Applicability of feature selection on multivariate time series data for robotic discovery

  title={Applicability of feature selection on multivariate time series data for robotic discovery},
  author={Shahzad Cheema and T. Henne and Uwe K{\"o}ckemann and E. Prassler},
  journal={2010 3rd International Conference on Advanced Computer Theory and Engineering(ICACTE)},
Open ended robotic discovery aims at enabling robots to autonomously design and execute sophisticated experiments for gaining conceptual insight about real world. Such experiments are planned activities rather than innate motor commands and thus each single experiment results in a multivariate time series. In such a scenario, reducing the number of features in order to allow a symbolic learner to build a correct conceptual model of underlying phenomena is a fundamental task. Only few feature… Expand
Unsupervised feature selection for sensor time-series in pervasive computing applications
  • D. Bacciu
  • Computer Science
  • Neural Computing and Applications
  • 2015
An efficient feature selection approach for multivariate time-series of heterogeneous sensor data within a pervasive computing scenario is introduced and an iterative filtering procedure is devised to reduce information redundancy measured in terms of time- series cross-correlation. Expand
Mutual information based feature subset selection in multivariate time series classification
This paper proposes a filter method to select a subset of time series using an adaptation of existing nonparametric mutual information estimators based on the k-nearest neighbor and relies on the use of dynamic time warping dissimilarity to bring these methods to the time series scenario. Expand
Statistical modeling and signal selection in multivariate time series pattern classification
The algorithm uses a statistical causality modeling method to select relevant signals, and a correlation analysis method to remove redundant signals to select a subset of 9 signals that are independent and most relevant to the pattern class. Expand
Feature selection and hierarchical classifier design with applications to human motion recognition
This thesis examines the impact of feature selection and classification problem division on classification accuracy and complexity, and presents two methods for creating feature-selected hierarchical classifiers and input feature selection measures. Expand
Feature selection techniques with class separability for multivariate time series
The proposed method CSFS for feature selection from multivariate time series with the trace-based class separability criterion is compared with CLeVer, Corona and AGV on the UCI EEG data sets, and the simulation results substantiate the good performance of CSFS. Expand
An Iterative Feature Filter for Sensor Timeseries in Pervasive Computing Applications
An iterative filtering procedure is devised to reduce information redundancy measured in terms of timeseries cross-correlation and is capable of identifying non-redundant sensor sources in an unsupervised fashion even in presence of a large proportion of noisy features. Expand
Cross-correlation based clustering and dimension reduction of multivariate time series
The introduced graph based clustering approach provides a more balanced clustering than classic ones, and it is suitable to reveal dependencies and connections among performance metrics time series data. Expand


Autonomous Design of Experiments for Learning by Experimentation
This work presents a framework for integrating autonomous robotic experimentation into an open-ended learning loop to increase the robot's conceptual world knowledge autonomously and indicates how the goaloriented data generation enables machine learning algorithms to revise the failed prediction model. Expand
Feature subset selection and feature ranking for multivariate time series
This work proposes a family of novel unsupervised methods for feature subset selection from multivariate time series (MTS) based on common principal component analysis, termed CLeVer, which outperforms RFE, FC, and random selection by up to a factor of two in terms of the classification accuracy, while taking up to 2 orders of magnitude less processing time than RFE and FC. Expand
Discovery of Temporal Patterns. Learning Rules about the Qualitative Behaviour of Time Series
This paper considers the problem of deriving local weather forecasting rules that allow us to conclude from the qualitative behaviour of the air-pressure curve to the wind-strength, and discovers frequent temporal patterns in a single series of labeled intervals, which is called a state sequence. Expand
A Supervised Feature Subset Selection Technique for Multivariate Time Series
Feature subset selection (FSS) is a known technique to pre-process the data before performing any data mining tasks, e.g., classification and clustering. FSS provides both cost-effective predictorsExpand
Combining Unsupervised and Supervised Approaches to Feature Selection for Multivariate Signal Compression
A problem of learning from a database where each sample consists of several time series and a single response is considered, and it is demonstrated that such combination maintains small signal distortion rates, and ensures no increase in the prediction error in contrast to the unsupervised compression with the same reduction ratio. Expand
Iterative Deepening Dynamic Time Warping for Time Series
Almost all algorithms that operate on time series data need to compute the similarity between them, and Euclidean distance, or some extension or modification thereof, is typically used. Expand
Support vector channel selection in BCI
Recursive Feature Elimination and Zero-Norm Optimization which are based on the training of support vector machines (SVM) can provide more accurate solutions than standard filter methods for feature selection for EEG channels. Expand
An Introduction to Variable and Feature Selection
The contributions of this special issue cover a wide range of aspects of variable selection: providing a better definition of the objective function, feature construction, feature ranking, multivariate feature selection, efficient search methods, and feature validity assessment methods. Expand
Feature selection using principal feature analysis
A novel method for dimensionality reduction of a feature set by choosing a subset of the original features that contains most of the essential information, using the same criteria as PCA is proposed, and is called Principal Feature Analysis (PFA). Expand
A comparison of DFT and DWT based similarity search in time-series databases
The feasibility of replacing DFT by DWT is explored with a comprehensive analysis of the DFT and DWT as matching functions in time-series databases and the results show that although the DWT based technique has several advantages, it does not reduce relativ e matching error and does not increase query precision in similarity searc h as suggested by previous works. Expand