New kernel functions and learning methods for text and data mining

Recent advances in machine learning methods enable increasingly the automatic construction of various types of computer assisted methods that have been difficult or laborious to program by human experts. The tasks for which this kind of tools are needed arise in many areas, here especially in the fields of bioinformatics and natural language processing. The machine learning methods may not work satisfactorily if they are not appropriately tailored to the task in question. However, their learning performance can often be improved by taking advantage of deeper insight of the application domain or the learning problem at hand. This thesis considers developing kernel-based learning algorithms incorporating this kind of prior knowledge of the task in question in an advantageous way. Moreover, computationally efficient algorithms for training the learning machines for specific tasks are presented. In the context of kernel-based learning methods, the incorporation of prior knowledge is often done by designing appropriate kernel functions. Another well-known way is to develop cost functions that fit to the task under consideration. For disambiguation tasks in natural language, we develop kernel functions that take account of the positional information and the mutual similarities of words. It is shown that the use of this information significantly improves the disambiguation performance of the learning machine. Further, we design a new cost function that is better suitable for the task of information retrieval and for more general ranking problems than the cost functions designed for regression and classification. We also consider other applications of the kernel-based learning algorithms such as text categorization, and pattern recognition in differential display. We develop computationally efficient algorithms for training the considered learning machines with the proposed kernel functions. We also design a fast cross-validation algorithm for regularized least-squares type of learning algorithm. Further, an efficient version of the regularized least-squares algorithm that can be used together with the new cost function for preference learning and ranking tasks is proposed. In summary, we demonstrate that the incorporation of prior knowledge is possible and beneficial, and novel advanced kernels and cost functions can be used in algorithms efficiently.

Socially Responsible Investing: Considerable Alternative to Conventional Investing?

The aim of the thesis was to examine socially responsible investing, its background, development, and performance relative to conventional investing. Finance theory was exploited in the study in order to find possible weaknesses of socially responsible investing. A number of U.S.-based studies about the same subject were analyzed as well. According to the majority of the studies, socially responsible investing performs equally well with conventional investing. Return differences during May 2000 through November 2008 were measured by conducting an empirical study about the Calvert Social Index, the broad-based S&P 500 index, and the technology-based Nasdaq index. Return differences were observed by using measures of simple return and risk-return ratios. Based on this empirical research we state that socially responsible investing underperforms conventional investing, which differs from the majority of the earlier study results. We also state that the time period used in this study is exceptional compared to that of the earlier studies, however, any factors causing the underperformance were not identified.

Machine Learning and Clinical Text. Supporting Health Information Flow

Fluent health information flow is critical for clinical decision-making. However, a considerable part of this information is free-form text and inabilities to utilize it create risks to patient safety and cost-­effective hospital administration. Methods for automated processing of clinical text are emerging. The aim in this doctoral dissertation is to study machine learning and clinical text in order to support health information flow.First, by analyzing the content of authentic patient records, the aim is to specify clinical needs in order to guide the development of machine learning applications.The contributions are a model of the ideal information flow,a model of the problems and challenges in reality, and a road map for the technology development. Second, by developing applications for practical cases,the aim is to concretize ways to support health information flow. Altogether five machine learning applications for three practical cases are described: The first two applications are binary classification and regression related to the practical case of topic labeling and relevance ranking.The third and fourth application are supervised and unsupervised multi-class classification for the practical case of topic segmentation and labeling.These four applications are tested with Finnish intensive care patient records.The fifth application is multi-label classification for the practical task of diagnosis coding. It is tested with English radiology reports.The performance of all these applications is promising. Third, the aim is to study how the quality of machine learning applications can be reliably evaluated.The associations between performance evaluation measures and methods are addressed,and a new hold-out method is introduced.This method contributes not only to processing time but also to the evaluation diversity and quality. The main conclusion is that developing machine learning applications for text requires interdisciplinary, international collaboration. Practical cases are very different, and hence the development must begin from genuine user needs and domain expertise. The technological expertise must cover linguistics,machine learning, and information systems. Finally, the methods must be evaluated both statistically and through authentic user-feedback.

Conventional and novel cardiovascular risk factors in young Finns and their associations with structural and functional vascular changes of subclinical atherosclerosis. The Cardiovascular Risk in Young Finns Study

Background: Atherosclerosis begins in early life progressing from asymptomatic to symptomatic as we age. Although substantial progress has been made in identifying the determinants of atherosclerosis in middle to older age adults at increased cardiovascular risk, there is lack of data examining determinants and prediction of atherosclerosis in young adults. Aims: The current study was designed to investigate levels of cardiovascular risk factors in young adults, subclinical measures of atherosclerosis, and prediction of subclinical arterial changes with conventional risk factor measures and novel metabolic profiling of serum samples. Subjects and Methods: This thesis utilised data from the follow-ups performed in 2001 and 2007 in the Cardiovascular Risk in Young Finns study, a Finnish population-based prospective cohort study that examined 2,204 subjects who were aged 30-45 years in 2007. Subclinical atherosclerosis was studied using noninvasive ultrasound measurements of carotid intima-media thickness (IMT), carotid arterial distensibility (CDist) and brachial flow-mediated dilation (FMD). Measurements included conventional risk factors and metabolic profiling using highthroughput nuclear magnetic resonance (NMR) methods that provided data on 42 lipid markers and 16 circulating metabolites. Results: Trends in lipids were favourable between 2001 and 2007, whereas waist circumference, fasting glucose, and blood pressure levels increased. To study the stability of noninvasive ultrasound markers, 6-year tracking (the likelihood to maintain the original fractile over time) in 6 years was examined. IMT tracked more strongly than CDist and FMD. Cardiovascular risk scores (Framingham, SCORE, Finrisk, Reynolds and PROCAM) predicted subclinical atherosclerosis equally. Lipoprotein subclass testing did not improve the prediction of subclinical atherosclerosis over and above conventional risk factors. However, circulating metabolites improved risk stratification. Tyrosine and docosahexaenoic acid were found to be novel biomarkers of high IMT. Conclusions: Prediction of cardiovascular risk in young Finnish adults can be performed with any of the existing risk scores. The addition of metabonomics to risk stratification improves prediction of subclinical changes and enables more accurate targeting of prevention at an early stage.

Identification of research trends in the field of separation processes. Application of epidemiological model, citation analysis, text mining, and technical analysis of the financial markets

Choice of industrial development options and the relevant allocation of the research funds become more and more difficult because of the increasing R&D costs and pressure for shorter development period. Forecast of the research progress is based on the analysis of the publications activity in the field of interest as well as on the dynamics of its change. Moreover, allocation of funds is hindered by exponential growth in the number of publications and patents. Thematic clusters become more and more difficult to identify, and their evolution hard to follow. The existing approaches of research field structuring and identification of its development are very limited. They do not identify the thematic clusters with adequate precision while the identified trends are often ambiguous. Therefore, there is a clear need to develop methods and tools, which are able to identify developing fields of research. The main objective of this Thesis is to develop tools and methods helping in the identification of the promising research topics in the field of separation processes. Two structuring methods as well as three approaches for identification of the development trends have been proposed. The proposed methods have been applied to the analysis of the research on distillation and filtration. The results show that the developed methods are universal and could be used to study of the various fields of research. The identified thematic clusters and the forecasted trends of their development have been confirmed in almost all tested cases. It proves the universality of the proposed methods. The results allow for identification of the fast-growing scientific fields as well as the topics characterized by stagnant or diminishing research activity.

Syvää vai pelkästään tiheää : neuvostoliittolaisen ja venäläisen sotataidollisen ajattelun lähtökohdat, kehittyminen, soveltaminen käytäntöön ja nykytilanne. Näkökulmana 1920- ja 1930-luvun syvän taistelun ja operaation opit

Sosialistisen vallankumouksen jälkeen Neuvosto-Venäjän oli monien muiden kysymysten ohella ratkaistava sosialismin saavutusten puolustaminen. Aluksi ratkaisuksi suunniteltiin vapaaehtoisuuteen perustuvaa punakaartia, mutta riittävän miesvahvuuden turvaamiseksi päädyttiin yleiseen asevelvollisuuteen. Pian Venäjän sisällissodan jälkeen sotataidon suunta painottui enemmän vanhan armeijan asiantuntijoiden näkemysten kuin vallankumoussankarien kokemusten mukaiseksi, vaikka Frunzen puna-armeijalle kirjoittama doktriini perustui luokkataisteluun ja korosti sisällissodassa hyväksi koettua operatiivista liikkuvuutta. Neuvostoliiton ja Venäjän sotataidon perustana on Pietari I:n aloittama länsimainen suuntaus, jota kuitenkin täydentävät vahvat kansalliset piirteet. Venäläisen sotataidon henkisenä isänä voidaan hyvällä syyllä pitää Aleksandr Suvorovia, jonka opetukset näkyvät tekstilainausten lisäksi myös periaatteissa ja sotilaskasvatuksessa. Napoleonin sotien jälkeen perustettu Keisarillinen yleisesikunta-akatemia loi Venäjälle sotatieteellisen tutkimuksen ja opetuksen. Sotatieteen mahdollisuuksia ei 1800-luvun Venäjällä osattu täysin hyödyntää. Aseistuksen kasvavan tehon merkitystä vähättelevä asenne johti sotataidon taantumisen ja katastrofiin Venäjän–Japanin sodassa. Sen kokemuksia analysoidessaan Aleksandr Neznamov kehitti edelleen saksalaista operaation käsitettä ja loi perustan Neuvostoliitossa 1920-luvulla kehitetylle operaatiotaidolle. Neuvostoliittolaisen sotataidon päämääränä oli kehittää taktinen ja operatiivinen ratkaisu aseistuksen tehon kasvun aikaansaamaan puolustuksen ylivoimaisuuteen. Ratkaisussa hyödynnettiin brittien kokemuksia ja tutkimusta. Neuvostoliittolainen taktiikka ja operaatiotaito eivät kuitenkaan olleet brittiläisen mekanisoidun sodankäynnin tai saksalaisen salamasodan itäinen kopioita vaan itsenäisiin ratkaisuihin pohjautuvia. Syvän taistelun ja operaation teoriaa kokeiltiin harjoituksissa, ja sitä kehitettiin Stalinin vuoden 1937 puhdistuksiin saakka. Toisen maailmansodan taisteluissa puna-armeija sovelsi alkuvaiheen katastrofin jälkeen syvän taistelun ja syvän operaation oppeja. Komentajien ja joukkojen taito ei riittänyt teorian vaatimusten mukaiseen toimintaan, siksi syväksi aiotusta taistelusta tuli ajoittain ainoastaan tiheää. Suuren isänmaallisen sodan kokemusten perusteella neuvostoliittolainen sotatiede kehitti yleisjoukkojen taistelun periaatteet, jotka ovat säilyneet muuttumattomina nykypäivään saakka. Kylmän sodan aikakaudella ydin- ja tavanomaisen aseistuksen merkitys sodan ja taistelun kuvassa vaihteli. Lännen sotataidon ja aseteknologian kehitys pakotti Neuvostoliiton siirtymään 1980-luvulla sotilaallisessa ajattelussaan hyökkäyksestä puolustukseen. Neuvostoliiton hajoamisen jälkeen Venäjän sotilaallisen turvallisuuden takaajana on ydinaseistus. Yhdysvaltain tavanomainen ilma-avaruushyökkäyskyky vaatii Venäjää kehittämään torjuntajärjestelmiä. Tavanomaisten joukkojen rakentamisessa Venäjä seuraa tarkasti läntisen sotataidon kehittymistä, mutta pitäytyy omaperäisiin ratkaisuihin, joiden kehittämisessä sen vahvalla sotatieteellisellä järjestelmällä ja dialektisen materialismin metodilla on edelleen olennaisen tärkeä merkitys.

An Alternative American Approach to Repositories

Presentation at Open Repositories 2014, Helsinki, Finland, June 9-13, 2014

Fluvio-morphological processes of meander bends - Combining conventional field measurements, close-range remote sensing and computational modelling

Meandering rivers have been perceived to evolve rather similarly around the world independently of the location or size of the river. Despite the many consistent processes and characteristics they have also been noted to show complex and unique sets of fluviomorphological processes in which local factors play important role. These complex interactions of flow and morphology affect notably the development of the river. Comprehensive and fundamental field, flume and theoretically based studies of fluviomorphological processes in meandering rivers have been carried out especially during the latter part of the 20th century. However, as these studies have been carried out with traditional field measurements techniques their spatial and temporal resolution is not competitive to the level achievable today. The hypothesis of this study is that, by exploiting e increased spatial and temporal resolution of the data, achieved by combining conventional field measurements with a range of modern technologies, will provide new insights to the spatial patterns of the flow-sediment interaction in meandering streams, which have perceived to show notable variation in space and time. This thesis shows how the modern technologies can be combined to derive very high spatial and temporal resolution data on fluvio-morphological processes over meander bends. The flow structure over the bends is recorded in situ using acoustic Doppler current profiler (ADCP) and the spatial and temporal resolution of the flow data is enhanced using 2D and 3D CFD over various meander bends. The CFD are also exploited to simulate sediment transport. Multi-temporal terrestrial laser scanning (TLS), mobile laser scanning (MLS) and echo sounding data are used to measure the flow-based changes and formations over meander bends and to build the computational models. The spatial patterns of erosion and deposition over meander bends are analysed relative to the measured and modelled flow field and sediment transport. The results are compared with the classic theories of the processes in meander bends. Mainly, the results of this study follow well the existing theories and results of previous studies. However, some new insights regarding to the spatial and temporal patterns of the flow-sediment interaction in a natural sand-bed meander bend are provided. The results of this study show the advantages of the rapid and detailed measurements techniques and the achieved spatial and temporal resolution provided by CFD, unachievable with field measurements. The thesis also discusses the limitations which remain in the measurement and modelling methods and in understanding of fluvial geomorphology of meander bends. Further, the hydro- and morphodynamic models’ sensitivity to user-defined parameters is tested, and the modelling results are assessed against detailed field measurement. The study is implemented in the meandering sub-Arctic Pulmanki River in Finland. The river is unregulated and sand-bed and major morphological changes occur annually on the meander point bars, which are inundated only during the snow-melt-induced spring floods. The outcome of this study applies to sandbed meandering rivers in regions where normally one significant flood event occurs annually, such as Arctic areas with snow-melt induced spring floods, and where the point bars of the meander bends are inundated only during the flood events.

A performance analysis of conventional and fundamental exchange traded funds: ETFs and their risk-return characteristics in relation to building institutional investor’s passive portfolio

An exchange traded fund (ETF) is a financial instrument that tracks some predetermined index. Since their initial establishment in 1993, ETFs have grown in importance in the field of passive investing. The main reason for the growth of the ETF industry is that ETFs combine benefits of stock investing and mutual fund investing. Although ETFs resemble mutual funds in many ways, also many differences occur. In addition, ETFs not only differ from mutual funds but also differ among each other. ETFs can be divided into two categories, i.e. market capitalisation ETFs and fundamental (or strategic) ETFs, and further into subcategories depending on their fundament basis. ETFs are a useful tool for diversification especially for a long-term investor. Although the economic importance of ETFs has risen drastically during the past 25 years, the differences and risk-return characteristics of fundamental ETFs have yet been rather unstudied area. In effect, no previous research on market capitalisation and fundamental ETFs was found during the research process. For its part, this thesis seeks to fill this research gap. The studied data consist of 50 market capitalisation ETFs and 50 fundamental ETFs. The fundaments, on which the indices that the fundamental ETFs track, were not limited nor segregated into subsections. The two types of ETFs were studied at an aggregate level as two different research groups. The dataset ranges from June 2006 to December 2014 with 103 monthly observations. The data was gathered using Bloomberg Terminal. The analysis was conducted as an econometric performance analysis. In addition to other econometric measures, the methods that were used in the performance analysis included modified Value-at-Risk, modified Sharpe ratio and Treynor ratio. The results supported the hypothesis that passive market capitalisation ETFs outperform active fundamental ETFs in terms of risk-adjusted returns, though the difference is rather small. Nevertheless, when taking into account the higher overall trading costs of the fundamental ETFs, the underperformance gap widens. According to the research results, market capitalisation ETFs are a recommendable diversification instrument for a long-term investor. In addition to better risk-adjusted returns, passive ETFs are more transparent and the bases of their underlying indices are simpler than those of fundamental ETFs. ETFs are still a young financial innovation and hence data is scarcely available. On future research, it would be valuable to research the differences in risk-adjusted returns also between the subsections of fundamental ETFs.

University students’ regulation of learning and text processing – examples from medical and teacher education

The general aim of the thesis was to study university students’ learning from the perspective of regulation of learning and text processing. The data were collected from the two academic disciplines of medical and teacher education, which share the features of highly scheduled study, a multidisciplinary character, a complex relationship between theory and practice and a professional nature. Contemporary information society poses new challenges for learning, as it is not possible to learn all the information needed in a profession during a study programme. Therefore, it is increasingly important to learn how to think and learn independently, how to recognise gaps in and update one’s knowledge and how to deal with the huge amount of constantly changing information. In other words, it is critical to regulate one’s learning and to process text effectively. The thesis comprises five sub-studies that employed cross-sectional, longitudinal and experimental designs and multiple methods, from surveys to eye tracking. Study I examined the connections between students’ study orientations and the ways they regulate their learning. In total, 410 second-, fourth- and sixth-year medical students from two Finnish medical schools participated in the study by completing a questionnaire measuring both general study orientations and regulation strategies. The students were generally deeply oriented towards their studies. However, they regulated their studying externally. Several interesting and theoretically reasonable connections between the variables were found. For instance, self-regulation was positively correlated with deep orientation and achievement orientation and was negatively correlated with non-commitment. However, external regulation was likewise positively correlated with deep orientation and achievement orientation but also with surface orientation and systematic orientation. It is argued that external regulation might function as an effective coping strategy in the cognitively loaded medical curriculum. Study II focused on medical students’ regulation of learning and their conceptions of the learning environment in an innovative medical course where traditional lectures were combined wth problem-based learning (PBL) group work. First-year medical and dental students (N = 153) completed a questionnaire assessing their regulation strategies of learning and views about the PBL group work. The results indicated that external regulation and self-regulation of the learning content were the most typical regulation strategies among the participants. In line with previous studies, self-regulation wasconnected with study success. Strictly organised PBL sessions were not considered as useful as lectures, although the students’ views of the teacher/tutor and the group were mainly positive. Therefore, developers of teaching methods are challenged to think of new solutions that facilitate reflection of one’s learning and that improve the development of self-regulation. In Study III, a person-centred approach to studying regulation strategies was employed, in contrast to the traditional variable-centred approach used in Study I and Study II. The aim of Study III was to identify different regulation strategy profiles among medical students (N = 162) across time and to examine to what extent these profiles predict study success in preclinical studies. Four regulation strategy profiles were identified, and connections with study success were found. Students with the lowest self-regulation and with an increasing lack of regulation performed worse than the other groups. As the person-centred approach enables us to individualise students with diverse regulation patterns, it could be used in supporting student learning and in facilitating the early diagnosis of learning difficulties. In Study IV, 91 student teachers participated in a pre-test/post-test design where they answered open-ended questions about a complex science concept both before and after reading either a traditional, expository science text or a refutational text that prompted the reader to change his/her beliefs according to scientific beliefs about the phenomenon. The student teachers completed a questionnaire concerning their regulation and processing strategies. The results showed that the students’ understanding improved after text reading intervention and that refutational text promoted understanding better than the traditional text. Additionally, regulation and processing strategies were found to be connected with understanding the science phenomenon. A weak trend showed that weaker learners would benefit more from the refutational text. It seems that learners with effective learning strategies are able to pick out the relevant content regardless of the text type, whereas weaker learners might benefit from refutational parts that contrast the most typical misconceptions with scientific views. The purpose of Study V was to use eye tracking to determine how third-year medical studets (n = 39) and internal medicine residents (n = 13) read and solve patient case texts. The results revealed differences between medical students and residents in processing patient case texts; compared to the students, the residents were more accurate in their diagnoses and processed the texts significantly faster and with a lower number of fixations. Different reading patterns were also found. The observed differences between medical students and residents in processing patient case texts could be used in medical education to model expert reasoning and to teach how a good medical text should be constructed. The main findings of the thesis indicate that even among very selected student populations, such as high-achieving medical students or student teachers, there seems to be a lot of variation in regulation strategies of learning and text processing. As these learning strategies are related to successful studying, students enter educational programmes with rather different chances of managing and achieving success. Further, the ways of engaging in learning seldom centre on a single strategy or approach; rather, students seem to combine several strategies to a certain degree. Sometimes, it can be a matter of perspective of which way of learning can be considered best; therefore, the reality of studying in higher education is often more complicated than the simplistic view of self-regulation as a good quality and external regulation as a harmful quality. The beginning of university studies may be stressful for many, as the gap between high school and university studies is huge and those strategies that were adequate during high school might not work as well in higher education. Therefore, it is important to map students’ learning strategies and to encourage them to engage in using high-quality learning strategies from the beginning. Instead of separate courses on learning skills, the integration of these skills into course contents should be considered. Furthermore, learning complex scientific phenomena could be facilitated by paying attention to high-quality learning materials and texts and other support from the learning environment also in the university. Eye tracking seems to have great potential in evaluating performance and growing diagnostic expertise in text processing, although more research using texts as stimulus is needed. Both medical and teacher education programmes and the professions themselves are challenging in terms of their multidisciplinary nature and increasing amounts of information and therefore require good lifelong learning skills during the study period and later in work life.