Kernel-Based Ranking. Methods for Learning and Performance Estimation

Machine learning provides tools for automated construction of predictive models in data intensive areas of engineering and science. The family of regularized kernel methods have in the recent years become one of the mainstream approaches to machine learning, due to a number of advantages the methods share. The approach provides theoretically well-founded solutions to the problems of under- and overfitting, allows learning from structured data, and has been empirically demonstrated to yield high predictive performance on a wide range of application domains. Historically, the problems of classification and regression have gained the majority of attention in the field. In this thesis we focus on another type of learning problem, that of learning to rank. In learning to rank, the aim is from a set of past observations to learn a ranking function that can order new objects according to how well they match some underlying criterion of goodness. As an important special case of the setting, we can recover the bipartite ranking problem, corresponding to maximizing the area under the ROC curve (AUC) in binary classification. Ranking applications appear in a large variety of settings, examples encountered in this thesis include document retrieval in web search, recommender systems, information extraction and automated parsing of natural language. We consider the pairwise approach to learning to rank, where ranking models are learned by minimizing the expected probability of ranking any two randomly drawn test examples incorrectly. The development of computationally efficient kernel methods, based on this approach, has in the past proven to be challenging. Moreover, it is not clear what techniques for estimating the predictive performance of learned models are the most reliable in the ranking setting, and how the techniques can be implemented efficiently. The contributions of this thesis are as follows. First, we develop RankRLS, a computationally efficient kernel method for learning to rank, that is based on minimizing a regularized pairwise least-squares loss. In addition to training methods, we introduce a variety of algorithms for tasks such as model selection, multi-output learning, and cross-validation, based on computational shortcuts from matrix algebra. Second, we improve the fastest known training method for the linear version of the RankSVM algorithm, which is one of the most well established methods for learning to rank. Third, we study the combination of the empirical kernel map and reduced set approximation, which allows the large-scale training of kernel machines using linear solvers, and propose computationally efficient solutions to cross-validation when using the approach. Next, we explore the problem of reliable cross-validation when using AUC as a performance criterion, through an extensive simulation study. We demonstrate that the proposed leave-pair-out cross-validation approach leads to more reliable performance estimation than commonly used alternative approaches. Finally, we present a case study on applying machine learning to information extraction from biomedical literature, which combines several of the approaches considered in the thesis. The thesis is divided into two parts. Part I provides the background for the research work and summarizes the most central results, Part II consists of the five original research articles that are the main contribution of this thesis.

Open science, citizen science, crowd science – promises and challenges

Presentation at the Nordic Perspectives on Open Access and Open Science seminar, Helsinki, October 15, 2013

Open knowledge in science and elsewhere

Presentation at the Nordic Perspectives on Open Access and Open Science seminar, Helsinki, October 15, 2013

Research Data Management in the Cloud

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

Design Space Exploration for MPSoC Architectures

Multiprocessor system-on-chip (MPSoC) designs utilize the available technology and communication architectures to meet the requirements of the upcoming applications. In MPSoC, the communication platform is both the key enabler, as well as the key differentiator for realizing efficient MPSoCs. It provides product differentiation to meet a diverse, multi-dimensional set of design constraints, including performance, power, energy, reconfigurability, scalability, cost, reliability and time-to-market. The communication resources of a single interconnection platform cannot be fully utilized by all kind of applications, such as the availability of higher communication bandwidth for computation but not data intensive applications is often unfeasible in the practical implementation. This thesis aims to perform the architecture-level design space exploration towards efficient and scalable resource utilization for MPSoC communication architecture. In order to meet the performance requirements within the design constraints, careful selection of MPSoC communication platform, resource aware partitioning and mapping of the application play important role. To enhance the utilization of communication resources, variety of techniques such as resource sharing, multicast to avoid re-transmission of identical data, and adaptive routing can be used. For implementation, these techniques should be customized according to the platform architecture. To address the resource utilization of MPSoC communication platforms, variety of architectures with different design parameters and performance levels, namely Segmented bus (SegBus), Network-on-Chip (NoC) and Three-Dimensional NoC (3D-NoC), are selected. Average packet latency and power consumption are the evaluation parameters for the proposed techniques. In conventional computing architectures, fault on a component makes the connected fault-free components inoperative. Resource sharing approach can utilize the fault-free components to retain the system performance by reducing the impact of faults. Design space exploration also guides to narrow down the selection of MPSoC architecture, which can meet the performance requirements with design constraints.

Kallet til livets embete : mødre i helse og lidelse

Mothers represent the natural caring. Natural caring is the object of caring science and of research interest because it establishes the central core of professional caring. In this study, we encounter patients who are mothers in need of care in a psychiatric context. Motherhood involves taking responsibility that extends beyond one's own life, because the child represents possibilities in a yet unknown future. Understanding and knowledge about the mothers' struggle in health and suffering are of crucial importance to enable clinical practice to make provisions for and adapt to the individual patient. The overall purpose of this dissertation is to illuminate how the innermost essence of caring emerges in health and suffering in patients who are mothers in psychiatric care. The purpose of the study in a clinical sense is to seek to understand and illuminate the patient's inner world in health and suffering in terms of contextual, existential, ontological and ethical dimensions. The dissertation is exploratory and descriptive in nature and encompasses induction, deduction and abduction as logics tools of reasoning. A theoretical model of natural caring and a universal theoretical model of the innermost essence of caring is developed as seen from the patient's world in a psychiatric context. The dissertation is anchored in human science's view of the human being and the world and in caring science's perspective. Caring science's view of the human being as a unity comprising body, soul and spirit is central in the study's concept of the patient. This multi-dimensional conception of the human being encompasses the dissertation's basic values and is decisive for choice of methodology. Hermeneutic epistemology guided the interpretation of the empirical data, the paradigmatic theses and assumptions. The dialectical movement in interpretation moves back and forth between empirical data, caring science theory and philosophical theory and reveals deeper insight into meaningful content in the clinical context. The interpretation process comprises four levels of abstraction: rational, contextual, existential and ontological. Hermeneutic philosophy guides the inductive and deductive approach to interpretation, as well as the movement between the clinical context and the caring science paradigm. In this encounter between the visible and invisible reality, the image of natural caring – motherliness emerged. The dissertation consists of four studies. The first study is a systematic review of nineteen research articles. The three other studies are hermeneutical interpretations based on text materials from open interviews. Fifteen participants were interviewed, all of whom are mothers of children between 0 and 18 years of age. All were outpatients in the psychiatric specialist health service. In the interpretation process, the mothers' struggle in health and suffering emerges as a struggle between the inner and outer world. Being a mother and patient in health and suffering in a psychiatric context means to struggle to be oneself, to create oneself, to live and realize one's good deeds as a mother and human being. To be oneself, to possess oneself as a mother is not only a question of tending, playing and learning in order to master a practical situation or to survive. It involves constituting a deep, inner desire to courageously create oneself so that the child is able to realize his or her potential in health and suffering. Motherliness manifests itself in caring as a call to ministering humanity and life. The voice of motherliness is understood as the voice of life—the eternal, inner call of love and freedom. The inner call craves fulfilment. Motherliness in natural caring does not retreat. Motherliness defines the Other as freedom and proceeds without regard for all other exterior requirements to realizing wellbeing. The inner essence of caring is attentive, aware and heeds the call of the heart. The innermost essence of caring is to be and to make oneself responsible for the Other. Responsibility cannot be relinquished; free choice consists in whether or not to follow the call. To renounce the inner call to responsibility is to deny oneself and one's dignity as a human being. The theoretical models provide clinical and systematic caring science with knowledge and understanding based on the natural caring spirit inherent in the human being. The study elucidates and strengthens the ontological basic assumptions about the human being as a unity of body, soul and spirit, the sanctity of the human being and the core of caring, ethos. The results of the dissertation will provide clinical practice with knowledge about the inner movements of the mothers' souls in relation to their responsibility as mothers and human beings. Being able to understand the basic conditions for responsibility is crucial for developing care that encompasses mother and child and the mutual relationship between them. This is basic knowledge for developing attitudes and actions that meet and provide for the needs of the patient as mother and as a whole, suffering human being.

An Open Source, DDI-based Curation System for Social Science Data

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

Supporting the creation, management, and long-term preservation of social science research data

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

A rose is a rose is a rose? Defining significant properties of social science research data

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

Concentrate feeding and milk yield based on field data of milk recorded herds

Selostus: Väkirehuruokinnan vaikutus maidontuotantoon karjantarkkailutiloilta kerätyssä kenttäaineistossa

Geostatistical prediction of clay percentage based on soil survey data

Selostus: Viljelymaiden savespitoisuuden alueellistaminen geostatistiikan ja pistemäisen tiedon avulla

On the innovation capacity of technologyrelated knowledge-intensive business services. A case study of the technology and engineering consulting (TEC) sector in Singapore

Even though the research on innovation in services has expanded remarkably especially during the past two decades, there is still a need to increase understanding on the special characteristics of service innovation. In addition to studying innovation in service companies and industries, research has also recently focused more on services in innovation, as especially the significance of so-called knowledge intensive business services (KIBS) for the competitive edge of their clients, othercompanies, regions and even nations has been proved in several previous studies. This study focuses on studying technology-based KIBS firms, and technology andengineering consulting (TEC) sector in particular. These firms have multiple roles in innovation systems, and thus, there is also a need for in-depth studies that increase knowledge about the types and dimensions of service innovations as well as underlying mechanisms and procedures which make the innovations successful. The main aim of this study is to generate new knowledge in the fragmented research field of service innovation management by recognizing the different typesof innovations in TEC services and some of the enablers of and barriers to innovation capacity in the field, especially from the knowledge management perspective. The study also aims to shed light on some of the existing routines and new constructions needed for enhancing service innovation and knowledge processing activities in KIBS companies of the TEC sector. The main samples of data in this research include literature reviews and public data sources, and a qualitative research approach with exploratory case studies conducted with the help of the interviews at technology consulting companies in Singapore in 2006. These complement the qualitative interview data gathered previously in Finland during a larger research project in the years 2004-2005. The data is also supplemented by a survey conducted in Singapore. The respondents for the survey by Tan (2007) were technology consulting companies who operate in the Singapore region. The purpose ofthe quantitative part of the study was to validate and further examine specificaspects such as the influence of knowledge management activities on innovativeness and different types of service innovations, in which the technology consultancies are involved. Singapore is known as a South-east Asian knowledge hub and is thus a significant research area where several multinational knowledge-intensive service firms operate. Typically, the service innovations identified in the studied TEC firms were formed by several dimensions of innovations. In addition to technological aspects, innovations were, for instance, related to new client interfaces and service delivery processes. The main enablers of and barriers to innovation seem to be partly similar in Singaporean firms as compared to the earlier study of Finnish TEC firms. Empirical studies also brought forth the significance of various sources of knowledge and knowledge processing activities as themain driving forces of service innovation in technology-related KIBS firms. A framework was also developed to study the effect of knowledge processing capabilities as well as some moderators on the innovativeness of TEC firms. Especially efficient knowledge acquisition and environmental dynamism seem to influence the innovativeness of TEC firms positively. The results of the study also contributeto the present service innovation literature by focusing more on 'innovation within KIBs' rather than 'innovation through KIBS', which has been the typical viewpoint stressed in the previous literature. Additionally, the study provides several possibilities for further research.

Success of service-intensive manufacturing firms - resource-based view

The main objective of this study is to examine the relationships between resources, competitive advantage and firm success. The study focuses, on one hand, on the financial performance of service-intensive manufac-turing firms against competitors with a lower service intensity and, on the other hand, on the resources as drivers for competitive advantage and success. The purpose of the theoretical part is to link the study in the field of the strategy research. The empirical part of the study is based on the quantitative analyses of the survey data collected from 50 major suppliers of industrial machinery and transportation equipment in Europe and North America. Results indicate that service-intensive manufacturing firms have performed better and their performance has been more stable vis-à-vis their peers. The main resources that differentiate service-intensive manufacturing firms from their non-service intensive competitors are service strategy and service-oriented top management. The analyses on the VRIO resources produced only a limited amount of information and solely service-centred culture appeared to be a rent generating resource.

Competence in intensive and critical care nursing - development of a basic assessment scale for graduating nursing students

Intensive and critical care nursing is a speciality in its own right and with its own nature within the nursing profession. This speciality poses its own demands for nursing competencies. Intensive and critical care nursing is focused on severely ill patients and their significant others. The patients are comprehensively cared for, constantly monitored and their vital functions are sustained artificially. The main goal is to win time to cure the cause of the patient’s situation or illness. The purpose of this empirical study was i) to describe and define competence and competence requirements in intensive and critical care nursing, ii) to develop a basic measurement scale for competence assessment in intensive and critical care nursing for graduating nursing students, and iii) to describe and evaluate graduating nursing students’ basic competence in intensive and critical care nursing by seeking the reference basis of self-evaluated basic competence in intensive and critical care nursing from ICU nurses. However, the main focus of this study was on the outcomes of nursing education in this nursing speciality. The study was carried out in different phases: basic exploration of competence (phase 1 and 2), instrumentation of competence (phase 3) and evaluation of competence (phase 4). Phase 1 (n=130) evaluated graduating nursing students’ basic biological and physiological knowledge and skills for working in intensive and critical care with Basic Knowledge Assessment Tool version 5 (BKAT-5, Toth 2012). Phase 2 focused on defining competence in intensive and critical care nursing with the help of literature review (n=45 empirical studies) as well as competence requirements in intensive and critical care nursing with the help of experts (n=45 experts) in a Delphi study. In phase 3 the scale Intensive and Critical Care Nursing Competence Scale (ICCN-CS) was developed and tested twice (pilot test 1: n=18 students and n=12 nurses; pilot test 2: n=56 students and n=54 nurses). Finally, in phase 4, graduating nursing students’ competence was evaluated with ICCN-CS and BKAT version 7 (Toth 2012). In order to develop a valid assessment scale of competence for graduating nursing students and to evaluate and establish the competence of graduating nursing students, empirical data were retrieved at the same time from both graduating nursing students (n=139) and ICU nurses (n=431). Competence can be divided into clinical and general professional competence. It can be defined as a specific knowledge base, skill base, attitude and value base and experience base of nursing and the personal base of an intensive and critical care nurse. Personal base was excluded in this self-evaluation based scale. The ICCN-CS-1 consists of 144 items (6 sum variables). Finally, it became evident that the experience base of competence is not a suitable sum variable in holistic intensive and critical care competence scale for graduating nursing students because of their minor experience in this special nursing area. ICCN-CS-1 is a reliable and tolerably valid scale for use among graduating nursing students and ICU nurses Among students, basic competence of intensive and critical care nursing was self-rated as good by 69%, as excellent by 25% and as moderate by 6%. However, graduating nursing students’ basic biological and physiological knowledge and skills for working in intensive and critical care were poor. The students rated their clinical and professional competence as good, and their knowledge base and skill base as moderate. They gave slightly higher ratings for their knowledge base than skill base. Differences in basic competence emerged between graduating nursing students and ICU nurses. The students’ self-ratings of both their basic competence and clinical and professional competence were significantly lower than the nurses’ ratings. The students’ self-ratings of their knowledge and skill base were also statistically significantly lower than nurses’ ratings. However, both groups reported the same attitude and value base, which was excellent. The strongest factor explaining students’ conception of their competence was their experience of autonomy in nursing. Conclusions: Competence in intensive and critical care nursing is a multidimensional concept. Basic competence in intensive and critical care nursing can be measured with self-evaluation based scale but alongside should be used an objective evaluation method. Graduating nursing students’ basic competence in intensive and critical care nursing is good but their knowledge and skill base are moderate. Especially the biological and physiological knowledge base is poor. Therefore in future in intensive and critical care nursing education should be focused on both strengthening students’ biological and physiological knowledge base and on strengthening their overall skill base. Practical implications are presented for nursing education, practice and administration. In future, research should focus on education methods and contents, mentoring of clinical practice and orientation programmes as well as further development of the scale.

Thinking Outside the Box: Enhancing Science Teaching by Combining (Instead of Contrasting) Laboratory and Simulation Activities

The focus of the present work was on 10- to 12-year-old elementary school students’ conceptual learning outcomes in science in two specific inquiry-learning environments, laboratory and simulation. The main aim was to examine if it would be more beneficial to combine than contrast simulation and laboratory activities in science teaching. It was argued that the status quo where laboratories and simulations are seen as alternative or competing methods in science teaching is hardly an optimal solution to promote students’ learning and understanding in various science domains. It was hypothesized that it would make more sense and be more productive to combine laboratories and simulations. Several explanations and examples were provided to back up the hypothesis. In order to test whether learning with the combination of laboratory and simulation activities can result in better conceptual understanding in science than learning with laboratory or simulation activities alone, two experiments were conducted in the domain of electricity. In these experiments students constructed and studied electrical circuits in three different learning environments: laboratory (real circuits), simulation (virtual circuits), and simulation-laboratory combination (real and virtual circuits were used simultaneously). In order to measure and compare how these environments affected students’ conceptual understanding of circuits, a subject knowledge assessment questionnaire was administered before and after the experimentation. The results of the experiments were presented in four empirical studies. Three of the studies focused on learning outcomes between the conditions and one on learning processes. Study I analyzed learning outcomes from experiment I. The aim of the study was to investigate if it would be more beneficial to combine simulation and laboratory activities than to use them separately in teaching the concepts of simple electricity. Matched-trios were created based on the pre-test results of 66 elementary school students and divided randomly into a laboratory (real circuits), simulation (virtual circuits) and simulation-laboratory combination (real and virtual circuits simultaneously) conditions. In each condition students had 90 minutes to construct and study various circuits. The results showed that studying electrical circuits in the simulation–laboratory combination environment improved students’ conceptual understanding more than studying circuits in simulation and laboratory environments alone. Although there were no statistical differences between simulation and laboratory environments, the learning effect was more pronounced in the simulation condition where the students made clear progress during the intervention, whereas in the laboratory condition students’ conceptual understanding remained at an elementary level after the intervention. Study II analyzed learning outcomes from experiment II. The aim of the study was to investigate if and how learning outcomes in simulation and simulation-laboratory combination environments are mediated by implicit (only procedural guidance) and explicit (more structure and guidance for the discovery process) instruction in the context of simple DC circuits. Matched-quartets were created based on the pre-test results of 50 elementary school students and divided randomly into a simulation implicit (SI), simulation explicit (SE), combination implicit (CI) and combination explicit (CE) conditions. The results showed that when the students were working with the simulation alone, they were able to gain significantly greater amount of subject knowledge when they received metacognitive support (explicit instruction; SE) for the discovery process than when they received only procedural guidance (implicit instruction: SI). However, this additional scaffolding was not enough to reach the level of the students in the combination environment (CI and CE). A surprising finding in Study II was that instructional support had a different effect in the combination environment than in the simulation environment. In the combination environment explicit instruction (CE) did not seem to elicit much additional gain for students’ understanding of electric circuits compared to implicit instruction (CI). Instead, explicit instruction slowed down the inquiry process substantially in the combination environment. Study III analyzed from video data learning processes of those 50 students that participated in experiment II (cf. Study II above). The focus was on three specific learning processes: cognitive conflicts, self-explanations, and analogical encodings. The aim of the study was to find out possible explanations for the success of the combination condition in Experiments I and II. The video data provided clear evidence about the benefits of studying with the real and virtual circuits simultaneously (the combination conditions). Mostly the representations complemented each other, that is, one representation helped students to interpret and understand the outcomes they received from the other representation. However, there were also instances in which analogical encoding took place, that is, situations in which the slightly discrepant results between the representations ‘forced’ students to focus on those features that could be generalised across the two representations. No statistical differences were found in the amount of experienced cognitive conflicts and self-explanations between simulation and combination conditions, though in self-explanations there was a nascent trend in favour of the combination. There was also a clear tendency suggesting that explicit guidance increased the amount of self-explanations. Overall, the amount of cognitive conflicts and self-explanations was very low. The aim of the Study IV was twofold: the main aim was to provide an aggregated overview of the learning outcomes of experiments I and II; the secondary aim was to explore the relationship between the learning environments and students’ prior domain knowledge (low and high) in the experiments. Aggregated results of experiments I & II showed that on average, 91% of the students in the combination environment scored above the average of the laboratory environment, and 76% of them scored also above the average of the simulation environment. Seventy percent of the students in the simulation environment scored above the average of the laboratory environment. The results further showed that overall students seemed to benefit from combining simulations and laboratories regardless of their level of prior knowledge, that is, students with either low or high prior knowledge who studied circuits in the combination environment outperformed their counterparts who studied in the laboratory or simulation environment alone. The effect seemed to be slightly bigger among the students with low prior knowledge. However, more detailed inspection of the results showed that there were considerable differences between the experiments regarding how students with low and high prior knowledge benefitted from the combination: in Experiment I, especially students with low prior knowledge benefitted from the combination as compared to those students that used only the simulation, whereas in Experiment II, only students with high prior knowledge seemed to benefit from the combination relative to the simulation group. Regarding the differences between simulation and laboratory groups, the benefits of using a simulation seemed to be slightly higher among students with high prior knowledge. The results of the four empirical studies support the hypothesis concerning the benefits of using simulation along with laboratory activities to promote students’ conceptual understanding of electricity. It can be concluded that when teaching students about electricity, the students can gain better understanding when they have an opportunity to use the simulation and the real circuits in parallel than if they have only the real circuits or only a computer simulation available, even when the use of the simulation is supported with the explicit instruction. The outcomes of the empirical studies can be considered as the first unambiguous evidence on the (additional) benefits of combining laboratory and simulation activities in science education as compared to learning with laboratories and simulations alone.