Abstract:
Gait velocity and stride length are acute health indicators for older adults. A decade of
medical research shows that Gait speed is the sixth vital sign of health. Though still
these metrics are measured only during medical check-ups which lessens the
opportunities to intervene and detect changes timely in the impairment process. The
objective ofthis project is to develop health monitoring system to predict health state
on gait speed and stride length.
This project uses the Convolutional Neural Network technique to
develop the system. The main advantage of using this technique is that it provides
features extraction and detection that is suitable for image recognition. Model of
convolutional neural network and Error-back propagation algorithm was used due to
its’ capability of forming internal representations of features in classification. After
trials and errors, a suitable set oftraining parameters are define and network structure
is created.
The system first proceeds with the pre-process ofthe captured image
with threshold, inverting and smoothing. Filtering, segmentation, resizing and features
extraction are also performed in the process. Next, the feed forward process through
the network is invoked to yield an output matrix. Based on the output matrix, the health
state can be determined. This system is designed to customize the network according
to the network data
