China
Africa
Explore chapters and articles related to this topic
Early warning method of water inrush in mining area based on a curve similarity analysis model
Published in Ahmad Safuan Bin A Rashid, Junwen Zhang, Advances in Mineral Resources, Geotechnology and Geological Exploration, 2023
Xingguo Qiu, Yuge Si, Zhen Liu
Dynamic time warping (DTW) is a technology to measure the similarity of two groups of unequal length sequences (Senin 2008). For two sequences A and B, the DTW distance is a path to minimize the cumulative distance of the two curves, as shown in Figure 1. This path is defined as a warping path (WP) and represented by W, the first element of W is defined as Wk = (i, j)k, which defines the mapping of sequences A and B. There are:Wk=(w1,w2,...,wk,...,wK),max(m,n)≤K<m+n−1
Smartphone-Based Human Activity Recognition
Published in Yufeng Wang, Athanasios V. Vasilakos, Qun Jin, Hongbo Zhu, Device-to-Device based Proximity Service, 2017
Yufeng Wang, Athanasios V. Vasilakos, Qun Jin, Hongbo Zhu
Once signals have been mapped to strings, exact or approximate matching and edit distances are key techniques used to evaluate string similarity and thus either find known patterns or classify the user activity. Some typical metrics of evaluating string similarity are as follows: Euclidian-related distances between symbols are defined by the corresponding numeric distance between the signal values that correspond to each symbol in the string representation.Levenshtein edit distance determines the minimum number of symbol insertions, deletion, and substitutions needed to transform one string into the other.Dynamic time warping (DTW) is a metric for measuring similarity between two sequences that may vary in length and can thus correspond to different time basis. It can capture similarities of strings with distinct sampling period, but has a relatively high computational cost.
Understanding the merging behavior patterns and evolutionary mechanism at freeway on-Ramps
Published in Journal of Intelligent Transportation Systems, 2023
Yue Zhang, Yajie Zou, Yangyang Wang, Lingtao Wu, Wanbing Han
The primitives from the NHMM are time series composed of the temporal features of merging behaviors. Abundant primitives may contain the same merging behavior patterns. In order to identify different merging behavior patterns, a clustering method is used to classify similar primitives into a group. Note that these primitives are variable-length time series. Thus, the Time Series K-Means clustering (Tavenard et al., 2020) is applied as the primitive clustering method. And the Dynamic Time Warping (DTW) is considered as the metric to evaluate the distance between primitives. DTW distance is the optimal alignment length of two primitives based on shape similarity. Assuming all primitives are classified into clusters and the center of each cluster is The objective is to minimize the within-cluster sum-of-squares in Eq. (7).
A closed-loop electrical stimulation system triggered by EOG for acupuncture therapy
Published in Systems Science & Control Engineering, 2020
Ding Yuan, Yurong Li, Tian Wang, Jianguo Chen, Dongyi Chen, Dong Lin, Yuan Yang
Dynamic time warping (DTW) is a commonly used measure of similarity in time series classification, which can match two given time series even with different lengths of data, overcoming their phase distortions (Su, Chiang, & Huang, 2014). It uses a dynamic searching strategy to find the minimal distance between two given time series, where the time series is warped by stretching or shrinking the time dimension. The recorded EOGs are influenced by the play period of the visual evocation system. Therefore, DTW is suitable to measure the similarity of the recorded EOGs and the targeted EOG recordings.
Regional forecasting of wind speed in large scale wind plants
Published in International Journal of Green Energy, 2023
Dynamic time warping (DTW) is a method to measure time series similarity (Keogh and Ratanamahatana 2005; Wang, Pedrycz, and Liu 2015). In order to solve the problem of inconsistency or mismatch between the number of samples, the time domain signal is processed by DTW, as shown in Figure 3. It can be seen from the figure that DTW bends the curve points, which can better discover the similar patterns between series. In the figure, curve a and curve b are two different curves. Through DTW, the peaks and valleys of the two curves are found and matched.