Wyniki wyszukiwania - BazTech

1

Klasyfikacja akcji nóg w szermierce z użyciem akcelerometru

Malawski F.

Elektronika : konstrukcje, technologie, zastosowania

|

2017

|

Vol. 58, nr 4

8--12

PL

Automatyczna analiza oraz klasyfikacja akcji w sporcie stanowi użyteczne narzędzie dla zawodników oraz trenerów. W niniejszej pracy zaprezentowano efektywną metodę klasyfikacji akcji nóg w szermierce z wykorzystaniem akcelerometru. Do opisu ruchu wykorzystano zarówno cechy czasowe jak i częstotliwościowe. Do wyboru podzbioru cech o największej sile dyskryminacyjnej zastosowano metody selekcji cech oparte o algorytmy AdaBoost oraz Lasso. Klasyfikację akcji zrealizowano w oparciu o metody DTW oraz SVM. Przeprowadzono badania eksperymentalne na dedykowanej bazie danych z akcjami nóg w szermierce, która zawiera trudne do klasyfikacji akcje o podobnej trajektorii, ale różnej dynamice ruchu. Metody zaproponowane w niniejszej pracy umożliwiają uzyskanie 70% skuteczności klasyfikacji.

EN

Automatic analysis and classification of actions in sports constitutes a useful tool for both athletes and coaches. In this paper we present an efficient method for classification of actions in fencing footwork by employing an accelerometer. Fencers’ motion is described by both time and frequency domain features. In order to select a relevant subset of features we employ feature selection methods, namely AdaBoost and Lasso. In the classification we use DTW and SVM algorithms. Experiments were conducted on a dedicated dataset with fencing footwork actions, which contains actions, which are difficult to classify, as they have similar trajectories and vary mostly in the dynamics of the motion. The proposed methods achieved recognition accuracy better than 70%.

2

Physical activity recognition by smartphones, a survey

Morales J., Akopian D.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 3

388--400

EN

Human activity recognition (HAR) from wearable motion sensor data is a promising research field due to its applications in healthcare, athletics, lifestyle monitoring, and computer–human interaction. Smartphones are an obvious platform for the deployment of HAR algorithms. This paper provides an overview of the state-of-the-art when it comes to the following aspects: relevant signals, data capture and preprocessing, ways to deal with unknown on-body locations and orientations, selecting the right features, activity models and classifiers, metrics for quantifying activity execution, and ways to evaluate usability of a HAR system. The survey covers detection of repetitive activities, postures, falls, and inactivity.

3

Relational Transformation-based Tagging for Activity Recognition

Landwehr N., Gutmann B., Thon I., Raedt L. de, Philipose M.

Fundamenta Informaticae

|

2008

|

Vol. 89, nr 1

111-129

EN

The ability to recognize human activities from sensory information is essential for developing the next generation of smart devices. Many human activity recognition tasks are - from a machine learning perspective-quite similar to tagging tasks in natural language processing. Motivated by this similarity, we develop a relational transformation-based tagging system based on inductive logic programming principles, which is able to cope with expressive relational representations as well as a background theory. The approach is experimentally evaluated on two activity recognition tasks and an information extraction task, and compared to Hidden Markov Models, one of the most popular and successful approaches for tagging.

4

Weighted ensemble boosting for robust activity recognition in video

Ivanov Y., Hamid R.

Machine Graphics and Vision

|

2006

|

Vol. 15, No. 3/4

415-427

EN

In this paper we introduce a novel approach to classifier combination, which we term Weighted Ensemble Boosting. We apply the proposed algorithm to the problem of activity recognition in video, and compare its performance to different classifier combination methods. These include Approximate Bayesian Combination, Boosting, Feature Stacking, and the more traditional Sum and Product rules. Our proposed Weighted Ensemble Boosting algorithm combines the Bayesian averaging strategy with the boosting framework, finding useful conjunctive feature combinations and achieving a lower error rate than the traditional boosting algorithm. The method demonstrates a comparable level of stability with respect to the classifier selection pool. We show the performance of our technique for a set of 6 types of classifiers in an office setting, detecting 7 classes of typical office activities.