Search

Showing total 6 results
Start Over Search Limiters Peer Reviewed Topic artificial neural networks Publication Type Electronic Resources
6 results

1. Forecasting foreign exchange rates and volatility with artificial neural networks

Author

Wang, Guan, ap Gwilym, Owain, and Vasilakis, Chrysovalantis

Subjects
332.4, foreign exchange rates, artificial neural networks, time series, technical trading
Abstract

The foreign exchange (FX) market is long established as the largest and most important global financial market. While a large number of research papers focus on forecasting in the FX market, there are still gaps in the literature. First, very few papers focus on improving the parameter estimation process in the forecasting context. Second, artificial neural networks (ANN) with large sizes have not been applied to FX forecasting with the recently fast-developed GPU techniques. Third, forecasting for trading purposes in the FX market has been limited to either building forecasting models or analysing technical indicators. A combination of ANN forecasting models with technical indicators is rare in the existing literature. The use of more accurate parameter estimation algorithms and GPU techniques also makes the thesis unique in the methodological sense. The thesis uses three types of ANN models, namely GARCH-ANN, large Multilayer Perceptron (MLPNN) and Long Short Term Memory (LSTM), to forecast volatility, the direction of price movements and price patterns in the FX market. Research is conducted at three data frequencies, namely monthly, daily and hourly as the analysis goes from the macro-perspective to the micro-perspective. In the first empirical chapter, a Recursive Simulation Algorithm (RSGA) is proposed for estimating the parameters of a volatility forecasting model using GARCH-ANN. The proposed algorithm significantly improves the stability and accuracy of the estimation process by dealing with the local-optimum and convergence problems. The second empirical chapter utilises a large MLPNN model with GPU implementation to forecast the price direction of different FX pairs, with over 40 macro-economic indicators as input variables. Highly profitable out-of-sample results are observed for some of the currency pairs, which challenges the semi-strong form of the Efficient Market Hypothesis (EMH). Significant efficiency improvement is achieved with the GPU implementation. The third empirical chapter proposes the use of the Relative Strength Indicator (RSI) as a measure of the extent of trend-following and mean-reversion patterns of FX rates. A LSTM modelis utilised to forecast price movement patterns (measured by RSI). The trading strategy based on forecasting results of price movement patterns generates more stable profits than the benchmark Moving Average (MA) or RSI implemented on their own. However, the overall low profitability over time for the four currency pairs fails to challenge the weak-form EMH. Overall, with the novel methodologies and technologies implemented within different models, this thesis finds evidence on some extent of inefficiency of the FX market at lower trading frequency (e.g. monthly) and less inefficiency of the FX market at higher trading frequency (e.g. hourly). One possible explanation is that at higher frequencies, the large number of daily (or higher frequency) traders and high-frequency trading algorithms reduce both the number of mis-pricing opportunities and the length of time that any mis-pricing opportunity may last.

Published
2021

2. Bioinformatics Applications Based On Machine Learning.

Author

Chamoso, Pablo, Chamoso, Pablo, González-Briones, Alfonso, Mohamad, Mohd, and Rodriguez, Sara

Subjects
Technology: general issues, Affective Computing, Arabidopsis thaliana, Artificial Neural Networks, CTX-M, Decision table, Harmony Search, Machine Learning, PART, Particle Swarm Optimization, Weka, bi-directional LSTM, bioinformatics, biological functions detection, classification, clinical data, clinical implications, cluster, computer vision, convolutional neural network, data mining, deep learning, derivative-free optimization, detection, diabetes, dynamic models, ear detection, epidemiology, evolutionary computation, evolutionary computing, feature selection, forecast, fuel cell, gene clustering, genetic programming, glycolysis, gradient boosting, hybrid systems, hydrogen energy, image recognition, informative genes, intelligent systems, machine learning, metabolism, metagenomics, metrics, mitochondrial protein, parameter estimation, personality assessment, plasmodium falciparum, power management, real-life patients, regression, swarm intelligence, transposable elements, video analysis, yeast
Abstract

Summary: The great advances in information technology (IT) have implications for many sectors, such as bioinformatics, and has considerably increased their possibilities. This book presents a collection of 11 original research papers, all of them related to the application of IT-related techniques within the bioinformatics sector: from new applications created from the adaptation and application of existing techniques to the creation of new methodologies to solve existing problems.

3. Assessment of Renewable Energy Resources with Remote Sensing.

Author

Martins, Fernando Ramos and Martins, Fernando Ramos

Subjects
Research & information: general, Baltic area, CSP plants, GES-CAL software, Hazaki Oceanographical Research Station, artificial neural networks, climate, cloud, cloud coverage, cloud detection, coastal wind measurements, coastline, computational design method, convection, data processing, digitized image processing, electrical resistivity tomography, extreme value analysis, feature engineering, feature importance, forecasting, geophysical prospecting, geothermal energy, global radiation, graphical user interface software, hydropower reservoir, image processing, lake breeze influence, light gradient boosting machine, machine learning, machine learning techniques, metaheuristic, multistep-ahead prediction, parameter extraction, passive design strategy, photovoltaic power plant, plan position indicator, point cloud data, potential well field location, remote sensing, remote sensing data acquisition, renewable energy resource assessment and forecasting, satellite, scanning LiDAR, scatterometer, shading envelopes, sky camera, smart island, solar energy, solar energy resource, solar irradiance enhancement, solar irradiance estimation, solar irradiance forecasting, solar photovoltaic, solar radiation forecasting, statistical analysis, surface solar radiation, time domain electromagnetic method, total sky imagery, velocity volume processing, voxel-design approach, whale optimization algorithm, wind speed
Abstract

Summary: The book "Assessment of Renewable Energy Resources with Remote Sensing" focuses on disseminating scientific knowledge and technological developments for the assessment and forecasting of renewable energy resources using remote sensing techniques. The eleven papers inside the book provide an overview of remote sensing applications on hydro, solar, wind and geothermal energy resources and their major goal is to provide state of art knowledge to contribute with the renewable energy resource deployment, especially in regions where energy demand is rapidly expanding. Renewable energy resources have an intrinsic relationship with local environmental features and the regional climate. Even small and fast environment and/or climate changes can cause significant variability in power generation at different time and space scales. Methodologies based on remote sensing are the primary source of information for the development of numerical models that aim to support the planning and operation of an electric system with a substantial contribution of intermittent energy sources. In addition, reliable data and knowledge on renewable energy resource assessment are fundamental to ensure sustainable expansion considering environmental, financial and energetic security.

4. Quantitative Methods in Economics and Finance.

Author

Kliestik, Tomas, Kliestik, Tomas, Kovacova, Maria, and Valaskova, Katarina

Subjects
Coins, banknotes, medals, seals (numismatics), AUD-USD exchange rate, American-type option, EBIT, International Valuation Standards (IVS), Monte Carlo simulation, RAROC, artificial neural networks, business finance, cost of sales, customer relationship management (CRM), Big Data, diffusion, earnings management, economic security of companies, exchange rate, exchange traded funds, exchange-rate risk, financial innovations, financial modelling, global economy, homogeneity, legal disputes over intellectual rights, loan origination, loan pricing, long-range dependency, multi-frequency analysis, multi-layer perceptron, omnichannel (omni-channel) sales, optimal stopping, prediction, radial basis function, robo-advisor, sales funnel, seasonal fluctuations, stationarity, stock index futures, stock index options, stock market indexes, time series, time series methods, unit root, valuation of intangible assets and intellectual property, wavelets, π-option
Abstract

Summary: The purpose of the Special Issue "Quantitative Methods in Economics and Finance" of the journal Risks was to provide a collection of papers that reflect the latest research and problems of pricing complex derivates, simulation pricing, analysis of financial markets, and volatility of exchange rates in the international context. This book can be used as a reference for academicians and researchers who would like to discuss and introduce new developments in the field of quantitative methods in economics and finance and explore applications of quantitative methods in other business areas.

5. Hot Deformation and Microstructure Evolution of Metallic Materials.

Author

Schindler, Ivo and Schindler, Ivo

Subjects
History of engineering & technology, Materials science, Technology: general issues, 47Zr-45Ti-5Al-3V alloy, Al-Cu alloys, Al6061, Barkhausen noise, CA, CCT diagram, DRX behavior, FE, FEM, FEM modelling, KoBo extrusion, LPSO phase, Mg-6.8Y-2.5Zn-0.4Zr, Nb-Mo-microalloyed steels, PSCT, SEM-EBSD microstructural analysis, activation energy at hot forming, activation energy maps, aircraft mounts, aluminium, aluminium alloys, aluminum alloy, artificial neural networks, austenite conditioning, austenite grain size, austenite to ferrite transformation, austenitization temperature, bonding strength, brake disk, car bodies, carbon steels, cellular automaton, closure of discontinuities, compression, constitutive equations, constitutive model, critical strain for induce of dynamic recrystallization, deformation, deformation characteristics, deformation mechanism, dynamic and post-dynamic softening, dynamic recrystallisation, dynamic recrystallization, extrusion, ferrite grain size, final microstructure and mechanical properties, finite element method (FEM), flat anvils, flow behavior, flow curve, flow stress maps, flow stress model, forging, forging metal specimens, forming, hammer forging, hidden defects, high-carbon bainitic steel, hot deformation behavior, hot flow stress curves, hot rolling, hot-rolling, hot-working, industrial research, low carbon and low alloy steel, low-alloy steel, magnesium alloy AZ91, magnesium alloys, mechanical properties, meshless methods, metal matrix composite, microstructure, microstructure and superplastic deformation, microstructure evolution, multipass torsion tests, n/a, open die forging, peak flow stress, peak strain, phase transformations, physical modeling, physical modelling, plastic deformation, plastometric tests, processing map, processing maps, radial basis functions, recrystallization, rheological properties, semi-solid isothermal compression, shaped anvils, static recrystallization, steel, strain-induced precipitation, stress correction, structure, super-duplex stainless steel (SDSS), tensile deformation, texture, thermal stability, thermomechanical processing, twin-roll casting, ultrasonic investigation, warm deformation, β titanium alloy
Abstract

Summary: Hot deformation is a key method of processing metallic materials and controlling their final properties through structure-forming processes. The ability to exploit the structural potentiality of both traditional alloys and new progressive materials is crucial in terms of sustainable development and economic growth. This reprint focuses not only on conventional technologies (e.g., rolling or forging) but also on modern procedures, such as various types of complex thermomechanical processing and controlled cooling. Most papers are based on the application of advanced hot deformation simulators and structural analysis methods, as well as computer simulations of bulk-forming processes.

6. Advances in Asphalt Pavement Technologies and Practices.

Author

Tabakovic, Amir, He, Liang, Tabakovic, Amir, and Valentin, Jan

Subjects
History of engineering & technology, Technology: general issues, AFM, Bayesian optimization, DSR, FTIR, Google Earth, Grouted Semi-flexible Pavement, International Roughness Index, J-integral, RSM, SBS modified asphalt, SMA, Saudi Arabia, Trinidad lake asphalt, additives, aged asphalt, artificial neural networks, asphalt concrete, asphalt mixture, asphalt pavement, asphalt pavements, base layers, bearing capacity, bitumen, bituminous mixtures, characteristic parameter, cigarette filters, coarse-grained, cold recycling, compaction quality control, comprehensive evaluation, construction control, correlation, crumb rubber asphalt (CR), cyclic triaxial test (CTT), degree of compaction, digital image correlation (DIC), dynamic creep, emulsified asphalt, evaluation method, extended finite element method, factor importance, falling weight deflectometer (FWD), fibers, flexible pavement, foamed asphalt, force field, full-scale pavement structure, high and low temperature performance, high-modulus asphalt mixture, hot mix asphalt, hot-mix recycled asphalt mixture, hybrid self-healing system, indirect tensile strength, induction heating, influential factor, infrared spectroscopy, interface cracking, laboratory test, local correction coefficient, long-term observation data, low temperature performance, machine learning, management system, master curve, model accuracy evaluation, moisture, moisture damage, moisture sensitivity, molecular dynamics, morphological properties, multiple aging and rejuvenation cycles, n/a, neural network, non-destructive testing, numerical analysis, orthogonal experimental design, orthogonal test, pavement, pavement condition evaluation, pavement design, pavement maintenance, performance, porosity, porous asphalt mixture, prediction, random forest, reclaimed asphalt pavement, recycled cigarette butts, reflection crack, relaxation characteristics, resilient modulus, rutting performance prediction model, rutting prediction, self-healing, smartphone sensors, steel slag aggregate, stiffness modulus, stress intensity factors, subbase layers, toposable set theory, unbound granular material (UGM), vibration, warm mix asphalt, water sensitivity, wheel tracking rutting resistance
Abstract

Summary: Unlike other construction materials, road materials have developed minimally over the past 100 years. However, since the 1970s, the focus has been on more sustainable road construction materials such as recycled asphalt pavements. Recycling asphalt involves removing old asphalt and mixing it with new (fresh) aggregates, binders, and/or rejuvenators. Similarly, there are various efforts to use alternative modifiers and technical solutions such as crumb rubber, plastics, or various types of fibres. For the past two decades, researchers have been developing novel materials and technologies, such as self-healing materials, in order to improve road design, construction, and maintenance efficiency and reduce the financial and environmental burden of road construction. This Special Issue on "Advances in Asphalt Pavement Technologies and Practices" curates advanced/novel work on asphalt pavement design, construction, and maintenance. The Special Issue comprises 19 papers describing unique works that address the current challenges that the asphalt industry and road owners face.