Search results for: random effects model

Authors: Swathi Ganesan, Nalinda Somasiri, Rebecca Jeyavadhanam, Gayathri Karthick

Abstract:

The COVID-19 crisis presents a substantial and critical hazard to worldwide health. Since the occurrence of the disease in late January 2020 in the UK, the number of infected people confirmed to acquire the illness has increased tremendously across the country, and the number of individuals affected is undoubtedly considerably high. The purpose of this research is to figure out a predictive machine learning archetypal that could forecast COVID-19 cases within the UK. This study concentrates on the statistical data collected from 31st January 2020 to 31st March 2021 in the United Kingdom. Information on total COVID cases registered, new cases encountered on a daily basis, total death registered, and patients’ death per day due to Coronavirus is collected from World Health Organisation (WHO). Data preprocessing is carried out to identify any missing values, outliers, or anomalies in the dataset. The data is split into 8:2 ratio for training and testing purposes to forecast future new COVID cases. Support Vector Machines (SVM), Random Forests, and linear regression algorithms are chosen to study the model performance in the prediction of new COVID-19 cases. From the evaluation metrics such as r-squared value and mean squared error, the statistical performance of the model in predicting the new COVID cases is evaluated. Random Forest outperformed the other two Machine Learning algorithms with a training accuracy of 99.47% and testing accuracy of 98.26% when n=30. The mean square error obtained for Random Forest is 4.05e11, which is lesser compared to the other predictive models used for this study. From the experimental analysis Random Forest algorithm can perform more effectively and efficiently in predicting the new COVID cases, which could help the health sector to take relevant control measures for the spread of the virus.

Keywords: COVID-19, machine learning, supervised learning, unsupervised learning, linear regression, support vector machine, random forest

Procedia PDF Downloads 87

Authors: H. Triki, Y. Hamaizi, A. El-Akrmi

Abstract:

We consider the higher order nonlinear Schrödinger equation model with fourth-order dispersion, cubic-quintic terms, and self-steepening. This equation governs the propagation of fem to second pulses in optical fibers. We present new bright and dark solitary wave type solutions for such a model under certain parametric conditions. This kind of solution may be useful to explain some physical phenomena related to wave propagation in a nonlinear optical fiber systems supporting high-order nonlinear and dispersive effects.

Keywords: nonlinear Schrödinger equation, high-order effects, soliton solution

Procedia PDF Downloads 599

Authors: Fawaz Abdulmalek

Abstract:

The two-stage flowshop assembly scheduling problem is considered in this paper. There are more than one parallel machines at stage one and an assembly machine at stage two. The jobs will be processed into the flowshop based on Johnson rule and two extensions of Johnson rule. A simulation model of the two-stage flowshop is constructed where both machines at stage one are subject to random failures. Three simulation experiments will be conducted to test the effect of the three job ranking rules on the makespan. Johnson Largest heuristic outperformed both Johnson rule and Johnson Smallest heuristic for two performed experiments for all scenarios where each experiments having five scenarios.

Keywords: flowshop scheduling, random failures, johnson rule, simulation

Procedia PDF Downloads 306

Authors: Gultekin Gurcay

Abstract:

In this paper, effects and responses of stock were analyzed. This analysis was done periodically. The dimensions of the financial crisis impact on the stock market were investigated by GARCH model. In this context, S&P 500 stock market is modeled with DAX, NIKKEI and BIST100. In this way, The effects of the changing in S&P 500 stock market were examined on European and Asian stock markets. Conditional variance coefficient will be calculated through garch model. The scope of the crisis period, the conditional covariance coefficient will be analyzed comparatively.

Keywords: conditional variance coefficient, financial crisis, garch model, stock market

Procedia PDF Downloads 261

Authors: Yaowei Hu, Yongkai Wu, Lu Zhang, Xintao Wu

Abstract:

Causal inference from observational data is receiving wide applications in many fields. However, unidentifiable situations, where causal effects cannot be uniquely computed from observational data, pose critical barriers to applying causal inference to complicated real applications. In this paper, we develop a bounding method for estimating the average causal effect (ACE) under unidentifiable situations due to hidden confounders. We propose to parameterize the unknown exogenous random variables and structural equations of a causal model using neural networks and implicit generative models. Then, with an adversarial learning framework, we search the parameter space to explicitly traverse causal models that agree with the given observational distribution and find those that minimize or maximize the ACE to obtain its lower and upper bounds. The proposed method does not make any assumption about the data generating process and the type of the variables. Experiments using both synthetic and real-world datasets show the effectiveness of the method.

Keywords: average causal effect, hidden confounding, bound estimation, generative adversarial learning

Procedia PDF Downloads 153

Authors: Thota Sai Prakash, B. Yaswanth, Jhade Bhuvaneswar, Marreddy Divakar Reddy, Shyam Ji Gupta

Abstract:

Across the globe, there are a lot of chronic diseases, and heart disease stands out as one of the most perilous. Sadly, many lives are lost to this condition, even though early intervention could prevent such tragedies. However, identifying heart disease in its initial stages is not easy. To address this challenge, we propose an automated system aimed at predicting the presence of heart disease using advanced techniques. By doing so, we hope to empower individuals with the knowledge needed to take proactive measures against this potentially fatal illness. Our approach towards this problem involves meticulous data preprocessing and the development of predictive models utilizing classification algorithms such as Support Vector Machines (SVM), Decision Tree, and Random Forest. We assess the efficiency of every model based on metrics like accuracy, ensuring that we select the most reliable option. Additionally, we conduct thorough data analysis to reveal the importance of different attributes. Among the models considered, Random Forest emerges as the standout performer with an accuracy rate of 96.04% in our study.

Keywords: support vector machines, decision tree, random forest

Procedia PDF Downloads 9

Authors: Shabnam Najafi, Metin Turkay

Abstract:

Network design problem (NDP) is used to determine the set of optimal values for certain pre-specified decision variables such as capacity expansion of nodes and links by optimizing various system performance measures including safety, congestion, and accessibility. The designed transportation network should improve objective functions defined for the system by considering the route choice behaviors of network users at the same time. The NDP studies mostly investigated the random demand and route selection constraints separately due to computational challenges. In this work, we consider both random demand and route selection constraints simultaneously. This work presents a nonlinear stochastic model for land use and road network design problem to address the development of different functional zones in urban areas by considering both cost function and air pollution. This model minimizes cost function and air pollution simultaneously with random demand and stochastic route selection constraint that aims to optimize network performance via road capacity expansion. The Bureau of Public Roads (BPR) link impedance function is used to determine the travel time function in each link. We consider a city with origin and destination nodes which can be residential or employment or both. There are set of existing paths between origin-destination (O-D) pairs. Case of increasing employed population is analyzed to determine amount of roads and origin zones simultaneously. Minimizing travel and expansion cost of routes and origin zones in one side and minimizing CO emission in the other side is considered in this analysis at the same time. In this work demand between O-D pairs is random and also the network flow pattern is subject to stochastic user equilibrium, specifically logit route choice model. Considering both demand and route choice, random is more applicable to design urban network programs. Epsilon-constraint is one of the methods to solve both linear and nonlinear multi-objective problems. In this work epsilon-constraint method is used to solve the problem. The problem was solved by keeping first objective (cost function) as the objective function of the problem and second objective as a constraint that should be less than an epsilon, where epsilon is an upper bound of the emission function. The value of epsilon should change from the worst to the best value of the emission function to generate the family of solutions representing Pareto set. A numerical example with 2 origin zones and 2 destination zones and 7 links is solved by GAMS and the set of Pareto points is obtained. There are 15 efficient solutions. According to these solutions as cost function value increases, emission function value decreases and vice versa.

Keywords: epsilon-constraint, multi-objective, network design, stochastic

Procedia PDF Downloads 616

Authors: Mehmet Savsar, Majid Aldaihani

Abstract:

Flexible Manufacturing Systems (FMS) are used to produce a variety of parts on the same equipment. Therefore, their utilization is higher than traditional machining systems. Higher utilization, on the other hand, results in more frequent equipment failures and additional need for maintenance. Therefore, it is necessary to carefully analyze operational characteristics and productivity of FMS or Flexible Manufacturing Cells (FMC), which are smaller configuration of FMS, before installation or during their operation. Appropriate models should be developed to determine production rates based on operational conditions, including equipment reliability, availability, and repair capacity. In this paper, a stochastic model is developed for an automated FMC system, which consists of two machines served by two robots and a single repairman. The model is used to determine system productivity and equipment utilization under different operational conditions, including random machine failures, random repairs, and limited repair capacity. The results are compared to previous study results for FMC system with sufficient repair capacity assigned to each machine. The results show that the model will be useful for design engineers and operational managers to analyze performance of manufacturing systems at the design or operational stages.

Keywords: flexible manufacturing, FMS, FMC, stochastic modeling, production rate, reliability, availability

Procedia PDF Downloads 491

Authors: Serpil Türkyılmaz, Mesut Balıbey

Abstract:

In this study, long memory properties in volatility of Turkey Stock Market are being examined through the FIGARCH, FIEGARCH and FIAPARCH models under different distribution assumptions as normal and skewed student-t distributions. Furthermore, structural changes in volatility of Turkey Stock Market are investigated. The results display long memory property and the presence of asymmetric effects of shocks in volatility of Turkey Stock Market.

Keywords: FIAPARCH model, FIEGARCH model, FIGARCH model, structural break

Procedia PDF Downloads 266

Authors: Michael A. Kraus, Navid Pourmoghaddam, Martin Botz, Jens Schneider, Geralt Siebert

Abstract:

Fragmentation analysis of tempered glass gives insight into the quality of the tempering process and defines a certain degree of safety as well. Different standard such as the European EN 12150-1 or the American ASTM C 1048/CPSC 16 CFR 1201 define a minimum number of fragments required for soda-lime safety glass on the basis of fragmentation test results for classification. This work presents an approach for the glass breakage pattern prediction using a Voronoi Tesselation over Random Fields. The random Voronoi tessellation is trained with and validated against data from several breakage patterns. The fragments in observation areas of 50 mm x 50 mm were used for training and validation. All glass specimen used in this study were commercially available soda-lime glasses at three different thicknesses levels of 4 mm, 8 mm and 12 mm. The results of this work form a Bayesian framework for the training and prediction of breakage patterns of tempered soda-lime glass using a Voronoi Random Field Tesselation. Uncertainties occurring in this process can be well quantified, and several statistical measures of the pattern can be preservation with this method. Within this work it was found, that different Random Fields as basis for the Voronoi Tesselation lead to differently well fitted statistical properties of the glass breakage patterns. As the methodology is derived and kept general, the framework could be also applied to other random tesselations and crack pattern modelling purposes.

Keywords: glass breakage predicition, Voronoi Random Field Tessellation, fragmentation analysis, Bayesian parameter identification

Procedia PDF Downloads 131

Authors: L. Yettou

Abstract:

In this study, the calculations of proton emission spectra produced by ⁶³Cu(n,xp) and ⁶⁵Cu(n,xp) reactions are used in the framework of preequilibrium models using the EMPIRE code and TALYS code. Exciton Model predidtions combined with the Kalbach angular distribution systematics and the Hybrid Monte Carlo Simulation (HMS) were used. The effects of levels densities and those of a-parameter have been investigated for our calculations. The comparison with experimental data shows clear improvement over the Exciton Model and HMS calculations.

Keywords: Preequilibrium models , level density, level density a-parameter., Empire code, Talys code.

Procedia PDF Downloads 102

Authors: Alpana Goel, Kawalpreet Kalra

Abstract:

The study of level structures of deformed nuclei is the most complex topic in nuclear physics. For the description of level structure, a simple model is good enough to bring out the basic features which may then be further refined. The low lying level structures of these nuclei can, therefore, be understood in terms of Two Quasiparticle plus axially symmetric Rotor Model (TQPRM). The formulation of TQPRM for deformed nuclei has been presented. The analysis of available experimental data on two quasiparticle rotational bands of deformed nuclei present unusual features like signature dependence, odd-even staggering, signature inversion and signature reversal in two quasiparticle rotational bands of deformed nuclei. These signature effects are well discussed within the framework of TQPRM. The model is well efficient in reproducing the large odd-even staggering and anomalous features observed in even-even and odd-odd deformed nuclei. The effect of particle-particle and the Coriolis coupling is well established from the model. Detailed description of the model with implications to deformed nuclei is presented in the paper.

Keywords: deformed nuclei, signature effects, signature inversion, signature reversal

Procedia PDF Downloads 140

Authors: I. Wiedemann, A. R. Sharifi, A. Mählmeyer, C. Knorr

Abstract:

A requirement for sperm motility is a morphologically intact flagellum with a central axoneme. The flagellar beating is caused by the varying activation and inactivation of dynein molecules which are located in the axoneme. DNAL4 (dynein, axonemal, light chain 4) is regarded as a possible functional candidate gene encoding a small subunit of the dyneins. In the present study, 5814bp of the porcine DNAL4 (GenBank Acc. No. AM284696.1, 6097 bp, 4 exons) were comparatively sequenced using three boars with a high motility (>68%) and three with a low motility (<60%). Primers were self-designed except for those covering exons 1, 2 and 3. Prior to sequencing, the PCR products were purified. Sequencing was performed with an ABI PRISM 3100 Genetic Analyzer using the BigDyeTM Terminator v3.1 Cycle Sequencing Reaction Kit. Finally, 23 SNPs were described and genotyped for 82 AI boars representing the breeds Piétrain, German Large White and German Landrace. The genotypes were used to assess possible associations with standard spermatological parameters (ejaculate volume, density, and sperm motility (undiluted (Motud), 24h (Mot1) and 48h (Mot2) after semen collection) that were regularly recorded on the AI station. The analysis included a total of 8,833 spermatological data sets which ranged from 2 to 295 sets per boar in five years. Only SNP g.1007A>G had a significant effect. Finally, the gene substitution effect using the following statistical model was calculated: Yijk= µ+αi+βj+αβij+b1Sijk+b2Aijk+b3T ijk + b4Vijk+b5(α*A)ijk +b6(β*A)ijk+b7(A*T)ijk+Uijk+eijk where Yijk is the semen characteristics, µ is the general mean, α is the main effect of breed, β is the main effect of season, S is the effect of SNP (g.1007A > G), A is the effect of age at semen collection, V is the effect of diluter, αβ, α*A, β*A, A*T are interactions between the fixed effects, b1-b7 are regression coefficients between y and the respective covariate, U is the random effect of repeated observation on animal and e is the random error. The results from the single marker regression analysis revealed highly significant effects (p < 0.0001) of SNP g.1007A > G on Mot1 resp. on Mot2, resulting in a marked reduction by 11.4% resp. 15.4%. Furthermore a loss of Motud by 4.6% was detected (p < 0.0178). Considering the SNP g.1007A > G as a main factor (dominant-recessive model), significant differences between genotypes AA and AG as well as AA and GG for Mot1 and Mot2 exist. For Motud there was a significant difference between AA and GG.

Keywords: association, DNAL4, porcine, sperm traits

Procedia PDF Downloads 427

Authors: S. Rostami, S. H. Hosseini, A. A. Torabi, M. Bekhradi

Abstract:

Introduction: Interest in the use of caffeine as an ergogenic aid has increased since the International Olympic Committee lifted the partial ban on its use. Caffeine has beneficial effects on various aspects of athletic performance, but its effects on training have been neglected. The purpose of this study was to investigate the acute effect of caffeine on testosterone and cortisole in young futsal players. Methods: Twenty-four professional futsal players with 18.3± 1.9 years ingested caffeine doses of 0, 200 and 800 mg in random order 1 hr before an anaerobic-exercise session (RAST test). Samples were taken at the time of caffeine ingestion and 30 min after the session. Data were log-transformed to estimate percent effects with mixed modeling, and effects were standardized to assess magnitudes. fects on training have been neglected. Results: Testosterone concentration showed a small increase of 15% (90% confidence limits, ± 19%) during exercise. Caffeine raised this concentration in a dose-dependent manner by a further small 21% (± 24%) at the highest dose. The 800-mg dose also produced a moderate 52% (± 44%) increase in cortisol. The effect of caffeine on the testosterone: cortisol ratio was a small decline (14%; ± 21%). Discussion and Conclusion: Caffeine has some potential to benefit training outcomes via the anabolic effects of the increase in testosterone concentration, but this benefit might be counteracted by the opposing catabolic effects of the increase in cortisol and resultant decline in the testosterone: cortisol ratio.

Keywords: anabolic, catabolic, performance, testosterone, cortisol ratio, RAST test

Procedia PDF Downloads 415

Authors: Zafer Yüce, Paşa Yayla, Alev Taşkın

Abstract:

There are heaps of analytical methods to estimate the crack growth life of a component. Soft computing methods have an increasing trend in predicting fatigue life. Their ability to build complex relationships and capability to handle huge amounts of data are motivating researchers and industry professionals to employ them for challenging problems. This study focuses on soft computing methods, especially random forest regressors and artificial neural networks with hyperparameter optimization algorithms such as grid search and random grid search, to estimate the crack growth life of an aircraft wing splice joint under variable amplitude loading. TensorFlow and Scikit-learn libraries of Python are used to build the machine learning models for this study. The material considered in this work is 7050-T7451 aluminum, which is commonly preferred as a structural element in the aerospace industry, and regarding the crack type; corner crack is used. A finite element model is built for the joint to calculate fastener loads and stresses on the structure. Since finite element model results are validated with analytical calculations, findings of the finite element model are fed to AFGROW software to calculate analytical crack growth lives. Based on Fighter Aircraft Loading Standard for Fatigue (FALSTAFF), 90 unique fatigue loading spectra are developed for various load levels, and then, these spectrums are utilized as inputs to the artificial neural network and random forest regression models for predicting crack growth life. Finally, the crack growth life predictions of the machine learning models are compared with analytical calculations. According to the findings, a good correlation is observed between analytical and predicted crack growth lives.

Keywords: aircraft, fatigue, joint, life, optimization, prediction.

Procedia PDF Downloads 138

Authors: Sergey Kuznetsov, Yuri Urman

Abstract:

We present an approach to investigate non-linear dynamical effects occurring in the noncontact superconducting and diamagnetic suspensions, when levitated body has finite size. This approach is based on the calculation of interaction energy between spherical finite size superconducting or diamagnetic body with external magnetic field. Effects of small deviations from spherical shape may be also taken into account by introducing small corrections to the energy. This model allows investigating dynamical effects important for practical applications, such as nonlinear resonances, change of vibration plane, coupling of rotational and translational motions etc. We also show how the geometry of suspension affects various dynamical effects and how an inverse problem may be formulated to enforce or diminish various dynamical effects.

Keywords: levitation, non-linear dynamics, superconducting, diamagnetic stability

Procedia PDF Downloads 373

Authors: Van Truong Pham

Abstract:

Background: Self-management was described as a potential strategy for blood pressure control in patients with hypertension. However, the effects of self-management interventions on blood pressure, self-efficacy, medication adherence, and body mass index (BMI) in older adults with hypertension have not been systematically evaluated. We evaluated the effects of self-management interventions on systolic blood pressure (SBP) and diastolic blood pressure (DBP), self-efficacy, medication adherence, and BMI in hypertensive older adults. Methods: We followed the recommended guidelines of preferred reporting items for systematic reviews and meta-analyses. Searches in electronic databases including CINAHL, Cochrane Library, Embase, Ovid-Medline, PubMed, Scopus, Web of Science, and other sources were performed to include all relevant studies up to April 2019. Studies selection, data extraction, and quality assessment were performed by two reviewers independently. We summarized intervention effects as Hedges' g values and 95% confidence intervals (CI) using a random-effects model. Data were analyzed using Comprehensive Meta-Analysis software 2.0. Results: Twelve randomized controlled trials met our inclusion criteria. The results revealed that self-management interventions significantly improved blood pressure control, self-efficacy, medication adherence, whereas the effect of self-management on BMI was not significant in older adult patients with hypertension. The following Hedges' g (effect size) values were obtained: SBP, -0.34 (95% CI, -0.51 to -0.17, p < 0.001); DBP, -0.18 (95% CI, -0.30 to -0.05, p < 0.001); self-efficacy, 0.93 (95%CI, 0.50 to 1.36, p < 0.001); medication adherence, 1.72 (95%CI, 0.44 to 3.00, p=0.008); and BMI, -0.57 (95%CI, -1.62 to 0.48, p = 0.286). Conclusions: Self-management interventions significantly improved blood pressure control, self-efficacy, and medication adherence. However, the effects of self-management on obesity control were not supported by the evidence. Healthcare providers should implement self-management interventions to strengthen patients' role in managing their health care.

Keywords: self-management, meta-analysis, blood pressure control, self-efficacy, medication adherence, body mass index

Procedia PDF Downloads 97

Authors: Luma Al-Tamimi, Hassan Farhat, Wessam Hasan

Abstract:

A three-dimensional (3D) hybrid quasi-steady thermal lattice Boltzmann model is developed to couple the effects of surfactant, temperature, interfacial tension, and contact angle. This 3D model is an extended scheme of a previously introduced two-dimensional (2D) hybrid lattice Boltzmann model. The 3D model is used to study the combined multi-physics effects on emulsion systems flowing in rectangular microchannels with and without confinements, where the suspended phase is made of droplets, plugs, or a mixture of both. The simulation results show that emulsion systems with plugs as the suspended phase are more efficient than with droplets, whereas mixed systems that form large plugs through coalescence have even greater efficiency. The 3D contact angle model generates matching results to those of the 2D model, which were validated with experiments. Furthermore, the effects of various confinements on adhering single drop systems are investigated for delineating their influence on the power required for transporting the suspended phase through the channel. It is shown that the deeper the constriction is, the lower the system efficiency. Increasing the surfactant concentration or fluid temperature in a channel with confinement carries a substantial positive effect on oil droplet transportation.

Keywords: lattice Boltzmann method, thermal, contact angle, surfactants, high viscosity ratio, porous media

Procedia PDF Downloads 152

Authors: Anderson Ngowa Chembe, John Olukuru

Abstract:

Greenhouse emissions by human activities are known to irreversibly increase global temperatures through the greenhouse effect. This study seeks to propose a mortality model with sensitivity to heat-change effects as one of the underlying parameters in the model. As such, the study sought to establish the relationship between greenhouse emissions and mortality indices in five OECD countries (USA, UK, Japan, Canada & Germany). Upon the establishment of the relationship using correlation analysis, an additional parameter that accounts for the sensitivity of heat-changes to mortality rates was incorporated in the Lee-Carter model. Based on the proposed model, new parameter estimates were calculated using iterative algorithms for optimization. Finally, the goodness of fit for the original Lee-Carter model and the proposed model were compared using deviance comparison. The proposed model provides a better fit to mortality rates especially in USA, UK and Germany where the mortality indices have a strong positive correlation with the level of greenhouse emissions. The results of this study are of particular importance to actuaries, demographers and climate-risk experts who seek to use better mortality-modeling techniques in the wake of heat effects caused by increased greenhouse emissions.

Keywords: climate risk, greenhouse emissions, Lee-Carter model, OECD

Procedia PDF Downloads 310

Authors: Nadia Adnan, Muhammad Mohsin Raza, Latha Ravindran

Abstract:

Based on the principles above, the study presents an economic model of food waste for consumers, intermediaries, and producers. We discriminate between purchasing and selling, purchases versus customers consumption, and gross output versus sales for each intermediary. To compensate for waste at each level of the supply chain, agents must charge higher sales prices. The research model can produce more accurate predictions about how actions (public regulations or private efforts) to reduce food waste impact markets, including indirect (cascading) effects. With a formal model, researchers demonstrate the uniqueness of these interaction effects and simulate an empirical model calibrated to market characteristics and waste rates in Saudi Arabia. Researchers demonstrate that the effects of waste reduction differ per commodity, depending on supply and demand elasticities, degree of openness to international commerce, and the beginning rates of food loss and waste at each level of the value chain. Because of the consequential effects related to the supply chain, initiatives to minimize food waste will be strengthened in some circumstances and partially countered in others.

Keywords: food loss, food waste, supply chain management, Saudi Arabia, food supply

Procedia PDF Downloads 72

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 66

Authors: André Jesus, Yanjie Zhu, Irwanda Laory

Abstract:

Structural health monitoring is one of the most promising technologies concerning aversion of structural risk and economic savings. Analysts often have to deal with a considerable variety of uncertainties that arise during a monitoring process. Namely the widespread application of numerical models (model-based) is accompanied by a widespread concern about quantifying the uncertainties prevailing in their use. Some of these uncertainties are related with the deterministic nature of the model (code uncertainty) others with the variability of its inputs (parameter uncertainty) and the discrepancy between a model/experiment (systematic uncertainty). The actual process always exhibits a random behaviour (observation error) even when conditions are set identically (residual variation). Bayesian inference assumes that parameters of a model are random variables with an associated PDF, which can be inferred from experimental data. However in many Bayesian methods the determination of systematic uncertainty can be problematic. In this work systematic uncertainty is associated with a discrepancy function. The numerical model and discrepancy function are approximated by Gaussian processes (surrogate model). Finally, to avoid the computational burden of a fully Bayesian approach the parameters that characterise the Gaussian processes were estimated in a four stage process (modular Bayesian approach). The proposed methodology has been successfully applied on fields such as geoscience, biomedics, particle physics but never on the SHM context. This approach considerably reduces the computational burden; although the extent of the considered uncertainties is lower (second order effects are neglected). To successfully identify the considered uncertainties this formulation was extended to consider multiple responses. The efficiency of the algorithm has been tested on a small scale aluminium bridge structure, subjected to a thermal expansion due to infrared heaters. Comparison of its performance with responses measured at different points of the structure and associated degrees of identifiability is also carried out. A numerical FEM model of the structure was developed and the stiffness from its supports is considered as a parameter to calibrate. Results show that the modular Bayesian approach performed best when responses of the same type had the lowest spatial correlation. Based on previous literature, using different types of responses (strain, acceleration, and displacement) should also improve the identifiability problem. Uncertainties due to parametric variability, observation error, residual variability, code variability and systematic uncertainty were all recovered. For this example the algorithm performance was stable and considerably quicker than Bayesian methods that account for the full extent of uncertainties. Future research with real-life examples is required to fully access the advantages and limitations of the proposed methodology.

Keywords: bayesian, calibration, numerical model, system identification, systematic uncertainty, Gaussian process

Procedia PDF Downloads 301

Authors: Hung-Chi Chang

Abstract:

For an extended EPQ model with random yield, the existent study revealed that both the disaggregating and consolidating shipment policies for the imperfect quality items are independent of holding cost, and recommended a model with economic benefit by comparing the least total cost for each of the three models investigated. To better capture the real situation, we generalize the existent study to include different holding costs for perfect and imperfect quality items. Through analysis, we show that the above shipment policies are dependent on holding costs. Furthermore, we derive a simple decision rule solely based on the thresholds of problem parameters to select a superior model. The results are illustrated analytically and numerically.

Keywords: consolidating shipments, disaggregating shipments, EPQ, imperfect quality, inventory

Procedia PDF Downloads 348

Authors: Gajendra Kumar Mourya, Dinesh Bhatia, Akash Handique, Sunita Warjri, Syed Achaab Amir

Abstract:

Nowadays, Medical imaging has become an integral part of modern healthcare. Abdominal CT images are an invaluable mean for abdominal organ investigation and have been widely studied in the recent years. Diagnosis of liver pathologies is one of the major areas of current interests in the field of medical image processing and is still an open problem. To deeply study and diagnose the liver, segmentation of liver is done to identify which part of the liver is mostly affected. Manual segmentation of the liver in CT images is time-consuming and suffers from inter- and intra-observer differences. However, automatic or semi-automatic computer aided segmentation of the Liver is a challenging task due to inter-patient Liver shape and size variability. In this paper, we present a technique for automatic segmenting the liver from CT images using Random Forest Classifier. Random forests or random decision forests are an ensemble learning method for classification that operate by constructing a multitude of decision trees at training time and outputting the class that is the mode of the classes of the individual trees. After comparing with various other techniques, it was found that Random Forest Classifier provide a better segmentation results with respect to accuracy and speed. We have done the validation of our results using various techniques and it shows above 89% accuracy in all the cases.

Keywords: CT images, image validation, random forest, segmentation

Procedia PDF Downloads 281

Authors: Sasiporn Rattanasupha, Settapat Chinviriyasit

Abstract:

The treatment function adopts a continuous and differentiable function which can describe the effect of delayed treatment when the number of infected individuals increases and the medical condition is limited. In this paper, the SEIR epidemic model with treatment function is studied to investigate the dynamics of the model due to the effect of treatment. It is assumed that the treatment rate is proportional to the number of infective patients. The stability of the model is analyzed. The model is simulated to illustrate the analytical results and to investigate the effects of treatment on the spread of infection.

Keywords: basic reproduction number, local stability, SEIR epidemic model, treatment function

Procedia PDF Downloads 486

Authors: Xiangtuo Chen, Paul-Henry Cournéde

Abstract:

Crop yield prediction is a paramount issue in agriculture. The main idea of this paper is to find out efficient way to predict the yield of corn based meteorological records. The prediction models used in this paper can be classified into model-driven approaches and data-driven approaches, according to the different modeling methodologies. The model-driven approaches are based on crop mechanistic modeling. They describe crop growth in interaction with their environment as dynamical systems. But the calibration process of the dynamic system comes up with much difficulty, because it turns out to be a multidimensional non-convex optimization problem. An original contribution of this paper is to propose a statistical methodology, Multi-Scenarios Parameters Estimation (MSPE), for the parametrization of potentially complex mechanistic models from a new type of datasets (climatic data, final yield in many situations). It is tested with CORNFLO, a crop model for maize growth. On the other hand, the data-driven approach for yield prediction is free of the complex biophysical process. But it has some strict requirements about the dataset. A second contribution of the paper is the comparison of these model-driven methods with classical data-driven methods. For this purpose, we consider two classes of regression methods, methods derived from linear regression (Ridge and Lasso Regression, Principal Components Regression or Partial Least Squares Regression) and machine learning methods (Random Forest, k-Nearest Neighbor, Artificial Neural Network and SVM regression). The dataset consists of 720 records of corn yield at county scale provided by the United States Department of Agriculture (USDA) and the associated climatic data. A 5-folds cross-validation process and two accuracy metrics: root mean square error of prediction(RMSEP), mean absolute error of prediction(MAEP) were used to evaluate the crop prediction capacity. The results show that among the data-driven approaches, Random Forest is the most robust and generally achieves the best prediction error (MAEP 4.27%). It also outperforms our model-driven approach (MAEP 6.11%). However, the method to calibrate the mechanistic model from dataset easy to access offers several side-perspectives. The mechanistic model can potentially help to underline the stresses suffered by the crop or to identify the biological parameters of interest for breeding purposes. For this reason, an interesting perspective is to combine these two types of approaches.

Keywords: crop yield prediction, crop model, sensitivity analysis, paramater estimation, particle swarm optimization, random forest

Procedia PDF Downloads 205

Authors: Deniz Peksen

Abstract:

This thesis aims to predict trend movement of closing price of stock and to maximize portfolio by utilizing the predictions. In this context, the study aims to define a stock portfolio strategy from models created by using Logistic Regression, Gradient Boosting and Random Forest. Recently, predicting the trend of stock price has gained a significance role in making buy and sell decisions and generating returns with investment strategies formed by machine learning basis decisions. There are plenty of studies in the literature on the prediction of stock prices in capital markets using machine learning methods but most of them focus on closing prices instead of the direction of price trend. Our study differs from literature in terms of target definition. Ours is a classification problem which is focusing on the market trend in next 20 trading days. To predict trend direction, fourteen years of data were used for training. Following three years were used for validation. Finally, last three years were used for testing. Training data are between 2002-06-18 and 2016-12-30 Validation data are between 2017-01-02 and 2019-12-31 Testing data are between 2020-01-02 and 2022-03-17 We determine Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate as benchmarks which we should outperform. We compared our machine learning basis portfolio return on test data with return of Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate. We assessed our model performance with the help of roc-auc score and lift charts. We use logistic regression, Gradient Boosting and Random Forest with grid search approach to fine-tune hyper-parameters. As a result of the empirical study, the existence of uptrend and downtrend of five stocks could not be predicted by the models. When we use these predictions to define buy and sell decisions in order to generate model-based-portfolio, model-based-portfolio fails in test dataset. It was found that Model-based buy and sell decisions generated a stock portfolio strategy whose returns can not outperform non-model portfolio strategies on test dataset. We found that any effort for predicting the trend which is formulated on stock price is a challenge. We found same results as Random Walk Theory claims which says that stock price or price changes are unpredictable. Our model iterations failed on test dataset. Although, we built up several good models on validation dataset, we failed on test dataset. We implemented Random Forest, Gradient Boosting and Logistic Regression. We discovered that complex models did not provide advantage or additional performance while comparing them with Logistic Regression. More complexity did not lead us to reach better performance. Using a complex model is not an answer to figure out the stock-related prediction problem. Our approach was to predict the trend instead of the price. This approach converted our problem into classification. However, this label approach does not lead us to solve the stock prediction problem and deny or refute the accuracy of the Random Walk Theory for the stock price.

Keywords: stock prediction, portfolio optimization, data science, machine learning

Procedia PDF Downloads 52

Authors: Rikson Gultom

Abstract:

Hate Speech and Abusive language on social media is difficult to detect, usually, it is detected after it becomes viral in cyberspace, of course, it is too late for prevention. An early detection system that has a fairly good accuracy is needed so that it can reduce conflicts that occur in society caused by postings on social media that attack individuals, groups, and governments in Indonesia. The purpose of this study is to find an early detection model on Twitter social media using machine learning that has high accuracy from several machine learning methods studied. In this study, the support vector machine (SVM), Naïve Bayes (NB), and Random Forest Decision Tree (RFDT) methods were compared with the Support Vector machine with genetic algorithm (SVM-GA), Nave Bayes with genetic algorithm (NB-GA), and Random Forest Decision Tree with Genetic Algorithm (RFDT-GA). The study produced a comparison table for the accuracy of the hate speech and abusive language detection model, and presented it in the form of a graph of the accuracy of the six algorithms developed based on the Indonesian-language Twitter dataset, and concluded the best model with the highest accuracy.

Keywords: abusive language, hate speech, machine learning, optimization, social media

Procedia PDF Downloads 100

Authors: R. Ruslee, H. Gollee

Abstract:

Functional electrical stimulation (FES) is a commonly used technique in rehabilitation and often associated with rapid muscle fatigue which becomes the limiting factor in its applications. The objective of this study is to investigate the effects on the onset of fatigue of conventional synchronous stimulation, as well as asynchronous stimulation that mimic voluntary muscle activation targeting different motor units which are activated sequentially or randomly via multiple pairs of stimulation electrodes. We investigate three different approaches with various electrode configurations, as well as different patterns of stimulation applied to the gastrocnemius muscle: Conventional Synchronous Stimulation (CSS), Asynchronous Sequential Stimulation (ASS) and Asynchronous Random Stimulation (ARS). Stimulation was applied repeatedly for 300 ms followed by 700 ms of no-stimulation with 40 Hz effective frequency for all protocols. Ten able-bodied volunteers (28±3 years old) participated in this study. As fatigue indicators, we focused on the analysis of Normalized Fatigue Index (NFI), Fatigue Time Interval (FTI) and pre-post Twitch-Tetanus Ratio (ΔTTR). The results demonstrated that ASS and ARS give higher NFI and longer FTI confirming less fatigue for asynchronous stimulation. In addition, ASS and ARS resulted in higher ΔTTR than conventional CSS. In this study, we proposed a randomly distributed stimulation method for the application of FES and investigated its suitability for reducing muscle fatigue compared to previously applied methods. The results validated that asynchronous stimulation reduces fatigue, and indicates that random stimulation may improve fatigue resistance in some conditions.

Keywords: asynchronous stimulation, electrode configuration, functional electrical stimulation (FES), muscle fatigue, pattern stimulation, random stimulation, sequential stimulation, synchronous stimulation

Procedia PDF Downloads 281

Authors: M. Uysal, M. Yilmaz, I. Tiryakioğlu

Abstract:

Digital Terrain Model (DTM) is a digital numerical representation of the Earth's surface. DTMs have been applied to a diverse field of tasks, such as urban planning, military, glacier mapping, disaster management. In the expression of the Earth' surface as a mathematical model, an infinite number of point measurements are needed. Because of the impossibility of this case, the points at regular intervals are measured to characterize the Earth's surface and DTM of the Earth is generated. Hitherto, the classical measurement techniques and photogrammetry method have widespread use in the construction of DTM. At present, RADAR, LiDAR, and stereo satellite images are also used for the construction of DTM. In recent years, especially because of its superiorities, Airborne Light Detection and Ranging (LiDAR) has an increased use in DTM applications. A 3D point cloud is created with LiDAR technology by obtaining numerous point data. However recently, by the development in image mapping methods, the use of unmanned aerial vehicles (UAV) for photogrammetric data acquisition has increased DTM generation from image-based point cloud. The accuracy of the DTM depends on various factors such as data collection method, the distribution of elevation points, the point density, properties of the surface and interpolation methods. In this study, the random data reduction method is compared for DTMs generated from image based point cloud data. The original image based point cloud data set (100%) is reduced to a series of subsets by using random algorithm, representing the 75, 50, 25 and 5% of the original image based point cloud data set. Over the ANS campus of Afyon Kocatepe University as the test area, DTM constructed from the original image based point cloud data set is compared with DTMs interpolated from reduced data sets by Kriging interpolation method. The results show that the random data reduction method can be used to reduce the image based point cloud datasets to 50% density level while still maintaining the quality of DTM.

Keywords: DTM, Unmanned Aerial Vehicle (UAV), uniform, random, kriging

Procedia PDF Downloads 124