Blog
About

187
views
0
recommends
+1 Recommend
1 collections
    4
    shares
      • Record: found
      • Abstract: found
      • Conference Proceedings: found
      Is Open Access

      Development of a Holistic System for Activity Classification Based on Multimodal Sensor Data

      , , ,

      Proceedings of the 32nd International BCS Human Computer Interaction Conference (HCI)

      Human Computer Interaction Conference

      4 - 6 July 2018

      Wearable Sensors, Human Activity Recognition, Machine Learning, Ubiquitous Computing

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          As the world of portable computers has evolved, mobile activity and mobility monitoring has become one of the major trends of recent years using widely used technologies such as smartphone sensors and wearables. These technologies are the basis for a wide range of applications in the areas of health monitoring, fitness games and telematics systems in vehicles. In the resulting use cases, the focus is on recognizing, differentiating and qualitatively evaluating different types of movements. The key factor in this context is a high degree of recognition accuracy in almost real time. Due to the ongoing development of mobile devices and the associated increase in performance, it is now possible to use the interfaces provided in mobile operating systems for the use of deep learning technologies. Due to the high availability of the end devices, new context-sensitive applications can be created, which can adapt the program logic to the current environment of a user.

          Related collections

          Most cited references 5

          • Record: found
          • Abstract: found
          • Article: found
          Is Open Access

          Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

          Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters’ influence on performance to provide insights about their optimisation.
            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Performance Analysis of Smartphone-Sensor Behavior for Human Activity Recognition

             Yufei Chen,  Chao Shen (2017)
              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Robust human activity recognition from depth video using spatiotemporal multi-fused features

                Bookmark

                Author and article information

                Contributors
                Conference
                July 2018
                July 2018
                : 1-4
                Affiliations
                Hochschule Mittweida

                Technikumplatz 17

                D-09648 Mittweida
                Article
                10.14236/ewic/HCI2018.167
                © Rolletschke et al. Published by BCS Learning and Development Ltd. Proceedings of British HCI 2018. Belfast, UK.

                This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

                Proceedings of the 32nd International BCS Human Computer Interaction Conference
                HCI
                32
                Belfast, UK
                4 - 6 July 2018
                Electronic Workshops in Computing (eWiC)
                Human Computer Interaction Conference
                Product
                Product Information: 1477-9358BCS Learning & Development
                Self URI (journal page): https://ewic.bcs.org/
                Categories
                Electronic Workshops in Computing

                Comments

                Comment on this article