Building IoT based applications for Smart Cities: How can ontology catalogs help?

Integrative urban AI to expand coverage, access, and equity of urban data

We consider the use of AI techniques to expand the coverage, access, and equity of urban data. We aim to enable holistic research on city dynamics, steering AI research attention away from profit-oriented, societally harmful applications (e.g., facial recognition) and toward foundational questions in mobility, participatory governance, and justice. By making available high-quality, multi-variate, cross-scale data for research, we aim to link the macrostudy of cities as complex systems with the reductionist view of cities as an assembly of independent prediction tasks. We identify four research areas in AI for cities as key enablers: interpolation and extrapolation of spatiotemporal data, using NLP techniques to model speech- and text-intensive governance activities, exploiting ontology modeling in learning tasks, and understanding the interaction of fairness and interpretability in sensitive contexts.

LSTM-Based Path Prediction for Effective Sensor Filtering in Sensor Registry System

The Internet of Things (IoT) is expected to provide intelligent services by receiving heterogeneous data from ambient sensors. A mobile device employs a sensor registry system (SRS) to present metadata from ambient sensors, then connects directly for meaningful data. The SRS should provide metadata for sensors that may be successfully connected. This process is location-based and is also known as sensor filtering. In reality, GPS sometimes shows the wrong position and thus leads to a failed connection. We propose a dual collaboration strategy that simultaneously collects GPS readings and predictions from historical trajectories to improve the probability of successful requests between mobile devices and ambient sensors. We also update the evaluation approach of sensor filtering in SRS by introducing a Monte Carlo-based simulation flow to measure the service provision rate. The empirical study shows that the LSTM-based path prediction can compensate for the loss of location abnormalities and is an effective sensor filtering model.

A Comparative Study of Traffic Classification Techniques for Smart City Networks

Smart city networks involve many applications that impose specific Quality of Service (QoS) requirements, thus representing a challenging scenario for network management. Solutions aiming to guarantee QoS support have not been deployed in large-scale networks. Traffic classification is a mechanism used to manage different aspects, including QoS requirements. However, conventional traffic classification methods, such as the port-based method, are inefficient because of their inability to handle dynamic port allocation and encryption. Traffic classification using machine learning has gained research interest as an alternative method to achieve high performance. In fact, machine learning embeds intelligence into network functions, thus improving network management. In this study, we apply machine learning algorithms to predict network traffic classification. We apply four supervised learning algorithms: support vector machine, random forest, k-nearest neighbors, and decision tree. We also apply a port-based method of traffic classification based on applications' popular assigned port numbers. Then, we compare the results of this method to those obtained from the machine learning algorithms. The evaluation results indicate that the decision tree algorithm provides the highest average accuracy among the evaluated algorithms, at 99.18%. Moreover, network traffic classification using machine learning provides more accurate results and higher performance than the port-based method.

Smart City Ontologies and Their Applications: A Systematic Literature Review

The increasing interconnections of city services, the explosion of available urban data, and the need for multidisciplinary analysis and decision making for city sustainability require new technological solutions to cope with such complexity. Ontologies have become viable and effective tools to practitioners for developing applications requiring data and process interoperability, big data management, and automated reasoning on knowledge. We investigate how and to what extent ontologies have been used to support smart city services and we provide a comprehensive reference on what problems have been addressed and what has been achieved so far with ontology-based applications. To this purpose, we conducted a systematic literature review finalized to presenting the ontologies, and the methods and technological systems where ontologies play a relevant role in shaping current smart cities. Based on the result of the review process, we also propose a classification of the sub-domains of the city addressed by the ontologies we found, and the research issues that have been considered so far by the scientific community. We highlight those for which semantic technologies have been mostly demonstrated to be effective to enhance the smart city concept and, finally, discuss in more details about some open problems.

Explainable Artificial Intelligence for Developing Smart Cities Solutions

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.

Knowledge-Based Smart City Service System

A smart city can be defined as a city exploiting information and communication technologies to enhance the quality of life of its citizens by providing them with improved services while ensuring a conscious use of the available limited resources. This paper introduces a conceptual framework for the smart city, namely, the Smart City Service System. The framework proposes a vision of the smart city as a service system according to the principles of the Service-Dominant Logic and the service science theories. The rationale is that the services offered within the city can be improved and optimized via the exploitation of information shared by the citizens. The Smart City Service System is implemented as an ontology-based system that supports the decision-making processes at the government level through reasoning and inference processes, providing the decision-makers with a common operational picture of what is happening in the city. A case study related to the local public transportation service is proposed to demonstrate the feasibility and validity of the framework. An experimental evaluation using the Situation Awareness Global Assessment Technique (SAGAT) has been performed to measure the impact of the framework on the decision-makers’ level of situation awareness.

Automatic Knowledge Extraction to build Semantic Web of Things Applications

The Internet of Things (IoT) primary objective is to make a hyper-connected world for various application domains. However, IoT suffers from a lack of interoperability leading to a substantial threat to the predicted economic value. Schema.org provides semantic interoperability to structure heterogeneous data on the Web. An extension of this vocabulary for the IoT domain (iot.schema.org) is an ongoing research effort to address semantic interoperability for the Web of Things (WoT). To design this vocabulary, a central challenge is to identify the main topics (concepts and properties) automatically from existing knowledge in IoT applications. We designed KE4WoT (Knowledge Extraction for the Web of Things) to automatically identify the most important topics from literature ontologies of 3 different IoT application domains - smart home, smart city and smart weather - based on our corpus consisting of 4500 full-text conference and journal articles to utilize domain-specific knowledge encoded within IoT publications. Despite the importance of automatically identifying the relevant topics for iot.schema.org, up to know there is no study dealing with this issue. To evaluate the extracted topics, we compare the descriptiveness of these topics for the 10 most popular ontologies in the 3 domains with empirical evaluations of 23 domain experts. The results illustrate that the identified main topics of IoT ontologies can be used to sufficiently describe existing ontologies as keywords.

Ontological Representation of Smart City Data: From Devices to Cities

Existing smart city ontologies allow representing different types of city-related data from cities. They have been developed according to different ontological commitments and hence do not share a minimum core model that would facilitate interoperability among smart city information systems. In this work, a survey has been carried out in order to study available smart city ontologies and to identify the domains they are representing. Taking into account the findings of the survey and a set of ontological requirements for smart city data, a list of ontology design patterns is proposed. These patterns aim to be easily replicated and provide a minimum set of core concepts in order to guide the development of smart city ontologies.

Interactive 3D Exploration of RDF Graphs through Semantic Planes

This article presents Tarsier, a tool for the interactive 3D visualization of RDF graphs. Tarsier is mainly intended to support teachers introducing students to Semantic Web data representation formalisms and developers in the debugging of applications based on Semantic Web knowledge bases. The tool proposes the metaphor of semantic planes as a way to visualize an RDF graph. A semantic plane contains all the RDF terms sharing a common concept; it can be created, and further split into several planes, through a set of UI controls or through SPARQL 1.1 queries, with the full support of OWL and RDFS. Thanks to the 3D visualization, links between semantic planes can be highlighted and the user can navigate within the 3D scene to find the better perspective to analyze data. Data can be gathered from generic SPARQL 1.1 protocol services. We believe that Tarsier will enhance the human friendliness of semantic technologies by: (1) helping newcomers assimilate new data representation formats; and (2) increasing the capabilities of inspection to detect relevant situations even in complex RDF graphs.