Rapid urbanization burdens city infrastructure and creates the need for local governments to maximize the usage of resources to serve its citizens. Smart city projects aim to alleviate the urbanization problem by deploying a vast amount of Internet-of-things (IoT) devices to monitor and manage environmental conditions and infrastructure. However, smart city projects can be extremely expensive to deploy and manage partly due to the cost of providing Internet connectivity via 5G or WiFi to IoT devices. This thesis proposes the use of delay tolerant networks (DTNs) as a backbone for smart city communication; enabling developing communities to become smart cities at a fraction of the cost. A model is introduced to aid policy makers in designing and evaluating the expected performance of such networks and results are presented based on a public transit network data-set from Chapel Hill, North Carolina and Louisville, Kentucky. We also demonstrate that the performance of our network can be optimized using algorithms associated on set-cover and Influence maximization problems. Several optimization algorithms are then developed to facilitate the effective placement of gateways within the network model and these algorithms are shown to outperform traditional centrality-based algorithms in terms of cost-efficiency and network performance. Finally, other innovative ways of improving network performance in a low-cost smart city is discussed.

Memoria para optar al título de Ingeniero Civil Eléctrico / Una Smart City es un concepto asociado a un tipo de desarrollo urbano basado en la sostenibilidad, desarrollo que es capaz de responder a las necesidades básicas de instituciones, empresas y de los propios habitantes, tanto en el plano económico como en los aspectos operativos, sociales y ambientales. El rol de las TIC es pasivo, remitiéndose a la recopilación y análisis de datos, y la optimización en la utilización de infraestructuras, así como facilitar la comunicación entre los diferentes servicios de la ciudad. Asimismo, la introducción de nuevas tecnologías emergentes se convierte en una oportunidad por la cual diversas comunidades políticamente organizadas optan por adoptar, gracias a los beneficios energéticos que estas entregan, en conjunto con la inteligencia que estas proporcionan. De esta manera, múltiples ciudades han decidido integrar infraestructuras TICAR (Tecnología de Información, Telecomunicaciones, Automatización y Robótica) a fin de responder adecuadamente a diversas necesidades. En el caso de Chile, si bien existen diversas iniciativas para apoyar la investigación, desarrollo e integración de nuevas tecnologías, estas no logran ser suficientes para el potencial mismo del país. En el contexto de Smart Cities, el país presenta un gran potencial para integrar tecnologías TICAR, gracias al sólido conocimiento existente de las mismas, la factibilidad económica para su adquisición, y la existencia de múltiples infraestructuras. Referido a este último punto, una infraestructura de gran interés resulta ser el alumbrado público. Este sistema se caracteriza por iluminar zonas urbanas y sectores residenciales, con el objetivo de proporcionar la visibilidad adecuada para el normal desarrollo de actividades. Si existe una infraestructura física, que dispone de recursos energéticos, ¿por qué no diseñar un sistema de luminarias inteligentes, que responda como infraestructura habilitante para Smart Cities, con versatilidad para la integración de diversas tecnologías de comunicaciones e IoT? En este contexto, la realización del presente trabajo de título tiene por objetivo modelar una infraestructura TICAR habilitante para Smart Cities, con foco a las redes de comunicaciones. Como infraestructura habilitante se propone el desarrollo de una red pública de luminarias inteligentes. Para esto, se realiza una revisión profunda de antecedentes que permitan contextualizar la problemática presente, una comparación preliminar entre tecnologías IoT que permita observar el desempeño y comportamiento de las mismas en entornos urbanos, y el diseño de la infraestructura habilitante desde la perspectiva de las tecnologías de la comunicación. A fin de validar esta propuesta, se considera dentro de los parámetros de diseño estandarizaciones y regulaciones de ambientes urbanos y tecnologías emergentes, junto a la utilización de plataformas de simulación que permitan caracterizar de manera robusta cada uno de los escenarios elaborados.

In the domain of social design, this thesis introduces a design project that explores a place-centric view on interaction design to address issues of participation, representation, and place. The project aims to envision possible futures of city-scaled digital twins as places that enable collective engagement within communities and between citizens and cities. It explores this aim with a methodology grounded in co-design- and ethnographic values, focusing on the place of Ringön in Gothenburg. The final design outcome of the study is an augmented reality-based application connected to the city-scaled digital twin of Gothenburg. The application introduces a concept that enables citizens to express location-based social and cultural values and engage in common concerns. It enables the City of Gothenburg to communicate with citizens and develop an enriched understanding of the identity and character of places in Gothenburg. The study hopes to contribute with knowledge to the body of work within social design that explores how sustainable smart cities can develop from a bottom-up perspective, in a more participatory and socially sustainable way.

This thesis summarises the outcomes of a Big Data analysis, performed on a set of hourly district heating energy consumption data from 2012 for nearly 15 000 buildings in the City of Stockholm. The aim of the study was to find patterns and inefficiencies in the consumption data using KNIME, a big data analysis tool, and to initiate a retrofitting plan for the city to counteract these inefficiencies. By defining a number of energy saving scenarios, the potential for increased efficiency is estimated and the resulting methodology can be used by other (smart) cities and policy makers to estimate savings potential elsewhere. In addition, the influence of weather circumstances, building location and building types is studied. In the introduction, a concise overview of the concepts Smart City and Big Data is given, together with their relevance for the energy challenges of the 21st century. Thereafter, a summary of the previous studies at the foundation of this research and a brief theory review of less common methods used in this thesis are presented. The method of this thesis consisted of first understanding and describing the dataset using descriptive statistics, studying the annual fluctuations in energy consumption and clustering all consumer groups per building class according to total consumption, consumption intensity and time of consumption. After these descriptive steps, a more analytical part starts with the definition of a number of energy saving scenarios. They are used to estimate the maximal potential for energy savings, regardless of actual measures, financial or temporal aspects. This hypothetical simulation is supplemented with a more realistic retrofitting plan that explores the feasibility of Stockholm’s Climate Action Plan for 2012-2015, using a limited set of energy efficiency measures and a fixed investment horizon. The analytical part is concluded with a spatial regression that sets out to determine the influence of wind velocity and temperature in different parts of Stockholm. The conclusions of this thesis are that the potential for energy savings in the studied data set can go up to 59% or 4.6 TWh. The financially justified savings are estimated at ca. 6% using favourable investment parameters. However, these savings quickly diminish because of a high sensitivity on the input parameters. The clustering analysis has not yielded the anticipated results, but they can be used as a tool to target investments towards groups of buildings that have a high return on investment.

The application of Internet of Things (IoT) where sensors and actuators embedded in physical objects are linked through wired and wireless networks has shown a rapid growth over the past years in various domains with the benefits of improving efficiency and productivity, reducing cost, providing mobility and agility, etc. This dissertation focuses on developing signal processing and machine learning based techniques in IoT with applications to 1) smart energy generation and 2) robust indoor localization in smart city. Smart grids, in contrast to legacy grids, facilitate more efficient electricity generation and consumption by allowing two-way information exchange among various components in the grid and the users based on the measurements from numerous sensors located at different places. Due to the introduction of information communications, a smart grid is faced with the risk of external attacks which is aimed to take control of the grid. In particular, electricity generation from photovoltaic (PV) systems is a mature power generation technology utilizing renewable resources, owning to its advantages in clean production, reduced cost and high flexibility. However, the performance of a PV system can be susceptible and unstable due to various physical failures and dynamic environments (internal circuit faults, partial shading, etc.). To safeguard the system security, fault or attack detection technologies are of great importance for PV systems and smart grids. Existing approaches on fault or attack detection either rely on the prediction by a predetermined system model which acts as reference data for comparison or can be applied only within a certain set of component (e.g., several PV strings) based on local statistical properties without the capability of generalization. Furthermore, the output performance of a PV system is dynamic under different environmental conditions (irradiance level, temperature, etc.), which can be optimized by the technique of maximum power point tracking (MPPT). However, previous studies on MPPT usually require prior knowledge of the system model or high computational complexity for iterative optimization. Smart city, as another important application of IoT, relies on analysis of the measurement data from sensors located at users and environments to provider intelligent solutions in our daily life. One of the fundamental tasks for advanced location-based services is to accurately localize the user in a certain environment, e.g., on a certain floor inside a building. Indoor localization is faced with challenges of moving users, limited availability of sensors and noisy measurements due to hardware constraints and external interferences. This dissertation first describes our advanced fault/attack detection and localization methods for PV systems and smart grids, then develops our enhanced MPPT techniques for PV systems, and finally presents our robust indoor localization methods for smartphone users, based on statistical signal processing and machine learning approaches. In Chapter 2 and Chapter 3, we proposes fault/attack detection method in PV systems and smart grids respectively in the framework of abrupt change detection utilizing sequential output measurements without assuming any prior knowledge of the system characteristics or particular faulty/attack patterns, such that an alarm will triggered regardless of the magnitude or the type of faulty/attack signals. Starting from the proposed fault detection method in Chapter 2, we present our fault localization method for PV systems in Chapter 4 where the central controller is able to identify the faulty PV strings without full knowledge of each local measurements. Chapter 5 studies the MPPT method under dynamic shading conditions where we adopt neural networks to assist the identification of the global maximum power point by depicting the relationship between the system output power and the operating voltage. In Chapter 6, to tackle the challenge of accurate and robust indoor localization for smart city when sensors provides noisy measurement data, we propose a cooperative localization method which exploits the readings of the received strengths of Wi-Fi signals at the smartphone users and the relative distances among neighboring users to combat the deterioration due to aggregated measurement errors. Throughout the dissertation, our proposed methods are followed by simulations (of a PV system or a grid under various operating conditions) or experiments (of localizing moving users with smartphones to record sensors' measurements). The results demonstrate that our proposed fault/attack detection and localization methods and MPPT schemes can achieve higher adaptivity and efficiency with robustness against various external conditions an lower computational complexity, and our cooperative localization methods have high localization accuracy even given large measurement errors and limited measurement data.

Magister Commercii (Information Management) - MCom(IM) / The advent of the 4th Industrial Revolution brought on an onslaught of technology rippling through a multitude of industries. Smart Cities, Smart Communities, Artificial Intelligence and Cloud Computing are but a few buzzwords of this digital age. It is argued in Information Systems that many of the challenges faced by communities can be addressed in part through the innovative use of technology. As Higher Education (HE) communities move from traditional campus communities to smart campus communities, the application and implementation of technological advancements and digital skills are needed to facilitate the transition. The disruption caused by COVID-19 virus has had a significant effect on the tertiary educational sector. This research is particularly important and relevant in a post-pandemic phase in which HE finds itself. Especially, establishing a technological and digitally equipped HE community to safeguard itself from possible future threats that impede daily operations within HE campus communities.

Autonomously monitoring and analyzing the behavior of the crowd is an open research topic in the transportation field because of its criticality to the safety of people. Real-time identification, tracking, and prediction of crowd behavior are primordial to ensure smooth crowd management operations and the welfare of the public in many public areas, such as public transport stations and streets. This being said, enabling such systems is not a straightforward procedure. First, the complexity brought by the interaction and fusion from individual to group needs to be assessed and analyzed. Second, the classification of these actions might be useful in identifying danger and avoiding any undesirable consequences. The adoption of the Internet-of-things (IoT) in such systems has made it possible to gather a large amount of data. However, it raises diverse compatibility and trustworthiness challenges, among others, hindering the use of conventional service discovery and network navigability processes for enabling crowd management systems. In fact, as the IoT network is known for its highly dynamic topology and frequently changing characteristics (e.g., the devices' status, such as availability, battery capacity, and memory usage), traditional methods fail to learn and understand the evolving behavior of the network so as to enable real-time and context-aware service discovery to assign and select relevant IoT devices for monitoring and managing the crowd. In large-scale IoT networks, crowd management systems usually collect large data streams of images from different heterogeneous sources (e.g., CCTVs, IoT devices, or people with their smartphones) in an inadvertent way. Due to the limitations and challenges related to communication bandwidth, storage, and processing capabilities, it is unwise to transfer unselectively all the collected images since some of these images either contain duplicate information, are inaccurate, or might be falsely submitted by end-users; hence, a filtering and quality check mechanism must be put in place. As images can only provide limited information about the crowd by capturing only a snapshot of the scene at a specific point in time with limited context, an extension to deal with videos to enable efficient analysis such as crowd tracking and identification is essential for the success of crowd management systems. In this thesis, we propose to design a smart image enhancement and quality control system for resource pooling and allocation in the Internet-of-Things applied to crowd management systems. We first rely on the Social IoT (SIoT) concept, which defines the relationships among the connected objects, to extract accurate information about the network and enable trustworthy and context-aware service exchange and resource allocation. We investigate the service discovery process in SIoT networks and essentially focus on graph-based techniques while overviewing their utilization in SIoT and discussing their advantages. We also propose an alternative to these scalable methods by introducing a low-complexity context-aware Graph Neural Network (GNN) approach to enable rapid and dynamic service discovery in a large-scale heterogeneous IoT network to enable efficient crowd management systems. Secondly, we propose to design a smart image selection procedure using an asymmetric multi-modal neural network autoencoder to select a subset of photos with high utility coverage for multiple incoming streams in the IoT network. The proposed architecture enables the selection of high-context data from an evolving picture stream and ensures relevance while discarding images that are irrelevant or falsely submitted by smartphones, for example. The approach uses the photo's metadata, such as geolocation and timestamps, along with the pictures' semantics to decide which photos can be submitted and which ones must be discarded. To extend our framework beyond just images and deal with real-time videos, we propose a transformer-based crowd management monitoring framework called V3Trans-Crowd that captures information from video data and extracts meaningful output to categorize the crowd's behavior. The proposed 3D Video Transformer is inspired from Video Swin-Transformer/VIVIT and provides an improved hierarchical transformer for multi-modal tasks with spatial and temporal fusion layers. Our simulations show that due to its ability to embed the devices' features and relations, the GNN is capable of providing more concise clusters compared to traditional techniques, allowing for better IoT network learning and understanding. Moreover, we show that the GNN approach speeds up the service lookup search space and outperforms the traditional graph-based techniques to select suitable IoT devices for reporting and monitoring. Simulation results for three different multi-modal autoencoder architectures indicate that a hierarchical asymmetric autoencoder approach can yield better results, outperforming the mixed asymmetric autoencoder and a concatenated input autoencoder, while leveraging user-side rendering to reduce bandwidth consumption and computational overhead. Also, performance evaluation for the proposed V3Trans-Crowd model has shown great results in terms of accuracy for crowd behavior classification compared to state-of-the-art methods such as C3D pre-trained, I3D pre-trained, and ResNet 3D pre-trained on the Crowd-11 and MED datasets.

<p dir="ltr">The roads in the US received a "D" grade on the 2021 report card for America's infrastructure by the American Society of Civil Engineers (ASCE). Poor road conditions generally translate into traffic accidents and vehicle damage, which result in additional expenses for drivers in terms of vehicle repairs and operating costs. To maintain a satisfactory pavement condition over an extended period of time, frequent inspections should be conducted, and any existing and imminent defects should be promptly addressed through corrective and preventive maintenance. However, the current practices are hindered by issues of inspectors' subjectivity, delayed responsiveness, and high costs. This study aims to develop innovative solutions that harness Artificial Intelligence (AI), robotics, and virtual reality (VR) to enhance pavement quality in smart cities.</p><p dir="ltr">The study developed an autonomous system that relies on crowdsourced RGB and depth (RGB-D) data to assess road conditions. A cost-effective data acquisition system that can be mounted on multiple vehicles, was developed. Armed with a substantial dataset of RGB-D pavement surface data, this study explores the effectiveness of various depth-encoding techniques and RGB-D data fusion methods, using pothole detection as a case study. Comprehensive experiments were conducted to evaluate the effectiveness of defect detection using deep convolutional neural networks (DCNN). This study considered all major types of pavement defects in order to comprehensively evaluate pavement conditions. The Pavement Surface Evaluation Rating (PASER) for asphalt pavement is used as a case study. The establishment of an expert system for pavement condition evaluation involves the classification and quantification of pavement data. The system also facilitates the tracking of identified defects and repair work, providing up-to-date information on pavement deterioration and maintenance.</p><p dir="ltr">Another aspect of this study is the improvement of pavement maintenance quality. To enhance the assessment of the effectiveness of pavement maintenance, this study developed immersive VR modules that provide technical staff with a supplementary platform for training. The training materials focus on two common types of pavement maintenance operations: crack sealing and patching. These modules include an interactive decision-making module for evaluating the quality of operations, as well as a hands-on task-performing module for crack sealing machinery preparation and the procedure of full-depth patching. This dissertation has revealed innovative approaches for integrating cutting-edge technologies into the assessment of pavement conditions. The proposed research aims to improve the safety, </p>

Vehicular Ad-hoc Networks (VANETs) provide networks for smart vehicles and will enable future systems to provide services that enhance the overall transportation experience. However, these applications require consideration to possible damage to both property and human life. Communication between vehicles requires data immutability and user privacies to provide safe operation of the system. Blockchains can provide these properties and more to create a more secure and decentralized system. However, a chain’s security comes from the chain length. VANETs’ ephemeral connections provide harm limits how much data can be exchanged during vehicle rendezvous. This thesis investigates lightweight blockchains that operate with lower overheads. A survey of current techniques to accomplish this are discussed in Chapter 1. Two techniques are demonstrated within two separate environments to demonstrate the network overhead reductions when using a lightweight blockchain with respect to network and storage loads within these VANET environments.

The smart city is not a new concept. For centuries urbanists have sought to rationalize city making and explore more efficient means to operate cities. Meanwhile, the exponential utilization of information and communication technologies (ICT) have opened up for a new wave of ‘smart’ development that is rapidly sweeping across the globe contributing to a previously unseen ‘datafication’ of cities. The concept of smart cities is often met by staunch criticism due to, among other things, the influence from corporate actors. Smart cities have also been criticized for not adequately addressing issues related to sustainable development. Despite this recent upswing of smart initiatives and plans, there is still a significant gap in our understanding of what this looks like in situ. While spectacular cases (Songdo, South Korea; Masdar City, UAE, among others) of smart cities have been dissected and covered extensively over the last few years, more ordinary examples of already existing cities transitioning into smart cities are still largely unexplored. Against the backdrop of both the high appraisal and vast criticism of smart cities, a growing literature have recently called for a more nuanced approach, advocating for a focus on the ‘actually existing smart city’ and how smart cities unfold in specific contexts. This study examines the situatedness of smart cities in the Australian context through a grounded theory lens, looking specifically at how the ‘datafication’ plays out and how it influences the realization of the sustainable city. Taking an inductive approach, this study applies semi-structured interviews with key smart cities stakeholders in Australia and participant observations to identify key themes in the smart city sphere in relation to sustainability and data. The findings highlight that smart city initiatives do not necessarily fit into preconceived ideas about smart cities. Secondly, while data is seen almost universally as a valuable source of information to better understand and manage cities, it is not clear that it influences sustainable development. In addition, competing opinions on open data also suggest that this is a fairly contested topic in Australia, which should encourage further investigation of its intended contributions to a more sustainable form of urban development. This study adds to a relatively scarce number of qualitative studies of smart cities in general, and of smart cities in the Australian context in particular.