Combination Of Dynamic Time Warping Research Articles

Pattern-based and context-aware electricity theft detection in smart grid

The smart grid offers numerous potential benefits for energy management by two-way information transmission. However, the incorporation of smart infrastructure such as smart meters into the grid systems made it vulnerable to various communication attacks. The electricity consumption data coming from the smart meters can be acquired and analyzed to detect malicious behavior, tampering, and data manipulation. In this paper, a pattern-based and context-aware approach for electricity theft detection (PCETD) is proposed to mitigate the challenges of theft-based Non-Technical Losses (NTLs). The proposed approach considers the relevant calendar context and features of daily electricity demand for a given day to compute the probability of customers being malicious. In this process, a combination of dynamic time warping (DTW) and k-nearest neighbors (k-NN) is proposed, where DTW is utilized to capture the relationship between two consumption patterns correctly, and k-NN is employed to rank the anomalousness of the given day. This research introduces several forms of theft attacks and assesses the effectiveness of the proposed approach. The results exhibited the overall F1-score for the proposed approach to be 94%, the True-Positive Rate (TPR) as 93%, and the False-Positive Rate (FPR) as 1.1%, which substantiates the efficiency of the model in detecting electricity theft. These findings further advocate that the approach outperforms the prior contributions in terms of high detection rate and low false-positive rate. Electric utilities can be provided with anomaly scores and plan on-site inspections to catch fraudulent customers. • An electricity theft detection algorithm for residential customers is developed. • The algorithm uses consumption patterns along with relevant calendar context. • The inclusion of calendar context is vital for efficiently fraudulent customers. • The algorithm performs better with FPR of 1.1% as compared to the previous works. • Electric utilities can use the results of algorithm to plan on-site inspections.

A WaveNet-based fully stochastic dynamic stall model

Abstract. Accurate modeling of the dynamic stall remains a challenge for the design and construction of turbine blades and helicopter rotors. At the same time, wind turbines, for instance, are becoming steadily larger, further increasing the demands on their structure and necessitating even more detailed modeling of the forces at hand. The primarily used (semi-)empirical models today have a long research history and are invariably based on phase-averaged data from oscillating blade pitch experiments. However, much potential for more accurate modeling of uncertainties and force peaks is wasted here, since averaging blurs many features of the response signals. Even computational fluid dynamics can help little in this regard, since the Reynolds-averaged Navier–Stokes equations used in practice cannot account for cycle variations, and scale-resolving models require extremely large amounts of computational resources. This paper presents an approach for a fully stochastic machine learning model that can nevertheless simulate these critical properties. Aerodynamic coefficients are compared with experimental data for different test cases. It is shown that synthetic force profiles which cannot be distinguished from the experimental data visually and are very close to them in the frequency spectrum can be generated. Additionally, attention is drawn to the difficulty of evaluating such a model, as traditional error metrics are of little use. A combination of dynamic time warping and the Earth mover's distance provides a robust solution for this problem.

Faulty Section Location Method Based on Dynamic Time Warping Distance in a Resonant Grounding System

When a single-phase grounding fault occurs in a resonant grounding system, the determination of the fault location remains a significant challenge due to the small fault current and the instability of the grounding arc. In order to solve the problem of low protection sensitivity when a high-resistance grounding fault occurs in a resonant grounding system, this paper proposes a fault location method based on the combination of dynamic time warping (DTW) distance and fuzzy C-means (FCM) clustering. By analyzing the characteristics of the zero-sequence current upstream and downstream of the fault point when a single-phase grounding fault occurs in the resonant grounding system, it is concluded that the waveform similarity on both sides of the fault point is low. DTW distance can be used to measure the similarity of two time series, and has the characteristics of good fault tolerance and synchronization error tolerance. According to the rule that the DTW value of faulty section is much larger than that of nonfaulty sections, FCM clustering is used to classify the DTW value of each section. The membership degree matrix and cluster centers are obtained. In the membership degree matrix, the section corresponding to the data in a class of their own is the faulty section, and all other data correspond to the nonfaulty section; otherwise, it is a fault occurring at the end of the line. The simulation results of MATLAB/Simulink and the field data test show that the method can accurately locate the faulty section.

Faulty Line Selection Method Based on Comprehensive Dynamic Time Warping Distance in a Flexible Grounding System

A flexible grounding system is a system in which the neutral point of the power supply is grounded via the arc suppression coil in parallel with a low-resistance resistor. When operating normally or a temporary ground fault occurs, the arc suppression coil is used for grounding, whereas the small resistance is switched on when a permanent ground fault occurs. At present, the problem of low protection sensitivity when a high-resistance ground fault occurs in a flexible grounding system has not been solved yet. According to the characteristics of low waveform similarity between the faulty line and the non-faulty line when a single-phase grounding fault occurred, a new faulty line selection method based on a combination of Dynamic Time Warping (DTW) distance and the transient projection method is proposed in this paper. Firstly, the fault transient signal is extracted by a digital filter as a basis for faulty line selection. Secondly, the transient zero-sequence current of each line is projected onto the busbar transient zero-sequence voltage, and the projected DTW distance of each line is calculated. Finally, according to the calculation formula of waveform comprehensive similarity coefficient, the Comprehensive DTW (CDTW) distance is obtained, and the top three CDTW distance values are selected to determine the faulty line. If the maximum value is greater than the sum of the other two CDTW distance values, the line corresponding to the maximum value is judged as the faulty line; otherwise, it is judged as a busbar fault. The simulation results based on MATLAB/Simulink and field data test show that the method can accurately determine the faulty line under diverse fault conditions.

Temporal and kinematic patterns distinguishing the G2 from the G4 skating sub-technique

ABSTRACT In cross-country ski skating, both the G2 and G4 sub-techniques involve one pole push for every second ski push but are used at largely different speed-slope ranges. The aim of this study was to compare temporal and kinematic patterns between G2 and G4 at both identical and different speed-slope conditions. A mixed model was used to analyse spatio-temporal parameters, while a combination of dynamic time warping and statistical parametric mapping was used to compare time traces. Main spatio-temporal parameters, such as cycle time, ski contact time and swing time, differed between G2 and G4 (all p < 0.01). Moreover, two forward and more pronounced acceleration phases of the centre of mass (CoM) were visible in G4 while only one acceleration phase was present in G2. The more continuous propulsion in G2 allows for maintaining a more constant speed at steep slopes and low speeds where this sub-technique is preferred. In contrast, the achievement of high speeds while skiing on flatter terrain seem to require more dynamic motion with shorter, more explosive propulsion periods allowed for in G4. In conclusion, G2 and G4 are two unique movements as characterised by fundamentally different CoM motion and should be denoted as two different sub-techniques.

Representing Time Series Data in Intelligent Training Systems

Many of the most popular intelligent training systems, including driving and flight simulators, generate user time series data. This paper presents a comparison of representation options for two different student modeling problems: 1) early failure prediction and 2) classifying student activities. Data for this analysis was gathered from pilots executing simple tasks in a virtual reality flight simulator. We demonstrate that our proposed embedding which uses a combination of dynamic time warping (DTW) and multidimensional scaling (MDS) is valuable for both student modeling tasks. However, Euclidean distance + MDS was found to be a superior embedding for predicting student failure, since DTW can obscure important agility differences between successful and unsuccessful pilots.

A flight maneuver recognition method based on multi-strategy affine canonical time warping

Maneuver recognition for unmanned combat air vehicle (UCAV) is a necessary technique for autonomous air combat. As a spatiotemporal alignment problem of multidimensional time series, the flight maneuver recognition is solved by a novel alignment measure, multi-strategy affine canonical time warping approach (MACTW) and its derivative form, which are extensions of affine canonical time warping (ACTW). MACTW makes several contributions: (1) it proposes multi-strategy success-history based adaptive differential evolution algorithm with linear population size reduction (MLSHADE) to accelerate the search of warping path of dynamic time warping (DTW); (2) it introduces affine strategy to address offset and scaling of canonical time warping (CTW), which is a combination of DTW and canonical correlation analysis (CCA); and (3) it extends ACTW based on MLSHADE to align multidimensional time series In addition, MLSHADE is a novel optimization technique that employs weighted mutation, inferior solution search, and eigen Gaussian walk strategies to improve the optimization efficiency. The experimental results on the CEC 2018 test suite illustrate the superior benefits of MLSHADE. UCAV flight maneuver recognition system which includes segmentation, preprocessing and recognition modules is modeled. The experimental results on UCR datasets and UCAV maneuver datasets including action units and long maneuver datasets illustrate the superiority of MACTW and its derivative form compared with other state-of-the-art alignment measures.

Mortality prediction for ICU patients with individualized single classification method

In intensive care units (ICUs), mortality prediction is crucial to help doctors select appropriate diagnosis and treatment methods and reasonably allocate medical resources. However, the scoring system currently used by hospitals may not be suitable for every patient. Therefore, personalized diagnosis is trending because it responds to a wide range of needs. This study proposes a new combination of dynamic time warping (DTW) and one-class extreme learning machine (ELM) to improve the mortality prediction accuracy, termed as one-class DTW-ELM, where DTW is used to find similar cases for new patients, and while one-class ELM is adopted for fast and accurate model building. The testing results on the real physiological data from PhysioNet demonstrate that the area under curve (AUC) index of one-class DTW-ELM model is 0.9739, with the Lift of 8.1081 and the G-mean of 0.8137. The accuracy rate is 0.9583, with specificity and sensitivity of 1 and 0.6622, respectively. As mentioned, one-class DTW-ELM can accurately predict the future physiological state of a patient by using early physiological parameters.

Enhanced dynamic programming approach for subunit modelling to handle segmentation and recognition ambiguities in sign language

Sign language serves as a primary means of communication among the deaf impaired community. The major challenges faced by the Sign Language Recognition (SLR) system are recognizing signs from large vocabularies in continuous video sequences. In this research paper, a novel subunit sign modelling framework is proposed for vision-based SLR which aims in solving the major issues in SLR systems. The problem of hand segmentation ambiguities and segregating epentheses movements between two adjacent signs in continuous video sequences are addressed. A novel subunit sign modelling framework is presented and illustrated to embark upon these problems while considering large-vocabularies. This framework is developed using a novel methodology of Enhanced Dynamic Programming (EDP) approach in subunit sign modelling. This EDP framework works with a combination of dynamic time warping and spatiotemporal clustering techniques. Since, sign language consists of both spatial and temporal feature vectors, dynamic time warping is used as a distance measure to compute the distance between two adjacent signs in sign trajectories. This distance is used as a temporal feature vector during the clustering of spatial feature vectors using Minimum Entropy Clustering (MEC). This process is done recursively to cluster all the epentheses movements dynamically without using any explicit or implicit modelling. Experimental results have confirmed that the computation cost of the proposed system is less because the epenthesis movements are eliminated before classification and the gesture base space utilized by the sign gestures is very low because the proposed system does not require any modelling to handle epenthesis movements. The results obtained from the proposed subunit sign modelling framework is compared with other existing models in order to prove that the proposed system is best among the existing systems.

Classification of time series using combination of DTW and LCSS dissimilarity measures

ABSTRACTIn the domain of time series, different dissimilarity measures are applied for comparing sequences, the most successful ones being based on dynamic programming. Such measures include Longest Common SubSequence () and Dynamic Time Warping (DTW). In this article, a novel method is proposed to measure the dissimilarity of time series. We propose a parametric combination of and derivative DTW. The new dissimilarity measure is used in classification with the 1NN rule. We empirically compare our new approach to and DTW used separately and demonstrate its superiority in classification accuracy. In addition, our method is statistically comparable with method proposed by Lines and Bagnall considered so far the most accurate method of time series classification.

Statistical engineering approach to improve the realism of computer-simulated experiments with aircraft trajectory clustering

ABSTRACTThis article presents a statistical engineering approach for clustering aircraft trajectories. The clustering methodology was developed to address the need to incorporate more realistic trajectories in fast-time computer simulations used to evaluate an aircraft spacing algorithm. The methodology is a combination of Dynamic Time Warping and k-Means clustering, and can be viewed as one of many possible solutions to the immediate problem. The implementation of this statistical engineering approach is also repeatable, scalable, and extendable to the investigation of other air traffic management technologies. Development of the clustering methodology is presented in addition to an application and description of results.

R3DG features: Relative 3D geometry-based skeletal representations for human action recognition

Recently introduced cost-effective depth sensors coupled with real-time skeleton extraction algorithms have generated a renewed interest in skeleton-based human action recognition. Most of the existing skeleton-based approaches use either the joint locations or the joint angles to represent the human skeleton. In this paper, we introduce and evaluate a new family of skeletal representations for human action recognition, which we refer to as R3DG features. The proposed representations explicitly model the 3D geometric relationships between various body parts using rigid body transformations, i.e., rotations and translations in 3D space. Using the proposed skeletal representations, human actions are modeled as curves in R3DG feature spaces. Finally, we perform action recognition by classifying these curves using a combination of dynamic time warping, Fourier temporal pyramid representation and support vector machines. Experimental results on five benchmark action datasets show that the proposed representations perform better than many existing skeletal representations. The proposed approach also outperforms various state-of-the-art skeleton-based human action recognition approaches.

Human activity prediction by mapping grouplets to recurrent Self-Organizing Map

Human activity prediction is defined as inferring the high-level activity category with the observation of only a few action units. It is very meaningful for time-critical applications such as emergency surveillance. For efficient prediction, we represent the ongoing human activity by using body part movements and taking full advantage of inherent sequentiality, then find the best matching activity template by a proper aligning measurement.In streaming videos, dense spatio-temporal interest points (STIPs) are first extracted as low-level descriptors for their high detection efficiency. Then, sparse grouplets, i.e., clustered point groups, are located to represent body part movements, for which we propose a scale-adaptive mean shift method that can determine grouplet number and scale for each frame adaptively. To learn the sequentiality, located grouplets are successively mapped to Recurrent Self-Organizing Map (RSOM), which has been pre-trained to preserve the temporal topology of grouplet sequences. During this mapping, a growing RSOM trajectory, which represents the ongoing activity, is obtained. For the special structure of RSOM trajectory, a combination of dynamic time warping (DTW) distance and edit distance, called DTW-E distance, is designed for similarity measurement. Four activity datasets with different characteristics such as complex scenes and inter-class ambiguities serve for performance evaluation. Experimental results confirm that our method is very efficient for predicting human activity and yields better performance than state-of-the-art works.

Localization and Recognition of Digit-Writing Hand Gestures for Smart TV Systems

A novel framework is put forward in this paper for localization and recognition of digit-writing hand gestures, which forms the basis of a vision-based interactive interface that we will develop later for smart television systems. The framework uses as input a video stream capturing the hand gesture of writing a digit dynamically by the user, and outputs the digit inferred from the gesture. A fast and robust tracker is used to flnd the gesture trajectory, and prior constraints and a motion predictor are applied to improve the tracker’s performance. The trajectory is then turned into the flnal output by a recognizer, which is formed by the combination of dynamic time warping and the convolutional neural network. The efiectiveness of the proposed framework is validated by experiments.

Combining Dynamic Time Warping and Single Hidden Layer Feedforward Neural Networks for Temporal Sign Language Recognition

Temporal Sign Language Recognition (TSLR) from hand motion is an active area of gesture recognition research in facilitating efficient communication with deaf people. TSLR systems consist of two stages: a motion sensing step which extracts useful features from signers’ motion and a classification process which classifies these features as a performed sign. This work focuses on two of the research problems, namely unknown time varying signal of sign languages in feature extraction stage and computing complexity and time consumption in classification stage due to a very large sign sequences database. In this paper, we propose a combination of Dynamic Time Warping (DTW) and application of the Single hidden Layer Feedforward Neural networks (SLFNs) trained by Extreme Learning Machine (ELM) to cope the limitations. DTW has several advantages over other approaches in that it can align the length of the time series data to a same prior size, while ELM is a useful technique for classifying these warped features. Our experiment demonstrates the efficiency of the proposed method with the recognition accuracy up to 98.67%. The proposed approach can be generalized to more detailed measurements so as to recognize hand gestures, body motion and facial expression.

Combination of dynamic time warping and multivariate analysis for the comparison of comprehensive two-dimensional gas chromatograms: Application to plant extracts

Comprehensive two-dimensional gas chromatography (GC × GC) is now recognized as the preferred technique for the detailed analysis and characterization of complex mixtures of volatile compounds. However, for comparison purposes, taking into account all the information contained in the chromatogram is far from trivial. In this paper, it is shown that the combination of peak alignment by dynamic time warping and multivariate analysis facilitated the comparison of complex chromatograms of tobacco extracts. The comparison is shown to be efficient enough to provide a clear discrimination among three types of tobacco. A tentative interpretation of loadings is presented in order to give access to the compounds which differ from one sample to another. Once located, mass spectrometry was used to identify markers of tobacco type.

Synchronization of batch trajectories using dynamic time warping

AbstractThe application of dynamic time warping (DTW) to the analysis and monitoring of batch processes is presented. This dynamic‐programming‐based technique has been used in the area of speech recognition for the recognition of isolated and connected words. DTW has the ability to synchronize two trajectories by appropriately translating, expanding, and contracting localized segments within both trajectories to achieve a minimum distance between the trajectories. Batch processes often are characterized by unsynchronized trajectories, due to the presence of batch‐to‐batch disturbances and the existence of physical constraints. To compare these batch histories and apply statistical analysis one needs to reconcile the timing differences among these trajectories. This can be achieved using DTW with only a minimal amount of process knowledge. The combination of DTW and a monitoring method based on Multiway PCA/PLS is used for both off‐line and on‐line implementation. Data fiom an industrial polymerization reactor are used to illustrate the implementation and the performance of this method.