Explainable artificial intelligence for traffic signal detection using LIMEalgorithm

Abstract

As technology progresses, so does everything around us, such as televisions, mobile  phones,  and  robots,  which  grow  wiser.  Of  these  technologies, artificial  intelligence (AI)  is  used  to  aid  the  computer  in  making  decisions comparable to humans, and this intelligence is supplied to the machine as a model.  As  AI  deals  with  the  concept  of  Black-Box,  the  model’s  decisions were poorly comprehended by the end users. Explainable AI (XAI) is where humans can understand the judgments and decisions made by the AI. Earlier, the predictions made by the AI were not as easy as we know the data now, and there was some confusion regarding the predictions made by the AI. The intention for the use of XAI is to improve the user interface of products and services  by  helping  themtrust  the  decisions  made  by  AI.  Themachine learning (ML) model White-box shows us the result that can be understood by  the  people  in  that  domain,  wherein  the  end  users  cannot  understand  the decisions. To further enhance traffic signal detectionusing XAI, the concept calledlocal interpretable model-agnostic explanation(LIME) algorithm has been taken into consideration and the performance is improved in this paper.