Intrusion detection is the practice of examining information from computers and networks to identify cyberattacks. It is an important topic in practice, since the frequency and consequences of cyberattacks continues to increase and affect organizations. It is important for research, since many problems exist for intrusion detection systems. Intrusion detection systems monitor large volumes of data and frequently generate false positives. This results in additional effort for security analysts to review and interpret alerts. After long hours spent reviewing alerts, security analysts become fatigued and make bad decisions. There is currently no approach to intrusion detection that reduces the workload of human analysts by providing a probabilistic prediction that a computer is experiencing a cyberattack. This research addressed this problem by estimating the probability that a computer system was being attacked, rather than alerting on individual events. This research combined concepts from cyber situation awareness by applying clustering ensembles, probability analysis, and active learning. The unique contribution of this research is that it provides a higher level of meaning for intrusion alerts than traditional approaches. Three experiments were conducted in the course of this research to demonstrate the feasibility of these concepts. The first experiment evaluated cluster generation approaches that provided multiple perspectives of network events using unsupervised machine learning. The second experiment developed and evaluated a method for detecting anomalies from the clustering results. This experiment also determined the probability that a computer system was being attacked. Finally, the third experiment integrated active learning into the anomaly detection results and evaluated its effectiveness in improving the accuracy. This research demonstrated that clustering ensembles with probabilistic analysis were effective for identifying normal events. Abnormal events remained uncertain and were assigned a belief. By aggregating the belief to find the probability that a computer system was under attack, the resulting probability was highly accurate for the source IP addresses and reasonably accurate for the destination IP addresses. Active learning, which simulated feedback from a human analyst, eliminated the residual error for the destination IP addresses with a low number of events that required labeling.

Music and emotion are two realms traditionally considered to be unique to human intelligence. This dissertation focuses on furthering artificial intelligence research, specifically in the area of computational creativity, by investigating methods of composing music that elicits desired emotional and physiological responses. It includes the following: an algorithm for generating original musical selections that effectively elicit targeted emotional and physiological responses; a description of some of the musical features that contribute to the conveyance of a given emotion or the elicitation of a given physiological response; and an account of how this algorithm can be used effectively in two different situations, the generation of soundtracks for fairy tales and the generation of melodic accompaniments for lyrics. This dissertation also presents research on more general machine learning topics. These include a method of combining output from base classifiers in an ensemble that improves accuracy over a number of different baseline strategies and a description of some of the problems inherent in the Bayesian model averaging strategy and a novel algorithm for improving it.

[pt] Atualmente algoritmos de aprendizado de máquina (ML) estão incrivelmente presentes no nosso cotidiano, desde sistemas de recomendação de filmes e músicas até áreas de alto risco como saúde, justiça criminal, finanças e assim por diante, auxiliando na tomada de decisões. Mas a complexidade de criação desses algoritmos de ML também está aumentando, enquanto sua interpretabilidade está diminuindo. Muitos algoritmos e suas decisões não podem ser facilmente explicados por desenvolvedores ou usuários, e os algoritmos também não são autoexplicáveis. Com isso, erros e vieses podem acabar ficando ocultos, o que pode impactar profundamente a vida das pessoas. Devido a isso, iniciativas relacionadas a transparência, explicabilidade e interpretabilidade estão se tornando cada vez mais relevantes, como podemos ver no novo regulamento sobre proteção e tratamento de dados pessoais (GDPR, do inglês General Data Protection Regulation), aprovado em 2016 para a União Europeia, e também na Lei Geral de Proteção de Dados (LGPD) aprovada em 2020 no Brasil. Além de leis e regulamentações tratando sobre o tema, diversos autores consideram necessário o uso de algoritmos inerentemente interpretáveis; outros mostram alternativas para se explicar algoritmos caixa-preta usando explicações locais, tomando a vizinhança de um determinado ponto e então analisando a fronteira de decisão dessa região; enquanto ainda outros estudam o uso de explicações contrafactuais. Seguindo essa linha dos contrafactuais, nos propomos a desenvolver uma interface com usuário para o sistema Optimal Counterfactual Explanations in Tree Ensembles (OCEAN), denominada OceanUI, através do qual o usuário gera explicações contrafactuais plausíveis usando Programação Inteira Mista e Isolation Forest. O propósito desta interface é facilitar a geração de contrafactuais e permitir ao usuário obter um contrafactual personalizado e mais aplicável individualmente, por meio da utilização de restrições e gráficos interativos. / [en] Machine learning algorithms (ML) are becoming incredibly present in our daily lives, from movie and song recommendation systems to high-risk areas like health care, criminal justice, finance, and so on, supporting decision making. But the complexity of those algorithms is increasing while their interpretability is decreasing. Many algorithms and their decisions cannot be easily explained by either developers or users, and the algorithms are also not self-explanatory. As a result, mistakes and biases can end up being hidden, which can profoundly impact people s lives. So, initiatives concerning transparency, explainability, and interpretability are becoming increasingly more relevant, as we can see in the General Data Protection Regulation (GDPR), approved in 2016 for the European Union, and in the General Data Protection Law (LGPD) approved in 2020 in Brazil. In addition to laws and regulations, several authors consider necessary the use of inherently interpretable algorithms; others show alternatives to explain black-box algorithms using local explanations, taking the neighborhood of a given point and then analyzing the decision boundary in that region; while yet others study the use of counterfactual explanations. Following the path of counterfactuals, we propose to develop a user interface for the system Optimal Counterfactual Explanations in Tree Ensembles (OCEAN), which we call OceanUI, through which the user generates plausible counterfactual explanations using Mixed Integer Programming and Isolation Forest. The purpose of this user interface is to facilitate the counterfactual generation and to allow the user to obtain a personal and more individually applicable counterfactual, by means ofrestrictions and interactive graphics.

The purpose of this study was to examine pedagogical practices of an Indian music professor, or guru, who teaches an Indian music ensemble in a United States institution of higher learning. The role of the world music professor has been refined and redefined over the last decade. The guru-shishya paramparā system of teaching has reached a crossroad; new conditions challenge this approach. The focus of this study was to investigate, through the lens of the guru, tensions that exist between Indian pedagogy and Western pedagogy. The research design was a single-case ethnographic study that utilized participant observation in an Indian music ensemble class. I expanded Schippers’s (2009) Twelve Continuum Transmission Framework by adding aesthetics to the continuum of the framework. I used this framework as a tool to examine Indian music transmission, through a distinct pedagogical viewpoint of a guru leading a non-Western music ensemble. In this study I noted factors that influence world music transmission in Indian music education at the School of Jazz and Contemporary Music at The New School. Information regarding attitudes and the reasons for certain pedagogical practices in Indian music education can provide insight to ensemble instructors and to administrators interested in building Indian music programs. This research has implications outside of Indian music education and for music department directors interested in expanding music programs.

No description available.

No description available.

No description available.

Music participation, specifically in an ensemble setting, is known to promote learning and social skills and to contribute to a well-rounded overall education. With this in mind, this qualitative, constructivist grounded theory study explored the impacts that participating in chorus, band, or orchestra has on students’ overall experience in middle school, with a focus on joy and identity development. The researcher interviewed fifteen students about their personal experiences and feelings about their lives as middle schoolers and musicians. The findings, shared in six theoretical concepts tied to the research question, reveal important facets of these students’ experiences that shed light on the value of music education and ensemble opportunities at the middle school level. The discourse shared by the participants communicates to educators and other stakeholders how critical music is to their individual and school lives, and how different the experience might be without it.

Dans un plan stratifié, le calcul des bornes de strates peut se faire de plusieurs façons. On peut se fier à un jugement personnel et séparer les unités de la population en se basant sur la distribution de la variable de stratification. D’autres méthodes scientifiques et rigoureuses donnent un meilleur résultat, dont les algorithmes de cum √f, Sethi et Kosak. Pour les populations asymétriques, telles que retrouvées dans les enquêtes entreprises, l’utilisation d’une strate recensement permet de diminuer la taille d’échantillon et donner des estimations plus fiables. Parfois, la variable de stratification utilisée dans l’élaboration du plan de sondage ne garantit pas l’obtention de la précision cible pour toutes les variables d’intérêt de l’enquête. Utiliser la variable d’intérêt la plus difficile à estimer, comme variable de stratification, permet de garantir un CV cible minimal pour toutes les autres variables, mais engendre des grandes tailles d’échantillon. / In a stratified sampling design, the calculation of the stratum boundaries can be done in several ways. We can rely on personal judgment and separate the units of the population based on the distribution of the stratification variable. Other scientific and rigorous methods give a better result, including the algorithms of cum √f, Sethi and Kosak. For asymmetric populations, as found in the business surveys, the use of a census stratum reduces the sample size and gives more reliable estimates. Univariate methods, those that use a single stratification variable in calculating the boundaries, do not guarantee that the target precision will be obtained for all the variables of interest in the survey. Using the variable of interest that is the most difficult to estimate, as a stratification variable, makes it possible to guarantee a minimum target CV for all the other variables, but generates large sample sizes.

Tableau d’honneur de la Faculté des études supérieures et postdoctorales, 2010-2011 / L'ensemble de Julia d'une fonction rationnelle, issu de la théorie dite classique de l'itération, possède une généralisation à une théorie dite aléatoire, où les fonctions appliquées peuvent être différentes d'une itération à l'autre. En restreignant notre étude de l'itération aléatoire aux cas où les suites de fonctions considérées sont des suites dites bornées de polynômes, plusieurs phénomènes de la théorie classique se généralisent, et on se demande jusqu'à quel point c'est le cas. On étudie donc les liens entre les deux théories via la question suivante : comment est modifié l'ensemble de Julia lorsque les coefficients des fonctions qui l'engendrent sont modifiés? Un théorème classique décrit ainsi l'ensemble de Julia comme ressemblant à une multifonction méromorphe, et on tente de généraliser celui-ci. Il faut donc, d'abord, décrire les grandes lignes de la théorie l'itération et de celle des multifonctions méromorphes.