The Hadoop framework has become the most deployed platform for processing Big Data. Despite its advantages, Hadoop s infrastructure is still deployed within the secured network perimeter because the framework lacks adequate inherent security mechanisms against various security threats. However, this approach is not sufficient for providing adequate security layer against attacks such as Distributed Denial of Service. Furthermore, current work to secure Hadoop s infrastructure against DDoS attacks is unable to provide a distributed node-level detection mechanism. This thesis presents a software agent-based framework that allows distributed, real-time intelligent monitoring and detection of DDoS attack at Hadoop s node-level. The agent s cognitive system is ingrained with cumulative sum statistical technique to analyse network utilisation and average server load and detect attacks from these measurements. The framework is a multi-agent architecture with transducer agents that interface with each Hadoop node to provide real-time detection mechanism. Moreover, the agents contextualise their beliefs by training themselves with the contextual information of each node and monitor the activities of the node to differentiate between normal and anomalous behaviours. In the experiments, the framework was exposed to TCP SYN and UDP flooding attacks during a legitimate MapReduce job on the Hadoop testbed. The experimental results were evaluated regarding performance metrics such as false-positive ratio, false-negative ratio and response time to attack. The results show that UDP and TCP SYN flooding attacks can be detected and confirmed on multiple nodes in nineteen seconds with 5.56% false-positive ration, 7.70% false-negative ratio and 91.5% success rate of detection. The results represent an improvement compared to the state-of the-art.

Advances in speech recognition and voice synthesis software now allow "smart agents" (e.g., voice-controlled devices like Amazon's Alexa and Google Home) to interact naturally with humans. The machines have a skills repertoire with which they can "communicate" and form relationships with consumers – managing aspects of their daily lives and providing advice on various issues including purchases. This dissertation develops three essays that examine the role played by the smart agent's voice (rational vs. emotional) in such relationships. The social cognition and persuasion literature on interpersonal communication serves as a comparison backdrop. In Essay 1, I investigate how identical purchase recommendations delivered in a rational or an emotional voice elicit different consumer responses, when the voice is ascribed to a human versus a smart agent. I argue that consumers distinctively categorize smart agents and humans, which, in turn, leads them to have different expectations when interacting with them. In Essay 2, I focus on how a smart agent's vocal tone (rational vs. emotional) influences consumer compliance with the agent's recommendation as well as the role of trust as a mediator of the underlying process. I find that the level of intimacy in the relationship between the smart agent and the human user moderates whether the voice effect on persuasion operates through trust that is cognitively or affectively rooted. In Essay 3, I examine the proposition that consumers may anthropomorphize a smart agent both mindfully (consciously) and mindlessly (non-consciously), depending on the agent's voice. In addition to using extant measures of the degree to which anthropomorphism is explicit (conscious), I develop an auditory analog of the implicit association test (IAT) that assesses implicit (non-conscious) anthropomorphism. In additional experiments, I further assess the robustness of the auditory IAT test and demonstrated a dissociation between the measures of the explicit and implicit subconstructs of anthropomorphism. Taken together, these essays contribute to our understanding of the factors driving consumer relationships with smart agents in the rapidly evolving IoT world. / Doctor of Philosophy / Advances in artificial intelligence technologies are creating "smart devices," i.e., machines that can "understand" how people talk and respond meaningfully to such communication in their own voices. Thus, familiar voice-controlled devices like Amazon's Alexa and Google Home are now increasingly able to "communicate" and form relationships with consumers – managing aspects of their daily lives and providing advice on various issues including purchases. However, little is known about how a smart agent's vocal tones (rational vs. emotional) may influence how consumers perceive and relate to the smart agent. My primary goal in this research is to contribute to our understanding of the role played by the smart agent's voice (rational vs. emotional) in such relationships. Specifically, in Essay 1, I investigate how identical purchase recommendations delivered in a rational or an emotional voice elicit different consumer responses, when the voice is ascribed to a human versus a smart agent. I argue that consumers perceive smart agents and humans as belonging to distinct categories, which leads them to have different expectations when interacting with them. In Essay 2, I focus on how a smart agent's vocal tone (rational vs. emotional) influences consumer compliance with the agent's recommendation as well as the role of trust as a mediator of the underlying process. The level of intimacy in the relationship between the smart agent and the human user influences whether the voice effect on persuasion is driven by trust that is rooted in cognition (knowledge, competence) or affect (caring, warmth). In Essay 3, I examine whether consumers imbue humanlike qualities (anthropomorphize) a smart agent both mindfully (consciously) and mindlessly (non-consciously) based on the agent's voice. In addition to using available measures of conscious anthropomorphism, I develop an auditory analog of the implicit association test (IAT) to assesses implicit (non-conscious) anthropomorphism. In additional experiments, I assess the robustness of the auditory IAT test and the relationship between measures of mindful and mindless anthropomorphism. Taken together, the research reported in these three essays contributes to our understanding of the factors driving consumer relationships with smart agents in the rapidly evolving IoT (Internet of Things) world.

La thèse défendue dans ce manuscrit s'intéresse à la simulation multi-agents appliquée à la simulation d'individus dans des bâtiments 3D virtuels.Pour ce faire, nos travaux proposent de capitaliser l'expérience acquise dans le domaine du web sémantique sur les ontologies et les moteurs d'inférence associés pour faciliter la conception et le développement de comportements intelligents pour des agents évoluant dans des univers virtuels.L'objectif est de fournir aux agents une approche générique pour gérer leur représentation du monde et raisonner sur cette représentation.Pour cela, la problématique centrale repose sur la définition d'une ontologie décidable modélisant l'ensemble des connaissances contenues dans l'environnement virtuel 3D pour enrichir sémantiquement l'environnement d'une simulation multi-agents.Cette ontologie décidable a pour but d'offrir la possibilité d'intégrer les moteurs d'inférence sémantique au c\oe{}ur de la modélisation de comportements d'agents mobiles dans un environnement virtuel. / This thesis focuses on multi-agent simulation applied to the simulation of individuals in virtual 3D buildings. To do this, our work suggests to capitalize on the experience gained in the field of semantic web ontologies and inference engines to facilitate the design and development of intelligent behavior for agents operating in virtual worlds. The goal is to provide to agents a generic approach to managing their representation of the world and reason about this representation. For this, the central problem is based on the definition of a decidable ontology modeling all of the knowledge contained in the virtual 3D environment to enrich semantically the environment of a multi-agent simulation. This decidable ontology aims to provide an opportunity to integrate semantic inference engine at the heart of modeling behavior of mobile agents in a virtual environment.

Made available in DSpace on 2016-06-02T20:12:13Z (GMT). No. of bitstreams: 1 2315.pdf: 835286 bytes, checksum: bb4fc006ed09b9b9f8cb1920ee0092de (MD5) Previous issue date: 2009-03-27 / The thesis main goal is to analyze the various forms of relationship between subjects and technical-objects, with emphasis on the use of digital computers and, particularly, softwares called smart agents. The thesis analyzes the space and its qualitative changes in actuality, from the concept of space as a human production, analyzing how the changes underway in the environment affect our subjectivities and, conversely, how we affect our environments. There are presented arguments about the possibilities of survival for the naked man in these new spaces, unless it is properly updated with the latest technology - sensory and motor prostheses. There is a discussion about the use of space as a part of the thought process and about the abstract space par excellence, the virtual worlds. From the discussions of space, the thesis proposes reflections about the body that will be included in these new spaces. There is presented a pattern for the use of artifacts by man and its effects on subjectivity. The body that is increasingly appropriating technical-objects, prosthetic body, establishing new relationships with technology and is a parabiotic system. Then, the thesis discusses the pattern applied to the use of intangible technical-objects (software). There are two conceptual proposals, about the possibility of considering the smart agents as one of the layers of dennett s model of consciousness (multiple drafts model). The second proposal, similar in approach, shows that smart agents can be considered as modules under the model of conscience of Fodor. The thesis brings thoughts about the possibility of considering smart agents as autonomous and independent the Artificial Intelligence. It presents a conceptual proposal, which is the definition of objective states that may not be objectively treated, as a possible root to the possibility of autonomy in computing machines. The conclusions of the thesis indicate a growing difficulty in discerning the boundaries between minds and digital machines, in a world of hybrids cognitive systems. / A tese tem como objetivo principal refletir sobre as várias formas de relação entre sujeitos e objetos-técnicos, com ênfase para a utilização dos computadores digitais e, particularmente, os softwares chamados agentes inteligentes. A tese analisa o espaço e suas mudanças qualitativas na atualidade, a partir do conceito do espaço como produção humana, analisando como as transformações em curso no ambiente afetam nossas subjetividades e, reciprocamente, como afetamos nossos ambientes. São discutidas as possibilidades de sobrevivência do homem nu nesses novos espaços, sem que esteja devidamente atualizado com as últimas novidades tecnológicas próteses sensoriais e motoras. O trabalho perpassa a discussão sobre o pensamento que se utiliza do espaço como elemento constituinte do próprio pensamento e reflete sobre o espaço abstrato por excelência, os mundos virtuais. A partir das discussões do espaço, a tese propõe reflexões sobre o corpo que vai se inserir nesses novos espaços. Discute-se o padrão de apropriação de artefatos pelo homem e seus efeitos na subjetividade. O corpo que se apropria crescentemente dos objetos técnicos, corpo protético, estabelece novas relações com a tecnologia, constituindo-se em um sistema parabiótico. Em seguida, a tese discute a manutenção do padrão de apropriação dos objetos-técnicos materiais em relação às formas de apropriação dos objetos-técnicos intangíveis (softwares). São apresentadas duas propostas conceituais inovadoras, quanto à possibilidade de se assumir os softwares (agentes inteligentes), entidades incorpóreas e autônomas, como uma das camadas da consciência, no âmbito do modelo dennettiano de uma consciência com múltiplas camadas (multiple drafts model). A segunda proposta, similar na abordagem, postula que os agentes inteligentes possam se configurar como módulos (faculdades verticais) no âmbito do modelo de consciência de Fodor. A tese traz reflexões sobre a possibilidade de autonomização completa dos agentes inteligentes e a sua instituição, ipso facto, como agentes a chamada Inteligência Artificial. Apresenta-se uma proposta conceitual original, que é a definição de estados objetais não objetiváveis como, possivelmente, uma primeira raiz para que se comece a discutir as possibilidades de singularização das máquinas computacionais. As conclusões da tese sinalizam para uma crescente dificuldade no discernimento das fronteiras entre mentes e máquinas digitais, em um mundo de sistemas cognitivos híbridos.

This dissertation reports five experiments exploring the use of AI-based smart agents to support physician-patient interactions. In each experiment, a sample of female participants evaluates video tapes of simulated physician-patient interactions in a setting involving early stage breast cancer diagnosis. Experiment 1 manipulates communication style (empathetic/impassive) for both a human physician (played by an actor) and an avatar that mimics the human. Empathetic styles elicit more liking and trust from patients and are also more persuasive. The avatar loses less than the human physician on desirable patient outcomes when communication style changes from empathetic to impassive. A mediation analysis shows that the communication style and physician type effects flow serially through liking and trust to persuasion. Experiment 2 reports an extended replication, adding a new avatar with less resemblance to the human physician. The findings match those of Experiment 1: both avatars have similar effects on liking, trust, and persuasion and are similarly anthropomorphized. Experiment 3 examines whether the patient's mindset (hope/fear about the cancer prognosis) influences likely patient outcomes. The mindset manipulation does not influence patient outcomes, but we find support for the core serial mediation model (from liking to trust to persuasion). Experiment 4 explores whether it matters how the avatar is deployed. Introducing the avatar as the physician's assistant lowers its evaluations perhaps because the patients feel deprioritized. The human physician is evaluated significantly higher on all outcome dimensions. Experiments 1-4 focused on the first phase of a standard three-phased physician-patient interaction protocol. Experiment 5 examines communication style (empathetic/ impassive) and physician type (human/avatar) effects across the three sequential phases. Patient outcomes improve monotonically over the three interaction phases across all study conditions. Overall, our studies show that an empathetic communication style is more effective in eliciting higher levels of liking, trust, and persuasion. The human physician and the avatar elicit similar levels of these desirable patient interaction outcomes. The avatar loses less when communication style changes from empathetic to impassive, suggesting that patients may have lower expectations of empathy from avatars. Thus, if carefully deployed, smart agents acting as physicians' avatars may effectively support physician-patient interactions. / Doctor of Philosophy / Healthcare professionals often have the difficult task of breaking bad news to patients. Research has shown that physician's communication style influences patient outcomes (liking, trust, persuasion, and compliance). Some physicians may adopt an impassive communication style to avoid emotional involvement with patients and some others may be overly empathetic and are prone to be perceived as inauthentic. These deficiencies persist despite an emphasis on developing physician communication skills. As in other service domains, a new generation of humanoid service robots (HSRs) offers potential for supporting physician-patient interactions. The effectiveness of such Artificial Intelligence (AI)/smart agent supported physician-patient interactions will rest, in part, on the communication style designed into the smart agents. A patient interacting with a smart agent emulating a human physician may assess different cognitive capabilities (knowledge and expertise), attribute different motivations, and make different socio-cultural appraisals than when they interact with the physician in-person. This research examines whether communication style (empathetic versus impassive) implemented via facial expression and vocal delivery elicits different patient responses when interacting with a smart agent (a physician' avatar) versus the physician in person. Findings suggest that, an empathetic (vs impassive) communication style elicits more positive patient responses, avatar physicians fare at par or better than the human physician and lose less on the patient outcomes when the communication style changes from empathetic to impassive. The avatars' appearance does not play a role in persuasion. Avatars were similarly anthropomorphized and participants' mindset (Hope/Fear) did not influence the outcomes. However, if the avatars are introduced as assistants (versus standalone physicians) there is a possibility that patients may feel downgraded/deprioritized, leading to lower evaluations for the avatars than the human physician. The contrast created when the human physician introduces the avatar may have unintended consequences that lower the avatar's evaluation. Without a direct contrast, patients may be more receptive to avatar interactions, particularly as they become more familiar in service environments. Our findings suggest that, if carefully deployed, smart agents acting as physicians' avatars may effectively support physician-patient interactions. Indeed, patients may have lower expectations of empathy from an avatar versus a human physician. This can facilitate more effective physician-patient interactions and elicit positive downstream effects on patient liking, trust and compliance.