Christl Lauterbach

Human tracking and identification using a sensitive floor and wearable accelerometers

We describe a method for user tracking and localization based on textile capacitive sensor arrays placed under the floor. The sensor array is a commercial product (SensFloor®) that can be installed under any standard floor type (from carpet to stone) and is able to detect objects (including the users foot) being placed on it. The challenges addressed in this paper are (1) how to map sequences of such signals onto user trajectories and (2) how to correlate the steps detected by the SensFloor system with the step detection based on a wearable accelerometer as means of user identification. Footstep detection is performed online on the devices, which are seamlessly integrated with the floors wireless sensor network. Initial experiments performed over a week in a real life office environment show the ability to track multiple humans and to identify up to three users walking in a narrow corridor at the same time.

Large-area wireless sensor system based on smart textiles

The SensFloor® is a textile-based large-area sensor system which is installed beneath the floor. It is able to detect people moving across the floor, calculating their trajectories and distinguishes between foot steps and a fall. It enables a variety of different applications like control of automatic doors, intrusion alarm and activity monitoring.

SensFloor® and NaviFloor®: Robotics Applications for a Large-Area Sensor System

The following chapter describes two systems, which both are perfect examples for ambient intelligence: sensor electronics, which is invisibly integrated into the floor. The first system comprises active sensors with high spatial resolution. It is able to detect people walking across the floor and recognizes peoples location and movement behaviour. While the main application domains are Ambient Assisted Living AAL, health care, security systems and home automation, several robotics applications are possible and have been investigated already. The second system serves for localizing moving objects such as robots, wheelchairs or hospital beds by means of passive RFID tags in the floor and an active RFID reader attached to the moving object. In the following, we describe the technical details of the two systems and robotics applications, which have already been realized or are under development.

Learning Behavioural Routines for Early Detection of Health Changes

A persons daily routine is a valuable early indicator of a changing health status. Ageing diseases in an early stage have an impact on measurable behaviours like sleeping times and quality, consistency of activity sequences and gait characteristics. Unfortunately, these interesting parameters of daily routine are hard to assess. In this work a technical system is proposed that is capable of detecting those changes in indoor daily routine automatically, unobtrusively and over long periods of time. The system relies on a combination of various sensors, including a novel capacitance sensing system covering large areas in the home environment, that is capable of detecting the locations of persons. A processing scheme is proposed to extract behavioural information from the sensor data, which is fed into a learning algorithm that internally represents typical patterns, and outputs a measure for the divergence of current behaviour from typical behaviour. As a noticeable feature, no interaction with the patient is required.

Recognising Gait Patterns of People in Risk of Falling with a Multi-layer Perceptron

We present an approach to estimate a person’s risk of falling by analysing gait recordings from a 6 m walk on a sensor floor. The risk of falls correlates with certain parameters of the human gait. Although these parameters are not measured directly with this sensor, their information is reflected in the data. The sensor floor works with a capacitance measurement principle and is sensitive to contact, such that persons standing, walking or lying on the floor are recognisable. In a preprocessing step, the person’s position is determined from the sensor data and the spread of contact points calculated. This spread implicitly contains the step sizes for the step phase in which two contact points are present. For each experiment, the distribution of occurring spreads is binned and taken as an input feature vector to a feed-forward perceptron. The neural network was trained by backpropagation with gait recordings from persons in low risk of falling and persons in high risk of falling. In the dataset, subjects were labelled as being in high risk of falling based on the prevalence of diseases, falls that already happened, and expert opinions. Though in this setup the data was recorded within a controlled environment, the results are transferable to larger installations and long-term observation periods.

AAL Functions for Home Care and Security

Abstract We describe a holistic AAL concept for senior residences that is based on a large-area sensor floor. This system provides general home-automation functions such as light control, intrusion alarm and energy saving. However, advanced homecare features such as activity monitoring, fall detection and the discovery of changes in daily routines assist the resident and support the carer. After explaining the components and general working principle of the system, we describe how these applications are realized in practice. The focus lays on the unobtrusiveness, flexibility and multifunctionality of the solution.

Estimating a person's age from walking over a sensor floor

Ageing has an effect on many parameters of the physical condition, and one of them is the way a person walks. This property, the gait pattern, can unintrusively be observed by letting people walk over a sensor floor. The electric capacitance sensors built into the floor deliver information about when and where feet get into close proximity and contact with the floor during the phases of human locomotion. We processed gait patterns recorded this way by extracting a feature vector containing the discretised distribution of occurring geometrical extents of significant sensor readings. This kind of feature vector is an implicit measure encoding the ratio of swing-to stance phase timings in the gait cycle and representing how cleanly the leg swing is performed. We then used the dataset to train a Multi-Layer Perceptron to perform regression with the age of the person as the target value, and the feature vector as input. With this method and a dataset size of 142 persons recorded, we achieved a mean absolute error of approximately 10 years between the true age and the estimated age of the person. Considering the novelty of our approach, this is an acceptable result. The combination of a floor sensor and machine learning methods for interpreting the sensor data seems promising for further research and applications in care and medicine.