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.

Stiffness based trajectory planning and feedforward based vibration suppression control of parallel robot machines

The dissertation proposes two control strategies, which include the trajectory planning and vibration suppression, for a kinematic redundant serial-parallel robot machine, with the aim of attaining the satisfactory machining performance. For a given prescribed trajectory of the robot's end-effector in the Cartesian space, a set of trajectories in the robot's joint space are generated based on the best stiffness performance of the robot along the prescribed trajectory. To construct the required system-wide analytical stiffness model for the serial-parallel robot machine, a variant of the virtual joint method (VJM) is proposed in the dissertation. The modified method is an evolution of Gosselin's lumped model that can account for the deformations of a flexible link in more directions. The effectiveness of this VJM variant is validated by comparing the computed stiffness results of a flexible link with the those of a matrix structural analysis (MSA) method. The comparison shows that the numerical results from both methods on an individual flexible beam are almost identical, which, in some sense, provides mutual validation. The most prominent advantage of the presented VJM variant compared with the MSA method is that it can be applied in a flexible structure system with complicated kinematics formed in terms of flexible serial links and joints. Moreover, by combining the VJM variant and the virtual work principle, a systemwide analytical stiffness model can be easily obtained for mechanisms with both serial kinematics and parallel kinematics. In the dissertation, a system-wide stiffness model of a kinematic redundant serial-parallel robot machine is constructed based on integration of the VJM variant and the virtual work principle. Numerical results of its stiffness performance are reported. For a kinematic redundant robot, to generate a set of feasible joints' trajectories for a prescribed trajectory of its end-effector, its system-wide stiffness performance is taken as the constraint in the joints trajectory planning in the dissertation. For a prescribed location of the end-effector, the robot permits an infinite number of inverse solutions, which consequently yields infinite kinds of stiffness performance. Therefore, a differential evolution (DE) algorithm in which the positions of redundant joints in the kinematics are taken as input variables was employed to search for the best stiffness performance of the robot. Numerical results of the generated joint trajectories are given for a kinematic redundant serial-parallel robot machine, IWR (Intersector Welding/Cutting Robot), when a particular trajectory of its end-effector has been prescribed. The numerical results show that the joint trajectories generated based on the stiffness optimization are feasible for realization in the control system since they are acceptably smooth. The results imply that the stiffness performance of the robot machine deviates smoothly with respect to the kinematic configuration in the adjacent domain of its best stiffness performance. To suppress the vibration of the robot machine due to varying cutting force during the machining process, this dissertation proposed a feedforward control strategy, which is constructed based on the derived inverse dynamics model of target system. The effectiveness of applying such a feedforward control in the vibration suppression has been validated in a parallel manipulator in the software environment. The experimental study of such a feedforward control has also been included in the dissertation. The difficulties of modelling the actual system due to the unknown components in its dynamics is noticed. As a solution, a back propagation (BP) neural network is proposed for identification of the unknown components of the dynamics model of the target system. To train such a BP neural network, a modified Levenberg-Marquardt algorithm that can utilize an experimental input-output data set of the entire dynamic system is introduced in the dissertation. Validation of the BP neural network and the modified Levenberg- Marquardt algorithm is done, respectively, by a sinusoidal output approximation, a second order system parameters estimation, and a friction model estimation of a parallel manipulator, which represent three different application aspects of this method.

Multikerrosperceptroni ja sen sovellusalueet

Tietokoneet kykenevät suoriutumaan suuresta määrästä raskaita laskutoimituksia lyhyessä ajassa. Niillä on näin ollen siis mahdollista automatisoida sellaisia toimintoja, joissa esimerkiksi ihminen sortuu helposti tarkkaavaisuusvirheisiin. Ihminen pystyy toisaalta sellaisiin toimintoihin, jotka ovat tietokoneille hyvin vaikeita. Esimerkiksi luova ajattelu ja tutun ihmisen kasvojen tunnistaminen onnistuu ihmisiltä huomattavasti helpommin kuin tietokoneilta. Ilman tarkkoja ohjeita tietokone on toimintakyvytön, eikä tuntemattomia ongelmia ole mahdollista ratkaista. Ihmisaivojen toimintaa on niiden kykyjen vuoksi pidetty mielenkiintoisena tutkimuskohteena tietojenkäsittelyn kannalta. Yritykset mallintaa niiden toimintaa ovat johtaneet neuroverkkojen syntyyn. Kehitys alkoi neuronin mallin esittelemisestä ja jatkui edelleen perceptroniin. Lopulta kehitys päättyi neuroverkkoihin, joita on useita erilaisia. Suosituin niistä on kerroksittaisen rakenteen omaava multikerrosperceptroni. Neuroverkkoja on koulutettava halutun toiminnan aikaansaamiseksi. Niitä voidaan kouluttaa ohjatusti, ohjaamattomasti ja arvostellusti. Perceptronin kouluttaminen on helpompaa sen yksinkertaisen rakenteen takia kuin multikerrosperceptronin kouluttaminen. Esimerkiksi back propagation- algoritmi soveltuu multikerrosperceptronin kouluttamiseen. Koulutusprosessissa on oltava tarkkana, sillä neuroverkko voi oppia liikaa opeteltavasta asiasta ja tuottaa huonoja tuloksia koulutuksen jälkeen. Verkon oppimista onkin seurattava tarkkaan kouluttamisen yhteydessä. Oppimiseen vaikuttaa myös verkon rakenne. Neuroverkkojen, erityisesti multikerros perceptronien on todettu sopivan erityisen hyvin erilaisiin käytännön sovelluksiin. Esimerkiksi optisessa kuvantunnistuksessa sen on havaittu tuottavan erityisen hyviä tuloksia, jos kuva tekstistä on prosessoitu oikein neuroverkkoa varten.

Maintenance of male sterile germplasm in Brassica rapa in vitro propagation

Selostus: Isästeriilin kevätrypsin geeniaineksen ylläpito in vitro mikroviljelyllä

Propagation of the Ignition Front against Airflow in Packed Beds of Wood Particles

Combustion of wood is increasing because of the needs of decreasing the emissions of carbon dioxide and the amount of waste going to landfills. Wood based fuels are often scattered on a large area. The transport distances should be short enough to prevent too high costs, and so the size of heating and power plants using wood fuels is often rather small. Combustion technologies of small-size units have to be developed to reach efficient and environmentally friendly energy production. Furnaces that use different packed bed combustion or gasification techniques areoften most economic in small-scale energy production. Ignition front propagation rate affects the stability, heat release rate and emissions of packed bed combustion. Ignition front propagation against airflow in packed beds of wood fuels has been studied. The research has been carried out mainly experimentally. Theoretical aspects have been considered to draw conclusions about the experimental results. The effects of airflow rate, moisture content of the fuel, size, shape and density of particles, and porosity of the bed on the propagation rate of the ignition front have been studied. The experiments were carried out in a pot furnace. The fuels used in the experiments were mainly real wood fuels that are often burned in the production of energy. The fuel types were thin wood chips, saw dust, shavings, wood chips, and pellets with different sizes. Also a few mixturesof the above were tested. Increase in the moisture content of the fuel decreases the propagation rates of the ignition front and makes the range of possible airflow rates narrower because of the energy needed for the evaporation of water and the dilution of volatile gases due to evaporated steam. Increase in the airflow rate increases the ignition rate until a maximum rate of propagation is reached after which it decreases. The maximum flame propagation rate is not always reached in stoichiometric combustion conditions. Increase in particle size and density transfers the optimum airflow rate towards fuel lean conditions. Mixing of small and large particles is often advantageous, because small particles make itpossible to reach the maximum ignition rate in fuel rich conditions, and large particles widen the range of possible airflow rates. A correlation was found forthe maximum rate of ignition front propagation in different wood fuels. According to the correlation, the maximum ignition mass flux is increased when the sphericity of the particles and the porosity of the bed are increased and the moisture content of the fuel is decreased. Another fit was found between sphericity and porosity. Increase in sphericity decreases the porosity of the bed. The reasons of the observed results are discussed.

Minimization of the experimental workload for the prediction of pollutants propagation in rivers. Mathematical modelling and knowledge re-use

The present thesis in focused on the minimization of experimental efforts for the prediction of pollutant propagation in rivers by mathematical modelling and knowledge re-use. Mathematical modelling is based on the well known advection-dispersion equation, while the knowledge re-use approach employs the methods of case based reasoning, graphical analysis and text mining. The thesis contribution to the pollutant transport research field consists of: (1) analytical and numerical models for pollutant transport prediction; (2) two novel techniques which enable the use of variable parameters along rivers in analytical models; (3) models for the estimation of pollutant transport characteristic parameters (velocity, dispersion coefficient and nutrient transformation rates) as functions of water flow, channel characteristics and/or seasonality; (4) the graphical analysis method to be used for the identification of pollution sources along rivers; (5) a case based reasoning tool for the identification of crucial information related to the pollutant transport modelling; (6) and the application of a software tool for the reuse of information during pollutants transport modelling research. These support tools are applicable in the water quality research field and in practice as well, as they can be involved in multiple activities. The models are capable of predicting pollutant propagation along rivers in case of both ordinary pollution and accidents. They can also be applied for other similar rivers in modelling of pollutant transport in rivers with low availability of experimental data concerning concentration. This is because models for parameter estimation developed in the present thesis enable the calculation of transport characteristic parameters as functions of river hydraulic parameters and/or seasonality. The similarity between rivers is assessed using case based reasoning tools, and additional necessary information can be identified by using the software for the information reuse. Such systems represent support for users and open up possibilities for new modelling methods, monitoring facilities and for better river water quality management tools. They are useful also for the estimation of environmental impact of possible technological changes and can be applied in the pre-design stage or/and in the practical use of processes as well.

It all comes back to you

Soitinnus: big band.

Recovery of carboxylic acids from aqueous streams by extraction and back extraction

Separation of carboxylic acids from aqueous streams is an important part of their manufacturing process. The aqueous solutions are usually dilute containing less than 10 % acids. Separation by distillation is difficult as the boiling points of acids are only marginally higher than that of water. Because of this distillation is not only difficult but also expensive due to the evaporation of large amounts of water. Carboxylic acids have traditionally been precipitated as calcium salts. The yields of these processes are usually relatively low and the chemical costs high. Especially the decomposition of calcium salts with sulfuric acid produces large amounts of calcium sulfate sludge. Solvent extraction has been studied as an alternative method for recovery of carboxylic acids. Solvent extraction is based on mixing of two immiscible liquids and the transfer of the wanted components form one liquid to another due to equilibrium difference. In the case of carboxylic acids, the acids are transferred from aqueous phase to organic solvent due to physical and chemical interactions. The acids and the extractant form complexes which are soluble in the organic phase. The extraction efficiency is affected by many factors, for instance initial acid concentration, type and concentration of the extractant, pH, temperature and extraction time. In this paper, the effects of initial acid concentration, type of extractant and temperature on extraction efficiency were studied. As carboxylic acids are usually the products of the processes, they are wanted to be recovered. Hence the acids have to be removed from the organic phase after the extraction. The removal of acids from the organic phase also regenerates the extractant which can be then recycled in the process. The regeneration of the extractant was studied by back-extracting i.e. stripping the acids form the organic solution into diluent sodium hydroxide solution. In the solvent regeneration, the regenerability of different extractants and the effect of initial acid concentration and temperature were studied.

Negative refractive index materials and propagation

Negative refractive index materials and propagation of electromagnetic waves in them started to draw attention of scientists not so long ago. This review highlights historically important and recent papers on practical and theoretical aspects related to these issues. Namely, basic properties and peculiarities of such materials related to both their design and wave propagation in them, experimental verification of predictions theoretically made for them, possible practical applications and prospects in this area are considered.

Tavanomaisen irtaimen esineen sale and lease back -järjestely. Tarkastelussa erityisesti vuokralleottajan sivullissuoja.

Tutkielman aiheena on tavanomaisen irtaimen esineen sale and lease back -järjestely. Järjestelyyn kuuluu nimensä mukaisesti luovutus ja takaisinvuokraus. Kokonaisjärjestelyn avulla rahoittaja ja luotonsaaja pyrkivät luomaan luotonmaksun vakuudeksi omistusoikeuteen perustuvan esinevakuuden. Järjestelyn tavoitteena on, että luotonsaajan asemassa oleva myyjä pystyisi käyttämään samaa esinettä samanaikaisesti sekä va-kuusobjektina että elinkeinotoimintansa tuotantovälineenä. Juuri siitä syystä, että luo-tonsaaja tarvitsee esinettä koko ajan elinkeinotoiminnassaan, ei panttausta voida käyttää. Tutkielma on oikeusdogmaattinen ja sen pyrkimyksenä on antaa selkeä kokonaiskäsitys irtaimen esineen sale and lease back -järjestelystä ja sen käytettävyydestä vakuusjärjestelynä. Oikeusdogmaattiselle tutkimukselle tyypillisesti tutkielmassa tarkastellaan olemassa olevaa tietomateriaalia. Keskeisimmät tutkielmassa käytetyt kirjallisuuslähteet ovat Jarno Teporan useat sale and lease back -järjestelyyn keskittyvät artikkelit, Jarmo Tuomiston omistusvakuuksia koskeva kirjallisuus sekä Erkki Havansin esineoikeudellinen perusteos Esinevakuudet. Virallislähteistä selvästi merkittävimmät ovat vuonna 1997 voimaantullut maakaari ja sen esityöt. Tutkimuksessa keskitytään erityisesti vuokralleottajan sivullissuojaan. Näin ollen tärkeimmäksi tutkimuskysymykseksi jäsentyy se, voiko sale and lease back -järjestelyssä ostajan roolissa oleva sijoittaja tai rahoittaja saavuttaa järjestelyn avulla kollisiotilanteiden varalta turvaavan vakuusaseman. Tutkimuksen kannalta keskeinen omistusvakuus-järjestely on vakuusluovutus, jollaiseksi vakuustarkoituksessa tehty sale and lease back -järjestely melko vakiintuneesti tulkitaan. Tutkimuksessa tarkastellaan mahdollisuutta hyväksyä sale and lease back -järjestely rahoittajalle dynaamista kollisiosuojaa tarjoavaksi vakuusjärjestelyksi ilman julkivarmistusta. Toisaalta selvitetään julkivarmistuksen toteuttamisen mahdollisuutta ilman hallinnansiirtoa muun muassa maakaaren 14:4.1:n 1 kohdan mukaisen kirjaamisen avulla. Nykylainsäädännön puitteissa järjestelyn hyväksyminen itsenäiseksi omistusvakuudeksi näyttää olevan epätodennäköistä ja ilman julkivarmistusta dynaaminen sivullissuoja jää saavuttamatta, vaikka järjestely on sitova inter partes. Tutkimuksen loppupäätelmissä pohditaan, voisiko sale and lease back -järjestelyyn liittyviä ongelmia ratkaista muuttamalla voimassa olevaa lainsäädäntöä tai antamalla täysin uutta lainsäädäntöä. Asiaa pohditaan myös oikeusvertailun keinoin selvittäen muiden Pohjoismaiden sekä Saksan oikeusjärjestelmien kantaa järjestelyyn.