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.

Operational Reliability Analysis of a Three-Tiered Thin-Client ERP-system in an International Corporate Environment

Internationalization and the following rapid growth have created the need to concentrate the IT systems of many small-to-medium-sized production companies. Enterprise Resource Planning systems are a common solution for such companies. Deployment of these ERP systems consists of many steps, one of which is the implementation of the same shared system at all international subsidiaries. This is also one of the most important steps in the internationalization strategy of the company from the IT point of view. The mechanical process of creating the required connections for the off-shore sites is the easiest and most well-documented step along the way, but the actual value of the system, once operational, is perceived in its operational reliability. The operational reliability of an ERP system is a combination of many factors. These factors vary from hardware- and connectivity-related issues to administrative tasks and communication between decentralized administrative units and sites. To accurately analyze the operational reliability of such system, one must take into consideration the full functionality of the system. This includes not only the mechanical and systematic processes but also the users and their administration. All operational reliability in an international environment relies heavily on hardware and telecommunication adequacy so it is imperative to have resources dimensioned with regard to planned usage. Still with poorly maintained communication/administration schemes no amount of bandwidth or memory will be enough to maintain a productive level of reliability. This thesis work analyzes the implementation of a shared ERP system to an international subsidiary of a Finnish production company. The system is Microsoft Dynamics Ax, currently being introduced to a Slovakian facility, a subsidiary of Peikko Finland Oy. The primary task is to create a feasible base of analysis against which the operational reliability of the system can be evaluated precisely. With a solid analysis the aim is to give recommendations on how future implementations are to be managed.

Prediction in transformed images

The study is related to lossless compression of greyscale images. The goal of the study was to combine two techniques of lossless image compression, i.e. Integer Wavelet Transform and Differential Pulse Code Modulation to attain better compression ratio. This is an experimental study, where we implemented Integer Wavelet Transform, Differential Pulse Code Modulation and an optimized predictor model using Genetic Algorithm. This study gives encouraging results for greyscale images. We achieved a better compression ration in term of entropy for experiments involving quadrant of transformed image and using optimized predictor coefficients from Genetic Algorithm. In an other set of experiments involving whole image, results are encouraging and opens up many areas for further research work like implementing Integer Wavelet Transform on multiple levels and finding optimized predictor at local levels.

Flash Memory Cells Reliability Parameters Investigation

The present work is a part of the large project with purpose to qualify the Flash memory for automotive application using a standardized test and measurement flow. High memory reliability and data retention are the most critical parameters in this application. The current work covers the functional tests and data retention test. The purpose of the data retention test is to obtain the data retention parameters of the designed memory, i.e. the maximum time of information storage at specified conditions without critical charge leakage. For this purpose the charge leakage from the cells, which results in decrease of cells threshold voltage, was measured after a long-time hightemperature treatment at several temperatures. The amount of lost charge for each temperature was used to calculate the Arrhenius constant and activation energy for the discharge process. With this data, the discharge of the cells at different temperatures during long time can be predicted and the probability of data loss after years can be calculated. The memory chips, investigated in this work, were 0.035 μm CMOS Flash memory testchips, designed for further use in the Systems-on-Chips for automotive electronics.

Effects of modern variable frequency drive on the reliability of an old crane induction motor

The work aims to analyze the possibilities of utilizing old crane driving AC induction motors in modern pulse-width-modulated variable frequency drives. Bearing currents and voltage stresses are the two main problems associated with modern IGBT inverters, and they may cause premature failure of an old induction motor. The origins of these two problems are studied. An analysis of the mechanism of bearing failure is proposed. Certain types of bearing currents are considered in detail. The most effective and economical means are chosen for bearing currents mitigation. Transient phenomena of cables and mechanism of over voltages occurring at motor terminals are studied in the work. The weakest places of the stator winding insulation system are shown and recommendations are given considering the mitigation of voltage stresses. Only the most appropriate and cost effective preventative methods are chosen for old motor drives. Rewinding of old motors is also considered.

Reliability analysis of medium voltage feeder

Distribution companies are facing numerous challenges in the near future. Regulation defines correlation between power quality and revenue cap. Companies have to take measures for reliability increase to successfully compete in modern conditions. Most of the failures seen by customers originate in medium voltage networks. Implementation of network automation is the very effective measure to reduce duration and number of outages, and consequently, outage costs. Topic of this diploma work is study of automation investments effect on outage costs and other reliability indices. Calculation model have been made to perform needed reliability calculations. Theoretical study of different automation scenarios has been done. Case feeder from actual distribution company has been studied and various renovation plans have been suggested. Network automation proved to be effective measure for increasing medium voltage network reliability.

Eliminating Software Failures - A Literature Survey

Software faults are expensive and cause serious damage, particularly if discovered late or not at all. Some software faults tend to be hidden. One goal of the thesis is to figure out the status quo in the field of software fault elimination since there are no recent surveys of the whole area. Basis for a structural framework is proposed for this unstructured field, paying attention to compatibility and how to find studies. Bug elimination means are surveyed, including bug knowhow, defect prevention and prediction, analysis, testing, and fault tolerance. The most common research issues for each area are identified and discussed, along with issues that do not get enough attention. Recommendations are presented for software developers, researchers, and teachers. Only the main lines of research are figured out. The main emphasis is on technical aspects. The survey was done by performing searches in IEEE, ACM, Elsevier, and Inspect databases. In addition, a systematic search was done for a few well-known related journals from recent time intervals. Some other journals, some conference proceedings and a few books, reports, and Internet articles have been investigated, too. The following problems were found and solutions for them discussed. Quality assurance is testing only is a common misunderstanding, and many checks are done and some methods applied only in the late testing phase. Many types of static review are almost forgotten even though they reveal faults that are hard to be detected by other means. Other forgotten areas are knowledge of bugs, knowing continuously repeated bugs, and lightweight means to increase reliability. Compatibility between studies is not always good, which also makes documents harder to understand. Some means, methods, and problems are considered method- or domain-specific when they are not. The field lacks cross-field research.

The Effect of Operational Disturbances on Reliability and Operation Time Distribution of NCmachine Tools in FMS

This thesis concentrates on studying the operational disturbance behavior of machine tools integrated into FMS. Operational disturbances are short term failures of machine tools which are especially disruptive to unattended or unmanned operation of FMS. The main objective was to examine the effect of operational disturbances on reliability and operation time distribution for machine tools. The theoretical part of the thesis covers the fimdamentals of FMS relating to the subject of this study. The concept of FMS, its benefits and operator's role in FMS operation are reviewed. The importance of reliability is presented. The terms describing the operation time of machine tools are formed by adopting standards and references. The concept of failure and indicators describing reliability and operational performance for machine tools in FMSs are presented. The empirical part of the thesis describes the research methodology which is a combination of automated (ADC) and manual data collection. By using this methodology it is possible to have a complete view of the operation time distribution for studied machine tools. Data collection was carried out in four FMSs consisting of a total of 17 machine tools. Each FMS's basic features and the signals of ADC are described. The indicators describing the reliability and operation time distribution of machine tools were calculated according to collected data. The results showed that operational disturbances have a significant influence on machine tool reliability and operational performance. On average, an operational disturbance occurs every 8,6 hours of operation time and has a down time of 0,53 hours. Operational disturbances cause a 9,4% loss in operation time which is twice the amount of losses caused by technical failures (4,3%). Operational disturbances have a decreasing influence on the utilization rate. A poor operational disturbance behavior decreases the utilization rate. It was found that the features of a part family to be machined and the method technology related to it are defining the operational disturbance behavior of the machine tool. Main causes for operational disturbances were related to material quality variations, tool maintenance, NC program errors, ATC and machine tool control. Operator's role was emphasized. It was found that failure recording activity of the operators correlates with the utilization rate. The more precisely the operators record the failure, the higher is the utilization rate. Also the FMS organizations which record failures more precisely have fewer operational disturbances.

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.

Delivery Reliability: Timely and Quantitative Accuracy in a Forest Industry Company

The primary objective of this thesis was to research delivery reliability of mill business unit of a forest industry company, especially timely and quantitative accuracy of sales orders. Delivery reliability is an important factor of customer satisfaction, which has a great influence for success of a company. The secondary objective was to find out reasons for possible problems of delivery reliability and give propositions for improvable performances. The empirical part of the thesis based on reporting database of the forest industry company’s ERP-software and detailed information of the mill system. The delivery reliability results of the mill business unit were compared to delivery reliability of similar mill business unit inside the forest industry company. The research results expressed problems in the supply chain. The delivery reliability reporting should be also developed further. This would advance delivery reliability monitoring. The improvement propositions of the thesis were logistic operation mode estimation, particular benchmarking of the compared mill business unit and more detailed survey on production delivery reliability.

Kompressoriyksiköiden mekaaninen kunnonhallinta

Kunnossapidon kuluista suurimman osan aiheuttavat koneiden ennakoimattomat rikkoutumiset ja niiden tuomat tuotannonpysäytykset. Kunnossapidon suunnitelmallisuutta ja vikojen ennustettavuutta pyritään parantamaan erilaisin kunnonvalvonnallisin keinoin. Havaitsemalla alkava vikaantuminen ajoissa ja seuraamalla sen kehittymistä luodaan mahdollisuus korjaustoimenpiteiden ja -ajankohdan hallittuun suunnitteluun ja tätä kautta kustannussäästöihin. Tässä työssä on tutkittu kompressoriyksiköiden (kaasuturbiini ja keskipakokompressori) ja niiden apulaitteiden kunnossapidon menetelmiä, niiden hyödynnettävyyttä sekä mahdollisuuksia kehittää mekaanista kunnonhallintaa. Työssä päädyttiin johtopäätökseen, että käytettävien menetelmien hyödynnettävyydessä on kehitettävää. Kunnonvalvonnan ohjeistuksia tarkennettiin vastaamaan tämän päivän tavoitteita. Todettiin myös, että värähtelynvalvontaan perustuva kunnonvalvontajärjestelmä soveltuu hyvin kompressoriyksiköiden kunnonvalvonnan järjestelmäksi. Värähtelynvalvontaan perustuva kunnonvalvontajärjestelmä luo mahdollisuuden turvallisen käyttöajan ennustamiseen. Kunnonvalvonnan kehittämisen ja käyttövarmuuden parantamisen kannalta jatkotutkimuksen tekeminen kompressoriyksiköiden mekaanistenlaitteiden turvallisen käyttöajan ennustamiseksi on perusteltua.