1,720,996 research outputs found
SandP500 index stock ranking algorithm development and testing.
No full textInvestors in stock markets are searching for computer software tools to analyze and rank stocks to make investment decisions. The analysis tools fall into two main groups: tools for fundamental analysis and tools for technical analysis of stock. In the current paper the author is looking for ways to combine fundamental and technical analysis to make better investment recommendations. Special emphasis is on money management rules used to open positions, calculate position size for each stock and overall portfolio value. Author also explains how to apply money management rules to not lose money in the markets. The object of this paper is S&P500 index stock ranking algorithms. The aim of the paper is to develop and test new stock ranking algorithms based on both technical and fundamental indicators. Money management rules is also a critical part selecting stocks and creating stock portfolios. In part 1 of the paper the reasons why each investor should you use both fundamental and technical analysis in his or her trading, and the importance of proper money management is explained. Author also writes about advantages using system trading instead of discretional trading. In part 2 of the paper the expert system is described. In part 3 of the paper the expert system is tested by analyzing S&P500 index stock and making trading decisions to form a stock portfolio. The expert system was tested for two weeks after is has been completed. Results of the system testing are analyzed and explained. This MBA paper consists of introduction, three parts, conclusion and annexes. The material is discussed in 65 pages, including 8 tables and 58 pictures, and 4 annexes
Modelling and investigation of control system for glucose level in blood.
No full textThe aim of Master’s thesis is to perform a modelling and investigation of control system for glucose level in blood. The paper provides an overview of the glucose concentration control system, development of control system and model predictive control methodology, describes the main aspects of simulation model development, process control algorithms. MATLAB / SIMULINK program package is selected for control system implementation. PI control algorithms and model predictive controller methodology have been applied to simulate the simulation model. Parameters of the glucose-insulin interaction model transfer function, which are further used for PI controller alignment, are identified from the jump transition curve using step function method. Finally, the quality/performance of the control of the MPC and PI controllers was compared to the different controllers sampling steps. The result of the system is presented in Master’s thesis
Modernization of water level control system in boiler.
No full textThe Master's thesis examines the equipment used in steam boiler rooms and control systems of water level in steam boilers. As the modern steam boilers are of relatively small volume and high pressure, the water level tends to rise with an increase of load in the steam boiler. A sudden removal of steam may cause the water level to fall sharply in the steam boiler. Low water level in a steam boiler can lead to pipe rupture, and thereby damage it. Therefore, water level in steam boilers is a critical element of system management. In order to ensure a reliable, safe and efficient operation of a steam boiler, the present paper analyses and proposes the strategies of water level control. Modelling has shown that the water level in the steam boilers without the disturbance compensation system is maintained with large fluctuations. The simulation results showed that the most appropriate strategy is the three measuring elements' strategy with the disturbance compensation system. This system maintains the water level within the given limits and reduces the volatility of water in the steam boiler. For steam boilers modernization, the Siemens 1200 programmable logic controller which is designed for the control of technological processes of a steam boiler has been chosen. The logic controller maintains a constant water level in the steam boiler by regulating the actuator according to an outgoing steam flow from the boiler, incoming feed water stream and the existing water level in the steam boiler
Application of self-organizing neural networks to corporate securities analysis.
No full textThe paper provides an overview of artificial intelligence methods applications in finance. The method of self-organizing neural networks (SOM) and the application of this method for the analysis of financial markets and securities is more widely explored. Software for SOM implementation is presented. Research methodology is provided. The created scheme is presented for the selection of company securities and portfolio formation through SOM. The four-month market monitoring survey suggests that the chosen clustering algorithm with the SOM allows for a good forecast of the evolution of financial markets
Monitoring of Pedestrian Traffic Using Hierarchical Temporal Memory Algorithms.
No full textThe main purpose of this paper is to investigate the application of Hierarchical Temporal Memory (HTM) mechanism for pedestrian traffic calculation in a public places using WEB cameras. The proposed approach distinguishes humans from other objects in a current video frame, identifies the movement in both directions and calculates balance of the pedestrians’ traffic. The proposed methodic can be used even for wider passage-ways. As a result, all people entering and leaving room can be counted and information about pedestrian-traffic can be acquired in real time. This information is very useful for further traffic monitoring and can be used for various tasks
Modernization of control system for air compressor in ammonia plant.
No full textIn the bachelor's thesis the existing air compressor automation control systems are analysed and then a modernization of automatic control system is proposed. This system includes modern controller which replays existing relays. In the thesis the operation of air compressor system is analysed and revised scheme is presented in details. Selection of the required elements for newly developed automation control system is presented. Designed modernized automation control panel, system elements and selected mounting location are given. MATLAB/ Simulink software package is used to model the chosen control system. The parameters of selected controller type (PID) are determined. Then the system is tested for set-point changes and disturbances and the best controller is suggested to use in the control system
Development of modeling environment for bioprecesses analysis and investigation.
No full textIn this work there is conducted analysis of the literature about technological peculiarities of important biotechnological processes (yeast growing, E.coli bacteria and mammalian cells culture) and mathematical modelling principles of these processes. It is presented yeast classification, phases of their growth and the mathematical model. It is analysed aspects of E.coli bacteria culture, biology of bacteria and mathematical model of growth. It is described biotechnological processes of mammalian cells growing and mathematical modelling of these processes. It is presented classification of the bioreactors. Mathematical models of culturing all three cultures are implemented in the Matlab/Simulink environment. For the realization of each above-mentioned model it is created a user-friendly graphical interface. It is made schemes for the regulation of important culture process variables, which allows modelling various culture regimes for the user oneself. Model of yeast growing process is used for regulating dissolved oxygen concentration in the medium, changing the coefficient of the mass transfer from gaseous to the liquid (by manipulating the air flow and the stirrer speed). E.coli growing process model is used to illustrate the control principle of glucose concentration in the reactor while changing glucose feeding stream. Process model of growing mammalian cells is used for regulation of glutamine concentration in the medium while changing glutamine feeding stream. Results of modelling are presented under various culture conditions which can be chosen by the user. At the end of work there are presented results of the work and conclusions
Akcijų kainų kitimo rangavimo metodas vertybinių popierių prekybos sistemose
Get PDFThe goal of this paper was to introduce a stock ranking method and to show how this method could be incorporated into stock trading systems. The proposed method analyses a large number of securities and rankes them according relative change in price during the defined interval of time. Then the values of ranks arc being normalized and assume the values from -1 to +1. The securities with ranking values close to -1 are good candidates for an investor portfolio, because these securities historically had shown a statistically significant price increase by the following days. The proposed method was tested using experimental data from US security markets. Two groups of securities (30 companies from Dow Jones Industrial Index and 292 companies from SP500 Index) were tested during time interval between 1992-2002. First investigations had shown efficiency of the proposed method. The stock’s rank indicator exhibits a mean reverting behavior. For the stocks with strong negative rank a positive stock price change in mean is followed. Furthermore, a negative stock price change on average is followed for the high ranked stocks. So these results contradict the statements of the effective market hypothesis and motivate the creating of stock trading systems, based on stock’s price rank. In this paper we analyze the usefulness of this method while applying it in a virtual stock trading system. The trading simulation is executed using historical data from USA stock market (1992-2002). The trading system has given significantly higher return. relative the benchmark (SP500 index). However, there are some practical problems that must be overcome if we arc going to apply the stock’s rank method in real stock trading process. The most important of these is the taxes rate during stock trading operations. In the paper we analyze the influence of taxes rate on the systems profit and we give some suggestions how to make this system more suitable for the practical applications.Straipsnyje nagrinėjamas autoriaus pasiūlytas akcijų kainų kitimo rangavimo metodas ir šio metodo taikymas vertybinių popierių prekybos sistemose. Atlikti eksperimentiniai tyrimai parodė, kad taikant siūlomą metodą istoriniams akcijų kainų kitimo duomenims įvertinti, virtualūs investavimo rezultatai ilgą laiką yra ženkliai geresni negu rinkos vidurkis. Taigi šie rezultatai prieštarauja efektyvios rinkos hipotezės teiginiams ir motyvuoja prekybos sistemų, pagrįstų akcijų kainų kitimo rangavimu, kūrimą ir eksperimentinius tyrimus. Straipsnyje analizuojami praktiniai šio metodo taikymo realioje rinkoje aspektai ir komisinių mokesčių už vertybinių popierių pirkimo-pardavimo operacijas dydžio įtaka investavimo rezultatams
Investigation of deep learning methods for volatility index prediction in stock markets.
No full textThe aim of this project is to analyze and investigate the possibilities of classical and deep learning methods to predict the market volatility index in stock markets. In this project, the methods and algorithms for forecasting the stock markets and the volatility index are analyzed. Classical ARMA / ARMAX / NARMA / NARMAX and deep learning models are applied to predict the change in VIX index for the following day and week, using VIX and other indices as model inputs. Experimental studies have shown that only a few models achieve sufficient accuracy to predict the interval of change in the VIX index (rising, stable, or falling) and the direction of change to be used as investment tools for investors or traders. It was also found that the mean absolute errors of the models are too high, so none of the developed deep learning models can be used as a reliable investment tool to predict the absolute value of the change in the VIX index
Multifunctional user interface for quadriplegics: development and investigation.
No full textThis dissertation presents a multifunctional user interface developed for people suffering from severe motor disabilities. The presented user interface can be used to input text, select real world objects and answer questions. Dissertation presents a detailed architecture of the developed system. Dissertation also presents novel algorithms that help to ensure system efficiency. Projection mapping user interface automatically detects tabletop objects and highlights them using projector. Efficient camera control algorithm helps to ensure the stability of computer vision algorithms. We present a cascade-based camera parameter control algorithm with automatic gain scheduling. Dissertation also contains a description of region based stereo matching algorithm. The algorithm is capable of processing images in real time on an embedded computer. Text input user interface uses a specialized text prediction algorithm that decreases text input time. Experiments were performed to demonstrate the benefits of the proposed algorithms. Developed user interface was evaluated using participant questionnaire and measuring task execution times
- …
