logo
  
e-AR (ear-worn Activity Recognition) Sensor

The design of the e-AR sensor was inspired by the human inner ear. The human inner

ear consists of an auditory system (the cochlea) and a balancing (vestibular) system.  Within the vestibular system there are two sensory mechanisms, called the semicircular canals and the otoliths for sensing the rotational and translational motions. To emulate the sensory functions of the human vestibular system, the e-AR sensor is equipped with a MEMS (Micro Electro-Mechanical System) 3-axis accelerometer which is capable of detecting acceleration in 3 dimensions (up and down, left and right, back and forth). An accelerometer consists of a mass, and when the sensor is moved, the mass moves. Electronic sensing components determine the acceleration. By positioning the accelerometer on the ear, the e-AR sensor can pick up similar information to the vestibular system, and this records the posture and activities of the user.



Pervasive Sensing for Sport Training

In situ measurements of athletes' physiological parameters during training and competitions are essential for identifying the underlying elements which affects sport performances. To enable real-time continuous measurements of athletes' performance indices during training and competitions, a number of pervasive sensing technologies have been introduced under the ESPRIT (Elite Sport Performance Research in Training) Programme. Through working closely with sports governing bodies, technologies developed have been validated for different sport exemplars. Under the programme, different novel sensing technologies have been introduced from body worn biomotion sensors, wheel chair velocity and tracking system, to rowing blackbox, and video tracking system.
 


    Pervasive sensor for gait analysis

      Gait analysis is an important part of orthopedics, rehabilitation, sport medicine and biomechanics. To quantify gait, motion capture systems, electromyography (EMG) sensors and force plates (or foot pressure insoles) are commonly used to capture kinematics, muscle contraction, and Ground Reaction Force (GRF). To measure GRF, force plates or foot pressure insoles are commonly used; however, both systems are costly, thus limiting their use mainly to dedicated biomechanics laboratories. The measurements performed are also constrained to brief time periods which may or may not represent the normal walking/running conditions. A novel concept of an ear-worn sensor is introduced for pervasive sensing of GRF patterns, and a hierarchical Bayesian network is developed to estimate the planar force distribution from the raw e-AR sensor signals. The approach has been validated against commercially available foot pressure sensing insoles and it has been shown that the sensor can accurately estimate the plantar force distribution.


      Activity Recognition/Monitoring for Patient Care

         

        Fall detection/risk assessment

        • Marie Tolkiehn, Louis Atallah, Benny Lo and Guang-Zhong Yang, "Direction Sensitive Fall Detection Using a Triaxial Accelerometer and Barometric Pressure Sensor", To be appeared in EMBC'11, Boston, USA.
        • Rachel C. King, Louis Atallah, Charence Wong, Frank Miskelly and Guang-Zhong Yang, "Elderly Risk Assessment of Falls with BSN", In Proceedings of BSN 2010.

        Autonomic sensing
         

        Following the concept of ubiquitous computing, the computers will be further miniaturised and the number of computers per person will continue to grow.  It has envisaged that the cost of managing and administrating the vast number of computers will soon become a significant obstacle to the growth of the technology.

        Similarly, Body Sensor Networks and pervasive healthcare technologies will soon face the same problems, and managing the tiny sensors will be even more difficult, especially when they are capturing and handling crucial patient data. Based on the idea of autonomic computing, the concept of autonomic sensing has been proposed. The rationale behind the autonomic sensing is to develop a self-managed body sensor networks, such that no or minimal human intervention is required. To enable self-management, bio-inspired approaches have been proposed to emulate healing, protection, adaptation, etc., abilities of biological systems.

        Pervasive sensing for post-operative care
         
        Recent advances in endoscopic surgical technologies have greatly shortened the patient recovery period, and patients are often discharged a week or even days after an operation.  However, the early discharged patients are still at risk of complications. Due to the limited resources, only routine visits can be carried out by nurses or health visitors to monitor the progress of the recovery, and which could results in late discovery of complications. The pervasive network of body sensors have been proposed as a tool or a system to enable continuous monitoring of post-operative patients both in hospital and homecare settings such that complications or deteriorations can be detected at an early stage.

        Pervasive sensors for healthcare applications
        To facilitate the research on pervasive sensing for healthcare application, a number of physiological sensors were developed based on the BSN development platform, such as ECG sensors, heart rate strap, SpO2 sensor and PDA user interface.
         

        Body Sensor Networks Platform
        Recent advances in wireless sensor networks have facilitate the realisation of pervasive health monitoring for both homecare and hospital environments. The concept of Body Sensor Networks (BSN) has been introduced recently where miniaturised wearable or implantable wireless sensors are used for continuous monitoring of patients. To facilitate research and development in BSN, a BSN hardware development platform, called BSN node, is proposed by Imperial College London. With its compact, low power and flexible design, the BSN nodes provide a versatile developing environment for pervasive healthcare applications.