Dominik Schuldhaus

Hierarchical, Multi-Sensor Based Classification of Daily Life Activities: Comparison with State-of-the-Art Algorithms Using a Benchmark Dataset

Insufficient physical activity is the 4th leading risk factor for mortality. Methods for assessing the individual daily life activity (DLA) are of major interest in order to monitor the current health status and to provide feedback about the individual quality of life. The conventional assessment of DLAs with self-reports induces problems like reliability, validity, and sensitivity. The assessment of DLAs with small and light-weight wearable sensors (e.g. inertial measurement units) provides a reliable and objective method. State-of-the-art human physical activity classification systems differ in e.g. the number and kind of sensors, the performed activities, and the sampling rate. Hence, it is difficult to compare newly proposed classification algorithms to existing approaches in literature and no commonly used dataset exists. We generated a publicly available benchmark dataset for the classification of DLAs. Inertial data were recorded with four sensor nodes, each consisting of a triaxial accelerometer and a triaxial gyroscope, placed on wrist, hip, chest, and ankle. Further, we developed a novel, hierarchical, multi-sensor based classification system for the distinction of a large set of DLAs. Our hierarchical classification system reached an overall mean classification rate of 89.6% and was diligently compared to existing state-of-the-art algorithms using our benchmark dataset. For future research, the dataset can be used in the evaluation process of new classification algorithms and could speed up the process of getting the best performing and most appropriate DLA classification system.

Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data

Changes in gait patterns provide important information about individuals’ health. To perform sensor based gait analysis, it is crucial to develop methodologies to automatically segment single strides from continuous movement sequences. In this study we developed an algorithm based on time-invariant template matching to isolate strides from inertial sensor signals. Shoe-mounted gyroscopes and accelerometers were used to record gait data from 40 elderly controls, 15 patients with Parkinson’s disease and 15 geriatric patients. Each stride was manually labeled from a straight 40 m walk test and from a video monitored free walk sequence. A multi-dimensional subsequence Dynamic Time Warping (msDTW) approach was used to search for patterns matching a pre-defined stride template constructed from 25 elderly controls. F-measure of 98% (recall 98%, precision 98%) for 40 m walk tests and of 97% (recall 97%, precision 97%) for free walk tests were obtained for the three groups. Compared to conventional peak detection methods up to 15% F-measure improvement was shown. The msDTW proved to be robust for segmenting strides from both standardized gait tests and free walks. This approach may serve as a platform for individualized stride segmentation during activities of daily living.

Subsequence dynamic time warping as a method for robust step segmentation using gyroscope signals of daily life activities

The segmentation of gait signals into single steps is an important basis for objective gait analysis. Only a precise detection of step beginning and end enables the computation of step parameters like step height, variability and duration. A special challenge for the application is the accurateness of such an algorithm when based on signals from daily live activities. In this study, gyroscopes were attached laterally to sport shoes to collect gait data. For the automated step segmentation, subsequence Dynamic Time Warping was used. 35 healthy controls and ten patients with Parkinsons disease performed a four times ten meter walk. Furthermore 4 subjects were recorded during different daily life activities. The algorithm enabled counting steps, detecting precisely step beginning and end and rejecting other movements. Results showed a recognition rate of steps during ten meter walk exercises of 97.7% and in daily life activities of 86.7%. The segmentation procedure can be used for gait analysis from daily life activities and can constitute the basis for computation of precise step parameters. The algorithm is applicable for long-term gait monitoring as well as for analyzing gait abnormalities.

Real-Time ECG and EMG Analysis for Biking Using Android-Based Mobile Devices

We developed an application for Android-based mobile devices that enables a real-time calculation of heart rate and cadence for biking. Therefore, both ECG and EMG data are acquired in real time by Shimmer sensors and transmitted via Bluetooth, as well as processed and evaluated on the mobile device. The ECG algorithm is based on the Pan-Tompkins algorithm for QRS-Detection and offers a heart beat detection rate of more than 94%. The EMG algorithm offers a treadle detection rate of more than 91%. The applications range of features is complemented by GPS data for the calculation of speed and location information. It is available for download and can for example be used for controlling the users training status, for live training supervision and for the subsequent analysis of the various training runs.

A framework for early event detection for wearable systems

A considerable number of wearable system applications necessitate early event detection (EED). EED is defined as the detection of an event with as much lead time as possible. Applications include physiological (e.g., epileptic seizure or heart stroke) or biomechanical (e.g., fall movement or sports event) monitoring systems. EED for wearable systems is under-investigated in literature. Therefore, we introduce a novel EED framework for wearable systems based on hybrid Hidden Markov Models. Our study specifically targets EED based on inertial measurement unit (IMU) signals in sports. We investigate the early detection of high intensive soccer kicks, with the possible pre-kick adaptation of a soccer shoe before the shoe-ball impact in mind. We conducted a study with ten subjects and recorded 226 kicks using a custom IMU placed in a soccer shoe cavity. We evaluated our framework in terms of EED accuracy and EED latency. In conclusion, our framework delivers the required accuracy and lead times for EED of soccer kicks and can be straightforwardly adapted to other wearable system applications that necessitate EED.

Performance Comparison of Two Step Segmentation Algorithms Using Different Step Activities

Insufficient physical activity is the 4th leading risk factor for mortality. The physical activity of a person is reflected in the walking behavior. Different methods for the calculation of the accurate step number exists and most of them are evaluated using different walking speeds measured on a treadmill or using a small sample size of overground walking. In this paper, we introduce the BaSA (Basic Step Activities) dataset consisting of four different step activities (walking, jogging, ascending, and descending stairs) that were performed under natural conditions. We further compare two step segmentation algorithms (a simple peak detection algorithm vs. subsequence Dynamic Time Warping (sDTW)). We calculated a multivariate Analysis of Variance (ANOVA) with repeated measures followed by multiple dependent t-tests with Bonferroni correction to test for significant differences in the two algorithms. sDTW performed equally good compared to the peak detection algorithm, but was not considerably better. In further analysis, continuous, real walking signals with transitions from one step activity to the other step activity should be considered to investigate the adaptability of these two step segmentation algorithms.

Workshop on wearables for sports

Wearables are becoming mainstream technology, however there is still room for improvement in the sports domain of this field. Monitoring performance and collecting large scale data are of high interest among athletes - amateurs and professionals alike. The current state-of-the art wearable solutions for sports analysis are able to provide individual statistics to the user, however they have shortcomings in certain aspects, such as isolating and visualizing important information for the user, beyond statistics. This workshop focuses on the application of wearable technology in sports. We will explore novel ideas and application scenarios of how sensors and actuators are capable of supporting athletes in monitoring and improving their performance. We will discuss the design space of the domain by bringing together experts from various communities and exchanging ideas from different perspectives on wearables for sports applications. Participants will collaboratively produce sports related prototype applications.

Your personal movie producer: generating highlight videos in soccer using wearables

Manually browsing through high amount of sports videos, selecting interesting highlight scenes, and applying video effects are time-consuming and one major burden these days. Automatic approaches are preferred, but currently require high-quality TV broadcast material which is usually not available in recreational sports. Thus, the purpose of this paper was to develop a personal low-cost movie producer for highlight videos using wearables. The feasibility of the proposed approach was shown for soccer scenarios. The automatic highlight video generation included three contributions: (i) sensor-based full-instep kick detection and extraction of corresponding video segments, (ii) sensor-based ball speed estimation for provision of highlight-related metadata shown in the final video, and (iii) sensor-driven video effect generation. The proposed system was evaluated on eleven subjects which were equipped with inertial sensors in the cavity of soccer shoes. A mean sensitivity of 95.6 % and a mean absolute error of 7.7 km/h were achieved for the full-instep kick classification and the ball speed estimation, respectively. This personal movie producer based on wearables is a novel idea to provide recreational athletes with attractive automatically generated highlight videos in sports.