Modelling non-industrial private forest landowners' strategic decision making by using logistic regression and neural networks: case of predicting the choice of forest taxation basis

Summary

Use of neural networks in robot positioning of large flexible redundant manipulators

Deflection compensation of flexible boom structures in robot positioning is usually done using tables containing the magnitude of the deflection with inverse kinematics solutions of a rigid structure. The number of table values increases greatly if the working area of the boom is large and the required positioning accuracy is high. The inverse kinematics problems are very nonlinear, and if the structure is redundant, in some cases it cannot be solved in a closed form. If the structural flexibility of the manipulator arms is taken into account, the problem is almost impossible to solve using analytical methods. Neural networks offer a possibility to approximate any linear or nonlinear function. This study presents four different methods of using neural networks in the static deflection compensation and inverse kinematics solution of a flexible hydraulically driven manipulator. The training information required for training neural networks is obtained by employing a simulation model that includes elasticity characteristics. The functionality of the presented methods is tested based on the simulated and measured results of positioning accuracy. The simulated positioning accuracy is tested in 25 separate coordinate points. For each point, the positioning is tested with five different mass loads. The mean positioning error of a manipulator decreased from 31.9 mm to 4.1 mm in the test points. This accuracy enables the use of flexible manipulators in the positioning of larger objects. The measured positioning accuracy is tested in 9 separate points using three different mass loads. The mean positioning error decreased from 10.6 mm to 4.7 mm and the maximum error from 27.5 mm to 11.0 mm.

Forecasting of wind speeds and directions with artificial neural networks

In this master’s thesis, wind speeds and directions were modeled with the aim of developing suitable models for hourly, daily, weekly and monthly forecasting. Artificial Neural Networks implemented in MATLAB software were used to perform the forecasts. Three main types of artificial neural network were built, namely: Feed forward neural networks, Jordan Elman neural networks and Cascade forward neural networks. Four sub models of each of these neural networks were also built, corresponding to the four forecast horizons, for both wind speeds and directions. A single neural network topology was used for each of the forecast horizons, regardless of the model type. All the models were then trained with real data of wind speeds and directions collected over a period of two years in the municipal region of Puumala in Finland. Only 70% of the data was used for training, validation and testing of the models, while the second last 15% of the data was presented to the trained models for verification. The model outputs were then compared to the last 15% of the original data, by measuring the mean square errors and sum square errors between them. Based on the results, the feed forward networks returned the lowest generalization errors for hourly, weekly and monthly forecasts of wind speeds; Jordan Elman networks returned the lowest errors when used for forecasting of daily wind speeds. Cascade forward networks gave the lowest errors when used for forecasting daily, weekly and monthly wind directions; Jordan Elman networks returned the lowest errors when used for hourly forecasting. The errors were relatively low during training of the models, but shot up upon simulation with new inputs. In addition, a combination of hyperbolic tangent transfer functions for both hidden and output layers returned better results compared to other combinations of transfer functions. In general, wind speeds were more predictable as compared to wind directions, opening up opportunities for further research into building better models for wind direction forecasting.

Pretraining Convolutional Neural Networks for Visual Recognition

Convolutional Neural Networks (CNN) have become the state-of-the-art methods on many large scale visual recognition tasks. For a lot of practical applications, CNN architectures have a restrictive requirement: A huge amount of labeled data are needed for training. The idea of generative pretraining is to obtain initial weights of the network by training the network in a completely unsupervised way and then fine-tune the weights for the task at hand using supervised learning. In this thesis, a general introduction to Deep Neural Networks and algorithms are given and these methods are applied to classification tasks of handwritten digits and natural images for developing unsupervised feature learning. The goal of this thesis is to find out if the effect of pretraining is damped by recent practical advances in optimization and regularization of CNN. The experimental results show that pretraining is still a substantial regularizer, however, not a necessary step in training Convolutional Neural Networks with rectified activations. On handwritten digits, the proposed pretraining model achieved a classification accuracy comparable to the state-of-the-art methods.

Deep convolutional neural networks for semantic video object segmentation

In this thesis, we propose to infer pixel-level labelling in video by utilising only object category information, exploiting the intrinsic structure of video data. Our motivation is the observation that image-level labels are much more easily to be acquired than pixel-level labels, and it is natural to find a link between the image level recognition and pixel level classification in video data, which would transfer learned recognition models from one domain to the other one. To this end, this thesis proposes two domain adaptation approaches to adapt the deep convolutional neural network (CNN) image recognition model trained from labelled image data to the target domain exploiting both semantic evidence learned from CNN, and the intrinsic structures of unlabelled video data. Our proposed approaches explicitly model and compensate for the domain adaptation from the source domain to the target domain which in turn underpins a robust semantic object segmentation method for natural videos. We demonstrate the superior performance of our methods by presenting extensive evaluations on challenging datasets comparing with the state-of-the-art methods.

On the differential evolution algorithm and its appliation to training radial basis function networks

The parameter setting of a differential evolution algorithm must meet several requirements: efficiency, effectiveness, and reliability. Problems vary. The solution of a particular problem can be represented in different ways. An algorithm most efficient in dealing with a particular representation may be less efficient in dealing with other representations. The development of differential evolution-based methods contributes substantially to research on evolutionary computing and global optimization in general. The objective of this study is to investigatethe differential evolution algorithm, the intelligent adjustment of its controlparameters, and its application. In the thesis, the differential evolution algorithm is first examined using different parameter settings and test functions. Fuzzy control is then employed to make control parameters adaptive based on an optimization process and expert knowledge. The developed algorithms are applied to training radial basis function networks for function approximation with possible variables including centers, widths, and weights of basis functions and both having control parameters kept fixed and adjusted by fuzzy controller. After the influence of control variables on the performance of the differential evolution algorithm was explored, an adaptive version of the differential evolution algorithm was developed and the differential evolution-based radial basis function network training approaches were proposed. Experimental results showed that the performance of the differential evolution algorithm is sensitive to parameter setting, and the best setting was found to be problem dependent. The fuzzy adaptive differential evolution algorithm releases the user load of parameter setting and performs better than those using all fixedparameters. Differential evolution-based approaches are effective for training Gaussian radial basis function networks.

Implementing telephony signalling over IP networks using SIGTRAN standards

Diplomityössä tutkitaan yhteiskanavamerkinantoverkon signalointiliikenteen siirtoa IP-pohjaisiin verkkoihin käyttäen IETF:n aliorganisaation, SIGTRAN:in, määrittelemiä standardeja. Tutkimuksen lisäksi työssä suoritetaan myös toteutus, joka mahdollistaa em. verkkojen yhdistymisen. Ensin työssä käsitellään yhteiskanavamerkinantoverkon tulevaisuus ja alan yleiset näkymät, jotka luovat pohjan työn toteutuksen ymmärtämiseen. Toiseksi työssä esitellään toteutuksessa käytetyt teknologiat. Esiteltäviin teknologioihin kuuluvat yhteiskanavamerkinantoverkko, IP-pohjainen verkko, SIGTRAN:in määrittelemät standardit, toteutustyökalut sekä ympäristö, johon toteutus liitetään. Toteutukseen olennaisesti liittyvät asiat ovat painotettuina teknologioiden esittelyssä. Diplomityön loppuosassa kuvataan merkinantoyhdyskäytävän toteutus suunnittelun ja toteutettujen toiminnallisuuksien osalta. Diplomityön tuloksena saatiin uusi testattu merkinantosovellus, joka täyttää yhteiskanavamerkinantoverkolle asetetut vaatimukset. Toteutus toimii osana Intellitel(TM) ONE palvelualustaa. Toteutuksen kehitys tulee jatkumaan.

Application of Neural Network Methods in the Prediction of Stock Markets

The purpose of the research is to define practical profit which can be achieved using neural network methods as a prediction instrument. The thesis investigates the ability of neural networks to forecast future events. This capability is checked on the example of price prediction during intraday trading on stock market. The executed experiments show predictions of average 1, 2, 5 and 10 minutes’ prices based on data of one day and made by two different types of forecasting systems. These systems are based on the recurrent neural networks and back propagation neural nets. The precision of the predictions is controlled by the absolute error and the error of market direction. The economical effectiveness is estimated by a special trading system. In conclusion, the best structures of neural nets are tested with data of 31 days’ interval. The best results of the average percent of profit from one transaction (buying + selling) are 0.06668654, 0.188299453, 0.349854787 and 0.453178626, they were achieved for prediction periods 1, 2, 5 and 10 minutes. The investigation can be interesting for the investors who have access to a fast information channel with a possibility of every-minute data refreshment.

Text Classification and Indexing in IP Networks

Internet on elektronisen postin perusrakenne ja ollut tärkeä tiedonlähde akateemisille käyttäjille jo pitkään. Siitä on tullut merkittävä tietolähde kaupallisille yrityksille niiden pyrkiessä pitämään yhteyttä asiakkaisiinsa ja seuraamaan kilpailijoitansa. WWW:n kasvu sekä määrällisesti että sen moninaisuus on luonut kasvavan kysynnän kehittyneille tiedonhallintapalveluille. Tällaisia palveluja ovet ryhmittely ja luokittelu, tiedon löytäminen ja suodattaminen sekä lähteiden käytön personointi ja seuranta. Vaikka WWW:stä saatavan tieteellisen ja kaupallisesti arvokkaan tiedon määrä on huomattavasti kasvanut viime vuosina sen etsiminen ja löytyminen on edelleen tavanomaisen Internet hakukoneen varassa. Tietojen hakuun kohdistuvien kasvavien ja muuttuvien tarpeiden tyydyttämisestä on tullut monimutkainen tehtävä Internet hakukoneille. Luokittelu ja indeksointi ovat merkittävä osa luotettavan ja täsmällisen tiedon etsimisessä ja löytämisessä. Tämä diplomityö esittelee luokittelussa ja indeksoinnissa käytettävät yleisimmät menetelmät ja niitä käyttäviä sovelluksia ja projekteja, joissa tiedon hakuun liittyvät ongelmat on pyritty ratkaisemaan.

Development of research networks : the case of social capital

The aim of this study is to explore how a new concept appears inscientific discussion and research, how it diffuses to other fields and out of the scientific communities, and how the networks are formed around the concept. Text and terminology take the interest of a reader in the digital environment. Texts create networks where the terminology used is dependent on the ideas, viewsand paradigms of the field. This study is based mainly on bibliographic data. Materials for bibliometric studies have been collected from different databases. The databases are also evaluated and their quality and coverage are discussed. The thesauri of those databases that have been selected for a more in depth study have also been evaluated. The material selected has been used to study how long and in which ways an innovative publication, which can be seen as a milestone in a specific field, influences the research. The concept that has been chosen as a topic for this research is Social Capital, because it has been a popular concept in different scientific fields as well as in everyday speech and the media. It seemed to be a `fashion concept´ that appeared in different situations at the Millennium. The growth and diffusion of social capital publications has been studied. The terms connected with social capital in different fields and different stages of the development have also been analyzed. The methods that have been used in this study are growth and diffusion analysis, content analysis, citation analysis, coword analysis and cocitation analysis. One method that can be used tounderstand and to interpret results of these bibliometric studies is to interview some key persons, who are known to have a gatekeeper position in the diffusion of the concept. Thematic interviews with some Finnish researchers and specialists that have influenced the diffusion of social capital into Finnish scientificand social discussions provide background information. iv The Milestone Publications on social capital have been chosen and studied. They give answers to the question "What is Social Capital?" By comparing citations to Milestone Publications with the growth of all social capital publications in a database, we can drawconclusions about the point at which social capital became generally approved `tacit knowledge´. The contribution of the present study lies foremost in understanding the development of network structures around a new concept that has diffused in scientific communities and also outside them. The network means both networks of researchers, networks of publications and networks of concepts that describe the research field. The emphasis has been on the digital environment and onthe socalled information society that we are now living in, but in this transitional stage, the printed publications are still important and widely used in social sciences and humanities. The network formation is affected by social relations and informal contacts that push new ideas. This study also gives new information about using different research methods, like bibliometric methods supported by interviews and content analyses. It is evident that interpretation of bibliometric maps presupposes qualitative information and understanding of the phenomena under study.

Communication Solutions for LVDC Island Networks

Production and generation of electrical power is evolving to more environmental friendly technologies and schemes. Pushed by the increasing cost of fossil fuels, the operational costs of producing electrical power with fossil fuels and the effect in the environment, like pollution and global warming, renewable energy sources gain con-stant impulse into the global energy economy. In consequence, the introduction of distributed energy sources has brought a new complexity to the electrical networks. In the new concept of smart grids and decen-tralized power generation; control, protection and measurement are also distributed and requiring, among other things, a new scheme of communication to operate with each other in balance and improve performance. In this research, an analysis of different communication technologies (power line communication, Ethernet over unshielded twisted pair (UTP), optic fiber, Wi-Fi, Wi-MAX, and Long Term Evolution) and their respective characteristics will be carried out. With the objective of pointing out strengths and weaknesses from different points of view (technical, economical, deployment, etc.) to establish a richer context on which a decision for communication approach can be done depending on the specific application scenario of a new smart grid deployment. As a result, a description of possible optimal deployment solutions for communication will be shown considering different options for technologies, and a mention of different important considerations to be taken into account will be made for some of the possible network implementation scenarios.

Aligning Regional Repository Networks

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