The Internet of Things (IoT) is a network of interconnected devices and objects that have various functions,such as sensing, identifying, computing, providing services and communicating. It is estimated that by the year 2030, there will be approximately 29.42 billion IoT devices globally, facilitating extensive data exchange among them. In response to this rapid growth of IoT, Artificial Intelligence (AI) has become a pivotal technology in automating key aspects of IoT systems, including decision-making, predictive data analysis among others. The widespread use of AI across various industries has brought about significant transformations in business ecosystems. Despite its immense potential, IoT systems still face several challenges. These challenges encompass concerns related to privacy and security, data management, standardization issues, trust among others. Looking at these challenges, AI emerges as an essential enabler, enhancing the intelligence and sophistication of IoT systems. Its diverse applications offer effective solutions to address the inherent challenges within IoT systems. This, in turn, leads to the optimization of processes and the development of more intelligent and smart IoT systems.This thesis presents a semi-systematic literature review (SSLR) that aims to explore the role of AI in IoT systems. A systematic search was performed on three (3) databases (Scopus, IEEE-Xplore and the ACM digital library), 29 scientific and peer reviewed studies published between 2018-2022 were selected and examined to provide answers to the research questions. This study also encompasses an additional study within the context of AI and trustworthiness in IoT systems, user acceptance within IoT systems and AIoT's impact on sustainable economic growth across industries. This thesis also presents the DIMACERI Framework which encompasses eight dimensions of IoT challenges and concludes with recommendations for stakeholders in AIoT systems. AI is strategically integrated across the DIMACERI dimensions to create reliable, secure and efficient IoT systems.

Yes / The technological choices facing the manufacturing industry are vast and complex as the industry contemplates the increasing levels of digitization and automation in readiness for the modern competitive age. These changes broadly categorized as Industry 4.0, offer significant transformation challenges and opportunities, impacting a multitude of operational aspects of manufacturing organizations. As manufacturers seek to deliver increased levels of productivity and adaptation by innovating many aspects of their business and operational processes, significant challenges and barriers remain. The roadmap toward Industry 4.0 is complex and multifaceted, as manufacturers seek to transition toward new and emerging technologies, whilst retaining operational effectiveness and a sustainability focus. This study approaches many of these significant themes by presenting a critical evaluation of the core topics impacting the next generation of manufacturers, challenges and key barriers to implementation. These factors are further evaluated via the presentation of a new Industry 4.0 framework and alignment of I4.0 themes with the UN Sustainability Goals.

Asthma, a chronic respiratory disease affecting millions of people worldwide, can vary in severity depending on individual triggers such as Carbon Dioxide, Particulate Matter, dust mites, tobacco smoke, and indoor household activities such as cooking, cleaning, use of heating, and window opening, which can have a negative impact on indoor air quality (IAQ) and exacerbate asthma symptoms. Investigating the relationship between IAQ and asthma severity, a case study was conducted on five asthmatic participants from Bradford, UK. IAQ was measured using IoT indoor air quality monitoring devices. Indoor activities were recorded using a daily household activities questionnaire, and asthma severity was assessed using the Asthma Control Questionnaire (ACQ). Machine learning prediction models were used to analyse various IAQ parameters, such as particulate matter, carbon dioxide, and humidity levels, to identify the most significant predictors of asthma severity with IAQ. The study aimed to develop targeted interventions to improve IAQ and reduce the burden of asthma. Results showed that higher asthma severity scores were associated with increased indoor activity and higher levels of indoor air pollution. Some interventions were implemented to improve ventilation hours, significantly improving IAQ and reducing asthma symptoms, particularly those with more severe asthma. The findings indicate that interventions targeting IAQ, and indoor activities can effectively reduce asthma severity, with up to a 60% reduction in symptoms for asthma patients.

Balancing indoor comfort and energy consumption is crucial to building energy efficiency. Occupancy information is a vital aspect in this process, as it determines the energy demand. Although there are various sensors used to gather occupancy information, environmental sensors stand out due to their low cost and privacy benefits. Machine learning algorithms play a critical role in estimating the relationship between occupancy levels and environmental data. To improve performance, more complex models such as deep learning algorithms are necessary. Long Short-Term Memory (LSTM) is a powerful deep learning algorithm that has been utilized in occupancy estimation. However, recently, an algorithm named Attention has emerged with improved performance. The study proposes a more effective model for occupancy level estimation by incorporating Attention into the existing Long Short-Term Memory algorithm. The results show that the proposed model is more accurate than using a single algorithm and has the potential to be integrated into building energy control systems to conserve even more energy. / Master of Science / The motivation for energy conservation and sustainable development is rapidly increasing, and building energy consumption is a significant part of overall energy use. In order to make buildings more energy efficient, it is necessary to obtain information on the occupancy level of rooms in the building. Environmental sensors are used to measure factors such as humidity and sound to determine occupancy information. However, the relationship between sensor readings and occupancy levels is complex, making it necessary to use machine learning algorithms to establish a connection. As a subfield of machine learning, deep learning is capable of processing complex data. This research aims to utilize advanced deep learning algorithms to estimate building occupancy levels based on environmental sensor data.

A future Internet of Things (IoT) system will consist of a huge quantity of heterogeneous IoT devices, each capable of providing services upon request. It is of utmost importance for an IoT device to know if another IoT service is trustworthy when requesting it to provide a service. In this dissertation research, we develop trust-based service management techniques applicable to distributed, centralized, and hybrid IoT environments. For distributed IoT systems, we develop a trust protocol called Adaptive IoT Trust. The novelty lies in the use of distributed collaborating filtering to select trust feedback from owners of IoT nodes sharing similar social interests. We develop a novel adaptive filtering technique to adjust trust protocol parameters dynamically to minimize trust estimation bias and maximize application performance. Our adaptive IoT trust protocol is scalable to large IoT systems in terms of storage and computational costs. We perform a comparative analysis of our adaptive IoT trust protocol against contemporary IoT trust protocols to demonstrate the effectiveness of our adaptive IoT trust protocol. For centralized or hybrid cloud-based IoT systems, we propose the notion of Trust as a Service (TaaS), allowing an IoT device to query the service trustworthiness of another IoT device and also report its service experiences to the cloud. TaaS preserves the notion that trust is subjective despite the fact that trust computation is performed by the cloud. We use social similarity for filtering recommendations and dynamic weighted sum to combine self-observations and recommendations to minimize trust bias and convergence time against opportunistic service and false recommendation attacks. For large-scale IoT cloud systems, we develop a scalable trust management protocol called IoT-TaaS to realize TaaS. For hybrid IoT systems, we develop a new 3-layer hierarchical cloud structure for integrated mobility, service, and trust management. This architecture supports scalability, reconfigurability, fault tolerance, and resiliency against cloud node failure and network disconnection. We develop a trust protocol called IoT-HiTrust leveraging this 3-layer hierarchical structure to realize TaaS. We validate our trust-based IoT service management techniques developed with real-world IoT applications, including smart city air pollution detection, augmented map travel assistance, and travel planning, and demonstrate that our trust-based IoT service management techniques outperform contemporary non-trusted and trust-based IoT service management solutions. / Ph. D.

Internet of Things (IoT) är en växande teknologi som spelar en allt större roll i samhället. Den innefattar ett nätverk av internetanslutna enheter som samlar in och utbyter data. Samtidigt som IoT växer uppstår utmaningar kring hantering av stora datamängder och säkerhetsaspekter. Företaget Softhouse står inför utmaningen att välja en effektiv tidsseriedatabas för hantering av temperatur- och geopositionsdata från värmesystem i privata bostäder, där både prestanda och dataintegritet via kryptering är av stor vikt. Detta examensarbete har därför utfört en prestandajämförelse mellan AWSTimestream och InfluxDB, där olika tester har använts för att mäta exekveringstiden för inskrivning av sensordata och databasfrågor. Jämförelsen inkluderar AWS Timestream i krypterad form mot InfluxDB i dess AWS-molnversion i krypterad form, samt InfluxDB AWS i krypterad form mot InfluxDB i okrypterad form. Syftet med studien var att ge riktlinjer för valet av tidsseriedatabaser med fokus på prestanda och säkerhetsaspekter, inklusivekryptering. Studien undersökte även hur valet av rätt databas påverkar företag som Softhouse, både i termer av kvantitativa och kvalitativa fördelar, samt att ge en bedömning av kostnaderna. Resultatet visade att InfluxDB i dess AWS-molnversion generellt presterade bättre än AWS Timestream och InfluxDB i dess standardversion. Det fanns tydliga skillnader i prestanda mellan AWS Timestream och InfluxDB i dess AWS-molnversion, men inte lika tydliga skillnader i prestanda mellan InfluxDB i dess AWS-molnversion och standardversionen. Med hänsyn till både prestanda och säkerhet framstår InfluxDB i dess AWS-molnversion som det mest lämpliga alternativet. Det är emellertid av stor vikt att ta kostnadaspekten i beaktande, då AWS Timestream visar sig vara avsevärt mer kostnadseffektivt än InfluxDB. / The Internet of Things (IoT) is a growing technology that plays an increasingly significant role in society. It encompasses a network of internet-connected devices that collect and exchange data. As IoT continues to expand, challenges arise regarding the management of large volumes of data and security aspects. The company Softhouse faces the challenge of choosing an efficient time-series database for handling temperature and geoposition data from heating systems in homes, where both performance and data integrity through encryption are of great importance. Therefore, this thesis has conducted a performance comparison between AWS Timestream and InfluxDB, using various tests to measure the execution times for data ingestion of sensor data and database queries. The comparison includes AWS Timestream in encrypted form versus InfluxDB in its AWS cloud version in encrypted form, as well as InfluxDB AWS in encrypted form versus InfluxDB in unencrypted form. The aim of the study was to provide guidelines for the selection of time-series databases with a focus on performance and security aspects, including encryption. The study also explored how the choice of the right database affects companies like Softhouse, both in terms of quantitative and qualitative benefits, and provided an assessment of costs. The results showed that InfluxDB in its AWS cloud version generally outperformed AWS Timestream and InfluxDB in its standard version. There were clear performance differences between AWS Timestream and InfluxDB in its AWS cloud version, but not as pronounced differences in performance between InfluxDB in itsAWS cloud version and the standard version. Considering both performance and security, InfluxDB in its AWS cloud version appears to be the most suitable option. However, it is crucial to consider the cost aspect, as AWS Timestream proves to be significantly more cost-effective than InfluxDB.

This thesis introduces the circuit and system design of interactive Radio-Frequency Identification (RFID) for Internet of Things (IoT) applications. IoT has the vision of connectivity for anything, at anytime and anywhere. One of the most important characteristics of IoT is the automatic and massive interaction of real physical world (things and human) with the virtual Internet world.RFID tags integrated with sensors have been considered as one suitable technology for realizing the interaction. However, while it is important to have RFID tags with sensors as the input interaction, it is also important to have RFID tags with displays as the output interaction.Display interfaces vary based on the information and application scenarios. On one side, remote and centralized display interface is more suitable for scenarios such as monitoring and localization. On the other side, tag level display interface is more suitable for scenarios such as object identification and online to offline propagation. For tag level display, though a substantial number of researches have focused on introducing sensing functionalities to low power Ultra-High Frequency (UHF) RFID tags, few works address UHF RFID tags with display interfaces. Power consumption and integration with display of rigid substrate are two main challenges.With the recent emerging of Electronic Paper Display (EPD) technologies, it becomes possible to overcome the two challenges. EPD resembles ordinary ink on paper by characteristics of substrate flexibility, pattern printability and material bi-stability. Average power consumption of display is significantly reduced due to bi-stability, the ability to hold color for certain periods without power supplies. Among different EPD types, Electrochromic (EC) display shows advantage of low driving voltage compatible to chip supply voltage.Therefore this thesis designs a low power UHF RFID tag integrated in 180 nm CMOS process with inkjet-printed EC polyimide display. For applications where refresh rate is ultra-low (such as electronic label in retailing and warehouse), the wireless display tag is passive and supplied by the energy harvested from UHF RF wave. For applications where refresh rate is not ultra-low (such as object identification label in mass customized manufacturing), the wireless display tag is semi-passive and supplied by soft battery. It works at low average power consumption and with out-of-battery alert. For remote and centralized display, the limitations of uplink (from tags to reader) capacity and massive-tag information feedback in IoT scenarios is the main challenge. Compared to conventional UHF RFID backscattering whose data rate is limited within hundreds of kb/s, Ultra-wideband (UWB) transmission have been verified with the performance of Mb/s data rate with several tens of pJ/pulse energy consumption.Therefore, a circuit prototype of UHF/UWB RFID tag replacing UHF backscattering with UWB transmitter is implemented. It also consists of Analog-to-Digital Converter (ADC) and Electrocardiogram (ECG) electrodes for healthcare applications of real-time remote monitoring of multiple patients ECG signals. The ECG electrodes are fabricated on paper substrate by inkjet printing to improve patient comfort. Key contribution of the thesis includes: 1) the power management scheme and circuit design of passive UHF/UWB RFID display tag. The tag sensitivity (the input RF power) is -10.5 dBm for EC display driving, comparable to the performance of conventional passive UHF RFID tags without display functions, and -18.5 dBm for UWB transmission, comparable to the state-of-the-art performance of passive UHF RFID tag. 2) communication flow and circuit design of UHF/UWB RFID tag with ECG sensing. The optimum system throughout is 400 tags/second with 1.5 KHz ECG sampling rate and 10 Mb/s UWB pulse rate. / <p>QC 20151012</p>

abstract: With the increasing user demand for low latency, elastic provisioning of computing resources coupled with ubiquitous and on-demand access to real-time data, cloud computing has emerged as a popular computing paradigm to meet growing user demands. However, with the introduction and rising use of wear- able technology and evolving uses of smart-phones, the concept of Internet of Things (IoT) has become a prevailing notion in the currently growing technology industry. Cisco Inc. has projected a data creation of approximately 403 Zetabytes (ZB) by 2018. The combination of bringing benign devices and connecting them to the web has resulted in exploding service and data aggregation requirements, thus requiring a new and innovative computing platform. This platform should have the capability to provide robust real-time data analytics and resource provisioning to clients, such as IoT users, on-demand. Such a computation model would need to function at the edge-of-the-network, forming a bridge between the large cloud data centers and the distributed connected devices. This research expands on the notion of bringing computational power to the edge- of-the-network, and then integrating it with the cloud computing paradigm whilst providing services to diverse IoT-based applications. This expansion is achieved through the establishment of a new computing model that serves as a platform for IoT-based devices to communicate with services in real-time. We name this paradigm as Gateway-Oriented Reconfigurable Ecosystem (GORE) computing. Finally, this thesis proposes and discusses the development of a policy management framework for accommodating our proposed computational paradigm. The policy framework is designed to serve both the hosted applications and the GORE paradigm by enabling them to function more efficiently. The goal of the framework is to ensure uninterrupted communication and service delivery between users and their applications. / Dissertation/Thesis / Masters Thesis Computer Science 2015

<p>Developing resiliency in supply chains became vital in the recent years due to global diversification and vulnerability to risks. Firms need to identify, evaluate, and mitigate risks in supply chain to maintain continuity and create competitive advantage. Although the problem of supply chain disruptions has existed for a long time, less attention has been given by researchers in exploring the adoption of advanced technologies to build resilient supply chains. This study explored the potential of mitigating supply chain disruptions with the use of Industry 4.0 technologies such as Internet of Things (IoT) and Supply chain data analytics platform which develops digital twin environment for supply chains. </p> <p><br></p> <p>This research gathered expert’s opinion on the resilience capabilities developed in supply chain by digital twin adoption, stages and practices involved in digital twin assimilation through Delphi survey with subject matter experts and supply chain practitioners. Semi-structured interviews were conducted with participants to attain deep understanding on the resilience capabilities gained by digital twin and stages in digital twin adoption. Comparison of the results from Delphi survey and interviews was carried out to synthesize the results to yield a comprehensive understanding of resilience capabilities gained through digital twin and adoption stages of supply chain digital twin. This research has conducted interviews with 21 subject matter experts and completed three rounds of Delphi survey (with participants n = 15, 11, 11 in three rounds respectively) to develop a framework for digital twin adoption to enhance supply chain resilience. </p> <p><br></p> <p>This research determined that digital twin develops real-time monitoring and sensing capabilities, planning and decision support system, and automating decisions and action execution capabilities in supply chain. In addition, digital twin positively impacts resilience elements such as agility, supply chain reconfiguration, robustness, and collaboration in supply chain, which improves the supply chain performance. The results from this study were utilized to develop a framework for enabling supply chain resilience through digital twin. The framework included antecedents, consequences, and various moderators that impact digital twin adoption and diffusion in supply chains. Finally, this research developed a five-stage roadmap for adopting digital twin capabilities in supply chain. </p>

Wireless sensor networks (WSNs) groups specialized transducers that provide sensing services to Internet of Things (IoT) devices with limited energy and storage resources. Since replacement or recharging of batteries in sensor nodes is almost impossible, power consumption becomes one of the crucial design issues in WSN. Clustering algorithm plays an important role in power conservation for the energy constrained network. Choosing a cluster head (CH) can appropriately balance the load in the network thereby reducing energy consumption and enhancing lifetime. This paper focuses on an efficient CH election scheme that rotates the CH position among the nodes with higher energy level as compared to other. The algorithm considers initial energy, residual energy, and an optimum value of CHs to elect the next group of CHs for the network that suits for IoT applications, such as environmental monitoring, smart cities, and systems. Simulation analysis shows the modified version performs better than the low energy adaptive clustering hierarchy protocol by enhancing the throughput by 60%, lifetime by 66%, and residual energy by 64%.