Yes / Event monitoring is an essential application of Smart City platforms. Real-time monitoring of gully and drainage blockage is an important part of flood monitoring applications. Building viable IoT sensors for detecting blockage is a complex task due to the limitations of deploying such sensors in situ. Image classification with deep learning is a potential alternative solution. However, there are no image datasets of gullies and drainages. We were faced with such challenges as part of developing a flood monitoring application in a European Union-funded project. To address these issues, we propose a novel image classification approach based on deep learning with an IoT-enabled camera to monitor gullies and drainages. This approach utilises deep learning to develop an effective image classification model to classify blockage images into different class labels based on the severity. In order to handle the complexity of video-based images, and subsequent poor classification accuracy of the model, we have carried out experiments with the removal of image edges by applying image cropping. The process of cropping in our proposed experimentation is aimed to concentrate only on the regions of interest within images, hence leaving out some proportion of image edges. An image dataset from crowd-sourced publicly accessible images has been curated to train and test the proposed model. For validation, model accuracies were compared considering model with and without image cropping. The cropping-based image classification showed improvement in the classification accuracy. This paper outlines the lessons from our experimentation that have a wider impact on many similar use cases involving IoT-based cameras as part of smart city event monitoring platforms. / European Regional Development Fund Interreg project Smart Cities and Open Data REuse (SCORE).

The design and construction of high-performance buildings have emerged as a preferred solution for reducing energy consumption and greenhouse gas emissions. However, sometimes there is a considerable gap between the design performance and the actual performance of the buildings. Post Occupancy Evaluations (POE) provide tools to quantify the performance relative to the occupant's health, well-being, and comfort. POE is getting widely accepted to obtain feedback for various parameters such as water, energy, indoor environmental quality, and occupant comfort. Key Performance Indicators (KPIs) can be derived based on the obtained feedback to determine the performance gaps. POE has evolved to be a robust scientific methodology; however, traditional methods of conducting POE have been proven time-consuming, inconsistent, and inefficient. This research aims to conceptualize the next generation of post occupancy evaluations that leverages cutting-edge technologies such as Building Information Modeling (BIM), Internet of Things based sensors (IoT), Geographic Information Systems (GIS), and digital twins. The key contributions of this research are presented in a series of manuscripts. In the first paper, the gaps in the existing POE were determined by conducting a thorough literature review. The observed gaps were classified in data collection, analysis, and visualization categories. Broader POE definition, spot measurements of parameters, and 2D plans and charts for visualization made the existing POE procedure time-consuming. Using digital twins that combine the geometric and parametric data from BIM models and built-environment data from GIS and sensor measurements were recommended as potential solutions to address the observed gaps. The second paper explored the application of BIM-IoT-GIS integration to conduct POE. Use case scenarios were developed to derive system requirements to host the BIM-IoT-GIS-integrated POE. Four sequential tests were conducted to integrate a BIM model from Revit and sensors' data from Excel with ArcGIS pro that contained the surrounding environment data. Based on lessons learned from the tests, an optimized workflow was recommended that can be used across a variety of projects. The third paper used the BIM-IoT-GIS-integration concept to create a holistic proof of concept for digital-twin-enabled POE. The proof of concept was validated by conducting a digital-twin-based POE on the STTC building on the Red River College campus in Winnipeg. The indoor thermal comfort was visualized within the STTC digital twin developed in ArcGIS Pro. The preliminary energy consumption analysis concluded that the STTC buildings' average energy savings were approximately 70,000 KWH/year. The potential users for digital-twin-enabled POE were presented with a comparison of iv existing POE and digital-twin-based POE over a survey and a focus group discussion. Based on opinion-based feedback, the conclusion can be made that digital twins improve the overall efficiency of POE. The fourth paper recommended the digital-twin-enabled POE procedure for UVic's engineering expansion project. It established the semantics for POE, followed by a digital twin execution plan that can be used for developing a digital twin during each phase (from planning to operations) of the project. Furthermore, the benefits of the digital-twin-enabled POE procedure were demonstrated by comparison with the existing POE procedure relative to the project phases. This study concluded that conducting the POE on the UVic ECS expansion project will enable the researchers to determine the effectiveness of sustainable features by comparing the performance of existing and proposed facilities. In conclusion, BIM-IoT-GIS-integrated digital twins address the limitations of data collection, analysis, and visualization. These digital twins will enable multi-objective analysis and spatial-temporal visualization and provide deeper insights into the way these high-performance buildings function. / Graduate / 2023-05-24