Falls and fall-related injuries are major incidents, especially for elderly people, which often mark the onset of major deterioration of health. More than one-third of home-dwelling people aged 65 or above and two-thirds of those in residential care fall once or more each year. Reliable fall detection, as well as prevention, is an important research topic for monitoring elderly living alone in residential or hospital units. The aim of this study is to review the existing fall detection systems and some of the key research challenges faced by the research community in this field. We categorize the existing platforms into two groups: wearable and ambient devices; the classification methods are divided into rule-based and machine learning techniques. The relative merit and potential drawbacks are discussed, and we also outline some of the outstanding research challenges that emerging new platforms need to address.

No abstract

Abstract. The use of vision based algorithms in minimally invasive surgery has attracted significant attention in recent years due to its potential in providing in situ 3D tissue deformation recovery for intra-operative surgical guidance and robotic navigation. Thus far, a large number of feature descriptors have been proposed in computer vision but direct application of these techniques to minimally invasive surgery has shown significant problems due to free-form tissue deformation and varying visual appearances of surgical scenes. This paper evaluates the current state-of-the-art feature descriptors in computer vision and outlines their respective performance issues when used for deformation tracking. A novel probabilistic framework for selecting the most discriminative descriptors is presented and a Bayesian fusion method is used to boost the accuracy and temporal persistency of soft-tissue deformation tracking. The performance of the proposed method is evaluated with both simulated data with known ground truth, as well as in vivo video sequences recorded from robotic assisted MIS procedures.

No abstract

This paper presents a new design of a wireless sensor glove developed for American Sign Language fingerspelling gesture recognition. Five contact sensors are installed on the glove, in addition to five flex sensors on the fingers and a 3D accelerometer on the back of the hand. Each pair of flex and contact sensors are combined into the same input channel on the BSN node in order to save the number of channels and the installation area. After which, the signal is analyzed and separated back into flex and contact features by software. With electrical contacts and wirings made of conductive fabric and threads, the glove design has become thinner and more flexible. For validation, ASL fingerspelling gesture recognition experiments have been performed on signals collected from six speech-impaired subjects and a normal subject. With the new sensor glove design, the experimental results have shown a significant increase in classification accuracy.

No abstract

In high-density road networks, with each vehicle broadcasting multiple messages per second, the arrival rate of safety messages can easily exceed the rate at which digital signatures can be verified. Since not all messages can be verified, algorithms for selecting which messages to verify are required to ensure that each vehicle receives appropriate awareness about neighbouring vehicles. This paper presents a novel scheme to select important safety messages for verification in vehicular ad hoc networks (VANETs). The proposed scheme uses location and direction of the sender, as well as proximity and relative-time between vehicles, to reduce the number of irrelevant messages verified (i.e., messages from vehicles that are unlikely to cause an accident). Compared with other existing schemes, the analysis results show that the proposed scheme can verify messages from nearby vehicles with lower inter-message delay and reduced packet loss and thus provides high level of awareness of the nearby vehicles.

No abstract