The electrocardiograms (ECGs) record the electrical activity of the heart and are used to diagnose many heart disorders. This paper proposes a two-stage feed forward neural network for ECG signal classification. The research is aimed at the design of an intelligent ECG diagnosis tool that can recognise heart abnormalities while reducing the complexity, cost, and response time of the system. A number of neural network architectures are designed and compared for their ability to classify six different heart conditions. Two network architectures based on one stage and two stage feed forward neural networks are chosen for this investigation. The training and testing ECG signals are obtained from MIT-BIH database. The network inputs are comprised of 12 ECG features and 13 compressed components of each heart beat signal. The performance of the different modules as well as the efficiency of the whole system is presented. Among different architectures, a proposed multi-stage network named NET_BST possesses the highest recognition rate of around 93%. Therefore, this network proves to be a suitable candidate in ECG signal diagnosis systems.

Background: Tablet computers are generally associated with an intuitive interface. The adoption and use of tablet computers within the early-stage dementia context could potentially assist in daily living and provide users with a source for leisure activities and social networking. As dementia mainly affects the older adult population, it is expected that many people with dementia and even their carers do not use tablet computers as part of their everyday living. Objective: This paper explores the usability of tablet computers within the early-stage dementia context as a source of leisure for people with dementia. The main advantage of the use of tablet computers in this manner is to provide carers some reprieve from the constant care and attention often required in caring for people with dementia. Methods: Seven-day in-home trials were conducted to determine whether people with early-stage dementia were -capable of using a tablet computer independently. Twenty-one people with early-stage dementia and carer dyads participated in the trial. Feedback was gathered through questionnaires from both the person with dementia and their carer regarding the use of a tablet computer as part of their everyday living. Results: Approximately half the participants with dementia were able to engage with and use the tablet computer independently, which proved to be helpful to their carers. No significant traits were observed to help identify those who were less likely to use a tablet computer. Carer relief was quantified by the amount of time participants with dementia spent using the device without supervision. Conclusions: The results and feedback from the trial provide significant insights to introducing new technology within the early-stage dementia context. Users' needs must be considered on a case-by-case basis to successfully facilitate the uptake of tablet computers in the dementia context. The trial has provided sufficient justification to further explore more uses of tablet computers in the dementia context, and not just for early-stage dementia.

Objectives: The objectives of this study were 2-fold: (1) to perform detailed analysis of cortical screw tightening stiffness during automated insertion, and (2) to determine the effect of 3 torque levels on the holding strength of the bone surrounding the screw threads as assessed by screw pullout. Methods: Ten pairs of ovine tibiae were used with 3 test sites spaced 20 mm apart centered along the shaft. One side of each pair was used for measuring ultimate failure torque (Tmax). These Tmax and bone-density values were used to predict Tmax at contralateral tibia sites. Screws were inserted and tightened to 50%, 70%, and 90% of predicted Tmax at the contralateral sites to encompass the average clinical level of torque (86% Tmax). Pullout tests were performed and maximum force values were normalized by cortical thickness. Results: Torque to failure tests indicated tightening to 86% Tmax occurs after yield and leads to an average 51% loss in stiffness. Normalized pullout strength for screws tightened to 50% Tmax, 70% Tmax, and 90% Tmax were 2525 ± 244, 2707 ± 280, and 2344 ± 346 N, respectively, with a significant difference between 70% Tmax and 90% Tmax groups (P < 0.05). Conclusions: Within the limitations of our study involving the testing of 1 type of screw purchase in ovine tibiae, results demonstrate that clinical levels of lag screw tightening (86% Tmax) are past the yield point of bone. Tightening to these high torque levels can cause damage leading to compromised holding strength. Further research is still required to establish the appropriate level of torque required for achieving optimal fracture fixation and healing.