Smart cities are seen as the answer for specific problems, that we will face in the future: overpopulation, shortage of resources, demographic change, etc. At the same time more people than ever will live in cities. This creates huge difficulties for governmental institutions on the one side, but also profit promising opportunities for companies on the other. This thesis will have a close look at this tension and unpack the vision of the smart cities, as they are created with the help of integrators and service companies. Through the lens of Critical Design, it will result in a fictional artifact to trigger the imagination and a debate about a possible future in which corporate interests changed the relationship between the city and its citizens.

Yes / One of the common cardiac disorders is a cardiac attack called Myocardial infarction (MI), which occurs due to the blockage of one or more coronary arteries. Timely treatment of MI is important and slight delay results in severe consequences. Electrocardiogram (ECG) is the main diagnostic tool to monitor and reveal the MI signals. The complex nature of MI signals along with noise poses challenges to doctors for accurate and quick diagnosis. Manually studying large amounts of ECG data can be tedious and time-consuming. Therefore, there is a need for methods to automatically analyze the ECG data and make diagnosis. Number of studies has been presented to address MI detection, but most of these methods are computationally expensive and faces the problem of overfitting while dealing real data. In this paper, an effective computer-aided diagnosis (CAD) system is presented to detect MI signals using the convolution neural network (CNN) for urban healthcare in smart cities. Two types of transfer learning techniques are employed to retrain the pre-trained VGG-Net (Fine-tuning and VGG-Net as fixed feature extractor) and obtained two new networks VGG-MI1 and VGG-MI2. In the VGG-MI1 model, the last layer of the VGG-Net model is replaced with a specific layer according to our requirements and various functions are optimized to reduce overfitting. In the VGG-MI2 model, one layer of the VGG-Net model is selected as a feature descriptor of the ECG images to describe it with informative features. Considering the limited availability of dataset, ECG data is augmented which has increased the classification performance. A standard well-known database Physikalisch-Technische Bundesanstalt (PTB) Diagnostic ECG is used for the validation of the proposed framework. It is evident from experimental results that the proposed framework achieves a high accuracy surpasses the existing methods. In terms of accuracy, sensitivity, and specificity; VGG-MI1 achieved 99.02%, 98.76%, and 99.17%, respectively, while VGG-MI2 models achieved an accuracy of 99.22%, a sensitivity of 99.15%, and a specificity of 99.49%. / This project was funded by University of Jeddah, Jeddah, Saudi Arabia (Project number: UJ-02-018-ICGR).

Yes / Since the 1980s, the digital revolution has been both a negative and positive force. Within a few weeks of the Covid-19 outbreak, lockdown accelerated the adoption of digital solutions at an unprecedented pace, creating unforeseen opportunities for scaling up alternative approaches to social and economic life. But it also brought digital risks and threats that placed new demands on policymakers. This article assembles evidence from different areas of social science expertise about the impacts of Covid-19 in digitised societies and policy responses. The authors show how the pandemic supported changes in data collection techniques and dissemination practices for official statistics, and how seemingly insuperable obstacles to the implementation of e-health treatments were largely overcome. They demonstrate how the ethics of artificial intelligence became a primary concern for government legislation at national and international levels, and how the features enabling smart cities to act as drivers of productivity did not necessarily give them an advantage during the pandemic. At the micro-level, families are shown to have become ‘digital by default’, as children were exposed to online risks and opportunities. Globally, the spread of the pandemic provided a fertile ground for cybercrime, while digital disinformation and influencing risked becoming normalised and domesticated.

Many countries around the world are undergoing massive urbanization campaigns at an unprecedented rate, heralded by promises of economical prosperity and bolstered population health and well-being. Projections indicate that by 2050, nearly 68% of the world populace will reside in these urban environments. However, rapid growth at such an exceptional scale poses unique challenges pertaining to environmental quality and food production, which can negate the effectiveness of the aforementioned boons. As such, there is an emphasis on mitigating these negative effects through the construction of smart and connected communities (S&CC), which integrate both artificial intelligence (AI) and the Internet of Things (IoT). This coupling of intelligent technologies also poses interesting system design challenges pertaining to the fusion of the diverse, heterogeneous datasets available to IoT environments, and the ability to learn multiple S&CC problem sets concurrently. Attention-based Transformer networks are of particular interest given their success across diverse fields of natural language processing (NLP), computer vision, time-series regression, and multi-modal data fusion in recent years. This begs the question whether Transformers can be further diversified to leverage fusions of IoT data sources for heterogeneous multi-task learning in S&CC trade spaces. This is a fundamental question that this thesis seeks to answer. Indeed, the key contribution of this thesis is the design and application of Transformer networks for developing AI systems in emerging smart cities. This is executed within a collaborative U.S.-Indonesia effort between Virginia Tech, the University of Colorado Boulder, the Universitas Gadjah Mada, and the Institut Teknologi Bandung with the goal of growing smart and sustainable garden alleys in Makassar City, Indonesia. Specifically, a proof-of-concept AI nerve-center is proposed using a backbone of pure-encoder Transformer architectures to learn a diverse set of tasks such as multivariate time-series regression, visual plant disease classification, and image-time-series fusion. To facilitate the data fusion tasks, an effective algorithm is also proposed to synthesize heterogeneous feature sets, such as multivariate time-series and time-correlated images. Moreover, a hyperparameter tuning framework is also proposed to standardize and automate model training regimes. Extensive experimentation shows that the proposed Transformer-based systems can handle various input data types via custom sequence embedding techniques, and are naturally suited to learning a diverse set of tasks. Further, the results also show that multi-task learners increase both memory and computational efficiency while maintaining comparable performance to both single-task variants, and non-Transformer baselines. This demonstrates the flexibility of Transformer networks to learn from a fusion of IoT data sources, their applicability in S&CC trade spaces, and their further potential for deployment on edge computing devices. / Master of Science / Many countries around the world are undergoing massive urbanization campaigns at an unprecedented rate, heralded by promises of economical prosperity and bolstered population health and well-being. Projections indicate that by 2050, nearly 68% of the world populace will reside in these urban environments. However, rapid growth at such an exceptional scale poses unique environmental and food cultivation challenges. Hence, there is a focus on reducing these negative effects through building smart and connected communities (S&CC). The term connected is derived from the integration of small, low-cost devices which gather information from the surrounding environment, called the Internet of Things (IoT). Likewise, smart is a term derived from the integration of artificial intelligence (AI), which is used to make informed decisions based on IoT-collected information. This coupling of intelligent technologies also poses its own unique challenges pertaining to the blending of IoT data with highly diverse characteristics. Of specific interest is the design of AI models that can not only learn from a fusion of this diverse information, but also learn to perform multiple tasks in parallel. Attention-based networks are a relatively new category of AI which learn to focus on, or attend to, the most important portions of an arbitrary data sequence. Transformers are AI models which are designed using attention as their backbone, and have been employed to much success in many fields in recent years. This success begs the question whether Transformers can be further extended to put the smart in S&CC. The overarching goal of this thesis is to design and implement a Transformer-based AI system for emerging smart cities. In particular, this is accomplished within a U.S.-Indonesia collaborative effort with the goal of growing smart and sustainable garden alleys in Makassar City, Indonesia.

Yes / The concept of smart city is emerging as a key strategy to tackle the problems generated by the urban population growth and rapid development. It is widely recognised that Information and Communications Technology (ICT) play a key role in addressing some of the urban societal challenges such as improving energy efficiency and reducing carbon emissions. Although there are various ICT tools providing intelligence and services relating to energy consumption and monitoring processes, they mostly tend to work in isolation. Therefore, this paper presents the outcomes and impacts of the concept of DAREED which aims to deliver an integrated ICT service platform to drive energy efficiency and low carbon activities at neighbourhood, city and district levels. Furthermore, the research highlights the need for ICT-driven policy making using platforms such as DAREED in the context of e-Government. This paper contributes to the current understandings of e-Government literature in terms of how ICT can help public authorities and stakeholders such as policy makers to achieve and drive energy efficiency. From a practical stance, the paper offers valuable insights to public administrations on how ICT can be used to address pressing societal challenges such as efficient energy use and facilitate better policy making.

Yes / The emerging information revolution makes it necessary to manage vast amounts of unstructured data rapidly. As the world is increasingly populated by IoT devices and sensors that can sense their surroundings and communicate with each other, a digital environment has been created with vast volumes of volatile and diverse data. Traditional AI and machine learning techniques designed for deterministic situations are not suitable for such environments. With a large number of parameters required by each device in this digital environment, it is desirable that the AI is able to be adaptive and self-build (i.e. self-structure, self-configure, self-learn), rather than be structurally and parameter-wise pre-defined. This study explores the benefits of self-building AI and machine learning with unsupervised learning for empowering big data analytics for smart city environments. By using the growing self-organizing map, a new suite of self-building AI is proposed. The self-building AI overcomes the limitations of traditional AI and enables data processing in dynamic smart city environments. With cloud computing platforms, the selfbuilding AI can integrate the data analytics applications that currently work in silos. The new paradigm of the self-building AI and its value are demonstrated using the IoT, video surveillance, and action recognition applications. / Supported by the Data to Decisions Cooperative Research Centre (D2D CRC) as part of their analytics and decision support program and a La Trobe University Postgraduate Research Scholarship.

Yes / The wider use of Internet of Things (IoT) makes it possible to create smart cities. The purpose of this paper is to identify key IoT challenges and understand the relationship between these challenges to support the development of smart cities. Design/methodology/approach: Challenges were identified using literature review, and prioritised and elaborated by experts. The contextual interactions between the identified challenges and their importance were determined using Interpretive Structural Modelling (ISM). To interrelate the identified challenges and promote IoT in the context of smart cities, the dynamics of interactions of these challenges were analysed using an integrated Matrice d’Impacts Croisés Multiplication Appliqués à un Classement (MICMAC)-ISM approach. MICMAC is a structured approach to categorise variables according to their driving power and dependence. Findings: Security and privacy, business models, data quality, scalability, complexity and governance were found to have strong driving power and so are key challenges to be addressed in sustainable cities projects. The main driving challenges are complexity and lack of IoT governance. IoT adoption and implementation should therefore focus on breaking down complexity in manageable parts, supported by a governance structure. Practical implications: This research can help smart city developers in addressing challenges in a phase-wise approach by first ensuring solid foundations and thereafter developing other aspects. Originality/value: A contribution originates from the integrated MICMAC-ISM approach. ISM is a technique used to identify contextual relationships among definite elements, whereas MICMAC facilitates the classification of challenges based on their driving and dependence power. The other contribution originates from creating an overview of challenges and theorising the contextual relationships and dependencies among the challenges.

Submitted by Fabio Sobreira Campos da Costa (fabio.sobreira@ufpe.br) on 2016-10-31T12:04:21Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) DissertacaoHerbertt_CIN_UFPE.pdf: 3162767 bytes, checksum: 3208dfce28e7404730479384c2ba99a0 (MD5) / Made available in DSpace on 2016-10-31T12:04:21Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) DissertacaoHerbertt_CIN_UFPE.pdf: 3162767 bytes, checksum: 3208dfce28e7404730479384c2ba99a0 (MD5) Previous issue date: 2016-03-04 / Cada vez mais se evidencia uma maior escassez de recursos e uma disputa por espaços físicos, em decorrência da crescente e demasiada concentração populacional nas grandes cidades. Nesse âmbito, surge a necessidade de soluções que vão de encontro à iniciativa de “Cidades Inteligentes" (Smart Cities). Essas soluções buscam centralizar o monitoramento e controle, para auxiliar no apoio à tomada de decisão. No entanto, essas fontes de TICs formam estruturas complexas e geram um grande volume de dados, que apresentam enormes desafios e oportunidades. Uma das principais ferramentas tecnológicas utilizadas nesse contexto é o Complex Event Processing (CEP), o qual pode ser considerado uma boa solução, para lidar com o aumento da disponibilidade de grandes volumes de dados, em tempo real. CEPs realizam captação de eventos de maneira simplificada, utilizando linguagem de expressão, para definir e executar regras de processamento. No entanto, apesar da eficiência comprovada dessas ferramentas, o fato das regras serem expressas em baixo nível, torna o seu uso exclusivo para usuários especialistas, dificultando a criação de soluções. Com intuito de diminuir a complexidade das ferramentas de CEP, em algumas soluções, tem-se utilizado uma abordagem de modelos Model-Driven Development (MDD), a fim de se produzir uma camada de abstração, que possibilite criar regras, sem que necessariamente seja um usuário especialista em linguagem de CEP. No entanto, muitas dessas soluções acabam tornando-se mais complexas no seu manuseio do que o uso convencional da linguagem de baixo nível. Este trabalho tem por objetivo a construção de uma Graphic User Interface (GUI) para criação de regras de CEP, utilizando MDD, a fim de tornar o desenvolvimento mais intuitivo, através de um modelo adaptado as necessidades do usuário não especialista. / Nowadays is Increasingly evident a greater resources scarcity and competition for physical space, in result of growing up and large population concentration into large cities. In this context, comes up the necessity of solutions that are in compliance with initiative of smart cities. Those solutions seek concentrate monitoring and control, for help to make decisions. Although, this sources of information technology and communications (ITCs) forming complex structures and generates a huge quantity of data that represents biggest challenges and opportunities. One of the main technological tools used in this context is the Complex Event Processing (CEP), which may be considered a good solution to deal with increase of the availability and large volume of data, in real time. The CEPs realizes captation of events in a simple way, using expressive languages, to define and execute processing rules. Although the efficient use of this tools, the fact of the rules being expressed in low level, becomes your use exclusive for specialists, difficulting the creation of solutions. With the aim of reduce the complexity of the CEPs tools, solutions has used an approach of models Model-Driven Development (MDD), in order to produce an abstraction layer, that allows to create rules, without necessarily being a specialist in CEP languages. however, many this tools become more complex than the conventional low level language approach. This work aims to build a Graphic User Interface (GUI) for the creation of CEP rules, using MDD, in order to a more intuitive development, across of the adapted model how necessities of the non specialist users.

A cidade de São Paulo é o município mais populoso do Brasil, caracterizado por uma segregação urbana responsável por inúmeros problemas relacionados a mobilidade urbana. As ações atuais para resolver os problemas de mobilidade urbana têm pouco aprofundamento em questões tecnológicas e melhorias dos sistemas computacio- nais existentes como as necessárias ao Sistema Integrado de Monitoramento e Transporte (SIM), utilizado para gestão e monitoramento do transporte público por ônibus de São Paulo. Uma das possíveis melhorias é integrar o SIM às Redes Sociais. Com essa perspectiva de integração, esse trabalho tem como objetivo uti- lizar tweets e dados do SIM na caracterização de eventos de exceção e de seus respectivos impactos no sistema de transporte público por ônibus da cidade de São Paulo. Para alcançar tal objetivo, esse trabalho propõe utilizar tweets publicados por instituições governamentais responsáveis por reportar eventos de exceção, dados dos módulos AVL (Automatic Vehicle Location) do SIM, responsáveis por rastrear e localizar os ônibus do município e GTFS (General Transit Feed Specification) da SPTrans. Visando alcançar o objetivo proposto, classificamos manualmente 60.984 tweets e treinamos diferentes modelos por meio de algoritmos de aprendizado de máquina supervisionado para identificar eventos de exceção. Além disso, propomos uma nova metodologia para extrair e geolocalizar os endereços dos eventos de exceção, por meio de Processamento de Língua Natural e Expressão Regular. Com isso, demonstramos que é possível correlacionar os dados desses eventos com os dados históricos do SIM e da GTFS, para caracterizar como o transporte público por ônibus da cidade de São Paulo é impactado nesses cenários. Adicionalmente, propomos uma arquitetura distribuída para exploração e visualização de grandes volumes de dados relacionados a transporte público / The city of São Paulo is the most populous municipality in Brazil, characterized by an urban segregation responsible for numerous problems related to urban mobility. The current actions to solve the problems of urban mobility have little deepening in technological issues and improvements of existing computer systems such as those required for the Integrated Monitoring and Transport System (in the Portuguese acronym: SIM), used for the management and monitoring of public transport by buses of the city of São Paulo. One of the possible improvements is integrating the SIM with Social Networks. With this perspective of integration, this work aims to use tweets and data from SIM in the characterization of exception events and their respective impacts on the public transport system by buses of the city of São Paulo. In order to achieve this objective, this work proposes to use tweets published by governmental institutions responsible for reporting exception events, data from SIM Automatic Vehicle Location (AVL) modules, responsible for the tracking and locating of urban buses and data from SPTrans GTFS (General Transit Feed Specification). In order to reach the proposed goal, we manually classified 60,984 tweets and trained different models through supervised machine learning algorithms to identify exception events. In addition, we propose a new methodology to extract and geolocalize the addresses of the exception events, through Natural Language Processing and Regular Expression. Using that approaches, we show that it is possible to correlate the data of these events with the historical data of the SIM and GTFS, to characterize how the public transport by bus of the city of São Paulo is impacted in these scenarios. Additionally, we propose a distributed architecture for exploration and visualization of large volumes of data related to public transport

The volume of information in the Internet is growing exponentially. The ability to find intelligible information among vast amounts of data is transforming the human vision of the universe and everything within it. The underlying question then becomes which methods or techniques can be applied to transform the raw data into something intelligible, active and personal? This question is explored in this document by investigating techniques that improve intelligence for systems in order to make them perceptive/active to the recent information shared by each individual. Consequently, the main objective of this thesis is to enhance the experience of the user (individual) by providing a broad perspective about an event, which could result in improved ideas and better decisions. Therefore, three different data sources (individual data, sensor data, web data) have been investigated. This thesis includes research into techniques that process, interpret and reduce these data. By aggregating these techniques into a platform it is possible to deliver personalised information to applications and services. The contribution of this thesis is twofold. First, it presents a novel process that has shifted its focus from IoT technology to the user (or smart citizen). Second, this research shows that huge volumes of data can be reduced if the underlying sensor signal has adequate spectral properties to be filtered and good results can be obtained when employing a filtered sensor signal in applications. By investigating these areas it is possible to contribute to this new interconnected society by offering socially aware applications and services. / Sem resumo