BackgroundExercise is an important and effective approach to preventing falls in older people, but adherence to exercise participation remains a persistent problem. A unique purpose-built exercise park was designed to provide a fun but physically challenging environment to support exercise in a community setting. This project is a randomised controlled trial designed to evaluate the effectiveness of an exercise intervention using an exercise park specifically designed for older people in reducing the risk of falls.Methods/DesignThis study will be a parallel randomised control trial with pre and post intervention design. One hundred and twenty people aged between 60 and 90 years old will be recruited from Melbourne suburbs and will be randomly allocated to either an exercise park intervention group (EPIG) or a control group (CG). The CG will receive social activities and an educational booklet on falls prevention. The BOOMER balance test will be used as the primary outcome measure. Secondary outcome measures will include hand grip strength, two minute walk test, lower limb strength test, spatio-temporal walking parameters, health related quality of life, feasibility, adherence, safety, and a number of other psychosocial measures. Outcome assessment will be conducted at baseline and at 18 and 26 weeks after intervention commencement. Participants will inform their falls and physical activity history for a 12-month period via monthly calendars. Mixed linear modelling incorporating intervention and control groups at the baseline and two follow up time points (18 weeks and 26 weeks after intervention commencement) will be used to assess outcomes.DiscussionThis planned trial will be the first to provide evidence if the exercise park can improve functional and physiological health, psychological and well-being. In addition, this study will provide empirical evidence for effectiveness and explore the barriers to participation and the acceptability of the senior exercise park in the Australian older community.Trial registrationThis trial is registered with the Australian New Zealand Clinical Trials Registry - Registry No. ACTRN12614000700639 registered on Jul 3rd 2014.Electronic supplementary materialThe online version of this article (doi:10.1186/s12877-015-0057-5) contains supplementary material, which is available to authorized users.

Artificial neural networks (ANN) have been increasingly used in gait analysis. Back-propagation neural network has been widely used because of its good predicting power in supervised training mode for gait data analysis. In this paper an artificial neural network was used to model relationships between minimum toe clearance (MTC) characteristics derived from fewer gait trials and that derived from gait data during a 30-minute continuous treadmill walking. The ANN was separately trained and tested with nine statistics calculated from 10 different data segment lengths as inputs, and the mean and standard deviation of MTC data calculated from 30 minutes gait trials as outputs. The results suggest that a trained ANN is able to accurately predict stabilized MTC data, even a 5-gait cycles' data predicted with about 80% accuracy and the prediction accuracy was seen to improve with increase in the length of input data segment.