A new approach for varied speed weigh-in-motion vehicle based on smartphone inertial sensors

<p>Dynamic vehicle weight measuring, weigh-in-motion (WIM), is an important metric that can reflect significantly driving behaviour and in turn, it will affect both safety traffic status. Several accurate WIM systems are developed implemented successfully. These using under road weighing sensor which costly to implement. Moreover, not very practical embed a continuous system used cars. In this work, low-cost varied-speed approach was suggested continuously measuring load based on the response of smartphone sensors reflection dynamics. This apply any moving at speed without need for extra added hardware makes applicable because widely device. The tested through six-trips experiment. Three capacities had been designed be classified neural network classifier. classification performance metrics calculated show accuracy 91.2%. level within error limits existing especially high proved success approach.</p>