Gudrun Stockmanns

A novel approach to creating artificial training and test data for an HMM based posture recognition system

Demographic change in the next few years will lead to a pronounced disparity in generation distribution. Hence there is a need to develop intelligent systems to support and maintain the autonomy of the elderly at home. A high priority in this case assumes the preparation-free acquisition of vital signs and patient parameters in long-term monitoring systems to detect early changes or deterioration in health. It is thus possible to initiate treatment of a disease at an early stage. One way to carry out a long-term monitoring of vital signs at home is based on the functionalization of furniture, for example, through the use of suitable sensors in chairs [1] and beds [2, 3] to derive various patient parameters. In addition to monitoring basic parameters, e.g. the heart rate and respiratory activity, it is also possible to access information regarding motion or sleep patterns by means of pattern recognition systems. In addition to the challenge of building a suitable pattern recognition system there is a need for corresponding training data to create reference patterns. Typically, the necessary sensor data for the reference pattern training is generated in time-consuming sessions with real people. In this paper, a novel approach is presented, which provides a multi-stage model to create artificial training or test data. The model can be used as a supporting tool in the development of posture recognition systems and to create artificial data for training and testing.

An HMM-based averaging approach for creating mean motion data from a full-body Motion Capture system to support the development of a biomechanical model

Abstract Motion capture systems or MoCap systems are used for game development and in the field of sports for the assessment and digitalization of human movement. Furthermore, MoCap systems are also used in the medical and therapeutic field for the analysis of human movement patterns. As examples gait analysis or examination of the musculoskeletal system and its function should be mentioned. Most application relate to a specific person and their movement or to the comparison of movements of different people. Within the scope of this paper an averaged motion sequence is supposed to be generated from MoCap data in order to be able to use it in the field of biomechanical modeling and simulation. For the averaging of individual movement sequences of different persons a Hidden Markov Model (HMM) based approach is presented.

MoveHN-A database to support the development of motion based biosignal processing systems

In the field of signal processing, pattern recognition and also modeling and simulation, it is often necessary to use large data sets. These allow reliable, independent and test case spanning development of algorithms or even of complete systems. The data is usually taken from existing data sets such as TIMIT for speech recognition and processing or EPILEPSIAE to develop algorithms for epileptic seizure prediction, to give just two examples. Apart from the fact that some of these databases imply a considerable cost factor and thus are not accessible to all research groups, even greater problems arise if no data is available at all. In the field of speech recognition, this problem was solved more or less by creating databases. In the area of biosignal processing with a focus on the functionalization of furniture for care and clinical facilities, there is still a need for large data sets. This was also the case with biomechanical modeling of functionalized furniture, since up to now none or few data on the human movement sequences were available. In order to overcome this deficiency, the following paper presents a new database of motion patterns, which is intended to support the development of algorithms for motion detection as well as modeling biosignal processing. The database can be used and downloaded by any interested researcher for free.

Improvement of a multi-stage model for the modeling of a functionalized nursing bed as support for the sensor-assisted function-alization of furniture in the hospital and care sector

Abstract Development of preparation-free functionalized furniture based patient monitoring systems for use in the area of home- or stationary- care is often empirically driven. In particular, functionalization of furniture by means of different sensors is strongly affected by this development methodology. As a result, the systems are often not extensive-ly extendable or cannot be optimized because basic mechanisms are not comprehensible. In order to support development or optimization, a modelling approach is often useful. Thus, using a more comprehensive approach the required sensitivity of the sensors as well as their position in the system can be derived from a simulation model. In order to solve this problem, a multi-stage model was introduced at the BMT conference in 2014 by the authors, which allows the designer to model the entire system. The model has been extended and improved in the meantime and the achieved progress is presented in this work. The presented modelling approach can be divided into three main components. These are the person under supervision, the furniture (in our case a nursing bed) and the sensors (force measuring cells) which are modelled separately. In this work the main focus will be on improving the modelling of the human movement process and its implementation. Furthermore, the modelling of the sensor behavior in the nursing bed is described in detail with regard to their oscillation behavior and the influence on the model.