With the ubiquity of mobile devices, there has been increased interest in determining how they can be used with location-based services. These types of services work best when the device has the ability to sense its location frequently, while still maintaining enough battery life to carry out its normal daily functions. Since the life of the battery on a mobile device is already so limited, ways of preserving that energy has become an important issue. The goal of this thesis is to demonstrate that Bluetooth can assist in providing energy efficient mobile device localization. This goal is achieved through a proposed Bluetooth Location Service Discovery framework which provides an API that can be incorporated into third party applications. The API allows BlackBerry devices to use surrounding Bluetooth devices in order to make a prediction about its current location. Predictions are completed with the assistance of the K-Nearest Neighbour data mining algorithm, and can be used as an alternative to invoking the GPS. The results obtained through experiments demonstrate that the results are comparable to those obtained with GPS.

The k-nearest neighbour (k-NN) classifier is one of the oldest and most important supervised learning algorithms for classifying datasets. Traditionally the Euclidean norm is used as the distance for the k-NN classifier. In this thesis we investigate the use of alternative distances for the k-NN classifier. We start by introducing some background notions in statistical machine learning. We define the k-NN classifier and discuss Stone's theorem and the proof that k-NN is universally consistent on the normed space R^d. We then prove that k-NN is universally consistent if we take a sequence of random norms (that are independent of the sample and the query) from a family of norms that satisfies a particular boundedness condition. We extend this result by replacing norms with distances based on uniformly locally Lipschitz functions that satisfy certain conditions. We discuss the limitations of Stone's lemma and Stone's theorem, particularly with respect to quasinorms and adaptively choosing a distance for k-NN based on the labelled sample. We show the universal consistency of a two stage k-NN type classifier where we select the distance adaptively based on a split labelled sample and the query. We conclude by giving some examples of improvements of the accuracy of classifying various datasets using the above techniques.

The Swedish educational reforms of the 1990s introduced a choice- and voucher-based system, which allowed students to choose schools regardless of their proximity to them. As a consequence, new opportunities for geographical disparities in educational provisions as well as in home-to- school mobilities have emerged. The following thesis addresses this development by focusing on compulsory school (grade 9) students’ home-to-school mobility patterns. More specifically, a Bourdieusian lens is applied to understand mobility in terms of both physical and social space. In contrast to the Bourdieusian tradition, articulations between social and physical space are operationalized by constructing individually defined, scalable neighbourhoods. The software EquiPop is used to compute neighbourhood context neighbours in the municipality of Stockholm (n = 779 079) using the k-nearest neighbour algorithm (k = 1 600). A k-means cluster analysis is applied to construct income-based neighbourhood types. On this basis, this thesis asks about the localizations and positions of schools and students as well as about the mobility patterns and predictors of students residing in low-income, and thus economic capital deprived, neighbourhoods (n = 2 346). Utilizing register data, the study finds an unequal distribution of educational provisions in relation to different providers, i.e. municipal schools and independent schools, as well as different school types. Furthermore, the results indicate that students from low-income neighbourhoods are unequally mobilized dependent on migration background and the educational background of mothers. Moreover, independent schools have been found to be a attractive alternative for students from low-income neighbourhoods. / Research project "On the outskirt of the school market" by Håkan Forsberg

Yes / Automatic gender classification has become a topic of great interest to the visual computing research community in recent times. This is due to the fact that computer-based automatic gender recognition has multiple applications including, but not limited to, face perception, age, ethnicity, identity analysis, video surveillance and smart human computer interaction. In this paper, we discuss a machine learning approach for efficient identification of gender purely from the dynamics of a person’s smile. Thus, we show that the complex dynamics of a smile on someone’s face bear much relation to the person’s gender. To do this, we first formulate a computational framework that captures the dynamic characteristics of a smile. Our dynamic framework measures changes in the face during a smile using a set of spatial features on the overall face, the area of the mouth, the geometric flow around prominent parts of the face and a set of intrinsic features based on the dynamic geometry of the face. This enables us to extract 210 distinct dynamic smile parameters which form as the contributing features for machine learning. For machine classification, we have utilised both the Support Vector Machine and the k-Nearest Neighbour algorithms. To verify the accuracy of our approach, we have tested our algorithms on two databases, namely the CK+ and the MUG, consisting of a total of 109 subjects. As a result, using the k-NN algorithm, along with tenfold cross validation, for example, we achieve an accurate gender classification rate of over 85%. Hence, through the methodology we present here, we establish proof of the existence of strong indicators of gender dimorphism, purely in the dynamics of a person’s smile.

No / This chapter is concerned with the discussion of a computational framework to aid with gender classification in an automated fashion using the dynamics of a smile. The computational smile dynamics framework we discuss here uses the spatio-temporal changes on the face during a smile. Specifically, it uses a set of spatial and temporal features on the overall face. These include the changes in the area of the mouth, the geometric flow around facial features and a set of intrinsic features over the face. These features are explicitly derived from the dynamics of the smile. Based on it, a number of distinct dynamic smile parameters can be extracted which can then be fed to a machine learning algorithm for gender classification.

Yes / We present a technique for automatically acquiring operational knowledge on how to adapt assembly systems to new production demands or recover from disruptions. Dealing with changes and disruptions affecting an assembly station is a complex process which requires deep knowledge of the assembly process, the product being assembled and the adopted technologies. Shop-floor operators typically perform a series of adjustments by trial and error until the expected results in terms of performance and quality are achieved. With the proposed approach, such adjustments are captured and their effect on the station is measured. Adaptation knowledge is then derived by generalising from individual cases using a variant of the k-nearest neighbour algorithm. The operator is informed about potential adaptations whenever the station enters a state similar to one contained in the experience base, that is, a state on which adaptation information has been captured. A case study is presented, showing how the technique enables to reduce adaptation times. The general system architecture in which the technique has been implemented is described, including the role of the different software components and their interactions.

The numerical model to forecast road conditions, Model of the Environment and Temperature of Roads (METRo), laid the foundation of solving the energy balance and calculating the temperature evolution of roads. METRo does this by providing a numerical modelling system making use of Road Weather Information Stations (RWIS) and meteorological projections. While METRo accommodates tools for correcting errors at each station, such as regional differences or microclimates, this thesis proposes machine learning as a supplement to the METRo prognostications for accounting station characteristics. Controlled experiments were conducted by comparing four regression algorithms, that is, recurrent and dense neural network, random forest and k-nearest neighbour, to predict the squared deviation of METRo forecasted road surface temperatures. The results presented reveal that the models utilising the random forest algorithm yielded the most reliable predictions of METRo deviations. However, the study also presents the promise of neural networks and the ability and possible advantage of seasonal adjustments that the networks could offer.

This paper uses statistical learning to examine and compare three different statistical methods with the aim to predict credit card fraud. The methods compared are Logistic Regression, K-Nearest Neighbour and Random Forest. They are applied and estimated on a data set consisting of nearly 300,000 credit card transactions to determine their performance using classification of fraud as the outcome variable. The three models all have different properties and advantages. The K-NN model preformed the best in this paper but has some disadvantages, since it does not explain the data but rather predict the outcome accurately. Random Forest explains the variables but performs less precise. The Logistic Regression model seems to be unfit for this specific data set.

<p>The ion current measured from the spark plug in a spark ignited combustion engine is used </p><p>as basis for analysis and control of the combustion variability caused by exhaust gas </p><p>recirculation. Methods for extraction of in-cylinder pressure information from the ion </p><p>current are analyzed in terms of reliability and processing efficiency. A model for the </p><p>recognition of combustion variability using this information is selected and tested on both </p><p>simulated and car data.</p>

The ion current measured from the spark plug in a spark ignited combustion engine is used as basis for analysis and control of the combustion variability caused by exhaust gas recirculation. Methods for extraction of in-cylinder pressure information from the ion current are analyzed in terms of reliability and processing efficiency. A model for the recognition of combustion variability using this information is selected and tested on both simulated and car data.