Dissertation > Excellent graduate degree dissertation topics show
Motif Extraction Algorithm of Time Series Based on DTW
Author: MaBaiMing
Tutor: FengLin
School: Dalian University of Technology
Course: Applied Computer Technology
Keywords: Time Series Dynamic Time Average method The middle of the sequence Keynote mode
CLC: O211.61
Type: Master's thesis
Year: 2011
Downloads: 20
Quote: 0
Read: Download Dissertation
Abstract
|
The time sequence is widely existence of an important type of data in the areas of finance , biology , science experiments . Classification, applications such as pattern extraction and anomaly detection , it is often the need to calculate the center of the collection of time sequence ( core sequence ) is used to represent the common mode . In some centers clustering method also must calculate the center of the time series , for example , k-means algorithm . Dynamic Time Warping (DTW) distance measure for time series has a strong advantage than the Euclidean distance . How to define based the DTW metric center sequence is a problem . Some of the literature in this regard , the attempt to define the center sequence , and given the central sequence solving method . In this paper, the definition of a new center sequence . The advantage of this definition is that the sequence to be able to make the center distance and the minimum of the other sequences , and thus more representative . This paper discusses the definition of this central sequence method for solving global constraints and local constraints . For the particularity of local constraints , the article focuses on the slope of the constraints of the solution , and gives an effective pruning algorithm . Center of two time series - based solution method , the paper gives the Methods Solving multiple sequence Center . The method uses aliquot collection , the shape of the first and other rules , to avoid the conventional simple pairwise method for solving the weaknesses. Finally , a large number of experiments to prove the rationality and superiority of this definition , the validity of the slope constraints pruning algorithm , as well as multi- center algorithm superiority sequences .
|
Related Dissertations
- Crop Evapotranspiration Study on Evolution Rule and Forecast Model in Chaoyang Area,S161.4
- Based on Data Mining Technologies in Urban Water Supply Analysis and Decision,F299.24;F224
- The Design and Implementation of Assessment Information System of PLA Officers in Active Service,TP311.52
- The Design and Implementation of PGIS on Intelligent Mobile Terminal,TN929.53
- Analysis and Prediction of the Epidemic Situation of Schistosomiasis in Qianjiang City,R532.21
- Concurrent negotiations based on the associated issues Genetic Algorithm,TP18
- Multidimensional Time-varying Volume Data Visualization Software Platform,TP391.41
- Quality management in the network monitoring application performance study,F626
- Research on International Express Market and Its Cyclical Characteristics,F224
- GPU-based parallel search algorithm for time series,TP391.41
- Kernel-based SOM time series prediction,O211.61
- Short-term load forecasting technology,TM715
- A Time Series Forecasting Model Base on ANN for Residential Price,F293.3
- Research on the Subway Travel Demand Based on Multiply Social & Economic Factors,U231
- Characteristics Analysis for DNA Sequences of the Influenza Virus Based on the Time Series Theory Methods,R346
- Signature Verification Based on Video,TP391.41
- Research on Weather Radar Factors Calibration and Rainfall Retrieval Based on GIS,P208
- The Statistical Analysis of Temperature and Short-term Forecast,P457.3
- Researches on the Theories and Algorithms of Earth Orientation Paramters Prediction,P22
- Deformation Analysis and Prediction Based on Chaotic Time Series,N945.2
CLC: > Mathematical sciences and chemical > Mathematics > Probability Theory and Mathematical Statistics > Theory of probability ( probability theory, probability theory ) > Random process > Smooth process and the process of second-order moment
© 2012 www.DissertationTopic.Net Mobile
|