Explainable Artificial Intelligence for Developing Smart Cities Solutions

Abstract

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.

IoT in Smart Cities: A Survey of Technologies, Practices and Challenges

“…Explainability is another important factor for Smart City analytics to be widely acceptable, specially in the area of smart health. There have been some approaches suggested towards this end, in [43] a hybrid deep learning classifier and semantic web technologies based solution is demonstrated for the application of flood monitoring. In [44], the authors present an explainable deep learning based healthcare system at the Edge for COVID-19 care based on a distributed learning paradigm with promising results.…”

Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges

“…Here the analysis is performed using AI techniques that conclude damage detection, classification, localisation and condition assessment, and remaining-life prediction, therefore, aims to save the cost of maintenance while minimising disruption [210]. Some of the areas where smart monitoring have been applied are bridge monitoring [211], flood monitoring [212], dam monitoring [213], subsea valve maintenance [214], wind turbine monitoring [215].…”

“…[203] Proposed guidelines for using XAI techniques and simulations using XR for secured human-robots interactions. [233] Maximizing Explainability with SF-Lasso and Selective Inference for Video and Picture Ads [234] Attentive capsule network for click-through rate and conversion rate prediction in online advertising [212] Proposed an XAI solution using DL and Semantic Web technologies for flood monitoring [208] Proposed a SHAP-based method to interpret the outputs of a multilayer perceptron for buildingdamage assessment.…”

Wind-Induced Pressure Prediction on Tall Buildings Using Generative Adversarial Imputation Network

“…Missing values can be imputed using any of the deep learning models, such as ANNs, CNNs, and recurrent neural networks [ 51 , 52 , 53 ]. Although neural-network-based models can predict wind pressures on structures, the prediction of wind pressure data at multiple points of the structures at different time intervals remains challenging [ 54 ].…”

“…Given that MICE operates by conducting multiple imputations, it is also called sequential regression multiple imputation. MICE operates on multiple imputations to handle the statistical uncertainty caused by the single imputation procedure [ 54 , 56 ]. The chained equation approach in MICE can handle variables of varying types and complexities.…”