Comparison Structure Analysis

This study presents an automatic, computer-aided analytical method called Comparison Structure Analysis (CSA), which can be applied to different dimensions of music. The aim of CSA is first and foremost practical: to produce dynamic and understandable representations of musical properties by evaluating the prevalence of a chosen musical data structure through a musical piece. Such a comparison structure may refer to a mathematical vector, a set, a matrix or another type of data structure and even a combination of data structures. CSA depends on an abstract systematic segmentation that allows for a statistical or mathematical survey of the data. To choose a comparison structure is to tune the apparatus to be sensitive to an exclusive set of musical properties. CSA settles somewhere between traditional music analysis and computer aided music information retrieval (MIR). Theoretically defined musical entities, such as pitch-class sets, set-classes and particular rhythm patterns are detected in compositions using pattern extraction and pattern comparison algorithms that are typical within the field of MIR. In principle, the idea of comparison structure analysis can be applied to any time-series type data and, in the music analytical context, to polyphonic as well as homophonic music. Tonal trends, set-class similarities, invertible counterpoints, voice-leading similarities, short-term modulations, rhythmic similarities and multiparametric changes in musical texture were studied. Since CSA allows for a highly accurate classification of compositions, its methods may be applicable to symbolic music information retrieval as well. The strength of CSA relies especially on the possibility to make comparisons between the observations concerning different musical parameters and to combine it with statistical and perhaps other music analytical methods. The results of CSA are dependent on the competence of the similarity measure. New similarity measures for tonal stability, rhythmic and set-class similarity measurements were proposed. The most advanced results were attained by employing the automated function generation – comparable with the so-called genetic programming – to search for an optimal model for set-class similarity measurements. However, the results of CSA seem to agree strongly, independent of the type of similarity function employed in the analysis.

Semantic and fuzzy modelling for human behaviour recognition in smart spaces : a case study on ambient assisted living.

Human activity recognition in everyday environments is a critical, but challenging task in Ambient Intelligence applications to achieve proper Ambient Assisted Living, and key challenges still remain to be dealt with to realize robust methods. One of the major limitations of the Ambient Intelligence systems today is the lack of semantic models of those activities on the environment, so that the system can recognize the speci c activity being performed by the user(s) and act accordingly. In this context, this thesis addresses the general problem of knowledge representation in Smart Spaces. The main objective is to develop knowledge-based models, equipped with semantics to learn, infer and monitor human behaviours in Smart Spaces. Moreover, it is easy to recognize that some aspects of this problem have a high degree of uncertainty, and therefore, the developed models must be equipped with mechanisms to manage this type of information. A fuzzy ontology and a semantic hybrid system are presented to allow modelling and recognition of a set of complex real-life scenarios where vagueness and uncertainty are inherent to the human nature of the users that perform it. The handling of uncertain, incomplete and vague data (i.e., missing sensor readings and activity execution variations, since human behaviour is non-deterministic) is approached for the rst time through a fuzzy ontology validated on real-time settings within a hybrid data-driven and knowledgebased architecture. The semantics of activities, sub-activities and real-time object interaction are taken into consideration. The proposed framework consists of two main modules: the low-level sub-activity recognizer and the high-level activity recognizer. The rst module detects sub-activities (i.e., actions or basic activities) that take input data directly from a depth sensor (Kinect). The main contribution of this thesis tackles the second component of the hybrid system, which lays on top of the previous one, in a superior level of abstraction, and acquires the input data from the rst module's output, and executes ontological inference to provide users, activities and their in uence in the environment, with semantics. This component is thus knowledge-based, and a fuzzy ontology was designed to model the high-level activities. Since activity recognition requires context-awareness and the ability to discriminate among activities in di erent environments, the semantic framework allows for modelling common-sense knowledge in the form of a rule-based system that supports expressions close to natural language in the form of fuzzy linguistic labels. The framework advantages have been evaluated with a challenging and new public dataset, CAD-120, achieving an accuracy of 90.1% and 91.1% respectively for low and high-level activities. This entails an improvement over both, entirely data-driven approaches, and merely ontology-based approaches. As an added value, for the system to be su ciently simple and exible to be managed by non-expert users, and thus, facilitate the transfer of research to industry, a development framework composed by a programming toolbox, a hybrid crisp and fuzzy architecture, and graphical models to represent and con gure human behaviour in Smart Spaces, were developed in order to provide the framework with more usability in the nal application. As a result, human behaviour recognition can help assisting people with special needs such as in healthcare, independent elderly living, in remote rehabilitation monitoring, industrial process guideline control, and many other cases. This thesis shows use cases in these areas.

Genetic, prenatal and postnatal determinants of weight gain and obesity in young children – The STEPS Study

Genetic, Prenatal and Postnatal Determinants of Weight Gain and Obesity in Young Children – The STEPS Study University of Turku, Faculty of Medicine, Department of Paediatrics, University of Turku Doctoral Program of Clinical Investigation (CLIPD), Turku Institute for Child and Youth Research. Conditions of being overweight and obese in childhood are common health problems with longlasting effects into adulthood. Currently 22% of Finnish boys and 12% of Finnish girls are overweight and 4% of Finnish boys and 2% of Finnish girls are obese. The foundation for later health is formed early, even before birth, and the importance of prenatal growth on later health outcomes is widely acknowledged. When the mother is overweight, had high gestational weight gain and disturbances in glucose metabolism during pregnancy, an increased risk of obesity in children is present. On the other hand, breastfeeding and later introduction of complementary foods are associated with a decreased obesity risk. In addition to these, many genetic and environmental factors have an effect on obesity risk, but the clustering of these factors is not extensively studied. The main objective of this thesis was to provide comprehensive information on prenatal and early postnatal factors associated with weight gain and obesity in infancy up to two years of age. The study was part of the STEPS Study (Steps to Healthy Development), which is a follow-up study consisting of 1797 families. This thesis focused on children up to 24 months of age. Altogether 26% of boys and 17% of girls were overweight and 5% of boys and 4% of girls were obese at 24 months of age according to New Finnish Growth references for Children BMI-for-age criteria. Compared to children who remained normal weight, the children who became overweight or obese showed different growth trajectories already at 13 months of age. The mother being overweight had an impact on children’s birth weight and early growth from birth to 24 months of age. The mean duration of breastfeeding was almost 2 months shorter in overweight women in comparison to normal weight women. A longer duration of breastfeeding was protective against excessive weight gain, high BMI, high body weight and high weight-for-length SDS during the first 24 months of life. Breast milk fatty acid composition differed between overweight and normal weight mothers, and overweight women had more saturated fatty acids and less n-3 fatty acids in breast milk. Overweight women also introduced complementary foods to their infants earlier than normal weight mothers. Genetic risk score calculated from 83 obesogenic- and adiposity-related single nucleotide polymorphisms (SNPs) showed that infants with a high genetic risk for being overweight and obese were heavier at 13 months and 24 months of age than infants with a low genetic risk, thus possibly predisposing to later obesity in obesogenic environment. Obesity Risk Score showed that children with highest number of risk factors had almost 6-fold risk of being overweight and obese at 24 months compared to children with lowest number of risk factors. The accuracy of the Obesity Risk Score in predicting overweight and obesity at 24 months was 82%. This study showed that many of the obesogenic risk factors tend to cluster within children and families and that children who later became overweight or obese show different growth trajectories already at a young age. These results highlight the importance of early detection of children with higher obesity risk as well as the importance of prevention measures focused on parents. Keywords: Breastfeeding, Child, Complementary Feeding, Genes, Glucose metabolism, Growth, Infant Nutrition Physiology, Nutrition, Obesity, Overweight, Programming