant to human body size. Dynamic Time Warping is then applied to the resulted feature vector. We examine our approach to recognize several actions and we confirm our method can work well with several experiments. Further experiment for benchmarking the result will be held in near future.

Featureweighting in dynamic timewarping for gesture recognition in depth data

Abstract: We present a gesture recognition approach for depth video data based on a novel Feature Weighting approach within the Dynamic Time Warping framework. Depth features from human joints are compared through video sequences using Dynamic Time Warping, and weights are assigned to features based on inter-intra class gesture variability. Feature Weighting in Dynamic Time Warping is then applied for recognizing begin-end of gestures in data sequences. The obtained results recognizing several gestures in depth data show high performance compared with classical Dynamic Time Warping approach.

Methods and systems for indoor navigation

Abstract: Methods and systems for indoor navigation utilize a smartphone equipped with various sensors. When a person whose initial position is unknown, and in some circumstances whose sight has been impaired, specifies a destination, the navigation system will calculate the coordinates of his/her present location from the sensor readings. It will then calculate the distance to be traveled to the destination and form routes to direct him/her towards the desired location. These steps are carried out using sensor readings and in some cases magnetic maps of the interiors of buildings stored on the smartphone. In some cases dynamic time warping (“DTW”) is used to align a recorded signature of the person's movement through the building with a stored magnetic map in order to identify the person's location within the building.

Improving differential power analysis by elastic alignment

Abstract: To prevent smart card attacks using Differential Power Analysis (DPA), manufacturers commonly implement DPA countermeasures that create misalignment in power trace sets and decrease the effectiveness of DPA. We design and investigate the elastic alignment algorithm for non-linearly warping trace sets in order to align them. Elastic alignment uses FastDTW, originally a method for aligning speech utterances in speech recognition systems, to obtain so-called warp paths that can be used to perform alignment. We show on traces obtained from a smart card with random process interrupts that misalignment is reduced significantly, and that even under an unstable clock the algorithm is able to perform alignment.

A Novel Accelerometer-Based Gesture Recognition System

Abstract: In this paper, we address the problem of gesture recognition using the theory of random projection (RP) and by formulating the whole recognition problem as an l1-minimization problem. The gesture recognition system operates primarily on data from a single 3-axis accelerometer and comprises two main stages: a training stage and a testing stage. For training, the system employs dynamic time warping as well as affinity propagation to create exemplars for each gesture while for testing, the system projects all candidate traces and also the unknown trace onto the same lower dimensional subspace for recognition. A dictionary of 18 gestures is defined and a database of over 3700 traces is created from seven subjects on which the system is tested and evaluated. To the best of our knowledge, our dictionary of gestures is the largest in published studies related to acceleration-based gesture recognition. The system achieves almost perfect user-dependent recognition, and mixed-user and user-independent recognition accuracies that are highly competitive with systems based on statistical methods and with the other accelerometer-based gesture recognition systems available in the literature.

Preventing replay attacks on speaker verification systems

Abstract: In this paper, we describe a system for detecting spoofing attacks on speaker verification systems. We understand as spoofing the fact of impersonating a legitimate user. We focus on detecting two types of low technology spoofs. On the one side, we try to expose if the test segment is a far-field microphone recording of the victim that has been replayed on a telephone handset using a loudspeaker. On the other side, we want to determine if the recording has been created by cutting and pasting short recordings to forge the sentence requested by a text dependent system. This kind of attacks is of critical importance for security applications like access to bank accounts. To detect the first type of spoof we extract several acoustic features from the speech signal. Spoofs and non-spoof segments are classified using a support vector machine (SVM). The cut and paste is detected comparing the pitch and MFCC contours of the enrollment and test segments using dynamic time warping (DTW). We performed experiments using two databases created for this purpose. They include signals from land line and GSM telephone channels of 20 different speakers. We present results of the performance separately for each spoofing detection system and the fusion of both. We have achieved error rates under 10% for all the conditions evaluated. We show the degradation on the speaker verification performance in the presence of this kind of attack and how to use the spoofing detection to mitigate that degradation.

Comparing gesture recognition accuracy using color and depth information

Abstract: In human-computer interaction applications, gesture recognition has the potential to provide a natural way of communication between humans and machines. The technology is becoming mature enough to be widely available to the public and real-world computer vision applications start to emerge. A typical example of this trend is the gaming industry and the launch of Microsoft's new camera: the Kinect. Other domains, where gesture recognition is needed, include but are not limited to: sign language recognition, virtual reality environments and smart homes. A key challenge for such real-world applications is that they need to operate in complex scenes with cluttered backgrounds, various moving objects and possibly challenging illumination conditions. In this paper we propose a method that accommodates such challenging conditions by detecting the hands using scene depth information from the Kinect. On top of our detector we employ a dynamic programming method for recognizing gestures, namely Dynamic Time Warping (DTW). Our method is translation and scale invariant which is a desirable property for many HCI systems. We have tested the performance of our approach on a digits recognition system. All experimental datasets include hand signed digits gestures but our framework can be generalized to recognize a wider range of gestures.

Rapid Evaluation of Speech Representations for Spoken Term Discovery.

Abstract: Acoustic front-ends are typically developed for supervised learning tasks and are thus optimized to minimize word error rate, phone error rate, etc. However, in recent efforts to develop zero-resource speech technologies, the goal is not to use transcribed speech to train systems but instead to discover the acoustic structure of the spoken language automatically. For this new setting, we require a framework for evaluating the quality of speech representations without coupling to a particular recognition architecture. Motivated by the spoken term discovery task, we present a dynamic time warping-based framework for quantifying how well a representation can associate words of the same type spoken by different speakers. We benchmark the quality of a wide range of speech representations using multiple frame-level distance metrics and demonstrate that our performance metrics can also accurately predict phone recognition accuracies.

Shape, texture and local movement hand gesture features for Indian Sign Language recognition

Abstract: This paper proposes an automatic gesture recognition approach for Indian Sign Language (ISL). Indian sign language uses both hands to represent each alphabet. We propose an approach which addresses local-global ambiguity identification, inter-class variability enhancement for each hand gesture. Hand region is segmented and detected by YCbCr skin color model reference. The shape, texture and finger features of each hand are extracted using Principle Curvature Based Region (PCBR) detector, Wavelet Packet Decomposition (WPD-2) and complexity defects algorithms respectively for hand posture recognition process. To classify each hand posture, multi class non linear support vector machines (SVM) is used, for which a recognition rate of 91.3% is achieved. Dynamic gestures are classified using Dynamic Time Warping (DTW) with the trajectory feature vector with 86.3% recognition rate. The performance of the proposed approach is analyzed with well known classifiers like SVM, KNN & DTW. Experimental results are compared with the conventional and existing algorithms to prove the better efficiency of the proposed approach.

Embedding-based subsequence matching in time-series databases

Abstract: We propose an embedding-based framework for subsequence matching in time-series databases that improves the efficiency of processing subsequence matching queries under the Dynamic Time Warping (DTW) distance measure. This framework partially reduces subsequence matching to vector matching, using an embedding that maps each query sequence to a vector and each database time series into a sequence of vectors. The database embedding is computed offline, as a preprocessing step. At runtime, given a query object, an embedding of that object is computed online. Relatively few areas of interest are efficiently identified in the database sequences by comparing the embedding of the query with the database vectors. Those areas of interest are then fully explored using the exact DTW-based subsequence matching algorithm. We apply the proposed framework to define two specific methods. The first method focuses on time-series subsequence matching under unconstrained Dynamic Time Warping. The second method targets subsequence matching under constrained Dynamic Time Warping (cDTW), where warping paths are not allowed to stray too much off the diagonal. In our experiments, good trade-offs between retrieval accuracy and retrieval efficiency are obtained for both methods, and the results are competitive with respect to current state-of-the-art methods.

Recognition Of Multivariate Temporal Musical Gestures Using N-Dimensional Dynamic Time Warping.

Abstract: This paper presents a novel algorithm that has been specifically designed for the recognition of multivariate temporal musical gestures. The algorithm is based on Dynamic Time Warping and has been extended to classify any Ndimensional signal, automatically compute a classication threshold to reject any data that is not a valid gesture and be quickly trained with a low number of training examples. The algorithm is evaluated using a database of 10 temporal gestures performed by 10 participants achieving an average cross-validation result of 99%.

Classification of rigid and deformable objects using a novel tactile sensor

Abstract: In this paper, we present a novel tactile-array sensor for use in robotic grippers based on flexible piezoresistive rubber. We start by describing the physical principles of piezoresistive materials, and continue by outlining how to build a flexible tactile-sensor array using conductive thread electrodes. A real-time acquisition system scans the data from the array which is then further processed. We validate the properties of the sensor in an application that classifies a number of household objects while performing a palpation procedure with a robotic gripper. Based on the haptic feedback, we classify various rigid and deformable objects. We represent the array of tactile information as a time series of features and use this as the input for a k-nearest neighbors classifier. Dynamic time warping is used to calculate the distances between different time series. The results from our novel tactile sensor are compared to results obtained from an experimental setup using a Weiss Robotics tactile sensor with similar characteristics. We conclude by exemplifying how the results of the classification can be used in different robotic applications.

INSIGHT: efficient and effective instance selection for time-series classification

Abstract: Time-series classification is a widely examined data mining task with various scientific and industrial applications. Recent research in this domain has shown that the simple nearest-neighbor classifier using Dynamic Time Warping (DTW) as distance measure performs exceptionally well, in most cases outperforming more advanced classification algorithms. Instance selection is a commonly applied approach for improving efficiency of nearest-neighbor classifier with respect to classification time. This approach reduces the size of the training set by selecting the best representative instances and use only them during classification of new instances. In this paper, we introduce a novel instance selection method that exploits the hubness phenomenon in time-series data, which states that some few instances tend to be much more frequently nearest neighbors compared to the remaining instances. Based on hubness, we propose a framework for score-based instance selection, which is combined with a principled approach of selecting instances that optimize the coverage of training data. We discuss the theoretical considerations of casting the instance selection problem as a graph-coverage problem and analyze the resulting complexity. We experimentally compare the proposed method, denoted as INSIGHT, against FastAWARD, a state-of-the-art instance selection method for time series. Our results indicate substantial improvements in terms of classification accuracy and drastic reduction (orders of magnitude) in execution times.

Fault Diagnosis of Batch Chemical Processes Using a Dynamic Time Warping (DTW)-Based Artificial Immune System

Abstract: Fault diagnosis is important for ensuring chemical processes stability and safety. The strong nonlinearity and complexity of batch chemical processes make such diagnosis more difficult than that for continuous processes. In this paper, a new fault diagnosis methodology is proposed for batch chemical processes, based on an artificial immune system (AIS) and dynamic time warping (DTW) algorithm. The system generates diverse antibodies using known normal and fault samples and calculates the difference between the test data and the antibodies by the DTW algorithm. If the difference for an antibody is lower than a threshold, then the test data are deemed to be of the same type of this antibody’s fault. Its application to a simulated penicillin fermentation process demonstrates that the proposed AIS can meet the requirements for online dynamic fault diagnosis of batch processes and can diagnose new faults through self-learning. Compared with dynamic locus analysis and artificial neural networks, the proposed me...

A unified approach to real time audio-to-score and audio-to-audio alignment using sequential Montecarlo inference techniques

Abstract: We present a methodology for the real time alignment of music signals using sequential Montecarlo inference techniques. The alignment problem is formulated as the state tracking of a dynamical system, and differs from traditional Hidden Markov Model - Dynamic Time Warping based systems in that the hidden state is continuous rather than discrete. The major contribution of this paper is addressing both problems of audio-to-score and audio-to-audio alignment within the same framework in a real time setting. Performances of the proposed methodology on both problems are then evaluated and discussed.

An inner-product lower-bound estimate for dynamic time warping

Abstract: In this paper, we present a lower-bound estimate for dynamic time warping (DTW) on time series consisting of multi-dimensional posterior probability vectors known as posteriorgrams. We develop a lower-bound estimate based on the inner-product distance that has been found to be an effective metric for computing similarities between posteriorgrams. In addition to deriving the lower-bound estimate, we show how it can be efficiently used in an admissible K nearest neighbor (KNN) search for spotting matching sequences. We quantify the amount of computational savings achieved by performing a set of unsupervised spoken keyword spotting experiments using Gaussian mixture model posteriorgrams. In these experiments the proposed lower-bound estimate eliminates 89% of the DTW previously required calculations without affecting overall keyword detection performance.

Indoor localization through dynamic time warping

Abstract: Identifying and locating oneself in different hallways of high rise buildings forms the classic indoor localization problem. GPS does not work indoors and WiFi may not be omnipresent. This paper presents a novel approach to ambient magnetic fields based indoor localization. We present a system that classifies magnetic signatures using dynamic time warping. Specifically, by aligning similar magnetic signatures that differ in magnitude or time, we classify the signatures and infer the location irrepective of the person and his/her mode of commuting. A Nexus One smartphone was employed, utilizing its builtin magnetic field sensor to create a user friendly localization application solely on the phone. By using a variety of subjects including sighted, blindfolded and people using wheelchairs to handle the human speed variation problem, we evaluated the system across 26 and 15 hallways of two different buildings and obtained accuracies of 92.6%, and 91.1% respectively. With these encouraging results, we believe our proposed solution is user independent and caters to a wide range of hallways.

Cardiac arrhythmia detection using dynamic time warping of ECG beats in e-healthcare systems

Abstract: Automatic real-time detection and classification of ECG patterns is of great importance in early diagnosis and treatment of life-threatening cardiac arrhythmia. In this paper, we have presented dynamic time warping (DTW) distance based approach for classification of arrhythmic ECG beats, with an aim of using it in smart-phone/mobile environment. The performance of the proposed method is tested on ECG beats of various arrhythmia types selected from MIT-BIH arrhythmia database. We have compared the proposed DTW approach using naive Bayes classifier with relative band spectral power as feature. The DTW approach has shown superior performance compared to the naive Bayes classifier. Furthermore, we have verified the performance of the DTW approach on down-sampled ECG beats in order to improve speed of the DTW algorithm. It is observed that the performance of the DTW approach did not deteriorate even after subsampling of ECG beats. The DTW with subsampling has been aimed at real-time arrhythmia detection in wearable mobile healthcare systems in telemedicine scenario for continuous monitoring of ECG records from cardiac patients.