No description available.

Financial market forecasting is a challenging and complex task due to the sensitivity of the market to various factors such as political, economic, and social factors. However, recent advances in machine learning and computation technology have led to an increased interest in using deep learning for forecasting financial data. One the one hand, the famous efficient market hypothesis states that the market is so efficient that no one can consistently benefit from it, and the random walk theory suggests that asset prices are unpredictable based on historical data. On the other hand, previous research has shown that financial time series can be forecasted to some extent using artificial neural networks (ANNs). Despite being a relatively new addition to financial research with less study than the traditional models such as moving averages and linear regression models, ANNs have been shown to outperform the traditional models to some extent. Hence, considering the efficient market hypothesis and the random walk theory, there is a knowledge gap on whether neural networks can be used for financial time series prediction. This paper explores the use of ANNs, specifically recurrent neural networks, to predict financial time series data using a long short-term memory (LSTM) network model. The study will employ an experimental research strategy to construct and test an LSTM model to predict financial time series data, with the aim of examining its performance and evaluating it relative to other models and methods. For evaluating its performance, evaluation metrics are computed and the model is compared with a constructed simple moving average (SMA) model as well as other models in existing studies. The paper also explores the application and processing of transformed financial data, where it was found that achieving stationarity by data transformation was not necessary for the LSTM model to perform better. The study also found that the LSTM model outperformed the SMA model when hyperparameters were set to capture long-term dependencies. However, in the short-term, the SMA model outperformed the LSTM model.

The thesis deals with design of novel circuit structure suitable for hardware implementations of feedforward neural networks. The structure utilizes innovative data bus structure. The main contribution of the structure is in optimization of the utilization of implemented computing units. Proposed architecture is flexible and suitable for implementations of variety of feedforward neural network structures.

The goal of this project is to construct a machine learning algorithmthat improves over time. This was done by first constructing a datasetthat reflects real world messages, that would simulate receiving emailsfrom two different sources. The data set was constructed by combiningdata from two different online forums. Two application programminginterrfaces were used to collect and send data to the program. Thedataset was tested on 4 different methods where the best one would beused for the final product. The 4 different methods were: k-nearestneighbors, adaptive boosting, random forest and artificial neuralnetwork. All the above methods were tested and tuned to achieve the bestaccuracy. From the result it became clear that the artificial neuralnetwork outperformed the other methods by a large margin and would bemost suited for the final product. The final product was an algorithmthat would improve over time. This was achieved by using a feedback loopon the new data that was collected over time from the online forums. Ifthe algorithm was sure that a new datapoint was the right class it wouldincorporate it into the dataset and over time the dataset would growlarger and the algorithm would adapt to new data and trends. The finalresult became a growing dataset that started on a 1000 data points andended up at 8464 data points, where the total amount ofmisclassification ended up at 74.

Interpreting time varying phenomena is a key challenge in the capital markets. Time series analysis using autoregressive methods has been carried out over the last couple of decades, often with reassuring results. However, such methods sometimes fail to explain trends and cyclical fluctuations, which may be characterized by long-range dependencies or even dependencies between the input features. The purpose of this thesis is to investigate whether recurrent neural networks with LSTM-cells can be used to capture these dependencies, and ultimately be used as a complement for index trading decisions. Experiments are made on different setups of the S&P-500 stock index, and two distinct models are built, each one being an improvement of the previous model. The first model is a multivariate regression model, and the second model is a multivariate binary classifier. The output of each model is used to reason about the future behavior of the index. The experiment shows for the configuration provided that LSTM RNNs are unsuitable for predicting exact values of daily returns, but gives satisfactory results when used to predict the direction of the movement. / Att förstå och kunna förutsäga hur index varierar med tiden och andra parametrar är ett viktigt problem inom kapitalmarknader. Tidsserieanalys med autoregressiva metoder har funnits sedan årtionden tillbaka, och har oftast gett goda resultat. Dessa metoder saknar dock möjligheten att förklara trender och cykliska variationer i tidsserien, något som kan karaktäriseras av tidsvarierande samband, men även samband mellan parametrar som indexet beror utav. Syftet med denna studie är att undersöka om recurrent neural networks (RNN) med long short-term memory-celler (LSTM) kan användas för att fånga dessa samband, för att slutligen användas som en modell för att komplettera indexhandel. Experimenten är gjorda mot en modifierad S&P-500 datamängd, och två distinkta modeller har tagits fram. Den ena är en multivariat regressionsmodell för att förutspå exakta värden, och den andra modellen är en multivariat klassifierare som förutspår riktningen på nästa dags indexrörelse. Experimenten visar för den konfiguration som presenteras i rapporten att LSTM RNN inte passar för att förutspå exakta värden för indexet, men ger tillfredsställande resultat när modellen ska förutsäga indexets framtida riktning.

The process of data integration is an important part of the database field when it comes to database migrations and the merging of data. The research in the area has grown with the addition of machine learning approaches in the last 20 years. Due to the complexity of the research field, no go-to solutions have appeared. Instead, a wide variety of ways of enhancing database migrations have emerged. This thesis examines how well a learning-based solution performs for the semantic integration problem in database migrations. Two algorithms are implemented. One that is based on information retrieval theory, with the goal of yielding a matching result that can be used as a benchmark for measuring the performance of the machine learning algorithm. The machine learning approach is based on grouping data with agglomerative hierarchical clustering and then training a neural network to recognize patterns in the data. This allows making predictions about potential data correspondences across two databases. The results show that agglomerative hierarchical clustering performs well in the task of grouping the data into classes. The classes can in turn be used for training a neural network. The matching algorithm gives a high recall of matching tables, but improvements are needed to both receive a high recall and precision. The conclusion is that the proposed learning-based approach, using agglomerative hierarchical clustering and a neural network, works as a solid base to semi-automate the data integration problem seen in this thesis. But the solution needs to be enhanced with scenario specific algorithms and rules, to reach desired performance. / Dataintegrering är en viktig del inom området databaser när det kommer till databasmigreringar och sammanslagning av data. Forskning inom området har ökat i takt med att maskininlärning blivit ett attraktivt tillvägagångssätt under de senaste 20 åren. På grund av komplexiteten av forskningsområdet, har inga optimala lösningar hittats. Istället har flera olika tekniker framställts, som tillsammans kan förbättra databasmigreringar. Denna avhandling undersöker hur bra en lösning baserad på maskininlärning presterar för dataintegreringsproblemet vid databasmigreringar. Två algoritmer har implementerats. En är baserad på informationssökningsteori, som främst används för att ha en prestandamässig utgångspunkt för algoritmen som är baserad på maskininlärning. Den algoritmen består av ett första steg, där data grupperas med hjälp av hierarkisk klustring. Sedan tränas ett artificiellt neuronnät att hitta mönster i dessa grupperingar, för att kunna göra förutsägelser huruvida olika datainstanser har ett samband mellan två databaser. Resultatet visar att agglomerativ hierarkisk klustring presterar väl i uppgiften att klassificera den data som använts. Resultatet av matchningsalgoritmen visar på att en stor mängd av de matchande tabellerna kan hittas. Men förbättringar behöver göras för att både ge hög en hög återkallelse av matchningar och hög precision för de matchningar som hittas. Slutsatsen är att ett inlärningsbaserat tillvägagångssätt, i detta fall att använda agglomerativ hierarkisk klustring och sedan träna ett artificiellt neuronnät, fungerar bra som en basis för att till viss del automatisera ett dataintegreringsproblem likt det som presenterats i denna avhandling. För att få bättre resultat, krävs att lösningen förbättras med mer situationsspecifika algoritmer och regler.

Yes / Seeking efficient solutions to nonlinear boundary value problems is a crucial challenge in the mathematical modelling of many physical phenomena. A well-known example of this is solving the Biharmonic equation relating to numerous problems in fluid and solid mechanics. One must note that, in general, it is challenging to solve such boundary value problems due to the higher-order partial derivatives in the differential operators. An artificial neural network is thought to be an intelligent system that learns by example. Therefore, a well-posed mathematical problem can be solved using such a system. This paper describes a mesh free method based on a suitably crafted deep neural network architecture to solve a class of well-posed nonlinear boundary value problems. We show how a suitable deep neural network architecture can be constructed and trained to satisfy the associated differential operators and the boundary conditions of the nonlinear problem. To show the accuracy of our method, we have tested the solutions arising from our method against known solutions of selected boundary value problems, e.g., comparison of the solution of Biharmonic equation arising from our convolutional neural network subject to the chosen boundary conditions with the corresponding analytical/numerical solutions. Furthermore, we demonstrate the accuracy, efficiency, and applicability of our method by solving the well known thin plate problem and the Navier-Stokes equation.

Very limited research studies have been conducted to examine the behaviour of rubberised concrete (RuC) with nano silica (NS) and addressed the acoustic benefits of rubberised concrete. The current research investigates the effect of incorporating colloidal nano silica on the mechanical, thermal and acoustic properties of Rubberised concrete and compares them with normal concrete (NC). Two sizes of rubber were used RA (0.5 – 1.5 mm) and RB (1.5 – 3 mm). Fine aggregate was replaced with rubber at a ratio of 0%, 10%, 20% and 30% by volume, and NS is used as partial cement replacement by 0%, 1.5% and 3%. A constant water to cement ratio of 0.45 was used in all concrete mixes. Various properties of rubberised concrete, including the density, water absorption, the compressive strength, the flexural strength, splitting tensile strength and the drying shrinkage of samples was studied as well as thermal and acoustic properties. Experimental results of compressive strength obtained from this study together with collected comprehensive database from different sources available in the literature were compared to five existing models, namely Khatib and Bayomy- 99 model, Guneyisi-04 model, Khaloo-08 model, Youssf-16 model, and Bompa-17 model. To assess the quality of predictive models, influence of rubber content on the compressive strength is studied. An artificial neural network (ANN) models were developed to predict compressive strength of RuC using the same data used in the existing models. Three ANN sets namely ANN1, ANN2 and ANN3 with different numbers of hidden layer neurons were constructed. Comparison between the results given by the ANN2 model and the results obtained by the five existing predicted models were presented. A finite element approach is proposed for calculating the transmission loss of concrete, the displacement in the solid phase and the pressure in the fluid phase is investigated. The transmission loss of the 50mm concrete samples is calculated via the COMSOL environment, the results from the simulation show good agreement with the measured data. The results showed that, using up to 20% of rubber as fine aggregate with the addition of 3% NS can produce a higher compressive strength than the NC. Experimental results of this research indicate that incorporating nano silica into RuC mixes enhance sound absorption and thermal conductivity compared to normal concrete (NC) and rubberised concrete without nano silica. This work suggests that it is possible to design and manufacture concrete which can provide an improvement to conventional concrete in terms of the attained vibro-acoustic and thermal performance. / Libyan Ministry of Higher Education

Construction on problematic soils is challenging owing to the potential of volume changes due to variation of moisture content. Lime stabilisation can be used to treat problematic soils. The main drawbacks of lime addition to the clayey soils are the need for lengthy curing periods and relatively large quantities of lime for significant improvement and also loss in ductility. Using eco-friendly agricultural and industrial wastes, that can partially be substituted by the material responsible for greenhouse gases such as lime, can overcome these drawbacks and decrease global warming. In the current study, variables controlling the unconfined compressive strength of lime treated clay with a focus on assessing the effects of moisture content were investigated. Furthermore, the effects of adding agricultural waste (Dried Athel Leaves (DAL)) and industrial waste (Silica Fume (SF)) on hydromechanical properties of lime treated clay were assessed. The performance of the treated mixtures was examined based on results attained from unconfined compressive strength, swelling pressure and permeability. Specimens were treated with deferent percentages of lime and cured at different periods and temperatures to observe the strength behaviour. In oedometer tests, the specimens were prepared and tested immediately after compaction. The failure patterns were also studied to better understand the ultimate behaviour of lime stabilised clays. The appearance and presence of cementitious products were identified by using the scanning electron microscope and energy dispersive X-ray spectrometer techniques to elucidate their strength development. The findings indicated that the effect of moisture content is controlled by the clay content and unit weight. The addition of 7% lime to clay caused a remarkable increase in the unconfined compressive strength by 363%. The incorporation of 2% DAL and 5% SF within lime treated clay further increased the strength by 6% and 33% respectively after curing of 28 days at 20 °c in comparison with those attained by lime treatment only. The improvement of the strength of the lime­ treated clay augmented with both wastes continued in long term. Temperature and lime content have positive effects on the improvement of strength, however, increasing lime content to 11% negatively affected the strength of lime treated specimens with 2% DAL. The formation of cementitious products was observed in SEM images and detected quantitatively through EDS analysis. The results of the recorded oedometric tests for lime-DAL and lime-SF mixtures revealed that incorporation of the 2% DAL and 5% SF reduced the clay swelling pressures by 25% and 10% compared to that attained by lime treatment only resulting in total reductions of 93.6% and 68% from that recorded on untreated clay. In addition, the impermeable clay transformed into permeable material by adding DAL and SF. Of the two types of wastes considered in this research, DAL demonstrated more superior improving capability. A further study was conducted to develop ANN model based on collated laboratory data for the prediction of the UCS values of lime treated soils. The promising outcomes of this research suggest that the drawbacks of lime stabilisation can be overcome by the addition of agricultural and industrial wastes. Consequently, the findings attained could be considered in future practice standards with regards to the requirement of lime stabilisation. / Ministry of Higher Education and Scientific Research in Libya

Studies of animal spatial distributions typically use prior knowledge of animal habitat requirements and behavioral ecology to deduce the most likely explanations of observed habitat use. Animal-borne accelerometers can be used to distinguish behaviors which allows us to incorporate in situ behavior into our understanding of spatial distributions. Past research has focused on using supervised machine-learning, which requires a priori specification of behavior to identify signals whereas unsupervised approaches allow the model to identify as many signal types as permitted by the data. The following framework couples direct observation to behavioral clusters identified from unsupervised machine learning on a large accelerometry dataset. A behavioral profile was constructed to describe the proportion of behaviors observed per cluster and the framework was applied to an acceleration dataset collected from wild pigs (Sus scrofa). Although, most clusters represented combinations of behaviors, a leave-p-out validation procedure indicated this classification system accurately predicted new data.