IoT applications in a smart city context

• Autor(a) principal: Oliveira, Rafael Fernandes de
• Data de Publicação: 2021
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10773/31381
• topic: Smart city; Iot; Pasmo; Plaftorm; Public service; Sensor fusion

Over the last few years, Smart City solutions mature very rapidly alongside IoT and cloud computing. These technologies made it easier to create services and incorporate applications devoted to improving citizen’s quality of life and offer ways for businesses to implement their solutions. Through rapid advances in the quality of sensors, new methods emerged, combining different types of devices to create a better picture of the environment. The purpose of this dissertation is to provide useful information thought public services, that can be accessed by people visiting or residing in the beach area of Costa Nova and Barra. It also provides a solution for the traffic classification problem that projects based on radar data tend to face. These applications take advantage of the devices implemented in the PASMO project, such as parking sensors, radars, and CCTV cameras. By making the service public, businesses have the opportunity to build applications on top of it, utilizing the sensor data without being directly connected to the data storage. The example developed in this dissertation offers a dashboard experience where users can navigate through charts that provide a variety of data and real-time maps. It also provides a public API that researchers and businesses can use to develop new applications in the context of PASMO. The other area tackled in this document is traffic classification. Although the data provided is reliable for the most part, one big issue is the accuracy of vehicle classification provided by the radar. Still, this device offers precise values when it comes to detection, with the cameras doing a good job in classifying traffic. The goal is to combine these two devices to present much precise information, using state-of-the-art object detection algorithms and sensor fusion methods. In the end, the system will enrich the PASMO project by making its data easily available to the public while correcting the accuracy problems of some devices.