Ilkka Korhonen

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.

EEG spectral entropy, heart rate, photoplethysmography and motor responses to skin incision during sevoflurane anaesthesia.

Background:  Analgesia is a part of balanced anaesthesia, but direct indicators of nociception do not exist. We examined the relationship between motor reactions and physiological variables during skin incision in sevoflurane anaesthesia and hypothesized that nociception could be detected and graded by significant changes in these variables.

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.

Bridging the physical and virtual worlds by local connectivity-based physical selection

The prevalent visions of ambient intelligence emphasise natural interaction between user and functions and services embedded in the environment or available through mobile devices. In these scenarios the physical and virtual worlds seamlessly gear into each other, making crossing the border between these worlds natural or even invisible to the user. The bottleneck in reaching these scenarios appear in the natural mapping between the physical objects and their virtual counterparts. The emergence of local connectivity in mobile devices opens possibilities for implementing novel user interface paradigms to enhance this mapping. We present physical selection paradigm for implementing an intuitive human technology interaction for mobile devices. In order to demonstrate the feasibility of the paradigm we implemented two experimental set-ups using commercially available smart phones with IrDA connectivity. The experiments involved selecting a website by physically pointing at its symbol and making a phone call by pointing at an icon representing the person to be called. In tentative user experiments the physical selection method was more time-efficient and it was perceived more positively by the users than a conventional method.

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

IST Vivago/spl reg/ - an intelligent social and remote wellness monitoring system for the elderly

Increasing life expectancy accompanied with decreasing dependency ratio in developed countries calls for new solutions to support independent living of the elderly. IST Vivago/spl reg/ is a novel intelligent social alarm system also providing continuous remote monitoring of the users activity level. The system is based on wireless sensing technology, telecommunications, and intelligent signal processing. In this paper we describe the system and provide application examples of the system.