Conference Paper

Object-Based Activity Recognition with Heterogeneous Sensors on Wrist.

DOI: 10.1007/978-3-642-12654-3_15 In proceeding of: Pervasive Computing, 8th International Conference, Pervasive 2010, Helsinki, Finland, May 17-20, 2010. Proceedings
Source: DBLP

ABSTRACT This paper describes how we recognize activities of daily living (ADLs) with our designed sensor device, which is equipped
with heterogeneous sensors such as a camera, a microphone, and an accelerometer and attached to a user’s wrist. Specifically,
capturing a space around the user’s hand by employing the camera on the wrist mounted device enables us to recognize ADLs
that involve the manual use of objects such as making tea or coffee and watering plant. Existing wearable sensor devices equipped
only with a microphone and an accelerometer cannot recognize these ADLs without object embedded sensors. We also propose an
ADL recognition method that takes privacy issues into account because the camera and microphone can capture aspects of a user’s
private life. We confirmed experimentally that the incorporation of a camera could significantly improve the accuracy of ADL
recognition.

0 Bookmarks
 · 
48 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes an activity recognition method that models an end user’s activities without using any labeled/unlabeled acceleration sensor data obtained from the user. Our method employs information about the end user’s physical characteristics such as height and gender to find and select appropriate training data obtained from other users in advance. Then, we model the end user’s activities by using the selected labeled sensor data. Therefore, our method does not require the end user to collect and label her training sensor data. In this paper, we propose and test two methods for finding appropriate training data by using information about the end user’s physical characteristics. Moreover, our recognition method improves the recognition performance without the need for any effort by the end user because the method automatically adapts the activity models to the end user when it recognizes her unlabeled sensor data. We confirmed the effectiveness of our method by using 100 h of sensor data obtained from 40 participants.
    Personal and Ubiquitous Computing 03/2013; 17(3). · 1.13 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Activity recognition is a key technology for realizing ambient assisted living applications such as care of the elderly and home automation. This paper proposes a new activity recognition method that employs hand-worn magnetic sensors to recognize a broad range of activities ranging from simple activities that involve hand movements such as walking and running to the use of portable electrical devices such as cell phones and cameras. We sense magnetic fields emitted by electrical devices and the earth with hand-worn sensors, and recognize what a user is doing or which electrical device the user is employing. We frequently use a large number of different electrical devices in our daily lives, and so we can estimate high-level daily activities by recognizing their use. Our approach permits us to recognize a range extending from low-level simple activities to high-level activities that relate to the hands without the need to attach any sensors to the electrical devices.
    Personal and Ubiquitous Computing 08/2013; · 1.13 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: We propose a new activity recognition system for the daily activity by using a generative/discriminative hybrid model that can learn an activity classification model with small quantities of training data by sharing training data among different activity classes. Many existing activity recognition studies employ a supervised machine learning approach and thus require an end user's labeled training data, this approach places a large burden on the user. In this study, we assume that a user wears sensors (accelerometers) on several parts of the body such as the wrist, waist, and thigh, and by sharing sensor data obtained from only selected accelerometers (e.g., only waist and thigh sensors) among two different activity classes based on a sensor data similarity measure, the quantities of training data can be increased. For further reduction of the burden on the user, we also adopt semi-supervised approach to train the classifier in our study.
    Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publication; 09/2013

Full-text (2 Sources)

View
21 Downloads
Available from
May 31, 2014