Falls among the elderly is an important health issue. Fall detection and movement tracking are therefore instrumental in addressing this issue. This paper responds to the challenge of classifying different movements as a part of a system designed to fulfill the need for a wearable device to collect data for fall and near-fall analysis. Four different fall trajectories (forward, backward, left and right), three normal activities (standing, walking and lying down) and near-fall situations are identified and detected. Different machine learning algorithms are compared and the best one is used for real time classification. The comparison is made using Waikato Environment for Knowledge Analysis (WEKA), one of the most popular machine learning software. The system also has the ability to adapt to the different gait characteristics of each individual. A feature selection algorithm is also introduced to reduce the number of features required for the classification problem.