Feature subset selection and feature ranking for multivariate time series

Yoon, Hyunjin; Yang, Kiyoung; Shahabi, Cyrus

doi:10.1109/tkde.2005.144

Cited by 176 publications

(91 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The research in this area mostly focuses on feature extraction [2], [3], indexing, and similarity measurements [4], [5]. Indexing methods specially designed for multidimensional data have been proposed and explored for similarity search.…”

Section: A Wavelet Transform In Time Series Analysismentioning

confidence: 99%

Multiresolution Analysis Based on Wavelet Transform for Commodity Prices Time Series Forecasting

Bunrit¹,

Kerdprasop²,

Kerdprasop³

2018

IJMLC

View full text Add to dashboard Cite

Abstract-This research proposes time series forecasting of commodity prices by using multiresolution analysis from wavelet transform. In this work, discrete wavelet transform based multiresolution decomposition of Deubechies family is used. Firstly, Deubechies wavelet transform is applied to the training set of time series data up to level four. The reconstruction values of the approximation part of wavelet from each level are then used for the forecasting process by ARIMA model. The validation set of data is used to analyze and select the best model from all 4 levels of multiresolution decomposition. Finally, best selected validating model is used for evaluating the remaining testing data set. The forecasting results by using multiresolution analysis are compared to the case where the original data are directly modeled and forecasted by ARIMA. Results based on the mean absolute percentage error evaluation from using multiresolution analysis are better for both of the two studied data including daily gold price and rubber price. By applying multiresolution analysis, the improvement is 10.83% for gold price and 42.68% for rubber price. The variances of errors from the proposed method on both data sets are also much less than directly use the original time series data for forecasting.

show abstract

Section: A Wavelet Transform In Time Series Analysismentioning

confidence: 99%

Multiresolution Analysis Based on Wavelet Transform for Commodity Prices Time Series Forecasting

Bunrit¹,

Kerdprasop²,

Kerdprasop³

2018

IJMLC

View full text Add to dashboard Cite

show abstract

“…Based on PCA, Lu et al puts forward principal feature analysis (PFA) [23] and Yoon et la. put forward the characteristics scoring method of the multivariate time sequence on the basis of the correlation between information according to the common principal component analysis (CPCA) [24].…”

Section: Feature Extraction Of Data In Social Media Stock Data Spacementioning

confidence: 99%

Relationship discovery in public opinion and actual behavior for social media stock data space

Xue

Qiu

et al. 2016

J Wireless Com Network

View full text Add to dashboard Cite

With the rise of social data media, the cyber world nearly parallels to the real world. The trajectory of a hot event is reflected in social media by Public Opinion Data Space (OS) and Actual Behavior Data Space (BS). However, the relationships with a variety of mechanisms in each space or between them are often unknown. To solve the above issues, the traditional methods for inferring relationship are by performing a statistical similarity analysis of time sequence from dynamic elements. In specially, the research of clustering nonlinear correlation data object is rare, so we propose Matrix Similarity Clustering Algorithm (MSCA) based on random matrix theory and combined with sliding window technology to cluster the similarity of multidimensional time sequences. This method is effective to detect the trend relationship of time sequences with multiple dynamic elements. In addition, we construct a knowledge map to analyse the relationships in OS and BS.

show abstract

“…PFA avoids this problem by selecting a subset of features with most information. PFA has been applied to select facial points for face tracking and content-based image retrieval [19] and an approach similar to PFA has been successfully applied to find a subset of features from multivariate time series data, such as human gait data and electroencephalogram (EEG) data [21].…”

Section: Explorative Navigation Using Sparse Gaussian Processesmentioning

confidence: 99%

“…A principal component is a linear transformation of original features and this transformation is described by coefficients of principal components. These coefficients can be understood as contributions or weights on determining the directions of principal components [21]. Hence, when the absolute value of the -th coefficient of a principal component is high, we can interpret this as an indication that the -th feature is dominant in that principal component.…”

Section: Explorative Navigation Using Sparse Gaussian Processesmentioning

confidence: 99%

Explorative navigation of mobile sensor networks using sparse Gaussian processes

Choi

2010

49th IEEE Conference on Decision and Control (CDC)

View full text Add to dashboard Cite

Abstract-This paper presents an explorative navigation method using sparse Gaussian processes for mobile sensor networks. We first show that a near-optimal approximation is possible with a subset of measurements if we select the subset carefully, i.e., if the correlation between the selected measurements and the remaining measurements is small and the correlation between the prediction locations and the remaining measurements is small. An estimation method based on a subset of measurements is desirable for mobile sensor networks since we can always bound computational and memory requirements and unprocessed raw measurements can be easily shared with other agents for further processing (e.g., consensusbased distributed algorithms or distributed learning). We then present an explorative navigation method using sparse Gaussian processes with a subset of measurements. Using the explorative navigation method, mobile sensor networks can actively seek for new measurements to reduce the prediction error and maintain high-quality estimation about the field of interest indefinitely with limited memory.

show abstract

Feature subset selection and feature ranking for multivariate time series

Cited by 176 publications

References 25 publications

Multiresolution Analysis Based on Wavelet Transform for Commodity Prices Time Series Forecasting

Multiresolution Analysis Based on Wavelet Transform for Commodity Prices Time Series Forecasting

Relationship discovery in public opinion and actual behavior for social media stock data space

Explorative navigation of mobile sensor networks using sparse Gaussian processes

Contact Info

Product

Resources

About