Dynamic Time Warping Method Research Articles

A New Similarity Measure for Time Series Data Mining Based on Longest Common Subsequence

In this research, a new similarity measurement method that named Developed Longest Common Subsequence (DLCSS) is suggested for time series data mining. The main idea of the DLCSS is using the logic of the Longest Common Subsequence (LCSS) method and the concept of similarity in time series data. In most studies related to time series data mining, referred to the LCSS and Dynamic Time Warping (DTW) methods as the best and most usable for similarity measurement methods, but the LCSS is intrinsically designed to measure the similarity of two sequences of character, which later was developed for time series by defining and determining the similarity threshold. The value of similarity threshold has huge impact on the quality of time series data mining. In the DLCSS by defining two similarity thresholds and determining the values of them, this defect is eliminated. The performance of the DLCSS will be compared with the LCSS and DTW in time series data mining by the Query by content and K-medoids Clustering techniques on 23 datasets from the UCR datasets. The result shows that it is possible to claim that the performance of the DLCSS is better than the LCSS and DTW with 90% confidence.

Physiological Function Assessment Based on Kinect V2

This paper presented a framework based on fog computing for convenient and efficient Physiological Function Assessment, which consists of three parts: 1)measuring the degree of joint mobility; 2) investigating the abnormality of actions of upper limbs; and 3) abnormal gait detection for lower limbs. Especially, we introduced semi-automatic Rapid Upper Limb Assessment (RULA) using Kinect v2 for the upper limb motion evaluation. Since a specific action can be described by action sequences of different length, we used dynamic time warping (DTW) to find the similarity between action sequences with different length. Traditional DTW algorithm does not work well when the action sequences are long and complex. To address this problem, we improved the DTW method by modifying the mapping relationship and limiting the computation space. Our modified DTW algorithm was evaluated on a standard 3D action dataset (SYSU 3D HOI) and Human Upper Action dataset (HUA), achieving the accuracy of 83.75%, 89.50%, respectively. The result is significantly better than the traditional DTW and the reported methods. In our previous work, we described the framework and how to make physiological function assessment. The goal of this paper is to 1) enrich the experiments of previous work and 2) introduce the framework of using RULA for physiological function assessment. All the tests have been done in this framework based on fog computing.

A Method for RNA Structure Prediction Shows Evidence for Structure in lncRNAs.

To compare the secondary structure profiles of RNA molecules we developed the CROSSalign method. CROSSalign is based on the combination of the Computational Recognition Of Secondary Structure (CROSS) algorithm to predict the RNA secondary structure profile at single-nucleotide resolution and the Dynamic Time Warping (DTW) method to align profiles of different lengths. We applied CROSSalign to investigate the structural conservation of long non-coding RNAs such as XIST and HOTAIR as well as ssRNA viruses including HIV. CROSSalign performs pair-wise comparisons and is able to find homologs between thousands of matches identifying the exact regions of similarity between profiles of different lengths. In a pool of sequences with the same secondary structure CROSSalign accurately recognizes repeat A of XIST and domain D2 of HOTAIR and outperforms other methods based on covariance modeling. The algorithm is freely available at the webpage http://service.tartaglialab.com//new_submission/crossalign.

Dynamic Outlier Detection in the Calibration by Comparison Method Applied to Strain Gauge Weight Sensors.

The present work proposes a robust method of analyzing sets of data series shifted in time in respect to each other utilizing the process of dynamic calibration by comparison. Usually the Pearson’s correlation analysis coefficient is applied for this purpose. However, in some cases the method does not bring satisfactory results, as it can be seen in the results of the research conducted for the purpose of this paper. The Dynamic Time Warping method may be the solution to this problem, as it appears to be more efficient while comparing the shapes of calibration characteristics done with the use of the Pearson’s method. The presented method may also be applied to eliminate dynamic outliers collected in the process of recurrence examination or the analysis of strain gauge weight sensors hysteresis. This fact also makes the method a good tool for eliminating improper data series which might appear in the calibration process due to, e.g., malfunctioning devices installed in the calibration stand. The article presents an example of using the proposed method in eliminating improper dynamic characteristics obtained in a simulated calibration stand. Moreover, a comparative analysis performed on the simulation data is also presented in the article, as well as the result of the laboratory experiment.

Hybrydowa diagnostyka uszkodzeń zwrotnic kolejowych w oparciu o segmentację krzywych prądowych

Switches are one of the most important pieces of infrastructure in railway signal systems, and they significantly influence the efficiency and safety of train operation. Currently, the identification of switch failures mainly depends on the experience of railway staff and the use of simple thresholding methods. However, these basic methods are highly inaccurate and frequently result in false and missing alarms. This paper aims to develop a hybrid fault diagnosis (HFD) method for railway switches. The method is an intelligent diagnosis method that uses massive current curves collected by microcomputer monitoring systems. We first divide the switch operation current curves into three segments based on the three mechanical processes that occur during switch operation. Then, a standard curve is selected from the fault-free curves, and common typical faults are ascertained through a microcomputer monitoring system. Finally, derivative dynamic time warping and a quartile scheme are employed to identify fault curves. An experiment based on current curves collected from the Guangzhou Railway Bureau in China demonstrates that the HFD method is extremely accurate and has low false and missing alarm rates. HFD performs better than the studied support vector machine (SVM) and dynamic time warping (DTW) methods, which are widely used for fault diagnosis.

QP-DTW: Upgrading Dynamic Time Warping to Handle Quasi Periodic Time Series Alignment

Dynamic time warping (DTW) is the main algorithms for time series alignment. However, it is unsuitable for quasi-periodic time series. In the current situation, except the recently published the shape exchange algorithm (SEA) method and its derivatives, no other technique is able to handle alignment of this type of very complex time series. In this work, we propose a novel algorithm that combines the advantages of the SEA and the DTW methods. Our main contribution consists in the elevation of the DTW power of alignment from the lowest level (Class A, non-periodic time series) to the highest level (Class C, multiple-periods time series containing different number of periods each), according to the recent classification of time series alignment methods proposed by Boucheham (Int J Mach Learn Cybern, vol. 4, no. 5, pp. 537-550, 2013). The new method (quasi-periodic dynamic time warping [QP-DTW]) was compared to both SEA and DTW methods on electrocardiogram (ECG) time series, selected from the Massachusetts Institute of Technology - Beth Israel Hospital (MIT-BIH) public database and from the PTB Diagnostic ECG Database. Results show that the proposed algorithm is more effective than DTW and SEA in terms of alignment accuracy on both qualitative and quantitative levels. Therefore, QP-DTW would potentially be more suitable for many applications related to time series (e.g., data mining, pattern recognition, search/retrieval, motif discovery, classification, etc.).

Which Phonetic Features Should Pronunciation Instructions Focus on? An Evaluation on the Accentedness of Segmental/Syllable Errors in L2 Speech

Many English language instructors are reluctant to incorporate pronunciation instruction into their teaching curriculum (Thomson 2014). One reason for such reluctance is that L2 pronunciation errors are numerous, and there is not enough time for teachers to address all of them (Munro and Derwing 2006; Thomson 2014). The current study aims to help language teachers set priorities for their instruction by identifying the segmental and structural aspects of pronunciation that are most foreign-accented to native speakers of American English. The current study employed a perception experiment. 100 speech samples selected from the Speech Accent Archive (Weinberger 2016) were presented to 110 native American English listeners who listened to and rated the foreign accentedness of each sample on a 9-point rating scale. 20 of these samples portray no segmental or syllable structure L2 errors. The other 80 samples contain a single consonant, vowel, or syllable structure L2 error. The backgrounds of the speakers of these samples came from 52 different native languages. Global prosody of each sample was controlled for by comparing its F0 contour and duration to a native English sample using the Dynamic Time Warping method (Giorgino 2009). The results show that 1) L2 consonant errors in general are judged to be more accented than vowel or syllable structure errors; 2) phonological environment affects accent perception, 3) occurrences of non-English consonants always lead to higher accentedness ratings; 4) among L2 syllable errors, vowel epenthesis is judged to be as accented as consonant substitutions, while deletion is judged to be less accented or not accented at all. The current study, therefore, recommends that language instructors attend to consonant errors in L2 speech while taking into consideration their respective phonological environments.

Context-aware pattern discovery for moving object trajectories

Abstract. Movement of point objects are highly sensitive to the underlying situations and conditions during the movement, which are known as contexts. Analyzing movement patterns, while accounting the contextual information, helps to better understand how point objects behave in various contexts and how contexts affect their trajectories. One potential solution for discovering moving objects patterns is analyzing the similarities of their trajectories. This article, therefore, contextualizes the similarity measure of trajectories by not only their spatial footprints but also a notion of internal and external contexts. The dynamic time warping (DTW) method is employed to assess the multi-dimensional similarities of trajectories. Then, the results of similarity searches are utilized in discovering the relative movement patterns of the moving point objects. Several experiments are conducted on real datasets that were obtained from commercial airplanes and the weather information during the flights. The results yielded the robustness of DTW method in quantifying the commonalities of trajectories and discovering movement patterns with 80 % accuracy. Moreover, the results revealed the importance of exploiting contextual information because it can enhance and restrict movements.

An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping

This paper proposes an open-boundary locally weighted dynamic time warping (OLWDTW) method using MODIS Normalized Difference Vegetation Index (NDVI) time-series data for cropland recognition. The method solves the problem of flexible planting times for crops in Southeast Asia, which has sufficient thermal and water conditions. For NDVI time series starting at the beginning of the year and terminating at the end of the year, the method can separate the non-growing season cycle and growing season cycle for crops. The non-growing season cycle may provide some useful information for crop recognition, such as soil conditions. However, the shape of the growing season’s NDVI time series for crops is the key to separating cropland from other land cover types because the shape contains all of the crop growth information. The principle of the OLWDTW method is to enhance the effects of the growing season cycle on the NDVI time series by adding a local weight to the growing season when comparing the similarity of time series based on the open-boundary dynamic time warping (DTW) method. Experiments with two satellite datasets located near the Khorat Plateau in the Lower Mekong Basin validate that OLWDTW effectively improves the precision of cropland recognition compared to a non-weighted open-boundary DTW method in terms of overall accuracy. The method’s classification accuracy on cropland exceeds the non-weighted open-boundary DTW by 5–7%. In future studies, an open-boundary self-adaption locally weighted DTW and a more effective combination rule for different crop types should be explored for the method’s best performance and highest extraction accuracy for cropland.

Template-Matching-Based Detection of Freezing of Gait Using Wearable Sensors

Parkinson’s disease (PD) lead to lots of injuries associated with fall incidences every year, causing lots of human suffering and assets loss for patients. Freezing of Gait (FOG), which is one of the most common symptoms of PD, is quite responsible for most incidents. Although lots of research have been done on characterize analysis and detection methods of FOG, large room for improvement still exists in the high accuracy and high efficiency examination of FOG. In view of the above requirements, this paper presents a template-matching-based improved subsequence Dynamic Time Warping (IsDTW) method, and experimental tests were carried out on typical open source datasets. Results show that proposed IsDTW not only embodies higher experimental accuracy (92%), but also has a significant runtime efficiency.

Beta Iterative Synchronization: An Algorithm for Structural Signal Averaging

Many biomedical signals can be considered as the sets of repetitions due to the occurrence of a repetitive pattern of features. Those features, however, are characterized by some jitter, which often renders standard arithmetic averaging inadequate. Examples include electrocardiogram, ocular pulse or corneal pulse, series of evoked potentials in electro- and magnetoencephalography, among many others. We propose a new approach to structural averaging of such signals. We use the family of beta cumulative distribution functions as a set of candidates for time warping function in order to synchronize repetitions, and then apply a variant of the Procrustes method to find the average signal. For both synthetic and real data, we provide a comparison where we challenge the Dynamic Time Warping (DTW) method and present both theoretical and practical advantages of our algorithm. As an illustrative real-data example, we address corneal pulse waveforms with their dicrotic valleys as the feature of interest. The detection of the dicrotic valleys turned out more reproducible than in the case of DTW while maintaining similar classification performance and having fewer parameters. The proposed method for structural averaging provides effective estimation in the case of the analyzed signals. The method can readily be extended to other biomedical signals characterized by repetitive feature patterns.

Isolated Automatic Speech Recognition of Quechua Numbers using MFCC, DTW and KNN

The Automatic Speech (ASR) area is defined as the transformation of acoustic signals into string words. This area has been being developed for many year facilitating the lives of people so it was implemented in several languages. However, the development of ASR in some languages with few database resources but with a large population speaking these languages is very low. The development of ASR in Quechua language is almost null which leads culture and population isolation from technology and information. In this work an ASR system of isolated Quechua numbers is developed where Mel-Frequency Cepstral Coefficients (MFCC), Dynamic Time Warping (DTW) and K-Nearest Neighbor (KNN) methods are implemented using a database composed by recorded audio numbers from one to ten in Quechua. The recorded audios to feed the data base were uttered by natives man and women speakers of Quechua. The recognition accuracy reached in this research work was 91.1%.

On-line Maneuver Identification in Highway Traffic Using Elastic Template Matching

Early identification and interpretation of traffic maneuvers will become key elements of modern driver assistance systems. Currently, only simple traffic situations can be detected by using a decision tree (DT) procedure in most cases. Even though this approach is straightforward, it still requires an expert to build a different DT for every maneuver. Moreover, for complex driving behaviours such simple logic identification does not work. In the present work we develop a template (or pattern) matching (TM) algorithm for maneuver recognition in highway traffic with a particular focus on a cut-in maneuver. By using maneuver patterns we are able to consider scenarios of arbitrary complexity and make the identification procedure more systematic and with minimal man expert involvement. The key element of the proposed TM algorithm is the settlement of a distance measure. We use dynamic time warping (DTW) method for an optimal non-linear alignment between two sequences under certain restrictions. It enables a correct assignment of the same maneuver but having different dynamics (speed, aggressiveness, etc.), and is robust to data with missing values. We illustrate the proposed method by cut-in detection from real traffic data and compare it to the standard DT identification.

A Posteriori Processing Optimization Method for Gesture Interaction in Aseptic Operation Room

Gesture recognition plays an important role in the applications of human-centered smart technologies. This paper designs a gesture recognition approach in a special human-computer interaction environment. Generally, in an aseptic operation room, doctors cannot access the patient’s image data directly, and they have to let the nurse operate the system under their instructions. After the nurses finish their task, they also need to re-dress the surgical gown, disinfect their hands, then they can go back to the operating room. If the doctor could access the image directly by gestures during the operation, they would be able to save a lot of time and work more efficiently. Although some template matching algorithms, such as dynamic time warping (DTW), have been widely used in gesture recognition, those traditional methods are not accurate enough, and they are unable to identify continuous repetitive gestures. This paper proposes an improved DTW method based on posteriori processing, which achieved some key operations, including parameter regulations, invalid area determination, and static gesture processing. This method will address the problem of continuous repetitive gesture recognition, with higher accuracy. The experimental results show that the method can improve the accuracy of recognition by over 40%, and it can also perform real-time dynamic gesture recognition tasks effectively.

Encrypted network behaviors identification based on dynamic time warping and k-nearest neighbor

In order to solve the problem of encrypted traffic identification, the identification method based on dynamic time warping (DTW) and k-nearest neighbor (KNN) for the encrypted network behaviors was proposed. The method took the encrypted Twitter traffic as an example of research, and a large number of encrypted Twitter network behaviors were deeply analyzed, and then the features representing the encrypted network behaviors were extracted, and the specific encrypted network behavior module database based on DTW and KNN were established, and the DTW between the collection data set and the module database were calculated, and then were normalized, and then the encrypted network behaviors were classified by comparing with the preset empirical threshold, and the distance information were also considered by DTW algorithm, at the same time, the influence of TCP retransmission and duplicate ACK packets can be effectively eliminated by the dynamic time warping algorithm. In order to overcome the noise interference of the similar data traffic except the distance information, the similar filtered data packets were classified as the true behavior or the false behavior by KNN algorithm, and then the encrypted network behaviors were identified automatically and in real time, compared with the only correlation coefficient method or only DTW method, the online correct recognition rate by DTW and KNN has been greatly increased and reached to about 93%, and the missed detection rate is almost same with the traditional methods, the experiments and actual project applications showed that the proposed method was effective.

Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis

Efficient methodologies for mapping croplands are an essential condition for the implementation of sustainable agricultural practices and for monitoring crops periodically. The increasing spatial and temporal resolution of globally available satellite images, such as those provided by Sentinel-2, creates new possibilities for generating accurate datasets on available crop types, in ready-to-use vector data format. Existing solutions dedicated to cropland mapping, based on high resolution remote sensing data, are mainly focused on pixel-based analysis of time series data. This paper evaluates how a time-weighted dynamic time warping (TWDTW) method that uses Sentinel-2 time series performs when applied to pixel-based and object-based classifications of various crop types in three different study areas (in Romania, Italy and the USA). The classification outputs were compared to those produced by Random Forest (RF) for both pixel- and object-based image analysis units. The sensitivity of these two methods to the training samples was also evaluated. Object-based TWDTW outperformed pixel-based TWDTW in all three study areas, with overall accuracies ranging between 78.05% and 96.19%; it also proved to be more efficient in terms of computational time. TWDTW achieved comparable classification results to RF in Romania and Italy, but RF achieved better results in the USA, where the classified crops present high intra-class spectral variability. Additionally, TWDTW proved to be less sensitive in relation to the training samples. This is an important asset in areas where inputs for training samples are limited.

Whispered speech recognition based on gammatone filterbank cepstral coefficients

This paper presents the results on whispered speech recognition using gammatone filterbank cepstral coefficients for speaker dependent mode. The isolated words used for this experiment are taken from the Whi-Spe database. Whispered speech recognition is based on dynamic time warping and hidden Markov models methods. The experiments are focused on the following modes: normal speech, whispered speech and their combinations (normal/whispered and whispered/normal). The results demonstrated an important improvement in recognition after application of cepstral mean subtraction, especially in mixed train/test scenarios.

MULTI-DIMENSIONAL PATTERN DISCOVERY OF TRAJECTORIES USING CONTEXTUAL INFORMATION

Abstract. Movement of point objects are highly sensitive to the underlying situations and conditions during the movement, which are known as contexts. Analyzing movement patterns, while accounting the contextual information, helps to better understand how point objects behave in various contexts and how contexts affect their trajectories. One potential solution for discovering moving objects patterns is analyzing the similarities of their trajectories. This article, therefore, contextualizes the similarity measure of trajectories by not only their spatial footprints but also a notion of internal and external contexts. The dynamic time warping (DTW) method is employed to assess the multi-dimensional similarities of trajectories. Then, the results of similarity searches are utilized in discovering the relative movement patterns of the moving point objects. Several experiments are conducted on real datasets that were obtained from commercial airplanes and the weather information during the flights. The results yielded the robustness of DTW method in quantifying the commonalities of trajectories and discovering movement patterns with 80 % accuracy. Moreover, the results revealed the importance of exploiting contextual information because it can enhance and restrict movements.

Processing degraded speech for text dependent speaker verification

This work explores the use of speech enhancement for enhancing degraded speech which may be useful for text dependent speaker verification system. The degradation may be due to noise or background speech. The text dependent speaker verification is based on the dynamic time warping (DTW) method. Hence there is a necessity of the end point detection. The end point detection can be performed easily if the speech is clean. However the presence of degradation tends to give errors in the estimation of the end points and this error propagates into the overall accuracy of the speaker verification system. Temporal and spectral enhancement is performed on the degraded speech so that ideally the nature of the enhanced speech will be similar to the clean speech. Results show that the temporal and spectral processing methods do contribute to the task by eliminating the degradation and improved accuracy is obtained for the text dependent speaker verification system using DTW.

Wearable sensor devices for early detection of Alzheimer disease using dynamic time warping algorithm

Alzheimer disease is a significant problem in public health. Alzheimer disease causes severe problems with thinking, memory and activities. Alzheimer disease affected more on the people who are in the age group of 80-year-90. The foot movement monitoring system is used to detect the early stage of Alzheimer disease. internets of things (IoT) devices are used in this paper to monitor the patients’ foot movement in continuous manner. This paper uses dynamic time warping (DTW) algorithm to compare the various shapes of foot movements collected from the wearable IoT devices. The foot movements of the normal individuals and people who are affected by Alzheimer disease are compared with the help of middle level cross identification (MidCross) function. The identified cross levels are used to classify the gait signal for Alzheimer disease diagnosis. Sensitivity and specificity are calculated to evaluate the DTW algorithm based classification model for Alzheimer disease. The classification results generated using the DTW is compared with the various classification algorithms such as inertial navigation algorithm, K-nearest neighbor classifier and support vector machines. The experimental results proved the effectiveness of the DTW method.