Multi-Features Classification of SMD Screen in Smart Cities using Randomised Machine Learning Algorithms

Abstract

Urban informatization applications are getting better and better, and smart cities are now taking shape because of the emergence of the Internet of Things (IoT), cloud computing, mobile Internet, and other new technologies. Smart cities allow information about a city's economic viability and culture to be shared and transmitted more rapidly. There is an increase in interconnection and communication using this method. People's living standards will rise because of the government's increased management and service capabilities. As smart cities become more common, new data sources, such as user behavior, preferences, and other insights, will be developed. A lot of data mining and analysis will be required. Urban informatization and industrialization will be achieved by implementing new information technology into a wide range of industries around the city. Efficiencies in urban management and the quality of life for residents will be enhanced by this reform. Many parts of city planning might be called “smart,” including transportation, health care, public safety, and education. Machine learning methods are being used to detect abnormalities in SMD Screen data, which includes information on all networking protocols. SMD LEDs used in LED displays are the subject of this research, which focuses on the most common causes of failure. When it comes to SMD LEDs' wet stress, antistatic capabilities, and hidden circuitry defects, we thoroughly inspect them. Following this research, we offer practical preventive solutions based on machine learning categorization models.