Fast Constrained Dynamic Time Warping for Similarity Measure of Time Series Data

Choi, Won-Young; Cho, Jaechan; Lee, Seongjoo; Jung, Yunho

doi:10.1109/access.2020.3043839

Cited by 37 publications

(10 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A lot of variants of DTW exist, they have specific features for a very large panel of uses. Each version of DTW can improve a specific aspect like the speed (Geler et al 2019;Sakoe and Chiba 1978;Choi et al 2020) or the precision (Jeong, Jeong, and Omitaomu 2011;Muscillo et al 2007;Munich and Perona 1999), but the calculation time and the complexity of the algorithm will also increase. It is possible to use combinations of several versions of DTW to combine advantages.…”

Section: Related Workmentioning

confidence: 99%

Temporal Alignment and Demonstration Selection as Pre-Processing Phase for Learning by Demonstration

Donjat

Legeleux²,

Buche³

et al. 2022

FLAIRS

View full text Add to dashboard Cite

Robots can benefit from users’ demonstrations to learnmotions. To be efficient, a pre-processing phase needsto be performed on data recorded from demonstrations.This paper presents pre-processing methods developedfor Learning By Demonstration (LbD). Thepre-processing phase consists in methods composedof alignment algorithms and algorithms that select thegood demonstrations. In this paper we propose sixmethods and compare them to select the best one.

show abstract

Section: Related Workmentioning

confidence: 99%

Temporal Alignment and Demonstration Selection as Pre-Processing Phase for Learning by Demonstration

Donjat

Legeleux²,

Buche³

et al. 2022

FLAIRS

View full text Add to dashboard Cite

show abstract

“…After running the API on the image, the output is a set of landmarks in the image's X, Y, Z proportions, a flag indicating whether the hand is right or left, and a probability of the hand's presence in the image. To get the essential rows extracted from the repetitive guitarist's performance frames, the proposed method suggests using FDTW [50] fast dynamic time warping, RNN Recurrent neural networks, LSTM long short-term memory, and transformers to detect the repeated patterns in a time series.…”

Section: Hand Finger Recognitionmentioning

confidence: 99%

Note Frequency Recognition and Finger Motion Capture of a Guitarist: A Survey and Challenges Ahead

Emad

Sobeah

Hassan

et al. 2022

Journal of Computing and Communication

View full text Add to dashboard Cite

One of the main issues that face new guitar aspirants is that there is a lot of further information, which proves a lot to take in for just a beginner as it causes much-disliked confusion. Students also face problems with their left-hand motion and correct pitch frequency. Researchers have tackled this problem in many ways and have mainly landed on using two approaches. The first was Finger Motion Capture, where previous research specialized in analyzing images and videos of the guitarist. The second was Note Frequency Recognition, where the research's primary purpose was to examine the sound and audio recorded by the guitarist. This paper surveys all the approaches taken to solve this problem, discussing them in detail and exploring the challenges faced with each approach. Furthermore, this paper proposes a hybrid solution that includes both Note Frequency Recognition and Finger Motion Capture to make a full assessment and give feedback on a guitarist's performance.

show abstract

“…The DTW is able to calculate the distance between two-time series and is thus a common method to measure similarity [42,43,47] . This method intends to find the optimal alignment of two temporal sequences with different lengths and speeds [48] , which results in better performance and more meaningful discrepancy distances than other approaches [42,49] . The DTW result represents the distance value in the scalar quantity [50] , which is employed to measure how similar two diffusion trends are in time sequences.…”

Section: Comparing the Similarity Of Trend Comparisonmentioning

confidence: 99%

An Operator-Based Approach for Modeling Influence Diffusion in Complex Social Networks

Jiang

D'Arienzo

et al. 2021

J. Soc. Comput.

View full text Add to dashboard Cite

Social media have dramatically changed the mode of information dissemination. Various models and algorithms have been developed to model information diffusion and address the influence maximization problem in complex social networks. However, it appears difficult for state-of-the-art models to interpret complex and reversible real interactive networks. In this paper, we propose a novel influence diffusion model, i.e., the Operator-Based Model (OBM), by leveraging the advantages offered from the heat diffusion based model and the agent-based model. The OBM improves the performance of simulated dissemination by considering the complex user context in the operator of the heat diffusion based model. The experiment obtains a high similarity of the OBM simulated trend to the real-world diffusion process by use of the dynamic time warping method. Furthermore, a novel influence maximization algorithm, i.e., the Global Topical Support Greedy algorithm (GTS-Greedy algorithm), is proposed corresponding to the OBM. The experimental results demonstrate its promising performance by comparing it against other classic algorithms.

show abstract

Fast Constrained Dynamic Time Warping for Similarity Measure of Time Series Data

Cited by 37 publications

References 45 publications

Temporal Alignment and Demonstration Selection as Pre-Processing Phase for Learning by Demonstration

Temporal Alignment and Demonstration Selection as Pre-Processing Phase for Learning by Demonstration

Note Frequency Recognition and Finger Motion Capture of a Guitarist: A Survey and Challenges Ahead

An Operator-Based Approach for Modeling Influence Diffusion in Complex Social Networks

Contact Info

Product

Resources

About