Search results for: regression analysis (RA)

Authors: Shahadut Hossain, Jacek Wesolowski, Zahirul Hoque

Abstract:

In many epidemiological and environmental studies covariate measurements are subject to the detection limit. In most applications, covariate measurements are usually truncated from below which is known as left-truncation. Because the measuring device, which we use to measure the covariate, fails to detect values falling below the certain threshold. In regression analyses, it causes inflated bias and inaccurate mean squared error (MSE) to the estimators. This paper suggests a response-based regression calibration method to correct the deleterious impact introduced by the covariate detection limit in the estimators of the parameters of simple logistic regression model. Compared to the maximum likelihood method, the proposed method is computationally simpler, and hence easier to implement. It is robust to the violation of distributional assumption about the covariate of interest. In producing correct inference, the performance of the proposed method compared to the other competing methods has been investigated through extensive simulations. A real-life application of the method is also shown using data from a population-based case-control study of non-Hodgkin lymphoma.

Keywords: environmental exposure, detection limit, left truncation, bias, ad-hoc substitution

Procedia PDF Downloads 211

Authors: Nabilah Filzah Mohd Radzuan, Andi Putra, Zalinda Othman, Azuraliza Abu Bakar, Abdul Razak Hamdan

Abstract:

Precipitation forecast is important to avoid natural disaster incident which can cause losses in the involved area. This paper reviews three techniques logistic regression, decision tree, and random forest which are used in making precipitation forecast. These combination techniques through the vector auto-regression (VAR) model help in finding the advantages and strengths of each technique in the forecast process. The data-set contains variables of the rain’s domain. Adaptation of artificial intelligence techniques involved in rain domain enables the forecast process to be easier and systematic for precipitation forecast.

Keywords: logistic regression, decisions tree, random forest, VAR model

Procedia PDF Downloads 417

Authors: Jui-Chen Huang

Abstract:

This research used artificial intelligence method to explore elderly’s opinions on the reuse of telecare, its effect on their service quality, satisfaction and the relationship between customer perceived value and intention to reuse. This study conducted a questionnaire survey on the elderly. A total of 124 valid copies of a questionnaire were obtained. It adopted Backpropagation Network (BPN) to propose an effective and feasible analysis method, which is different from the traditional method. Two third of the total samples (82 samples) were taken as the training data, and the one third of the samples (42 samples) were taken as the testing data. The training and testing data RMSE (root mean square error) are 0.022 and 0.009 in the BPN, respectively. As shown, the errors are acceptable. On the other hand, the training and testing data RMSE are 0.100 and 0.099 in the regression model, respectively. In addition, the results showed the service quality has the greatest effects on the intention to reuse, followed by the satisfaction, and perceived value. This result of the Backpropagation Network method is better than the regression analysis. This result can be used as a reference for future research.

Keywords: artificial intelligence, backpropagation network (BPN), elderly, reuse, telecare

Procedia PDF Downloads 181

Authors: Omar Dib, Rita Yaacoub, Luc Eveleigh, Nathalie Locquet, Hussein Dib, Ali Bassal, Christophe B. Y. Cordella

Abstract:

The potential of front-face fluorescence coupled with chemometric techniques, namely parallel factor analysis (PARAFAC) and multiple linear regression (MLR) as a rapid analysis tool to characterize Lebanese virgin olive oils was investigated. Fluorescence fingerprints were acquired directly on 102 Lebanese virgin olive oil samples in the range of 280-540 nm in excitation and 280-700 nm in emission. A PARAFAC model with seven components was considered optimal with a residual of 99.64% and core consistency value of 78.65. The model revealed seven main fluorescence profiles in olive oil and was mainly associated with tocopherols, polyphenols, chlorophyllic compounds and oxidation/hydrolysis products. 23 MLR regression models based on PARAFAC scores were generated, the majority of which showed a good correlation coefficient (R > 0.7 for 12 predicted variables), thus satisfactory prediction performances. Acid values, peroxide values, and Delta K had the models with the highest predictions, with R values of 0.89, 0.84 and 0.81 respectively. Among fatty acids, linoleic and oleic acids were also highly predicted with R values of 0.8 and 0.76, respectively. Factors contributing to the model's construction were related to common fluorophores found in olive oil, mainly chlorophyll, polyphenols, and oxidation products. This study demonstrates the interest of front-face fluorescence as a promising tool for quality control of Lebanese virgin olive oils.

Keywords: front-face fluorescence, Lebanese virgin olive oils, multiple Linear regressions, PARAFAC analysis

Procedia PDF Downloads 427

Authors: Basan Shrestha

Abstract:

The relationship between the household size and the poverty is not well understood. Malthus followers advocate that the increasing population add pressure to the dwindling resource base due to increasing demand that would lead to poverty. Others claim that bigger households are richer due to availability of household labour for income generation activities. Facts from Nepal were analyzed to examine the relationship between the household size and poverty rate. The analysis of data from 3,968 Village Development Committee (VDC)/ municipality (MP) located in 75 districts of all five development regions revealed that the average household size had moderate positive correlation with the poverty rate (Karl Pearson's correlation coefficient=0.44). In a regression analysis, the household size determined 20% of the variation in the poverty rate. Higher positive correlation was observed in eastern Nepal (Karl Pearson's correlation coefficient=0.66). The regression analysis showed that the household size determined 43% of the variation in the poverty rate in east. The relation was poor in far-west. It could be because higher incidence of poverty was there irrespective of household size. Overall, the facts revealed that the bigger households were relatively poorer. With the increasing level of awareness and interventions for family planning, it is anticipated that the household size will decrease leading to the decreased poverty rate. In addition, the government needs to devise a mechanism to create employment opportunities for the household labour force to reduce poverty.

Keywords: household size, poverty rate, nepal, regional development

Procedia PDF Downloads 338

Authors: Japnoor Garcha, Andrew P. Smith

Abstract:

There has been a significant increase in the prevalence and estimates of neurodevelopmental disorders specially autism spectrum disorders in the last decade. The literature has seen increasing research on understanding well-being and mental health. The current studies have focused on seeing the impact of mental health and well-being in autism spectrum disorders and ADHD both with and without a diagnosis. To further understand the association and interaction of well-being and mental health with autism and ADHD a survey was given to 560 secondary school students. The survey used the well-being process questionnaire, the autism spectrum quotient, the ADHD self-report scale, and the strengths and difficulties questionnaire. The analysis conducted using SPSS showed that there was a significant correlation between anxiety, depression, AQ and ADHD. Anxiety and depression were also significantly correlated with all well-being and SDQ variables. The regression analysis showed that anxiety was significantly associated with positive well-being, negative well-being, emotional problems and prosocial behaviour whereas depression was significantly associated with positive well-being, negative well-being, physical health, flourishing, conduct problems, emotional problems and peer problems. This interaction led to the formation of a combined variable to see what impact the variables of anxiety, depression, AQ and ADHD would have coupled together. Further analysis showed that the combined variable was significantly correlated with all outcome variables. The regression analysis showed that the Combined variable was significantly correlated with emotional problems, and hyperactivity, stress, negative coping, psychological capital and sleepiness.

Keywords: AQ, adhd, sdq, well-being, combined variable

Procedia PDF Downloads 21

Authors: Yogita Mishra, Arijit Roy, Dhruval Bhavsar

Abstract:

The study estimates the nitrogen concentration in selected vegetation community’s i.e. chir pine (pinusroxburghii) by using hyperspectral satellite data and also identified the appropriate spectral bands and nitrogen indices. The Short Wave InfraRed reflectance spectrum at 1790 nm and 1680 nm shows the maximum possible absorption by nitrogen in selected species. Among the nitrogen indices, log normalized nitrogen index performed positively and negatively too. The strong positive correlation is taken out from 1510 nm and 760 nm for the pinusroxburghii for leaf nitrogen concentration and leaf nitrogen mass while using NDNI. The regression value of R² developed by using linear equation achieved maximum at 0.7525 for the analysis of satellite image data and R² is maximum at 0.547 for ground truth data for pinusroxburghii respectively.

Keywords: hyperspectral, NDNI, nitrogen concentration, regression value

Procedia PDF Downloads 265

Authors: Hussain A. Alkharusi, Said S. Aldhafri, Hilal Z. Alnabhani, Muna Alkalbani

Abstract:

Analysing classroom assessments is one of the responsibilities of the teacher. It aims improving teacher’s instruction and assessment as well as student learning. The present study investigated factors that might explain variation in teachers’ practices regarding analysis of classroom assessments. The factors considered in the investigation included gender, in-service assessment training, teaching load, teaching experience, knowledge in assessment, attitude towards quantitative aspects of assessment, and self-perceived competence in analysing assessments. Participants were 246 in-service teachers in Oman. Results of a stepwise multiple linear regression analysis revealed that self-perceived competence was the only significant factor explaining the variance in teachers’ analysis of assessments. Implications for research and practice are discussed.

Keywords: analysis of assessment, classroom assessment, in-service teachers, self-competence

Procedia PDF Downloads 302

Authors: Suganya Chandrababu, Dhundy Bastola

Abstract:

Like in the gut, the subgingival microbiota plays a crucial role in oral hygiene, health, and cariogenic diseases. Human activities like diet, antibiotics, and periodontal treatments alter the bacterial communities, metabolism, and functions in the oral cavity, leading to a dysbiotic state and changes in the plaques of orthodontic patients. Fixed periodontal appliances hinder oral hygiene and cause changes in the dental plaques influencing the subgingival microbiota. However, the microbial species’ diversity and complexity pose a great challenge in understanding the taxa’s community distribution patterns and their role in oral health. In this research, we analyze the subgingival microbial samples from individuals with fixed dental appliances (metal/clear) using an in silico approach. We employ exploratory hypothesis-driven multivariate and regression analysis to shed light on the microbial community and its functional fluctuations due to dental appliances used and identify risks associated with complex disease phenotypes. Our findings confirm the changes in oral microbiota composition due to the presence and type of fixed orthodontal devices. We identified seven main periodontic pathogens, including Bacteroidetes, Actinobacteria, Proteobacteria, Fusobacteria, and Firmicutes, whose abundances were significantly altered due to the presence and type of fixed appliances used. In the case of metal braces, the abundances of Bacteroidetes, Proteobacteria, Fusobacteria, Candidatus saccharibacteria, and Spirochaetes significantly increased, while the abundance of Firmicutes and Actinobacteria decreased. However, in individuals With clear braces, the abundance of Bacteroidetes and Candidatus saccharibacteria increased. The highest abundance value (P-value=0.004 < 0.05) was observed with Bacteroidetes in individuals with the metal appliance, which is associated with gingivitis, periodontitis, endodontic infections, and odontogenic abscesses. Overall, the bacterial abundances decrease with clear type and increase with metal type of braces. Regression analysis further validated the multivariate analysis of variance (MANOVA) results, supporting the hypothesis that the presence and type of the fixed oral appliances significantly alter the bacterial abundance and composition.

Keywords: oral microbiota, statistical analysis, fixed or-thodontal appliances, bacterial abundance, multivariate analysis, regression analysis

Procedia PDF Downloads 160

Authors: Quangyen Tran, YeZhuang Tian, Chengfeng Li

Abstract:

Psychological contract violations may lead to damaging an organization through losing its potential employees; it is a very significant concept in understanding the employment relationships. The authors selected contents of psychological contract violation scale based on the nine areas of violation most relevant to managerial samples (High pay, training, job security, career development, pay based on performance, promotion, feedback, expertise and quality of co-workers and support with personal problems), using regression analysis, the degree of psychological contract violations was measured by an adaptation of a multiplicative scale with Cronbach’s alpha as a measure of reliability. Through the regression analysis, psychological contract violations was found have a positive impact on employees’ job satisfaction, the frequency of psychological contract violations was more intense among male employees particularly in terms of training, job security and pay based on performance. Job dissatisfaction will lead to a lowering of employee commitment in the job, enterprises in Hanoi, Vietnam should therefore offer lucrative jobs in terms of salary and other emoluments to their employees.

Keywords: psychological contract, psychological contract violation, job satisfaction, subordinate employees, employers’ obligation

Procedia PDF Downloads 302

Authors: Jui-Chen Huang, Shou-Hsiung Cheng

Abstract:

This study examined their willingness to use telecare for people who have had experience falling in the last three months in Taiwan. This study adopted convenience sampling and a structural questionnaire to collect data. It was based on the definition and the constructs related to the Health Belief Model (HBM). HBM is comprised of seven constructs: perceived benefits (PBs), perceived disease threat (PDT), perceived barriers of taking action (PBTA), external cues to action (ECUE), internal cues to action (ICUE), attitude toward using (ATT), and behavioral intention to use (BI). This study adopted Fuzzy Neural Network (FNN) to put forward an effective method. It shows the dependence of ATT on PB, PDT, PBTA, ECUE, and ICUE. The training and testing data RMSE (root mean square error) are 0.028 and 0.166 in the FNN, respectively. The training and testing data RMSE are 0.828 and 0.578 in the regression model, respectively. On the other hand, as to the dependence of ATT on BI, as presented in the FNN, the training and testing data RMSE are 0.050 and 0.109, respectively. The training and testing data RMSE are 0.529 and 0.571 in the regression model, respectively. The results show that the FNN method is better than the regression analysis. It is an effective and viable good way.

Keywords: fall, fuzzy neural network, health belief model, telecare, willingness

Procedia PDF Downloads 157

Authors: Lule Basha, Eralda Gjika

Abstract:

This study is focused on analyzing climate change in Albania and its potential effects on cereal yields. Initially, monthly temperature and rainfalls in Albania were studied for the period 1960-2021. Climacteric variables are important variables when trying to model cereal yield behavior, especially when significant changes in weather conditions are observed. For this purpose, in the second part of the study, linear and nonlinear models explaining cereal yield are constructed for the same period, 1960-2021. The multiple linear regression analysis and lasso regression method are applied to the data between cereal yield and each independent variable: average temperature, average rainfall, fertilizer consumption, arable land, land under cereal production, and nitrous oxide emissions. In our regression model, heteroscedasticity is not observed, data follow a normal distribution, and there is a low correlation between factors, so we do not have the problem of multicollinearity. Machine-learning methods, such as random forest, are used to predict cereal yield responses to climacteric and other variables. Random Forest showed high accuracy compared to the other statistical models in the prediction of cereal yield. We found that changes in average temperature negatively affect cereal yield. The coefficients of fertilizer consumption, arable land, and land under cereal production are positively affecting production. Our results show that the Random Forest method is an effective and versatile machine-learning method for cereal yield prediction compared to the other two methods.

Keywords: cereal yield, climate change, machine learning, multiple regression model, random forest

Procedia PDF Downloads 57

Authors: Zhidong Zhang, Amanda Resendez

Abstract:

This study is to examine how teachers’ perspective on education technology use in their class influence their students’ achievement. The authors hypothesized that teachers’ perspective can directly or indirectly influence students’ learning, performance, and achievements. In this study, a questionnaire entitled, Teacher’s Perspective on Educational Technology, was delivered to 63 teachers and 1268 students’ mathematics and reading achievement records were collected. The questionnaire consists of four parts: a) demographic variables, b) attitudes on technology integration, c) outside factor affecting technology integration, and d) technology use in the classroom. Kruskal-Wallis and hierarchical regression analysis techniques were used to examine: 1) the relationship between the demographic variables and teachers’ perspectives on educational technology, and 2) how the demographic variables were causally related to students’ mathematics and reading achievements. The study found that teacher demographics were significantly related to the teachers’ perspective on educational technology with p < 0.05 and p < 0.01 separately. These teacher demographical variables included the school district, age, gender, the grade currently teach, teaching experience, and proficiency using new technology. Further, these variables significantly predicted students’ mathematics and reading achievements with p < 0.05 and p < 0.01 separately. The variations of R² are between 0.176 and 0.467. That means 46.7% of the variance of a given analysis can be explained by the model.

Keywords: teacher's perception of technology use, mathematics achievement, reading achievement, Kruskal-Wallis test, hierarchical regression analysis

Procedia PDF Downloads 111

Authors: Pirzada Sami Ullah Sabri

Abstract:

The present study examines the relationship between work engagement (WE) and employee turnover intentions (TI) in telecommunication sector using human resource development climate (HRDC) as a moderator. Based on 538 employees of telecommunication sector Hierarchal regression analysis is employed to examine the influence of HRDC on the relationship of work engagement and turnover intentions. The result indicates the negative correlation between work engagement and turnover intentions; HRD climate support as a powerful moderator increases the work engagement and lessens the turnover intentions. The study shows the importance of favorable and supportive HRD climate which foster the work engagement of the employees in the organization. By understanding the importance of human resource development climate and work engagement in reducing the turnover intentions can increase the productivity and performance of the organization.

Keywords: turnover intentions, work engagement, human resource development, climate, hierarchal regression analysis, telecommunication sector

Procedia PDF Downloads 404

Authors: Inten Meutia, Emylia Yuniarti

Abstract:

The objective of this study is to analyze the effects of interest rate, the rate of return of Islamic banks on the amount of mudarabah deposits in Islamic banks. In analyzing the effect of rate of return in the Islamic banks and interest rate risk in the conventional banks, the 1-month Islamic deposit rate of return and 1 month fixed deposit interest rate of a total Islamic deposit are considered. Using data covering the period from January 2010 to Sepember 2013, the study applies the regression analysis to analyze the effect between variable and independence t-test to analyze the mean difference between rate of return and rate of interest. Regression analysis shows that rate of return have significantly negative influence on mudarabah deposits, while interest rate have negative influence but not significant. The result of independent t test shows that the interest rate is not different from the rate of return in Islamic Bank. It supports the hyphotesis that rate of return in Islamic banking mimic rate of interest in conventional bank. The results of the study have important implications on the risk management practices of the Islamic banks in Indonesia.

Keywords: conventional bank, interest rate, Islamic bank, rate of return

Procedia PDF Downloads 483

Authors: Kehinde Peter Oyeduntan, Kayode Oshinubi

Abstract:

The west African ports have been experiencing large inflow and outflow of containerized cargo in the last decades, and this has created a quest amongst the countries to attain the status of hub port for the sub-region. This study analyzed the relationship between the container throughput and Gross Domestic Products (GDP) of nine west African countries, using Simple Linear Regression (SLR), Polynomial Regression Model (PRM) and Support Vector Machines (SVM) with a time series of 20 years. The results showed that there exists a high correlation between the GDP and container throughput. The model also predicted the container throughput in west Africa for the next 20 years. The findings and recommendations presented in this research will guide policy makers and help improve the management of container ports and terminals in west Africa, thereby boosting the economy.

Keywords: container, ports, terminals, throughput

Procedia PDF Downloads 179

Authors: Hossein Alimohammadi, Mohsen Amirmojahedi, Mehrdad Rowhani

Abstract:

Soil properties are used by geotechnical engineers to evaluate and analyze site conditions for designing purposes. Although basic soil classification tests are easy to perform and provide useful information to determine the properties of soils, it may take time to get the result and add some costs to the projects. Standard Penetration Test (SPT) provides an opportunity to evaluate soil parameters without performing laboratory tests. In addition to its simplicity and cheapness, the results become available immediately. This research provides a guideline on the application of the SPT test method, reliability of adapting the SPT test results in evaluating soil physical and mechanical properties such as Atterberg limits, shear strength, and compressive strength compressibility parameters. A total of 70 boreholes were investigated in this study by taking soil samples between depths of 1.2 to 15.25 meters. The project site was located in Morrow County, Ohio. A regression-based formula was proposed based on Tobit regression with a stepwise variable selection analysis conducted between SPT and other typical soil properties obtained from soil tests. The results of the research illustrated that the shear strength and physical properties of the soil affect the SPT number. The proposed correlation can help engineers to use SPT test results in their design with higher accuracy.

Keywords: standard penetration test, soil properties, soil classification, regression method

Procedia PDF Downloads 159

Authors: Kuixi Du, Thomas J. Lipscomb

Abstract:

The proficiency in Mathematics skills is fundamental to success in the STEM disciplines. In the US, beginning college students who are placed in remedial/developmental Mathematics courses frequently struggle to achieve academic success. Therefore, Mathematics remediation in college has become an important concern, and providing Mathematics remediation is a prevalent way to help the students who may not be fully prepared for college-level courses. Programs vary, however, and the effectiveness of a particular remedial Mathematics program must be empirically demonstrated. The purpose of this study was to apply the sharp regression discontinuity (RD) technique to determine the effectiveness of the Jack Leaps Summer (JLS) Mathematic remediation program in supporting improved Mathematics learning outcomes among newly admitted Mathematics students in the South Dakota State University. The researchers studied the newly admitted Fall 2019 cohort of Mathematics majors (n=423). The results indicated that students whose pretest score was lower than the cut-off point and who were assigned to the JLS program experienced significantly higher scores on the post-test (Math 101 final score). Based on these results, there is evidence that the JLS program is effective in meeting its primary objective.

Keywords: causal inference, mathematisc remedial program evaluation, quasi-experimental research design, regression discontinuity design, cohort studies

Procedia PDF Downloads 64

Authors: Adem Peker, Yüksel Eroğlu, İsmail Ay

Abstract:

As the information and communication technologies have become embedded in everyday life of adolescents, both their possible benefits and risks to adolescents are being identified. The information and communication technologies provide opportunities for adolescents to connect with peers and to access to information. However, as with other social connections, users of information and communication devices have the potential to meet and interact with in harmful ways. One emerging example of such interaction is cyber bullying. Cyber bullying occurs when someone uses the information and communication technologies to harass or embarrass another person. Cyber bullying can take the form of malicious text messages and e-mails, spreading rumours, and excluding people from online groups. Cyber bullying has been linked to psychological problems for cyber bullies and victims. Therefore, it is important to determine how internet addiction contributes to cyber bullying. Building on this question, this study takes a closer look at the relationship between internet addiction and cyber bullying. For this purpose, in this study, based on descriptive relational model, it was hypothesized that loss of control, excessive desire to stay online, and negativity in social relationships, which are dimensions of internet addiction, would be associated positively with cyber bullying and victimization. Participants were 383 high school students (176 girls and 207 boys; mean age, 15.7 years). Internet addiction was measured by using Internet Addiction Scale. The Cyber Victim and Bullying Scale was utilized to measure cyber bullying and victimization. The scales were administered to the students in groups in the classrooms. In this study, stepwise regression analyses were utilized to examine the relationships between dimensions of internet addiction and cyber bullying and victimization. Before applying stepwise regression analysis, assumptions of regression were verified. According to stepwise regression analysis, cyber bullying was predicted by loss of control (β=.26, p<.001) and negativity in social relationships (β=.13, p<.001). These variables accounted for 9 % of the total variance, with the loss of control explaining the higher percentage (8 %). On the other hand, cyber victimization was predicted by loss of control (β=.19, p<.001) and negativity in social relationships (β=.12, p<.001). These variables altogether accounted for 8 % of the variance in cyber victimization, with the best predictor loss of control (7 % of the total variance). The results of this study demonstrated that, as expected, loss of control and negativity in social relationships predicted cyber bullying and victimization positively. However, excessive desire to stay online did not emerge a significant predictor of both cyberbullying and victimization. Consequently, this study would enhance our understanding of the predictors of cyber bullying and victimization since the results proposed that internet addiction is related with cyber bullying and victimization.

Keywords: cyber bullying, internet addiction, adolescents, regression

Procedia PDF Downloads 289

Authors: Yildiz Stella Dak, Jale Tezcan

Abstract:

Ground motion models that relate a strong motion parameter of interest to a set of predictive seismological variables describing the earthquake source, the propagation path of the seismic wave, and the local site conditions constitute a critical component of seismic hazard analyses. When a sufficient number of strong motion records are available, ground motion relations are developed using statistical analysis of the recorded ground motion data. In regions lacking a sufficient number of recordings, a synthetic database is developed using stochastic, theoretical or hybrid approaches. Regardless of the manner the database was developed, ground motion relations are developed using regression analysis. Development of a ground motion relation is a challenging process which inevitably requires the modeler to make subjective decisions regarding the inclusion criteria of the recordings, the functional form of the model and the set of seismological variables to be included in the model. Because these decisions are critically important to the validity and the applicability of the model, there is a continuous interest on procedures that will facilitate the development of ground motion models. This paper proposes the use of the Least Absolute Shrinkage and Selection Operator (LASSO) in selecting the set predictive seismological variables to be used in developing a ground motion relation. The LASSO can be described as a penalized regression technique with a built-in capability of variable selection. Similar to the ridge regression, the LASSO is based on the idea of shrinking the regression coefficients to reduce the variance of the model. Unlike ridge regression, where the coefficients are shrunk but never set equal to zero, the LASSO sets some of the coefficients exactly to zero, effectively performing variable selection. Given a set of candidate input variables and the output variable of interest, LASSO allows ranking the input variables in terms of their relative importance, thereby facilitating the selection of the set of variables to be included in the model. Because the risk of overfitting increases as the ratio of the number of predictors to the number of recordings increases, selection of a compact set of variables is important in cases where a small number of recordings are available. In addition, identification of a small set of variables can improve the interpretability of the resulting model, especially when there is a large number of candidate predictors. A practical application of the proposed approach is presented, using more than 600 recordings from the National Geospatial-Intelligence Agency (NGA) database, where the effect of a set of seismological predictors on the 5% damped maximum direction spectral acceleration is investigated. The set of candidate predictors considered are Magnitude, Rrup, Vs30. Using LASSO, the relative importance of the candidate predictors has been ranked. Regression models with increasing levels of complexity were constructed using one, two, three, and four best predictors, and the models’ ability to explain the observed variance in the target variable have been compared. The bias-variance trade-off in the context of model selection is discussed.

Keywords: ground motion modeling, least absolute shrinkage and selection operator, penalized regression, variable selection

Procedia PDF Downloads 303

Authors: Mikiyas Adugna

Abstract:

Effort estimation is among the activities carried out in software development processes. An accurate model of estimation leads to project success. The method of agile effort estimation is a complex task because of the dynamic nature of software development. Researchers are still conducting studies on agile effort estimation to enhance prediction accuracy. Due to these reasons, we investigated and proposed a model on LASSO and Elastic Net regression to enhance estimation accuracy. The proposed model has major components: preprocessing, train-test split, training with default parameters, and cross-validation. During the preprocessing phase, the entire dataset is normalized. After normalization, a train-test split is performed on the dataset, setting training at 80% and testing set to 20%. We chose two different phases for training the two algorithms (Elastic Net and LASSO) regression following the train-test-split. In the first phase, the two algorithms are trained using their default parameters and evaluated on the testing data. In the second phase, the grid search technique (the grid is used to search for tuning and select optimum parameters) and 5-fold cross-validation to get the final trained model. Finally, the final trained model is evaluated using the testing set. The experimental work is applied to the agile story point dataset of 21 software projects collected from six firms. The results show that both Elastic Net and LASSO regression outperformed the compared ones. Compared to the proposed algorithms, LASSO regression achieved better predictive performance and has acquired PRED (8%) and PRED (25%) results of 100.0, MMRE of 0.0491, MMER of 0.0551, MdMRE of 0.0593, MdMER of 0.063, and MSE of 0.0007. The result implies LASSO regression algorithm trained model is the most acceptable, and higher estimation performance exists in the literature.

Keywords: agile software development, effort estimation, elastic net regression, LASSO

Procedia PDF Downloads 23

Authors: Bitewulign Mekonnen

Abstract:

Context: This scientific paper focuses on the use of near-infrared (NIR) spectroscopy to determine glucose concentration in aqueous solutions accurately and rapidly. The study compares six different machine learning methods for predicting glucose concentration and also explores the development of a deep learning model for classifying NIR spectra. The objective is to optimize the detection model and improve the accuracy of glucose prediction. This research is important because it provides a comprehensive analysis of various machine-learning techniques for estimating aqueous glucose concentrations. Research Aim: The aim of this study is to compare and evaluate different machine-learning methods for predicting glucose concentration from NIR spectra. Additionally, the study aims to develop and assess a deep-learning model for classifying NIR spectra. Methodology: The research methodology involves the use of machine learning and deep learning techniques. Six machine learning regression models, including support vector machine regression, partial least squares regression, extra tree regression, random forest regression, extreme gradient boosting, and principal component analysis-neural network, are employed to predict glucose concentration. The NIR spectra data is randomly divided into train and test sets, and the process is repeated ten times to increase generalization ability. In addition, a convolutional neural network is developed for classifying NIR spectra. Findings: The study reveals that the SVMR, ETR, and PCA-NN models exhibit excellent performance in predicting glucose concentration, with correlation coefficients (R) > 0.99 and determination coefficients (R²)> 0.985. The deep learning model achieves high macro-averaging scores for precision, recall, and F1-measure. These findings demonstrate the effectiveness of machine learning and deep learning methods in optimizing the detection model and improving glucose prediction accuracy. Theoretical Importance: This research contributes to the field by providing a comprehensive analysis of various machine-learning techniques for estimating glucose concentrations from NIR spectra. It also explores the use of deep learning for the classification of indistinguishable NIR spectra. The findings highlight the potential of machine learning and deep learning in enhancing the prediction accuracy of glucose-relevant features. Data Collection and Analysis Procedures: The NIR spectra and corresponding references for glucose concentration are measured in increments of 20 mg/dl. The data is randomly divided into train and test sets, and the models are evaluated using regression analysis and classification metrics. The performance of each model is assessed based on correlation coefficients, determination coefficients, precision, recall, and F1-measure. Question Addressed: The study addresses the question of whether machine learning and deep learning methods can optimize the detection model and improve the accuracy of glucose prediction from NIR spectra. Conclusion: The research demonstrates that machine learning and deep learning methods can effectively predict glucose concentration from NIR spectra. The SVMR, ETR, and PCA-NN models exhibit superior performance, while the deep learning model achieves high classification scores. These findings suggest that machine learning and deep learning techniques can be used to improve the prediction accuracy of glucose-relevant features. Further research is needed to explore their clinical utility in analyzing complex matrices, such as blood glucose levels.

Keywords: machine learning, signal processing, near-infrared spectroscopy, support vector machine, neural network

Procedia PDF Downloads 57

Authors: Hui-Yen Lee, Hsiu-Yun Wei, Guey-Jen Lin, Pi-Yueh Lee Lee

Abstract:

Background: Unplanned hospital readmissions increase healthcare costs and have been considered a marker of poor healthcare performance. The elderly face a higher risk of unplanned readmission due to elderly-specific characteristics such as deteriorating body functions and the relatively high incidence of complications after treatment of acute diseases. Purpose: The aim of this study was exploring the factors that relate to the unplanned readmission of elderly within 14 days of discharge at our hospital in southern Taiwan. Methods: We retrospectively reviewed the medical records of patients aged ≥65 years who had been re-admitted between January 2018 and December 2018.The Charlson Comorbidity score was calculated using previous used method. Related factors that affected the rate of unplanned readmission within 14 days of discharge were screened and analyzed using the chi-squared test and logistic regression analysis. Results: This study enrolled 829 subjects aged more than 65 years. The numbers of unplanned readmission patients within 14 days were 318 cases, while those did not belong to the unplanned readmission were 511 cases. In 2018, the rate of elderly patients in unplanned 14 days readmissions was 38.4%. The majority patients were females (166 cases, 52.2%), with an average age of 77.6 ± 7.90 years (65-98). The average value of Charlson Comorbidity score was 4.42±2.76. Using logistic regression analysis, we found that the gastric or peptic ulcer (OR=1.917 , P< 0.002), diabetes (OR= 0.722, P< 0.043), hemiplegia (OR= 2.292, P< 0.015), metastatic solid tumor (OR= 2.204, P< 0.025), hypertension (OR= 0.696, P< 0.044), and skin ulcer/cellulitis (OR= 2.747, P< 0.022) have significantly higher risk of 14-day readmissions. Conclusion: The results of the present study may assist the healthcare teams to understand the factors that may affect unplanned readmission in the elderly. We recommend that these teams give efficient approach in their medical practice, provide timely health education for elderly, and integrative healthcare for chronic diseases in order to reduce unplanned readmissions.

Keywords: unplanning readmission, elderly, Charlson comorbidity score, logistic regression analysis

Procedia PDF Downloads 109

Authors: Issam Aouari, Abdelmalek Abdelhamid

Abstract:

For seismologists, the characterization of seismic demand should include the amplitude and duration of strong shaking in the system. The duration of ground shaking is one of the key parameters in earthquake resistant design of structures. This paper proposes a nonlinear statistical model to estimate earthquake ground motion duration in soft soils using multiple seismicity indicators. Three definitions of ground motion duration proposed by literature have been applied. With a comparative study, we select the most significant definition to use for predict the duration. A stochastic model is presented for the McCann and Shah Method using nonlinear regression analysis based on a data set for moment magnitude, source to site distance and site conditions. The data set applied is taken from PEER strong motion databank and contains shallow earthquakes from different regions in the world; America, Turkey, London, China, Italy, Chili, Mexico...etc. Main emphasis is placed on soft site condition. The predictive relationship has been developed based on 600 records and three input indicators. Results have been compared with others published models. It has been found that the proposed model can predict earthquake ground motion duration in soft soils for different regions and sites conditions.

Keywords: duration, earthquake, prediction, regression, soft soil

Procedia PDF Downloads 119

Authors: Ghada A. Alfattni

Abstract:

Analysing unbalanced datasets is one of the challenges that practitioners in machine learning field face. However, many researches have been carried out to determine the effectiveness of the use of the synthetic minority over-sampling technique (SMOTE) to address this issue. The aim of this study was therefore to compare the effectiveness of the SMOTE over different models on unbalanced datasets. Three classification models (Logistic Regression, Support Vector Machine and Nearest Neighbour) were tested with multiple datasets, then the same datasets were oversampled by using SMOTE and applied again to the three models to compare the differences in the performances. Results of experiments show that the highest number of nearest neighbours gives lower values of error rates. 

Keywords: imbalanced datasets, SMOTE, machine learning, logistic regression, support vector machine, nearest neighbour

Procedia PDF Downloads 314

Authors: Osamu Komori, Shinto Eguchi, Hiroshi Okamura, Momoko Ichinokawa

Abstract:

The long time-series data on population assessments are essential for global ecosystem assessment because the temporal change of biomass in such a database reflects the status of global ecosystem properly. However, the available assessment data usually have limited sample sizes and the ratio of populations with low abundance of biomass (collapsed) to those with high abundance (non-collapsed) is highly imbalanced. To allow for the imbalance and uncertainty involved in the ecological data, we propose a binary regression model with mixed effects for inferring ecosystem status through an asymmetric logistic model. In the estimation equation, we observe that the weights for the non-collapsed populations are relatively reduced, which in turn puts more importance on the small number of observations of collapsed populations. Moreover, we extend the asymmetric logistic regression model using propensity score to allow for the sample biases observed in the labeled and unlabeled datasets. It robustified the estimation procedure and improved the model fitting.

Keywords: double robust estimation, ecological binary data, mixed effect logistic regression model, propensity score

Procedia PDF Downloads 235

Authors: Dieudonne Uwizeye

Abstract:

Introduction: Diarrhoea is one of the major causes of morbidity and mortality among communities living in urban informal settlements of developing countries. It is assumed that mountainous environment introduces variations of the burden among residents of the same settlements. Design and Objective: A cross-sectional study was done in Kigali to explore the effect of mountainous informal settlements on diarrhoea risk variations. Data were collected among 1,152 households through household survey and transect walk to observe the status of sanitation. The outcome variable was the incidence of diarrhoea among household members of any age. The study used the most knowledgeable person in the household as the main respondent. Mostly this was the woman of the house as she was more likely to know the health status of every household member as she plays various roles: mother, wife, and head of the household among others. The analysis used cross tabulation and logistic regression analysis. Results: Results suggest that risks for diarrhoea vary depending on home location in the settlements. Diarrhoea risk increased as the distance from the road increased. The results of the logistic regression analysis indicate the adjusted odds ratio of 2.97 with 95% confidence interval being 1.35-6.55 and 3.50 adjusted odds ratio with 95% confidence interval being 1.61-7.60 in level two and three respectively compared with level one. The status of sanitation within and around homes was also significantly associated with the increase of diarrhoea. Equally, it is indicated that stable households were less likely to have diarrhoea. The logistic regression analysis indicated the adjusted odds ratio of 0.45 with 95% confidence interval being 0.25-0.81. However, the study did not find evidence for a significant association between diarrhoea risks and household socioeconomic status in the multivariable model. It is assumed that environmental factors in mountainous settings prevailed. Households using the available public water sources were more likely to have diarrhoea in their households. Recommendation: The study recommends the provision and extension of infrastructure for improved water, drainage, sanitation and wastes management facilities. Equally, studies should be done to identify the level of contamination and potential origin of contaminants for water sources in the valleys to adequately control the risks for diarrhoea in mountainous urban settings.

Keywords: urbanisation, diarrhoea risk, mountainous environment, urban informal settlements in Rwanda

Procedia PDF Downloads 141

Authors: Michael Tilahun Mulugeta

Abstract:

Pedestrians are the most vulnerable road users as they are more exposed to the risk of collusion. Pedestrian safety at road intersections still remains the most vital and yet unsolved issue in Addis Ababa, Ethiopia. One of the critical points in pedestrian safety is the occurrence of conflict between turning vehicle and pedestrians at un-signalized intersection. However, a better understanding of the factors that affect the likelihood of the conflicts would help provide direction for countermeasures aimed at reducing the number of crashes. This paper has sorted to explore a model to describe the relation between traffic conflicts and influencing factors using Multiple Linear regression methodology. In this research the main focus is to study the interaction of turning (left & right) vehicle with pedestrian at unsignalized intersections. The specific objectives also to determine factors that affect the number of potential conflicts and develop a model of potential conflict.

Keywords: potential, regression analysis, pedestrian, conflicts

Procedia PDF Downloads 22

Authors: Jui Chen Wu, Ming Yi Hsu

Abstract:

Background and Purpose: Shift work of nursing staff is inevitable in hospital to provide continuing medical care. However, shift work is considered as a health hazard that may cause physical and psychological problems. Serious workplace fatigue of nursing shift work might impact on family, social and work life, moreover, causes serious reduction of quality of medical care, or even malpractice. This study aims to explore relationships among nursing staff’s shift, workplace fatigue and quality of working life. Method: Structured questionnaires were used in this study to explore relationships among shift work, workplace fatigue and quality of working life in nursing staffs. We recruited 590 nursing staffs in different Community Teaching hospitals in Taiwan. Data analysed by descriptive statistics, single sample t-test, single factor analysis, Pearson correlation coefficient and hierarchical regression, etc. Results: The overall workplace fatigue score is 50.59 points. In further analysis, the score of personal burnout, work-related burnout, over-commitment and client-related burnout are 57.86, 53.83, 45.95 and 44.71. The basic attributes of nursing staff are significantly different from those of workplace fatigue with different ages, licenses, sleeping quality, self-conscious health status, number of care patients of chronic diseases and number of care people in the obstetric ward. The shift variables revealed no significant influence on workplace fatigue during the hierarchical regression analysis. About the analysis on nursing staff’s basic attributes and shift on the quality of working life, descriptive results show that the overall quality of working life of nursing staff is 3.23 points. Comparing the average score of the six aspects, the ranked average score are 3.47 (SD= .43) in interrelationship, 3.40 (SD= .46) in self-actualisation, 3.30 (SD= .40) in self-efficacy, 3.15 (SD= .38) in vocational concept, 3.07 (SD= .37) in work aspects, and 3.02 (SD= .56) in organization aspects. The basic attributes of nursing staff are significantly different from quality of working life in different marriage situations, education level, years of nursing work, occupation area, sleep quality, self-conscious health status and number of care in medical ward. There are significant differences between shift mode and shift rate with the quality of working life. The results of the hierarchical regression analysis reveal that one of the shifts variables 'shift mode' which does affect staff’s quality of working life. The workplace fatigue is negatively correlated with the quality of working life, and the over-commitment in the workplace fatigue is positively related to the vocational concept of the quality of working life. According to the regression analysis of nursing staff’s basic attributes, shift mode, workplace fatigue and quality of working life related shift, the results show that the workplace fatigue has a significant impact on nursing staff’s quality of working life. Conclusion: According to our study, shift work is correlated with workplace fatigue in nursing staffs. This results work as important reference for human resources management in hospitals to establishing a more positive and healthy work arrangement policy.

Keywords: nursing staff, shift, workplace fatigue, quality of working life

Procedia PDF Downloads 245

Authors: Rajarshi Sharma, Rashidul Alam, Visavino Seleyi, Yuvila Sangtam

Abstract:

The Intensity-Duration-Frequency (IDF) relationship of rainfall amounts is one of the most commonly used tools in water resources engineering for planning, design and operation of water resources project, or for various engineering projects against design floods. The establishment of such relationships was reported as early as in 1932 (Bernard). Since then many sets of relationships have been constructed for several parts of the globe. The objective of this research is to derive IDF relationship of rainfall for western watershed of Guwahati, Assam. These relationships are useful in the design of urban drainage works, e.g. storm sewers, culverts and other hydraulic structures. In the study, rainfall depth for 10 years viz. 2001 to 2010 has been collected from the Regional Meteorological Centre Borjhar, Guwahati. Firstly, the data has been used to construct the mass curve for duration of more than 7 hours rainfall to calculate the maximum intensity and to form the intensity duration curves. Gumbel’s frequency analysis technique has been used to calculate the probable maximum rainfall intensities for a period of 2 yr, 5 yr, 10 yr, 50 yr, 100 yr from the maximum intensity. Finally, regression analysis has been used to develop the intensity-duration-frequency (IDF) curve. Thus, from the analysis the values for the constants ‘a’,‘b’ &‘c’ have been found out. The values of ‘a’ for which the sum of the squared deviation is minimum has been found out to be 40 and when the corresponding value of ‘c’ and ‘b’ for the minimum squared deviation of ‘a’ are 0.744 and 1981.527 respectively. The results obtained showed that in all the cases the correlation coefficient is very high indicating the goodness of fit of the formulae to estimate IDF curves in the region of interest.

Keywords: intensity-duration-frequency relationship, mass curve, regression analysis, correlation coefficient

Procedia PDF Downloads 214