Juha Pärkkä

Activity classification using realistic data from wearable sensors

Automatic classification of everyday activities can be used for promotion of health-enhancing physical activities and a healthier lifestyle. In this paper, methods used for classification of everyday activities like walking, running, and cycling are described. The aim of the study was to find out how to recognize activities, which sensors are useful and what kind of signal processing and classification is required. A large and realistic data library of sensor data was collected. Sixteen test persons took part in the data collection, resulting in approximately 31 h of annotated, 35-channel data recorded in an everyday environment. The test persons carried a set of wearable sensors while performing several activities during the 2-h measurement session. Classification results of three classifiers are shown: custom decision tree, automatically generated decision tree, and artificial neural network. The classification accuracies using leave-one-subject-out cross validation range from 58 to 97% for custom decision tree classifier, from 56 to 97% for automatically generated decision tree, and from 22 to 96% for artificial neural network. Total classification accuracy is 82% for custom decision tree classifier, 86% for automatically generated decision tree, and 82% for artificial neural network

Detection of Daily Activities and Sports With Wearable Sensors in Controlled and Uncontrolled Conditions

Physical activity has a positive impact on peoples well-being, and it may also decrease the occurrence of chronic diseases. Activity recognition with wearable sensors can provide feedback to the user about his/her lifestyle regarding physical activity and sports, and thus, promote a more active lifestyle. So far, activity recognition has mostly been studied in supervised laboratory settings. The aim of this study was to examine how well the daily activities and sports performed by the subjects in unsupervised settings can be recognized compared to supervised settings. The activities were recognized by using a hybrid classifier combining a tree structure containing a priori knowledge and artificial neural networks, and also by using three reference classifiers. Activity data were collected for 68 h from 12 subjects, out of which the activity was supervised for 21 h and unsupervised for 47 h. Activities were recognized based on signal features from 3-D accelerometers on hip and wrist and GPS information. The activities included lying down, sitting and standing, walking, running, cycling with an exercise bike, rowing with a rowing machine, playing football, Nordic walking, and cycling with a regular bike. The total accuracy of the activity recognition using both supervised and unsupervised data was 89% that was only 1% unit lower than the accuracy of activity recognition using only supervised data. However, the accuracy decreased by 17% unit when only supervised data were used for training and only unsupervised data for validation, which emphasizes the need for out-of-laboratory data in the development of activity-recognition systems. The results support a vision of recognizing a wider spectrum, and more complex activities in real life settings.

Health monitoring in the home of the future

We discuss health monitoring as a potential application field for wearable sensors. We present some usage models for health monitoring and discuss the technical requirements for the health-monitoring system based on wearable and ambient sensors, which measure health-related data in daily environments of the users or patients. The presentation is by no means complete, but it aims to give an idea of the system-level issues to be considered for real applications. The technology in this area is rapidly developing, and without doubt we will evidence emergence of these applications in the coming years in the market.

Mobile Diary for Wellness Management—Results on Usage and Usability in Two User Studies

The prevalence of lifestyle-related health problems is increasing rapidly. Many of the diseases and health risks could be prevented or alleviated by making changes toward healthier lifestyles. We have developed the Wellness Diary (WD), a concept for personal and mobile wellness management based on Cognitive-Behavioral Therapy (CBT). Two implementations of the concept were made for the Symbian Series 60 (S60) mobile phone platform, and their usability, usage, and acceptance were studied in two 3-month user studies. Study I was related to weight management and study II to general wellness management. In both the studies, the concept and its implementations were well accepted and considered as easy to use and useful in wellness management. The usage rate of the WD was high and sustained at a high level throughout the study. The average number of entries made per day was 5.32 (SD = 2.59, range = 0-14) in study I, and 5.48 (SD = 2.60, range = 0-17) in study II. The results indicate that the WD is well suited for supporting CBT-based wellness management.

A wireless wellness monitor for personal weight management

Despite increasing possibilities for the citizen to play a more active role in personal health management, the use of Internet based health applications remains limited. Poor usability, limited personalization, and problems with security and accessibility often frustrate a continued use. The paper presents a possible solution by actively using wireless communications and ad-hoc networking techniques to minimize the users efforts in using the application. Overweightness is a widespread and increasing problem in western countries. There are indications that self-monitoring combined with guidelines provide a good basis for personal weight management. The wireless wellness monitor implements a self-monitoring and guidance system using Bluetooth- and Jini-based networking. A scale, heart rate monitor, mobile terminal (personal digital assistant or WAP-enabled digital cellular phone), and home server communicate locally via Bluetooth. Internet based communications take care of remote use. The set-up allows us to investigate the behavior and use cases based on equipment and protocols that are expected to be in general use in the coming years. Thus, the system provides a useful test-bed for evaluating new techniques that may bring personal health management to a new level.

Empowering Citizens for Well-being and Chronic Disease Management With Wellness Diary

Chronic conditions closely related to lifestyles are the major cause of disability and death in the developed world. Behavior change is the key to managing well-being and preventing and managing chronic diseases. Wellness diary (WD) is a mobile application designed to support citizens in learning about their behavior, and both making and maintaining behavior changes. WD has been found acceptable, useful, and suitable for long-term use as a part of an intervention. When used independently, however, it does not seem to have enough engaging and motivating features to support adoption and long-term commitment. The main improvement needs identified based on a review of WD-related studies were: personalization of the application to individual needs, increasing motivation during early use, maintaining motivation, and aiding in relapse recovery in long-term use. We present concepts to improve the personalization of WD as well as improvements to the feedback and interpretation of the self-observation data. We also present usage models on how this type of mobile application could be utilized.

Application of near field communication for health monitoring in daily life.

We study the possibility of applying an emerging RFID-based communication technology, NFC (Near Field Communication), to health monitoring. We suggest that NFC is, compared to other competing technologies, a high-potential technology for short-range connectivity between health monitoring devices and mobile terminals. We propose practices to apply NFC to some health monitoring applications and study the benefits that are attainable with NFC. We compare NFC to other short-range communication technologies such as Bluetooth and IrDA, and study the possibility of improving the usability of health monitoring devices with NFC. We also introduce a research platform for technical evaluation, applicability study and application demonstrations of NFC

Advancing from offline to online activity recognition with wearable sensors

Activity recognition with wearable sensors could motivate people to perform a variety of different sports and other physical exercises. We have earlier developed algorithms for offline analysis of activity data collected with wearable sensors. In this paper, we present our current progress in advancing the platform for the existing algorithms to an online version, onto a PDA. Acceleration data are obtained from wireless motion bands which send the 3D raw acceleration signals via a Bluetooth link to the PDA which then performs the data collection, feature extraction and activity classification. As a proof-of-concept, the online activity system was tested with three subjects. All of them performed at least 5 minutes of each of the following activities: lying, sitting, standing, walking, running and cycling with an exercise bike. The average second-by-second classification accuracies for the subjects were 99%, 97%, and 82 %. These results suggest that earlier developed offline analysis methods for the acceleration data obtained from wearable sensors can be successfully implemented in an online activity recognition application.

Estimating Intensity of Physical Activity: A Comparison of Wearable Accelerometer and Gyro Sensors and 3 Sensor Locations

Automatic estimation of physical activity using wearable sensors can be used for promotion of a healthier lifestyle. In this study, accelerometers and gyroscopes attached to ankle, wrist and hip were used to estimate intensity of physical activity. The estimates are compared to metabolic equivalent (MET) obtained from a portable cardiopulmonary exercise testing system. Data from common everyday tasks and exercise were collected with 11 subjects. The tasks include, e.g., ironing, vacuuming, walking, running and cycling on exercise bicycle (ergometer). The strongest linear correlation with metabolic equivalent was obtained with the tri-axial accelerometer attached to the ankle (r=0.86).

Automatic feature selection for context recognition in mobile devices

In mobile devices there exist several in-built sensor units and sources which provide data for context reasoning. More context sources can be attached via wireless network connections. Usually, the mobile devices and the context sources are battery powered and their computational and space resources are limited. This sets special requirements for the context recognition algorithms. In this paper, several classification and automatic feature selection algorithms are compared in the context recognition domain. The main goal of this study is to investigate how much advantage can be achieved by using sophisticated and complex classification methods compared with a simple method that can easily be implemented in mobile devices. The main result is that even a simple linear classification algorithm can achieve a reasonably good accuracy if the features calculated from raw data are selected in a suitable way. Usually context recognition algorithms are fitted to a particular problem instance in an off-line manner and modifying methods for on-line learning is difficult or impossible. An on-line version of the Minimum-distance classifier is presented in this paper and it is justified that it leads to considerably higher classification accuracies compared with the static off-line version of the algorithm. Moreover, we report superior performance for the Minimum-distance classifier compared to other classifiers from the view point of computational load and power consumption of a smart phone.