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

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.

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.

Verbal learning in mild cognitive impairment and alzheimer's disease : behavioural and neural approaches

The main focus of the present thesis was at verbal episodic memory processes that are particularly vulnerable to preclinical and clinical Alzheimer’s disease (AD). Here these processes were studied by a word learning paradigm, cutting across the domains of memory and language learning studies. Moreover, the differentiation between normal aging, mild cognitive impairment (MCI) and AD was studied by the cognitive screening test CERAD. In study I, the aim was to examine how patients with amnestic MCI differ from healthy controls in the different CERAD subtests. Also, the sensitivity and specificity of the CERAD screening test to MCI and AD was examined, as previous studies on the sensitivity and specificity of the CERAD have not included MCI patients. The results indicated that MCI is characterized by an encoding deficit, as shown by the overall worse performance on the CERAD Wordlist learning test compared with controls. As a screening test, CERAD was not very sensitive to MCI. In study II, verbal learning and forgetting in amnestic MCI, AD and healthy elderly controls was investigated with an experimental word learning paradigm, where names of 40 unfamiliar objects (mainly archaic tools) were trained with or without semantic support. The object names were trained during a 4-day long period and a follow-up was conducted one week, 4 weeks and 8 weeks after the training period. Manipulation of semantic support was included in the paradigm because it was hypothesized that semantic support might have some beneficial effects in the present learning task especially for the MCI group, as semantic memory is quite well preserved in MCI in contrast to episodic memory. We found that word learning was significantly impaired in MCI and AD patients, whereas forgetting patterns were similar across groups. Semantic support showed a beneficial effect on object name retrieval in the MCI group 8 weeks after training, indicating that the MCI patients’ preserved semantic memory abilities compensated for their impaired episodic memory. The MCI group performed equally well as the controls in the tasks tapping incidental learning and recognition memory, whereas the AD group showed impairment. Both the MCI and the AD group benefited less from phonological cueing than the controls. Our findings indicate that acquisition is compromised in both MCI and AD, whereas long13 term retention is not affected to the same extent. Incidental learning and recognition memory seem to be well preserved in MCI. In studies III and IV, the neural correlates of naming newly learned objects were examined in healthy elderly subjects and in amnestic MCI patients by means of positron emission tomography (PET) right after the training period. The naming of newly learned objects by healthy elderly subjects recruited a left-lateralized network, including frontotemporal regions and the cerebellum, which was more extensive than the one related to the naming of familiar objects (study III). Semantic support showed no effects on the PET results for the healthy subjects. The observed activation increases may reflect lexicalsemantic and lexical-phonological retrieval, as well as more general associative memory mechanisms. In study IV, compared to the controls, the MCI patients showed increased anterior cingulate activation when naming newly learned objects that had been learned without semantic support. This suggests a recruitment of additional executive and attentional resources in the MCI group.

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.

Patterns and processes of littoral zooplankton composition in relation to the trophic state of the environment

Avhandlingen handlar om hur kompositionen hos litoralt djurplankton varierar med omgivningens trofiska nivå (m.a.o. eutrofieringsgrad). Arbetets inledande mål är att beskriva hur mängden och artmångfalden hos djurplankton i strandnära vattnen och de omgivande organismsamhällen ändras med närsaltshalter. Huvudsyftet är att utreda allmänna mekanismer som styr dessa mönster och som på så sätt kan vara viktiga i att reglera samhällen även i andra ekologiska system. Undersökningarna gjordes i åländska flador över flera tillväxtsäsonger samt i laboratorier där omgivningsförhållanden i fladorna kunde simuleras och manipuleras. Djurplankton i dessa lagunlika vikar är lägliga modellsystem. Flador är lämpligt avgränsade från det omgivande havet och förekommer allmänt i norra Östersjöregionen. Således kan de inom ett litet område som Åland representera hela regionala gradienten från näringsfattiga till näringsrika förhållanden. De små kräft- och hjuldjuren som djurplankton består av befinner sig i mitten av näringsväven. De sammankopplar olika typer av mikrobiell produktion vidare till högre konsumenter och är på så sätt centrala för organismsamhällens struktur och funktion i nästan alla akvatiska miljöer. I likhet med primärproducenterna (d.v.s. växter och alger som direkt påverkas av närsaltshalterna, och som bl.a. utgör föda och habitat för djurplankton) samvarierar kompositionen hos djurplankton tydligt med omgivningens trofiska nivå tills den blir hög. Sedan börjar hela samhällskompositionen utveckla sig åt två skilda håll. Dessa mönster kan för djurplanktonets del förklaras med att dess komposition ingalunda styrs endast av primärproducenterna, utan av ett komplicerat samspel mellan dessa resurser samt konkurrerande och högre konsumenter (d.v.s. predatorer på flera högre trofinivåer). Detta kom fram speciellt i laboratorieförhållanden då kompositionen hos dessa samhällskomponenter manipulerades. Både deras sammansättning och relativa tätheter i sig, samt en kombination av båda visade sig styra djurplanktonkompositionen. Lokala processer (inom fladorna) och synnerligen förändringar hos olika fundament- (speciellt vass, borstnate och rödsträfse), kärn- (speciellt yngel av a bborre och mört) och nyckelarter (stora predatorer som gädda) verkar kunna avgöra till vilken grad djurplanktonkompositionen samvarierar med omgivningens trofiska nivå. Inte bara samhällen utan också de mekanismer som styr dem ändras med omgivningens trofiska nivå. Flador är ypperliga naturliga laboratorier för att studera dessa och även andra allmänekologiska mönster och mekanismer. De är också oerhört viktiga miljöer för hela kustregionens natur.

Helsinki hub – new traffic flows and business networks

This thesis is the Logistics Development Forum's assignment and the work dealing with the development of the Port of Helsinki as part of Helsinki hub. The Forum aims to develop logistics efficiency through public-private co-operation and development of the port is clearly dependent on both factors. Freight volumes in the Port of Helsinki are the biggest single factor in hub and, therefore, the role of the port of the entire hub development is strong. The aim is to look at how the port will develop as a result of changes in the foreign trade of Finland and the Northern European logistics trends in 25 years time period. Work includes the current state analysis and scenario work. The analyses are intended to find out, which trends are the most important in the port volume development. The change and effect of trends is examined through scenarios based on current state. Based on the work, the structure of Finnish export industry and international demand are in the key role in the port volume development. There is significant difference between demands of Finnish exporting products in different export markets and the development between the markets has different impacts on the port volumes by mass and cargo type. On the other hand, the Finnish economy is stuck in a prolonged recession and competition between ports has become a significant factor in the individual port's volume development. Ecological valuesand regulations have changed the competitive landscape and maritime transport emissions reductions has become an important competitive factor for short routes in the Baltic Sea, such as in the link between Helsinki and Tallinn.