Optimization and Applications of Large-Scale Biomedical Event Networks

The overwhelming amount and unprecedented speed of publication in the biomedical domain make it difficult for life science researchers to acquire and maintain a broad view of the field and gather all information that would be relevant for their research. As a response to this problem, the BioNLP (Biomedical Natural Language Processing) community of researches has emerged and strives to assist life science researchers by developing modern natural language processing (NLP), information extraction (IE) and information retrieval (IR) methods that can be applied at large-scale, to scan the whole publicly available biomedical literature and extract and aggregate the information found within, while automatically normalizing the variability of natural language statements. Among different tasks, biomedical event extraction has received much attention within BioNLP community recently. Biomedical event extraction constitutes the identification of biological processes and interactions described in biomedical literature, and their representation as a set of recursive event structures. The 2009–2013 series of BioNLP Shared Tasks on Event Extraction have given raise to a number of event extraction systems, several of which have been applied at a large scale (the full set of PubMed abstracts and PubMed Central Open Access full text articles), leading to creation of massive biomedical event databases, each of which containing millions of events. Sinece top-ranking event extraction systems are based on machine-learning approach and are trained on the narrow-domain, carefully selected Shared Task training data, their performance drops when being faced with the topically highly varied PubMed and PubMed Central documents. Specifically, false-positive predictions by these systems lead to generation of incorrect biomolecular events which are spotted by the end-users. This thesis proposes a novel post-processing approach, utilizing a combination of supervised and unsupervised learning techniques, that can automatically identify and filter out a considerable proportion of incorrect events from large-scale event databases, thus increasing the general credibility of those databases. The second part of this thesis is dedicated to a system we developed for hypothesis generation from large-scale event databases, which is able to discover novel biomolecular interactions among genes/gene-products. We cast the hypothesis generation problem as a supervised network topology prediction, i.e predicting new edges in the network, as well as types and directions for these edges, utilizing a set of features that can be extracted from large biomedical event networks. Routine machine learning evaluation results, as well as manual evaluation results suggest that the problem is indeed learnable. This work won the Best Paper Award in The 5th International Symposium on Languages in Biology and Medicine (LBM 2013).

Investigation of business models of free zones and possible implications in South East Finland

Tutkielma tarkastelee vapaa alue konseptia osana yritysten kansainvälistä toimitusketjua. Tarkoituksena on löytää keinoja, millä tavoin vapaa alueen houkuttelevuutta voidaan lisätä yritysten näkökulmasta ja millaista liiketoimintaa yritysten on vapaa alueella mahdollista harjoittaa. Tutkielmassa etsitään tekijöitä, jotka vaikuttavat vapaa alueen menestykseen ja jotka voisivat olla sovellettavissa Kaakkois-Suomen ja Venäjän raja-alueelle ottaen huomioon vallitsevat olosuhteet ja lainsäädäntö rajoittavina tekijöinä. Menestystekijöitä ja liiketoimintamalleja haetaan tutkimalla ja analysoimalla lyhyesti muutamia olemassa olevia ja toimivia vapaa alueita. EU tullilain harmonisointi ja kansainvälisen kaupan vapautuminen vähentää vapaa alueen perinteistä merkitystä tullivapaana alueena. Sen sijaan vapaa alueet toimivat yhä enenevissä määrin logistisina keskuksina kansainvälisessä kaupassa ja tarjoavat palveluita, joiden avulla yritykset voivat parantaa logistista kilpailukykyään. Verkostoituminen, satelliitti-ratkaisut ja yhteistoiminta ovat keinoja, millä Kaakkois-Suomen alueen eri logistiikkapalvelujen tarjoajat voivat parantaa suorituskykyään ja joustavuutta kansainvälisessä toimitusketjussa.

Internationalization of IT company: Case study of a Finnish MOOC platform

The interest to small and media size enterprises’ (SMEs) internationalization process is increasing with a growth of SMEs’ contribution to GDP. Internet gives an opportunity to provide variety of services online and reach market niche worldwide. The overlapping of SMEs’ internationalization and online services is the main issue of the research. The most SMEs internationalize according to intuitive decisions of CEO of the company and lose limited resources to worthless attempts. The purpose of this research is to define effective approaches to online service internationalization and selection of the first international market. The research represents single holistic case study of local massive open online courses (MOOCs) platform going global. It considers internationalization costs and internationalization theories applicable to online services. The research includes preliminary screening of the markets and in-depth analysis based on macro parameters of the market and specific characteristics of the customers and expert evaluation of the results. The specific issues as GILT (Globalization, Internationalization, Localization and Translation) approach and Internet-enabled internationalization are considered. The research results include recommendations on international market selection methodology for online services and for effective internationalization strategy development.