Deep learning and Internet of Things for tourist attraction recommendations in smart cities

Abstract We propose a tourist attraction IoT-enabled deep learning-based recommendation system to enhance experience in smart city. Travelers will enter details about their travels (traveling alone or with companion, type of companion such as partner family kids, traveling for business leisure, etc.) well user side information (age the traveler/s, hobbies, into city app/website. Our proposed process this personal set input features recommend activities/attractions that best fit his/her profile. Furthermore, when tourists are city, content-based (already visited attractions) and context-related (location, weather, time day, obtained real using IoT devices; allow our suggest additional activities and/or attractions time. multi-label learning classifier outperforms other models (decision tree, extra k-nearest neighbor random forest) can successfully first case [(a) searching planning before traveling] loss, accuracy, precision, recall F1-score 0.5%, 99.7%, 99.9%, 99.9% 99.8%, respectively. It also second [(b) looking within city] 3.7%, 99.5%, 99.7%