Search results for: multiple stepwise regression analysis

Authors: Aschalew Cherie Workneh, K. S. Hari Prasad, Chandra Shekhar Prasad Ojha

Abstract:

Due to the increase in water scarcity, the crop water stress index (CWSI) is receiving significant attention these days, especially in arid and semiarid regions, for quantifying water stress and effective irrigation scheduling. Nowadays, machine learning techniques such as neural networks are being widely used to determine CWSI. In the present study, the performance of two artificial neural networks, namely, Self-Organizing Maps (SOM) and Feed Forward-Back Propagation Artificial Neural Networks (FF-BP-ANN), are compared while determining the CWSI of rice crop. Irrigation field experiments with varying degrees of irrigation were conducted at the irrigation field laboratory of the Indian Institute of Technology, Roorkee, during the growing season of the rice crop. The CWSI of rice was computed empirically by measuring key meteorological variables (relative humidity, air temperature, wind speed, and canopy temperature) and crop parameters (crop height and root depth). The empirically computed CWSI was compared with SOM and FF-BP-ANN predicted CWSI. The upper and lower CWSI baselines are computed using multiple regression analysis. The regression analysis showed that the lower CWSI baseline for rice is a function of crop height (h), air vapor pressure deficit (AVPD), and wind speed (u), whereas the upper CWSI baseline is a function of crop height (h) and wind speed (u). The performance of SOM and FF-BP-ANN were compared by computing Nash-Sutcliffe efficiency (NSE), index of agreement (d), root mean squared error (RMSE), and coefficient of correlation (R²). It is found that FF-BP-ANN performs better than SOM while predicting the CWSI of rice crops.

Keywords: artificial neural networks; crop water stress index; canopy temperature, prediction capability

Procedia PDF Downloads 86

Authors: Barbara Gawda

Abstract:

Attachment model formed in childhood has an important impact on emotional development, personality, and social relationships. Attachment is also thought to have an impact on construction of affective-cognitive schemas and cognitive functioning. The aim of the current study was to verify whether there is an association between attachment and cognitive rigidity defined as dogmatism and intolerance of ambiguity. The analysis of 180 participants (persons of a similar age and education level, number of men and women was equal) was conducted. To test the attachment styles, the Revised Experiences in Close Relationships Inventory (ECR-R) was used. To examine cognitive rigidity, the Rokeach and Budner questionnaires were used. A multiple regression model was employed to examine whether attachment styles are predictors for dogmatism. The results confirmed that fearful-ambivalent attachment is the main predictor for dogmatism but not for intolerance of ambiguity.

Keywords: attachment styles, cognitive rigidity, dogmatism, intolerance of ambiguity

Procedia PDF Downloads 314

Authors: Lovro Štefan

Abstract:

The main purpose of the present study was to investigate the associations between the overweight/obesity status and lifestyle factors. In this cross-sectional study, participants were 1950 urban secondary-school students (54.7% of female students) aged 17-18 years old. Dependent variable was body-mass index status derived from self-reported height and weight. The outcome was binarised, where participants with value <25 kg/m2 were collapsed into „normal“, while those ≥25 kg/m2 into „overweight/obesity“ category. Independent variables were gender, type of school, physical activity, sedentary behaviour, self-rated health, self-perceived socioeconomic status and psychological distress. The associations between the dependent and independent variables were analyzed by using multiple logistic regression analysis. In the univariate model, being overweight/obese was significantly associated with being a male student (OR 0.31; 95% CI 0.23 to 0.42), attending a vocational school (OR 1.87; 95% CI 1.42 to 2.48), not meeting the recommendations for moderate-to-vigorous physical activity (OR 0.44; 95% CI 0.22 to 0.88), more time spending in sedentary behaviour (OR 1.53; 95% CI 1.07 to 2.19), poor self-rated health (OR 0.35, 95% CI 0.20 to 0.56) and lower socioeconomic status (OR 0.63; 95% CI 0.48 to 0.84). In the multivariate model, the same associations occured between the dependent and independent variable. In both models, psychological distress was not associated with being overweight/obese. In conclusion, our findings suggest, that lifestyle factors are independently associated with body-mass index

Keywords: body mass index, secondary-school students, Croatia, physical activity, sedentary behaviour, logistic regression

Procedia PDF Downloads 59

Authors: Shan-Hong Ying, Ying-Fang Wang

Abstract:

A surrogate approach was deployed for assessing exposures of multiple chemicals at the selected working area of coating processes and applied to assess the exposure concentration of similar exposed groups using the same chemicals but different formula ratios. For the selected area, 6 to 12 portable photoionization detector (PID) were placed uniformly in its workplace to measure its total VOCs concentrations (CT-VOCs) for 6 randomly selected workshifts. Simultaneously, one sampling strain was placed beside one of these portable PIDs, and the collected air sample was analyzed for individual concentration (CVOCi) of 5 VOCs (xylene, butanone, toluene, butyl acetate, and dimethylformamide). Predictive models were established by relating the CT-VOCs to CVOCi of each individual compound via simple regression analysis. The established predictive models were employed to predict each CVOCi based on the measured CT-VOC for each the similar working area using the same portable PID. Results show that predictive models obtained from simple linear regression analyses were found with an R2 = 0.83~0.99 indicating that CT-VOCs were adequate for predicting CVOCi. In order to verify the validity of the exposure prediction model, the sampling analysis of the above chemical substances was further carried out and the correlation between the measured value (Cm) and the predicted value (Cp) was analyzed. It was found that there is a good correction between the predicted value and measured value of each measured chemical substance (R2=0.83~0.98). Therefore, the surrogate approach could be assessed the exposure concentration of similar exposed groups using the same chemicals but different formula ratios. However, it is recommended to establish the prediction model between the chemical substances belonging to each coater and the direct-reading PID, which is more representative of reality exposure situation and more accurately to estimate the long-term exposure concentration of operators.

Keywords: exposure assessment, exposure prediction model, surrogate approach, TVOC

Procedia PDF Downloads 125

Authors: M. Miljkovic, A. Urakpo, M. Simic-Koumoutsaris

Abstract:

Benefit-risk assessment (BRA) is a valuable tool that takes place in multiple stages during a medicine's lifecycle, and this assessment can be conducted in a variety of ways. The aim was to summarize current BRA methods used during approval decisions and in post-approval settings and to see possible future directions. Relevant reviews, recommendations, and guidelines published in medical literature and through regulatory agencies over the past five years have been examined. BRA implies the review of two dimensions: the dimension of benefits (determined mainly by the therapeutic efficacy) and the dimension of risks (comprises the safety profile of a drug). Regulators, industry, and academia have developed various approaches, ranging from descriptive textual (qualitative) to decision-analytic (quantitative) models, to facilitate the BRA of medicines during the product lifecycle (from Phase I trials, to authorization procedure, post-marketing surveillance and health technology assessment for inclusion in public formularies). These approaches can be classified into the following categories: stepwise structured approaches (frameworks); measures for benefits and risks that are usually endpoint specific (metrics), simulation techniques and meta-analysis (estimation techniques), and utility survey techniques to elicit stakeholders’ preferences (utilities). All these approaches share the following two common goals: to assist this analysis and to improve the communication of decisions, but each is subject to its own specific strengths and limitations. Before using any method, its utility, complexity, the extent to which it is established, and the ease of results interpretation should be considered. Despite widespread and long-time use, BRA is subject to debate, suffers from a number of limitations, and currently is still under development. The use of formal, systematic structured approaches to BRA for regulatory decision-making and quantitative methods to support BRA during the product lifecycle is a standard practice in medicine that is subject to continuous improvement and modernization, not only in methodology but also in cooperation between organizations.

Keywords: benefit-risk assessment, benefit-risk profile, product lifecycle, quantitative methods, structured approaches

Procedia PDF Downloads 122

Authors: Othmane Touri, Sanaa El Filali, El Habib Benlahmar

Abstract:

Natural Language Processing (NLP) has gained significant attention lately. It has proved its ability to analyze and extract insights from unstructured text data in various languages. It is found that one of the most popular NLP applications is sentiment analysis which aims to identify the sentiment expressed in a piece of text, such as positive, negative, or neutral, in multiple languages. While there are several multilingual NLP models available for sentiment analysis, there is a need to investigate their effectiveness in different contexts and applications. In this study, we aim to investigate the effectiveness of different multilingual NLP models for sentiment analysis on a dataset of online product reviews in multiple languages. The performance of several NLP models, including Google Cloud Natural Language API, Microsoft Azure Cognitive Services, Amazon Comprehend, Stanford CoreNLP, spaCy, and Hugging Face Transformers are being compared. The models based on several metrics, including accuracy, precision, recall, and F1 score, are being evaluated and compared to their performance across different categories of product reviews. In order to run the study, preprocessing of the dataset has been performed by cleaning and tokenizing the text data in multiple languages. Then training and testing each model has been applied using a cross-validation approach where randomly dividing the dataset into training and testing sets and repeating the process multiple times has been used. A grid search approach to optimize the hyperparameters of each model and select the best-performing model for each category of product reviews and language has been applied. The findings of this study provide insights into the effectiveness of different multilingual NLP models for Multilingual Sentiment Analysis and their suitability for different languages and applications. The strengths and limitations of each model were identified, and recommendations for selecting the most performant model based on the specific requirements of a project were provided. This study contributes to the advancement of research methods in multilingual NLP and provides a practical guide for researchers and practitioners in the field.

Keywords: NLP, multilingual, sentiment analysis, texts

Procedia PDF Downloads 65

Authors: Dongjoo Chin

Abstract:

The purpose of this study was to investigate the effectiveness of an Early Intensive Behavioral Intervention (EIBI) program on infants with autism spectrum disorder (ASD) and to explore the factors predicting the effectiveness of the program, focusing on the infant's age, language ability, problem behaviors, and parental stress. 19 pairs of infants aged between 2 and 5 years who have had been diagnosed with ASD, and their parents participated in an EIBI program at a clinic providing evidence-based treatment based on applied behavior analysis. The measurement tools which were administered before and after the EIBI program and compared, included PEP-R, a curriculum evaluation, K-SIB-R, K-Vineland-II, K-CBCL, and PedsQL for the infants, and included PSI-SF and BDI-II for the parents. Statistical analysis was performed using a sample t-test and multiple regression analysis and the results were as follows. The EIBI program showed significant improvements in overall developmental age, curriculum assessment, and quality of life for infants. There was no difference in parenting stress or depression. Furthermore, measures for both children and parents at the start of the program predicted neither PEP-R nor the degree of improvement in curriculum evaluation measured six months later at the end of the program. Based on these results, the authors suggest future directions for developing an effective intensive early intervention (EIBI) program for infants with ASD in Korea, and discuss the implications and limitations of this study.

Keywords: applied behavior analysis, autism spectrum disorder, early intensive behavioral intervention, parental stress

Procedia PDF Downloads 156

Authors: Almontas Vilutis, Vytenis Jankauskas

Abstract:

The paper presents the results of the investigation of the dry sliding friction of wood-plastic composites (WPCs) against WC-Co cemented carbide. The dependence of the dynamic coefficient of friction on the main influencing factors (vertical load, temperature, and sliding distance) was investigated by evaluating their mutual interaction. Multiple regression analysis showed a high polynomial dependence (adjusted R2 > 0.98). The resistance of the composite to thermo-mechanical effects determines how temperature and force factors affect the magnitude of the coefficient of friction. WPC-B composite has the lowest friction and highest resistance compared to WPC-A, while composite and cemented carbide materials wear the least. Energy dispersive spectroscopy (EDS), based on elemental composition, provided important insights into the friction process.

Keywords: friction, composite, carbide, factors

Procedia PDF Downloads 58

Authors: Mohammed Bala Banki

Abstract:

This paper examines the relationship between employee satisfaction, customer satisfaction and loyalty in fast food restaurants in Nigeria and ascertains if prior job experience of employees before their present job moderate the relationship between customer satisfaction and loyalty. Data for this study were collected from matched pairs of employees and customers of fast restaurants in four Nigerian cities. A Structural Equation Modelling (SEM) was used for the analysis to test the proposed relationships and hierarchical multiple regression was performed in SPSS 22 to test moderating effect. Findings suggest that there is a direct positive and significant relationship between employee satisfaction and customer satisfaction and customer satisfaction and loyalty while the path between employee satisfaction and customer loyalty is insignificant. Results also reveal that employee’s prior job experience significantly moderate the relationship between customer satisfaction and loyalty. Further analysis indicates that employees with more years of experience provide more fulfilling services to restaurants customers. This paper provides some theoretical and managerial implications for academia and practitioners.

Keywords: employee’s satisfaction, customer’s satisfaction, loyalty, employee’s prior job experience, fast food industry

Procedia PDF Downloads 147

Authors: Yi Shan Cheng, Ya Hui Yeh, Hsiao Wen Hsu

Abstract:

Delirium is an acute state of confusion, which is mainly the result of the interaction of many factors, including: age>65 years, comorbidity, cognitive function and visual/auditory impairment, dehydration, pain, sleep disorder, pipeline retention, general anesthesia and major surgery… etc. Researches show the prevalence of delirium in hospitalized elderly patients over 50%. If it doesn't improve in time, may cause cognitive decline or impairment, not only prolong the length of hospital stay but also increase mortality. Some studies have shown that multiple nonpharmacological interventions are the most effective and common strategies, which are reorientation, early mobility, promoting sleep and nutritional support (including water intake), could improve or prevent delirium in the hospitalized elderly. In Taiwan, only one research to compare the delirium incidence of the older patients who have received orthopedic surgery between multi-nonpharmacological interventions and general routine care. Therefore, the purpose of this study is to address the prevention or improvement of delirium incidence density in medical hospitalized elderly, provide clinical nurses as a reference for clinical implementation, and develop follow-up related research. This study is a quasi-experimental design using purposive sampling. Samples are from two wards: the geriatric ward and the general medicine ward at a medical center in central Taiwan. The sample size estimated at least 100, and then the data will be collected through a self-administered structured questionnaire, including: demographic and professional evaluation items. Case recruiting from 5/13/2023. The research results will be analyzed by SPSS for Windows 22.0 software, including descriptive statistics and inferential statistics: logistic regression、Generalized Estimating Equation(GEE)、multivariate analysis of variance(MANOVA).

Keywords: multiple nonpharmacological interventions, hospitalized elderly, delirium incidence, delirium

Procedia PDF Downloads 50

Authors: Bhekisipho Twala, Mantepu Masetshaba, Ramapulana Nkoana

Abstract:

Multiple classifier systems combine several individual classifiers to deliver a final classification decision. However, an increasingly controversial question is whether such systems can outperform the single best classifier, and if so, what form of multiple classifiers system yields the most significant benefit. Also, multi-target tracking detection using multiple sensors is an important research field in mobile techniques and military applications. In this paper, several multiple classifiers systems are evaluated in terms of their ability to predict a system’s failure or success for multi-sensor target tracking tasks. The Bristol Eden project dataset is utilised for this task. Experimental and simulation results show that the human activity identification system can fulfill requirements of target tracking due to improved sensors classification performances with multiple classifier systems constructed using boosting achieving higher accuracy rates.

Keywords: single classifier, ensemble learning, multi-target tracking, multiple classifiers

Procedia PDF Downloads 237

Authors: Sukanya Sripho

Abstract:

The purpose of this research was to study the role of local administration management to promote culture based on philosophy of sufficiency economy to many communities in Thailand. The philosophy was given to the Thai people by their King and become one of the important policies from the Thai government. A total of 375 local people in main district, Amnadcharoen province were selected by random sampling. A questionnaire was used as the tool for collecting data. Descriptive statistics in this research included percentage, mean, and multiple regression analysis. The findings revealed that the role of facilitator was utilized the most from the management in order to promote culture based on philosophy of sufficiency economy to many communities in Thailand.

Keywords: administration, management, philosophy of sufficiency economy, facilitator

Procedia PDF Downloads 372

Authors: Yatin Wadhawan, Clifford Neuman, Anas Al Majali

Abstract:

In this paper, we evaluate the resilience of the smart grid system in the presence of multiple cyber-physical attacks on its distinct functional components. We discuss attack-defense scenarios and their effect on smart grid resilience. Through contingency simulations in the Network and PowerWorld Simulator, we analyze multiple cyber-physical attacks that propagate from the cyber domain to power systems and discuss how such attacks destabilize the underlying power grid. The analysis of such simulations helps system administrators develop more resilient systems and improves the response of the system in the presence of cyber-physical attacks.

Keywords: smart grid, gas pipeline, cyber- physical attack, security, resilience

Procedia PDF Downloads 287

Authors: Ren-Jieh Kuo, Chun-Shou Huang

Abstract:

The research of juice flavor forecasting has become more important in China. Due to the fast economic growth in China, many different kinds of juices have been introduced to the market. If a beverage company can understand their customers’ preference well, the juice can be served more attractively. Thus, this study intends to introduce the basic theory and computing process of grapes juice flavor forecasting based on support vector regression (SVR). Applying SVR, BPN and LR to forecast the flavor of grapes juice in real data, the result shows that SVR is more suitable and effective at predicting performance.

Keywords: flavor forecasting, artificial neural networks, Support Vector Regression, China

Procedia PDF Downloads 462

Authors: Rubén Manrique, Delio Balcázar, José Parrado, Sebastián Rodríguez

Abstract:

Hand in hand with the evolution of technology, education systems have moved to virtual environments to provide increased coverage and facilitate the access to education. However, measuring student performance in virtual environments presents significant challenges to ensure students are acquiring the expected skills. In this study, the confidence and performance of engineering students in virtual environments is analyzed through different evaluation strategies. The effect of the assessment strategy in student confidence is identified using educational data mining techniques. Four assessment strategies were used. First, a conventional multiple choice test; second, a multiple choice test with feedback; third, a multiple choice test with a second chance; and fourth; a multiple choice test with feedback and second chance. Our results show that applying testing with online feedback strategies can influence positively student confidence.

Keywords: assessment strategies, educational data mining, student performance, student confidence

Procedia PDF Downloads 330

Authors: Kawthar F. Albasri, Abdullah M. AlHudaithi, Dana B. AlTurairi, Abdullaziz S. AlQuraini, Adoub Y. AlDerazi, Reem A. Hubail, Haitham A. Jahrami

Abstract:

Several studies have found that medical students have a significant prevalence of anxiety. The purpose of this review paper is to carefully evaluate the current research on anxiety among medical students in the MENA region and, as a result, estimate the prevalence of these disturbances. Multiple databases, including the CINAHL (Cumulative Index to Nursing and Allied Health Literature), Cochrane Library, Embase, MEDLINE (Medical Literature Analysis and Retrieval System Online), PubMed, PsycINFO (Psychological Information Database), Scopus, Web of Science, UpToDate, ClinicalTrials.gov, WHO Global Health Library, EbscoHost, ProQuest, JAMA Network, and ScienceDirect, were searched. The retrieved article reference lists were rigorously searched and rated for quality. A random effects meta-analysis was performed to compute estimates. The current meta-analysis revealed an alarming estimated pooled prevalence of anxiety (K = 46, N = 27023) of 52.5% [95%CI: 43.3%–61.6%]. A total of 62.0% [95% CI 42.9%; 78.0%] of the students (K = 18, N = 16466) suffered from anxiety during the COVID-19 pandemic, while 52.5% [95% CI 43.3%; 61.6%] had anxiety before COVID-19. Based on the GAD-7 measure, a total of 55.7% [95%CI 30.5%; 78.3%] of the students (K = 10, N = 5830) had anxiety, and a total of 54.7% of the students (K = 18, N = 12154) [95%CI 42.8%; 66.0%] had anxiety using the DASS-21 or 42 measure. Anxiety is a common issue among medical students, making it a genuine problem. Further research should be conducted post-COVD 19, with a focus on anxiety prevention and intervention initiatives for medical students.

Keywords: anxiety, medical students, MENA, meta-analysis, prevalence

Procedia PDF Downloads 48

Authors: Alireza Pirkhaefi

Abstract:

Background: Multiple sclerosis (MS) is one of the most common diseases of the central nervous system (brain and spinal cord). Given the importance of cognitive disorders in patients with multiple sclerosis, the present study was in order to compare cognitive functions (Working memory, Attention and Centralization, and Visual-spatial perception) in patients with relapsing- remitting multiple sclerosis (RRMS) and secondary progressive multiple sclerosis (SPMS). Method: Present study was performed as a retrospective study. This research was conducted with Ex-Post Facto method. The samples of research consisted of 60 patients with multiple sclerosis (30 patients relapsing-retrograde and 30 patients secondary progressive), who were selected from Tehran Community of MS Patients Supported as convenience sampling. 30 normal persons were also selected as a comparison group. Montreal Cognitive Assessment (MOCA) was used to assess cognitive functions. Data were analyzed using multivariate analysis of variance. Results: The results showed that there were significant differences among cognitive functioning in patients with RRMS, SPMS, and normal individuals. There were not significant differences in working memory between two groups of patients with RRMS and SPMS; while significant differences in these variables were seen between the two groups and normal individuals. Also, results showed significant differences in attention and centralization and visual-spatial perception among three groups. Conclusions: Results showed that there are differences between cognitive functions of RRMS and SPMS patients so that the functions of RRMS patients are better than SPMS patients. These results have a critical role in improvement of cognitive functions; reduce the factors causing disability due to cognitive impairment, and especially overall health of society.

Keywords: multiple sclerosis, cognitive function, secondary-progressive, normal subjects

Procedia PDF Downloads 218

Authors: Uwe C. Fischer

Abstract:

Mental health and well-being for employees working in the human service system are getting more and more important given the increasing rate of absenteeism at work. Besides individual capacities, social and community factors seem to be important in the working setting. Starting from a demand resource framework including the classical demand control aspects, social support systems, specific demands and resources of the client work, and work-family conflict were considered in the present study. We state hypothetically, that these factors have a meaningful association with the mental quality of life of employees working in the field of social, educational and health sectors. 1140 employees, working in human service organizations (education, youth care, nursing etc.) were asked for strains and resources at work (selected scales from Salutogenetic Subjective Work Assessment SALSA and own new scales for client work), work-family conflict, and mental quality of life from the German Short Form Health Survey. Considering the complex influences of the variables, we conducted a multiple hierarchical regression analysis. One third of the whole variance of the mental quality of life can be declared by the different variables of the model. When the variables concerning social influences were included in the hierarchical regression, the influence of work related control resource decreased. Excessive workload, work-family conflict, social support by supervisors, co-workers and other persons outside work, as well as strains and resources associated with client work had significant regression coefficients. Conclusions: Social support systems are crucial in the social, educational and health related service sector, regarding the influence on mental well-being. Especially the work-family conflict focuses on the importance of the work-life balance. Also the specific strains and resources of the client work, measured with new constructed scales, showed great impact on mental health. Therefore occupational health promotion should focus more on the social factors within and outside the working place.

Keywords: client interaction, human service system, mental health, social support, work-family conflict

Procedia PDF Downloads 416

Authors: Rajeshwar Singh

Abstract:

The presence of multicollinearity is common in handling with several explanatory variables simultaneously due to exhibiting a linear relationship among them. A great problem arises in understanding the impact of explanatory variables on the dependent variable. Thus, the method of least squares estimation gives inexact estimates. In this case, it is advised to detect its presence first before proceeding further. Using the ridge regression degree of its occurrence is reduced but principal components regression gives good estimates in this situation. This paper discusses well-known techniques of the ridge and principal components regressions and applies to get the estimates of coefficients by both techniques. In addition to it, this paper also discusses the conflicting claim on the discovery of the method of ridge regression based on available documents.

Keywords: conflicting claim on credit of discovery of ridge regression, multicollinearity, principal components and ridge regressions, variance inflation factor

Procedia PDF Downloads 386

Authors: Jiexuan Lin, Huiyi Chen

Abstract:

The development of L2 pronunciation competence remains understudied in the literature and it is not clear what may influence learners’ development of L2 pronunciation. The present study was an attempt to find out which of the two common factors in L2 acquisition, i.e., foreign language anxiety or self-perceived L2 proficiency, can better predict Chinese EFL learners’ pronunciation performance. 78 first-year English majors, who had received a three-month pronunciation training course, were asked to 1) fill out a questionnaire on foreign language classroom anxiety, 2) self-report their L2 proficiency in general, in speaking and in pronunciation, and 3) complete an oral and a written test on their L2 pronunciation (the score of the oral part indicates participants’ pronunciation proficiency in oral production, and the score of the written part indexes participants’ ability in applying pronunciation knowledge in comprehension.) Results showed that the pronunciation scores were negatively correlated with the anxiety scores, and were positively correlated with the self-perceived pronunciation proficiency. But only the written scores in the L2 pronunciation test, not the oral scores, were positively correlated with the L2 self-perceived general proficiency. Neither the oral nor the written scores in the L2 pronunciation test had a significant correlation with the self-perceived speaking proficiency. Given the fairly strong correlations, the anxiety scores and the self-perceived pronunciation proficiency were put in regression models to predict L2 pronunciation performance. The anxiety factor alone accounted for 13.9% of the variance and the self-perceived pronunciation proficiency alone explained 12.1% of the variance. But when both anxiety scores and self-perceived pronunciation proficiency were put in a stepwise regression model, only the anxiety scores had a significant and unique contribution to the L2 pronunciation performance (4.8%). Taken together, the results suggested that the learners’ anxiety level could better predict their L2 pronunciation performance, compared with the self-perceived proficiency levels. The obtained data have the following pedagogical implications. 1) Given the fairly strong correlation between anxiety and L2 pronunciation performance, the instructors who are interested in predicting learners’ L2 pronunciation proficiency may measure their anxiety level, instead of their proficiency, as the predicting variable. 2) The correlation of oral scores (in the pronunciation test) with pronunciation proficiency, rather than with speaking proficiency, indicates that a) learners after receiving some amounts of training are to some extent able to evaluate their own pronunciation ability, implying the feasibility of incorporating self-evaluation and peer comments in course instruction; b) the ‘proficiency’ measure used to predict pronunciation performance should be used with caution. The proficiency of specific skills seemingly highly related to pronunciation (i.e., speaking in this case) may not be taken for granted as an effective predictor for pronunciation performance. 3) The correlation between the written scores with general L2 proficiency is interesting.

Keywords: anxiety, Chinese EFL learners, L2 pronunciation, self-perceived L2 proficiency

Procedia PDF Downloads 334

Authors: Shoumodip Roy, Ankit Singhania, Santanu Mallick, Abhiram Jha, M. K. Agarwal, R. V. Ramna, Uttam Singh

Abstract:

The quality of hot metal at any blast furnace is judged by the silicon content in it. Lower hot metal silicon not only enhances process efficiency at steel melting shops but also reduces hot metal costs. The Hot metal produced at G-Blast furnace Tata Steel Jamshedpur has a significantly higher Si content than Benchmark Blast furnaces. The higher content of hot metal Si is mainly due to inferior raw material quality than those used in benchmark blast furnaces. With minimum control over raw material quality, the only option left to control hot metal Si is via optimizing the furnace parameters. Therefore, in order to identify the levers to reduce hot metal Si, Data mining was carried out, and multiple regression models were developed. The statistical analysis revealed that Slag B3{(CaO+MgO)/SiO2}, Slag Alumina and Hot metal temperature are key controllable parameters affecting hot metal silicon. Contour Plots were used to determine the optimum range of levels identified through statistical analysis. A trial plan was formulated to operate relevant parameters, at G blast furnace, in the identified range to reduce hot metal silicon. This paper details out the process followed and subsequent reduction in hot metal silicon by 15% at G blast furnace.

Keywords: blast furnace, optimization, silicon, statistical tools

Procedia PDF Downloads 200

Authors: Carol Anne Hargreaves

Abstract:

A key issue in stock investment is how to select representative features for stock selection. The objective of this paper is to firstly determine whether an automated stock investment system, using machine learning techniques, may be used to identify a portfolio of growth stocks that are highly likely to provide returns better than the stock market index. The second objective is to identify the technical features that best characterize whether a stock’s price is likely to go up and to identify the most important factors and their contribution to predicting the likelihood of the stock price going up. Unsupervised machine learning techniques, such as cluster analysis, were applied to the stock data to identify a cluster of stocks that was likely to go up in price – portfolio 1. Next, the principal component analysis technique was used to select stocks that were rated high on component one and component two – portfolio 2. Thirdly, a supervised machine learning technique, the logistic regression method, was used to select stocks with a high probability of their price going up – portfolio 3. The predictive models were validated with metrics such as, sensitivity (recall), specificity and overall accuracy for all models. All accuracy measures were above 70%. All portfolios outperformed the market by more than eight times. The top three stocks were selected for each of the three stock portfolios and traded in the market for one month. After one month the return for each stock portfolio was computed and compared with the stock market index returns. The returns for all three stock portfolios was 23.87% for the principal component analysis stock portfolio, 11.65% for the logistic regression portfolio and 8.88% for the K-means cluster portfolio while the stock market performance was 0.38%. This study confirms that an automated stock investment system using machine learning techniques can identify top performing stock portfolios that outperform the stock market.

Keywords: machine learning, stock market trading, logistic regression, cluster analysis, factor analysis, decision trees, neural networks, automated stock investment system

Procedia PDF Downloads 135

Authors: P. V. Pramila , V. Mahesh

Abstract:

Pulmonary Function Tests are important non-invasive diagnostic tests to assess respiratory impairments and provides quantifiable measures of lung function. Spirometry is the most frequently used measure of lung function and plays an essential role in the diagnosis and management of pulmonary diseases. However, the test requires considerable patient effort and cooperation, markedly related to the age of patients esulting in incomplete data sets. This paper presents, a nonlinear model built using Multivariate adaptive regression splines and Random forest regression model to predict the missing spirometric features. Random forest based feature selection is used to enhance both the generalization capability and the model interpretability. In the present study, flow-volume data are recorded for N= 198 subjects. The ranked order of feature importance index calculated by the random forests model shows that the spirometric features FVC, FEF 25, PEF,FEF 25-75, FEF50, and the demographic parameter height are the important descriptors. A comparison of performance assessment of both models prove that, the prediction ability of MARS with the `top two ranked features namely the FVC and FEF 25 is higher, yielding a model fit of R2= 0.96 and R2= 0.99 for normal and abnormal subjects. The Root Mean Square Error analysis of the RF model and the MARS model also shows that the latter is capable of predicting the missing values of FEV1 with a notably lower error value of 0.0191 (normal subjects) and 0.0106 (abnormal subjects). It is concluded that combining feature selection with a prediction model provides a minimum subset of predominant features to train the model, yielding better prediction performance. This analysis can assist clinicians with a intelligence support system in the medical diagnosis and improvement of clinical care.

Keywords: FEV, multivariate adaptive regression splines pulmonary function test, random forest

Procedia PDF Downloads 283

Authors: Naomi W. Maina

Abstract:

Fertility preference is a subject of great significance in developing countries. Studies reveal that the preferences of fertility are actually significant in determining the society’s fertility levels because the fertility behavior of the future has a high likelihood of falling under the effect of currently observed fertility inclinations. The objective of this study was to establish the factors associated with fertility preference amongst couples in Kenya by fitting a multinomial logistic regression model against 5,265 couple data obtained from Kenya demographic health survey 2014. Results revealed that the type of place of residence, the region of residence, age and spousal age gap significantly influence desire for additional children among couples in Kenya. There was the notable high likelihood of couples living in rural settlements having similar fertility preference compared to those living in urban settlements. Moreover, geographical disparities such as in northern Kenya revealed significant differences in a couples desire to have additional children compared to Nairobi. The odds of a couple’s desire for additional children were further observed to vary dependent on either the wife or husbands age and to a large extent the spousal age gap. Evidenced from the study, was the fact that as spousal age gap increases, the desire for more children amongst couples decreases. Insights derived from this study would be attractive to demographers, health practitioners, policymakers, and non-governmental organizations implementing fertility related interventions in Kenya among other stakeholders. Moreover, with the adoption of devolution, there is a clear need for adoption of population policies that are County specific as opposed to a national population policy as is the current practice in Kenya. Additionally, researchers or students who have little understanding in the application of multinomial logistic regression, both theoretical understanding and practical analysis in SPSS as well as application on real datasets, will find this article useful.

Keywords: couples' desire, fertility, fertility preference, multinomial regression analysis

Procedia PDF Downloads 157

Authors: F. A. Al-Awadhi, D. Al-Hulail

Abstract:

In this study, we applied the Bayesian hierarchical model to detect single and multiple change points for daily earthquake body wave magnitude. The change point analysis is used in both backward (off-line) and forward (on-line) statistical research. In this study, it is used with the backward approach. Different types of change parameters are considered (mean, variance or both). The posterior model and the conditional distributions for single and multiple change points are derived and implemented using BUGS software. The model is applicable for any set of data. The sensitivity of the model is tested using different prior and likelihood functions. Using Mb data, we concluded that during January 2002 and December 2003, three changes occurred in the mean magnitude of Mb in Kuwait and its vicinity.

Keywords: multiple change points, Markov Chain Monte Carlo, earthquake magnitude, hierarchical Bayesian mode

Procedia PDF Downloads 431

Authors: Qiao Fan, Xiaobo Guo, Junxian Zhu, Xiaohu Ding, Ching-Yu Cheng, Tien-Yin Wong, Mingguang He, Heping Zhang, Xueqin Wang

Abstract:

A systematic, simultaneous analysis of multiple phenotypes in genome-wide association studies (GWASs) draws a great attention to integrate the signals from single phenotypes with increased power. However, lacking an interpretable and efficient multivariate GWAS analysis impede the application of such approach. In this study, we propose to decompose the multivariate model into a series of simple univariate models. This transformation illuminates what exactly the individual trait contributes to the significant signals from the multivariate analyses. By employing our approach in the analysis of three myopia-related endophenotypes from the Singapore Malay Eye Study (SIMES), we identify novel candidate loci which were successfully validated in an independent Guangzhou Twin Eye Study (GTES).

Keywords: GWAS multivariate, multiple traits, myopia, association

Procedia PDF Downloads 201

Authors: Kyung-Sook Bang

Abstract:

Background: The health status of school-age children has a great influence on their growth and life-long health. The purposes of this study were to identify physical and mental health status of late school-age children in Seoul, South Korea and to investigate the related factors for their health. Methods: After gaining the approval from Institutional Review Board (IRB), a cross-sectional study was conducted with elementary students in grade 4 or 5. Questionnaires were distributed to eight elementary schools located different regions of Seoul in November, 2016, and 302 participants were finally included. From all participants, informed consents from the parents, and assents from children were received. Children's socioeconomic status, family functioning, peer relations, physical health symptoms, and depression were measured with self-reported questionnaires. Data were analyzed with descriptive statistics, t-test, Pearson’s correlations, and multiple regression. Results: Children's physical health symptoms and depression were not significantly different, and only their peer relations were significantly different according to their socioeconomic status (t=-3.93, p<.001). Depression showed significant positive correlation with physical health symptoms (r=.720, p<.001) and negative correlations with family functioning (r=-.428, p<.001) and peer relations (r=-.775, p<.001). The multiple regression model, which explained 73.5% of variance, showed peer relations (r2 =.604), physical health symptoms (r2 change=.125), and family functioning (r2 change=.005) as significant predictors for depression. Only the peer relations was significant predictor for their physical health symptoms and explained 50.6% of it. Conclusions: The peer relations was the most important factor in their physical and mental health at this age, and it can be affected by their socioeconomic status. Nursing interventions for promoting social relations and family functioning are required to improve children’s physical and mental health, especially for vulnerable population.

Keywords: child, depression, health, peer relation

Procedia PDF Downloads 204

Authors: Pisit Potjanajaruwit

Abstract:

The objectives of the study were to determine the marketing mix factors that influencing tourist’s destination decision making for cultural tourism in the Chonburi province. Both quantitative and qualitative data were applied in this study. The samples of 400 cases for quantitative analysis were tourists (both Thai and foreign) who were interested in cultural tourism in the Chonburi province, and traveled to cultural sites in Chonburi and 14 representatives from provincial tourism committee of Chonburi and local tourism experts. Statistics utilized in this research included frequency, percentage, mean, standard deviation, and multiple regression analysis. The study found that Thai and foreign tourists are influenced by different important marketing mix factors. The important factors for Thai respondents were physical evidence, price, people, and place at high importance level. For foreign respondents, physical evidence, price, people, and process were high importance level, whereas, product, place, and promotion were moderate importance level.

Keywords: Chonburi Province, decision making, cultural tourism, marketing mixed

Procedia PDF Downloads 366

Authors: Mohammed Abdullah Alshahrani

Abstract:

The research focuses on investigating the use of partial least squares (PLS) methodology for addressing challenges associated with high-dimensional correlated data. Recent technological advancements have led to experiments producing data characterized by a large number of variables compared to observations, with substantial inter-variable correlations. Such data patterns are common in chemometrics, where near-infrared (NIR) spectrometer calibrations record chemical absorbance levels across hundreds of wavelengths, and in genomics, where thousands of genomic regions' copy number alterations (CNA) are recorded from cancer patients. PLS serves as a widely used method for analyzing high-dimensional data, functioning as a regression tool in chemometrics and a classification method in genomics. It handles data complexity by creating latent variables (components) from original variables. However, applying PLS can present challenges. The study investigates key areas to address these challenges, including unifying interpretations across three main PLS algorithms and exploring unusual negative shrinkage factors encountered during model fitting. The research presents an alternative approach to addressing the interpretation challenge of predictor weights associated with PLS. Sparse estimation of predictor weights is employed using a penalty function combining a lasso penalty for sparsity and a Cauchy distribution-based penalty to account for variable dependencies. The results demonstrate sparse and grouped weight estimates, aiding interpretation and prediction tasks in genomic data analysis. High-dimensional data scenarios, where predictors outnumber observations, are common in regression analysis applications. Ordinary least squares regression (OLS), the standard method, performs inadequately with high-dimensional and highly correlated data. Copy number alterations (CNA) in key genes have been linked to disease phenotypes, highlighting the importance of accurate classification of gene expression data in bioinformatics and biology using regularized methods like PLS for regression and classification.

Keywords: partial least square regression, genetics data, negative filter factors, high dimensional data, high correlated data

Procedia PDF Downloads 23

Authors: Aishvarya Gupta, Keerthana Anand, Sasirekha Rengaraj, Latha Chathurvedula

Abstract:

Introduction: Advances in assisted reproductive technology and increase in the proportion of infertile couples have both contributed to the steep increase in the incidence of twin pregnancies in past decades. Maternal and perinatal complications are higher in twins than in singleton pregnancies. Studies comparing the maternal and perinatal outcomes of ART twin pregnancies versus spontaneously conceived twin pregnancies report heterogeneous results making it unclear whether the complications are due to twin gestation per se or because of assisted reproductive techniques. The present study aims to compare both maternal and perinatal outcomes in twin pregnancies which are spontaneously conceived and after assisted conception methods, so that targeted steps can be undertaken in order to improve maternal and perinatal outcome of twins. Objectives: To study perinatal and maternal outcome in twin pregnancies conceived spontaneously as well as with assisted methods and compare the outcomes between the two groups. Setting: Women delivering at JIPMER (tertiary care institute), Pondicherry. Population: 380 women with twin pregnancies who delivered in JIPMER between June 2015 and March 2017 were included in the study. Methods: The study population was divided into two cohorts – one conceived by spontaneous conception and other by assisted reproductive methods. Association of various maternal and perinatal outcomes with the method of conception was assessed using chi square test or Student's t test as appropriate. Multiple logistic regression analysis was done to assess the independent association of assisted conception with maternal outcomes after adjusting for age, parity and BMI. Multiple logistic regression analysis was done to assess the independent association of assisted conception with perinatal outcomes after adjusting for age, parity, BMI, chorionicity, gestational age at delivery and presence of hypertension or gestational diabetes in the mother. A p value of < 0.05 was considered as significant. Result: There was increased proportion of women with GDM (21% v/s 4.29%) and premature rupture of membranes (35% v/s 22.85%) in the assisted conception group and more anemic women in the spontaneous group (71.27% v/s 55.1%). However assisted conception per se increased the incidence of GDM among twin gestations (OR 3.39, 95% CI 1.34 – 8.61) and did not influence any of the other maternal outcomes. Among the perinatal outcomes, assisted conception per se increased the risk of having very preterm (<32 weeks) neonates (OR 3.013, 95% CI 1.432 – 6.337). The mean birth weight did not significantly differ between the two groups (p = 0.429). Though there were higher proportion of babies admitted to NICU in the assisted conception group (48.48% v/s 36.43%), assisted conception per se did not increase the risk of admission to NICU (OR 1.23, 95% CI 0.76 – 1.98). There was no significant difference in perinatal mortality rates between the two groups (p = 0.829). Conclusion: Assisted conception per se increases the risk of developing GDM in women with twin gestation and increases the risk of delivering very preterm babies. Hence measures should be taken to ensure appropriate screening methods for GDM and suitable neonatal care in such pregnancies.

Keywords: assisted conception, maternal outcomes, perinatal outcomes, twin gestation

Procedia PDF Downloads 180