Stress is now recognized as one of the major causes of physical and psychological illness. It is known as a reaction to surrounding environmental threats and the best way to manage it is to understand its triggers. Although people continuously react to their surrounding environments, they sometimes are not aware that certain elements in their environment are considered to be stressors. Based on this fact, researchers have recently proposed context-aware stress management systems. Most of the proposed systems use context data to provide real time stress monitoring and visualization, along with intervention techniques. However, these interventions are limited to the second and tertiary stages and very little attention has been given to the primary stage. In this thesis, we introduce a system called CASP. The system’s objective is to provide stress status predictions based on a user’s current contextual data. Therefore, a detection method is developed using heart rate variability (HRV) as a stress indicator to deliver personalized context-aware stress reports. Based on the predicted status, the system provides users with stress interventions at an early stage in order to help avoid and/or eliminate the occurrence of stress. Our evaluation results show that the CASP system is able to predict the stress status of a user with an averaged accuracy of 78.23% through our limited activity, when compare to a stress status measured using physiological signals. Moreover, it provides prediction models that adapt to the changing nature of both the user’s stress status and the surrounding environment.

Today's technology is becoming more interactive with voice assistants like Siri. However, interactive systems such as Siri make mistakes. The purpose of this thesis is to explore using affect as an implicit feedback channel so that such mistakes would be easily corrected in real time. The CAfFEINE Framework, which was created by Dr. Saha, is a context-aware affective feedback loop in an intelligent environment. For the research described in this thesis, the focus will be on analyzing a user's physiological response to the service provided by an intelligent environment. To test this feedback loop, an experiment was constructed using an on-screen, step-by-step assembly guide for a Tangram puzzle. To categorize the user's response to the experiment, baseline readings were gathered for a user's stressed and non-stressed state. The Paced Stroop Test and two other baseline tests were conducted to gather these two states. The data gathered in the baseline tests was then used to train a support vector machine to predict the user's response to the Tangram experiment. During the data analysis phase of the research, the results for the predictions on the Tangram experiment were not as expected. Multiple trials of training data for the support vector machine were explored, but the data gathered throughout this research was not enough to draw proper conclusions. More focus was then given to analyzing the pre-processed data of the baseline tests in an attempt to find a factor or group of factors to determine if the user's physiological responses would be useful to train the Support Vector Machine. There were trends found when comparing the area under the curves of the Paced Stroop Test phasic driver plots. It was found that these comparison factors might be a useful approach for differentiating users based upon their physiological responses during the Paced Stroop Test. / Master of Science / The purpose of this thesis was to use the CAfFEINE Framework, proposed by Dr. Saha, in a real-world environment. Dr. Saha's Framework utilizes a user's physical responses, i.e. heart rate, in a smart environment to give information to the smart devices. For example, if Siri were to give a user directions to someone's home and told that user to turn right when the user knew they needed to turn left. That user would have a physical reaction as in their heart rate would increase. If the user were wearing a smart watch, Siri would be able to see the heart rate increase and realize, from past experiences with that user, that the information she gave to the user was incorrect. Then she would be able to correct herself. My research focused on measuring user reaction to a smart service provided in a real-world situation using a Tangram puzzle as a mock version of an industrial assembly situation. The users were asked to follow on-screen instructions to assemble the Tangram puzzle. Their reactions were recorded through a smart watch and analyzed post-experiment. Based on the results of a Paced Stroop Test they took before the experiment, a computer algorithm would predict their stress levels for each service provided by the step-by-step instruction guide. However, the results did not turn out as expected. Therefore, the rest of the research focused more on why the results did not support Dr. Saha's previous Framework results.

Pervasive (ubiquitous) computing is a new paradigm where the computers are submerged into the background of the everyday life. One important aspect of pervasive systems is context-awareness. Context-aware systems are those that can adapt their behaviours according to the current context. Context-aware applications are being integrated into our everyday activity aspects such as: health care, smart homes and transportations. There exist a wide range of context-aware applications such as: mobile phones, learning systems, smart vehicles. Some context-aware systems are critical since the consequence of failing to identify a given context may be catastrophic. For example, an auto-pilot system is a critical context-aware system; it senses the humidity, clouds, wind speed and accordingly adjusts the altitude, throttle and other parameters. Being a critical context-aware system has to be provably correct. Policy-based approaches has been used in many applications but not in context-aware systems. In this research, we want to discover the anatomy (i.e. architecture, structure and operational behaviour) of policy-based management as applied to context-aware systems, and how policies are managed within such a dynamic system. We propose a novel computational model and its formalisation is presented using the Calculus of Context-aware Ambients (CCA). CCA has been proposed as a suitable mathematical notation to model mobile and context-aware systems. We decided to use CCA due to three reasons: (i) in CCA, mobility and context-awareness are primitive constructs and are treated as first-class citizens; (ii) properties of a system can be formally analysed; (iii) CCA specifications are executable, and thus, leading to rapid prototyping and early validation of the system properties. We, then show how policies can be expressed in CCA. For illustration, the specification of the event-condition-action (ECA) conceptual policy model is modelled in CCA in a natural fashion. We also propose a policy-based architecture for context-aware systems, showing its different components, and how they interact. Furthermore, we give the specification of the policy enforcement mechanism used in our proposed architecture in CCA. To evaluate our approach, a real-world case study of an infostation-based mobile learning (mLearning) system is chosen. This mLearning system is deployed across a university campus to enable mobile users to access mobile services (mServices) represented by course materials (lectures, tests and tutorials) and communication services (intelligent message notification and VoIP). Users can access the mServices through their mobile devices (Hand-set phones, PDAs and laptops) regardless of their device type or location within a university campus. We have specified the mLearning system in CCA (i.e. specification based on policies of the mServices), afterwards, the specification is simulated using the CCA interpreter tool. We have developed an animation tool specially designed for the mLearning system. The animation tool provides graphical representation of the CCA processes. In terms of safety and liveness, some important properties of the mLearning system have been validated as a proof of concept.

Information protection is a key issue for the acceptance and adoption of pervasive computing systems where various portable devices such as smart phones, Personal Digital Assistants (PDAs) and laptop computers are being used to share information and to access digital resources via wireless connection to the Internet. Because these are resources constrained devices and highly mobile, changes in the environmental context or device context can affect the security of the system a great deal. A proper security mechanism must be put in place which is able to cope with changing environmental and system context. Usage CONtrol (UCON) model is the latest major enhancement of the traditional access control models which enables mutability of subject and object attributes, and continuity of control on usage of resources. In UCON, access permission decision is based on three factors: authorisations, obligations and conditions. While authorisations and obligations are requirements that must be fulfilled by the subject and the object, conditions are subject and object independent requirements that must be satisfied by the environment. As a consequence, access permission may be revoked (and the access stopped) as a result of changes in the environment regardless of whether the authorisations and obligations requirements are met. This constitutes a major shortcoming of the UCON model in pervasive computing systems which constantly strive to adapt to environmental changes so as to minimise disruptions to the user. We propose a Context-Aware and Adaptive Usage Control (CA-UCON) model which extends the traditional UCON model to enable adaptation to environmental changes in the aim of preserving continuity of access. Indeed, when the authorisation and obligations requirements are fulfilled by the subject and object, and the conditions requirements fail due to changes in the environmental or the system context, our proposed model CA-UCON triggers specific actions in order to adapt to the new situation, so as to ensure continuity of usage. We then propose an architecture of CA-UCON model, presenting its various components. In this model, we integrated the adaptation decision with usage decision architecture, the comprehensive definition of each components and reveals the functions performed by each components in the architecture are presented. We also propose a novel computational model of our CA-UCON architecture. This model is formally specified as a finite state machine. It demonstrates how the access request of the subject is handled in CA-UCON model, including detail with regards to revoking of access and actions undertaken due to context changes. The extension of the original UCON architecture can be understood from this model. The formal specification of the CA-UCON is presented utilising the Calculus of Context-aware Ambients (CCA). This mathematical notation is considered suitable for modelling mobile and context-aware systems and has been preferred over alternatives for the following reasons: (i) Mobility and Context awareness are primitive constructs in CCA; (ii) A system's properties can be formally analysed; (iii) Most importantly, CCA specifications are executable allowing early validation of system properties and accelerated development of prototypes. For evaluation of CA-UCON model, a real-world case study of a ubiquitous learning (u-learning) system is selected. We propose a CA-UCON model for the u-learning system. This model is then formalised in CCA and the resultant specification is executed and analysed using an execution environment of CCA. Finally, we investigate the enforcement approaches for CA-UCON model. We present the CA-UCON reference monitor architecture with its components. We then proceed to demonstrate three types of enforcement architectures of the CA-UCON model: centralised architecture, distributed architecture and hybrid architecture. These are discussed in detail, including the analysis of their merits and drawbacks.

published_or_final_version / Computer Science / Doctoral / Doctor of Philosophy

The Internet of Things is an emerging technology where everyday devices with sensing and actuating capabilities are connected to the Internet and seamlessly com- municate with other devices over the network. The proliferation of mobile devices enables access to unprecedented levels of rich information sources. Mobile app cre- ators can leverage this information to create personalized mobile applications. The amount of available mobile apps available for download will increase over time, and thus, accessing and managing apps can become cumbersome. This thesis presents AppXimity, a mobile-app-management that provides personalized app suggestions and recommendations by leveraging user preferences and contextual information to provide relevant apps in a given context. Suggested apps represent a subset of the installed apps that match nearby businesses or have been identified by AppXimity as apps of interest to the user, and recommended apps are those apps that are not installed on the user’s device, but may be of interest to the user, in that location. / Graduate / 0984

Location is a primary cue in many context-aware computing systems, and is often represented as a global coordinate, room number, or Euclidean distance various landmarks. A user?s concept of location, however, is often defined in terms of regions in which common activities occur. We show how to partition a space into such regions based on patterns of observed user location and motion. These regions, which we call activity zones, represent regions of similar user activity, and can be used to trigger application actions, retrieve information based on previous context, and present information to users. We suggest that context-aware applications can benefit from a location representation learned from observing users. We describe an implementation of our system and present two example applications whose behavior is controlled by users? entry, exit, and presence in the zones.

In the age of Web2.0, various network services became critical. Exchange of messages between entities in the network is so frequent that information explosion is quite common nowadays. Volume of Information passed is growing up rapidly. With the wide development of web applications, people need to learn how to filter the important messages; service providers have urgent need to trace the ever changing role of users. This research studies the detections of the user interaction scenario, based on the result from the test function in the on-line learning platform. The learning platform users are divided into two groups, teachers and students, based on their roles. Usually students sit for an on-line examination at the end of each learning activity. The teachers are in charge of helping students with their presentations, encouraging those with good grades, and helping the weaker ones to reach their potential. But in the one-to-many teaching method, a teacher needs to face many students and the resultant grade of an examination becomes a heap of fuzzy and difficult to comprehend numbers. Even though some mathematical tools can help the teachers analyze the data, it is still very difficult to provide appropriate response to each student. The purpose of this research motives building an examination system which combines context-awareness and auto-notification, and bring the advantages of digital examination. An inference engine is used to calculate linear regression of learning curve for each student, then review the old data, and transfer the analysis into the learning context. Then the feedback is given to the students under the various learning context or the teacher will get notification after it compile the analysis. Besides analyzing the past data, the linear regression result will be adjusted to fit the characteristics of learning curve and infer the personal goal of the student. If result is better than expected goal, students should be encouraged. On the other hand, the remediable actions will be administered. Those events can be scheduled by the manager of auto-notification system, published in the appropriate time, and achieve the goal of variety, personalization, and automation.

Thesis (Ph.D)--Computing, Georgia Institute of Technology, 2010. / Committee Chair: Rehg, James M.; Committee Member: Christensen, Henrik; Committee Member: Dellaert, Frank; Committee Member: Essa, Irfan; Committee Member: Malik, Jitendra. Part of the SMARTech Electronic Thesis and Dissertation Collection.

Mutation testing and adequacy testing are two major technologies to assure the quality of software. In this thesis, we present the first work that alleviates the high cost of mutation testing and ineffectiveness of adequacy testing for context-aware applications. We also present large-scale multi-subject case studies to evaluate how our work successfully alleviates these problems. Mutation testing incurs a high execution cost if randomly selected test inputs kill a small percentage of remaining live mutants. To address this problem, we formulate the notion of context diversity to measure the context changes inherent in test inputs, and propose three context-aware strategies in the selection of test inputs. The empirical results show that the use of test inputs with higher context diversity can significantly benefit mutation testing in terms of resulting in fewer test runs, fewer test case trials, and smaller resultant test suites that achieve a high mutation score level. The case study also shows that at the test case level, the context diversity of test inputs positively and strongly correlates with multiple types of adequacy metrics, which provide a foundation on why context diversity contributes to the effectiveness of test cases in revealing faults in context-aware applications. In adequacy testing, many strategies randomly select test cases to construct adequate test suites with respect to program-based adequacy criteria. They usually exclude redundant test cases that are unable to improve the coverage of the test requirements of an adequacy criterion achieved by constructing test suites. These strategies have not explored in the diversity in test inputs to improve the test effectiveness of test suites. To address this problem, we propose three context-aware refined strategies to check whether redundant test cases can replace previously selected test cases to achieve the same coverage level but with different context diversity levels. The empirical study shows that context diversity can be significantly injected into adequate test suites, and favoring test cases with higher context diversity can significantly improve the fault detection rates of adequate test suites for testing context-aware applications. In conclusion, this thesis makes the significant contributions to the research in testing context-aware applications: (1) It has formulated context diversity, a novel metric to measure context changes inherent in test inputs. (2) It has proposed three context-aware strategies to select test cases with different levels of context diversity. Compared with the baseline strategy, the strategy CAS-H that uses test cases with higher context diversity can significantly reduce the cost of mutation testing over context-aware applications in terms of less number of test runs, smaller adequate test suites, and less number of test inputs used to construct test suites. (3) It has defined three context-aware refined strategies to construct adequate test suites with different context diversity levels. Compared with the baseline strategy, the strategy CARS-H that favors test cases with higher context diversity can significantly improve the effectiveness of adequacy testing in terms of higher fault detection rates. / published_or_final_version / Computer Science / Doctoral / Doctor of Philosophy