Search results for: multivariate logistic regression

Authors: Fernanda M. Assef, Maria Teresinha A. Steiner

Abstract:

The aim of this paper is to compare and discuss better classifier algorithm options for credit risk assessment by applying different Machine Learning techniques. Using records from a Brazilian financial institution, this study uses a database of 5,432 companies that are clients of the bank, where 2,600 clients are classified as non-defaulters, 1,551 are classified as defaulters and 1,281 are temporarily defaulters, meaning that the clients are overdue on their payments for up 180 days. For each case, a total of 15 attributes was considered for a one-against-all assessment using four different techniques: Artificial Neural Networks Multilayer Perceptron (ANN-MLP), Artificial Neural Networks Radial Basis Functions (ANN-RBF), Logistic Regression (LR) and finally Support Vector Machines (SVM). For each method, different parameters were analyzed in order to obtain different results when the best of each technique was compared. Initially the data were coded in thermometer code (numerical attributes) or dummy coding (for nominal attributes). The methods were then evaluated for each parameter and the best result of each technique was compared in terms of accuracy, false positives, false negatives, true positives and true negatives. This comparison showed that the best method, in terms of accuracy, was ANN-RBF (79.20% for non-defaulter classification, 97.74% for defaulters and 75.37% for the temporarily defaulter classification). However, the best accuracy does not always represent the best technique. For instance, on the classification of temporarily defaulters, this technique, in terms of false positives, was surpassed by SVM, which had the lowest rate (0.07%) of false positive classifications. All these intrinsic details are discussed considering the results found, and an overview of what was presented is shown in the conclusion of this study.

Keywords: artificial neural networks (ANNs), classifier algorithms, credit risk assessment, logistic regression, machine Learning, support vector machines

Procedia PDF Downloads 103

Authors: Antoine Vikkey Hinson, Menonli Adjobimey, Gemayel Ahmed Biokou, Rose Mikponhoue

Abstract:

Introduction: Construction industry is a critical concern with regard to Health and Safety Service worldwide. World health Organization revealed that work-related disease and trauma were held responsible for the death of one million nine hundred thousand people in 2016. The aim of this study it was to determine the prevalence and factors associated with the occurrence of work accidents in a construction industry in Benin. Method: It was a descriptive cross-sectional and analytical study. Data analysis was performed with R software 4.1.1. In multivariate analysis, we performed a binary logistic regression. OR adjusted (ORa) association measures and their 95% confidence interval [CI95%] were presented for the explanatory variables used in the final model. The significance threshold for all tests selected was 5% (p < 0.05) Result: In this study, 472 workers were included, and, of these, 452 (95.7%) were men corresponding to a sex ratio of 22.6. The average age of the workers was 33 years ± 8.8 years. Workers were mostly laborers (84.7%), and had declared having inadequate personal protective equipment (50.6%, n=239). The prevalence of work accidents is 50.8%. Collision with a rolling stock (25.8%), cut (16.2%), and stumbling (16.2%) were the main types of work accidents on the construction site. Four factors were associated with contributing to work accidents. Fatigue or exhaustion (ORa : 1.53[1.03 ; 2.28]); The use of dangerous tools (ORa : 1.81 [1.22 ; 2.71]); The various laborers’ jobs (ORa : 4.78 [2.62 ; 9.21]); and seniority in the company ≥ 4 years (ORa : 2.00 [1.35 ; 2.96]). Conclusion: This study allowed us to identify the associated factors. It is imperative to implement a rigorous policy of occupational health and security mostly the continuing training for workers safe, the supply of appropriate work tools and protective

Keywords: prevalence, work accident, associated factors, construction, benin

Procedia PDF Downloads 54

Authors: Pham Van Nha, Le Cam Binh

Abstract:

Particle swarm optimization (PSO) is a population-based stochastic optimization algorithm. PSO was inspired by the natural behavior of birds and fish in migration and foraging for food. PSO is considered as a multidisciplinary optimization model that can be applied in various optimization problems. PSO’s ideas are simple and easy to understand but PSO is only applied in simple model problems. We think that in order to expand the applicability of PSO in complex problems, PSO should be described more explicitly in the form of a mathematical model. In this paper, we represent PSO in a mathematical model and apply in the multivariate data classification. First, PSOs general mathematical model (MPSO) is analyzed as a universal optimization model. Then, Model of Optimal Centroids (MOC) is proposed for the multivariate data classification. Experiments were conducted on some benchmark data sets to prove the effectiveness of MOC compared with several proposed schemes.

Keywords: analysis of optimization, artificial intelligence based optimization, optimization for learning and data analysis, global optimization

Procedia PDF Downloads 206

Authors: Mukesh Ravi Raushan

Abstract:

Despite consideration of obesity as a deadly public health issue contributing 2.6 million deaths worldwide every year developing country like India is facing malnutrition and it is more common than in Sub-Saharan Africa. About one in every three malnourished children in the world lives in India. The paper assess the nutritional health among children using data from total number of 43737 infant and young children aged 0-59 months (µ = 29.54; SD = 17.21) of the selected households by National Family Health Survey, 2005-06. The wasting was measured by a Z-score of standardized weight-for-height according to the WHO child growth standards. The impact of education with place of residence was found to be significantly associated with the complementary food diversity score (CFDS) in India. The education of mother was positively associated with the CFDS but the degree of performance was lower in rural India than their counterpart from urban. The result of binary logistic regression on wasting with WHO seven types of recommended food for children in India suggest that child who consumed the milk product food (OR: 0.87, p<0.0001) were less likely to be malnourished than their counterparts who did not consume, whereas, in case of other food items as the child who consumed food product of seed (OR: 0.75, p<0.0001) were less likely to be malnourished than those who did not. The nutritional status among children were negatively associated with the protein containing complementary food given the child as those child who received pulse in last 24 hour were less likely to be wasted (OR: 0.87, p<0.00001) as compared to the reference categories. The frequency to feed the indexed child increases by 10 per cent the expected change in child health outcome in terms of wasting decreases by 2 per cent in India when place of residence, education, religion, and birth order were controlled. The index gets improved as the risk for malnutrition among children in India decreases.

Keywords: CFDS, food diversity index, India, logistic regression

Procedia PDF Downloads 260

Authors: Yi-Hsien Wang, Fu-Ju Yang, Hwa-Rong Shen, Rui-Lin Tseng

Abstract:

The business is notably related to the market risk according to the increase of liberalization of financial markets. Hence, the company usually utilized high financial leverage of derivatives to hedge the risk. When the company choose different hedging instruments to face a variety of exchange rate risk, we employ the Multinomial Logistic-AHP to analyze the impact of various derivatives. Hence, the research summarized the literature on relevant factors affecting managers selected exchange rate hedging instruments, using Multinomial Logistic Model and and further integrate AHP. Using Experts’ Questionnaires can test multi-level selection and hedging effect of different hedging instruments in order to calculate the hedging instruments and the multi-level factors of weights to understand the gap between the empirical results and practical operation. Finally, the Multinomial Logistic-AHP Model will sort the weights to analyze. The research findings can be a basis reference for investors in decision-making.

Keywords: exchange rate risk, derivatives, hedge, multinomial logistic-AHP

Procedia PDF Downloads 441

Authors: Lubena Achmad, Herman Kristanto, Julian Dewantiningrum

Abstract:

Background: The Bishop score is a standard method used to predict the success of induction. This examination tends to be subjective with high inter and intraobserver variability, so it was presumed to have a low predictive value in terms of the outcome of labor induction. Cervical length measurement using transvaginal ultrasound is considered to be more objective to assess the cervical length. Meanwhile, this examination is not a complicated procedure and less invasive than vaginal touché. Objective: To compare transvaginal ultrasound and Bishop score in predicting successful induction. Methods: This study was a prospective cohort study. One hundred and twenty women with singleton pregnancies undergoing induction of labor at 37 – 42 weeks and met inclusion and exclusion criteria were enrolled in this study. Cervical assessment by both transvaginal ultrasound and Bishop score were conducted prior induction. The success of labor induction was defined as an ability to achieve active phase ≤ 12 hours after induction. To figure out the best cut-off point of cervical length and Bishop score, receiver operating characteristic (ROC) curves were plotted. Logistic regression analysis was used to determine which factors best-predicted induction success. Results: This study showed significant differences in terms of age, premature rupture of the membrane, the Bishop score, cervical length and funneling as significant predictors of successful induction. Using ROC curves found that the best cut-off point for prediction of successful induction was 25.45 mm for cervical length and 3 for Bishop score. Logistic regression was performed and showed only premature rupture of membranes and cervical length ≤ 25.45 that significantly predicted the success of labor induction. By excluding premature rupture of the membrane as the indication of induction, cervical length less than 25.3 mm was a better predictor of successful induction. Conclusion: Compared to Bishop score, cervical length using transvaginal ultrasound was a better predictor of successful induction.

Keywords: Bishop Score, cervical length, induction, successful induction, transvaginal sonography

Procedia PDF Downloads 324

Authors: Wenqi Liu, Reginald Bailey

Abstract:

This study explores an advanced approach to enhancing B2B sales forecasting by integrating machine learning models with a rule-based decision framework. The methodology begins with the development of a machine learning classification model to predict conversion likelihood, aiming to improve accuracy over traditional methods like logistic regression. The classification model's effectiveness is measured using metrics such as accuracy, precision, recall, and F1 score, alongside a feature importance analysis to identify key predictors. Following this, a machine learning regression model is used to forecast sales value, with the objective of reducing mean absolute error (MAE) compared to linear regression techniques. The regression model's performance is assessed using MAE, root mean square error (RMSE), and R-squared metrics, emphasizing feature contribution to the prediction. To bridge the gap between predictive analytics and decision-making, a rule-based decision model is introduced that prioritizes customers based on predefined thresholds for conversion probability and predicted sales value. This approach significantly enhances customer prioritization and improves overall sales performance by increasing conversion rates and optimizing revenue generation. The findings suggest that this combined framework offers a practical, data-driven solution for sales teams, facilitating more strategic decision-making in B2B environments.

Keywords: sales forecasting, machine learning, rule-based decision model, customer prioritization, predictive analytics

Procedia PDF Downloads 13

Authors: Mohammadreza Mohebbi, Masoumeh Sanagou

Abstract:

The ability to predict clinical outcomes is of great importance to physicians and clinicians. A number of different methods have been used in an effort to accurately predict these outcomes. These methods include the development of scoring systems based on multivariate statistical modelling, and models involving the use of classification and regression trees. The process usually consists of two consecutive phases, namely model development and external validation. The model development phase consists of building a multivariate model and evaluating its predictive performance by examining calibration and discrimination, and internal validation. External validation tests the predictive performance of a model by assessing its calibration and discrimination in different but plausibly related patients. A motivate example focuses on prediction modeling using a sample of patients undergone coronary artery bypass graft (CABG) has been used for illustrative purpose and a set of primary considerations for evaluating prediction model studies using specific quality indicators as criteria to help stakeholders evaluate the quality of a prediction model study has been proposed.

Keywords: clinical prediction models, clinical decision rule, prognosis, external validation, model calibration, biostatistics

Procedia PDF Downloads 295

Authors: Aleme Mekuria, Samuel Mathewos

Abstract:

Background: Teenage pregnancy has long been a worldwide social, economic and educational concern for the developed, developing and underdeveloped countries. Studies on adolescent sexuality and pregnancy are very limited in our country. Therefore, this study aims at assessing the prevalence of teenage pregnancy and its determinants among school adolescents of Arba Minch town. Methods: Institution- based, cross-sectional study was conducted from 20-30 March 2014. Systematic sampling technique was used to select a total of 578 students from four schools of the town. Data were collected by trained data collectors using a pre-tested, self-administered structured questionnaire. The analysis was made using the software SPSS version 20.0 statistical packages. Multivariate logistic regression was used to identify the predictors of teenage pregnancy. Results: The prevalence of teenage pregnancy among school adolescents of Arba Minch town was 7.7%. Being grade11(AOR=4.6;95%CI:1.4,9.3) and grade12 student (AOR=5.8;95% CI:1.3,14.4), not knowing the correct time to take emergency contraceptives(AOR=3.3;95%CI:1.4,7.4), substance use(AOR=3.1;95%CI:1.1,8.8), living with either of biological parents (AOR=3.3;95%CI:1.1,8.7) and poor parent-daughter interaction (AOR=3.1;95%CI:1.1,8.7) were found to be significant predictors of teenage pregnancy. Conclusion: This study revealed a high level of teenage pregnancy among school adolescents of Arba Minch town. A significant number of adolescent female school students were at risk of facing the challenges of teenage pregnancy in the study area. School-based reproductive health education and strong parent-daughter relationships should be strengthened.

Keywords: adolescent, Arba minch, risk factors, school, southern Ethiopia, teenage pregnancy

Procedia PDF Downloads 347

Authors: Suparman

Abstract:

Piecewise linear regression models are very flexible models for modeling the data. If the piecewise linear regression models are matched against the data, then the parameters are generally not known. This paper studies the problem of parameter estimation of piecewise linear regression models. The method used to estimate the parameters of picewise linear regression models is Bayesian method. But the Bayes estimator can not be found analytically. To overcome these problems, the reversible jump MCMC algorithm is proposed. Reversible jump MCMC algorithm generates the Markov chain converges to the limit distribution of the posterior distribution of the parameters of picewise linear regression models. The resulting Markov chain is used to calculate the Bayes estimator for the parameters of picewise linear regression models.

Keywords: regression, piecewise, Bayesian, reversible Jump MCMC

Procedia PDF Downloads 519

Authors: Ibrahim Ahmed, Richard Amoateng, Akhil Jain, Mohamed Ahmed

Abstract:

Alcoholic cardiomyopathy (ACM) is a type of acquired cardiomyopathy caused by chronic alcohol consumption. Frequently ACM is associated with arrhythmias such as atrial flutter. Our aim was to characterize the patient demographics and investigate the effect of atrial flutter (AF) on ACM. This was a retrospective cohort study using the Nationwide Inpatient Sample database to identify admissions in adults with principal and secondary diagnoses of alcoholic cardiomyopathy and atrial flutter from 2019. Multivariate linear and logistic regression models were adjusted for age, gender, race, household income, insurance status, Elixhauser comorbidity score, hospital location, bed size, and teaching status. The primary outcome was all-cause mortality, and secondary outcomes were the length of stay (LOS) and total charge in USD. There was a total of 21,855 admissions with alcoholic cardiomyopathy, of which 1,635 had atrial flutter (AF-ACM). Compared to Non-AF-ACM cohort, AF-ACM cohort had fewer females (4.89% vs 14.54%, p<0.001), were older (58.66 vs 56.13 years, p<0.001), fewer Native Americans (0.61% vs2.67%, p<0.01), had fewer smaller (19.27% vs 22.45%, p<0.01) & medium-sized hospitals (23.24% vs28.98%, p<0.01), but more large-sized hospitals (57.49% vs 48.57%, p<0.01), more Medicare (40.37% vs 34.08%, p<0.05) and fewer Medicaid insured (23.55% vs 33.70%, p=<0.001), fewer hypertension (10.7% vs 15.01%, p<0.05), and more obesity (24.77% vs 16.35%, p<0.001). Compared to Non-AF-ACM cohort, there was no difference in AF-ACM cohort mortality rate (6.13% vs 4.20%, p=0.0998), unadjusted mortality OR 1.49 (95% CI 0.92-2.40, p=0.102), adjusted mortality OR 1.36 (95% CI 0.83-2.24, p=0.221), but there was a difference in LOS 1.23 days (95% CI 0.34-2.13, p<0.01), total charge $28,860.30 (95% CI 11,883.96-45,836.60, p<0.01). In patients admitted with ACM, the presence of AF was not associated with a higher all-cause mortality rate or odds of all-cause mortality; however, it was associated with 1.23 days increase in LOS and a $28,860.30 increase in total hospitalization charge. Native Americans, older age and obesity were risk factors for the presence of AF in ACM.

Keywords: alcoholic cardiomyopathy, atrial flutter, cardiomyopathy, arrhythmia

Procedia PDF Downloads 111

Authors: Md Monoarul Haque

Abstract:

Nutritional status is a sensitive indicator of community health and nutrition among preschool children, especially the prevalence of undernutrition that affects all dimensions of human development and leads to growth faltering in early life. The present study is an attempt to assess the food intake pattern and nutritional status of pre-school Chakma tribe children. It was a cross-sectional community based study. The subjects were selected purposively. This study was conducted at Savar Upazilla of Rangamati. Rangamati is located in the Chittagong Division. Anthropometric data height and weight of the study subjects were collected by standard techniques. Nutritional status was measured using Z score according WHO classification. χ2 test, independent t-test, Pearson’s correlation, multiple regression and logistic regression was performed as P<0.05 level of significance. Statistical analyses were performed by appropriate univariate and multivariate techniques using SPSS windows 11.5. Moderate (-3SD to <-2SD) to severe underweight (<-3SD) were 23.8% and 76.2% study subjects had normal weight for their age. Moderate (-3SD to <-2SD) to severe (<-3SD) stunted children were only 25.6% and 74.4% children were normal and moderate to severe wasting were 14.7% whereas normal child was 85.3%. Significant association had been found between child nutritional status and monthly family income, mother education and occupation of father and mother. Age, sex and incomes of the family, education of mother and occupation of father were significantly associated with WAZ and HAZ of the study subjects (P=0.0001, P=0.025, P=0.001 and P=0.0001, P=0.003, P=0.031, P=0.092, P=0.008). Maximum study subjects took local small fish and some traditional tribal food like bashrool, jhijhipoka and pork very much popular food among tribal children. Energy, carbohydrate and fat intake was significantly associated with HAZ, WAZ, BAZ and MUACZ. This study demonstrates that malnutrition among tribal children in Bangladesh is much better than national scenario in Bangladesh. Significant association was found between child nutritional status and family monthly income, mother education and occupation of father and mother. Most of the study subjects took local small fish and some traditional tribal food. Significant association was also found between child nutritional status and dietary intake of energy, carbohydrate and fat.

Keywords: food intake pattern, nutritional status, preschool children, Chakma ethnic community

Procedia PDF Downloads 503

Authors: Srinivasa Rao Gadde

Abstract:

In this article, we considered a group acceptance sampling plans for exponentiated half logistic distribution when the life-test is truncated at a pre-specified time. It is assumed that the index parameter of the exponentiated half logistic distribution is known. The design parameters such as the number of groups and the acceptance number are obtained by satisfying the producer’s and consumer’s risks at the specified quality levels in terms of medians and 10th percentiles under the assumption that the termination time and the number of items in each group are pre-fixed. Finally, an example is given to illustration the methodology.

Keywords: group acceptance sampling plan, operating characteristic, consumer and producer’s risks, truncated life-test

Procedia PDF Downloads 339

Authors: Rafael Zhindon Almeida

Abstract:

Surface water quality is an important concern for the evaluation and prediction of water quality conditions. The objective of this study is to develop a statistical model that can accurately predict the water quality of the El Macho estuary in the city of Machala, El Oro province. The methodology employed in this study is of a basic type that involves a thorough search for theoretical foundations to improve the understanding of statistical modeling for water quality analysis. The research design is correlational, using a multivariate statistical model involving multiple linear regression and principal component analysis. The results indicate that water quality parameters such as fecal coliforms, biochemical oxygen demand, chemical oxygen demand, iron and dissolved oxygen exceed the allowable limits. The water of the El Macho estuary is determined to be below the required water quality criteria. The multiple linear regression model, based on chemical oxygen demand and total dissolved solids, explains 99.9% of the variance of the dependent variable. In addition, principal component analysis shows that the model has an explanatory power of 86.242%. The study successfully developed a statistical model to evaluate the water quality of the El Macho estuary. The estuary did not meet the water quality criteria, with several parameters exceeding the allowable limits. The multiple linear regression model and principal component analysis provide valuable information on the relationship between the various water quality parameters. The findings of the study emphasize the need for immediate action to improve the water quality of the El Macho estuary to ensure the preservation and protection of this valuable natural resource.

Keywords: statistical modeling, water quality, multiple linear regression, principal components, statistical models

Procedia PDF Downloads 96

Authors: Rachna Agarwal, R. Naveen, Darpan Thakre, Rohit Shahi, Maryam Abbasi, Upendra Rathore, Latika Gupta

Abstract:

Aim: Retinal changes are the window to systemic vasculature. Therefore, we explored retinal changes in patients with idiopathic inflammatory myopathies (IIM) as a surrogate for vascular health. Methods: Adult and juvenile IIM patients visiting a tertiary care centre in 2021 satisfying the International Myositis Classification Criteria were enrolled for detailed ophthalmic examination in comparison with healthy controls (HC). Patients with conditions that precluded thorough posterior chamber examination were excluded. Scale variables are expressed as median (IQR). Multivariate analysis (binary logistic regression-BLR) was conducted, adjusting for age, gender, and comorbidities besides factors significant in univariate analysis. Results: 43 patients with IIM [31 females; age 36 (23-45) years; disease duration 5.5 (2-12) months] were enrolled for participation. DM (44%) was the most common diagnosis. IIM patients exhibited frequent attenuation of retinal vessels (32.6% vs. 4.3%, p <0.001), AV nicking (14% vs. 2.2%, p=0.053), and vascular tortuosity (18.6% vs. 2.2%, p=0.012), besides decreased visual acuity (53.5% vs. 10.9%, p<0.001) and immature cataracts (34.9% vs. 2.2%, p<0.001). Attenuation of vessels [OR 10.9 (1.7-71), p=0.004] emerged as significantly different from HC after adjusting for covariates in BLR. Notably, adults with IIM were more predisposed to retinal abnormalities [21 (57%) vs. 1 (16%), p=0.068], especially attenuation of vessels [14(38%) vs. 0(0), p=0.067] than jIIM. However, no difference was found in retinal features amongst the subtypes of adult IIM, nor did they correlate with MDAAT, MDI, or HAQ-DI. Conclusion: Retinal microvasculopathy and diminution of vision occur in nearly one-third to half of the patients with IIM. Microvasculopathy occurs across subtypes of IIM, and more so in adults, calling for further investigation as a surrogate for damage assessment and potentially even systemic vascular health.

Keywords: idiopathic inflammatory myopathies, vascular health, retinal microvasculopathy, arterial attenuation

Procedia PDF Downloads 89

Authors: Sandipika Gupta

Abstract:

Objective: Due to admirably low 30-day mortality rates for paediatric cardiac surgery, it is now pertinent to turn towards more intermediate-length outcomes such as morbidities closely associated with these surgeries. One such morbidity, major adverse events (MAE) comprises a group of adverse outcomes associated with paediatric cardiac surgery (e.g. cardiac arrest, major haemorrhage). Methods: This is a retrospective study that analysed the incidence and impact of MAE which was the primary outcome in the UK population. The data was collected in 5 centres between October 2015 and June 2017, amassing 3090 surgical episodes. The incidence and risk factors for MAE, were assessed through descriptive statistical analyses and multivariate logistic regression. The secondary outcomes of life status at 6 months and the length of hospital stay were also evaluated to understand the impact of MAE on patients. Results: Out of 3090 episodes, 134 (4.3%) had a postoperative MAE. The majority of the episodes were in: neonates (47%, P<0.001), high-risk cardiac diagnosis groups (20.1%, P<0.001), episodes with longer 5mes on the bypass (72.4%, P<0.001) and urgent surgeries (57.9%, P<0.001). Episodes reporting MAE also reported longer lengths of stay in hospital (29 days vs 9 days, P<0.001). Furthermore, patients experiencing MAE were at a higher risk of mortality at the 6-month life status check (mortality rates: 29.2% vs 2%, P<0.001).Conclusions: Key risk factors were identified. An important negative impact of MAE was found for patients. The identified risk factors could be used to profile and flag at-risk patients. Monitoring of MAE rates and closer investigation into the care pathway before and after individual MAEs in children’s heart units may lead to a reduction in these terrible events.

Keywords:

Procedia PDF Downloads 231

Authors: Andrew Green, Jiaming Liu, Kellathur Srinivasan, Raymond Chua

Abstract:

Introduction: The size of Singapore’s online health product (HP) market (e-commerce) is largely unknown. However, it is recognized that a large majority comes from overseas and thus, unregulated. As buying HP from unauthorized sources significantly compromises public health safety, understanding e-commerce users’ demographics and their perceptions on online HP purchasing becomes a pivotal first step to form a basis for recommendations in Singapore’s pharmacovigilance efforts. Objective: To assess the prevalence of online HP purchasing behaviour among Singaporean e-commerce users. Methodology: This is a cross-sectional study targeting Singaporean e-commerce users recruited from various local websites and online forums. Participants were not randomized into study arms but instead stratified by random sampling method based on participants’ age. A self-administered anonymous questionnaire was used to explore participants' demographics, online HP purchasing behaviour, knowledge and attitude. The association of different variables with online HP purchasing behaviour was analysed using logistic regression statistics. Main outcome measures: Prevalence of HP e-commerce users in Singapore (%) and variables that contribute to the prevalence (adjusted prevalent ratio). Results: The study recruited 372 complete and valid responses. The prevalence of online HP consumers among e-commerce users in Singapore is estimated to be 55.9% (1.7 million consumers). Online purchasing of complementary HP (46.9%) was the most prevalent, followed by medical devices (21.6%) and Western medicine (20.5%). Multivariate analysis showed that age is an independent variable that correlates with the likelihood of buying HP online. The prevalence of HP e-commerce users is highest in the 35-44 age group (64.1%) and lowest among the 16-24 age group (36.4%). The most bought HP through the internet are vitamins and minerals (21.5%), non-herbal (15.9%), herbal (13.9%), weight loss (8.7%) and sports (8.4%) supplements. While the top 3 products are distributed equally between the genders, there is a skew towards female respondents (12.4% in females vs. 4.9% in males) for weight loss supplements and towards males (13.2% in males vs. 3.7% in females) for sports supplements. Even though online consumers are in the younger age brackets, our study found that up to 72.0% of HP bought online are bought for others (buyer’s family and/or friends). Multivariate analysis showed a statistically significant association between purchasing HP through online means and the perceptions that 'internet is safe' (adjusted Prevalence Ratio=1.15, CI 1.03-1.28), 'buying HP online is time saving' (PR=1.17, CI 1.01-1.36), and 'recognition of HP brand' (PR=1.21 CI 1.06-1.40). Conclusions: This study has provided prevalence data for online HP market in Singapore, and has allowed the country’s regulatory body to formulate a targeted pharmacovigilance approach to this growing problem.

Keywords: e-commerce, pharmaceuticals, pharmacovigilance, Singapore

Procedia PDF Downloads 362

Authors: Animish Jain

Abstract:

This study deals with using Multiplicative Weight Update within artificial intelligence and machine learning to create models that can diagnose skin cancer using microscopic images of cancer samples. In this study, the multiplicative weight update method is used to take the predictions of multiple models to try and acquire more accurate results. Logistic Regression, Convolutional Neural Network (CNN), and Support Vector Machine Classifier (SVMC) models are employed within the Multiplicative Weight Update system. These models are trained on pictures of skin cancer from the ISIC-Archive, to look for patterns to label unseen scans as either benign or malignant. These models are utilized in a multiplicative weight update algorithm which takes into account the precision and accuracy of each model through each successive guess to apply weights to their guess. These guesses and weights are then analyzed together to try and obtain the correct predictions. The research hypothesis for this study stated that there would be a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The SVMC model had an accuracy of 77.88%. The CNN model had an accuracy of 85.30%. The Logistic Regression model had an accuracy of 79.09%. Using Multiplicative Weight Update, the algorithm received an accuracy of 72.27%. The final conclusion that was drawn was that there was a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The conclusion was made that using a CNN model would be the best option for this problem rather than a Multiplicative Weight Update system. This is due to the possibility that Multiplicative Weight Update is not effective in a binary setting where there are only two possible classifications. In a categorical setting with multiple classes and groupings, a Multiplicative Weight Update system might become more proficient as it takes into account the strengths of multiple different models to classify images into multiple categories rather than only two categories, as shown in this study. This experimentation and computer science project can help to create better algorithms and models for the future of artificial intelligence in the medical imaging field.

Keywords: artificial intelligence, machine learning, multiplicative weight update, skin cancer

Procedia PDF Downloads 78

Authors: Masahiro Ohmura, Koh Kakusho, Takeshi Okadome

Abstract:

This paper presents a regression model with autocorrelated errors in which the inputs are social moods obtained by analyzing the adjectives in Twitter posts using a document topic model. The regression model predicts Dow Jones Industrial Average (DJIA) more precisely than autoregressive moving-average models.

Keywords: stock market prediction, social moods, regression model, DJIA

Procedia PDF Downloads 547

Authors: Narges Ebadi, Davod Ahmadi, Hiliary Monteith, Hugo Melgar-Quinonez

Abstract:

Migration cannot necessarily relieve pressure on water resources in origin communities, and male out-migration can increase the water management burden of women. However, inflows of financial remittances seem to offer possibilities of investing in improving drinking-water access. Therefore, remittances may be an important pathway for migrants to support water security. This paper explores the association between water access and the receipt of remittances in households in sub-Saharan Africa. Data from round 6 of the 'Afrobarometer' surveys in 2016 were used (n= 49,137). Descriptive, bivariate and multivariate statistical analyses were carried out in this study. Regardless of country, findings from descriptive analyses showed that approximately 80% of the respondents never received remittance, and 52% had enough clean water. Only one-fifth of the respondents had piped water supply inside the house (19.9%), and approximately 25% had access to a toilet inside the house. Bivariate analyses revealed that even though receiving remittances was significantly associated with water supply, the strength of association was very weak. However, other factors such as the area of residence (rural vs. urban), cash income frequencies, electricity access, and asset ownership were strongly associated with water access. Results from unadjusted multinomial logistic regression revealed that the probability of having no access to piped water increased among remittance recipients who received financial support at least once a month (OR=1.324) (p < 0.001). In contrast, those not receiving remittances were more likely to regularly have a water access concern (OR=1.294) (p < 0.001), and not have access to a latrine (OR=1.665) (p < 0.001). In conclusion, receiving remittances is significantly related to water access as the strength of odds ratios for socio-demographic factors was stronger.

Keywords: remittances, water access, SSA, migration

Procedia PDF Downloads 175

Authors: Linghui Meng, James Atlas, Deborah Munro

Abstract:

There is an increasing demand for prosthetics capable of mimicking natural limb movements and hand gestures, but precise movement control of prosthetics using only electrode signals continues to be challenging. This study considers the implementation of machine learning as a means of improving accuracy and presents an initial investigation into hand gesture recognition using models based on electromyographic (EMG) signals. EMG signals, which capture muscle activity, are used as inputs to machine learning algorithms to improve prosthetic control accuracy, functionality and adaptivity. Using logistic regression, a machine learning classifier, this study evaluates the accuracy of classifying two hand gestures from the publicly available Ninapro dataset using two-time series feature extraction algorithms: Time Series Feature Extraction (TSFE) and Convolutional Neural Networks (CNNs). Trials were conducted using varying numbers of EMG channels from one to eight to determine the impact of channel quantity on classification accuracy. The results suggest that although both algorithms can successfully distinguish between hand gesture EMG signals, CNNs outperform TSFE in extracting useful information for both accuracy and computational efficiency. In addition, although more channels of EMG signals provide more useful information, they also require more complex and computationally intensive feature extractors and consequently do not perform as well as lower numbers of channels. The findings also underscore the potential of machine learning techniques in developing more effective and adaptive prosthetic control systems.

Keywords: EMG, machine learning, prosthetic control, electromyographic prosthetics, hand gesture classification, CNN, computational neural networks, TSFE, time series feature extraction, channel count, logistic regression, ninapro, classifiers

Procedia PDF Downloads 18

Authors: Haoming Ma, Guo Yu, Peiru Zhou

Abstract:

Background: Previous studies show that dysglycemia, mostly hyperglycemia, hypoglycemia and glycemic variability(GV), are associated with excess mortality in critically ill patients, especially those without diabetes. Glycemic variability is an increasingly important measure of glucose control in the intensive care unit (ICU) due to this association. However, there is limited data pertaining to the relationship between different clinical factors and glycemic variability and clinical outcomes categorized by their DM status. This retrospective study of 958 intensive care unit(ICU) patients was conducted to investigate the relationship between GV and outcome in critically ill patients and further to determine the significant factors that contribute to the glycemic variability. Aim: We hypothesize that the factors contributing to mortality and the glycemic variability are different from critically ill patients with or without diabetes. And the primary aim of this study was to determine which dysglycemia (hyperglycemia\hypoglycemia\glycemic variability) is independently associated with an increase in mortality among critically ill patients in different groups (DM/Non-DM). Secondary objectives were to further investigate any factors affecting the glycemic variability in two groups. Method: A total of 958 diabetic and non-diabetic patients with severe diseases in the ICU were selected for this retrospective analysis. The glycemic variability was defined as the coefficient of variation (CV) of blood glucose. The main outcome was death during hospitalization. The secondary outcome was GV. The logistic regression model was used to identify factors associated with mortality. The relationships between GV and other variables were investigated using linear regression analysis. Results: Information on age, APACHE II score, GV, gender, in-ICU treatment and nutrition was available for 958 subjects. Predictors remaining in the final logistic regression model for mortality were significantly different in DM/Non-DM groups. Glycemic variability was associated with an increase in mortality in both DM(odds ratio 1.05; 95%CI:1.03-1.08,p＜0.001) or Non-DM group(odds ratio 1.07; 95%CI:1.03-1.11,p=0.002). For critically ill patients without diabetes, factors associated with glycemic variability included APACHE II score(regression coefficient, 95%CI:0.29,0.22-0.36,p＜0.001), Mean BG(0.73,0.46-1.01,p＜0.001), total parenteral nutrition(2.87,1.57-4.17,p＜0.001), serum albumin(-0.18,-0.271 to -0.082,p＜0.001), insulin treatment(2.18,0.81-3.55,p=0.002) and duration of ventilation(0.006,0.002-1.010,p=0.003).However, for diabetes patients, APACHE II score(0.203,0.096-0.310,p＜0.001), mean BG(0.503,0.138-0.869,p=0.007) and duration of diabetes(0.167,0.033-0.301,p=0.015) remained as independent risk factors of GV. Conclusion: We found that the relation between dysglycemia and mortality is different in the diabetes and non-diabetes groups. And we confirm that GV was associated with excess mortality in DM or Non-DM patients. Furthermore, APACHE II score, Mean BG, total parenteral nutrition, serum albumin, insulin treatment and duration of ventilation were significantly associated with an increase in GV in Non-DM patients. While APACHE II score, mean BG and duration of diabetes (years) remained as independent risk factors of increased GV in DM patients. These findings provide important context for further prospective trials investigating the effect of different clinical factors in critically ill patients with or without diabetes.

Keywords: diabetes, glycemic variability, predictors, severe disease

Procedia PDF Downloads 187

Authors: Shiwei Deng, Yang Bao

Abstract:

In this paper, we present a model-based regression test suite reducing approach that uses EFSM model dependence analysis and probability-driven greedy algorithm to reduce software regression test suites. The approach automatically identifies the difference between the original model and the modified model as a set of elementary model modifications. The EFSM dependence analysis is performed for each elementary modification to reduce the regression test suite, and then the probability-driven greedy algorithm is adopted to select the minimum set of test cases from the reduced regression test suite that cover all interaction patterns. Our initial experience shows that the approach may significantly reduce the size of regression test suites.

Keywords: dependence analysis, EFSM model, greedy algorithm, regression test

Procedia PDF Downloads 425

Authors: Luigi Delle Rose, Oliver Fischer, Ahmed Hammad

Abstract:

In this article, we study the prospects of the proposed Large Hadron electron Collider (LHeC) in the search for heavy neutral scalar particles. We consider a minimal model with one additional complex scalar singlet that interacts with the Standard Model (SM) via mixing with the Higgs doublet, giving rise to an SM-like Higgs boson and a heavy scalar particle. Both scalar particles are produced via vector boson fusion and can be tested via their decays into pairs of SM particles, analogously to the SM Higgs boson. Using multivariate techniques, we show that the LHeC is sensitive to heavy scalars with masses between 200 and 800 GeV down to scalar mixing of order 0.01.

Keywords: beyond the standard model, large hadron electron collider, multivariate analysis, scalar singlet

Procedia PDF Downloads 135

Authors: Suparman

Abstract:

Piecewise polynomial regression model is very flexible model for modeling the data. If the piecewise polynomial regression model is matched against the data, its parameters are not generally known. This paper studies the parameter estimation problem of piecewise polynomial regression model. The method which is used to estimate the parameters of the piecewise polynomial regression model is Bayesian method. Unfortunately, the Bayes estimator cannot be found analytically. Reversible jump MCMC algorithm is proposed to solve this problem. Reversible jump MCMC algorithm generates the Markov chain that converges to the limit distribution of the posterior distribution of piecewise polynomial regression model parameter. The resulting Markov chain is used to calculate the Bayes estimator for the parameters of piecewise polynomial regression model.

Keywords: piecewise regression, bayesian, reversible jump MCMC, segmentation

Procedia PDF Downloads 371

Authors: Yiseyon Sunday Hosu, Motebang Dominic Vincent Nakin, Elphina N. Cishe

Abstract:

Universal access to clean and safe drinking water and basic sanitation is one of the targets of the 6th Sustainable Development Goals (SDGs). This paper explores the evidence-based indicators of Water Rights Acts (2013) among households in the rural communities in the Mthatha River catchment of OR Tambo District Municipality of South Africa. Daily access to minimum 25 litres/person and the factors influencing clean water access were investigated in the catchment. A total number of 420 households were surveyed in the upper, peri-urban, lower and coastal regions of Mthatha Rivier catchment. Descriptive and logistic regression analyses were conducted on the data collected from the households to elicit vital information on domestic water security among rural community dwellers. The results show that approximately 68 percent of total households surveyed have access to the required minimum 25 litre/person/day, with 66.3 percent in upper region, 76 per cent in the peri-urban, 1.1 percent in the lower and 2.3 percent in the coastal regions. Only 30 percent among the total surveyed households had access to piped water either in the house or public taps. The logistic regression showed that access to clean water was influenced by lack of water infrastructure, proximity to urban regions, daily flow of pipe-borne water, household size and distance to public taps. This paper recommends that viable integrated rural community-based water infrastructure provision strategies between NGOs and local authority and the promotion of point of use (POU) technologies to enhance better access to clean water.

Keywords: domestic water, household technology, water security, rural community

Procedia PDF Downloads 353

Authors: Hyuk-Hoon Kim, Young Gi Min

Abstract:

Background: In carbon monoxide (CO) intoxication, the pathophysiology of delayed neurological sequelae (DNS) is very complex and remains poorly understood. And predicting whether patients who exhibit resolved acute symptoms have escaped or will experience DNS represents a very important clinical issue. Brain magnetic resonance (MR) imaging has been conducted to assess the severity of brain damage as an objective method to predict prognosis. And co-ingestion of a second poison in patients with intentional CO poisoning occurs in almost one-half of patients. Among patients with co-ingestions, 66% ingested ethanol. We assessed the effects of ethanol on neurologic sequelae prevalence in acute CO intoxication by means of abnormal lesion in brain MR. Method: This study was conducted retrospectively by collecting data for patients who visited an emergency medical center during a period of 5 years. The enrollment criteria were diagnosis of acute CO poisoning and the measurement of the serum ethanol level and history of taking a brain MR during admission period. Official readout data by radiologist are used to decide whether abnormal lesion is existed or not. The enrolled patients were divided into two groups: patients with abnormal lesion and without abnormal lesion in Brain MR. A standardized extraction using medical record was performed; Mann Whitney U test and logistic regression analysis were performed. Result: A total of 112 patients were enrolled, and 68 patients presented abnormal brain lesion on MR. The abnormal brain lesion group had lower serum ethanol level (mean, 20.14 vs 46.71 mg/dL) (p-value<0.001). In addition, univariate logistic regression analysis showed the serum ethanol level (OR, 0.99; 95% CI, 0.98 -1.00) was independently associated with the development of abnormal lesion in brain MR. Conclusion: Ethanol could have neuroprotective effect in acute CO intoxication by sedative effect in stressful situation and mitigative effect in neuro-inflammatory reaction.

Keywords: carbon monoxide, delayed neuropsychological sequelae, ethanol, intoxication, magnetic resonance

Procedia PDF Downloads 251

Authors: Ruttana Phetsitong, Patama Vapattanawong, Malee Sunpuwan, Marc Voelker

Abstract:

The majority of care for older people at home in Thai society falls upon caregivers resulting in caregiver’s mental health problem. Beyond individual characteristics, household factors might have a profound effect on the caregiver’s mental health. But reliable data capturing this at the household level have been limited to date. The objectives of the present study were to explore the levels of Thai caregiver’s mental health and to investigate the factors affecting the mental health at household level. Data were obtained from the 2011 National Survey of Thai Older Persons conducted by the National Statistical Office of Thailand. Caregiver’s mental health was measured by using the 15- items-short version of the Thai Mental Health Indicator (TMHI-15) developed by the Department of Mental Health, the Ministry of Public Health. Multivariate logistic regression models were used to explore the impact of potential factors on caregiver’s mental health. The THMI-15 produced an overall average caregiver mental health score of 30.9 out of 45 (SD 5.3). The score can be categorized into good (34.02-45), fair (27.01-34), and poor (0-27). Duration of care for older people, household wealth, and functional dependency of the older people significantly predicted total caregiver’s mental health. Household economic factor was key in predicting better mental health. Compared to those poorest households, the adjusted effect of the fifth quintile household wealth was high (OR=2.34; 95%CI=1.47-3.73). The findings of this study provide a fuller picture to a better understanding of the level and factors that cause the mental health of Thai caregivers. Health care providers and policymakers should consider these factors when designing interventions aimed at alleviating caregiver’s psychological burden when provided care for older people at home.

Keywords: caregiver’s mental health, household, older people, Thailand

Procedia PDF Downloads 144

Authors: Shih-Pin Chen, Shih-Syuan You

Abstract:

Fuzzy regression models are useful for investigating the relationship between explanatory variables and responses in fuzzy environments. To overcome the deficiencies of previous models and increase the explanatory power of fuzzy data, the graded mean integration (GMI) representation is applied to determine representative crisp regression coefficients. A fuzzy regression model is constructed based on the modified dissemblance index (MDI), which can precisely measure the actual total error. Compared with previous studies based on the proposed MDI and distance criterion, the results from commonly used test examples show that the proposed fuzzy linear regression model has higher explanatory power and forecasting accuracy.

Keywords: dissemblance index, fuzzy linear regression, graded mean integration, mathematical programming

Procedia PDF Downloads 435

Authors: Zachary Pan

Abstract:

Our general mission is to solve the problem of classifying images into different body part types and deciding if each of them is healthy or not. However, for now, we will determine healthiness for only one-sixth of the body parts, specifically the chest. We will detect pneumonia in X-ray scans of those chest images. With this type of AI, doctors can use it as a second opinion when they are taking CT or X-ray scans of their patients. Another ad-vantage of using this machine learning classifier is that it has no human weaknesses like fatigue. The overall ap-proach to this problem is to split the problem into two parts: first, classify the image, then determine if it is healthy. In order to classify the image into a specific body part class, the body parts dataset must be split into test and training sets. We can then use many models, like neural networks or logistic regression models, and fit them using the training set. Now, using the test set, we can obtain a realistic accuracy the models will have on images in the real world since these testing images have never been seen by the models before. In order to increase this testing accuracy, we can also apply many complex algorithms to the models, like multiplicative weight update. For the second part of the problem, to determine if the body part is healthy, we can have another dataset consisting of healthy and non-healthy images of the specific body part and once again split that into the test and training sets. We then use another neural network to train on those training set images and use the testing set to figure out its accuracy. We will do this process only for the chest images. A major conclusion reached is that convolutional neural networks are the most reliable and accurate at image classification. In classifying the images, the logistic regression model, the neural network, neural networks with multiplicative weight update, neural networks with the black box algorithm, and the convolutional neural network achieved 96.83 percent accuracy, 97.33 percent accuracy, 97.83 percent accuracy, 96.67 percent accuracy, and 98.83 percent accuracy, respectively. On the other hand, the overall accuracy of the model that de-termines if the images are healthy or not is around 78.37 percent accuracy.

Keywords: body part, healthcare, machine learning, neural networks

Procedia PDF Downloads 102