In this paper, Moroccan cities are taken as case studies. Another key feature is the use of machine learning to perform prediction. A key feature of MoreAir is its innovative sensor deployment strategy which is based on mobile and nomadic sensors as well as on medical data collected at a children’s hospital, used to identify urban areas of high prevalence of respiratory diseases. This paper describes the methodology used in the development of this system along with some preliminary data analysis results. MoreAir is a low-cost and agile urban air pollution monitoring system. The results of one of these campaigns (conducted in Hay Nahda II, Rabat, Morocco) is presented in this paper to showcase the platform. The developed platform has been tested in multiple measurement campaigns. The second offers a spatial visualization of air pollution levels using a Geographic Information System (GIS). The first is a mobile friendly air pollution meter. Finally, two applications have been developed and implemented for data visualization. A novel sensor management middle-ware has been designed and developed to have the flexibility to remotely control the operational settings of the sensor nodes and to reduce the volume of transmitted data. Both nomadic and mobile sensor nodes have been developed. The sensor nodes have been developed using low-cost off-the-shelf hardware. It aims to facilitate the testing of different data collection strategies, to simplify the air quality monitoring process, to provide the citizens with real-time information about air pollution, to allow citizens to participate in the air quality monitoring process, and to help the authorities identify zones of high air pollution and take the most appropriate measures to improve air quality. This paper presents an IoT platform designed for air pollution monitoring. It has improved energy consumption by up to three times and also reduced traffic by more than 80% compared to similar methods. The simulation results in MATLAB R2018b show that the proposed method reduces the network communications.
In the proposed schema, three methods containing Grid partitioning, Subtractive Clustering and fuzzy c-means have been used in two modes, including hybrid and error backpropagation, to predict the individual’s behavioral pattern and determine the patient's risk, attentively. It causes restricting sensed and transmitted data to the coordinator. This paper, it has been tried to present a method based on adapting sampling rate through patient’s risk and discovered pattern by employing an intelligence method based on adaptive neuro-fuzzy inference system, interpolation function, and a biosensor patron. Considering the importance of biosensors on the Internet of the patient body that collect vital signs and transmit them to the coordinator, energy consumption and network lifetime are essential challenges in these networks.