Search results for: market crash prediction
5085 A Time Delay Neural Network for Prediction of Human Behavior
Authors: A. Hakimiyan, H. Namazi
Abstract:
Human behavior is defined as a range of behaviors exhibited by humans who are influenced by different internal or external sources. Human behavior is the subject of much research in different areas of psychology and neuroscience. Despite some advances in studies related to forecasting of human behavior, there are not many researches which consider the effect of the time delay between the presence of stimulus and the related human response. Analysis of EEG signal as a fractal time series is one of the major tools for studying the human behavior. In the other words, the human brain activity is reflected in his EEG signal. Artificial Neural Network has been proved useful in forecasting of different systems’ behavior especially in engineering areas. In this research, a time delay neural network is trained and tested in order to forecast the human EEG signal and subsequently human behavior. This neural network, by introducing a time delay, takes care of the lagging time between the occurrence of the stimulus and the rise of the subsequent action potential. The results of this study are useful not only for the fundamental understanding of human behavior forecasting, but shall be very useful in different areas of brain research such as seizure prediction.Keywords: human behavior, EEG signal, time delay neural network, prediction, lagging time
Procedia PDF Downloads 6535084 Measurement of Innovation Performance
Authors: M. Chobotová, Ž. Rylková
Abstract:
Time full of changes which is associated with globalization, tougher competition, changes in the structures of markets and economic downturn, that all force companies to think about their competitive advantages. These changes can bring the company a competitive advantage and that can help improve competitive position in the market. Policy of the European Union is focused on the fast growing innovative companies which quickly respond to market demands and consequently increase its competitiveness. To meet those objectives companies need the right conditions and support of their state.Keywords: innovation, performance, measurements metrics, indices
Procedia PDF Downloads 3685083 A Linear Autoregressive and Non-Linear Regime Switching Approach in Identifying the Structural Breaks Caused by Anti-Speculation Measures: The Case of Hong Kong
Authors: Mengna Hu
Abstract:
This paper examines the impact of an anti-speculation tax policy on the trading activities and home price movements in the housing market in Hong Kong. The study focuses on the secondary residential property market where transactions dominate. The policy intervention substantially raised the transaction cost to speculators as well as genuine homeowners who dispose their homes within a certain period. Through the demonstration of structural breaks, our empirical results show that the rise in transaction cost effectively reduced speculative trading activities. However, it accelerated price increase in the small-sized segment by vastly demotivating existing homeowners from trading up to better homes, causing congestion in the lower-end market where the demand from first-time buyers is still strong. Apart from that, by employing regime switching approach, we further show that the unintended consequences are likely to be persistent due to this policy together with other strengthened cooling measures.Keywords: transaction costs, housing market, structural breaks, regime switching
Procedia PDF Downloads 2545082 Detection of Important Biological Elements in Drug-Drug Interaction Occurrence
Authors: Reza Ferdousi, Reza Safdari, Yadollah Omidi
Abstract:
Drug-drug interactions (DDIs) are main cause of the adverse drug reactions and nature of the functional and molecular complexity of drugs behavior in human body make them hard to prevent and treat. With the aid of new technologies derived from mathematical and computational science the DDIs problems can be addressed with minimum cost and efforts. Market basket analysis is known as powerful method to identify co-occurrence of thing to discover patterns and frequency of the elements. In this research, we used market basket analysis to identify important bio-elements in DDIs occurrence. For this, we collected all known DDIs from DrugBank. The obtained data were analyzed by market basket analysis method. We investigated all drug-enzyme, drug-carrier, drug-transporter and drug-target associations. To determine the importance of the extracted bio-elements, extracted rules were evaluated in terms of confidence and support. Market basket analysis of the over 45,000 known DDIs reveals more than 300 important rules that can be used to identify DDIs, CYP 450 family were the most frequent shared bio-elements. We applied extracted rules over 2,000,000 unknown drug pairs that lead to discovery of more than 200,000 potential DDIs. Analysis of the underlying reason behind the DDI phenomena can help to predict and prevent DDI occurrence. Ranking of the extracted rules based on strangeness of them can be a supportive tool to predict the outcome of an unknown DDI.Keywords: drug-drug interaction, market basket analysis, rule discovery, important bio-elements
Procedia PDF Downloads 3045081 An Automated Stock Investment System Using Machine Learning Techniques: An Application in Australia
Authors: Carol Anne Hargreaves
Abstract:
A key issue in stock investment is how to select representative features for stock selection. The objective of this paper is to firstly determine whether an automated stock investment system, using machine learning techniques, may be used to identify a portfolio of growth stocks that are highly likely to provide returns better than the stock market index. The second objective is to identify the technical features that best characterize whether a stock’s price is likely to go up and to identify the most important factors and their contribution to predicting the likelihood of the stock price going up. Unsupervised machine learning techniques, such as cluster analysis, were applied to the stock data to identify a cluster of stocks that was likely to go up in price – portfolio 1. Next, the principal component analysis technique was used to select stocks that were rated high on component one and component two – portfolio 2. Thirdly, a supervised machine learning technique, the logistic regression method, was used to select stocks with a high probability of their price going up – portfolio 3. The predictive models were validated with metrics such as, sensitivity (recall), specificity and overall accuracy for all models. All accuracy measures were above 70%. All portfolios outperformed the market by more than eight times. The top three stocks were selected for each of the three stock portfolios and traded in the market for one month. After one month the return for each stock portfolio was computed and compared with the stock market index returns. The returns for all three stock portfolios was 23.87% for the principal component analysis stock portfolio, 11.65% for the logistic regression portfolio and 8.88% for the K-means cluster portfolio while the stock market performance was 0.38%. This study confirms that an automated stock investment system using machine learning techniques can identify top performing stock portfolios that outperform the stock market.Keywords: machine learning, stock market trading, logistic regression, cluster analysis, factor analysis, decision trees, neural networks, automated stock investment system
Procedia PDF Downloads 1505080 Machine Learning Approach for Yield Prediction in Semiconductor Production
Authors: Heramb Somthankar, Anujoy Chakraborty
Abstract:
This paper presents a classification study on yield prediction in semiconductor production using machine learning approaches. A complicated semiconductor production process is generally monitored continuously by signals acquired from sensors and measurement sites. A monitoring system contains a variety of signals, all of which contain useful information, irrelevant information, and noise. In the case of each signal being considered a feature, "Feature Selection" is used to find the most relevant signals. The open-source UCI SECOM Dataset provides 1567 such samples, out of which 104 fail in quality assurance. Feature extraction and selection are performed on the dataset, and useful signals were considered for further study. Afterward, common machine learning algorithms were employed to predict whether the signal yields pass or fail. The most relevant algorithm is selected for prediction based on the accuracy and loss of the ML model.Keywords: deep learning, feature extraction, feature selection, machine learning classification algorithms, semiconductor production monitoring, signal processing, time-series analysis
Procedia PDF Downloads 1015079 The Influence of Market Attractiveness and Core Competence on Value Creation Strategy and Competitive Advantage and Its Implication on Business Performance
Authors: Firsan Nova
Abstract:
The average Indonesian watches 5.5 hours of TV a day. With a population of 242 million people and a Free-to-Air (FTA) TV penetration rate of 56%, that equates to 745 million hours of television watched each day. With such potential, it is no wonder that many companies are now attempting to get into the Pay TV market. Research firm Media Partner Asia has forecast in its study that the number of Indonesian pay-television subscribers will climb from 2.4 million in 2012 to 8.7 million by 2020, with penetration scaling up from 7 percent to 21 percent. Key drivers of market growth, the study says, include macro trends built around higher disposable income and a rising middle class, with leading players continuing to invest significantly in sales, distribution and content. New entrants, in the meantime, will boost overall prospects. This study aims to examine and analyze the effect of Market Attractiveness and the Core Competence on Value Creation and Competitive Advantage and its impact to Business Performance in the pay TV industry in Indonesia. The study using strategic management science approach with the census method in which all members of the population are as sample. Verification method is used to examine the relationship between variables. The unit of analysis in this research is all Indonesian Pay TV business units totaling 19 business units. The unit of observation is the director and managers of each business unit. Hypothesis testing is performed by using statistical Partial Least Square (PLS). The conclusion of the study shows that the market attractiveness affects business performance through value creation and competitive advantage. The appropriate value creation comes from the company ability to optimize its core competence and exploit market attractiveness. Value creation affects competitive advantage. The competitive advantage can be determined based on the company's ability to create value for customers and the competitive advantage has an impact on business performance.Keywords: market attractiveness, core competence, value creation, competitive advantage, business performance
Procedia PDF Downloads 3415078 Financial Market Reaction to Non-Financial Reports
Authors: Petra Dilling
Abstract:
This study examines the market reaction to the publication of integrated reports for a sample of 316 global companies for the reporting year 2018. Applying event study methodology, we find significant cumulative average abnormal returns (CAARs) after the publication date. To ensure robust estimation resultsthe three-factor model, according to Fama and French, is used as well as a market-adjusted model, a CAPM and a Frama-French model taking GARCH effects into account. We find a significant positive CAAR after the publication day of the integrated report. Our results suggest that investors react to information provided in the integrated report and that they react differently to the annual financial report. Furthermore, our cross-sectional analysis confirms that companies with a significant positive cumulative average abnormal show certain characteristic. It was found that European companies have a higher likelihood to experience a stronger significant positive market reaction to their integrated report publication.Keywords: integrated report, event methodology, cumulative abnormal return, sustainability, CAPM
Procedia PDF Downloads 1425077 Prediction of California Bearing Ratio from Physical Properties of Fine-Grained Soils
Authors: Bao Thach Nguyen, Abbas Mohajerani
Abstract:
The California bearing ratio (CBR) has been acknowledged as an important parameter to characterize the bearing capacity of earth structures, such as earth dams, road embankments, airport runways, bridge abutments, and pavements. Technically, the CBR test can be carried out in the laboratory or in the field. The CBR test is time-consuming and is infrequently performed due to the equipment needed and the fact that the field moisture content keeps changing over time. Over the years, many correlations have been developed for the prediction of CBR by various researchers, including the dynamic cone penetrometer, undrained shear strength, and Clegg impact hammer. This paper reports and discusses some of the results from a study on the prediction of CBR. In the current study, the CBR test was performed in the laboratory on some fine-grained subgrade soils collected from various locations in Victoria. Based on the test results, a satisfactory empirical correlation was found between the CBR and the physical properties of the experimental soils.Keywords: California bearing ratio, fine-grained soils, soil physical properties, pavement, soil test
Procedia PDF Downloads 5015076 Predicting Match Outcomes in Team Sport via Machine Learning: Evidence from National Basketball Association
Authors: Jacky Liu
Abstract:
This paper develops a team sports outcome prediction system with potential for wide-ranging applications across various disciplines. Despite significant advancements in predictive analytics, existing studies in sports outcome predictions possess considerable limitations, including insufficient feature engineering and underutilization of advanced machine learning techniques, among others. To address these issues, we extend the Sports Cross Industry Standard Process for Data Mining (SRP-CRISP-DM) framework and propose a unique, comprehensive predictive system, using National Basketball Association (NBA) data as an example to test this extended framework. Our approach follows a holistic methodology in feature engineering, employing both Time Series and Non-Time Series Data, as well as conducting Explanatory Data Analysis and Feature Selection. Furthermore, we contribute to the discourse on target variable choice in team sports outcome prediction, asserting that point spread prediction yields higher profits as opposed to game-winner predictions. Using machine learning algorithms, particularly XGBoost, results in a significant improvement in predictive accuracy of team sports outcomes. Applied to point spread betting strategies, it offers an astounding annual return of approximately 900% on an initial investment of $100. Our findings not only contribute to academic literature, but have critical practical implications for sports betting. Our study advances the understanding of team sports outcome prediction a burgeoning are in complex system predictions and pave the way for potential profitability and more informed decision making in sports betting markets.Keywords: machine learning, team sports, game outcome prediction, sports betting, profits simulation
Procedia PDF Downloads 945075 Risk Propagation in Electricity Markets: Measuring the Asymmetric Transmission of Downside and Upside Risks in Energy Prices
Authors: Montserrat Guillen, Stephania Mosquera-Lopez, Jorge Uribe
Abstract:
An empirical study of market risk transmission between electricity prices in the Nord Pool interconnected market is done. Crucially, it is differentiated between risk propagation in the two tails of the price variation distribution. Thus, the downside risk from upside risk spillovers is distinguished. The results found document an asymmetric nature of risk and risk propagation in the two tails of the electricity price log variations. Risk spillovers following price increments in the market are transmitted to a larger extent than those after price reductions. Also, asymmetries related to both, the size of the transaction area and related to whether a given area behaves as a net-exporter or net-importer of electricity, are documented. For instance, on the one hand, the bigger the area of the transaction, the smaller the size of the volatility shocks that it receives. On the other hand, exporters of electricity, alongside countries with a significant dependence on renewable sources, tend to be net-transmitters of volatility to the rest of the system. Additionally, insights on the predictive power of positive and negative semivariances for future market volatility are provided. It is shown that depending on the forecasting horizon, downside and upside shocks to the market are featured by a distinctive persistence, and that upside volatility impacts more on net-importers of electricity, while the opposite holds for net-exporters.Keywords: electricity prices, realized volatility, semivariances, volatility spillovers
Procedia PDF Downloads 1695074 Experimental Study and Neural Network Modeling in Prediction of Surface Roughness on Dry Turning Using Two Different Cutting Tool Nose Radii
Authors: Deba Kumar Sarma, Sanjib Kr. Rajbongshi
Abstract:
Surface finish is an important product quality in machining. At first, experiments were carried out to investigate the effect of the cutting tool nose radius (considering 1mm and 0.65mm) in prediction of surface finish with process parameters of cutting speed, feed and depth of cut. For all possible cutting conditions, full factorial design was considered as two levels four parameters. Commercial Mild Steel bar and High Speed Steel (HSS) material were considered as work-piece and cutting tool material respectively. In order to obtain functional relationship between process parameters and surface roughness, neural network was used which was found to be capable for the prediction of surface roughness within a reasonable degree of accuracy. It was observed that tool nose radius of 1mm provides better surface finish in comparison to 0.65 mm. Also, it was observed that feed rate has a significant influence on surface finish.Keywords: full factorial design, neural network, nose radius, surface finish
Procedia PDF Downloads 3625073 DQN for Navigation in Gazebo Simulator
Authors: Xabier Olaz Moratinos
Abstract:
Drone navigation is critical, particularly during the initial phases, such as the initial ascension, where pilots may fail due to strong external interferences that could potentially lead to a crash. In this ongoing work, a drone has been successfully trained to perform an ascent of up to 6 meters at speeds with external disturbances pushing it up to 24 mph, with the DQN algorithm managing external forces affecting the system. It has been demonstrated that the system can control its height, position, and stability in all three axes (roll, pitch, and yaw) throughout the process. The learning process is carried out in the Gazebo simulator, which emulates interferences, while ROS is used to communicate with the agent.Keywords: machine learning, DQN, gazebo, navigation
Procedia PDF Downloads 1005072 Research on the Aero-Heating Prediction Based on Hybrid Meshes and Hybrid Schemes
Authors: Qiming Zhang, Youda Ye, Qinxue Jiang
Abstract:
Accurate prediction of external flowfield and aero-heating at the wall of hypersonic vehicle is very crucial for the design of aircrafts. Unstructured/hybrid meshes have more powerful advantages than structured meshes in terms of pre-processing, parallel computing and mesh adaptation, so it is imperative to develop high-resolution numerical methods for the calculation of aerothermal environment on unstructured/hybrid meshes. The inviscid flux scheme is one of the most important factors affecting the accuracy of unstructured/ hybrid mesh heat flux calculation. Here, a new hybrid flux scheme is developed and the approach of interface type selection is proposed: i.e. 1) using the exact Riemann scheme solution to calculate the flux on the faces parallel to the wall; 2) employing Sterger-Warming (S-W) scheme to improve the stability of the numerical scheme in other interfaces. The results of the heat flux fit the one observed experimentally and have little dependence on grids, which show great application prospect in unstructured/ hybrid mesh.Keywords: aero-heating prediction, computational fluid dynamics, hybrid meshes, hybrid schemes
Procedia PDF Downloads 2325071 Development of Market Penetration for High Energy Efficiency Technologies in Alberta’s Residential Sector
Authors: Saeidreza Radpour, Md. Alam Mondal, Amit Kumar
Abstract:
Market penetration of high energy efficiency technologies has key impacts on energy consumption and GHG mitigation. Also, it will be useful to manage the policies formulated by public or private organizations to achieve energy or environmental targets. Energy intensity in residential sector of Alberta was 148.8 GJ per household in 2012 which is 39% more than the average of Canada 106.6 GJ, it was the highest amount among the provinces on per household energy consumption. Energy intensity by appliances of Alberta was 15.3 GJ per household in 2012 which is 14% higher than average value of other provinces and territories in energy demand intensity by appliances in Canada. In this research, a framework has been developed to analyze the market penetration and market share of high energy efficiency technologies in residential sector. The overall methodology was based on development of data-intensive models’ estimation of the market penetration of the appliances in the residential sector over a time period. The developed models were a function of a number of macroeconomic and technical parameters. Developed mathematical equations were developed based on twenty-two years of historical data (1990-2011). The models were analyzed through a series of statistical tests. The market shares of high efficiency appliances were estimated based on the related variables such as capital and operating costs, discount rate, appliance’s life time, annual interest rate, incentives and maximum achievable efficiency in the period of 2015 to 2050. Results show that the market penetration of refrigerators is higher than that of other appliances. The stocks of refrigerators per household are anticipated to increase from 1.28 in 2012 to 1.314 and 1.328 in 2030 and 2050, respectively. Modelling results show that the market penetration rate of stand-alone freezers will decrease between 2012 and 2050. Freezer stock per household will decline from 0.634 in 2012 to 0.556 and 0.515 in 2030 and 2050, respectively. The stock of dishwashers per household is expected to increase from 0.761 in 2012 to 0.865 and 0.960 in 2030 and 2050, respectively. The increase in the market penetration rate of clothes washers and clothes dryers is nearly parallel. The stock of clothes washers and clothes dryers per household is expected to rise from 0.893 and 0.979 in 2012 to 0.960 and 1.0 in 2050, respectively. This proposed presentation will include detailed discussion on the modelling methodology and results.Keywords: appliances efficiency improvement, energy star, market penetration, residential sector
Procedia PDF Downloads 2805070 The Influence of Housing Choice Vouchers on the Private Rental Market
Authors: Randy D. Colon
Abstract:
Through a freedom of information request, data pertaining to Housing Choice Voucher (HCV) households has been obtained from the Chicago Housing Authority, including rent price and number of bedrooms per HCV household, community area, and zip code from 2013 to the first quarter of 2018. Similar data pertaining to the private rental market will be obtained through public records found through the United States Department of Housing and Urban Development. The datasets will be analyzed through statistical and mapping software to investigate the potential link between HCV households and distorted rent prices. Quantitative data will be supplemented by qualitative data to investigate the lived experience of Chicago residents. Qualitative data will be collected at community meetings in the Chicago Englewood neighborhood through participation in neighborhood meetings and informal interviews with residents and community leaders. The qualitative data will be used to gain insight on the lived experience of community leaders and residents of the Englewood neighborhood in relation to housing, the rental market, and HCV. While there is an abundance of quantitative data on this subject, this qualitative data is necessary to capture the lived experience of local residents effected by a changing rental market. This topic reflects concerns voiced by members of the Englewood community, and this study aims to keep the community relevant in its findings.Keywords: Chicago, housing, housing choice voucher program, housing subsidies, rental market
Procedia PDF Downloads 1105069 Prediction of Welding Induced Distortion in Thin Metal Plates Using Temperature Dependent Material Properties and FEA
Authors: Rehan Waheed, Abdul Shakoor
Abstract:
Distortion produced during welding of thin metal plates is a problem in many industries. The purpose of this research was to study distortion produced during welding in 2mm Mild Steel plate by simulating the welding process using Finite Element Analysis. Simulation of welding process requires a couple field transient analyses. At first a transient thermal analysis is performed and the temperature obtained from thermal analysis is used as input in structural analysis to find distortion. An actual weld sample is prepared and the weld distortion produced is measured. The simulated and actual results were in quite agreement with each other and it has been found that there is profound deflection at center of plate. Temperature dependent material properties play significant role in prediction of weld distortion. The results of this research can be used for prediction and control of weld distortion in large steel structures by changing different weld parameters.Keywords: welding simulation, FEA, welding distortion, temperature dependent mechanical properties
Procedia PDF Downloads 3845068 Multiclass Support Vector Machines with Simultaneous Multi-Factors Optimization for Corporate Credit Ratings
Authors: Hyunchul Ahn, William X. S. Wong
Abstract:
Corporate credit rating prediction is one of the most important topics, which has been studied by researchers in the last decade. Over the last decade, researchers are pushing the limit to enhance the exactness of the corporate credit rating prediction model by applying several data-driven tools including statistical and artificial intelligence methods. Among them, multiclass support vector machine (MSVM) has been widely applied due to its good predictability. However, heuristics, for example, parameters of a kernel function, appropriate feature and instance subset, has become the main reason for the critics on MSVM, as they have dictate the MSVM architectural variables. This study presents a hybrid MSVM model that is intended to optimize all the parameter such as feature selection, instance selection, and kernel parameter. Our model adopts genetic algorithm (GA) to simultaneously optimize multiple heterogeneous design factors of MSVM.Keywords: corporate credit rating prediction, Feature selection, genetic algorithms, instance selection, multiclass support vector machines
Procedia PDF Downloads 2895067 Reliability-Simulation of Composite Tubular Structure under Pressure by Finite Elements Methods
Authors: Abdelkader Hocine, Abdelhakim Maizia
Abstract:
The exponential growth of reinforced fibers composite materials use has prompted researchers to step up their work on the prediction of their reliability. Owing to differences between the properties of the materials used for the composite, the manufacturing processes, the load combinations and types of environment, the prediction of the reliability of composite materials has become a primary task. Through failure criteria, TSAI-WU and the maximum stress, the reliability of multilayer tubular structures under pressure is the subject of this paper, where the failure probability of is estimated by the method of Monte Carlo.Keywords: composite, design, monte carlo, tubular structure, reliability
Procedia PDF Downloads 4565066 Stochastic Default Risk Estimation Evidence from the South African Financial Market
Authors: Mesias Alfeus, Kirsty Fitzhenry, Alessia Lederer
Abstract:
The present paper provides empirical studies to estimate defaultable bonds in the South African financial market. The main goal is to estimate the unobservable factors affecting bond yields for South African major banks. The maximum likelihood approach is adopted for the estimation methodology. Extended Kalman filtering techniques are employed in order to tackle the situation that the factors cannot be observed directly. Multi-dimensional Cox-Ingersoll-Ross (CIR)-type factor models are considered. Results show that default risk increased sharply in the South African financial market during COVID-19 and the CIR model with jumps exhibits a better performance.Keywords: default intensity, unobservable state variables, CIR, α-CIR, extended kalman filtering
Procedia PDF Downloads 1045065 Preventive Effects of Motorcycle Helmets on Clinical Outcomes in Motorcycle Crashes
Authors: Seung Chul Lee, Jooyeong Kim, Ki Ok Ahn, Juok Park
Abstract:
Background: Injuries caused by motorcycle crashes are one of the major public health burdens leading to high mortality, functional disability. The risk of death among motorcyclists is 30 times greater than that among car drivers, with head injuries the leading cause of death. The motorcycle helmet is crucial protective equipment for motorcyclists. Aims: This study aimed to measure the protective effect of motorcycle helmet use on intracranial injury and mortality and to compare the preventive effect in drivers and passengers. Methods: This is a cross-sessional study based on the Emergency Department (ED)–based Injury In-depth Surveillance (EDIIS) database from 23 EDs in Korea. All of the trauma patients injured in motorcycle crashes between January 1, 2013 and December 31, 2016 were eligible, excluding cases with unknown helmet use and outcomes. The primary and secondary outcomes were intracranial injury and in-hospital mortality. We calculated adjusted odds ratios (AORs) of helmet use for study outcomes after adjusting for potential confounders. Using interaction models, we compared the protective effect of helmet use on outcomes across driving status (driver and passenger). Results: Among 17,791 eligible patients, 10,668 (60.0%) patients were wearing helmets at the time of the crash, 2,128 (12.0%) patients had intracranial injuries and 331 (1.9%) patients had in-hospital death. 16,381 (92.1%) patients were drivers and 1410 (7.9%) patients were passengers. 62.6% of drivers and 29.1% of passengers were wearing helmets at the time of the crash. Compared to un-helmeted group, the helmeted group was less likely to have an intracranial injury(8.0% vs. 17.9%, AOR: 0.43 (0.39-0.48)) and in-hospital mortality (1.0% vs. 3.2%, AOR: 0.29 (0.22-0.37)).In the interaction model, AORs (95% CIs) of helmet use for intracranial injury were 0.42 (0.38-0.47) in drivers and 0.61(0.41-0.90) in passengers, respectively. There was a significant preventive effect of helmet use on in-hospital mortality in drivers (AOR: 0.26(0.21–0.34)). Discussion and conclusions: Wearing helmets in motorcycle crashes reduced intracranial injuries and in-hospital mortality. The preventive effect of motorcycle helmet use on intracranial injury was stronger in drivers than in passengers. There was a significant preventive effect of helmet use on in-hospital mortality in driver but not in passengers. Public health efforts to increase motorcycle helmet use are needed to reduce health burden from injuries caused by motorcycle crashes.Keywords: intracranial injury, helmet, mortality, motorcycle crashes
Procedia PDF Downloads 1745064 Using Historical Data for Stock Prediction
Authors: Sofia Stoica
Abstract:
In this paper, we use historical data to predict the stock price of a tech company. To this end, we use a dataset consisting of the stock prices in the past five years of ten major tech companies – Adobe, Amazon, Apple, Facebook, Google, Microsoft, Netflix, Oracle, Salesforce, and Tesla. We experimented with a variety of models– a linear regressor model, K nearest Neighbors (KNN), a sequential neural network – and algorithms - Multiplicative Weight Update, and AdaBoost. We found that the sequential neural network performed the best, with a testing error of 0.18%. Interestingly, the linear model performed the second best with a testing error of 0.73%. These results show that using historical data is enough to obtain high accuracies, and a simple algorithm like linear regression has a performance similar to more sophisticated models while taking less time and resources to implement.Keywords: finance, machine learning, opening price, stock market
Procedia PDF Downloads 1815063 Enhancing Technical Trading Strategy on the Bitcoin Market using News Headlines and Language Models
Authors: Mohammad Hosein Panahi, Naser Yazdani
Abstract:
we present a technical trading strategy that leverages the FinBERT language model and financial news analysis with a focus on news related to a subset of Nasdaq 100 stocks. Our approach surpasses the baseline Range Break-out strategy in the Bitcoin market, yielding a remarkable 24.8% increase in the win ratio for all Friday trades and an impressive 48.9% surge in short trades specifically on Fridays. Moreover, we conduct rigorous hypothesis testing to establish the statistical significance of these improvements. Our findings underscore considerable potential of our NLP-driven approach in enhancing trading strategies and achieving greater profitability within financial markets.Keywords: quantitative finance, technical analysis, bitcoin market, NLP, language models, FinBERT, technical trading
Procedia PDF Downloads 625062 Deep Q-Network for Navigation in Gazebo Simulator
Authors: Xabier Olaz Moratinos
Abstract:
Drone navigation is critical, particularly during the initial phases, such as the initial ascension, where pilots may fail due to strong external interferences that could potentially lead to a crash. In this ongoing work, a drone has been successfully trained to perform an ascent of up to 6 meters at speeds with external disturbances pushing it up to 24 mph, with the DQN algorithm managing external forces affecting the system. It has been demonstrated that the system can control its height, position, and stability in all three axes (roll, pitch, and yaw) throughout the process. The learning process is carried out in the Gazebo simulator, which emulates interferences, while ROS is used to communicate with the agent.Keywords: machine learning, DQN, Gazebo, navigation
Procedia PDF Downloads 715061 Recirculated Sedimentation Method to Control Contamination for Algal Biomass Production
Authors: Ismail S. Bostanci, Ebru Akkaya
Abstract:
Microalgae-derived biodiesel, fertilizer or industrial chemicals' production with wastewater has great potential. Especially water from a municipal wastewater treatment plant is a very important nutrient source for biofuel production. Microalgae biomass production in open ponds system is lower cost culture systems. There are many hurdles for commercial algal biomass production in large scale. One of the important technical bottlenecks for microalgae production in open system is culture contamination. The algae culture contaminants can generally be described as invading organisms which could cause pond crash. These invading organisms can be competitors, parasites, and predators. Contamination is unavoidable in open systems. Potential contaminant organisms are already inoculated if wastewater is utilized for algal biomass cultivation. Especially, it is important to control contaminants to retain in acceptable level in order to reach true potential of algal biofuel production. There are several contamination management methods in algae industry, ranging from mechanical, chemical, biological and growth condition change applications. However, none of them are accepted as a suitable contamination control method. This experiment describes an innovative contamination control method, 'Recirculated Sedimentation Method', to manage contamination to avoid pond cash. The method can be used for the production of algal biofuel, fertilizer etc. and algal wastewater treatment. To evaluate the performance of the method on algal culture, an experiment was conducted for 90 days at a lab-scale raceway (60 L) reactor with the use of non-sterilized and non-filtered wastewater (secondary effluent and centrate of anaerobic digestion). The application of the method provided the following; removing contaminants (predators and diatoms) and other debris from reactor without discharging the culture (with microscopic evidence), increasing raceway tank’s suspended solids holding capacity (770 mg L-1), increasing ammonium removal rate (29.83 mg L-1 d-1), decreasing algal and microbial biofilm formation on inner walls of reactor, washing out generated nitrifier from reactor to prevent ammonium consumption.Keywords: contamination control, microalgae culture contamination, pond crash, predator control
Procedia PDF Downloads 1995060 Drug-Drug Interaction Prediction in Diabetes Mellitus
Authors: Rashini Maduka, C. R. Wijesinghe, A. R. Weerasinghe
Abstract:
Drug-drug interactions (DDIs) can happen when two or more drugs are taken together. Today DDIs have become a serious health issue due to adverse drug effects. In vivo and in vitro methods for identifying DDIs are time-consuming and costly. Therefore, in-silico-based approaches are preferred in DDI identification. Most machine learning models for DDI prediction are used chemical and biological drug properties as features. However, some drug features are not available and costly to extract. Therefore, it is better to make automatic feature engineering. Furthermore, people who have diabetes already suffer from other diseases and take more than one medicine together. Then adverse drug effects may happen to diabetic patients and cause unpleasant reactions in the body. In this study, we present a model with a graph convolutional autoencoder and a graph decoder using a dataset from DrugBank version 5.1.3. The main objective of the model is to identify unknown interactions between antidiabetic drugs and the drugs taken by diabetic patients for other diseases. We considered automatic feature engineering and used Known DDIs only as the input for the model. Our model has achieved 0.86 in AUC and 0.86 in AP.Keywords: drug-drug interaction prediction, graph embedding, graph convolutional networks, adverse drug effects
Procedia PDF Downloads 955059 Impact of Brexit on the Structure of the European Insurance Market: A Solvency and Financial Condition Report Content Analysis of UK Insurance Companies
Authors: Antonia Müller, Svend Reuse
Abstract:
The Brexit referendum in June 2016 led to different publications analysing potential consequences for European and British insurance companies under the European Passport. This study addresses a research gap, regarding the measures taken by insurance companies based in the United Kingdom and thus on structural changes to the European insurance market by an innovative structured Solvency and Financial Condition Report content analysis. In scope are all insurance companies based in the United Kingdom, that fall under the Solvency II supervisory regime. The results show that the majority of British Solvency II insurance companies in scope, conducting cross-border business to the European Union, have applied and reported measures to be able to continue operating this cross-border business after Brexit. In addition, the study shows that 34 new insurance companies based in the European Union were established as a result of Brexit, indicating structural changes to the European insurance market.Keywords: brexit, europe, insurance market, solvency and financial condition repot, structural changes
Procedia PDF Downloads 1985058 Influences of Market Orientation and Supply Chain Management on Competitive Capability in Case of Automotive Parts Industry
Authors: Nattapong Techarattanased
Abstract:
The objectives of this research were to study the influence of market orientation and supply chain management on competitive capability in case of the automotive parts industry in Thailand. This study employed by survey research and questionnaire was used to collect the data from 400 entrepreneurs in the automotive parts industry in Thailand. The descriptive statistics and multiple regression analysis were used to analyze data. The results revealed that the overall dimensions of marketing orientation, namely, responsiveness, intelligence generation, and intelligence dissemination were rated at the high level. As well, the overall dimensions of supply chain management, namely, collaboration, communication, trust, and commitment were also rated at the high level. Furthermore, the hypothesis testing results showed that supply chain management and market orientation affected competitive capability of the automotive parts industry in Thailand which these two variables could be combined to predict competitive capability of the automotive parts industry in Thailand by 31.5 percent.Keywords: automotive parts industry, competitive capability, market orientation, supply chain management
Procedia PDF Downloads 3075057 Machine Learning for Disease Prediction Using Symptoms and X-Ray Images
Authors: Ravija Gunawardana, Banuka Athuraliya
Abstract:
Machine learning has emerged as a powerful tool for disease diagnosis and prediction. The use of machine learning algorithms has the potential to improve the accuracy of disease prediction, thereby enabling medical professionals to provide more effective and personalized treatments. This study focuses on developing a machine-learning model for disease prediction using symptoms and X-ray images. The importance of this study lies in its potential to assist medical professionals in accurately diagnosing diseases, thereby improving patient outcomes. Respiratory diseases are a significant cause of morbidity and mortality worldwide, and chest X-rays are commonly used in the diagnosis of these diseases. However, accurately interpreting X-ray images requires significant expertise and can be time-consuming, making it difficult to diagnose respiratory diseases in a timely manner. By incorporating machine learning algorithms, we can significantly enhance disease prediction accuracy, ultimately leading to better patient care. The study utilized the Mask R-CNN algorithm, which is a state-of-the-art method for object detection and segmentation in images, to process chest X-ray images. The model was trained and tested on a large dataset of patient information, which included both symptom data and X-ray images. The performance of the model was evaluated using a range of metrics, including accuracy, precision, recall, and F1-score. The results showed that the model achieved an accuracy rate of over 90%, indicating that it was able to accurately detect and segment regions of interest in the X-ray images. In addition to X-ray images, the study also incorporated symptoms as input data for disease prediction. The study used three different classifiers, namely Random Forest, K-Nearest Neighbor and Support Vector Machine, to predict diseases based on symptoms. These classifiers were trained and tested using the same dataset of patient information as the X-ray model. The results showed promising accuracy rates for predicting diseases using symptoms, with the ensemble learning techniques significantly improving the accuracy of disease prediction. The study's findings indicate that the use of machine learning algorithms can significantly enhance disease prediction accuracy, ultimately leading to better patient care. The model developed in this study has the potential to assist medical professionals in diagnosing respiratory diseases more accurately and efficiently. However, it is important to note that the accuracy of the model can be affected by several factors, including the quality of the X-ray images, the size of the dataset used for training, and the complexity of the disease being diagnosed. In conclusion, the study demonstrated the potential of machine learning algorithms for disease prediction using symptoms and X-ray images. The use of these algorithms can improve the accuracy of disease diagnosis, ultimately leading to better patient care. Further research is needed to validate the model's accuracy and effectiveness in a clinical setting and to expand its application to other diseases.Keywords: K-nearest neighbor, mask R-CNN, random forest, support vector machine
Procedia PDF Downloads 1345056 On the Impact of Oil Price Fluctuations on Stock Markets: A Multivariate Long-Memory GARCH Framework
Authors: Manel Youssef, Lotfi Belkacem
Abstract:
This paper employs multivariate long memory GARCH models to simultaneously estimate mean and conditional variance spillover effects between oil prices and different financial markets. Since different financial assets are traded based on these market sector returns, it’s important for financial market participants to understand the volatility transmission mechanism over time and across these series in order to make optimal portfolio allocation decisions. We examine weekly returns from January 1, 2003 to November 30, 2012 and find evidence of significant transmission of shocks and volatilities between oil prices and some of the examined financial markets. The findings support the idea of cross-market hedging and sharing of common information by investors.Keywords: oil prices, stock indices returns, oil volatility, contagion, DCC-multivariate (FI) GARCH
Procedia PDF Downloads 524