The research was carried out to detect dangerous road conditions. According to US Department of Transportation, wet roads caused accidents and 959.760 deaths in 4789 caused more than 10 years the period between 02 and 2012. This figure amounts to 74% of all accidents related to weather in the US and is 23 % of all accident vehicles in the country.
researchers from the IEEE (Institute of Electrical and Electronics Engineers) used neural networks recurring (NNI), a type of artificially intelligent of computer network to detect the slippery way is a road. In addition, they also attach a shotgun mic to analyze the audio feedback of the car's tires. In the process, they used 2014 Mercedes CLA trained for different road conditions weather and speed around the Boston area in Massachusetts.
Researchers at the Technical University of Madrid in 2014 used support vector machines (SVM), a type of learning model of the machine to analyze the sounds made when tires meeting the road and rank them accordingly. However, they found that the surface of scale types have limited audio input and irrelevant, like sound pebbles bounce against the tires could lead to false predictions.
Researchers at the University of Toyama in Japan conducted the same survey in October 2012. They were experimenting with a system that uses surveillance cameras on cars watching the reflections of the Lighthouse Route other drivers "through. He showed a specific state roads in the fog, snow and poor light, however, it took other drivers to be on the road as for this method to work.
0 Komentar