Search results for: penalized logistic regression

Authors: Kaycee Bills

Abstract:

Studies have demonstrated that middle and high school students with disabilities are more likely to experience bullying than other student groups. The high rates of bullying victimization observed among youth with disabilities can result in severe socio-emotional consequences. These socio-emotional consequences often manifest in detrimental impacts on the students’ personal relationships. Past studies have indicated that participating in extracurricular athletic activities can have several socio-emotional benefits for students with disabilities. Given the findings of past studies demonstrating the positive relationship between mental health and participation in sports among students with disabilities, it is possible that participating in athletics could have a moderating relationship on the severity of the impact that bullying has on a student’s relationships with family and friends. Using the National Crime Victimization Survey/School Crime Supplement (NCVS/SCS), this study employs an ordinal logistic regression to determine if participation in extracurricular athletic activities mitigates the damaging impact bullying has on the personal relationships with friends and family among students who have disabilities. This study identified statistically significant results suggesting that students with disabilities who participate in athletics reported reduced levels of negative personal relationships resulting from bullying compared to their peers who did not participate in athletics.

Keywords: disability, inclusion, bullying, relationships

Procedia PDF Downloads 168

Authors: Abdulrahman Sumayli, Saad M. AlShahrani

Abstract:

For the hydrogenation process, knowing the solubility of hydrogen (H2) in hydrocarbons is critical to improve the efficiency of the process. We investigated the H2 solubility computation in four heavy crude oil feedstocks using machine learning techniques. Temperature, pressure, and feedstock type were considered as the inputs to the models, while the hydrogen solubility was the sole response. Specifically, we employed three different models: Support Vector Regression (SVR), Gaussian process regression (GPR), and Bayesian ridge regression (BRR). To achieve the best performance, the hyper-parameters of these models are optimized using the whale optimization algorithm (WOA). We evaluated the models using a dataset of solubility measurements in various feedstocks, and we compared their performance based on several metrics. Our results show that the WOA-SVR model tuned with WOA achieves the best performance overall, with an RMSE of 1.38 × 10− 2 and an R-squared of 0.991. These findings suggest that machine learning techniques can provide accurate predictions of hydrogen solubility in different feedstocks, which could be useful in the development of hydrogen-related technologies. Besides, the solubility of hydrogen in the four heavy oil fractions is estimated in different ranges of temperatures and pressures of 150 ◦C–350 ◦C and 1.2 MPa–10.8 MPa, respectively

Keywords: temperature, pressure variations, machine learning, oil treatment

Procedia PDF Downloads 53

Authors: Bhawna Verma

Abstract:

Looking at the contraceptive use and unmet need specific to the different age groups would help to understand various determinants and characteristics of women from different age groups, which are often being neglected. The study explores contraceptive behavior, unmet need for family planning and its correlates among young nulliparous women aged 15-29, using data from NFHS-4 (2015-16), India. Method: The study utilized information from 26,924 currently married women, who has no child or who have had first terminated pregnancy and was aged 15-29 at the time of the survey. Chi-Square and logistic regression analysis have been used to assess the effects of socio-economic characteristics. Results: Of all the considered explanatory variables religion, caste, education, current age, age at marriage, media exposure and regional differences were found to be significantly affecting the behavior of contraceptive use. Women of the 25-29 age group are 0.6 percent less likely to have an unmet need than women of 12-19 age group. Unmet need is increasing with the increased level of education. Muslim women are 0.3 percent less likely to have an unmet need than women of Hindu category. Conclusion: Separate considerations must be given to the needs for family planning formation among nulliparous women along with the factors associated with the use and non-use of contraceptives among them. Separate considerations must be given for effective promotion of FP knowledge through print, electronic media, towards the unequal access to the contraceptives among nulliparous women. Marriages after legal minimum age and encouraging women for higher education may address existing socio-economic barriers.

Keywords: contraceptive use, unmet need, family planning, contraceptive behavior

Procedia PDF Downloads 97

Authors: Fatemeh Abdollahi, Munn-Sann Lye, Jamshid Yazdani Charati, Mehran Zarghami

Abstract:

Both obesity and intimate partner violence (IPV) are growing health threats. This study aimed to assess the prevalence and risk factors of both IPV and obesity and their association. In this cross-sectional study, 530 women aged 16-65 years attending Mazandaran primary health centers were recruited through the stratified random sampling method (2019-2020). Data were collected using the modified World Health Organization Domestic Violence questionnaire, Perceived Stress Scale, and socio-demographic, obstetric, and anthropometric questionnaires. The data were analyzed using descriptive statistics, the chi-square test, and multiple logistic regression. The prevalence of overweight, obesity and psychological, physical, and sexual IPV were 47.6%, 26.7%, 70.4%, 17.9%, and 6.4%, respectively. Increasing women’s educational level and exposure to violence during their lifespan increased the odds of any type of IPV while living in a nuclear family reduced it. In groups of women who were subjected to any type of IPV and only psychological IPV, experiencing violence during the lifespan was significant in predicting obesity. The alarming prevalence of IPV and obesity-overweight in this study points to the need for collaborative socio-political and health intervention. The link between experiencing violence during lifespan and obesity in some subgroups of women highlights the detrimental consequences of chronic violence and the urgent need for effective preventive programs.

Keywords: intimate partner violence, body mass index, obesity, risk factor, women

Procedia PDF Downloads 82

Authors: Benjamin Bobbia, Matthias Picard

Abstract:

In recent years active learning methodologies based on the representativity of the data seems more promising to limit overfitting. The presented query methodology for regression using the Wasserstein distance measuring the representativity of our labelled dataset compared to the global distribution. In this work a crucial use of GroupSort Neural Networks is made therewith to draw a double advantage. The Wasserstein distance can be exactly expressed in terms of such neural networks. Moreover, one can provide explicit bounds for their size and depth together with rates of convergence. However, heterogeneity of the dataset is also considered by weighting the Wasserstein distance with the error of approximation at the previous step of active learning. Such an approach leads to a reduction of overfitting and high prediction performance after few steps of query. After having detailed the methodology and algorithm, an empirical study is presented in order to investigate the range of our hyperparameters. The performances of this method are compared, in terms of numbers of query needed, with other classical and recent query methods on several UCI datasets.

Keywords: active learning, Lipschitz regularization, neural networks, optimal transport, regression

Procedia PDF Downloads 67

Authors: Viacheslav Shkuratskyy, Aminu Bello Usman, Michael O’Dea, Saifur Rahman Sabuj

Abstract:

This paper examines relationships between solar activity and earthquakes; it applied machine learning techniques: K-nearest neighbour, support vector regression, random forest regression, and long short-term memory network. Data from the SILSO World Data Center, the NOAA National Center, the GOES satellite, NASA OMNIWeb, and the United States Geological Survey were used for the experiment. The 23rd and 24th solar cycles, daily sunspot number, solar wind velocity, proton density, and proton temperature were all included in the dataset. The study also examined sunspots, solar wind, and solar flares, which all reflect solar activity and earthquake frequency distribution by magnitude and depth. The findings showed that the long short-term memory network model predicts earthquakes more correctly than the other models applied in the study, and solar activity is more likely to affect earthquakes of lower magnitude and shallow depth than earthquakes of magnitude 5.5 or larger with intermediate depth and deep depth.

Keywords: k-nearest neighbour, support vector regression, random forest regression, long short-term memory network, earthquakes, solar activity, sunspot number, solar wind, solar flares

Procedia PDF Downloads 54

Authors: Izani Uzair Zubair, Mohd Ismail Ibrahim, Mohd Nazri Shafei, Hassan Merican Omar Naina Merican, Mohamad Sabri Othman, Mohd Izmi Ahmad Ibrahim, Rasilah Ramli, Rajpal Singh Karam Singh

Abstract:

Nurses experience a higher prevalence of low back pain (LBP) and musculoskeletal complaints as compared to other hospital workers. Due to no proper policy related to LBP, the job has exposed them to the problem. Thus, the current study aims to look at the intensity of the problem and factors associated with development of LBP. Method and Tools: A cross sectional study was carried out among 1292 nurses from six public hospitals in Penang. They were randomly selected and those who were pregnant and have been diagnosed to have LBP were excluded. A Malay validated BACK Questionnaire was used. The associated factors were determined by using multiple logistic regression from SPSS version 20.0. Result: Most of the respondents were at mean age 30 years old and had mean working experience 86 months. The prevalence of LBP was identified as 76% (95% CI 74, 82). Factors that were associated with LBP among nurses include lifting a heavy object (OR2.626 (95% CI 1.978, 3.486) p =0.001 and the estimation weight of the lifted object (OR1.443 (95% CI 1.056, 1.970) p =0.021. Conclusion: Nurses who practice lifting heavy object and weight of the object lifted give a significant contribution to the development of LBP. The prevalence of the problem is significantly high. Thus, a proper no weight lifting policy should be considered.

Keywords: low back pain, nurses, Penang public hospital, Penang

Procedia PDF Downloads 460

Authors: K. K. Lee, H. W. Han, H. L. Kang, T. A. Kim, S. H. Han

Abstract:

For the robust optimization of the manufacturing product design, there are design objectives that must be achieved, such as a minimization of the mean and standard deviation in objective functions within the required sensitivity constraints. The authors utilized the sensitivity of objective functions and constraints with respect to the effective design variables to reduce the computational burden associated with the evaluation of the probabilities. The individual mean and sensitivity values could be estimated easily by using the 9 level orthogonal array based response surface models optimized by the stepwise regression. The present study evaluates a proposed procedure from the robust optimization of rubber domes that are commonly used for keyboard switching, by using the 9 level orthogonal array and stepwise regression along with a desirability function. In addition, a new robust optimization process, i.e., the I2GEO (Identify, Integrate, Generate, Explore and Optimize), was proposed on the basis of the robust optimization in rubber domes. The optimized results from the response surface models and the estimated results by using the finite element analysis were consistent within a small margin of error. The standard deviation of objective function is decreasing 54.17% with suggested sensitivity based robust optimization. (Business for Cooperative R&D between Industry, Academy, and Research Institute funded Korea Small and Medium Business Administration in 2017, S2455569)

Keywords: objective function, orthogonal array, response surface model, robust optimization, stepwise regression

Procedia PDF Downloads 277

Authors: Julita D. L. Nainggolan, Cindy Novita Ongkowijoyo, Veli Sungono, Dyana Safitri Velies, Ernestine Vivie Sadeli, Jimmy

Abstract:

Introduction: Normal menstrual cycle in women ranges from 21-34 days. Menopause is defined as the time when there have been no menstrual periods for 12 consecutive months and no other biological or physiological cause can be identified. Caffeine might increase the estradiol in the early of follicular phase and possibly increase the progesterone and shorten menstruation cycle. Women with shorter menstrual cycle, (below 26 days) would likely get to menopause 1.4 years earlier than those who are normal, and 2.2 years earlier than women with longer menstrual cycle. Purpose: To study the association of caffeine consumption in coffee, tea, and soft drinks with the age of menopause. Design Study: A cross-sectional study using purposive sampling of 132 menopause women from elderly nursing, hospitals and students’ relatives from August 2015-December 2015. The mean difference of age of menopause among the caffeine intake was analyzed by using the unpaired t-test and logistic regression. Results: Mean current age of the respondents are 61.4 years ± SD 9.8; and age of menopause was 47.7 years ± SD 4.2. There are 49.6% who drink coffee, 62.6% of tea and 7.6% of soft drinks. The analysis of t-test showed no significant mean difference in age of menopause among women who drink coffee, tea and soft drinks, mean age of 47.63 ± 4.3 in coffee with p=0.392, mean age of 47.8 ± 4 in tea with p=0.373; and mean age of 46 ± 5.5 with p=0.083 after adjustment of smoking history. Conclusion: Consumption of caffeine among women who drink coffee, tea, and soft drinks did not show significant mean difference in age of menopause.

Keywords: caffeine, menopause, coffee, tea, soda, soft drinks

Procedia PDF Downloads 220

Authors: Nazli Uren, Ayse Okur

Abstract:

Tactile comfort of a textile product is an essential property and a major concern when it comes to customer perceptions and preferences. The subjective nature of comfort and the difficulties regarding the simulation of human hand sensory feelings make it hard to establish a well-accepted link between tactile comfort and objective evaluations. On the other hand, shear behavior of a fabric is a mechanical parameter which can be measured by various objective test methods. The principal aim of this study is to determine the tactile comfort of commercially available denim fabrics by subjective measurements, create a tactile score database for denim fabrics and investigate the relations between tactile comfort and shear behavior. In-plane shear behaviors of 17 different commercially available denim fabrics with a variety of raw material and weave structure were measured by a custom design shear frame and conventional bias extension method in two corresponding diagonal directions. Tactile comfort of denim fabrics was determined via subjective customer evaluations as well. Aforesaid relations were statistically investigated and introduced as regression equations. The analyses regarding the relations between tactile comfort and shear behavior showed that there are considerably high correlation coefficients. The suggested regression equations were likewise found out to be statistically significant. Accordingly, it was concluded that the tactile comfort of denim fabrics can be estimated with a high precision, based on the results of in-plane shear behavior measurements.

Keywords: denim fabrics, in-plane shear behavior, linear regression estimation, tactile comfort

Procedia PDF Downloads 283

Authors: M. S. Wickramarachchi, L. S. Nawarathna, C. M. B. Dematawewa

Abstract:

Hatchery performance is critical for the profitability of poultry breeder operations. Some extrinsic parameters of eggs and breeders cause to increase or decrease the hatchability. This study aims to identify the affecting extrinsic parameters on the commercial hatchability of local chicken's eggs and determine the most efficient classification model with a hatchability rate greater than 90%. In this study, seven extrinsic parameters were considered: egg weight, moisture loss, breeders age, number of fertilised eggs, shell width, shell length, and shell thickness. Multiple linear regression was performed to determine the most influencing variable on hatchability. First, the correlation between each parameter and hatchability were checked. Then a multiple regression model was developed, and the accuracy of the fitted model was evaluated. Linear Discriminant Analysis (LDA), Classification and Regression Trees (CART), k-Nearest Neighbors (kNN), Support Vector Machines (SVM) with a linear kernel, and Random Forest (RF) algorithms were applied to classify the hatchability. This grouping process was conducted using binary classification techniques. Hatchability was negatively correlated with egg weight, breeders' age, shell width, shell length, and positive correlations were identified with moisture loss, number of fertilised eggs, and shell thickness. Multiple linear regression models were more accurate than single linear models regarding the highest coefficient of determination (R²) with 94% and minimum AIC and BIC values. According to the classification results, RF, CART, and kNN had performed the highest accuracy values 0.99, 0.975, and 0.972, respectively, for the commercial hatchery process. Therefore, the RF is the most appropriate machine learning algorithm for classifying the breeder outcomes, which are economically profitable or not, in a commercial hatchery.

Keywords: classification models, egg weight, fertilised eggs, multiple linear regression

Procedia PDF Downloads 73

Authors: Seongcheol Kwon, Jeongmin Kim, Kwang Ryel Ryu

Abstract:

We assume an IoT-based smart-home environment where the on-off status of each of the electrical appliances including the room lights can be recognized in a real time by monitoring and analyzing the smart meter data. At any moment in such an environment, we can recognize what the household or the user is doing by referring to the status data of the appliances. In this paper, we focus on a smart-home service that is to activate a robot vacuum cleaner at right time by recognizing the user situation, which requires a situation-aware model that can distinguish the situations that allow vacuum cleaning (Yes) from those that do not (No). We learn as our candidate models a few classifiers such as naïve Bayes, decision tree, and logistic regression that can map the appliance-status data into Yes and No situations. Our training and test data are obtained from simulations of user behaviors, in which a sequence of user situations such as cooking, eating, dish washing, and so on is generated with the status of the relevant appliances changed in accordance with the situation changes. During the simulation, both the situation transition and the resulting appliance status are determined stochastically. To compare the performances of the aforementioned classifiers we obtain their learning curves for different types of users through simulations. The result of our empirical study reveals that naïve Bayes achieves a slightly better classification accuracy than the other compared classifiers.

Keywords: situation-awareness, smart home, IoT, machine learning, classifier

Procedia PDF Downloads 405

Authors: Kiurski S. Jelena, Aksentijević M. Snežana, Kecić S. Vesna, Oros B. Ivana

Abstract:

The prosperity of electronic equipment in photocopying environment not only has improved work efficiency, but also has changed indoor air quality. Considering the number of photocopying employed, indoor air quality might be worse than in general office environments. Determining the contribution from any type of equipment to indoor air pollution is a complex matter. Non-methane hydrocarbons are known to have an important role of air quality due to their high reactivity. The presence of hazardous pollutants in indoor air has been detected in one photocopying shop in Novi Sad, Serbia. Air samples were collected and analyzed for five days, during 8-hr working time in three-time intervals, whereas three different sampling points were determined. Using multiple linear regression model and software package STATISTICA 10 the concentrations of occupational hazards and micro-climates parameters were mutually correlated. Based on the obtained multiple coefficients of determination (0.3751, 0.2389, and 0.1975), a weak positive correlation between the observed variables was determined. Small values of parameter F indicated that there was no statistically significant difference between the concentration levels of non-methane hydrocarbons and micro-climates parameters. The results showed that variable could be presented by the general regression model: y = b0 + b1xi1+ b2xi2. Obtained regression equations allow to measure the quantitative agreement between the variation of variables and thus obtain more accurate knowledge of their mutual relations.

Keywords: non-methane hydrocarbons, photocopying process, multiple regression analysis, indoor air quality, pollutant emission

Procedia PDF Downloads 362

Authors: Wajid Mumtaz, Aamir Saeed Malik, Syed Saad Azhar Ali, Mohd Azhar Mohd Yasin

Abstract:

In this paper, a technique based on electroencephalogram (EEG) analysis is presented, aiming for diagnosing major depressive disorder (MDD) among a potential population of MDD patients and healthy controls. EEG is recognized as a clinical modality during applications such as seizure diagnosis, index for anesthesia, detection of brain death or stroke. However, its usability for psychiatric illnesses such as MDD is less studied. Therefore, in this study, for the sake of diagnosis, 2 groups of study participants were recruited, 1) MDD patients, 2) healthy people as controls. EEG data acquired from both groups were analyzed involving inter-hemispheric asymmetry and composite permutation entropy index (CPEI). To automate the process, derived quantities from EEG were utilized as inputs to classifier such as logistic regression (LR) and support vector machine (SVM). The learning of these classification models was tested with a test dataset. Their learning efficiency is provided as accuracy of classifying MDD patients from controls, their sensitivities and specificities were reported, accordingly (LR =81.7 % and SVM =81.5 %). Based on the results, it is concluded that the derived measures are indicators for diagnosing MDD from a potential population of normal controls. In addition, the results motivate further exploring other measures for the same purpose.

Keywords: major depressive disorder, diagnosis based on EEG, EEG derived features, CPEI, inter-hemispheric asymmetry

Procedia PDF Downloads 528

Authors: Syahira Ibrahim, Herlina Abdul Rahim

Abstract:

The amylose content is an essential element in determining the texture and taste of rice grains. This paper evaluates the use of VIS-SWNIRS in estimating the amylose content for seven varieties of rice grains available in the Malaysian market. Each type consists of 30 samples and all the samples are scanned using the spectroscopy to obtain a range of values between 680-1000nm. The Savitzky-Golay (SG) smoothing filter is applied to each sample’s data before the Principal Component Regression (PCR) technique is used to examine the data and produce a single value for each sample. This value is then compared with reference values obtained from the standard iodine colorimetric test in terms of its coefficient of determination, R2. Results show that this technique produced low R2 values of less than 0.50. In order to improve the result, the range should include a wavelength range of 1100-2500nm and the number of samples processed should also be increased.

Keywords: amylose content, diffuse reflectance, Malaysia rice grain, principal component regression (PCR), Visible and Shortwave near-infrared spectroscopy (VIS-SWNIRS)

Procedia PDF Downloads 363

Authors: Antoine Vikkey Hinson, Ranty Jolianelle Dassi, Menonli Adjobimey, Rose Mikponhoue, Paul Ayelo

Abstract:

Introduction: The psychological hardship of the teaching profession maintains a chronic stress that inevitably evolves into burnout (BO) in the absence of adequate preventive measures. The objective of this study is to study the prevalence and factors associated with burnout among secondary school teachers in the city of Cotonou in 2022. Methods: This was a descriptive cross-sectional study with an analytical aim and prospective data collection that took place over a period of 2 months, from July 19 to August 19 and from October 1 to October 31, 2022. Sampling was done using a three-stage probability sampling technique. Data analysis was performed using R 4.1.1 software. Bivariate logistic regression was used to identify associated factors. The significance level chosen was 5% (p < 0.05). Results: A total of 270 teachers were included in the study, of whom 208 (77.00%) were men. The mean age of the workers was 38.03 ± 8.30 years. According to the Maslach Burnout Inventory, 58.51% of the teachers had burnout, with 41.10% of teachers in emotional exhaustion, 27.40% in depersonalization and 21.90% in loss of personal accomplishment. The severity of the syndrome was low to moderate in almost all teachers. The occurrence of BO was associated with), not practicing sports (ORa= 2,38 [1,32; 4,28]), jobs training (ORa= 1,86 [1,04; 3,34]) and an imbalance of effort/reward (ORa= 5,98 [2,24;15,98]). Conclusion: The prevalence of BO is high among secondary school teachers in the city of Cotonou. A larger scale study, including research on its consequences on the teacher and the learner, is necessary in order to act quickly to implement a prevention program.

Keywords: burnout, teachers, Maslach burnout inventory, associated factors, Benin

Procedia PDF Downloads 55

Authors: Aref Aasi, Sahar Ebrahimi Bajgani, Erfan Aasi

Abstract:

Breast cancer (BC) continues to be the most frequent cancer in females and causes the highest number of cancer-related deaths in women worldwide. Inspired by recent advances in studying the relationship between different patient attributes and features and the disease, in this paper, we have tried to investigate the different classification methods for better diagnosis of BC in the early stages. In this regard, datasets from the University Hospital Centre of Coimbra were chosen, and different machine learning (ML)-based and neural network (NN) classifiers have been studied. For this purpose, we have selected favorable features among the nine provided attributes from the clinical dataset by using a random forest algorithm. This dataset consists of both healthy controls and BC patients, and it was noted that glucose, BMI, resistin, and age have the most importance, respectively. Moreover, we have analyzed these features with various ML-based classifier methods, including Decision Tree (DT), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machine (SVM) along with NN-based Multi-Layer Perceptron (MLP) classifier. The results revealed that among different techniques, the SVM and MLP classifiers have the most accuracy, with amounts of 96% and 92%, respectively. These results divulged that the adopted procedure could be used effectively for the classification of cancer cells, and also it encourages further experimental investigations with more collected data for other types of cancers.

Keywords: breast cancer, diagnosis, machine learning, biomarker classification, neural network

Procedia PDF Downloads 115

Authors: Chanjuan Sun, Shijie Hong, Jialing Zhang, Yuchao Guo, Zhijun Zou, Chen Huang

Abstract:

Background: Studies on associations between air temperature and childhood respiratory diseases are lack in China. Objectives: We aim to analyze the relationship between air temperature and childhood respiratory diseases. Methods: We conducted the on-site inspection into 454 residences and questionnaires survey. Indoor air temperature were from field inspection and outdoor air temperature were from website. Multiple logistic regression analyses were used to investigate the associations. Results: Indoor extreme hot air temperature was positively correlated with duration of a common cold (>=2 weeks), and outdoor extreme hot air temperature was also positively related with pneumonia among children. Indoor and outdoor extreme cold air temperature was a risk factor for rhinitis among children. The biggest indoor air temperature difference (indoor maximum air temperature minus indoor minimum air temperature) (Imax minus Imin) (the 4th quartile, >4 oC) and outdoor air temperature difference (outdoor maximum air temperature minus outdoor minimum air temperature) (Omax minus Omin) (the 4th quartile, >8oC) were positively related to pneumonia among children. Meanwhile, indoor air temperature difference (Imax minus Imin) (the 4th quartile, >4 oC) was positively correlated with diagnosed asthma among children. Air temperature difference between indoor and outdoor was negatively related with the most childhood respiratory diseases. This may be partly related to the avoidance behavior. Conclusions: Improper air temperature may affect the respiratory diseases among children.

Keywords: air temperature, extreme air temperature, air temperature difference, respiratory diseases, children

Procedia PDF Downloads 153

Authors: Haifeng Wang, Haili Zhang

Abstract:

Most movie recommendation systems have been developed for customers to find items of interest. This work introduces a predictive model usable by small and medium-sized enterprises (SMEs) who are in need of a data-based and analytical approach to stock proper movies for local audiences and retain more customers. We used classification models to extract features from thousands of customers’ demographic, behavioral and social information to predict their movie genre preference. In the implementation, a Gaussian kernel support vector machine (SVM) classification model and a logistic regression model were established to extract features from sample data and their test error-in-sample were compared. Comparison of error-out-sample was also made under different Vapnik–Chervonenkis (VC) dimensions in the machine learning algorithm to find and prevent overfitting. Gaussian kernel SVM prediction model can correctly predict movie genre preferences in 85% of positive cases. The accuracy of the algorithm increased to 93% with a smaller VC dimension and less overfitting. These findings advance our understanding of how to use machine learning approach to predict customers’ preferences with a small data set and design prediction tools for these enterprises.

Keywords: computational social science, movie preference, machine learning, SVM

Procedia PDF Downloads 244

Authors: Anila Xhahysa, Migena Ceyhan, Neki Kuka, Klajdi Qoshi, Damiano Koxhaj

Abstract:

The seismic event catalog has been updated in the framework of a bilateral project supported by the Central European Investment Fund and with the extensive support of Global Earthquake Model Foundation to update Albania's national seismic hazard model. The earthquake catalogue prepared within this project covers the Western Balkan area limited by 38.0° - 48°N, 12.5° - 24.5°E and includes 41,806 earthquakes that occurred in the region between 510 BC and 2022. Since the moment magnitude characterizes the earthquake size accurately and the selected ground motion prediction equations for the seismic hazard assessment employ this scale, it was chosen as the uniform magnitude scale for the catalogue. Therefore, proxy values of moment magnitude had to be obtained by using new magnitude conversion equations between the local and other magnitude types to this unified scale. The Global Centroid Moment Tensor Catalogue was considered the most authoritative for moderate to large earthquakes for moment magnitude reports; hence it was used as a reference for calibrating other sources. The best fit was observed when compared to some regional agencies, whereas, with reports of moment magnitudes from Italy, Greece and Turkey, differences were observed in all magnitude ranges. For teleseismic magnitudes, to account for the non-linearity of the relationships, we used the exponential model for the derivation of the regression equations. The obtained regressions for the surface wave magnitude and short-period body-wave magnitude show considerable differences with Global Earthquake Model regression curves, especially for low magnitude ranges. Moreover, a conversion relation was obtained between the local magnitude of Albania and the corresponding moment magnitude as reported by the global and regional agencies. As errors were present in both variables, the Deming regression was used.

Keywords: regression, seismic catalogue, local magnitude, tele-seismic magnitude, moment magnitude

Procedia PDF Downloads 57

Authors: Maha Almumaiz, Harry Evdorides

Abstract:

Change in land value typically occurs when a new interurban road construction causes an increase in accessibility; this change in the adjacent lands values differs according to land characteristics such as geographic location, land use type, land area and sale time (appraisal time). A multiple regression model is obtained to predict the percent change in land value (CLV) based on four independent variables namely land distance from the constructed road, area of land, nature of land use and time from the works completion of the road. The random values of percent change in land value were generated using Microsoft Excel with a range of up to 35%. The trend of change in land value with the four independent variables was determined from the literature references. The statistical analysis and model building process has been made by using the IBM SPSS V23 software. The Regression model suggests, for lands that are located within 3 miles as the straight distance from the road, the percent CLV is between (0-35%) which is depending on many factors including distance from the constructed road, land use, land area and time from works completion of the new road.

Keywords: interurban road, land use types, new road construction, percent CLV, regression model

Procedia PDF Downloads 253

Authors: Chaiyaporn Yuksen

Abstract:

Backgroud: Supraventricular tachycardia (SVT) is an abnormally fast atrial tachycardia characterized by narrow (≤ 120 ms) and constant QRS. Adenosine was the drug of choice; the first dose was 6 mg. It can be repeated with the second and third doses of 12 mg, with greater than 90% success. The study found that patients observed at 4 hours after normal sinus rhythm was no recurrence within 24 hours. The objective of this study was to investigate the factors that influence the recurrence of SVT after adenosine in the emergency department (ED). Method: The study was conducted retrospectively exploratory model, prognostic study at the Emergency Department (ED) in Faculty of Medicine, Ramathibodi Hospital, a university-affiliated super tertiary care hospital in Bangkok, Thailand. The study was conducted for ten years period between 2010 and 2020. The inclusion criteria were age > 15 years, visiting the ED with SVT, and treating with adenosine. Those patients were recorded with the recurrence SVT in ED. The multivariable logistic regression model developed the predictive model and prediction score for recurrence PSVT. Result: 264 patients met the study criteria. Of those, 24 patients (10%) had recurrence PSVT. Five independent factors were predictive of recurrence PSVT. There was age>65 years, heart rate (after adenosine) > 100 per min, structural heart disease, and dose of adenosine. The clinical risk score to predict recurrence PSVT is developed accuracy 74.41%. The score of >6 had the likelihood ratio of recurrence PSVT by 5.71 times Conclusion: The clinical predictive score of > 6 was associated with recurrence PSVT in ED.

Keywords: clinical prediction score, SVT, recurrence, emergency department

Procedia PDF Downloads 135

Authors: Suman Bala, Sunil Kamboj, Vipin Saini

Abstract:

Quantitative Structure Activity Relationship (QSAR) analysis has been developed to relate antifungal activity of novel substituted 1,3,4-oxadiazole against Candida albicans and Aspergillus niger using computer assisted multiple regression analysis. The study has shown the better relationship between antifungal activities with respect to various descriptors established by multiple regression analysis. The analysis has shown statistically significant correlation with R² values 0.932 and 0.782 against Candida albicans and Aspergillus niger respectively. These derivatives were further subjected to molecular docking studies to investigate the interactions between the target compounds and amino acid residues present in the active site of glucosamine-6-phosphate synthase. All the synthesized compounds have better docking score as compared to standard fluconazole. Our results could be used for the further design as well as development of optimal and potential antifungal agents.

Keywords: 1, 3, 4-oxadiazole, QSAR, multiple linear regression, docking, glucosamine-6-phosphate synthase

Procedia PDF Downloads 321

Authors: Mayuko Matsuoka

Abstract:

This presentation reports the relationships among EFL(English as a Foreign Language) students’ story comprehension in reading a story written in English and Japanese and empathic reactions. The main focus is put on their self-reflection on past study experiences, one of the empathic reactions after reading a story. One hundred fifty-five first-year university students in Japan read three SRL-themed stories written in English (their foreign language) and those written in Japanese (their mother tongue). The levels of the stories are equivalent, at CEFR(Common European Framework of Reference for Languages) B2 level. The result of categorical correlation analysis shows significant moderate correlations among three empathic reactions in a group reading English versions: having similar emotions as a protagonist, reflecting on their past study experiences, and getting lessons from a story. In addition, the result of logistic regression analysis for the data in a group reading English versions shows the chance of getting lessons from a story significantly approximately doubles if participants’ scores of a comprehension test increases by one, while it approximately triples if participants’ self-reflection occurs. These results do not appear in a group reading Japanese versions. The findings imply that self-reflection may support their comprehension of the English texts and leads to the participants’ getting lessons about SRL.

Keywords: comprehension, lesson, self-reflection, SRL

Procedia PDF Downloads 167

Authors: Minseo Jo

Abstract:

The purpose of this paper is to examine the factors in the hedonic price models, that has significance impact in determining the price of apartments. There are many variables employed in the hedonic price models and their effectiveness vary differently according to the researchers and the regions they are analysing. In order to consider various conditions, the meta-regression analysis has been selected for the study. In this paper, four meta-independent variables, from the 65 hedonic price models to analysis. The factors that influence the prices of apartments, as well as including factors that influence the prices of apartments, regions, which are divided into two of the research performed, years of research performed, the coefficients of the functions employed. The covariance between the four meta-variables and p-value of the coefficients and the four meta-variables and number of data used in the 65 hedonic price models have been analyzed in this study. The six factors that are most important in deciding the prices of apartments are positioning of apartments, the noise of the apartments, points of the compass and views from the apartments, proximity to the public transportations, companies that have constructed the apartments, social environments (such as schools etc.).

Keywords: hedonic price model, housing price, meta-regression analysis, characteristics

Procedia PDF Downloads 382

Authors: J. Milton, C. Uzoigwe, O. Ayeko, B. Offorha, K. Anderson, R. G. Middleton

Abstract:

Background: We used the UK National Hip Fracture database to determine the effect of institution hip fracture case volume on hip fracture healthcare outcomes in 2019. Using logistic regression for each healthcare outcome, we compared the best performing 50 units with the poorest performing 50 units in order to determine if the unit volume was associated with performance for each particular outcome. Method: We analysed 175 institutions treating a total of 67,673 patients over the course of a year. Results: The number of hip fractures seen per unit ranged between 86 and 952. Larger units tendered to perform health assessments more consistently and mobilise patients more expeditiously post-operatively. Patients treated at large institutions had shorter lengths of stay. With regard to most other outcomes, there was no association between unit case volume and performance, notably compliance with the Best Practice Tariff, time to surgery, proportion of eligible patients undergoing total hip arthroplasty, length of stay, delirium risk, and pressure sore risk assessments. Conclusion: There is no relationship between unit volume and the majority of health care outcomes. It would seem that larger institutions tend to perform better at parameters that are dependent upon personnel numbers. However, where the outcome is contingent, even partially, on physical infrastructure capacity, there was no difference between larger and smaller units.

Keywords: institution volume, mortality, neck of femur fractures, osteoporosis

Procedia PDF Downloads 74

Authors: Harinder Singh

Abstract:

The paper sheds light on the perceptions of the uninsured workers employed in the urban informal sector of India, towards the health insurance. In addition to this, it also explores the association of the identified perceptions with household decisions to enroll for health insurance schemes in India. Firstly the data taken from the primary survey of the uninsured workers employed in the urban informal sector was analyzed using exploratory factor analysis to evaluate the perceptions. Thereafter, logistic regression was employed to determine the association of the identified perceptions regarding the enrollment. Our study identifies twelve perceptions related to the health insurance enrollment of the uninsured workers employed in the urban informal sector of India. The study demonstrates that perceptions have the strongest association with the voluntary enrollment. These specifically relate to the lack of awareness about the need to buy health insurance; comprehensive coverage; income constraint; future contingencies and social obligations; lack of information; availability of subsidized government health care; linkage with government hospitals and preference for government schemes. Conclusions: Along with the food security, health security has become a crying need of the workers employed in the informal sector and the time has come to scale up the health insurance schemes for them in the country. Policy makers or marketers of health insurance policies should recognize the household perceptions as a potential barrier and try to develop a health insurance package as per the actual needs of the informal sector (low income) in India.

Keywords: association, enrollment, health insurance, informal sector, perceptions, uninsured

Procedia PDF Downloads 246

Authors: Adam Chlapecka, Anna Kagstrom, Pavla Cermakova

Abstract:

Background: Increasing educational attainment (EA) could decrease the occurrence of depression. We investigated the relationship between EA and depressive symptoms in older individuals across four European regions. Methods: We studied 108 315 Europeans (54 % women, median age 63 years old) from the Survey on Health, Ageing and Retirement in Europe assessing EA (7 educational levels based on ISCED classification); and depressive symptoms (≥ 4 points on EURO-D scale). Logistic regression estimated the association between EA and depressive symptoms, adjusting for sociodemographic and health-related factors; testing for sex/age/region and education interactions. Results: Higher EA was associated with lower odds of depressive symptoms, independent of sociodemographic and health-related factors. A threshold of the lowest odds of depressive symptoms was detected at the first stage of tertiary education (OR 0.60; 95% CI 0.55-0.65; p<0.001; relative to no education). Central and Eastern Europe showed the strongest association (OR for high vs. low education 0.37; 95% CI 0.33-0.40; p<0.001) and Scandinavia the weakest (OR for high vs. low education 0.69; 95% CI 0.60-0.80; p<0.001). The association was strongest amongst younger individuals. There was a sex and education interaction only within Central and Eastern Europe. Conclusion: The level of EA is reflected in later-life depressive symptoms, suggesting that supporting individuals in achieving EA, and considering those with lower EA at increased risk for depression, could lead to the decreased burden of depression across the life course. Further educational support in Central and Eastern Europe may decrease the higher burden of depressive symptoms in women.

Keywords: depression, education, epidemiology, Europe

Procedia PDF Downloads 188

Authors: Bidyadhar Dehury, Sanjay Kumar Mohanty

Abstract:

According to the Right to Education Act of India, education is the fundamental right of all children of age group 6-14 year irrespective of their status. Using the unit level data from India Human Development Survey (IHDS), we tried to understand the inter-relationship between the level of poverty and the academic performance of the children aged 8-11 years. The level of multidimensional poverty is measured using five dimensions and 10 indicators using Alkire-Foster approach. The weighted deprivation score was obtained by giving equal weight to each dimension and indicators within the dimension. The weighted deprivation score varies from 0 to 1 and grouped into four categories as non-poor, vulnerable, multidimensional poor and sever multidimensional poor. The academic performance index was measured using three variables reading skills, math skills and writing skills using PCA. The bivariate and multivariate analysis was used in the analysis. The outcome variable was ordinal. So the predicted probabilities were calculated using the ordinal logistic regression. The predicted probabilities of good academic performance index was 0.202 if the child was sever multidimensional poor, 0.235 if the child was multidimensional poor, 0.264 if the child was vulnerable, and 0.316 if the child was non-poor. Hence, if the level of poverty among the children decreases from sever multidimensional poor to non-poor, the probability of good academic performance increases.

Keywords: multidimensional poverty, academic performance index, reading skills, math skills, writing skills, India

Procedia PDF Downloads 571

Authors: Nada Slimane, Foued Theljani, Faouzi Bouani

Abstract:

The paper addresses the problem of fault diagnosis for systems operating in several modes (normal or faulty) based on states assessment. We use, for this purpose, a methodology consisting of three main processes: 1) sequential data clustering, 2) linear model regression and 3) state filtering. Typically, Kalman Filter (KF) is an algorithm that provides estimation of unknown states using a sequence of I/O measurements. Inevitably, although it is an efficient technique for state estimation, it presents two main weaknesses. First, it merely predicts states without being able to isolate/classify them according to their different operating modes, whether normal or faulty modes. To deal with this dilemma, the KF is endowed with an extra clustering step based fully on sequential version of the k-means algorithm. Second, to provide state estimation, KF requires state space models, which can be unknown. A linear regularized regression is used to identify the required models. To prove its effectiveness, the proposed approach is assessed on a simulated benchmark.

Keywords: clustering, diagnosis, Kalman Filtering, k-means, regularized regression

Procedia PDF Downloads 165