Search results for: price prediction

Authors: Concepcion Gonzalez-Concepcion, Maria Candelaria Gil-Fariña, Celina Pestano-Gabino

Abstract:

We analyze six relevant economic and financial variables for the period 2000M1-2015M3 in the context of the Spanish economy: a financial index (IBEX35), a commodity (Crude Oil Price in euros), a foreign exchange index (EUR/USD), a bond (Spanish 10-Year Bond), the Spanish National Debt and the Consumer Price Index. The goal of this paper is to analyze the main relations between them by computing the Wavelet Power Spectrum and the Cross Wavelet Coherency associated with Morlet wavelets. By using a special toolbox in MATLAB, we focus our interest on the period variable. We decompose the time-frequency effects and improve the interpretation of the results by non-expert users in the theory of wavelets. The empirical evidence shows certain instability periods and reveals various changes and breaks in the causality relationships for sample data. These variables were individually analyzed with Daubechies Wavelets to visualize high-frequency variance, seasonality, and trend. The results are included in Proceeding 20th International Academic Conference, 2015, International Institute of Social and Economic Sciences (IISES), Madrid.

Keywords: economic and financial variables, Spain, time-frequency domain, wavelet coherency

Procedia PDF Downloads 241

Authors: Michael Kenomore, Mohamed Hassan, Amjad Shah, Hom Dhakal

Abstract:

Shale gas reservoirs have been of greater importance compared to shale oil reservoirs since 2009 and with the current nature of the oil market, understanding the technical and economic performance of shale gas reservoirs is of importance. Using the Barnett shale as a case study, an economic model was developed to quantify the effect of finding and development costs and gas prices on the basins in the Barnett shale using net present value as an evaluation parameter. A rate of return of 20% and a payback period of 60 months or less was used as the investment hurdle in the model. The Barnett was split into four basins (Strawn Basin, Ouachita Folded Belt, Forth-worth Syncline and Bend-arch Basin) with analysis conducted on each of the basin to provide a holistic outlook. The dataset consisted of only horizontal wells that started production from 2008 to at most 2015 with 1835 wells coming from the strawn basin, 137 wells from the Ouachita folded belt, 55 wells from the bend-arch basin and 724 wells from the forth-worth syncline. The data was analyzed initially on Microsoft Excel to determine the estimated ultimate recoverable (EUR). The range of EUR from each basin were loaded in the Palisade Risk software and a log normal distribution typical of Barnett shale wells was fitted to the dataset. Monte Carlo simulation was then carried out over a 1000 iterations to obtain a cumulative distribution plot showing the probabilistic distribution of EUR for each basin. From the cumulative distribution plot, the P10, P50 and P90 EUR values for each basin were used in the economic model. Gas production from an individual well with a EUR similar to the calculated EUR was chosen and rescaled to fit the calculated EUR values for each basin at the respective percentiles i.e. P10, P50 and P90. The rescaled production was entered into the economic model to determine the effect of the finding and development cost and gas price on the net present value (10% discount rate/year) as well as also determine the scenario that satisfied the proposed investment hurdle. The finding and development costs used in this paper (assumed to consist only of the drilling and completion costs) were £1 million, £2 million and £4 million while the gas price was varied from $2/MCF-$13/MCF based on Henry Hub spot prices from 2008-2015. One of the major findings in this study was that wells in the bend-arch basin were least economic, higher gas prices are needed in basins containing non-core counties and 90% of the Barnet shale wells were not economic at all finding and development costs irrespective of the gas price in all the basins. This study helps to determine the percentage of wells that are economic at different range of costs and gas prices, determine the basins that are most economic and the wells that satisfy the investment hurdle.

Keywords: shale gas, Barnett shale, unconventional gas, estimated ultimate recoverable

Procedia PDF Downloads 302

Authors: Wei Yao, Constantinos Alexiou

Abstract:

In the existing literature, many studies have focused on the implementation and effectiveness of quantitative easing (QE) since 2008, but only a few have evaluated QE’s effect on commodity prices. In this context, by following Frankel’s (1986) commodity price overshooting model, we study the dynamic covariation between the expected real interest rates and six agricultural commodities’ real returns over the period from 2000:1 to 2018 for the US economy. We use wavelet analysis to investigate the causal relationship and co-movement of time series data by calculating the coefficient of determination in different frequencies. We find that a) US unconventional monetary policy may cause more positive and significant covariation between the expected real interest rates and agricultural commodities’ real returns over the short horizons; b) a lead-lag relationship that runs from agricultural commodities’ real returns to the expected real short-term interest rates over the long horizons; and c) a lead-lag relationship from agricultural commodities’ real returns to the expected real long-term interest rates over short horizons. In the realm of monetary policy, we argue that QE may shift the negative relationship between most commodities’ real returns and the expected real interest rates to a positive one over a short horizon.

Keywords: QE, commodity price, interest rate, wavelet coherence

Procedia PDF Downloads 89

Authors: Gonzalez Carlos, Martinez Fransisco

Abstract:

The creation of a seismic prediction model that considers all the regional variations and perfectly adjusts its results to the response spectra is very complicated. To achieve statistically acceptable results, it is necessary to process a sufficiently robust data set, and even if high efficiencies are achieved, this model will only work properly in this region. However, when using it in other regions, differences are found due to different parameters that have not been calibrated to other regions, such as the site effect. The fact that impedance contrasts, as well as other factors belonging to the site, have a great influence on the local response is well known, which is why this work, using the residual method, is intended to establish a regional calibration of the corresponding parameters site effect for the Spain region in the global GMPM BSSA 14.

Keywords: GMPM, seismic prediction equations, residual method, response spectra, impedance contrast

Procedia PDF Downloads 84

Authors: Victor Bodell, Lukas Ekstrom, Somayeh Aghanavesi

Abstract:

Fuel consumption (FC) is one of the key factors in determining expenses of operating a heavy-duty vehicle. A customer may therefore request an estimate of the FC of a desired vehicle. The modular design of heavy-duty vehicles allows their construction by specifying the building blocks, such as gear box, engine and chassis type. If the combination of building blocks is unprecedented, it is unfeasible to measure the FC, since this would first r equire the construction of the vehicle. This paper proposes a machine learning approach to predict FC. This study uses around 40,000 vehicles specific and o perational e nvironmental c onditions i nformation, such as road slopes and driver profiles. A ll v ehicles h ave d iesel engines and a mileage of more than 20,000 km. The data is used to investigate the accuracy of machine learning algorithms Linear regression (LR), K-nearest neighbor (KNN) and Artificial n eural n etworks (ANN) in predicting fuel consumption for heavy-duty vehicles. Performance of the algorithms is evaluated by reporting the prediction error on both simulated data and operational measurements. The performance of the algorithms is compared using nested cross-validation and statistical hypothesis testing. The statistical evaluation procedure finds that ANNs have the lowest prediction error compared to LR and KNN in estimating fuel consumption on both simulated and operational data. The models have a mean relative prediction error of 0.3% on simulated data, and 4.2% on operational data.

Keywords: artificial neural networks, fuel consumption, friedman test, machine learning, statistical hypothesis testing

Procedia PDF Downloads 179

Authors: Arjun Paul, Adrijit Goswami

Abstract:

In our present work, an economic order quantity inventory model with shortages is developed where holding cost is expressed as linearly increasing function of time and demand rate is a ramp type function of time. The items considered in the model are deteriorating in nature so that a small fraction of the items is depleted with the passage of time. In order to consider a more realistic situation, the deterioration rate is assumed to follow a continuous uniform distribution with the parameters involved being triangular fuzzy numbers. The inventory manager offers his customer a discount in case he is willing to backorder his demand when there is a stock-out. The optimum ordering policy and the optimum discount offered for each backorder are determined by minimizing the total cost in a replenishment interval. For better illustration of our proposed model in both the crisp and fuzzy sense and for providing richer insights, a numerical example is cited to exemplify the policy and to analyze the sensitivity of the model parameters.

Keywords: fuzzy deterioration rate, price discount on backorder, ramp type demand, shortage, time varying holding cost

Procedia PDF Downloads 199

Authors: W. A. Nalaka Wijesooriya

Abstract:

The increasing paddy production, stabilization of domestic rice consumption and the increasing dynamism of rice processing and domestic markets call for a rethinking of the general direction of the rice milling industry in Sri Lanka. The main purpose of the study was to explore levels of concentration in rice milling industry in Polonnaruwa and Hambanthota which are the major hubs of the country for rice milling. Concentration indices reveal that the rice milling industry in Polonnaruwa operates weak oligopsony and is highly competitive in Hambanthota. According to the actual quantity of paddy milling per day, 47 % is less than 8Mt/Day, while 34 % is 8-20 Mt/day, and the rest (19%) is greater than 20 Mt/day. In Hambanthota, nearly 50% of the mills belong to the range of 8-20 Mt/day. Lack of experience of the milling industry, poor knowledge on milling technology, lack of capital and finding an output market are the major entry barriers to the industry. Major problems faced by all the rice millers are the lack of a uniform electricity supply and low quality paddy. Many of the millers emphasized that the rice ceiling price is a constraint to produce quality rice. More than 80% of the millers in Polonnaruwa which is the major parboiling rice producing area have mechanical dryers. Nearly 22% millers have modern machineries like color sorters, water jet polishers. Major paddy purchasing method of large scale millers in Polonnaruwa is through brokers. In Hambanthota major channel is miller purchasing from paddy farmers. Millers in both districts have major rice selling markets in Colombo and suburbs. Huge variation can be observed in the amount of pledge (for paddy storage) loans. There is a strong relationship among the storage ability, credit affordability and the scale of operation of rice millers. The inter annual price fluctuation ranged 30%-35%. Analysis of market margins by using series of secondary data shows that farmers’ share on rice consumer price is stable or slightly increases in both districts. In Hambanthota a greater share goes to the farmer. Only four mills which have obtained the Good Manufacturing Practices (GMP) certification from Sri Lanka Standards Institution can be found. All those millers are small quantity rice exporters. Priority should be given for the Small and medium scale millers in distribution of storage paddy of PMB during the off season. The industry needs a proper rice grading system, and it is recommended to introduce a ceiling price based on graded rice according to the standards. Both husk and rice bran were underutilized. Encouraging investment for establishing rice oil manufacturing plant in Polonnaruwa area is highly recommended. The current taxation procedure needs to be restructured in order to ensure the sustainability of the industry.

Keywords: conduct, performance, structure (SCP), rice millers

Procedia PDF Downloads 330

Authors: Ravneil Nand

Abstract:

Cooperative coevolution uses problem decomposition methods to solve a larger problem. The problem decomposition deals with breaking down the larger problem into a number of smaller sub-problems depending on their method. Different problem decomposition methods have their own strengths and limitations depending on the neural network used and application problem. In this paper we are introducing a new problem decomposition method known as Hidden-Neuron Level Decomposition (HNL). The HNL method is competing with established problem decomposition method in time series prediction. The results show that the proposed approach has improved the results in some benchmark data sets when compared to the standalone method and has competitive results when compared to methods from literature.

Keywords: cooperative coevaluation, feed forward network, problem decomposition, neuron, synapse

Procedia PDF Downloads 338

Authors: Seyran Naghdi

Abstract:

Background: Orphan drug development is limited by very high costs attributed to the research and development and small size market. How health policymakers address this challenge to consider both supply and demand sides need to be explored for directing the policies and plans in the right way. The price is an important signal for pharmaceutical companies’ profitability and the patients’ accessibility as well. Objective: This study aims to find out the orphan drugs' price-setting patterns and approaches in health systems through a systematic review of the available evidence. Methods: The Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) approach was used. MedLine, Embase, and Web of Sciences were searched via appropriate search strategies. Through Medical Subject Headings (MeSH), the appropriate terms for pricing were 'cost and cost analysis', and it was 'orphan drug production', and 'orphan drug', for orphan drugs. The critical appraisal was performed by the Joanna-Briggs tool. A Cochrane data extraction form was used to obtain the data about the studies' characteristics, results, and conclusions. Results: Totally, 1,197 records were found. It included 640 hits from Embase, 327 from Web of Sciences, and 230 MedLine. After removing the duplicates, 1,056 studies remained. Of them, 924 studies were removed in the primary screening phase. Of them, 26 studies were included for data extraction. The majority of the studies (>75%) are from developed countries, among them, approximately 80% of the studies are from European countries. Approximately 85% of evidence has been produced in the recent decade. Conclusions: There is a huge variation of price-setting among countries, and this is related to the specific pharmacological market structure and the thresholds that governments want to intervene in the process of pricing. On the other hand, there is some evidence on the availability of spaces to reduce the very high costs of orphan drugs development through an early agreement between pharmacological firms and governments. Further studies need to focus on how the governments could incentivize the companies to agree on providing the drugs at lower prices.

Keywords: orphan drugs, orphan drug production, pricing, costs, cost analysis

Procedia PDF Downloads 164

Authors: Nadia Allouache

Abstract:

The concept of second law is assumed to be important to optimize the energy losses in heat exchangers. The present study is devoted to the numerical prediction of entropy generation due to heat transfer and friction in a double tube heat exchanger partly or fully filled with a porous medium. The goal of this work is to find the optimal conditions that allow minimizing entropy generation. For this purpose, numerical modeling based on the control volume method is used to describe the flow and heat transfer phenomena in the fluid and the porous medium. Effects of the porous layer thickness, its permeability, and the effective thermal conductivity have been investigated. Unexpectedly, the fully porous heat exchanger yields a lower entropy generation than the partly porous case or the fluid case even if the friction increases the entropy generation.

Keywords: heat exchangers, porous medium, second law approach, turbulent flow

Procedia PDF Downloads 300

Authors: Tetsuji Tanaka, Jin Guo

Abstract:

The extant literature has not succeeded in uncovering the common determinants of price volatility transmissions of agricultural commodities from international to local markets, and further, has rarely investigated the role of self-sufficiency measures in the context of national food security. We analyzed various factors to determine the degree of price volatility transmissions of wheat, rice, and maize between world and domestic markets using GARCH models with dynamic conditional correlation (DCC) specifications and panel-feasible generalized least square models. We found that the grain autarky system has the potential to diminish volatility pass-throughs for three grain commodities. Furthermore, it was discovered that the substitutive commodity consumption behavior between maize and wheat buffers the volatility transmissions of both, but rice does not function as a transmission-relieving element, either for the volatilities of wheat or maize. The effectiveness of grain consumption substitution to insulate the pass-throughs from global markets is greater than that of cereal self-sufficiency. These implications are extremely beneficial for developing governments to protect their domestic food markets from uncertainty in foreign countries and as such, improves food security.

Keywords: food security, GARCH, grain self-sufficiency, volatility transmission

Procedia PDF Downloads 156

Authors: Sakshi Dhumale, Madhushree C., Amba Shetty

Abstract:

The effect of station density on the geostatistical prediction of groundwater levels is of critical importance to ensure accurate and reliable predictions. Monitoring station density directly impacts the accuracy and reliability of geostatistical predictions by influencing the model's ability to capture localized variations and small-scale features in groundwater levels. This is particularly crucial in regions with complex hydrogeological conditions and significant spatial heterogeneity. Insufficient station density can result in larger prediction uncertainties, as the model may struggle to adequately represent the spatial variability and correlation patterns of the data. On the other hand, an optimal distribution of monitoring stations enables effective coverage of the study area and captures the spatial variability of groundwater levels more comprehensively. In this study, we investigate the effect of station density on the predictive performance of groundwater levels using the geostatistical technique of Ordinary Kriging. The research utilizes groundwater level data collected from 121 observation wells within the semi-arid Berambadi watershed, gathered over a six-year period (2010-2015) from the Indian Institute of Science (IISc), Bengaluru. The dataset is partitioned into seven subsets representing varying sampling densities, ranging from 15% (12 wells) to 100% (121 wells) of the total well network. The results obtained from different monitoring networks are compared against the existing groundwater monitoring network established by the Central Ground Water Board (CGWB). The findings of this study demonstrate that higher station densities significantly enhance the accuracy of geostatistical predictions for groundwater levels. The increased number of monitoring stations enables improved interpolation accuracy and captures finer-scale variations in groundwater levels. These results shed light on the relationship between station density and the geostatistical prediction of groundwater levels, emphasizing the importance of appropriate station densities to ensure accurate and reliable predictions. The insights gained from this study have practical implications for designing and optimizing monitoring networks, facilitating effective groundwater level assessments, and enabling sustainable management of groundwater resources.

Keywords: station density, geostatistical prediction, groundwater levels, monitoring networks, interpolation accuracy, spatial variability

Procedia PDF Downloads 60

Authors: Ahmed I. Alutabi, Naghmeh Dezhabad, Sudhakar Ganti

Abstract:

Data centers have been growing in size and dema nd continuously in the last two decades. Planning for the deployment of resources has been shallow and always resorted to over-provisioning. Data center operators try to maximize the availability of their services by allocating multiple of the needed resources. One resource that has been wasted, with little thought, has been energy. In recent years, programmable resource allocation has paved the way to allow for more efficient and robust data centers. In this work, we examine the predictability of resource usage in a data center environment. We use a number of models that cover a wide spectrum of machine learning categories. Then we establish a framework to guarantee the client service level agreement (SLA). Our results show that using prediction can cut energy loss by up to 55%.

Keywords: machine learning, artificial intelligence, prediction, data center, resource allocation, green computing

Procedia PDF Downloads 109

Authors: James Moir

Abstract:

The mainstay of Big Data is prediction in that it allows practitioners, researchers, and policy analysts to predict trends based upon the analysis of large and varied sources of data. These can range from changing social and political opinions, patterns in crimes, and consumer behaviour. Big Data has therefore shifted the criterion of success in science from causal explanations to predictive modelling and simulation. The 19th-century science sought to capture phenomena and seek to show the appearance of it through causal mechanisms while 20th-century science attempted to save the appearance and relinquish causal explanations. Now 21st-century science in the form of Big Data is concerned with the prediction of appearances and nothing more. However, this pulls social science back in the direction of a more rule- or law-governed reality model of science and away from a consideration of the internal nature of rules in relation to various practices. In effect Big Data offers us no more than a world of surface appearance and in doing so it makes disappear any context-specific conceptual sensitivity.

Keywords: big data, appearance, disappearance, surface, epistemology

Procedia PDF Downloads 422

Authors: Yanping He-Ulbricht, Marc Oliver Rieger

Abstract:

Based on survey data collected from people with Chinese roots living in Germany, this paper examines the impact of assimilation degree and language priming (Chinese or German) on individuals’ perceived fairness of economic and social differences and their attitude towards these. The results show that both the language used and the length of time spent in a foreign culture have a significant impact. Subjects who had spent less than 10 years in Germany demonstrated a higher readiness to accept government intervention in markets with price limits than those who had lived there longer. Subjects who were asked and answered in German perceived the current economic situation as less fair and were also less inclined to accept inequality, even when it leads to a Pareto improvement. While the difference in fairness perception of inequality was a cultural effect, the difference in attitudes towards government intervention was rather a result of learning process. The findings imply that both learning processes of individuals and culture play an important role in perception and preferences regarding social and economic differences.

Keywords: assimilation, bilingualism, cross-cultural comparison, income inequality, language priming, price fairness

Procedia PDF Downloads 87

Authors: Razieh Rezaeekalantari

Abstract:

Objective: The purpose of this study was to investigate the prediction of parenting orientations in terms of the components of couples' sexual review. Methods: This was a descriptive correlational research method. The population consisted of 500 couples referring to Sari Health Center. Two hundred and fifteen (215) people were selected randomly by using Krejcie-Morgan-sample-size-table. For data collection, the childbearing orientations scale and the Multidimensional Sexual Self-Concept Questionnaire were used. Result: For data analysis, the mean and standard deviation were used and to analyze the research hypothesis regression correlation and inferential statistics were used. Conclusion: The findings indicate that there is not a significant relationship between the tendency to childbearing and the predictive value of sexual review (r = 0.84) with significant level (sig = 219.19) (P < 0.05). So, with 95% confidence, we conclude that there is not a meaningful relationship between sexual orientation and tendency to child-rearing.

Keywords: couples referring, health center, sexual review component, parenting orientations

Procedia PDF Downloads 220

Authors: Irsa Ejaz, Siyang He, Wei Li, Naiyue Hu, Chaochen Tang, Songbo Li, Meng Li, Boubacar Diallo, Guanghui Xie, Kang Yu

Abstract:

Background: Near-infrared spectroscopy (NIR) is a non-destructive, fast, and low-cost method to measure the grain quality of different cereals. Previously reported NIR model calibrations using the whole grain spectra had moderate accuracy. Improved predictions are achievable by using the spectra of whole grains, when compared with the use of spectra collected from the flour samples. However, the feasibility for determining the critical biochemicals, related to the classifications for food, feed, and fuel products are not adequately investigated. Objectives: To evaluate the feasibility of using NIRS and the influence of four sample types (whole grains, flours, hulled grain flours, and hull-less grain flours) on the prediction of chemical components to improve the grain sorting efficiency for human food, animal feed, and biofuel. Methods: NIR was applied in this study to determine the eight biochemicals in four types of sorghum samples: hulled grain flours, hull-less grain flours, whole grains, and grain flours. A total of 20 hybrids of sorghum grains were selected from the two locations in China. Followed by NIR spectral and wet-chemically measured biochemical data, partial least squares regression (PLSR) was used to construct the prediction models. Results: The results showed that sorghum grain morphology and sample format affected the prediction of biochemicals. Using NIR data of grain flours generally improved the prediction compared with the use of NIR data of whole grains. In addition, using the spectra of whole grains enabled comparable predictions, which are recommended when a non-destructive and rapid analysis is required. Compared with the hulled grain flours, hull-less grain flours allowed for improved predictions for tannin, cellulose, and hemicellulose using NIR data. Conclusion: The established PLSR models could enable food, feed, and fuel producers to efficiently evaluate a large number of samples by predicting the required biochemical components in sorghum grains without destruction.

Keywords: FT-NIR, sorghum grains, biochemical composition, food, feed, fuel, PLSR

Procedia PDF Downloads 69

Authors: Mariam Bibi, Rubab Mehboob, Mehreen Sirshar

Abstract:

Satisfying the customer requirements is the ultimate goal of producing or developing any product. The quality of the product is decided on the bases of the level of customer satisfaction. There are different techniques which have been reported during the survey which enhance the quality of the product through software defect prediction and by locating the missing software requirements. Some mining techniques were proposed to assess the individual performance indicators in collaborative environment to reduce errors at individual level. The basic intention is to produce a product with zero or few defects thereby producing a best product quality wise. In the analysis of survey the techniques like Genetic algorithm, artificial neural network, classification and clustering techniques and decision tree are studied. After analysis it has been discovered that these techniques contributed much to the improvement and enhancement of the quality of the product.

Keywords: data mining, defect prediction, missing requirements, software quality

Procedia PDF Downloads 469

Authors: P. Halder, A. Zaman

Abstract:

It is estimated that heart disease accounts for one in ten deaths worldwide. United States deaths due to heart disease are among the leading causes of death according to the World Health Organization. Cardiovascular diseases (CVDs) account for one in four U.S. deaths, according to the Centers for Disease Control and Prevention (CDC). According to statistics, women are more likely than men to die from heart disease as a result of strokes. A 50% increase in men's mortality was reported by the World Health Organization in 2009. The consequences of cardiovascular disease are severe. The causes of heart disease include diabetes, high blood pressure, high cholesterol, abnormal pulse rates, etc. Machine learning (ML) can be used to make predictions and decisions in the healthcare industry. Thus, scientists have turned to modern technologies like Machine Learning and Data Mining to predict diseases. The disease prediction is based on four algorithms. Compared to other boosts, the Ada boost is much more accurate.

Keywords: heart disease, cardiovascular disease, coronary artery disease, feature selection, random forest, AdaBoost, SVM, decision tree

Procedia PDF Downloads 154

Authors: Marcio Freire Cruz, Naoaki Ono, Shigehiko Kanaya, Carlos Arthur Mattos Teixeira Cavalcante

Abstract:

The systems that record patient care information, known as Electronic Medical Record (EMR) and those that monitor vital signs of patients, such as heart rate, body temperature, and blood pressure have been extremely valuable for the effectiveness of the patient’s treatment. Several kinds of research have been using data from EMRs and vital signs of patients to predict illnesses. Among them, we highlight those that intend to predict, classify, or, at least identify patterns, of sepsis illness in patients under vital signs monitoring. Sepsis is an organic dysfunction caused by a dysregulated patient's response to an infection that affects millions of people worldwide. Early detection of sepsis is expected to provide a significant improvement in its treatment. Preceding works usually combined medical, statistical, mathematical and computational models to develop detection methods for early prediction, getting higher accuracies, and using the smallest number of variables. Among other techniques, we could find researches using survival analysis, specialist systems, machine learning and deep learning that reached great results. In our research, patients are modeled as points moving each hour in an n-dimensional space where n is the number of vital signs (variables). These points can reach a sepsis target point after some time. For now, the sepsis target point was calculated using the median of all patients’ variables on the sepsis onset. From these points, we calculate for each hour the position vector, the first derivative (velocity vector) and the second derivative (acceleration vector) of the variables to evaluate their behavior. And we construct a prediction model based on a Long Short-Term Memory (LSTM) Network, including these derivatives as explanatory variables. The accuracy of the prediction 6 hours before the time of sepsis, considering only the vital signs reached 83.24% and by including the vectors position, speed, and acceleration, we obtained 94.96%. The data are being collected from Medical Information Mart for Intensive Care (MIMIC) Database, a public database that contains vital signs, laboratory test results, observations, notes, and so on, from more than 60.000 patients.

Keywords: dynamic analysis, long short-term memory, prediction, sepsis

Procedia PDF Downloads 126

Authors: Robert Caulk

Abstract:

A generalized framework for adaptive machine learning deployments in algorithmic trading is introduced, tested, and released as open-source code. The presented software aims to test the hypothesis that recent data contains enough information to form a probabilistically favorable short-term price prediction. Further, the framework contains various adaptive machine learning techniques that are geared toward generating profit during strong trends and minimizing losses during trend changes. Results demonstrate that this adaptive machine learning approach is capable of capturing trends and generating profit. The presentation also discusses the importance of defining the parameter space associated with the dynamic training data-set and using the parameter space to identify and remove outliers from prediction data points. Meanwhile, the generalized architecture enables common users to exploit the powerful machinery while focusing on high-level feature engineering and model testing. The presentation also highlights common strengths and weaknesses associated with the presented technique and presents a broad range of well-tested starting points for feature set construction, target setting, and statistical methods for enforcing risk management and maintaining probabilistically favorable entry and exit points. The presentation also describes the end-to-end data processing tools associated with FreqAI, including automatic data fetching, data aggregation, feature engineering, safe and robust data pre-processing, outlier detection, custom machine learning and statistical tools, data post-processing, and adaptive training backtest emulation, and deployment of adaptive training in live environments. Finally, the generalized user interface is also discussed in the presentation. Feature engineering is simplified so that users can seed their feature sets with common indicator libraries (e.g. TA-lib, pandas-ta). The user also feeds data expansion parameters to fill out a large feature set for the model, which can contain as many as 10,000+ features. The presentation describes the various object-oriented programming techniques employed to make FreqAI agnostic to third-party libraries and external data sources. In other words, the back-end is constructed in such a way that users can leverage a broad range of common regression libraries (Catboost, LightGBM, Sklearn, etc) as well as common Neural Network libraries (TensorFlow, PyTorch) without worrying about the logistical complexities associated with data handling and API interactions. The presentation finishes by drawing conclusions about the most important parameters associated with a live deployment of the adaptive learning framework and provides the road map for future development in FreqAI.

Keywords: machine learning, market trend detection, open-source, adaptive learning, parameter space exploration

Procedia PDF Downloads 89

Authors: Nini Johana Marin Rodriguez

Abstract:

This paper applies DCC, EWMA and OGARCH models to compare the dynamic correlations between exchange rates, oil prices, exchange rates and stock markets to examine the time-varying conditional correlations to the daily oil prices and index returns in relation to the US dollar/local currency for developed (Canada and Mexico) and emerging Latin American markets (Brazil, Chile, Colombia and Peru). Changes in correlation interactions are indicative of structural changes in market linkages with implications to contagion and interdependence. For each pair of stock price-exchange rate and oil price-US dollar/local currency, empirical evidence confirms of a strengthening negative correlation in the last decade. Methodologies suggest only two events have significatively impact in the countries analyzed: global financial crisis and Europe crisis, both events are associated with shifts of correlations to stronger negative level for most of the pairs analyzed. While, the first event has a shifting effect on mainly emerging members, the latter affects developed members. The identification of these relationships provides benefits in risk diversification and inflation targeting.

Keywords: crude oil, dynamic conditional correlation, exchange rates, interdependence, stock prices

Procedia PDF Downloads 308

Authors: Retno A. Vinarti, Lucy M. Hederman

Abstract:

This research describes a knowledge model for a system which give personalized alert to users about infectious disease risks in the context of weather, location and time. The knowledge model is based on established epidemiological concepts augmented by information gleaned from infection-related data repositories. The existing disease risk prediction research has more focuses on utilizing raw historical data and yield seasonal patterns of infectious disease risk emergence. This research incorporates both data and epidemiological concepts gathered from Atlas of Human Infectious Disease (AHID) and Centre of Disease Control (CDC) as basic reasoning of infectious disease risk prediction. Using CommonKADS methodology, the disease risk prediction task is an assignment synthetic task, starting from knowledge identification through specification, refinement to implementation. First, knowledge is gathered from AHID primarily from the epidemiology and risk group chapters for each infectious disease. The result of this stage is five major elements (Person, Infectious Disease, Weather, Location and Time) and their properties. At the knowledge specification stage, the initial tree model of each element and detailed relationships are produced. This research also includes a validation step as part of knowledge refinement: on the basis that the best model is formed using the most common features, Frequency-based Selection (FBS) is applied. The portion of the Infectious Disease risk model relating to Person comes out strongest, with Location next, and Weather weaker. For Person attribute, Age is the strongest, Activity and Habits are moderate, and Blood type is weakest. At the Location attribute, General category (e.g. continents, region, country, and island) results much stronger than Specific category (i.e. terrain feature). For Weather attribute, Less Precise category (i.e. season) comes out stronger than Precise category (i.e. exact temperature or humidity interval). However, given that some infectious diseases are significantly more serious than others, a frequency based metric may not be appropriate. Future work will incorporate epidemiological measurements of disease seriousness (e.g. odds ratio, hazard ratio and fatality rate) into the validation metrics. This research is limited to modelling existing knowledge about epidemiology and chain of infection concepts. Further step, verification in knowledge refinement stage, might cause some minor changes on the shape of tree.

Keywords: epidemiology, knowledge modelling, infectious disease, prediction, risk

Procedia PDF Downloads 242

Authors: Maria Amaia Iza Padilla, Ibai Ostolozaga

Abstract:

The objective of this paper is to analyze how transportation costs between regions within a country can affect not only domestic trade but also the allocation of resources in a given region, aggregate productivity, and relative domestic prices (tradable versus non-tradable). On the one hand, there is a vast literature that analyzes the transportation costs faced by countries when trading with the rest of the world. However, this paper focuses on the effect of transportation costs on domestic trade. Countries differ in their domestic road infrastructure and transport quality. There is also some literature that focuses on the effect of road infrastructure on the price difference between regions but not on relative prices at the aggregate level. On the other hand, this work is also related to the literature on resource misallocation. Finally, the paper is also related to the literature analyzing the effect of trade on the development of the manufacturing sector. Using the World Bank Enterprise Survey database, it is observed cross-country differences in the proportion of firms that consider transportation as an obstacle. From the International Comparison Program, we obtain a significant negative correlation between GDP per worker and relative prices (manufacturing sector prices relative to the service sector). Furthermore, there is a significant negative correlation between a country’s transportation quality and the relative price of manufactured goods with respect to the price of services in that country. This is consistent with the empirical evidence of a negative correlation between transportation quality and GDP per worker, on the one hand, and the negative correlation between GDP per worker and domestic relative prices, on the other. It is also shown that in a country, the share of manufacturing firms whose main market is at the local (regional) level is negatively related to the quality of the transportation infrastructure within the country. Similarly, this index is positively related to the share of manufacturing firms whose main market is national or international. The data also shows that those countries with a higher proportion of manufacturing firms operating locally have higher relative prices. With this information in hand, the paper attempts to quantify the effects of the allocation of resources between and within sectors. The higher the trade barriers caused by transportation costs, the less efficient allocation, which causes lower aggregate productivity. Second, it is built a two-sector model where regions within a country trade with each other. On the one hand, it is found that with respect to the manufacturing sector, those countries with less trade between their regions will be characterized by a smaller variety of goods, less productive manufacturing firms on average, and higher relative prices for manufactured goods relative to service sector prices. Thus, the decline in the relative price of manufactured goods in more advanced countries could also be explained by the degree of trade between regions. This trade allows for efficient intra-industry allocation (traders are more productive, and resources are allocated more efficiently)).

Keywords: misallocation, relative prices, TFP, transportation cost

Procedia PDF Downloads 86

Authors: Medani Prasad Rijal

Abstract:

The study outlines the impacts of decentralized forest policy on natural Sal (shorea robusta) forests in the Terai region of Nepal. The government has implemented community forestry program to manage the forest resources and improve the livelihood of local people collectively. The forest management authorities such as conserve, manage, develop and use of forest resources were shifted to the local communities, however, the ownership right of the forestland retained by the government. Local communities took the decision on harvesting, distribution, and sell of forest products by fixing the prices independently. The local communities were putting the low value of forest products and distributed among the user households on the name of collective decision. The decision of low valuation is devaluating the worth of forest products. Therefore, the study hypothesized that decision-making capacities are equally prominent next to the decentralized policy and program formulation. To accomplish the study, individual to group level discussions and questionnaire survey methods were applied with executive committee members and user households. The study revealed that the local intuition called Community Forest User Group (CFUG) committee normally took the decisions on consensus basis. Considering to the access and affording capacity of user households having poor economic backgrounds, low pricing mechanism of forest products has been practiced, even though the Sal timber is far expensive in the local market. The local communities thought that low pricing mechanism is accessible to all user households from poor to better off households. However, the analysis of forest products distribution opposed the assumption as most of the Sal timber, which is the most valuable forest product of community forest only purchased by the limited households of better economic conditions. Since the Terai region is heterogeneous by socio-economic conditions, better off households always have higher affording capacity and possibility of taking higher timber benefits because of low price mechanism. On the other hand, the minimum price rate of forest products has poor contribution in community fund collection. Consequently, it has poor support to carry out poverty alleviation activities to poor people. The local communities have been fixed Sal timber price rate around three times cheaper than normal market price, which is a strong evidence of forest product devaluation itself. Finally, the study concluded that the capacity building of local executives as the decision-makers of natural Sal forests is equally indispensable next to the policy and program formulation for effective decentralized forest management. Unilateral decentralized forest policy may devaluate the forest products rather than devolve of power to the local communities and empower to them.

Keywords: community forestry program, decentralized forest policy, Nepal, Sal forests, Terai

Procedia PDF Downloads 333

Authors: Michael K.O. Ayomoh, Khaled A. Abou-El-Hossein., Sameh F.M. Ghobashy

Abstract:

This paper proposes a numerical modelling scheme for surface roughness prediction. The approach is premised on the use of 3D difference analysis method enhanced with the use of feedback control loop where a set of adaptive weights are generated. The surface roughness values utilized in this paper were adapted from [1]. Their experiments were carried out using S55C high carbon steel. A comparison was further carried out between the proposed technique and those utilized in [1]. The experimental design has three cutting parameters namely: depth of cut, feed rate and cutting speed with twenty-seven experimental sample-space. The simulation trials conducted using Matlab software is of two sub-classes namely: prediction of the surface roughness readings for the non-boundary cutting combinations (NBCC) with the aid of the known surface roughness readings of the boundary cutting combinations (BCC). The following simulation involved the use of the predicted outputs from the NBCC to recover the surface roughness readings for the boundary cutting combinations (BCC). The simulation trial for the NBCC attained a state of total stability in the 7th iteration i.e. a point where the actual and desired roughness readings are equal such that error is minimized to zero by using a set of dynamic weights generated in every following simulation trial. A comparative study among the three methods showed that the proposed difference analysis technique with adaptive weight from feedback control, produced a much accurate output as against the abductive and regression analysis techniques presented in this.

Keywords: Difference Analysis, Surface Roughness; Mesh- Analysis, Feedback control, Adaptive weight, Boundary Element

Procedia PDF Downloads 622

Authors: Tebogo Emma Makaba, Barnabas Ndlovu Gatsheni

Abstract:

The cities of Johannesburg and Pretoria both located in the Gauteng province are separated by a distance of 58 km. The traffic queues on the Ben Schoeman freeway which connects these two cities can stretch for almost 1.5 km. Vehicle traffic congestion impacts negatively on the business and the commuter’s quality of life. The goal of this paper is to identify variables that influence the flow of traffic and to design a vehicle traffic prediction model, which will predict the traffic flow pattern in advance. The model will unable motorist to be able to make appropriate travel decisions ahead of time. The data used was collected by Mikro’s Traffic Monitoring (MTM). Multi-Layer perceptron (MLP) was used individually to construct the model and the MLP was also combined with Bagging ensemble method to training the data. The cross—validation method was used for evaluating the models. The results obtained from the techniques were compared using predictive and prediction costs. The cost was computed using combination of the loss matrix and the confusion matrix. The predicted models designed shows that the status of the traffic flow on the freeway can be predicted using the following parameters travel time, average speed, traffic volume and day of month. The implications of this work is that commuters will be able to spend less time travelling on the route and spend time with their families. The logistics industry will save more than twice what they are currently spending.

Keywords: bagging ensemble methods, confusion matrix, multi-layer perceptron, vehicle traffic flow

Procedia PDF Downloads 344

Authors: Lei Zhu, Nan Li

Abstract:

Cold stamping has been widely applied in the automotive industry for the mass production of a great range of automotive panels. Predicting the springback to ensure the dimensional accuracy of the cold-stamped components is a critical step. The main approaches for the prediction and compensation of springback in cold stamping include running Finite Element (FE) simulations and conducting experiments, which require forming process expertise and can be time-consuming and expensive for the design of cold stamping tools. Machine learning technologies have been proven and successfully applied in learning complex system behaviours using presentative samples. These technologies exhibit the promising potential to be used as supporting design tools for metal forming technologies. This study, for the first time, presents a novel application of a Convolutional Neural Network (CNN) based surrogate model to predict the springback fields for variable U-shape cold bending geometries. A dataset is created based on the U-shape cold bending geometries and the corresponding FE simulations results. The dataset is then applied to train the CNN surrogate model. The result shows that the surrogate model can achieve near indistinguishable full-field predictions in real-time when compared with the FE simulation results. The application of CNN in efficient springback prediction can be adopted in industrial settings to aid both conceptual and final component designs for designers without having manufacturing knowledge.

Keywords: springback, cold stamping, convolutional neural networks, machine learning

Procedia PDF Downloads 151

Authors: Almostafa Abdelaziz, Liang Guozhu, Anwer Elsayed

Abstract:

The determination of grain geometry is an important and critical step in the design of solid propellant rocket motor. In this study, the design process involved parametric geometry modeling in CAD, MATLAB coding of performance prediction and 2D star grain ignition experiment. The 2D star grain burnback achieved by creating new surface via each web increment and calculating geometrical properties at each step. The 2D star grain is further modified to burn as a tapered 3D star grain. Zero dimensional method used to calculate the internal ballistic performance. Experimental and theoretical results were compared in order to validate the performance prediction of the solid rocket motor. The results show that the usage of 3D grain geometry will decrease the pressure inside the combustion chamber and enhance the volumetric loading ratio.

Keywords: burnback analysis, rocket motor, star grain, three dimensional grains

Procedia PDF Downloads 245

Authors: Rania Sherif Abd El-Azim

Abstract:

The role of corporate social responsibility (CSR) in business has evolved and led to an era where industry leaders can no longer overlook the importance of being participative corporate citizens. This is not only because of the media’s skeptical attitude toward whether or not companies’ CSR efforts are sincere but also due to key stakeholders’ ability to hold companies to a higher standard than ever before as companies can gain competitive advantage through CSR. These programs result in addressing global challenges, such as climate, and poverty, or simply improving employee retention, so it has become increasingly clear that CSR is not just the new trend for companies but a necessary tool that organizations must integrate into their overall business strategies to build a stronger reputation as well as to also increase credibility among their key audience and enhance customers’ willingness to repurchase, pay premium price and enhancing positive word of mouth. According to the literature review, the link between CSR and competitive advantage at the firm level has long been an important topic for both CSR researchers and practitioners. Thus CSR can play an important role in enhancing the firm's competitive advantage, which seems an attractive area to investigate specially in Egypt. So, this paper will investigate the role of corporate social responsibility in enhancing the firm competitive advantage.

Keywords: corporate social responsibility, competitive advantage, corporate reputation, customers' willingness to repurchase, willingness to pay premium price, positive word of mouth

Procedia PDF Downloads 325