Teaching mathematics and programming : new approaches with empirical evaluation

Programming and mathematics are core areas of computer science (CS) and consequently also important parts of CS education. Introductory instruction in these two topics is, however, not without problems. Studies show that CS students find programming difficult to learn and that teaching mathematical topics to CS novices is challenging. One reason for the latter is the disconnection between mathematics and programming found in many CS curricula, which results in students not seeing the relevance of the subject for their studies. In addition, reports indicate that students' mathematical capability and maturity levels are dropping. The challenges faced when teaching mathematics and programming at CS departments can also be traced back to gaps in students' prior education. In Finland the high school curriculum does not include CS as a subject; instead, focus is on learning to use the computer and its applications as tools. Similarly, many of the mathematics courses emphasize application of formulas, while logic, formalisms and proofs, which are important in CS, are avoided. Consequently, high school graduates are not well prepared for studies in CS. Motivated by these challenges, the goal of the present work is to describe new approaches to teaching mathematics and programming aimed at addressing these issues: Structured derivations is a logic-based approach to teaching mathematics, where formalisms and justifications are made explicit. The aim is to help students become better at communicating their reasoning using mathematical language and logical notation at the same time as they become more confident with formalisms. The Python programming language was originally designed with education in mind, and has a simple syntax compared to many other popular languages. The aim of using it in instruction is to address algorithms and their implementation in a way that allows focus to be put on learning algorithmic thinking and programming instead of on learning a complex syntax. Invariant based programming is a diagrammatic approach to developing programs that are correct by construction. The approach is based on elementary propositional and predicate logic, and makes explicit the underlying mathematical foundations of programming. The aim is also to show how mathematics in general, and logic in particular, can be used to create better programs.

Enabling constructive alignment in programming instruction

In this thesis, simple methods have been sought to lower the teacher’s threshold to start to apply constructive alignment in instruction. From the phases of the instructional process, aspects that can be improved with little effort by the teacher have been identified. Teachers have been interviewed in order to find out what students actually learn in computer science courses. A quantitative analysis of the structured interviews showed that in addition to subject specific skills and knowledge, students learn many other skills that should be mentioned in the learning outcomes of the course. The students’ background, such as their prior knowledge, learning style and culture, affects how they learn in a course. A survey was conducted to map the learning styles of computer science students and to see if their cultural background affected their learning style. A statistical analysis of the data indicated that computer science students are different learners than engineering students in general and that there is a connection between the student’s culture and learning style. In this thesis, a simple self-assessment scale that is based on Bloom’s revised taxonomy has been developed. A statistical analysis of the test results indicates that in general the scale is quite reliable, but single students still slightly overestimate or under-estimate their knowledge levels. For students, being able to follow their own progress is motivating, and for a teacher, self-assessment results give information about how the class is proceeding and what the level of the students’ knowledge is.

Developing an introductory object-oriented programming course

The state of the object-oriented programming course in Lappeenranta University of Technology had reached the point, where it required changes to provide better learning opportunities and thus the learning outcomes. Based on the student feedback the course was partially dated and ineffective. The components of the course were analysed and the ineffective elements were removed and new methods were introduced to improve the course. The major changes included the change from traditional teaching methods to reverse classroom method and the use of Java as the programming language. The changes were measured by the student feedback, lecturer’s observations and comparison to previous years. The feedback suggested that the changes were successful; the course received higher overall grade than before.

Perceived effectiveness of alternative programming : a case study /

The topic of this research was alternative programming in secondary public education. The purpose of this research was to explore the perceived effectiveness of two public secondary programs that are aJternative to mainstream or "regular" education. Two case study sites were used to research diverse ends of the aJtemative programming continuum. The first case study demonstrated a gifted program and the second demonstrated a behavioral program. Student needs were examined in terms of academic needs, emotional needs, career needs, and social needs. Research conducted in these sites examined how the students, teachers, onsite staff, and program administrators perceived that individual needs were met and unmet in these two programs. The study was qualitative and exploratory, using deductive and inductive research techniques. Similar themes of best practice that were identified in the case study sites aided in the development of a teaching and learning model. Four themes were identified as important within the case study sites. These themes included the commitment and motivation of teachers and the support of administration in the gifted program, and the importance of location and the flow of information and communication in the behavior program. Six themes emerged that were similar across the case study sites. These themes included the individual nature of programming, recognition of student achievement, the alternative program as a place of safety and community, importance of interpersonal capacity, priority of basic needs, and, finally, matching student capacity with program expectations. The model incorporates these themes and is designed as a resource for teachers, program administrators, parents, and policy makers of alternative educational programs.

Learning to be literate : parental empowerment in early literacy interventions

Considerable research has focused on the success of early intervention programs for children. However, minimal research has focused on the effect these programs have on the parents of targeted children. Many current early intervention programs champion family-focused and inclusive programming, but few have evaluated parent participation in early interventions and fewer still have evaluated the impact of these programs on beliefs and attitudes and parenting practices. Since parents will continue to play a key role in their child's developmental course long after early intervention programs end, it is vital to examine whether these programs empower parents to take action to make changes in the lives of their children. The goal of this study was to understand parental influences on the early development of literacy, and in particular how parental attitudes, beliefs and self efficacy impact parent and child engagement in early literacy intervention activities. A mixed method procedure using quantitative and qualitative strategies was employed. A quasi-experimental research design was used. The research sample, sixty parents who were part of naturally occurring community interventions in at- risk neighbourhoods in a south-western Ontario city participated in the quantitative phase. Largely individuals whose home language was other than English, these participants were divided amongst three early literacy intervention groups, a Prescriptive Interventionist type group, a Participatory Empowering type group and a drop-in parent- child neighbourhood Control group. Measures completed pre and post a six session literacy intervention, on all three literacy and evidence of change in parental empowerment. Parents in all three groups, on average, held beliefs about early literacy that were positive and that were compatible with current approaches to language development and emergent literacy. No significant change in early literacy beliefs and attitudes for pre to post intervention was found. Similarly, there was no significant difference between groups on empowerment scores, but there was a significant change post intervention in one group's empowerment score. There was a drop in the empowerment score for the Prescriptive Interventionist type group, suggesting a drop in empowerment level. The qualitative aspect of this study involved six in-depth interviews completed with a sub-set of the sixty research participants. Four similar themes emerged across the groups: learning takes place across time and place; participation is key; success is achieved by taking small steps; and learning occurs in multiple ways. The research findings have important implications for practitioners and policy makers who target at risk populations with early intervention programming and wish to sustain parental empowerment. Study results show the value parents place on early learning and point to the importance of including parents in the development and delivery of early intervention programs. groups, were analyzed for evidence of change in parental attitudes and beliefs about early literacy and evidence of change in parental empowerment. Parents in all three groups, on average, held beliefs about early literacy that were positive and that were compatible with current approaches to language development and emergent literacy. No significant change in early literacy beliefs and attitudes for pre to post intervention was found. Similarly, there was no significant difference between groups on empowerment scores, but there was a significant change post intervention in one group's empowerment score. There was a drop in the empowerment score for the Prescriptive Interventionist type group, suggesting a drop in empowerment level. The qualitative aspect of this study involved six in-depth interviews completed with a sub-set of the sixty research participants. Four similar themes emerged across the groups: learning takes place across time and place; participation is key; success is achieved by taking small steps; and learning occurs in multiple ways. The research findings have important implications for practitioners and policy makers who target at risk populations with early intervention programming and wish to sustain parental empowerment. Study results show the value parents place on early learning and point to the importance of including parents in the development and delivery of early intervention programs.

Feature Selection and Classification Using Age Layered Population Structure Genetic Programming

The curse of dimensionality is a major problem in the fields of machine learning, data mining and knowledge discovery. Exhaustive search for the most optimal subset of relevant features from a high dimensional dataset is NP hard. Sub–optimal population based stochastic algorithms such as GP and GA are good choices for searching through large search spaces, and are usually more feasible than exhaustive and deterministic search algorithms. On the other hand, population based stochastic algorithms often suffer from premature convergence on mediocre sub–optimal solutions. The Age Layered Population Structure (ALPS) is a novel metaheuristic for overcoming the problem of premature convergence in evolutionary algorithms, and for improving search in the fitness landscape. The ALPS paradigm uses an age–measure to control breeding and competition between individuals in the population. This thesis uses a modification of the ALPS GP strategy called Feature Selection ALPS (FSALPS) for feature subset selection and classification of varied supervised learning tasks. FSALPS uses a novel frequency count system to rank features in the GP population based on evolved feature frequencies. The ranked features are translated into probabilities, which are used to control evolutionary processes such as terminal–symbol selection for the construction of GP trees/sub-trees. The FSALPS metaheuristic continuously refines the feature subset selection process whiles simultaneously evolving efficient classifiers through a non–converging evolutionary process that favors selection of features with high discrimination of class labels. We investigated and compared the performance of canonical GP, ALPS and FSALPS on high–dimensional benchmark classification datasets, including a hyperspectral image. Using Tukey’s HSD ANOVA test at a 95% confidence interval, ALPS and FSALPS dominated canonical GP in evolving smaller but efficient trees with less bloat expressions. FSALPS significantly outperformed canonical GP and ALPS and some reported feature selection strategies in related literature on dimensionality reduction.

Feature Selection and Classification Using Age Layered Population Structure Genetic Programming

The curse of dimensionality is a major problem in the fields of machine learning, data mining and knowledge discovery. Exhaustive search for the most optimal subset of relevant features from a high dimensional dataset is NP hard. Sub–optimal population based stochastic algorithms such as GP and GA are good choices for searching through large search spaces, and are usually more feasible than exhaustive and determinis- tic search algorithms. On the other hand, population based stochastic algorithms often suffer from premature convergence on mediocre sub–optimal solutions. The Age Layered Population Structure (ALPS) is a novel meta–heuristic for overcoming the problem of premature convergence in evolutionary algorithms, and for improving search in the fitness landscape. The ALPS paradigm uses an age–measure to control breeding and competition between individuals in the population. This thesis uses a modification of the ALPS GP strategy called Feature Selection ALPS (FSALPS) for feature subset selection and classification of varied supervised learning tasks. FSALPS uses a novel frequency count system to rank features in the GP population based on evolved feature frequencies. The ranked features are translated into probabilities, which are used to control evolutionary processes such as terminal–symbol selection for the construction of GP trees/sub-trees. The FSALPS meta–heuristic continuously refines the feature subset selection process whiles simultaneously evolving efficient classifiers through a non–converging evolutionary process that favors selection of features with high discrimination of class labels. We investigated and compared the performance of canonical GP, ALPS and FSALPS on high–dimensional benchmark classification datasets, including a hyperspectral image. Using Tukey’s HSD ANOVA test at a 95% confidence interval, ALPS and FSALPS dominated canonical GP in evolving smaller but efficient trees with less bloat expressions. FSALPS significantly outperformed canonical GP and ALPS and some reported feature selection strategies in related literature on dimensionality reduction.

Sequential Machine learning Approaches for Portfolio Management

Cette thèse envisage un ensemble de méthodes permettant aux algorithmes d'apprentissage statistique de mieux traiter la nature séquentielle des problèmes de gestion de portefeuilles financiers. Nous débutons par une considération du problème général de la composition d'algorithmes d'apprentissage devant gérer des tâches séquentielles, en particulier celui de la mise-à-jour efficace des ensembles d'apprentissage dans un cadre de validation séquentielle. Nous énumérons les desiderata que des primitives de composition doivent satisfaire, et faisons ressortir la difficulté de les atteindre de façon rigoureuse et efficace. Nous poursuivons en présentant un ensemble d'algorithmes qui atteignent ces objectifs et présentons une étude de cas d'un système complexe de prise de décision financière utilisant ces techniques. Nous décrivons ensuite une méthode générale permettant de transformer un problème de décision séquentielle non-Markovien en un problème d'apprentissage supervisé en employant un algorithme de recherche basé sur les K meilleurs chemins. Nous traitons d'une application en gestion de portefeuille où nous entraînons un algorithme d'apprentissage à optimiser directement un ratio de Sharpe (ou autre critère non-additif incorporant une aversion au risque). Nous illustrons l'approche par une étude expérimentale approfondie, proposant une architecture de réseaux de neurones spécialisée à la gestion de portefeuille et la comparant à plusieurs alternatives. Finalement, nous introduisons une représentation fonctionnelle de séries chronologiques permettant à des prévisions d'être effectuées sur un horizon variable, tout en utilisant un ensemble informationnel révélé de manière progressive. L'approche est basée sur l'utilisation des processus Gaussiens, lesquels fournissent une matrice de covariance complète entre tous les points pour lesquels une prévision est demandée. Cette information est utilisée à bon escient par un algorithme qui transige activement des écarts de cours (price spreads) entre des contrats à terme sur commodités. L'approche proposée produit, hors échantillon, un rendement ajusté pour le risque significatif, après frais de transactions, sur un portefeuille de 30 actifs.

Observational learning of motor skills : Looking for optimal models

L’observation d’un modèle pratiquant une habileté motrice promeut l’apprentissage de l’habileté en question. Toutefois, peu de chercheurs se sont attardés à étudier les caractéristiques d’un bon modèle et à mettre en évidence les conditions d’observation pouvant optimiser l’apprentissage. Dans les trois études composant cette thèse, nous avons examiné les effets du niveau d’habileté du modèle, de la latéralité du modèle, du point de vue auquel l’observateur est placé, et du mode de présentation de l’information sur l’apprentissage d’une tâche de timing séquentielle composée de quatre segments. Dans la première expérience de la première étude, les participants observaient soit un novice, soit un expert, soit un novice et un expert. Les résultats des tests de rétention et de transfert ont révélé que l’observation d’un novice était moins bénéfique pour l’apprentissage que le fait d’observer un expert ou une combinaison des deux (condition mixte). Par ailleurs, il semblerait que l’observation combinée de modèles novice et expert induise un mouvement plus stable et une meilleure généralisation du timing relatif imposé comparativement aux deux autres conditions. Dans la seconde expérience, nous voulions déterminer si un certain type de performance chez un novice (très variable, avec ou sans amélioration de la performance) dans l’observation d’une condition mixte amenait un meilleur apprentissage de la tâche. Aucune différence significative n’a été observée entre les différents types de modèle novices employés dans l’observation de la condition mixte. Ces résultats suggèrent qu’une observation mixte fournit une représentation précise de ce qu’il faut faire (modèle expert) et que l’apprentissage est d’autant plus amélioré lorsque l’apprenant peut contraster cela avec la performance de modèles ayant moins de succès. Dans notre seconde étude, des participants droitiers devaient observer un modèle à la première ou à la troisième personne. L’observation d’un modèle utilisant la même main préférentielle que soi induit un meilleur apprentissage de la tâche que l’observation d’un modèle dont la dominance latérale est opposée à la sienne, et ce, quel que soit l’angle d’observation. Ce résultat suggère que le réseau d’observation de l’action (AON) est plus sensible à la latéralité du modèle qu’à l’angle de vue de l’observateur. Ainsi, le réseau d’observation de l’action semble lié à des régions sensorimotrices du cerveau qui simulent la programmation motrice comme si le mouvement observé était réalisé par sa propre main dominante. Pour finir, dans la troisième étude, nous nous sommes intéressés à déterminer si le mode de présentation (en direct ou en vidéo) influait sur l’apprentissage par observation et si cet effet est modulé par le point de vue de l’observateur (première ou troisième personne). Pour cela, les participants observaient soit un modèle en direct soit une présentation vidéo du modèle et ceci avec une vue soit à la première soit à la troisième personne. Nos résultats ont révélé que l’observation ne diffère pas significativement selon le type de présentation utilisée ou le point de vue auquel l’observateur est placé. Ces résultats sont contraires aux prédictions découlant des études d’imagerie cérébrale ayant montré une activation plus importante du cortex sensorimoteur lors d’une observation en direct comparée à une observation vidéo et de la première personne comparée à la troisième personne. Dans l’ensemble, nos résultats indiquent que le niveau d’habileté du modèle et sa latéralité sont des déterminants importants de l’apprentissage par observation alors que le point de vue de l’observateur et le moyen de présentation n’ont pas d’effets significatifs sur l’apprentissage d’une tâche motrice. De plus, nos résultats suggèrent que la plus grande activation du réseau d’observation de l’action révélée par les études en imagerie mentale durant l’observation d’une action n’induit pas nécessairement un meilleur apprentissage de la tâche.

Modified Large Margin Nearest Neighbor Metric Learning for Regression

The main objective of this letter is to formulate a new approach of learning a Mahalanobis distance metric for nearest neighbor regression from a training sample set. We propose a modified version of the large margin nearest neighbor metric learning method to deal with regression problems. As an application, the prediction of post-operative trunk 3-D shapes in scoliosis surgery using nearest neighbor regression is described. Accuracy of the proposed method is quantitatively evaluated through experiments on real medical data.

Reinforcement Learning Approaches to Power System Scheduling

One major component of power system operation is generation scheduling. The objective of the work is to develop efficient control strategies to the power scheduling problems through Reinforcement Learning approaches. The three important active power scheduling problems are Unit Commitment, Economic Dispatch and Automatic Generation Control. Numerical solution methods proposed for solution of power scheduling are insufficient in handling large and complex systems. Soft Computing methods like Simulated Annealing, Evolutionary Programming etc., are efficient in handling complex cost functions, but find limitation in handling stochastic data existing in a practical system. Also the learning steps are to be repeated for each load demand which increases the computation time.Reinforcement Learning (RL) is a method of learning through interactions with environment. The main advantage of this approach is it does not require a precise mathematical formulation. It can learn either by interacting with the environment or interacting with a simulation model. Several optimization and control problems have been solved through Reinforcement Learning approach. The application of Reinforcement Learning in the field of Power system has been a few. The objective is to introduce and extend Reinforcement Learning approaches for the active power scheduling problems in an implementable manner. The main objectives can be enumerated as:(i) Evolve Reinforcement Learning based solutions to the Unit Commitment Problem.(ii) Find suitable solution strategies through Reinforcement Learning approach for Economic Dispatch. (iii) Extend the Reinforcement Learning solution to Automatic Generation Control with a different perspective. (iv) Check the suitability of the scheduling solutions to one of the existing power systems.First part of the thesis is concerned with the Reinforcement Learning approach to Unit Commitment problem. Unit Commitment Problem is formulated as a multi stage decision process. Q learning solution is developed to obtain the optimwn commitment schedule. Method of state aggregation is used to formulate an efficient solution considering the minimwn up time I down time constraints. The performance of the algorithms are evaluated for different systems and compared with other stochastic methods like Genetic Algorithm.Second stage of the work is concerned with solving Economic Dispatch problem. A simple and straight forward decision making strategy is first proposed in the Learning Automata algorithm. Then to solve the scheduling task of systems with large number of generating units, the problem is formulated as a multi stage decision making task. The solution obtained is extended in order to incorporate the transmission losses in the system. To make the Reinforcement Learning solution more efficient and to handle continuous state space, a fimction approximation strategy is proposed. The performance of the developed algorithms are tested for several standard test cases. Proposed method is compared with other recent methods like Partition Approach Algorithm, Simulated Annealing etc.As the final step of implementing the active power control loops in power system, Automatic Generation Control is also taken into consideration.Reinforcement Learning has already been applied to solve Automatic Generation Control loop. The RL solution is extended to take up the approach of common frequency for all the interconnected areas, more similar to practical systems. Performance of the RL controller is also compared with that of the conventional integral controller.In order to prove the suitability of the proposed methods to practical systems, second plant ofNeyveli Thennal Power Station (NTPS IT) is taken for case study. The perfonnance of the Reinforcement Learning solution is found to be better than the other existing methods, which provide the promising step towards RL based control schemes for practical power industry.Reinforcement Learning is applied to solve the scheduling problems in the power industry and found to give satisfactory perfonnance. Proposed solution provides a scope for getting more profit as the economic schedule is obtained instantaneously. Since Reinforcement Learning method can take the stochastic cost data obtained time to time from a plant, it gives an implementable method. As a further step, with suitable methods to interface with on line data, economic scheduling can be achieved instantaneously in a generation control center. Also power scheduling of systems with different sources such as hydro, thermal etc. can be looked into and Reinforcement Learning solutions can be achieved.

A Reinforcement Learning Approach to Economic Dispatch using Neural Networks

This paper presents a Reinforcement Learning (RL) approach to economic dispatch (ED) using Radial Basis Function neural network. We formulate the ED as an N stage decision making problem. We propose a novel architecture to store Qvalues and present a learning algorithm to learn the weights of the neural network. Even though many stochastic search techniques like simulated annealing, genetic algorithm and evolutionary programming have been applied to ED, they require searching for the optimal solution for each load demand. Also they find limitation in handling stochastic cost functions. In our approach once we learn the Q-values, we can find the dispatch for any load demand. We have recently proposed a RL approach to ED. In that approach, we could find only the optimum dispatch for a set of specified discrete values of power demand. The performance of the proposed algorithm is validated by taking IEEE 6 bus system, considering transmission losses

Evolving Distributed Algorithms with Genetic Programming

Distributed systems are one of the most vital components of the economy. The most prominent example is probably the internet, a constituent element of our knowledge society. During the recent years, the number of novel network types has steadily increased. Amongst others, sensor networks, distributed systems composed of tiny computational devices with scarce resources, have emerged. The further development and heterogeneous connection of such systems imposes new requirements on the software development process. Mobile and wireless networks, for instance, have to organize themselves autonomously and must be able to react to changes in the environment and to failing nodes alike. Researching new approaches for the design of distributed algorithms may lead to methods with which these requirements can be met efficiently. In this thesis, one such method is developed, tested, and discussed in respect of its practical utility. Our new design approach for distributed algorithms is based on Genetic Programming, a member of the family of evolutionary algorithms. Evolutionary algorithms are metaheuristic optimization methods which copy principles from natural evolution. They use a population of solution candidates which they try to refine step by step in order to attain optimal values for predefined objective functions. The synthesis of an algorithm with our approach starts with an analysis step in which the wanted global behavior of the distributed system is specified. From this specification, objective functions are derived which steer a Genetic Programming process where the solution candidates are distributed programs. The objective functions rate how close these programs approximate the goal behavior in multiple randomized network simulations. The evolutionary process step by step selects the most promising solution candidates and modifies and combines them with mutation and crossover operators. This way, a description of the global behavior of a distributed system is translated automatically to programs which, if executed locally on the nodes of the system, exhibit this behavior. In our work, we test six different ways for representing distributed programs, comprising adaptations and extensions of well-known Genetic Programming methods (SGP, eSGP, and LGP), one bio-inspired approach (Fraglets), and two new program representations called Rule-based Genetic Programming (RBGP, eRBGP) designed by us. We breed programs in these representations for three well-known example problems in distributed systems: election algorithms, the distributed mutual exclusion at a critical section, and the distributed computation of the greatest common divisor of a set of numbers. Synthesizing distributed programs the evolutionary way does not necessarily lead to the envisaged results. In a detailed analysis, we discuss the problematic features which make this form of Genetic Programming particularly hard. The two Rule-based Genetic Programming approaches have been developed especially in order to mitigate these difficulties. In our experiments, at least one of them (eRBGP) turned out to be a very efficient approach and in most cases, was superior to the other representations.

Adaptive Real-time Anomaly-based Intrusion Detection using Data Mining and Machine Learning Techniques

Die zunehmende Vernetzung der Informations- und Kommunikationssysteme führt zu einer weiteren Erhöhung der Komplexität und damit auch zu einer weiteren Zunahme von Sicherheitslücken. Klassische Schutzmechanismen wie Firewall-Systeme und Anti-Malware-Lösungen bieten schon lange keinen Schutz mehr vor Eindringversuchen in IT-Infrastrukturen. Als ein sehr wirkungsvolles Instrument zum Schutz gegenüber Cyber-Attacken haben sich hierbei die Intrusion Detection Systeme (IDS) etabliert. Solche Systeme sammeln und analysieren Informationen von Netzwerkkomponenten und Rechnern, um ungewöhnliches Verhalten und Sicherheitsverletzungen automatisiert festzustellen. Während signatur-basierte Ansätze nur bereits bekannte Angriffsmuster detektieren können, sind anomalie-basierte IDS auch in der Lage, neue bisher unbekannte Angriffe (Zero-Day-Attacks) frühzeitig zu erkennen. Das Kernproblem von Intrusion Detection Systeme besteht jedoch in der optimalen Verarbeitung der gewaltigen Netzdaten und der Entwicklung eines in Echtzeit arbeitenden adaptiven Erkennungsmodells. Um diese Herausforderungen lösen zu können, stellt diese Dissertation ein Framework bereit, das aus zwei Hauptteilen besteht. Der erste Teil, OptiFilter genannt, verwendet ein dynamisches "Queuing Concept", um die zahlreich anfallenden Netzdaten weiter zu verarbeiten, baut fortlaufend Netzverbindungen auf, und exportiert strukturierte Input-Daten für das IDS. Den zweiten Teil stellt ein adaptiver Klassifikator dar, der ein Klassifikator-Modell basierend auf "Enhanced Growing Hierarchical Self Organizing Map" (EGHSOM), ein Modell für Netzwerk Normalzustand (NNB) und ein "Update Model" umfasst. In dem OptiFilter werden Tcpdump und SNMP traps benutzt, um die Netzwerkpakete und Hostereignisse fortlaufend zu aggregieren. Diese aggregierten Netzwerkpackete und Hostereignisse werden weiter analysiert und in Verbindungsvektoren umgewandelt. Zur Verbesserung der Erkennungsrate des adaptiven Klassifikators wird das künstliche neuronale Netz GHSOM intensiv untersucht und wesentlich weiterentwickelt. In dieser Dissertation werden unterschiedliche Ansätze vorgeschlagen und diskutiert. So wird eine classification-confidence margin threshold definiert, um die unbekannten bösartigen Verbindungen aufzudecken, die Stabilität der Wachstumstopologie durch neuartige Ansätze für die Initialisierung der Gewichtvektoren und durch die Stärkung der Winner Neuronen erhöht, und ein selbst-adaptives Verfahren eingeführt, um das Modell ständig aktualisieren zu können. Darüber hinaus besteht die Hauptaufgabe des NNB-Modells in der weiteren Untersuchung der erkannten unbekannten Verbindungen von der EGHSOM und der Überprüfung, ob sie normal sind. Jedoch, ändern sich die Netzverkehrsdaten wegen des Concept drif Phänomens ständig, was in Echtzeit zur Erzeugung nicht stationärer Netzdaten führt. Dieses Phänomen wird von dem Update-Modell besser kontrolliert. Das EGHSOM-Modell kann die neuen Anomalien effektiv erkennen und das NNB-Model passt die Änderungen in Netzdaten optimal an. Bei den experimentellen Untersuchungen hat das Framework erfolgversprechende Ergebnisse gezeigt. Im ersten Experiment wurde das Framework in Offline-Betriebsmodus evaluiert. Der OptiFilter wurde mit offline-, synthetischen- und realistischen Daten ausgewertet. Der adaptive Klassifikator wurde mit dem 10-Fold Cross Validation Verfahren evaluiert, um dessen Genauigkeit abzuschätzen. Im zweiten Experiment wurde das Framework auf einer 1 bis 10 GB Netzwerkstrecke installiert und im Online-Betriebsmodus in Echtzeit ausgewertet. Der OptiFilter hat erfolgreich die gewaltige Menge von Netzdaten in die strukturierten Verbindungsvektoren umgewandelt und der adaptive Klassifikator hat sie präzise klassifiziert. Die Vergleichsstudie zwischen dem entwickelten Framework und anderen bekannten IDS-Ansätzen zeigt, dass der vorgeschlagene IDSFramework alle anderen Ansätze übertrifft. Dies lässt sich auf folgende Kernpunkte zurückführen: Bearbeitung der gesammelten Netzdaten, Erreichung der besten Performanz (wie die Gesamtgenauigkeit), Detektieren unbekannter Verbindungen und Entwicklung des in Echtzeit arbeitenden Erkennungsmodells von Eindringversuchen.

On the Convergence of Stochastic Iterative Dynamic Programming Algorithms

Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms, including the TD(lambda) algorithm of Sutton (1988) and the Q-learning algorithm of Watkins (1989), can be motivated heuristically as approximations to dynamic programming (DP). In this paper we provide a rigorous proof of convergence of these DP-based learning algorithms by relating them to the powerful techniques of stochastic approximation theory via a new convergence theorem. The theorem establishes a general class of convergent algorithms to which both TD(lambda) and Q-learning belong.