Stock market prediction has been a hot topic lately due to advances in computer technology and economics. One economic theory, called Efficient Market Hypothesis (EMH), states that all known information is already factored into the prices which makes it impossible to predict the stock market. Despite the EMH, many researchers have been successful in predicting the stock market using neural networks on historical data. This thesis investigates stock prediction using both linear regression and neural networks (NN), with a twist. The inputs to the proposed methods are a number of profit predictions calculated with stochastic methods such as generalized autoregressive conditional heteroskedasticity (GARCH) and autoregressive integrated moving average (ARIMA). By contrast the traditional approach was instead to use raw data as inputs. The proposed methods show superior result in yielding profit: at best 1.1% in the Swedish market and 4.6% in the American market. The neural network yielded more profit than the linear regression model, which is reasonable given its ability to find nonlinear patterns. The historical data was used with different window sizes. This gives a good understanding of the window size impact on the prediction performance.

Philosophiae Doctor - PhD / This chapter outlines basic gene structure and how gene structure is related to promoter structure in both prokaryotes and eukaryotes and their transcription machinery. An in-depth discussion is given on variations types of the promoters among both prokaryotes and eukaryotes and as well as among three prokaryotic organisms namely, E.coli, B.subtilis and Mycobacteria with emphasis on Mituberculosis. The simplest definition that can be given for a promoter is: It is a segment of Deoxyribonucleic Acid (DNA) sequence located upstream of the 5' end of the gene where the RNA Polymerase enzyme binds prior to transcription (synthesis of RNA chain representative of one strand of the duplex DNA). However, promoters are more complex than defined above. For example, not all sequences upstream of genes can function as promoters even though they may have features similar to some known promoters (from section 1.2). Promoters are therefore specific sections of DNA sequences that are also recognized by specific proteins and therefore differ from other sections of DNA sequences that are transcribed or translated. The information for directing RNA polymerase to the promoter has to be in section of DNA sequence defining the promoter region. Transcription in prokaryotes is initiated when the enzyme RNA polymerase forms a complex with sigma factors at the promoter site. Before transcription, RNA polymerase must form a tight complex with the sigma/transcription factor(s) (figure 1.1). The 'tight complex' is then converted into an 'open complex' by melting of a short region of DNA within the sequence involved in the complex formation. The final step in transcription initiation involves joining of first two nucleotides in a phosphodiester linkage (nascent RNA) followed by the release of sigma/transcription factors. RNA polymerase then continues with the transcription by making a transition from initiation to elongation of the nascent transcript.

Artificial neural networks (ANNs) are used in many types of computing applications. Traditionally, ANNs have been implemented in software, executing on CPUs and even GPUs, which capitalize on the parallelizable nature of ANNs. More recently, FPGAs have become a target platform for ANN implementations due to their relatively low cost, low power, and flexibility. Some safety-critical applications could benefit from ANNs, but these applications require a certain level of reliability. SRAM-based FPGAs are sensitive to single-event upsets (SEUs), which can lead to faults and errors in execution. However there are techniques that can mask such SEUs and thereby improve the overall design reliability. This thesis evaluates the SEU reliability of neural networks implemented in SRAM-based FPGAs and investigates mitigation techniques against upsets for two case studies. The first was based on the LeNet-5 convolutional neural network and was used to test an implementation with both fault injection and neutron radiation experiments, demonstrating that our fault injection experiments could accurately evaluate SEU reliability of the networks. SEU reliability was improved by selectively applying TMR to the most critical layers of the design, achieving a 35% improvement reliability at an increase in 6.6% resources. The second was an existing neural network called BNN-PYNQ. While the base design was more sensitive to upsets than the CNN previous tested, the TMR technique improved the reliability by approximately 7× in fault injection experiments.

Designing object-oriented software is hard, and designing reusable object-oriented software is even harder. This task is even more daunting for a developer of computational intelligence applications, as optimising one design objective tends to make others inefficient or even impossible. Classic examples in computer science include ‘storage vs. time’ and ‘simplicity vs. flexibility.’ Neural network requirements are by their very nature very tightly coupled – a required design change in one area of an existing application tends to have severe effects in other areas, making the change impossible or inefficient. Often this situation leads to a major redesign of the system and in many cases a completely rewritten application. Many commercial and open-source packages do exist, but these cannot always be extended to support input from other fields of computational intelligence due to proprietary reasons or failing to fully take all design requirements into consideration. Design patterns make a science out of writing software that is modular, extensible and efficient as well as easy to read and understand. The essence of a design pattern is to avoid repeatedly solving the same design problem from scratch by reusing a solution that solves the core problem. This pattern or template for the solution has well understood prerequisites, structure, properties, behaviour and consequences. CILib is a framework that allows developers to develop new computational intelligence applications quickly and efficiently. Flexibility, reusability and clear separation between components are maximised through the use of design patterns. Reliability is also ensured as the framework is open source and thus has many people that collaborate to ensure that the framework is well designed and error free. This dissertation discusses the design and implementation of a generic neural network framework that allows users to design, implement and use any possible neural network models and algorithms in such a way that they can reuse and be reused by any other computational intelligence algorithm in the rest of the framework, or any external applications. This is achieved by using object-oriented design patterns in the design of the framework. / Dissertation (MSc)--University of Pretoria, 2007. / Computer Science / unrestricted

Power grids have rapidly evolved into Smart grids and are heavily dependent on Supervisory Control and Data Acquisition (SCADA) systems for monitoring and control. However, this evolution increases the susceptibility of the remote (VMs, VPNs) and physical interfaces (sensors, PMUs LAN, WAN, sub-stations power lines, and smart meters) to sophisticated cyberattacks. The continuous supply of power is critical to power generation plants, power grids, industrial grids, and nuclear grids; the halt to global power could have a devastating effect on the economy's critical infrastructures and human life. Machine Learning and Deep Learning-based cyberattack detection modeling have yielded promising results when combined as a Hybrid with an Intrusion Detection System (IDS) or Host Intrusion Detection Systems (HIDs). This thesis proposes two cyberattack detection techniques; one that leverages Machine Learning algorithms and the other that leverages Artificial Neural networks algorithms to classify and detect the cyberattack data held in a foundational dataset crucial to network intrusion detection modeling. This thesis aimed to analyze and evaluate the performance of a Hybrid Machine Learning (ML) and a Hybrid Deep Learning (DL) during ingress packet filtering, class classification, and anomaly detection on a Smart grid network.

This study proposes a performance comparison between machine learning regression algorithms and Artificial Neural Network (ANN). The regression algorithms used in this study are Multiple linear, Least Absolute Selection Operator (Lasso), Ridge, Random Forest. Moreover, this study attempts to analyse the correlation between variables to determine the most important factors that affect house prices in Malmö, Sweden. There are two datasets used in this study which called public and local. They contain house prices from Ames, Iowa, United States and Malmö, Sweden, respectively.The accuracy of the prediction is evaluated by checking the root square and root mean square error scores of the training model. The test is performed after applying the required pre-processing methods and splitting the data into two parts. However, one part will be used in the training and the other in the test phase. We have also presented a binning strategy that improved the accuracy of the models.This thesis attempts to show that Lasso gives the best score among other algorithms when using the public dataset in training. The correlation graphs show the variables' level of dependency. In addition, the empirical results show that crime, deposit, lending, and repo rates influence the house prices negatively. Where inflation, year, and unemployment rate impact the house prices positively.

A sudden extreme change in the weather can result in significant impact onthe life system in the present-day scenario. A well-planned prediction for damage during extreme weather conditions can have minimal impact on the grid components and efficient response and recovery models. With technology advancements and innovation in smart grid technologies we can now have accesses to uninterrupted power supply with smart utilization of energy and reduce CO2 emissions. Artificial Intelligence plays a vital role insolving present day power issues. Large amounts of data and rapid usage of computational power has accelerated to use machine learning models topredict and forecast the energy demand. Hence this study aims to determine how machine learning will improve the microgrid operation at Tezpur University. The main application areas studied in this thesis are identified as demand and load forecasting, simulating Photovoltaic (PV)production in a Microgrid and power outages. This thesis is aimed to develop and compare different ML algorithms to test validate and predict the PV production, energy demand and power outages.

Disertační práce se zabývá metodami a prostředky pro hodnocení kvality obrazu ve videosekvencích, což je velmi aktuální téma, zažívající velký rozmach zejména v souvislosti s digitálním zpracováním videosignálů. Přestože již existuje relativně velké množství metod a metrik pro objektivní, tedy automatizované měření kvality videosekvencí, jsou tyto metody zpravidla založeny na porovnání zpracované (poškozené, například komprimací) a originální videosekvence. Metod pro hodnocení kvality videosekvení bez reference, tedy pouze na základě analýzy zpracovaného materiálu, je velmi málo. Navíc se takové metody převážně zaměřují na analýzu hodnot signálu (typicky jasu) v jednotlivých obrazových bodech dekódovaného signálu, což je jen těžko aplikovatelné pro moderní komprimační algoritmy jako je H.264/AVC, který používá sofistikovené techniky pro odstranění komprimačních artefaktů. V práci je nejprve podán stučný přehled dostupných metod pro objektivní hodnocení komprimovaných videosekvencí se zdůrazněním rozdílného principu metod využívajících referenční materiál a metod pracujících bez reference. Na základě analýzy možných přístupů pro hodnocení video sekvencí komprimovaných moderními komprimačními algoritmy je v dalším textu práce popsán návrh nové metody určené pro hodnocení kvality obrazu ve videosekvencích komprimovaných s využitím algoritmu H.264/AVC. Nová metoda je založena na sledování hodnot parametrů, které jsou obsaženy v transportním toku komprimovaného videa, a přímo souvisí s procesem kódování. Nejprve je provedena úvaha nad vlivem některých takových parametrů na kvalitu výsledného videa. Následně je navržen algoritmus, který s využitím umělé neuronové sítě určuje špičkový poměr signálu a šumu (peak signal-to-noise ratio -- PSNR) v komprimované videosekvenci -- plně referenční metrika je tedy nahrazována metrikou bez reference. Je ověřeno několik konfigurací umělých neuronových sítí od těch nejjednodušších až po třívrstvé dopředné sítě. Pro učení sítí a následnou analýzu jejich výkonnosti a věrnosti určení PSNR jsou vytvořeny dva soubory nekomprimovaných videosekvencí, které jsou následně komprimovány algoritmem H.264/AVC s proměnným nastavením kodéru. V závěrečné části práce je proveden rozbor chování nově navrženého algoritmu v případě, že se změní vlastnosti zpracovávaného videa (rozlišení, střih), případně kodéru (formát skupiny současně kódovaných snímků). Chování algoritmu je analyzováno až do plného vysokého rozlišení zdrojového signálu (full HD -1920 x 1080 obrazových bodů).

The dissertation is generally focused on the use of artificial intelligence tools in practice and with regard to the focus of study in the field of Management and Business Economics at using the tools of artificial intelligence in corporate practice, as a tool for decision support at the operational and tactical level management. In the narrower sense, the task deals with the proposal of the prediction sales model of selected food commodities. The proposed model is designed to serve as a substitute for a human expert in support decision-making process in the purchase of selected commodities, especially when training new staff and extend the currently used methods of managerial decision-making about artificial intelligence tools for company management and existing employees. The aim of this dissertation is the design prediction sales model of selected food commodities (apples and potatoes) for specific wholesale of fruit and vegetable operating in the Czech Republic. To become familiar with the behaviour of selected commodities were used primary and secondary research as well and knowledge gained from Czech and foreign literature sources and research. The resulting predictive model is developed using statistical analysis of time series and the sales prediction proceeds using the tools of artificial intelligence and is modeled by an artificial neural network. The dissertation in the practical part also contains proposals for the use of the prediction model and partial processing procedures for: • practice, • theory, • pedagogical activities.

No description available.