The future of modern cities largely depends on how well they can tackle intrinsic problems that confront them by embracing the next era of digital revolution. A vital element of such revolution is the creation of smart cities and associated technology infrastructures. Smart city is an emerging phenomenon that involves the deployment of information communication technology wares into public or private infrastructure to provide intelligent data gathering and analysis. Key areas that have been considered for smart city initiatives include monitoring of weather, energy consumption, environmental conditions, water usage and host of others. To align with the smart city revolution in the area of environmental cleanliness, this study involves the development of a web based smart city infrastructure for refuse disposal management using the design science research approach. The Jalali smart city reference architecture provided a template to develop the proposed architecture in this study. The proposed architecture contains four layers, which are signal sensing and processing, network, intelligent user application and Internet of Things (IoT) web application layers. A proof of concept prototype was designed and implemented based on the proposed architecture. The signal sensing and processing layer was implemented to produce a smart refuse bin, which is a bin that contains the Arduino microcontroller board, Wi-Fi transceiver, proximity sensor, gas sensor, temperature sensor and other relevant electronic components. The network layer provides interconnectivity among the layers via the internet. The intelligent user application layer was realized with non browser client application, statistical feature extraction and pattern classifiers. Whereas the IoT web application layer was realised with ThingSpeak, which is an online web application for IoT based projects. The sensors in the smart refuse bin, generates multivariate dataset that corresponds to the status of refuse in the bin. Training and testing features were extracted from the dataset using first order statistical feature extraction method. Afterward, Multilayer Perceptron Artificial Neural Network (MLP-ANN) and support vector machine were trained and compared experimentally. The MLP-ANN gave the overall best accuracy of 98.0%, and the least mean square error of 0.0036. The ThingSpeak web application connects seamlessly at all times via the internet to receive data from the smart refuse bin. Refuse disposal management agents can therefore query ThingSpeak for refuse status data via the non browser client application. The client application, then uses the trained MLP-ANN to appositely classify such data in order to determine the status of the bin.
Application-layer performance analysis of PRIME in Smart Metering networks
