Redirigiendo al acceso original de articulo en 15 segundos...
Inicio  /  Informatics  /  Vol: 5 Par: 3 (2018)  /  Artículo
ARTÍCULO
TITULO

Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models

Martin Jänicke    
Bernhard Sick and Sven Tomforde    

Resumen

Personal wearables such as smartphones or smartwatches are increasingly utilized in everyday life. Frequently, activity recognition is performed on these devices to estimate the current user status and trigger automated actions according to the user?s needs. In this article, we focus on the creation of a self-adaptive activity recognition system based on inertial measurement units that includes new sensors during runtime. Starting with a classifier based on Gaussian Mixture Models, the density model is adapted to new sensor data fully autonomously by issuing the marginalization property of normal distributions. To create a classifier from that, label inference is done, either based on the initial classifier or based on the training data. For evaluation, we used more than 10 h of annotated activity data from the publicly available PAMAP2 benchmark dataset. Using the data, we showed the feasibility of our approach and performed 9720 experiments, to get resilient numbers. One approach performed reasonably well, leading to a system improvement on average, with an increase in the F-score of 0.0053, while the other one shows clear drawbacks due to a high loss of information during label inference. Furthermore, a comparison with state of the art techniques shows the necessity for further experiments in this area.

 Artículos similares

       
 
Jounghoon Lim, Jinkee Kim and Jong Pal Kim    
A system has been developed to remotely, continuously, and quantitatively measure the physiological activity of trees. The developed tree physiological activity monitoring (TPAM) system is equipped with electrical impedance, temperature, and light intens... ver más
Revista: Applied Sciences

 
Olga. A. Glazunova, Konstantin V. Moiseenko and Tatyana V. Fedorova    
As a toxic xenobiotic compound, the anthraquinone dye Remazol Brilliant Blue R (RBBR) poses a serious threat to aquatic ecosystems. In the present study, the ability of Trametes hirsuta to remove RBBR from the medium was investigated, and the role of ads... ver más
Revista: Water

 
Suhee Jo, Ryeonggu Kwon and Gihwon Kwon    
GitHub serves as a platform for collaborative software development, where contributors engage, evolve projects, and shape the community. This study presents a novel approach to analyzing GitHub activity that departs from traditional methods. Using Discre... ver más
Revista: Applied Sciences

 
Francesco Caridi, Antonio Francesco Mottese, Giuseppe Paladini, Santina Marguccio, Maurizio D?Agostino, Alberto Belvedere, Domenico Majolino and Valentina Venuti    
In this article, an investigation into the natural radioactivity content in natural inorganic pigments was carried out, together with the assessment of the radiological health risk for the public related to external exposure to ionizing radiations, via H... ver más
Revista: Applied Sciences

 
Rehan Masood    
Prefabricated construction is expanding and taking over traditional construction with more intervention of prefabricated building elements. Despite prefabricated construction reducing health and safety risks compared to conventional construction, there i... ver más
Revista: Applied Sciences