Living Condition in Cities now Monitor using Image
Cities are the home to an increasing majority of the World’s population. At the current situation, it is difficult to track health, social, and economic outcomes in the cities. It is much needed to evaluate the policies regarding urban inequalities. But with the new technology, we can analyze and monitor the living conditions in the cities using images of cities by the approach to the street images to measure the distribution of income, health, housing, education and crime.
According to the report, 55% of the world population living in the cities. Naturally, urban area people’s have higher economic, educational and health than the rural resident. Normally, inequalities are present in an urban area where poor and rich live side by side with a massive difference in health and economic difference.
Now with the help of technology, a develope system can automatically detect the sign of inequalities from the street image. Artificial Intelligence will help us to track the living condition in cities with the help of images. Street images can be investigated using machine learning and visual inspection technique.
Esra Suel and colleagues at Imperial College London trained Artificial Intelligence to detect inequalities in four major countries of UK, named as London and West Midlands including Birmingham, Greater Manchester, West Yorkshire including Leeds with the help of Google street view application.
The AI was trained on 525,860 images from 156,581 posted from London which include health, education, income and the living environment in the area. The AI was most successful in spotting of inequalities and the predicitng difference in crime report and self-reported health, scoring 0.57 and 0.66 respectively.
After testing in London, the team then used AI to perform the same estimation in the other cities and after being fine tune with some additional images collected in those cities. It scored 0.68, 0.71 and 0.66 in the cities Birmingham, Manchester and Leeds respectively compare with the overall correlation of London i.e 0.77%.
The application of deep learning to street imaginary better-predicted inequalities in some outcome i.e income and leaving environment than the other crime and self-reported health.
Street Imaginary will be a helpful tool in monitoring the policies of the reduce inequalities. As they are updated more quickly than the government survey and census data.
Next challenge accepted by the team is to detect inequalities in developing countries, where the statistical data is not widely available.
Reference: Scientific Reports DOP:18:04:19
Also check Article on Microsoft Surface Earbuds
Also Check Article on Wireless Surface Earbuds