This thesis was prepared in collaboration with Acreo (Research and Development Company) and OpenCare (IT Company). Its purpose was to design and develop a research testbed to enable context awareness in pervasive environments by modifying the MediaSense framework (EU Funded project) of Mid Sweden University. In ubiquitous environments, the proliferation of devices such as sensors, active badges, mobile phones, RFID and NfC tags enables the development of intelligent services towards new forms of pervasive applications. These intelligent services seamlessly gather context information and the benefits offered are in the provision of better services. The inspiration given by these intelligent services has meant that the focus of thesis has been on using these services in a healthcare application. The challenge is that the proposed testbed should address the intelligent delivery of health information to any host, anywhere, based on the user’s context. Further, context reasoning requires substantial computing power and smart devices have limited resources in terms of processing and memory, so, the testbed should enable smart communication to take place between these devices. The proposed solution satisfies the stated requirements by using a cloud infrastructure and a Distributed Context eXchange Protocol (DCXP). Any device on the internet that is DCXP capable may register with the architecture and share context information in an efficient way. In order to view context information, TV, smartphones, internet tablets and web interfaces have been provided for both the user and the health centre. By successfully addressing the requirements of the testbed, this thesis has enabled the creation of a pervasive healthcare application. Hence, this thesis concludes with the observation that the proposed approach for context awareness in a healthcare system has the ability to deal with the stated challenges.

Abstract Ubiquitous computing transforms physical environments into smart spaces, supporting users in an unobtrusive fashion. Such support requires sensing and interpreting the situation of the user, and providing the required functionality utilizing resources available. In other words, context acquisition, context modelling, and context reasoning are required. This thesis explores rule-based context reasoning from three perspectives: to implement the functionality of ubiquitous applications, to support the creation of ubiquitous applications, and to achieve self-adaptation. First, implementing functionality with reasoning is studied by comparing an application equipped with rule-based reasoning with an application providing similar functionality with hard coded application logic. The scalability of rule-based reasoning is studied with a large-scale student assistant scenario. Reasoning with constrained resources is explored with an application that performs reasoning partially on mobile devices. Finally, distributing a reasoning component that supports smart space interaction is explored with centralized, hybrid, and distributed architectures. Second, the creation of applications with rule-based reasoning is explored. In the first study, rules support building applications from available services and resources based on the instructions that users give via physical user interfaces. The second study supports developers, by proposing middleware that dynamically selects services and data based on the rules written by application developers. Third, self-adaptation is explored with a conceptual framework that adds self-introspective monitoring and control to smart space applications. This framework is verified with simulation and theoretical studies, and an application that fuses diverse data to provide fuel-efficient driving recommendations and adapts decision-making based on the driver’s progress and feedback. The thesis’ contributions include demonstrative cases on using rule-based reasoning from different perspectives, different scales, and with different architectures. Frameworks, a middleware, simulations, and prototypes provide the concrete contribution of the thesis. Generally, the thesis contributes to understanding how rule-based reasoning can be used in ubiquitous computing. The results presented can be used as guidelines for developers of ubiquitous applications. / Tiivistelmä Jokapaikan tietotekniikka muokkaa fyysisen ympäristömme älykkääksi tilaksi, joka tukee käyttäjää häntä häiritsemättä. Tuki toteutetaan asentamalla ympäristöön käyttäjää ja ympäristöä havainnoivia laitteita, tulkitsemalla kerätyn tiedon perusteella käyttäjän tilanne ja tarjoamalla tilanteeseen sopiva toiminnallisuus käyttäen saatavilla olevia resursseja. Toisin sanoen, älykkään tilan on kyettävä tunnistamaan ja mallintamaan toimintatilanne sekä päättelemään toimintatilanteen perusteella. Tässä työssä tutkitaan sääntöpohjaista päättelyä toimintatilanteen perusteella sovellusten toiminnallisuuden toteutuksen, kehittämisen tuen sekä mukautuvuuden näkökulmista. Sovellusten toiminnallisuuden toteuttamista päättelemällä tutkitaan vertaamalla sääntöpohjaisen päättelyn avulla toteutettua toiminnallisuutta vastaavaan suoraan sovellukseen ohjelmoituun toiminnallisuuteen. Sääntöpohjaisen päättelyn skaalautuvuutta arvioidaan laajamittaisessa opiskelija-assistenttiskenaariossa. Niukkojen resurssien vaikutusta päättelyyn arvioidaan päättelemällä osittain mobiililaitteessa. Älykkään tilan vuorovaikutusta tukevan päättelykomponentin hajauttamista tutkitaan keskitetyn, hybridi- ja hajautetun arkkitehtuurin avulla. Sovelluskehityksen tukemiseksi päättelyn säännöt muodostetaan saatavilla olevista palveluista ja resursseista käyttäjän fyysisen käyttöliittymän välityksellä antamien ohjeiden mukaisesti. Toisessa tapauksessa sovelluskehitystä tuetaan väliohjelmistolla, joka valitsee palvelut ja datan dynaamisesti sovelluskehittäjien luomien sääntöjen perusteella. Mukautuvuutta tutkitaan tilan hallintaan ja itsehavainnointiin liittyvän toiminnallisuuden lisäämiseen pystyvän käsitteellisen kehyksen avulla. Kehyksen toiminta varmennetaan simulointien sekä teoreettisten tarkastelujen avulla. Toteutettu useita datalähteitä yhdistävä sovellus antaa ajoneuvon kuljettajalle polttoaineen kulutuksen vähentämiseen liittyviä suosituksia sekä mukautuu kuljettajan ajotavan kehityksen ja palautteen perusteella. Työssä on osoitettu sääntöpohjaisen päättelyn toimivuus eri näkökulmista, eri skaalautuvuuden asteilla sekä eri arkkitehtuureissa. Työn konkreettisia tuloksia ovat kehykset, väliohjelmistot, simuloinnit sekä prototyypit. Laajemmassa mittakaavassa työ edesauttaa ymmärtämään sääntöpohjaisen päättelyn soveltamista ja työn tuloksia voidaankin käyttää suosituksina sovelluskehittäjille.

Advances in mobile and pervasive computing, electronics technology, and the exponential growth in Internet of Things (IoT) applications and services has led to Building Automation System (BAS) that enhanced the buildings we live by delivering more energy-saving, intelligent, comfortable, and better utilization. Through the use of integrated protocols, a BAS can interconnects a wide range of building assets so that the control and management of asset operations and their services can be performed in one protocol. Moreover, through the use of distributed computing and IP based communication, a BAS can implement remote monitor and control in adaptive and real-time manner. However, the use of IoT and distributed computing techniques in BAS are leading to challenges to secure and protect information and services due to the significant increase in the attack surface and the inherent vulnerabilities of BAS integrated protocols. Since there is no intrusion detection and prevention available for BAS network, proposing a reliable security mechanism which can monitor the behavior of BAS assets becomes a major design issue. Anomaly Based Intrusion Detection is a security mechanism that uses baseline model to describe the normal behaviors of a system, so that malicious behaviors occurred in a system can be detected by comparing the observed behavior to the baseline model. With its ability of detecting novel and new attacks, Anomaly based Behavior Analysis (ABA) has been actively pursued by researchers for designing Intrusion Detection Systems. Since the information acquired from a BAS system can be from a variety of sources (e.g. sensors, network protocols, temporal and spatial information), the traditional ABA methodology which merely focuses on analyzing the behavior of communication protocols will not be effective in protecting BAS networks. In this dissertation we aim at developing a general methodology named Context Aware Anomaly based Behavior Analysis (CAABA) which combines Context Awareness technique with Anomaly based Behavior Analysis in order to detect any type of anomaly behaviors occurred in Building Automation Systems. Context Awareness is a technique which is widely used in pervasive computing and it aims at gathering information about a system's environment so it can accurately characterize the current operational context of the BAS network and its services. The CAABA methodology can be used to protect a variety of BAS networks in a sustainable and reliable way. To handle the heterogeneous BAS information, we developed a novel Context Aware Data Structure to represent the information acquired from the sensors and resources during execution of the BAS system which can explicitly describe the system's behavior. By performing Anomaly based Behavior Analysis over the set of context arrays using either data mining algorithm or statistical functions, the BAS baseline models are generated. To validate our methodology, we have applied it to two different building application scenarios: a smart building system which is usually implemented in industrial and commercial office buildings and a smart home system which is implemented in residential buildings, where we have achieved good detection results with low detection errors.

Context represents any knowledge obtained from Wireless Sensor Networks (WSNs) about the object being monitored (such as time and location of the sensed events). Time and location are important constituents of context as the information about the events sensed in WSNs is comprehensive when it includes spatio-temporal knowledge. In this thesis, we first concentrate on the development of a suite of lightweight algorithms on temporal event ordering and time synchronization as well as localization for WSNs. Then, we propose an energy-efficient clustering routing protocol for WSNs that is used for message delivery in the former algorithm. The two problems - temporal event ordering and synchronization - are dealt with together as both are concerned with preserving temporal relationships of events in WSNs. The messages needed for synchronization are piggybacked onto the messages exchanged in underlying algorithms. The synchronization algorithm is tailored to the clustered topology in order to reduce the overhead of keeping WSNs synchronized. The proposed localization algorithm has an objective of lowering the overhead of DV-hop based algorithms by reducing the number of floods in the initial position estimation phase. It also randomizes iterative refinement phase to overcome the synchronicity of DV-hop based algorithms. The position estimates with higher confidences are emphasized to reduce the impact of erroneous estimates on the neighbouring nodes. The proposed clustering routing protocol is used for message delivery in the proposed temporal algorithm. Nearest neighbour nodes are employed for inter-cluster communication. The algorithm provides Quality of Service by forwarding high priority messages via the paths with the least cost. The algorithm is also extended for multiple Sink scenario. The suite of algorithms proposed in this thesis provides the necessary tool for providing spatio-temporal context for context-aware WSNs. The algorithms are lightweight as they aim at satisfying WSN's requirements primarily in terms of energy-efficiency, low latency and fault tolerance. This makes them suitable for emergency response applications and ubiquitous computing.

With growing number of devices connected to the network, there is a greater need for use of Peer-to-Peer (P2P) networks and distributed P2P protocols.Devices participating in the P2P network do not usually need to use any central server that links up connections. It has many advantages but it needs to use so-called overlay network that consists of protocols used for traffic routing and decision making. Protocols used in today’s P2P networks are mostly not considerate of particular participating nodes and all the nodes in the network are usually equal. This can have negative impacts on network performance. In order to avoid or reduce some unwanted negative impacts, it would be advantageous if the overlay network could route traffic and make decisions according to context information like battery levels or connection speeds. This work reviews a few popular P2P overlay networks and based on that it introduces an improvement of one of them – Chord. The structure of the improved version of the Chord protocol called Context-Aware Chord is described. Then results of the evaluation are presented. With a use of the improved protocol, nodes can participate longer in the network and throughput of lookup messages is improved.

Context-aware computing requires software that can adapt to changes in context. When contextual circumstances trigger multiple adaptations, software must also understand the relationships between these adaptations and react according to the rules governing these relationships. Adaptable software needs a means to establish and interpret these rules in order to avoid any undesirable and potentially catastrophic conflicts. This dissertation designs and implements the Adaptation Rules Management API (ArmAPI). ArmAPI has been demonstrated to work with a Context-Oriented Programming variation for Java called ContextJ* to execute conflict-free adaptations in two software applications. ArmAPI allows programmers to define relationship types between adaptations, and transfers these definitions to Prolog facts and rules. The Prolog engine, encapsulated within ArmAPI, then works with imperative algorithms to determine the appropriate adaptations to execute based on the current set of facts, rules, and contextual circumstances. Context represents all of the conditions for all of the entities known to an observing device. In any environment, context represents a large amount of data that can influence a multitude of conflicting adaptations. This research provides an incremental step towards overcoming the problem of adaptation conflict by constructing an API that considers the relationship types of inclusion, exclusion, ordering, conditional dependency, and independence. The API has been validated via two prototypes that provide typical scenarios.

Campus universitários são ambientes compostos de recursos e pessoas que utilizam os tais. Um dos principais recursos utilizados pela comunidade de um campus são os objetos de aprendizagem. Tais objetos existem de maneira abundante, espalhados no ambiente ou concentrados em um único local. Entretanto, a abundancia desses objetos faz com que uma pessoa sinta-se cognitivamente cansada ao ter que analisar vários objetos e selecionar apenas alguns. Esse cansaço cognitivo acaba levando a pessoa a escolher um conjunto de objetos de aprendizagem que não satisfarão suas necessidades e interesses da melhor maneira possível. A computação evoluiu de grandes mainframes a pequenos computadores espalhados em um ambiente. Hoje é possível a existência de ambientes pervasivos, onde os recursos computacionais estão sempre presentes e agindo de forma invisível ao usuário. Tais ambientes tornam possível o acompanhamento das atividades do usuário, provendo informações contextuais que podem ser utilizadas para ajudar a seleção dos melhores recursos (ex. objetos de aprendizagem, restaurantes, salas de aula) à determinada pessoa. A localização é uma informação contextual de grande importância na seleção de tais recursos. Tal informação pode ser facilmente obtida através do sinal de GPS do dispositivo móvel de um usuário e utilizada em conjunto com os interesses do usuário para recomendar os recursos próximos que melhor atenderão ao mesmo. Neste contexto este trabalho descreve uma abordagem para recomendar objetos de aprendizagem físicos ou virtuais que estejam relacionados aos prédios próximos a atual localização do usuário. Para executar tal tarefa é descrito um sistema de recomendação que utiliza a informação de localização, obtida através do dispositivo móvel do usuário, combinada à informações do perfil do usuário, dos objetos de aprendizagem relacionados aos prédios e informações tecnológicas do dispositivo para instanciar um modelo ontológico de contexto. Após instanciado o modelo são utilizadas regras semânticas, escritas em forma de antecedente e consequente, que fazem uma correspondência entre os interesses do usuário e o domínio de conhecimento do objeto de aprendizagem para filtrar os objetos próximos ao usuário. De posse desses objetos recomendados o sistema os apresenta em uma interface adaptativa que mostra a localização tanto dos objetos quanto do usuário. Para validar a abordagem apresentada é desenvolvido um estudo de caso onde as regras semânticas de recomendação são executadas sobre o modelo ontológico desenvolvido. O resultado gerado por tais regras é um conjunto de pares (usuário, objeto de aprendizagem recomendado) e prova a validade da abordagem. / University campus are environments composed of resources and people who use them. One of the main resources used by a campus community are learning objects. Such objects are abundantly even scattered in the environment or concentrated in one location. However the abundance of such objects makes a person feel cognitively tired when having to analyze various objects and select just a few of them. This cognitive fatigue eventually leads the person to choose a set of learning objects that do not meet their needs and interests in the best possible way. Computing has evolved from large mainframe to small computers scattered in an environment. Today it is possible the existence of pervasive environments where computational resources are always present and acting in a manner invisible to the user. Such environments make it possible to monitor user activities, providing contextual information that can be used to help select the best resources (e.g. learning objects, restaurants, classrooms) to a particular person. The location is a contextual information of great importance in the selection of such resources. Such information can be easily obtained through the GPS signal from a mobile device and used with the user’s interests to recommend the nearby resources that best attend his needs and interests. In this context, this work describes an approach to recommend physical or virtual learning objects that are related to buildings near the user’s current location. To accomplish such a task we described a recommender system that uses the location information, obtained through the user's mobile device, combined with information from the user’s profile, learning objects related to buildings and technological information from the device to instantiate an ontological context model. Once the model is instantiated we used semantic rules, written in the form of antecedent and consequent, to make a match between the user’s interests and the knowledge domain of the learning object in order filter the user’s nearby objects. With such recommended objects, the system presents them in an adaptive interface that shows both the object and the user location. To validate the presented approach we developed a case study where the recommendation semantic rules are executed on the developed ontological model. The income generated by such rules is a set of pairs (user, recommended learning object) and proves the validity of the approach.

O trabalho apresentado nesta dissertação trata do desenvolvimento de um mecanismo para adaptação automática de ví?deo MPEG-4 ao vivo, de modo a atender as necessidades ou capacidades atuais de usuários e do sistema. Um dos desafios dessa área é capturar e representar as informações necessárias para realizar a adaptação. Assim, utilizando técnicas da área de computação ciente de contexto, foi desenvolvido um modelo extensível para representação de dispositivos. Também foram desenvolvidos métodos automáticos e semi-automáticos para capturar as informações necessárias. Neste trabalho foi adotado o modelo de recodificação de vídeo, o qual pode gerar atrasos que inviabilizam a adaptação de vídeo ao vivo em aplicações interativas. Assim, este trabalho realizou uma avaliação do impacto causado pela recodificação no atraso total, fim-a-fim, percebido pelo usuário. / This work presents the development of a mechanism to automatically adapt MPEG-4 live video, in a way to response the actual necessities or capacities of users or systems. One of the challanges in this area is to capture and represent the information needed to adapting content. Thus, using context aware computing techniques, an extensible model has been developed, which can be used to represent devices. It has also been developed automatic and semi-automatic methods to capture the needed information. In this work, the transcoding model has been adopted, which may generate latency, making difficult to use transcoding with interactive applications. In this way, this work has evaluated the impact caused by the transcoding when compared to the end-to-end total delay perceived by the user.

Machine Learning has shown great promise when combined with large volumes of historical data and produces great results when combined with contextual properties. In the world of the Internet of Things, the extraction of information regarding context, or contextual information, is increasingly prominent with scientific advances. Combining such advancements with artificial intelligence is one of the themes in this thesis. Particularly, there are two major areas of interest: context-aware attacker modelling and context-aware defensive methods. Both areas use authentication methods to either infiltrate or protect digital systems. After a brief introduction in chapter 1, chapter 2 discusses the current extracted contextual information within cybersecurity studies, and how machine learning accomplishes a variety of cybersecurity goals. Chapter 3 introduces an attacker injection model, championing the adversarial methods. Then, chapter 4 extracts contextual data and provides an intelligent machine learning technique to mitigate anomalous behaviours. Chapter 5 explores the feasibility of adopting a similar defensive methodology in the cyber-physical domain, and future directions are presented in chapter 6. Particularly, we begin this thesis by explaining the need for further improvements in cybersecurity using contextual information and discuss its feasibility, now that ubiquitous sensors exist in our everyday lives. These sensors often show a high correlation with user identity in surprising combinations. Our first contribution lay within the domain of Mobile CrowdSensing (MCS). Despite its benefits, MCS requires proper security solutions to prevent various attacks, notably injection attacks. Our smart-injection model, SINAM, monitors data traffic in an online-learning manner, simulating an injection model with undetection rates of 99%. SINAM leverages contextual similarities within a given sensing campaign to mimic anomalous injections. On the flip-side, we investigate how contextual features can be utilized to improve authentication methods in an enterprise context. Also motivated by the emergence of omnipresent mobile devices, we expand the Spatio-temporal features of unfolding contexts by introducing three contextual metrics: document shareability, document valuation, and user cooperation. These metrics are vetted against modern machine learning techniques and achieved an average of 87% successful authentication attempts. Our third contribution aims to further improve such results but introducing a Smart Enterprise Access Control (SEAC) technique. Combining the new contextual metrics with SEAC achieved an authenticity precision of 99% and a recall of 97%. Finally, the last contribution is an introductory study on risk analysis and mitigation using context. Here, cyber-physical coupling metrics are created to extract a precise representation of unfolding contexts in the medical field. The presented consensus algorithm achieves initial system conveniences and security ratings of 88% and 97% with these news metrics. Even as a feasibility study, physical context extraction shows good promise in improving cybersecurity decisions. In short, machine learning is a powerful tool when coupled with contextual data and is applicable across many industries. Our contributions show how the engineering of contextual features, adversarial and defensive methods can produce applicable solutions in cybersecurity, despite minor shortcomings.

abstract: The mobile crowdsensing (MCS) applications leverage the user data to derive useful information by data-driven evaluation of innovative user contexts and gathering of information at a high data rate. Such access to context-rich data can potentially enable computationally intensive crowd-sourcing applications such as tracking a missing person or capturing a highlight video of an event. Using snippets and pictures captured from multiple mobile phone cameras with specific contexts can improve the data acquired in such applications. These MCS applications require efficient processing and analysis to generate results in real time. A human user, mobile device and their interactions cause a change in context on the mobile device affecting the quality contextual data that is gathered. Usage of MCS data in real-time mobile applications is challenging due to the complex inter-relationship between: a) availability of context, context is available with the mobile phones and not with the cloud, b) cost of data transfer to remote cloud servers, both in terms of communication time and energy, and c) availability of local computational resources on the mobile phone, computation may lead to rapid battery drain or increased response time. The resource-constrained mobile devices need to offload some of their computation. This thesis proposes ContextAiDe an end-end architecture for data-driven distributed applications aware of human mobile interactions using Edge computing. Edge processing supports real-time applications by reducing communication costs. The goal is to optimize the quality and the cost of acquiring the data using a) modeling and prediction of mobile user contexts, b) efficient strategies of scheduling application tasks on heterogeneous devices including multi-core devices such as GPU c) power-aware scheduling of virtual machine (VM) applications in cloud infrastructure e.g. elastic VMs. ContextAiDe middleware is integrated into the mobile application via Android API. The evaluation consists of overheads and costs analysis in the scenario of ``perpetrator tracking" application on the cloud, fog servers, and mobile devices. LifeMap data sets containing actual sensor data traces from mobile devices are used to simulate the application run for large scale evaluation. / Dissertation/Thesis / Doctoral Dissertation Electrical Engineering 2019