Cloud computing systems fundamentally provide access to large pools of data and computational resources through a variety of interfaces similar in spirit to existing grid and HPC resource management and programming systems. These types of systems offer a new programming target for scalable application developers and have gained popularity over the past few years. However, most cloud computing systems in operation today are proprietary and rely upon infrastructure that is invisible to the research community, or are not explicitly designed to be instrumented and modified by systems researchers. In this research, Xen Server Management API is employed to build a framework for cloud computing that implements what is commonly referred to as Infrastructure as a Service (IaaS); systems that give users the ability to run and control entire virtual machine instances deployed across a variety physical resources. The goal of this research is to develop a cloud based resource and service sharing platform for Computer network security education a.k.a Virtual Lab.

Advances in the area of ubiquitous, pervasive and wearable computing have resulted in the development of low band-width, data rich environmental and body sensor networks, providing a reliable and non-intrusive methodology for capturing activity data from humans and the environments they inhabit. Assistive technologies that promote independent living amongst elderly and individuals with cognitive impairment are a major motivating factor for sensor-based activity recognition systems. However, the process of discerning relevant activity information from these sensor streams such as accelerometers is a non-trivial task and is an on-going research area. The difficulty stems from factors such as spatio-temporal variations in movement patterns induced by different individuals and contexts, sparse occurrence of relevant activity gestures in a continuous stream of irrelevant movements and the lack of real-world data for training learning algorithms. This work addresses these challenges in the context of wearable accelerometer-based simple activity and gesture recognition. The proposed computational framework utilizes discriminative classifiers for learning the spatio-temporal variations in movement patterns and demonstrates its effectiveness through a real-time simple activity recognition system and short duration, non- repetitive activity gesture recognition. Furthermore, it proposes adaptive discriminative threshold models trained only on relevant activity gestures for filtering irrelevant movement patterns in a continuous stream. These models are integrated into a gesture spotting network for detecting activity gestures involved in complex activities of daily living. The framework addresses the lack of real world data for training, by using auxiliary, yet related data samples for training in a transfer learning setting. Finally the problem of predicting activity tasks involved in the execution of a complex activity of daily living is described and a solution based on hierarchical Markov models is discussed and evaluated.

Cyber Physical Systems (CPSs) are systems comprising of computational systems that interact with the physical world to perform sensing, communication, computation and actuation. Common examples of these systems include Body Area Networks (BANs), Autonomous Vehicles (AVs), Power Distribution Systems etc. The close coupling between cyber and physical worlds in a CPS manifests in two types of interactions between computing systems and the physical world: intentional and unintentional. Unintentional interactions result from the physical characteristics of the computing systems and often cause harm to the physical world, if the computing nodes are close to each other, these interactions may overlap thereby increasing the chances of causing a Safety hazard. Similarly, due to mobile nature of computing nodes in a CPS planned and unplanned interactions with the physical world occur. These interactions represent the behavior of a computing node while it is following a planned path and during faulty operations. Both of these interactions change over time due to the dynamics (motion) of the computing node and may overlap thereby causing harm to the physical world. Lack of proper modeling and analysis frameworks for these systems causes system designers to use ad-hoc techniques thereby further increasing their design and development time. The thesis addresses these problems by taking a holistic approach to model Computational, Physical and Cyber Physical Interactions (CPIs) aspects of a CPS and proposes modeling constructs for them. These constructs are analyzed using a safety analysis algorithm developed as part of the thesis. The algorithm computes the intersection of CPIs for both mobile as well as static computing nodes and determines the safety of the physical system. A framework is developed by extending AADL to support these modeling constructs; the safety analysis algorithm is implemented as OSATE plug-in. The applicability of the proposed approach is demonstrated by considering the safety of human tissue during the operations of BAN, and the safety of passengers traveling in an Autonomous Vehicle.

Goal specification is an important aspect of designing autonomous agents. A goal does not only refer to the set of states for the agent to reach. A goal also defines restrictions on the paths the agent should follow. Temporal logics are widely used in goal specification. However, they lack the ability to represent goals in a non-deterministic domain, goals that change non-monotonically, and goals with preferences. This dissertation defines new goal specification languages by extending temporal logics to address these issues. First considered is the goal specification in non-deterministic domains, in which an agent following a policy leads to a set of paths. A logic is proposed to distinguish paths of the agent from all paths in the domain. In addition, to address the need of comparing policies for finding the best ones, a language capable of quantifying over policies is proposed. As policy structures of agents play an important role in goal specification, languages are also defined by considering different policy structures. Besides, after an agent is given an initial goal, the agent may change its expectations or the domain may change, thus goals that are previously specified may need to be further updated, revised, partially retracted, or even completely changed. Non-monotonic goal specification languages that can make these changes in an elaboration tolerant manner are needed. Two languages that rely on labeling sub-formulas and connecting multiple rules are developed to address non-monotonicity in goal specification. Also, agents may have preferential relations among sub-goals, and the preferential relations may change as agents achieve other sub-goals. By nesting a comparison operator with other temporal operators, a language with dynamic preferences is proposed. Various goals that cannot be expressed in other languages are expressed in the proposed languages. Finally, plans are given for some goals specified in the proposed languages.

This thesis investigates the role of activity visualization tools in increasing group awareness at the workspace. Today, electronic calendaring tools are widely used in the workplace. The primary function is to enable each person maintain a work schedule. They also are used to schedule meetings and share work details when appropriate. However, a key limitation of current tools is that they do not enable people in the workplace to understand the activity of the group as a whole. A tool that increases group awareness would promote reflection; it would enable thoughtful engagement with one's co-workers. I have developed two tools: the first tool enables the worker to examine detailed task information of one's own tasks, within the context of his/her peers' anonymized task data. The second tool is a public display to promote group reflection. I have used an iterative design methodology to refine the tools. I developed ActivityStream desktop tool that enables users to examine the detailed information of their own activities and the aggregate information of other peers' activities. ActivityStream uses a client-server architecture. The server collected activity data from each user by parsing RSS feeds associated with their preferred online calendaring and task management tool, on a daily basis. The client software displays personalized aggregate data and user specific tasks, including task types. The client display visualizes the activity data at multiple time scales. The activity data for each user is represented though discrete blocks; interacting with the block will reveal task details. The activity of the rest of the group is anonymized and aggregated. ActivityStream visualizes the aggregated data via Bezier curves. I developed ActivityStream public display that shows a group people's activity levels change over time to promote group reflection. In particular, the public display shows the anonymized task activity data, over the course of one year. The public display visualizes data for each user using a Bezier curve. The display shows data from all users simultaneously. This representation enables users to reflect on the relationships across the group members, over the course of one year. The survey results revealed that users are more aware of their peers' activities in the workspace.

Text search is a very useful way of retrieving document information from a particular website. The public generally use internet search engines over the local enterprise search engines, because the enterprise content is not cross linked and does not follow a page rank algorithm. On the other hand the enterprise search engine uses metadata information, which allows the user to specify the conditions that any retrieved document should meet. Therefore, using metadata information for searching will also be very useful. My thesis aims on developing an enterprise search engine using metadata information by providing advanced features like faceted navigation. The search engine data was extracted from various Indonesian web sources. Metadata information like person, organization, location, and sentiment analytic keyword entities should be tagged in each document to provide facet search capability. A shallow parsing technique like named entity recognizer is used for this purpose. There are more than 1500 entities that have been tagged in this process. These documents have been successfully converted into XML format and are indexed with "Apache Solr". It is an open source enterprise search engine with full text search and faceted search capabilities. The entities will be helpful for users to specify conditions and search faster through the large collection of documents. The user is assured results by clicking on a metadata condition. Since the sentiment analytic keywords are tagged with positive and negative values, social scientists can use these results to check for overlapping or conflicting organizations and ideologies. In addition, this tool is the first of its kind for the Indonesian language. The results are fetched much faster and with better accuracy.

US Senate is the venue of political debates where the federal bills are formed and voted. Senators show their support/opposition along the bills with their votes. This information makes it possible to extract the polarity of the senators. Similarly, blogosphere plays an increasingly important role as a forum for public debate. Authors display sentiment toward issues, organizations or people using a natural language.

In this research, given a mixed set of senators/blogs debating on a set of political issues from opposing camps, I use signed bipartite graphs for modeling debates, and I propose an algorithm for partitioning both the opinion holders (senators or blogs) and the issues (bills or topics) comprising the debate into binary opposing camps. Simultaneously, my algorithm scales the entities on a univariate scale. Using this scale, a researcher can identify moderate and extreme senators/blogs within each camp, and polarizing versus unifying issues. Through performance evaluations I show that my proposed algorithm provides an effective solution to the problem, and performs much better than existing baseline algorithms adapted to solve this new problem. In my experiments, I used both real data from political blogosphere and US Congress records, as well as synthetic data which were obtained by varying polarization and degree distribution of the vertices of the graph to show the robustness of my algorithm.

I also applied my algorithm on all the terms of the US Senate to the date for longitudinal analysis and developed a web based interactive user interface www.PartisanScale.com to visualize the analysis.

US politics is most often polarized with respect to the left/right alignment of the entities. However, certain issues do not reflect the polarization due to political parties, but observe a split correlating to the demographics of the senators, or simply receive consensus. I propose a hierarchical clustering algorithm that identifies groups of bills that share the same polarization characteristics. I developed a web based interactive user interface www.ControversyAnalysis.com to visualize the clusters while providing a synopsis through distribution charts, word clouds, and heat maps.

Internet browsers are today capable of warning internet users of a potential phishing attack. Browsers identify these websites by referring to blacklists of reported phishing websites maintained by trusted organizations like Google, Phishtank etc. On identifying a Unified Resource Locator (URL) requested by a user as a reported phishing URL, browsers like Mozilla Firefox and Google Chrome display an 'active' warning message in an attempt to stop the user from making a potentially dangerous decision of visiting the website and sharing confidential information like username-password, credit card information, social security number etc.

However, these warnings are not always successful at safeguarding the user from a phishing attack. On several occasions, users ignore these warnings and 'click through' them, eventually landing at the potentially dangerous website and giving away confidential information. Failure to understand the warning, failure to differentiate different types of browser warnings, diminishing trust on browser warnings due to repeated encounter are some of the reasons that make users ignore these warnings. It is important to address these factors in order to eventually improve a user’s reaction to these warnings.

In this thesis, I propose a novel design to improve the effectiveness and reliability of phishing warning messages. This design utilizes the name of the target website that a fake website is mimicking, to display a simple, easy to understand and interactive warning message with the primary objective of keeping the user away from a potentially spoof website.

Audio signals, such as speech and ambient sounds convey rich information pertaining to a user’s activity, mood or intent. Enabling machines to understand this contextual information is necessary to bridge the gap in human-machine interaction. This is challenging due to its subjective nature, hence, requiring sophisticated techniques. This dissertation presents a set of computational methods, that generalize well across different conditions, for speech-based applications involving emotion recognition and keyword detection, and ambient sounds-based applications such as lifelogging.

The expression and perception of emotions varies across speakers and cultures, thus, determining features and classification methods that generalize well to different conditions is strongly desired. A latent topic models-based method is proposed to learn supra-segmental features from low-level acoustic descriptors. The derived features outperform state-of-the-art approaches over multiple databases. Cross-corpus studies are conducted to determine the ability of these features to generalize well across different databases. The proposed method is also applied to derive features from facial expressions; a multi-modal fusion overcomes the deficiencies of a speech only approach and further improves the recognition performance.

Besides affecting the acoustic properties of speech, emotions have a strong influence over speech articulation kinematics. A learning approach, which constrains a classifier trained over acoustic descriptors, to also model articulatory data is proposed here. This method requires articulatory information only during the training stage, thus overcoming the challenges inherent to large-scale data collection, while simultaneously exploiting the correlations between articulation kinematics and acoustic descriptors to improve the accuracy of emotion recognition systems.

Identifying context from ambient sounds in a lifelogging scenario requires feature extraction, segmentation and annotation techniques capable of efficiently handling long duration audio recordings; a complete framework for such applications is presented. The performance is evaluated on real world data and accompanied by a prototypical Android-based user interface.

The proposed methods are also assessed in terms of computation and implementation complexity. Software and field programmable gate array based implementations are considered for emotion recognition, while virtual platforms are used to model the complexities of lifelogging. The derived metrics are used to determine the feasibility of these methods for applications requiring real-time capabilities and low power consumption.

This study investigated the ability to relate a test taker’s non-verbal cues during online assessments to probable cheating incidents. Specifically, this study focused on the role of time delay, head pose and affective state for detection of cheating incidences in a lab-based online testing session. The analysis of a test taker’s non-verbal cues indicated that time delay, the variation of a student’s head pose relative to the computer screen and confusion had significantly statistical relation to cheating behaviors. Additionally, time delay, head pose relative to the computer screen, confusion, and the interaction term of confusion and time delay were predictors in a support vector machine of cheating prediction with an average accuracy of 70.7%. The current algorithm could automatically flag suspicious student behavior for proctors in large scale online courses during remotely administered exams.