Analysis, modelling and classification of geospatial data using machine learning

The research considers the problem of spatial data classification using machine learning algorithms: probabilistic neural networks (PNN) and support vector machines (SVM). As a benchmark model simple k-nearest neighbor algorithm is considered. PNN is a neural network reformulation of well known nonparametric principles of probability density modeling using kernel density estimator and Bayesian optimal or maximum a posteriori decision rules. PNN is well suited to problems where not only predictions but also quantification of accuracy and integration of prior information are necessary. An important property of PNN is that they can be easily used in decision support systems dealing with problems of automatic classification. Support vector machine is an implementation of the principles of statistical learning theory for the classification tasks. Recently they were successfully applied for different environmental topics: classification of soil types and hydro-geological units, optimization of monitoring networks, susceptibility mapping of natural hazards. In the present paper both simulated and real data case studies (low and high dimensional) are considered. The main attention is paid to the detection and learning of spatial patterns by the algorithms applied.

Low-cost microprocessed instrument for evaluating soil temperature profile

This paper describes a low-cost microprocessed instrument for in situ evaluating soil temperature profile ranging from -20.0°C to 99.9°C, and recording soil temperature data at eight depths from 2 to 128 cm. Of great importance in agriculture, soil temperature affects plant growth directly, and nutrient uptake as well as indirectly in soil water and gas flow, soil structure and nutrient availability. The developed instrument has potential applications in the soil science, when temperature monitoring is required. Results show that the instrument with its individual sensors guarantees ±0.25°C accuracy and 0.1°C resolution, making possible localized management changes within decision support systems. The instrument, based on complementary metal oxide semiconductor devices as well as thermocouples, operates in either automatic or non-automatic mode.

Data-driven topo-climatic mapping with machine learning methods

Automatic environmental monitoring networks enforced by wireless communication technologies provide large and ever increasing volumes of data nowadays. The use of this information in natural hazard research is an important issue. Particularly useful for risk assessment and decision making are the spatial maps of hazard-related parameters produced from point observations and available auxiliary information. The purpose of this article is to present and explore the appropriate tools to process large amounts of available data and produce predictions at fine spatial scales. These are the algorithms of machine learning, which are aimed at non-parametric robust modelling of non-linear dependencies from empirical data. The computational efficiency of the data-driven methods allows producing the prediction maps in real time which makes them superior to physical models for the operational use in risk assessment and mitigation. Particularly, this situation encounters in spatial prediction of climatic variables (topo-climatic mapping). In complex topographies of the mountainous regions, the meteorological processes are highly influenced by the relief. The article shows how these relations, possibly regionalized and non-linear, can be modelled from data using the information from digital elevation models. The particular illustration of the developed methodology concerns the mapping of temperatures (including the situations of Föhn and temperature inversion) given the measurements taken from the Swiss meteorological monitoring network. The range of the methods used in the study includes data-driven feature selection, support vector algorithms and artificial neural networks.

Randomized trial of a computerized coronary heart disease risk assessment tool in HIV-infected patients receiving combination antiretroviral therapy.

BACKGROUND: Exposure to combination antiretroviral therapy (cART) can lead to important metabolic changes and increased risk of coronary heart disease (CHD). Computerized clinical decision support systems have been advocated to improve the management of patients at risk for CHD but it is unclear whether such systems reduce patients' risk for CHD. METHODS: We conducted a cluster trial within the Swiss HIV Cohort Study (SHCS) of HIV-infected patients, aged 18 years or older, not pregnant and receiving cART for >3 months. We randomized 165 physicians to either guidelines for CHD risk factor management alone or guidelines plus CHD risk profiles. Risk profiles included the Framingham risk score, CHD drug prescriptions and CHD events based on biannual assessments, and were continuously updated by the SHCS data centre and integrated into patient charts by study nurses. Outcome measures were total cholesterol, systolic and diastolic blood pressure and Framingham risk score. RESULTS: A total of 3,266 patients (80% of those eligible) had a final assessment of the primary outcome at least 12 months after the start of the trial. Mean (95% confidence interval) patient differences where physicians received CHD risk profiles and guidelines, rather than guidelines alone, were total cholesterol -0.02 mmol/l (-0.09-0.06), systolic blood pressure -0.4 mmHg (-1.6-0.8), diastolic blood pressure -0.4 mmHg (-1.5-0.7) and Framingham 10-year risk score -0.2% (-0.5-0.1). CONCLUSIONS: Systemic computerized routine provision of CHD risk profiles in addition to guidelines does not significantly improve risk factors for CHD in patients on cART.

Strategisten investointienhallinta ryhmäpäätöksenteon tukisysteemien avulla

Tutkielman tavoitteena on kehittää prosessi yrityksen strategisten investointien hal-lintaan siten, että yrityksen strateginen arkkitehtuuri mukailee dynaamisten mark-kinoiden jatkuvasti muuttuvia kriittisiä menestystekijöitä. Tutkielma tarjoaa ratkai-sun strategisten investointien kohtaamaan epävarmuuteen, kompleksisuuteen ja si-säisiin konflikteihin luomalla dynaamisiin kyvykkyyksiin perustuvan prosessin, joka toteutetaan ryhmäpäätöksenteon tukisysteemien avulla asiantuntijatietoa hyö-dyntäen. Yrityksen strateginen arkkitehtuuri on mahdollista mallintaa skenaariopohjaisen strategiakartan eli kyvykkyyskartan avulla. Kyvykkyyskarttaan sisällytetyt QFD- ja AHP-mallit mahdollistavat strategisten investointien arvottamisen markkinoiden kriittisten menestystekijöiden suhteen. Dynaamisiin kyvykkyyksiin perustuvat lead user- ja skenaariosuunnitteluvaiheet mahdollistavat puolestaan joustavan investoin-tistrategian luonnin. Tutkielma osoittaa dynaamisia kyvykkyyksiä ja ryhmäpäätök-senteon tukisysteemejä hyödyntävän strategisten investointien hallintaprosessin tarjoavan ratkaisun strategisien investointipäätösten kohtaamiin haasteisiin.Ky-vykkyyskarttaan pohjautuvan strategisen arkkitehtuurin optimointimallin katsottiin olevan realistinen ja uskottava ja korostavan investointien strategisia vaikutuksia.

MANAGING STRATEGIC CHANGE:New Business Models Applying Wireless Technology as a Source of Competitive Edge

The diffusion of mobile telephony began in 1971 in Finland, when the first car phones, called ARP1 were taken to use. Technologies changed from ARP to NMT and later to GSM. The main application of the technology, however, was voice transfer. The birth of the Internet created an open public data network and easy access to other types of computer-based services over networks. Telephones had been used as modems, but the development of the cellular technologies enabled automatic access from mobile phones to Internet. Also other wireless technologies, for instance Wireless LANs, were also introduced. Telephony had developed from analog to digital in fixed networks and allowed easy integration of fixed and mobile networks. This development opened a completely new functionality to computers and mobile phones. It also initiated the merger of the information technology (IT) and telecommunication (TC) industries. Despite the arising opportunity for firms' new competition the applications based on the new functionality were rare. Furthermore, technology development combined with innovation can be disruptive to industries. This research focuses on the new technology's impact on competition in the ICT industry through understanding the strategic needs and alternative futures of the industry's customers. The change speed inthe ICT industry is high and therefore it was valuable to integrate the DynamicCapability view of the firm in this research. Dynamic capabilities are an application of the Resource-Based View (RBV) of the firm. As is stated in the literature, strategic positioning complements RBV. This theoretical framework leads theresearch to focus on three areas: customer strategic innovation and business model development, external future analysis, and process development combining these two. The theoretical contribution of the research is in the development of methodology integrating theories of the RBV, dynamic capabilities and strategic positioning. The research approach has been constructive due to the actual managerial problems initiating the study. The requirement for iterative and innovative progress in the research supported the chosen research approach. The study applies known methods in product development, for instance, innovation process in theGroup Decision Support Systems (GDSS) laboratory and Quality Function Deployment (QFD), and combines them with known strategy analysis tools like industry analysis and scenario method. As the main result, the thesis presents the strategic innovation process, where new business concepts are used to describe the alternative resource configurations and scenarios as alternative competitive environments, which can be a new way for firms to achieve competitive advantage in high-velocity markets. In addition to the strategic innovation process as a result, thestudy has also resulted in approximately 250 new innovations for the participating firms, reduced technology uncertainty and helped strategic infrastructural decisions in the firms, and produced a knowledge-bank including data from 43 ICT and 19 paper industry firms between the years 1999 - 2004. The methods presentedin this research are also applicable to other industries.

On-Line Analytical Processing of Inventory Turnover

Operatiivisen tiedon tuottaminen loppukäyttäjille analyyttistä tarkastelua silmällä pitäen aiheuttaa ongelmia useille yrityksille. Diplomityö pyrkii ratkaisemaan ko. ongelman Teleste Oyj:ssä. Työ on jaettu kolmeen pääkappaleeseen. Kappale 2 selkiyttää On-Line Analytical Processing (OLAP)- käsitteen. Kappale 3 esittelee muutamia OLAP-tuotteiden valmistajia ja heidän arkkitehtuurejaan sekä tyypillisten sovellusalueiden lisäksi huomioon otettavia asioita OLAP käyttöönoton yhteydessä. Kappale 4, tuo esille varsinaisen ratkaisun. Teknisellä arkkitehtuurilla on merkittävä asema ratkaisun rakenteen kannalta. Tässä on sovellettu Microsoft:n tietovarasto kehysrakennetta. Kappaleen 4 edetessä, tapahtumakäsittelytieto muutetaan informaatioksi ja edelleen loppukäyttäjien tiedoksi. Loppukäyttäjät varustetaan tehokkaalla ja tosiaikaisella analysointityökalulla moniulotteisessa ympäristössä. Vaikka kiertonopeus otetaan työssä sovellusesimerkiksi, työ ei pyri löytämään optimaalista tasoa Telesten varastoille. Siitä huolimatta eräitä parannusehdotuksia mainitaan.

Tehdasalueiden liikenneturvallisuutta kehittävä malli

Työn tavoitteena oli antaa tietoa tehdasalueiden turvallisuuteen vaikuttavista tekijöistä ja luoda malli tehdasalueen liikenteen turvallisuuden parantamiseen päätöksenteon tukivälineitä apuna käyttäen. Työ sai alkunsa todellisen turvallisuutta parantavan investoinnin analysointi-tarpeesta. Aluksi työssä perehdytään yleisesti tehdasalueiden turvallisuuteen tarkastelemalla työturvallisuuden, riskienhallinnan ja turvallisuusjohtamisen asemaa, mittaamista ja taloudellisia vaikutuksia yrityksen toiminnalle. Yleiskatsaus tehdasalueiden turvallisuuteen antaa kuvan, millaiseen toimintaympäristöön turvallisuutta parantavaa mallia ollaan kehittämässä. Malli koostuu viidestä vaiheesta, joita voidaan käyttää kokonaisuutena tai toisistaan erillään. Ensin selvitään tutkittavan alueen kulkuväylät ja liikenne sekä mallinnetaan se. Tämän jälkeen kartoitetaan ongelmakohdat ja etsitään sopivia vaihtoehtoja niiden turvallisuuden parantamiseksi. Vaihtoehtoja analysoidaan SWOT-menetelmän avulla. Turvallisuutta parantavien investointien arvioimiseen esitetään muutamia mittareita, joita voidaan käyttää hankintojen arvioimiseen. Viimeisessä vaiheessa tutustutaan päätöksenteon tukisysteemeihin ja esitetään tietokoneavusteinen päätöksentekomenetelmä AHP. Käytännön soveltaminen on esitetty esimerkein mallin eri vaiheiden yhteydessä.Malli on tarkoitettu suunnittelijoiden, johdon ja työsuojelun työkaluksi, jonka avulla voidaan parantaa tehdasympäristön liikenteen tehokkuutta ja turvallisuutta sekä tutustuttaa käyttäjä päätöksentekomenetelmiin.

Reducing Cardiovascular Mortality Through Prevention and Management of Raised Blood Pressure: A World Heart Federation Roadmap.

Prospective epidemiological data have shown that blood pressure has a graded, continuous adverse effect on the risk of various forms of CVD (including stroke, myocardial infarction, heart failure, peripheral arterial disease and end-stage renal disease). 'Raised blood pressure' is frequently considered to be any systolic blood pressure greater than 115 mmHg. It accounts for 45% of all heart disease deaths and 51% of all stroke-related deaths [1], which together are the biggest causes of morbidity and mortality worldwide [2,3,4]. Annually, there are >17 million deaths due to CVD worldwide, of which 9.4 million are attributable to complications of raised blood pressure. This highlights the importance of both high-risk and population-based strategies in blood pressure management and control.

SQualTrack: A Tool for Robust Fault Detection

One of the techniques used to detect faults in dynamic systems is analytical redundancy. An important difficulty in applying this technique to real systems is dealing with the uncertainties associated with the system itself and with the measurements. In this paper, this uncertainty is taken into account by the use of intervals for the parameters of the model and for the measurements. The method that is proposed in this paper checks the consistency between the system's behavior, obtained from the measurements, and the model's behavior; if they are inconsistent, then there is a fault. The problem of detecting faults is stated as a quantified real constraint satisfaction problem, which can be solved using the modal interval analysis (MIA). MIA is used because it provides powerful tools to extend the calculations over real functions to intervals. To improve the results of the detection of the faults, the simultaneous use of several sliding time windows is proposed. The result of implementing this method is semiqualitative tracking (SQualTrack), a fault-detection tool that is robust in the sense that it does not generate false alarms, i.e., if there are false alarms, they indicate either that the interval model does not represent the system adequately or that the interval measurements do not represent the true values of the variables adequately. SQualTrack is currently being used to detect faults in real processes. Some of these applications using real data have been developed within the European project advanced decision support system for chemical/petrochemical manufacturing processes and are also described in this paper

An analytic approach to distribution logistics strategic management

Logistics management is increasingly being recognised by many companies to be of critical concern. The logistics function includes directly or indirectly many of the new areas for achieving or maintaining competitive advantage that companies have been forced to develop due to increasing competitive pressures. The key to achieving a competitive advantage is to manage the logistics function strategically which involves determining the most cost effective method of providing the necessary customer service levels from the many combinations of operating procedures in the areas of transportation, warehousing, order processing and information systems, production, and inventory management. In this thesis, a comprehensive distribution logistics strategic management process is formed by integrating the periodic strategic planning process with a continuous strategic issues management process. Strategic planning is used for defining the basic objectives for a company and assuring co operation and synergy between the different functions of a company while strategic issues management is used on a continuous basis in order to deal with environmental and internal turbulence. The strategic planning subprocess consists of the following main phases: (1) situational analyses, (2) defining the vision and strategic goals for the logistics function, (3) determining objectives and strategies, (4) drawing up tactical action plans, and (5) evaluating the implementation of the plans and making the needed adjustments. The aim of the strategic issues management subprocess is to continuously scan the environment and the organisation for early identification of the issues having a significant impact on the logistics function using the following steps: (1) the identification of trends, (2) assessing the impact and urgency of the identified trends, (3) assigning priorities to the issues, and (4) planning responses to the, issues. The Analytic Hierarchy Process (AHP) is a systematic procedure for structuring any problem. AHP is based on the following three principles: decomposition, comparative judgements, and synthesis of priorities. AHP starts by decomposing a complex, multicriteria problem into a hierarchy where each level consists of a few manageable elements which are then decomposed into another set of elements. The second step is to use a measurement methodology to establish priorities among the elements within each level of the hierarchy. The third step in using AHP is to synthesise the priorities of the elements to establish the overall priorities for the decision alternatives. In this thesis, decision support systems are developed for different areas of distribution logistics strategic management by applying the Analytic Hierarchy Process. The areas covered are: (1) logistics strategic issues management, (2) planning of logistic structure, (3) warehouse site selection, (4) inventory forecasting, (5) defining logistic action and development plans, (6) choosing a distribution logistics strategy, (7) analysing and selecting transport service providers, (8) defining the logistic vision and strategic goals, (9) benchmarking logistic performance, and (10) logistic service management. The thesis demonstrates the potential of AHP as a systematic and analytic approach to distribution logistics strategic management.

Päätöksentekomenetelmien hyödyntäminen pientalon lämmitysjärjestelmän valinnassa

Tämän diplomityön tavoitteena on valita sopiva lämmitysjärjestelmä case taloon käyttäen apuna päätöksentekoprosessia ja eri vaiheissa sovellettavia menetelmiä. Työn avulla pyritään selvittämään kuinka hyvin päätöksentekomenetelmät sopivat lämmitysjärjestelmän valintaan ja mitä hyötyjä se tuo tullessaan. Prosessissa selvitetään lämmitysjärjestelmiin liittyviä asiakastarpeita, arvioidaan lämmitysjärjestelmien ominaisuuksia ja tehdään valinta näiden tietojen pohjalta. Kymmenhenkinen kuluttajaryhmä teki lopullisen päätöksen valittavasta lämmitysjärjestelmästä. Menetelmien avulla saatiin luotua kattava kuva erilaisista asiakastarpeista, jotka otettiin huomioon valinnassa. Ryhmä valitsi case taloon seitsemästä yleisestä lämmitysjärjestelmästä maalämmön. Työssä käytetyt menetelmät toimivat hyvin yhteistyössä toistensa kanssa. Menetelmien käyttö mahdollisti kaikkien kriteereiden huomioimisen ja tuloksien lähemmän tarkastelun. Työssä saatuja tuloksia voidaan hyödyntää lämmitysjärjestelmän valinnassa ottaen huomioon erilaiset lähtötilanteet. Herkkyysanalyyseissa maalämpö kesti monien kriteerien painotuksien muuttamista ja osoittautui tällä tavoin sopivimmaksi järjestelmäksi.

New and Emerging Challenges of the ICT-Mediated Health and Well-Being Services

This monograph dissertation looks into the field of ICT-mediated health and well-being services. Through six chapters that extend the work done in the reviewed and published articles, the dissertation focuses on new and emerging technologies, and to impact of their use on the beneficiary; the individual who eventually derives advantage from the services. As the field is currently going through major changes particularly in the OECD countries, the focus is on shortterm developments in the field and the analysis on the long term developments is cursory by nature. The dissertation includes theoretical and empirical elements. Most of the empirical elements are linked to product development and conceptualization performed in the national MyWellbeing project that ended in 2010. In the project, the emphasis was on conceptualization of a personal aid for the beneficiary that could be used for managing information and services in the field of health and well-being services. This work continued the theme of developing individual-centric solutions for the field; a work that started in the InnoElli Senior program in 2006. The nature of this thesis is foremost a conceptual elaboration based on a literature review, illustrated in empirical work performed in different projects. As a theoretical contribution, this dissertation elaborates the role of a mediator, i.e. an intermediary, and it is used as an overarching theme. The role acts as a ‘lens’ through which a number of technology-related phenomena are looked at, pinned down and addressed to a degree. This includes introduction of solutions, ranging from anthropomorphic artefacts to decision support systems that may change the way individuals experience clinical encounters in the near-future. Due to the complex and multiform nature of the field, it is impractical and effectively impossible to cover all aspects that are related to mediation in a single work. Issues such as legislation, financing and privacy are all of equal importance. Consideration of all these issues is beyond the scope of this dissertation and their investigation is left to other work. It follows from this that the investigation on the role is not intended as inclusive one. The role of the mediator is also used to highlight some of the ethical issues related to personal health information management, and to mediating health and well-being related issues on behalf of another individual, such as an elderly relative or a fellow member of a small unit in the armed forces. The dissertation concludes in a summary about the use and functions of the mediator, describing some potential avenues for implementing such support mechanisms to the changing field of ICT-mediated health and well-being services. The conclusions also describe some of the limitations of this dissertation, including remarks on methodology and content.

Liiketoiminta-analytiikka osana yritysten päätöksentekoa

Liiketoiminta-analytiikka on yksi yritysten suorituskyvyn johtamisen osa-alue, joka on viime aikoina noussut vahvasti esille yritysten kilpailuedun mahdollistavana avaintekijänä. Tämän tutkimuksen tavoitteena oli kartoittaa yritysten liiketoiminta-analytiikan nykytila ja tarpeet Suomessa. Tutkimus on luonteeltaan kvalitatiivinen vertaileva tutkimus. Tutkimuksen empiirinen aineisto kerättiin kahden menetelmän yhdistelmänä. Liiketoiminta-analytiikan hyödyntämisessä edistyneempien yrityksien asiantuntijoille toteutettiin haastattelut. Lisäksi toteutettiin sähköpostitse lomakemuotoinen kyselytutkimus, jotta saavutettaisiin kattavampi näkemys analytiikan markkinoista. Tutkimuksessa on kartoitettu, miten Suomessa ymmärretään liiketoiminta- analytiikan käsite eri yrityksien analytiikan asiantuntijoiden toimesta, sekä minkälaisissa päätöksentekotilanteissa liiketoiminta-analytiikkaa hyödynnetään ja minkälaisilla tavoilla. Lisäksi on selvitetty, miten liiketoiminta-analytiikan kehittämistä ja analytiikan kyvykkyyksiä hallitaan yrityksissä. Liiketoiminta-analytiikka on Suomessa tietyillä toimialoilla erittäin kehittynyttä, mutta yleisesti ollaan jäljessä alan edelläkävijöitä ja esimerkiksi Ruotsia. Liiketoiminta-analytiikan hyödyntäminen ja tarpeet ovat pitkälti kohdistuneet päätöksentekotilanteisiin, joissa yritys kohtaa asiakkaansa. Suurin yksittäinen este liiketoiminta-analytiikan hyödyntämiselle on resurssi- ja osaamisvaje.

Model of Big Data Failure: Review of Information System Failure

In the new age of information technology, big data has grown to be the prominent phenomena. As information technology evolves, organizations have begun to adopt big data and apply it as a tool throughout their decision-making processes. Research on big data has grown in the past years however mainly from a technical stance and there is a void in business related cases. This thesis fills the gap in the research by addressing big data challenges and failure cases. The Technology-Organization-Environment framework was applied to carry out a literature review on trends in Business Intelligence and Knowledge management information system failures. A review of extant literature was carried out using a collection of leading information system journals. Academic papers and articles on big data, Business Intelligence, Decision Support Systems, and Knowledge Management systems were studied from both failure and success aspects in order to build a model for big data failure. I continue and delineate the contribution of the Information System failure literature as it is the principal dynamics behind technology-organization-environment framework. The gathered literature was then categorised and a failure model was developed from the identified critical failure points. The failure constructs were further categorized, defined, and tabulated into a contextual diagram. The developed model and table were designed to act as comprehensive starting point and as general guidance for academics, CIOs or other system stakeholders to facilitate decision-making in big data adoption process by measuring the effect of technological, organizational, and environmental variables with perceived benefits, dissatisfaction and discontinued use.