A smart sound and light anomaly monitoring system for highway tunnels based on Internet of Things technology was studied to address the issues of highway tunnel lighting systems. By utilizing Internet of Things technology, the tunnel lighting system is combined with abnormal sound recognition. Through the design of algorithm models, the recognition of abnormal sound inside the tunnel and the intelligent control of the lighting system is achieved. By pruning and validating the hidden layer nodes of the model, a more streamlined abnormal sound recognition model is obtained. Through experimental verification, this model has the highest recognition accuracy among all models, with a recognition rate of 91.75% at a compression rate of 20%. Compared with Average Percentage of Zeros (APoZ), Random Pruning and Mean Activation, the recognition rate is increased by 2.64%, 1.47% and 1.40%, respectively. In the design of tunnel lighting, fuzzy control is applied to the lighting inside the tunnel to improve the driving safety of drivers and further reduce the power consumption of excessive lighting in the tunnel. Through experiments, it has been proven that the system can work well, saving up to 727[Formula: see text] of energy per day.
Read full abstract