Traditional Artificial Intelligence (AI) technologies used in developing smart cities solutions, Machine Learning (ML) and recently Deep Learning (DL), rely more on utilising best representative training datasets and features engineering and less on the available domain expertise. We argue that such an approach to solution development makes the outcome of solutions less explainable, i.e., it is often not possible to explain the results of the model. There is a growing concern among policymakers in cities with this lack of explainability of AI solutions, and this is considered a major hindrance in the wider acceptability and trust in such AI-based solutions. In this work, we survey the concept of ‘explainable deep learning’ as a subset of the ‘explainable AI’ problem and propose a new solution using Semantic Web technologies, demonstrated with a smart cities flood monitoring application in the context of a European Commission-funded project. Monitoring of gullies and drainage in crucial geographical areas susceptible to flooding issues is an important aspect of any flood monitoring solution. Typical solutions for this problem involve the use of cameras to capture images showing the affected areas in real-time with different objects such as leaves, plastic bottles etc., and building a DL-based classifier to detect such objects and classify blockages based on the presence and coverage of these objects in the images. In this work, we uniquely propose an Explainable AI solution using DL and Semantic Web technologies to build a hybrid classifier. In this hybrid classifier, the DL component detects object presence and coverage level and semantic rules designed with close consultation with experts carry out the classification. By using the expert knowledge in the flooding context, our hybrid classifier provides the flexibility on categorising the image using objects and their coverage relationships. The experimental results demonstrated with a real-world use case showed that this hybrid approach of image classification has on average 11% improvement (F-Measure) in image classification performance compared to DL-only classifier. It also has the distinct advantage of integrating experts’ knowledge on defining the decision-making rules to represent the complex circumstances and using such knowledge to explain the results.

With the emergence of Low-Cost Sensor (LCS) devices, measuring real-time data on a large scale has become a feasible alternative approach to more costly devices. Over the years, sensor technologies have evolved which has provided the opportunity to have diversity in LCS selection for the same task. However, this diversity in sensor types adds complexity to appropriate sensor selection for monitoring tasks. In addition, LCS devices are often associated with low confidence in terms of sensing accuracy because of the complexities in sensing principles and the interpretation of monitored data. From the data analytics point of view, data quality is a major concern as low-quality data more often leads to low confidence in the monitoring systems. Therefore, any applications on building monitoring systems using LCS devices need to focus on two main techniques: sensor selection and calibration to improve data quality. In this paper, data-driven techniques were presented for sensor calibration techniques. To validate our methodology and techniques, an air quality monitoring case study from the Bradford district, UK, as part of two European Union (EU) funded projects was used. For this case study, the candidate sensors were selected based on the literature and market availability. The candidate sensors were narrowed down into the selected sensors after analysing their consistency. To address data quality issues, four different calibration methods were compared to derive the best-suited calibration method for the LCS devices in our use case system. In the calibration, meteorological parameters temperature and humidity were used in addition to the observed readings. Moreover, we uniquely considered Absolute Humidity (AH) and Relative Humidity (RH) as part of the calibration process. To validate the result of experimentation, the Coefficient of Determination (R²), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE) were compared for both AH and RH. The experimental results showed that calibration with AH has better performance as compared with RH. The experimental results showed the selection and calibration techniques that can be used in designing similar LCS based monitoring systems.

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.