Abstract. In this work, algorithms are developed and evaluated to detect physical activities from data acquired using five small biaxial accelerometers worn simultaneously on different parts of the body. Acceleration data was collected from 20 subjects without researcher supervision or observation. Subjects were asked to perform a sequence of everyday tasks but not told specifically where or how to do them. Mean, energy, frequency-domain entropy, and correlation of acceleration data was calculated and several classifiers using these features were tested. Decision tree classifiers showed the best performance recognizing everyday activities with an overall accuracy rate of 84%. The results show that although some activities are recognized well with subject-independent training data, others appear to require subject-specific training data. The results suggest that multiple accelerometers aid in recognition because conjunctions in acceleration feature values can effectively discriminate many activities. With just two biaxial accelerometers – thigh and wrist – the recognition performance dropped only slightly. This is the first work to investigate performance of recognition algorithms with multiple, wire-free accelerometers on 20 activities using datasets annotated by the subjects themselves. 1

Achieving context-aware computer systems requires that computers can automatically recognize what people are doing. In this work, algorithms are developed and evaluated to detect physical activities from data acquired using five small accelerometers worn simultaneously on different parts of the body. Acceleration data was collected from twenty subjects in both laboratory and semi-naturalistic environments. For semi-naturalistic data, subjects were asked to perform a sequence of everyday tasks outside of the laboratory. Mean, energy, frequency-domain entropy, and correlation of acceleration data was calculated over 6.71 s sliding windows. Decision table, nearest neighbor, decision tree, and Naive Bayesian classifiers were tested on these features. Classification results using individual training and leave-one-subject-out validation were compared. Leave-one-subject-out validation with decision tree classifiers

Abstract—Walking speed is an important component in energy expenditure. We present the use of Gaussian Process based Regression (GPR), a non-linear, non-parametric regression framework to estimate walking speed using data obtained from a single on-body sensor worn on the right hip. We compare the performance of GPR vis-a-vis Bayesian Linear Regression (BLR) and Least-Squares regression (LSR) in estimating treadmill walking speeds. We also study the effects of using treadmill walking in predicting overground walking speeds and that of combining data from more than one person to predict overground walking speed.

As computer systems become ubiquitously embedded in our environment, computer applications must be increasingly aware of user context. In order for these systems to interact with users in a meaningful and unobtrusive way, such as delivering important reminders at an appropriate time, their interfaces must be contextually-aware. This vision of future computer systems and the insight that the implementation of contextually-aware systems requires contextually-aware analysis and development tools has motivated the two primary contributions of this work. First, a Context-Aware Experience Sampling Tool has been designed, implemented, and tested. Second, this tool has been used to develop an algorithm that can detect transitions between human activities in office-like environments from planar accelerometer and heart rate data. The Context-Aware Experience Sampling Tool (CAES) is a program for Microsoft Pocket PC devices capable of gathering qualitative data, in the form of an electronic questionnaire, and quantitative data, in the form of sensor readings, from subjects.

The aims of the present study were: to identify the factors which are able to explain the performance in the 200 meters individual medley and 400 meters front crawl events in young swimmers, to model the performance in those events using non-linear mathematic methods through artificial neural networks (multi-layer perceptrons) and to assess the neural network models precision to predict the performance. A sample of 138 young swimmers (65 males and 73 females) of national level was submitted to a test battery comprising four different domains: kinanthropometric evaluation, dry land functional evaluation (strength and flexibility), swimming functional evaluation (hydrodynamics, hydrostatic and bioenergetics characteristics) and swimming technique evaluation. To establish a profile of the young swimmer non-linear combinations between preponderant variables for each gender and swim performance in the 200 meters medley and 400 meters font crawl events were developed. For this purpose a feed forward neural network was used (Multilayer Perceptron) with three neurons in a single hidden layer. The prognosis precision of the model (error lower than 0.8 % between true and estimated performances) is supported by recent evidence. Therefore, we consider that the neural network tool can be a good approach in the resolution of complex problems such as performance modeling and the talent identification in swimming and, possibly, in a wide variety of sports.