: This thesis applies neural network feature selection techniques to multivariate time series data to improve prediction of a target time series. Two approaches to feature selection are used. First, a subset enumeration method is used to determine which financial indicators are most useful for aiding in prediction of the S&P 500 futures daily price. The candidate indicators evaluated include RSI, Stochastics and several moving averages. Results indicate that the Stochastics and RSI indicators result in better prediction results than the moving averages. The second approach to feature selection is calculation of individual saliency metrics. A new decision boundary-based individual saliency metric, and a classifier independent saliency metric are developed and tested. Ruck's saliency metric, the decision boundary based saliency metric, and the classifier independent saliency metric are compared for a data set consisting of the RSI and Stochastics indicators as well as delayed closing price values. The decision based metric and the Ruck metric results are similar, but the classifier independent metric agrees with neither of the other metrics. The nine most salient features, determined by the decision boundary based metric, are used to train a neural network and the results are presented and compared to other published results. (AN)

/pdf/nonlinear-time-series-analysis-1j3a35n4y3.pdf

Nonlinear Time Series Analysis.

Cochrane review, hvor hensikten var a vurdere effekten av intervensjoner designet for reduksjon av fall blant eldre mennesker i sykehjem og sykehus.

Interventions for preventing falls in older people in care facilities and hospitals

/pdf/analysis-of-observed-chaotic-data-3spe9uweeb.pdf

Analysis of observed chaotic data

Formation and control of optimal trajectory in human multijoint arm movement : minimum torque-change model

Self-Organized Criticality

Fractal analyses for 'short' time series: A re-assessment of classical methods

On the use of sample entropy to analyze human postural sway data.

In the light of factories of the future, to ensure productive and safe interaction between robot and human coworkers, it is imperative that the robot extracts the essential information of the coworker. We address this by designing a reliable framework for real-time safe human-robot collaboration, using static hand gestures and 3D skeleton extraction. OpenPose library is integrated with Microsoft Kinect V2, to obtain a 3D estimation of the human skeleton. With the help of 10 volunteers, we recorded an image dataset of alpha-numeric static hand gestures, taken from the American Sign Language. We named our dataset OpenSign and released it to the community for benchmarking. Inception V3 convolutional neural network is adapted and trained to detect the hand gestures. To augment the data for training the hand gesture detector, we use OpenPose to localize the hands in the dataset images and segment the backgrounds of hand images, by exploiting the Kinect V2 depth map. Then, the backgrounds are substituted with random patterns and indoor architecture templates. Fine-tuning of Inception V3 is performed in three phases, to achieve validation accuracy of 99.1% and test accuracy of 98.9%. An asynchronous integration of image acquisition and hand gesture detection is performed to ensure real-time detection of hand gestures. Finally, the proposed framework is integrated in our physical human-robot interaction library OpenPHRI. This integration complements OpenPHRI by providing successful implementation of the ISO/TS 15066 safety standards for “safety rated monitored stop” and “speed and separation monitoring” collaborative modes. We validate the performance of the proposed framework through a complete teaching by demonstration experiment with a robotic manipulator.

A Real-time Human-Robot Interaction Framework with Robust Background Invariant Hand Gesture Detection

Dynamical structure of center of pressure fluctuations in elderly people.

We investigate postural sway data dynamics in older adult fallers and non-fallers. Center of pressure (COP) signals were recorded during quiet standing in 28 older adults. The subjects were divided in two groups: with and without history of falls. COP time series were analyzed using recurrence quantification analysis (RQA) in both anteroposterior and mediolateral (ML) directions. Classical stabilometric variables (path length and range) were also computed. The results showed that RQA outputs quantifying predictability of COP fluctuations and Shannon entropy of recurrence plot diagonal line length distribution, were significantly higher in fallers, only for ML direction. In addition, the range of ML COP signals was also significantly higher in fallers. This result is in accordance with some findings of the literature and could be interpreted as an increased hip strategy in fallers. The RQA results seem coherent with the theory of loss of complexity with aging and disease. Our results suggest that RQA is a promising approach for the investigation of COP fluctuations in a frail population.

Sofiane Ramdani

Papers

Fractal analyses for 'short' time series: A re-assessment of classical methods

On the use of sample entropy to analyze human postural sway data.

A Real-time Human-Robot Interaction Framework with Robust Background Invariant Hand Gesture Detection

Dynamical structure of center of pressure fluctuations in elderly people.

Recurrence Quantification Analysis of Human Postural Fluctuations in Older Fallers and Non-fallers