Machine Learning in Smart Cities: Survey of Wireless Sensor Network Applications

AI and ML methods can assist in processing automated tasks over the Internet on Things terminals deployed across smart communities. The key application areas of the Internet of Things in smart cities are smart traffic tracking, intelligent waste management, smart building optimisation and patient healthcare monitoring. The gateways then use WSN (Wireless Sensor and Bluetooth standards to push the data from small-sized IoT nodes over long distances. Network life maximization, connectivity issues regarding bandwidth and network coverage power consumption efficient data sharing deployment methodologies newer communication methods new infrastructure Available applications Major design challenges in the WSN-enabled smart cities. In this extensive literature survey, it is proposed to Machine Learning techniques as optimization methods for WSN-IoT nodes (Network of sensors) that are used in Smart City initiatives. This is, to the best of our knowledge, the first review study which covers all machine learning methods in low-power WSN-IoT for urban smart cities. Here the algorithms used varied in context of type as shown by results suggesting supervised learning ( 61%) for smart city applications, unsupervised learning(12%),and reinforcement learning(27%). This research will make a valuable contribution to the growing number of works on AI and ML usage with an impact on how these technologies can boost efficacy, efficiency as well as performance in smart city context for IoT deployments. Removal of the number references also maintains a level with version information voided of plagiarism.