DTW Distance Research Articles

Research on the railway multi-source homonymous geographical entity matching algorithm based on dynamic time warping

This study aims to explore an efficient technique for matching multisource homonymous geographical entities in railways to address the identification issues of homonymous geographical entities. Focusing on railway line vector spatial data, this research investigates the matching problem of multisource homonymous geographical entities. Building on statistical feature matching of attribute data, a curve similarity calculation method based on the DTW algorithm is designed to achieve better local elastic matching, overcoming the limitations of the Fréchet algorithm. The empirical study utilizes railway line layer data from two data sources within Beijing’s jurisdiction, fusing 6237 segment lines from source 2 with 105 long lines from source 1. The structural comparison between the two data sources is conducted through statistical methods, applying cosine similarity and the maximum similarity value of TF-IDF for text similarity calculation. Finally, Python is used to implement the DTW algorithm for curve similarity. The experimental results show an average DTW distance of 3.92, a standard deviation of 4.63, and a mode of 0.005. Similarity measurement results indicate that 95.53% of records are within the predetermined threshold, demonstrating the effectiveness and applicability of the method. The findings significantly enhance the accuracy of railway data matching, promoting the informatization of the railway industry, and hold substantial significance for improving railway operational efficiency and system performance.

HYDROSAFE: A Hybrid Deterministic-Probabilistic Model for Synthetic Appliance Profiles Generation.

Realistic appliance power consumption data are essential for developing smart home energy management systems and the foundational algorithms that analyze such data. However, publicly available datasets are scarce and time-consuming to collect. To address this, we propose HYDROSAFE, a hybrid deterministic-probabilistic model designed to generate synthetic appliance power consumption profiles. HYDROSAFE employs the Median Difference Test (MDT) for profile characterization and the Density and Dynamic Time Warping based Spatial Clustering for appliance operation modes (DDTWSC) algorithm to cluster appliance usage according to the corresponding Appliance Operation Modes (AOMs). By integrating stochastic methods, such as white noise, switch-on surge, ripples, and edge position components, the model adds variability and realism to the generated profiles. Evaluation using a normalized DTW-distance matrix shows that HYDROSAFE achieves high fidelity, with an average DTW distance of ten samples at a 1Hz sampling frequency, demonstrating its effectiveness in producing synthetic datasets that closely mimic real-world data.

Time series clustering based on polynomial fitting and multi-order trend features

Time series clustering serves as a potent data mining method, facilitating the analysis of an extensive array of time series data without the prerequisite of any prior knowledge. It finds wide-ranging use across various sectors, including but not limited to, financial and medical data analysis, and sensor data processing. Given the high dimensionality, non-linearity, and redundancy characteristics associated with time series, conventional clustering algorithms frequently fall short in yielding satisfactory results when directly applied to this kind of data. As such, there is a critical need to judiciously select suitable feature extraction methods and dimension reduction techniques. This paper introduces a time series clustering algorithm, drawing primarily from polynomial fitting derivative features as a wellspring for feature extraction to achieve effective clustering results. Initially, Hodrick Prescott (HP) filtering comes into play for the processing of raw time series data, thereby eliminating noise and redundancy. Subsequently, polynomial curve fitting (PCF) is applied to the data to derive a globally continuous function fitting this time series. Next, by securing multi-order derivative values via this function, the time series is transformed into a multi-order derivative feature sequence. Lastly, we designed a polynomial function derivative features-based dynamic time warping (PFD_DTW) algorithm for determining the distance between two equal or unequal granular length time series, and subsequently a hierarchical clustering method anchored on the PFD_DTW distances for time series clustering after computing interspecies distances. The effectiveness of this method is corroborated by experimental results obtained from several practical datasets.

Spatial domain transfer: Cross-regional paddy rice mapping with a few samples based on Sentinel-1 and Sentinel-2 data on GEE

The global population is on the rise, leading to an increased demand for food resources. Accurate mapping and monitoring of paddy rice fields have become crucial for effective food management and yield estimation. Several large-scale paddy rice mapping products with medium-to-high resolution have been made by using threshold-based phenological methods. The main shortcoming is that paddy rice varies in different regions due to differences in climate and planting habits, which results in the limitations of fixed phenological indicator thresholds for large-scale paddy rice mapping. Therefore, paddy rice samples from different regions are needed to account for regional differences between paddy rice and improve paddy rice mapping accuracy. To address two key shortcomings in existing sample generation methods (the non-robustness of DTW distance and the limitation of fixed phenological indicator thresholds for generating samples) and the three difficulties of cross-regional sample generation (different planting times, growth cycles, and planting intensities), this study proposed a novel approach for cross-regional paddy rice sample generation based on spatial domain transfer, achieving cross-regional paddy rice mapping. The accuracy results (OA of 95.16–97.54%) in three study regions with different climatic and topographic conditions in China and improved accuracy (OA improvement of 5.89–19.06%) compared with the method of NESEA-Rice10, proved the effectiveness of the proposed method and the potential of the proposed method in large-scale paddy rice mapping. The proposed method can obtain high-accuracy paddy rice mapping results in regions without paddy rice samples and be applied to the mapping of other crops and land cover types.

Sign Language Motion Generation from Sign Characteristics.

This paper proposes, analyzes, and evaluates a deep learning architecture based on transformers for generating sign language motion from sign phonemes (represented using HamNoSys: a notation system developed at the University of Hamburg). The sign phonemes provide information about sign characteristics like hand configuration, localization, or movements. The use of sign phonemes is crucial for generating sign motion with a high level of details (including finger extensions and flexions). The transformer-based approach also includes a stop detection module for predicting the end of the generation process. Both aspects, motion generation and stop detection, are evaluated in detail. For motion generation, the dynamic time warping distance is used to compute the similarity between two landmarks sequences (ground truth and generated). The stop detection module is evaluated considering detection accuracy and ROC (receiver operating characteristic) curves. The paper proposes and evaluates several strategies to obtain the system configuration with the best performance. These strategies include different padding strategies, interpolation approaches, and data augmentation techniques. The best configuration of a fully automatic system obtains an average DTW distance per frame of 0.1057 and an area under the ROC curve (AUC) higher than 0.94.

APPLICATION OF TIME SERIES CLUSTER ANALYSIS IN CLUSTERING THE CENTRAL JAVA PROVINCE BASED ON THE POVERTY DEPTH INDEX

Poverty is a problem that continues to be faced, especially in developing countries such as Indonesia. Poverty is included in one of the Sustainable Development Goals (SDGs) programs, which is related to hunger and health. The time series data can be clustered based on the characteristics of the time series data and adjusted to the time series pattern. The choice of distance and method used must be adjusted to the dynamic structure of time series data. The purpose of this research is to cluster districts/cities in Central Java Province based on the poverty depth index value from 2017 to 2022. The variable that used in this research is the Poverty Depth Index of 35 districts in Central Java Province from 2017 to 2022. This research used cluster time series with DTW similarity measurment. Based on theDTW and cophenetic coefficient correlation value using three linkage methods, the average linkage method has the highest cophenetic coefficient correlation value of 0.8017988. Testing the quality of clusters using the silhouette coefficient using DTW distance and average linkage method and 2 clusters are included in the good cluster category with a silhouette coefficient value of 0.60. The resulting clusters using the DTW distance and average linkage method are cluster 1 consisting of 25 districts / cities and cluster 2 consisting of 10 districts.

An integrated approach implementing sliding window and DTW distance for time series forecasting tasks

An integrated approach implementing sliding window and DTW distance for time series forecasting tasks

Pengelompokan Kemiskinan di Indonesia Menggunakan Time Series Based Clustering

Indonesia has a strong commitment in achieving the 2030 SDGs, which one of the targets is reducing poverty. Poverty itself is defined as the inability of an individual or group to meet the basic needs of both food and non-food. During the pandemic, Indonesia experienced an increase in poverty percentage, which peaked in September 2020 with 10.19%. The latest data in March 2022, showed that the number has decreased by 0.75% or equivalent of 1.79 million people. However, the decrease does not encompass all provinces, there are several provinces that still suffer from increasing poverty. Therefore, it is necessary to group the provinces in Indonesia based on its percentage of poverty, in order to provide more appropriate treatment. The analysis method used in this research is the time series-based clustering with dtw distance. The clustering algorithm used is hierarchical cluster complete linkage. Based on the analysis result, the use of dtw distance can increase the silhouette coefficient value to 0.75 compared to using the Euclidean distance. The silhouette coefficient is one of the parameters used to determine the goodness of the clustering results, where the value of 0.75 can already be said to be very good clustering results. The optimum result of the clustering is a total of 3 groups with low, medium, and high poverty categories, where NTT, Papua, and West Papua provinces have the highest poverty rates but have significant progress in reducing poverty.

An N400 identification method based on the combination of Soft-DTW and transformer.

As a time-domain EEG feature reflecting the semantic processing of the human brain, the N400 event-related potentials still lack a mature classification and recognition scheme. To address the problems of low signal-to-noise ratio and difficult feature extraction of N400 data, we propose a Soft-DTW-based single-subject short-distance event-related potential averaging method by using the advantages of differentiable and efficient Soft-DTW loss function, and perform partial Soft-DTW averaging based on DTW distance within a single-subject range, and propose a Transformer-based ERP recognition classification model, which captures contextual information by introducing location coding and a self-attentive mechanism, combined with a Softmax classifier to classify N400 data. The experimental results show that the highest recognition accuracy of 0.8992 is achieved on the ERP-CORE N400 public dataset, verifying the effectiveness of the model and the averaging method.

Automatic identification method of topology structure of low-voltage distribution station area based on multi-point measurement data

In order to improve the accuracy and success rate of the identification results of the topology structure of the station area, an automatic identification method of the topology structure of the low-voltage distribution station area based on multi-point measurement data is proposed. LoRa technology is used to obtain multi-point measurement data, and with the help of protocol compression technology, the acquisition of massive high-density measurement data is completed. A current-based identification model for the affiliation of equipment in the station area is constructed, and the affiliation between the primary branch and the secondary branch, and the affiliation between the secondary branch and the user energy meter cluster set are obtained by using the model. Finally, the DTW distance and cluster analysis are used to analyze the distribution terminal and the collected measurement data. So as to realize the automatic identification of the topology structure of the low-voltage distribution station area. The experimental results show that the identification results of the proposed method are more accurate, and the success rate is also effectively improved.

Design of DNA Storage Coding with Enhanced Constraints.

Traditional storage media have been gradually unable to meet the needs of data storage around the world, and one solution to this problem is DNA storage. However, it is easy to make errors in the subsequent sequencing reading process of DNA storage coding. To reduces error rates, a method to enhance the robustness of the DNA storage coding set is proposed. Firstly, to reduce the likelihood of secondary structure in DNA coding sets, a repeat tandem sequence constraint is proposed. An improved DTW distance constraint is proposed to address the issue that the traditional distance constraint cannot accurately evaluate non-specific hybridization between DNA sequences. Secondly, an algorithm that combines random opposition-based learning and eddy jump strategy with Aquila Optimizer (AO) is proposed in this paper, which is called ROEAO. Finally, the ROEAO algorithm is used to construct the coding sets with traditional constraints and enhanced constraints, respectively. The quality of the two coding sets is evaluated by the test of the number of issuing card structures and the temperature stability of melting; the data show that the coding set constructed with ROEAO under enhanced constraints can obtain a larger lower bound while improving the coding quality.

Motion Recognition Based on Deep Learning and Human Joint Points

In order to solve the problem that the traditional feature extraction methods rely on manual design, the research method is changed from the traditional method to the deep learning method based on convolutional neural networks. The experimental results show that the larger average DTW occurs near the 55th calculation, that is, about the 275th frame of the video. In the 55th calculation, the joint angle with the largest DTW distance is the right knee joint. A multiscene action similarity analysis algorithm based on human joint points has been realized. In the fitness scene, by analyzing the joint angle through cosine similarity, the time of fitness key posture in the action sequence can be recognized. In the sports scene, through the similarity analysis of joint angle sequences by the DTW algorithm, we can get the similarity between people's actions in the sports video and the joint positions with large differences in some time intervals, and the real validity of the experiment is verified. The accuracy of motion recognition before and after the improvement is 95.2% and 97.1%, which is 0.19% higher than that before the improvement. The methods and results are widely used in the fields of sports recognition, movement specification, sports training, health management, and so on.

The inherent time complexity and an efficient algorithm for subsequence matching problem

Subsequence matching is an important and fundamental problem on time series data. This paper studies the inherent time complexity of the subsequence matching problem and designs a more efficient algorithm for solving the problem. Firstly, it is proved that the subsequence matching problem is incomputable in time O ( n 1-δ ) even allowing polynomial time preprocessing if the hypothesis SETH is true, where n is the size of the input time series and 0 ≤ δ < 1, i.e., the inherent complexity of the subsequence matching problem is ω ( n 1-δ ). Secondly, an efficient algorithm for subsequence matching problem is proposed. In order to improve the efficiency of the algorithm, we design a new summarization method as well as a novel index for series data. The proposed algorithm supports both Euclidean Distance and DTW distance with or without z -normalization. Experimental results show that the proposed algorithm is up to about 3 ~ 10 times faster than the state of art algorithm on the constrained z -normalized Euclidean Distance and DTW distance, and is up to 7 ~ 12 times faster on Euclidean Distance.

Building-Level Urban Functional Area Identification Based on Multi-Attribute Aggregated Data from Cell Phones—A Method Combining Multidimensional Time Series with a SOM Neural Network

Portraying functional urban areas provides useful insights for understanding complex urban systems and formulating rational urban plans. Mobile phone user trajectory data are often used to infer the individual activity patterns of people and for functional area identification, but they are difficult to obtain because of personal privacy issues and have the drawback of a sparse spatial and temporal distribution. Deep learning models have been widely utilized in functional area recognition but are limited by the difficulty of acquiring training samples with large data volumes. This paper aims to achieve a fast and automatic identification of large-scale urban functional areas without prior knowledge. This paper uses Nanjing city as a test area, and a self-organizing map (SOM) neural network model based on an improved dynamic time warping (Ndim-DTW) distance is used to automatically identify the function of each building using mobile phone aggregated data containing work and residence attributes. The results show that the recognition accuracy reaches 88.7%, which is 12.4% higher than that of the K-medoids method based on the DTW distance using a single attribute and 7.8% higher than that of the K-medoids method based on the Ndim-DTW distance with multiple attributes, confirming the effectiveness of the multi-attribute mobile phone aggregated data and the SOM model based on the Ndim-DTW distance. Furthermore, at the traffic analysis zone (TAZ) level, this paper detects that Nanjing has seven functional area hotspots with a high degree of mixing. The results can provide a data basis for urban studies on, for example, the urban spatial structure, the separation of occupations and residences, and environmental suitability evaluation.

Research on Grey Relational Clustering Model of Multiobjective Human Resources Based on Time Constraint

The existing grey relational clustering method has limitations in the application of multidimensional sequences and cannot directly calculate the grey correlation degree between unequal-length sequences. In this paper, by introducing the multidimensional dynamic DTW distance into the existing 3D grey relational model, a new grey relational analysis model that can be applied to multidimensional data is proposed, which is based on DTW distance. The model does not require one-to-one correspondence of data points but evaluates the similarity of its geometric curves by calculating the shortest distance between sequences. In addition, since the traditional grey correlation clustering method is implemented, the method first extracts the reference sequence from the observation sequence and then calculates the similarity between the observation objects by calculating the grey correlation degree between each sequence and the reference sequence, so each object only needs to be calculated once. The experimental results show that the multidimensional grey correlation degree based on DTW distance and the grey relational clustering model oriented to multidimensional data are more accurate than other existing methods. Finally, the grey relation clustering method of multidimensional data is used to analyze the multiobjective human resource grey relational clustering model under time constraints, and the validity of the model is verified.

Fuzzy Clustering Method Based on Improved Weighted Distance

As an essential data processing technology, cluster analysis has been widely used in various fields. In clustering, it is necessary to select appropriate measures to evaluate the similarity in the data. In this paper, firstly, a cluster center selection method based on the grey relational degree is proposed to solve the problem of sensitivity in initial cluster center selection. Secondly, combining the advantages of Euclidean distance, DTW distance, and SPDTW distance, a weighted distance measurement based on three kinds of reach is proposed. Then, it is applied to Fuzzy C-MeDOIDS and Fuzzy C-means hybrid clustering technology. Numerical experiments are carried out with the UCI datasets. The experimental results show that the accuracy of the clustering results is significantly improved by using the clustering method proposed in this paper. Besides, the method proposed in this paper is applied to the MUSIC INTO EMOTIONS and YEAST datasets. The clustering results show that the algorithm proposed in this paper can also achieve a better clustering effect when dealing with practical problems.

An ensemble radius basis function network based on dynamic time warping for real-time monitoring of supersonic inlet flow patterns

As the basis of protection control, supersonic inlet plays an important role in a supersonic air-breathing propulsion system, so it is of great significance to ensure the safe and stable operation by monitoring its flow patterns. From the perspective of machine learning, this issue can be viewed as a time series classification (TSC) task. Traditionally, several manually-engineered features are extracted as the indicators to evaluate the operation status, which can be heavily dependent on the professional experience and time-consuming. This paper proposes a novel Dynamic Time Warping-Radius Basis Function (DTW-RBF) network to directly determine the flow patterns from the dynamic input signals. DTW-RBF network replaces the Euclidean distance in the static RBF kernels with the DTW distance, which exploits the elastic matching ability of DTW to align the input signals to the kernels. Then, the second-order Levenberg-Marquarelt (LM) optimization algorithm is used to allow the efficient training process of the proposed network. In order to determine the appropriate locations for sensor placement and enhance the robustness and reliability of monitoring flow patterns by a single sensor, an optimal subset of sensors is further selected for ensemble through multi-objective optimization and fuzzy decision. Experimental results demonstrate that the proposed DTW-RBF network works efficiently for TSC tasks on benchmark time series datasets, and has better comprehensive performance for monitoring supersonic inlet flow patterns in terms of classification accuracy and test time. The ensemble classifier further increases the classification accuracy with still meeting the real-time requirements.

A GPU Acceleration Framework for Motif and Discord Based Pattern Mining

With the fast digitalization of our society, mining patterns from large time series data is increasingly becoming a critical problem for a wide range of big data applications. Motif and discord discovery algorithms, which offer effective solutions to identify repeatedly appearing and abnormal patterns, respectively, are fundamental building blocks for time series processing. Both approaches, however, can be time extremely consuming when handling large time series due to the subsequence-based computations of distance similarity metrics. In this article, we show that the highly involved subsequence-based computations can actually be decomposed into a few fine-grained computing patterns for efficient data parallel computing. By developing highly efficient GPU algorithms for such basic patterns and effectively composing such patterns, we are able to solve both motif and discord discovery problems under euclidean and DTW distance metrics in a unified GPU acceleration framework. Extensive experiments prove that the proposed framework outperforms pruned CPU algorithms by up to three orders of magnitude. Our work paves the foundation of building GPU acceleration frameworks for large-scale time series datasets.

Motion Analysis of Traditional Korean Dance using Openpose and DTW Distance

Motion Analysis of Traditional Korean Dance using Openpose and DTW Distance

Power enterprise risk identification model based on convolutional neural network and adaptive comparison algorithm

Combined with the actual characteristics of risk identification in electric power enterprises, a convolutional neural network model suitable for load sequence data prediction is determined. Particle Swarm Optimization (PSO) algorithm is used to transform the convolutional neural network (convolutional neural network) to improve the global Optimization ability and convergence speed. Simulation results show that CNN can effectively extract sample information through its convolutional layer and pool layer. After particle swarm optimization, it also achieves good results in prediction accuracy and prediction speed. Secondly, classical interpretation combination model (ISM) is used to analyze the structure of the risk system of electric power enterprises, and the link relationship model of the risk of electric power enterprises is constructed. Through the structural analysis of risk and risk factors, the paper finds out the mutual influence relationship between risk and risk factors, and further finds out the risk chain and risk source. The classical explanatory structure model is extended to the fuzzy set, and then the influence intensity model of power enterprise risk is built. This model considers the influence of risk intensity when analyzing the risk relationship of electric power enterprises, and gives different risk link relations based on different impact intensity. Through comparative analysis, the relationship between the link relationship model and the influence intensity model of the risk of electric power enterprises is obtained. Put forward the sequence similarity matching algorithm based on adaptive search window (ADTW), average algorithm using Piecewise gathered (Piecewise Aggregate Approximation, PAA) strategy for sequence sampling sequence, low precision and low calculation precision sequence alignment of paths, and according to the change of gradient on the low precision of distance matrix forecast path deviation, expand the scope of limiting path search window; Then, the algorithm gradually improves the sequence accuracy, corrects the path in the search window, calculates the new search window, and finally realizes the fast solution of DTW distance and similarity alignment path.