Denne hovedoppgaven er rettet mot en praktisk implementasjon av et automatisk visuelt inspeksjonssystem. På bakgrunn av en serie av treningsbilder er målsetningen at systemet skal kunne klassifisere objekters avbildninger som godkjent eller underkjent. Arbeidet har lagt stor vekt på at systemet skal virke på generelle objekter. Systemet er implementert i Microsoft Visual Studio .NET 2003 C++, og viktige elementer tilknyttet arbeidet beskrives i denne rapporten. Resultatene virker lovende, da inspeksjonssystemet gjennomsnittlig klassifiserer 91% riktig på de 8 bildesett som systemet er testet med. Videre planer gir imidlertid håp om å utbedre systemet betydelig. Disse planene presenteres som videre arbeid i slutten av rapporten.

In this thesis, we develop a meta-reasoning system based on CBR which solves sliding-block puzzles. The meta-reasoning system is built on top of a search-based sliding-block puzzle solving program which was developed as part of the specialization project at NTNU. As part of the thesis work, we study existing literature on automatic puzzle solving methods and state space search, as well as the use of reasoning and meta-level reasoning applied to puzzles and games. The literature study forms the theoretical foundation for the development of the meta-reasoning system. The meta-reasoning system is further enhanced by adding a meta-control cycle which uses randomized search to generate new cases to apply to puzzles. In addition, we explore several ways of improving the underlying solver program by trying to solve hard puzzles by using the solution for easier variants, and by developing a more memory-efficient way of representing puzzle configurations. We evaluate the results of our system, and shows that it offers a slight improvement compared to solving the puzzles with a set of general cases, as well as showing vast improvement for a few isolated test cases, but the performance is slightly behind the hand-tuned parameters we found in the specialization project. We conclude our work by identifying parts of our system where improvement can be done, as well as suggesting other promising areas for further research.

This report will explore behavior-based robotics and relevant AI techniques. A system for autonomous control of mobile robots inspired by behavior-based robotics, in particular Rodney Brooks' subsumption architecture, have been implemented, adapted for use in a multiagent environment. The system is modular and flexible, allowing for easy addition and removal of system parts. A weight-based command fusion approach is taken to action selection, making it possible to satisfy multiple behaviors simultaneously.

This project report describes a hybrid genetic algorithm that works as a schedule generator for a complex robotic harvesting task. The task is set to a dynamic environment with a robotic opponent, making responsiveness of the planning algorithm particularly important. To solve this task, many previous scheduling algorithms were studied. Genetic algorithms have successfully been used in many dynamic scheduling tasks, due to their ability to incrementally adapt and optimize solutions when changes are made to the environment. Many of the previous approaches also used a separate heuristic to quicly adapt solutions to the new environment, making the algorithm more responsive. In addition, the study of previous work revealed the importance of population diversity when making a responsive genetic algorithm. Implementation was based on a genetic algorithm made as the author's fifth year specialization project for solving a static version of the same task. This algorithm was hybridized with a powerful local search technique that proved essential in generating good solutions for the complex harvesting task. When extending the algorithm to also work in a dynamically changing environment, several adaptations and extensions needed to be made, to make it more responsive. The extensions and adaptations include a fast-response heuristic for immediate adaptation to environmental changes, a decrease in genotype size to speed up local searches and a contingency planning module intending to solve problems before they arise. Experiments proved that the implemented dynamic planner successfully adapted its plans to a changing environment, clearly showing improvements compared to running a static plan. Further experiments also proved that the dynamic planner was able to deal with erroneous time estimates in its simulator module in a good way. Experiments on contingency planning gave no clear results, but indicated that using computational resources for planning ahead may be a good choice, if the contingency to plan for is carefully selected. As no unequivocal results were obtained, further studies of combining genetic algorithms and contingency planning may be an interesting task for future efforts.

A summary is a shortened version of a text that contains the main points of the original content. Automatic summarization is the task of generating a summary by a computer. For example, given a collection of news articles for the last week an automatic summarizer is able to create a concise overview of the important events. This summary can be used as the replacement for the original content or help to identify the events that a person is particularly interested in. Potentially, automatic summarization can save a lot of time for people that deal with a large amount of textual information. The straightforward way to generate a summary is to select several sentences from the original text and organize them in way to create a coherent text. This approach is called extraction-based summarization and is the topic of this thesis. Extraction-based summarization is a complex task that consists of several challenging subtasks. The essential part of the extraction-based approach is identification of sentences that contain important information. It can be done using graph-based representations and centrality measures that exploit similarities between sentences to identify the most central sentences. This thesis provide a comprehensive overview of methods used in extraction-based automatic summarization. In addition, several general natural language processing issues such as feature selection and text representation models are discussed with regard to automatic summarization. Part of the thesis is dedicated to graph-based representations and centrality measures used in extraction-based summarization. Theoretical analysis is reinforced with the experiments using the summarization framework implemented for this thesis. The task for the experiments is query-focused multi-document extraction-based summarization, that is, summarization of several documents according to a user query. The experiments investigate several approaches to this task as well as the use of different representation models, similarity and centrality measures. The obtained results indicate that use of graph centrality measures significantly improves the quality of generated summaries. Among the variety of centrality measure the degree-based ones perform better than path-based measures. The best performance is achieved when centralities are combined with redundancy removal techniques that prevent inclusion of similar sentences in a summary. Experiments with representation models reveal that a simple local term count representation performs better than the distributed representation based on latent semantic analysis, which indicates that further investigation of distributed representations in regard to automatic summarization is necessary. The implemented system performs quite good compared with the systems that participated in DUC 2007 summarization competition. Nevertheless, manual inspection of the generated summaries demonstrate some of the flaws of the implemented summarization mechanism that can be addressed by introducing advanced algorithms for sentence simplification and sentence ordering.

This thesis investigates the application of artificial neural networks (ANNs) for forecasting financial time series (e.g. stock prices).The theory of technical analysis dictates that there are repeating patterns that occur in the historic prices of stocks, and that identifying these patterns can be of help in forecasting future price developments. A system was therefore developed which contains several ``agents'', each producing recommendations on the stock price based on some aspect of technical analysis theory. It was then tested if ANNs, using these recommendations as inputs, could be trained to forecast stock price fluctuations with some degree of precision and reliability.The predictions of the ANNs were evaluated by calculating the Pearson correlation between the predicted and actual price changes, and the ``hit rate'' (how often the predicted and the actual change had the same sign). Although somewhat mixed overall, the empirical results seem to indicate that at least some of the ANNs were able to learn enough useful features to have significant predictive power. Tests were performed with ANNs forecasting over different time frames, including intraday. The predictive performance was seen to decline on the shorter time scales.

In this thesis we develop a novel network model that extends the traditional artificial neural network (ANN) model to include oscillatory behaviour. This model is able to correctly classify combinations of previously learned input patterns by grouping features that belong to the same category. This grouping process is termed segmentation and we show how synchrony of oscillations is the necessary missing component of ANNs to be able to perform this segmentation. Using this model we go on to show that top-down modulatory feedback is necessary to enable separation of multiple objects in a scene and segmentation of their individual features. This type of feedback is distinctly different than recurrency and is what enables the rich dynamics between the nodes of our network. Additionally, we show how our model's dynamics avoid the combinatorial explosion in required training repetitions of traditional feed-forward classification networks. In these networks, relations between objects must explicitly be learned. In contrast, the dynamics of modulatory feedback allow us to defer calculation of these relations until run-time, thus creating a more robust system. We call our model Fuzzy Oscillations, and it achieves good results when compared to existing models. However, oscillatory neural network models successful in achieving segmentation are a relatively recent development. We thus feel that our model is a contribution to the field of oscillatory neural networks.

Historical stock prices are used to predict the direction of future stock prices. The developed stock price prediction model uses a novel two-layer reasoning approach that employs domain knowledge from technical analysis in the first layer of reasoning to guide a second layer of reasoning based on machine learning. The model is supplemented by a money management strategy that use the historical success of predictions made by the model to determine the amount of capital to invest on future predictions. Based on a number of portfolio simulations with trade signals generated by the model, we conclude that the prediction model successfully outperforms the Oslo Benchmark Index (OSEBX).

Recommender systems aim to provide users with personalised recommendations of items based on their preferences. Such systems have during the last 15 years been applied in many domains and have enjoyed an increased popularity both in research communities and commerce. In this thesis our overlying aim is to work towards creating a recommender system for tourists visiting Trondheim. We begin this work by addressing the cold-start user problem, which is the problem of giving high-quality recommendations to new users who the system has little or no information about. The problem is severe in the tourist domain where the majority of users are cold-start users. To properly address the problem, we present a systematic literature review of the recommender system literature identifying nine types of solutions to the cold-start user problem. We evaluate the solution types in context of the tourist domain, and find that using demographic user data is the best solution in this domain. We include this solution as a part when we propose a design of a location-aware Bayesian recommender system for tourists visiting Trondheim.

<p>The main objective of the work reported in this thesis has been to study and develop methodologies that can improve the communication gap between design and manufacturing systems. The emphasis has been on searching for the possible means of modeling and optimizing processes in an integrated design and manufacturing system environment using the combined capabilities (hybrids) of computational intelligence tools particularly that of artificial neural networks and genetic algorithms. </p><p>Within the last two decades, a trend of interest towards use of computers has been observed in almost all business activities. This has forced the industrial business to undergo dynamic profound changes with automation through information and communication technology being on the forefront of business success. Business in manufacturing engineering is no exceptional to this trend. Several functions in the manufacturing field such as design, process planning and manufacturing have enjoyed the recent advances in information and communication technology. However, the earlier isolated automation in each function have created a significant hindrance to smooth flow of information particularly because there has been a very high system incompatibility among the computerized systems.</p><p>One of the most difficult problems in modern manufacturing is the instability of production systems to mimic the basis human capabilities such as adjusting appropriately to the ever-changing environment. From past studies, it has been possible to witness that advances in theory and application methodology of artificial intelligence techniques can overcome many of the obstacles existing in manufacturing discipline. Today, the emergence of advanced computational methods in the artificial intelligence world such as genetic algorithms and neural networks, both inspired by the natural evolutionary process, has created a new field of research and application referred to as computational intelligence (CI) approach.</p><p>Accordingly, this thesis focuses on the application of computational intelligence tools from two main perspectives. On the one hand, instead of the isolated automation of each manufacturing function, the CI techniques have been considered as powerful tools that allow all functions to operate within a fully integrated and intelligent manufacturing system. Particularly, since process planning, is the main linking element between design and manufacturing functions, an automated and optimized process planning function creates a much more powerful environment that leads to the optimization of the whole process. Particularly, being able to integrate feature recognition and operation sequence optimization is an important element in the manufacturing system chain that can highly contribute to the automation and flexibility of the integrated design and manufacturing system. On the other hand, the computational intelligence techniques themselves have certain weakness of their own in solving the complex manufacturing process as a stand-alone form. In a hybrid form, however, they can either support or complement each other.</p><p>To realize these two points, this thesis has focused on the development of theories and application methodologies of hybrid computational intelligence systems to model and optimize complex manufacturing processes. The aim is to exploit the strong side of one computational intelligence tool and support or complement the weakness of the other. To this effect, qualitative analysis and reasoning of computational intelligence based hybrid systems are comprehensively discussed. The development theoretical backgrounds and methodologies are further used in key problem areas of the manufacturing system such as operation sequencing, machining economics analysis using multi-objective optimization approach and modeling and optimization of unstructured data collected from a non-conventional machining environment (electro-discharge machining). The results from the hybrid CI application to model and optimize the electro-discharge machine show that the methodology is also important not only to the industrial activities using this technology, but also promotes further research and application in the discipline. Though the focus in this thesis has been on discrete part manufacturing industries, it is important to mention that the facts, the developed methodologies and the discussed issues in the study are applicable to other industrial businesses. </p>