Falls are a significant threat to the health and independence of elderly people and represent an enormous burden on the healthcare system. Successfully predicting falls could be of great help, yet this requires a timely and accurate fall risk assessment. Gait abnormalities are one of the best predictive signs of underlying locomotion conditions and precursors of falls. The advent of wearable sensors and wrist-worn devices provides new opportunities for continuous and unobtrusive monitoring of gait during daily activities, including the identification of unexpected changes in gait. To this end, we present in this paper a novel method for determining gait abnormalities based on a wrist-worn device and a deep neural network. It integrates convolutional and bidirectional long short-term memory layers for successful learning of spatiotemporal features from multiple sensor signals. The proposed method was evaluated using data from 18 subjects, who recorded their normal gait and simulated abnormal gait while wearing impairment glasses. The data consist of inertial measurement unit (IMU) sensor signals obtained from smartwatches that the subjects wore on both wrists. Numerous experiments showed that the proposed method provides better results than the compared methods, achieving 88.9% accuracy, 90.6% sensitivity, and 86.2% specificity in the detection of abnormal walking patterns using data from an accelerometer, gyroscope, and rotation vector sensor. These results indicate that reliable fall risk assessment is possible based on the detection of walking abnormalities with the use of wearable sensors on a wrist.

No abstract

Virtual Reality (VR) enables the simulation of ecologically validated scenarios, which are ideal for studying behaviour in controllable conditions. Physiological measures captured in these studies provide a deeper insight into how an individual responds to a given scenario. However, the combination of the various biosensing devices presents several challenges, such as efficient time synchronisation between multiple devices, replication between participants and settings, as well as managing cumbersome setups. Additionally, important salient facial information is typically covered by the VR headset, requiring a different approach to facial muscle measurement. These challenges can restrict the use of these devices in laboratory settings. This paper describes a solution to this problem. More specifically, we introduce the emteqPRO system which provides an all-in-one solution for the collection of physiological data through a multi-sensor array built into the VR headset. EmteqPRO is a ready to use, flexible sensor platform enabling convenient, heterogenous, and multimodal emotional research in VR. It enables the capture of facial muscle activations, heart rate features, skin impedance, and movement data—important factors for the study of emotion and behaviour. The platform provides researchers with the ability to monitor data from users in real-time, in co-located and remote set-ups, and to detect activations in physiology that are linked to arousal and valence changes. The SDK (Software Development Kit), developed specifically for the Unity game engine enables easy integration of the emteqPRO features into VR environments.Code available at: (https://github.com/emteqlabs/emteqvr-unity/releases)

No abstract