Search results for: logistic regression models

Authors: Mohadeseh Shojaei Shahrokhabadi, Ding-Geng (Din) Chen

Abstract:

Positive continuous outcomes with a substantial number of zero values and incomplete longitudinal follow-up are quite common in medical cost data. To jointly model semi-continuous longitudinal cost data and survival data and to provide marginalized covariate effect estimates, a marginalized two-part joint model (MTJM) has been developed for outcome variables with lognormal distributions. In this paper, we propose MTJM models for outcome variables from a generalized gamma (GG) family of distributions. The GG distribution constitutes a general family that includes approximately all of the most frequently used distributions like the Gamma, Exponential, Weibull, and Log Normal. In the proposed MTJM-GG model, the conditional mean from a conventional two-part model with a three-parameter GG distribution is parameterized to provide the marginal interpretation for regression coefficients. In addition, MTJM-gamma and MTJM-Weibull are developed as special cases of MTJM-GG. To illustrate the applicability of the MTJM-GG, we applied the model to a set of real electronic health record data recently collected in Iran, and we provided SAS code for application. The simulation results showed that when the outcome distribution is unknown or misspecified, which is usually the case in real data sets, the MTJM-GG consistently outperforms other models. The GG family of distribution facilitates estimating a model with improved fit over the MTJM-gamma, standard Weibull, or Log-Normal distributions.

Keywords: marginalized two-part model, zero-inflated, right-skewed, semi-continuous, generalized gamma

Procedia PDF Downloads 176

Authors: Noppawan Piaseu, Surat Komindr

Abstract:

This study aimed to determine factors predicting food insecurity in older Thai women living in crowded urban communities. Through purposive sampling, 315 participants were recruited from community dwelling older women in Bangkok, Thailand. Data collection included interview from questionnaires and anthropometric measurement. Results showed that approximately half of the sample were 60-69 years old (51.1%), married (50.6%), obtained primary education (52.3%), had low family income (51.7%), lived in poor physical environment (49.9%) with normal body mass index (51.0%). Logistic regression analysis revealed that older women who were widowed/divorced/separated (OR = 1.804, 95% CI = 1.052-3.092, p = .032), who reported low family income (OR =.654, 95% CI = .523-.817, p < .001), and who had poor physical environment surrounding home (OR = 2.338, 95% CI = 1.057-5.171, p = .036) were more likely to have food insecurity. Results support that social and environmental factors are major factors predicting food insecurity in older women living in the urban community. Health professionals need to identify and monitor psychosocial, economic and environmental dimensions of food insecurity among them.

Keywords: food insecurity, older women, urban communities, Thailand

Procedia PDF Downloads 406

Authors: Oscar E. Cariceo, Claudia V. Casal

Abstract:

Machine learning offers a set of techniques to promote social work interventions and can lead to support decisions of practitioners in order to predict new behaviors based on data produced by the organizations, services agencies, users, clients or individuals. Machine learning techniques include a set of generalizable algorithms that are data-driven, which means that rules and solutions are derived by examining data, based on the patterns that are present within any data set. In other words, the goal of machine learning is teaching computers through 'examples', by training data to test specifics hypothesis and predict what would be a certain outcome, based on a current scenario and improve that experience. Machine learning can be classified into two general categories depending on the nature of the problem that this technique needs to tackle. First, supervised learning involves a dataset that is already known in terms of their output. Supervising learning problems are categorized, into regression problems, which involve a prediction from quantitative variables, using a continuous function; and classification problems, which seek predict results from discrete qualitative variables. For social work research, machine learning generates predictions as a key element to improving social interventions on complex social issues by providing better inference from data and establishing more precise estimated effects, for example in services that seek to improve their outcomes. This paper exposes the results of a classification algorithm to predict cyberbullying among adolescents. Data were retrieved from the National Polyvictimization Survey conducted by the government of Chile in 2017. A logistic regression model was created to predict if an adolescent would experience cyberbullying based on the interaction and behavior of gender, age, grade, type of school, and self-esteem sentiments. The model can predict with an accuracy of 59.8% if an adolescent will suffer cyberbullying. These results can help to promote programs to avoid cyberbullying at schools and improve evidence based practice.

Keywords: cyberbullying, evidence based practice, machine learning, social work research

Procedia PDF Downloads 168

Authors: M. Bodner, M. Scampicchio

Abstract:

Fourier Transform Infrared (FT-IR) spectroscopy coupled with chemometrics was used to distinguish between butter samples and non-butter samples. Further, quantification of the content of margarine in adulterated butter samples was investigated. Fingerprinting region (1400-800 cm^–1) was used to develop unsupervised pattern recognition (Principal Component Analysis, PCA), supervised modeling (Soft Independent Modelling by Class Analogy, SIMCA), classification (Partial Least Squares Discriminant Analysis, PLS-DA) and regression (Partial Least Squares Regression, PLS-R) models. PCA of the fingerprinting region shows a clustering of the two sample types. All samples were classified in their rightful class by SIMCA approach; however, nine adulterated samples (between 1% and 30% w/w of margarine) were classified as belonging both at the butter class and at the non-butter one. In the two-class PLS-DA model’s (R² = 0.73, RMSEP, Root Mean Square Error of Prediction = 0.26% w/w) sensitivity was 71.4% and Positive Predictive Value (PPV) 100%. Its threshold was calculated at 7% w/w of margarine in adulterated butter samples. Finally, PLS-R model (R² = 0.84, RMSEP = 16.54%) was developed. PLS-DA was a suitable classification tool and PLS-R a proper quantification approach. Results demonstrate that FT-IR spectroscopy combined with PLS-R can be used as a rapid, simple and safe method to identify pure butter samples from adulterated ones and to determine the grade of adulteration of margarine in butter samples.

Keywords: adulterated butter, margarine, PCA, PLS-DA, PLS-R, SIMCA

Procedia PDF Downloads 143

Authors: Vishal Das, Tianyi Mao, Zhicheng Geng, Carmen Flores, Diego Pelloso, Fang Wang

Abstract:

Accurate sell-in and sell-out forecasting is a ubiquitous problem in the retail industry. It is an important element of any demand planning activity. As a global food and beverage company, Nestlé has hundreds of products in each geographical location that they operate in. Each product has its sell-in and sell-out time series data, which are forecasted on a weekly and monthly scale for demand and financial planning. To address this challenge, Nestlé Chilein collaboration with Amazon Machine Learning Solutions Labhas developed their in-house solution of using machine learning models for forecasting. Similar products are combined together such that there is one model for each product category. In this way, the models learn from a larger set of data, and there are fewer models to maintain. The solution is scalable to all product categories and is developed to be flexible enough to include any new product or eliminate any existing product in a product category based on requirements. We show how we can use the machine learning development environment on Amazon Web Services (AWS) to explore a set of forecasting models and create business intelligence dashboards that can be used with the existing demand planning tools in Nestlé. We explored recent deep learning networks (DNN), which show promising results for a variety of time series forecasting problems. Specifically, we used a DeepAR autoregressive model that can group similar time series together and provide robust predictions. To further enhance the accuracy of the predictions and include domain-specific knowledge, we designed an ensemble approach using DeepAR and XGBoost regression model. As part of the ensemble approach, we interlinked the sell-out and sell-in information to ensure that a future sell-out influences the current sell-in predictions. Our approach outperforms the benchmark statistical models by more than 50%. The machine learning (ML) pipeline implemented in the cloud is currently being extended for other product categories and is getting adopted by other geomarkets.

Keywords: sell-in and sell-out forecasting, demand planning, DeepAR, retail, ensemble machine learning, time-series

Procedia PDF Downloads 273

Authors: Davod Ahmadi, Narges Ebadi, Ethan Wang, Hugo Melgar-Quiñonez

Abstract:

Compared to the other Least Developed Countries (LDCs), major countries in sub-Saharan Africa (SSA) have limited access to the clean water. People in this region, and more specifically females, suffer from acute water scarcity problems. They are compelled to spend too much of their time bringing water for domestic use like drinking and washing. Apart from domestic use, water through affecting agriculture and livestock contributes to the food security status of people in vulnerable regions like SSA. Livestock needs water to grow, and agriculture requires enormous quantities of water for irrigation. The main objective of this study is to explore the association between access to water and individuals’ food security status. Data from 2017 Gallup World Poll (GWP) for SSA were analyzed (n=35,000). The target population in GWP is the entire civilian, non-institutionalized, aged 15 and older population. All samples selection is probability based and nationally representative. The Gallup surveys an average of 1,000 samples of individuals per country. Three questions related to water (i.e., water quality, availability of water for crops and availability of water for livestock) were used as the exposure variables. Food Insecurity Experience Scale (FIES) was used as the outcome variable. FIES measures individuals’ food security status, and it is composed of eight questions with simple dichotomous responses (1=Yes and 0=No). Different statistical analyses such as descriptive, crosstabs and binary logistic regression, form the basis of this study. Results from descriptive analyses showed that more than 50% of the respondents had no access to enough water for crops and livestock. More than 85% of respondents were categorized as “food insecure”. Findings from cross-tabulation analyses showed that food security status was significantly associated with water quality (0.135; P=0.000), water for crops (0.106; P=0.000) and water for livestock (0.112; P=0.000). In regression analyses, the probability of being food insecure increased among people who expressed no satisfaction with water quality (OR=1.884 (OR=1.768-2.008)), not enough water for crops (OR=1.721 (1.616-1.834)) and not enough water for livestock (OR=1.706 (1.819)). In conclusion, it should note that water access affects food security status in SSA.

Keywords: water access, agriculture, livestock, FIES

Procedia PDF Downloads 150

Authors: Mikiyas Adugna

Abstract:

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

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

Procedia PDF Downloads 71

Authors: Ebru Turgal, Beyza Doganay Erdogan

Abstract:

Machine learning aims to model the relationship between the response and features. Medical decision-making researchers would like to make decisions about patients’ course and treatment, by examining the repeated measurements over time. Boosting approach is now being used in machine learning area for these aims as an influential tool. The aim of this study is to show the usage of multivariate tree boosting in this field. The main reason for utilizing this approach in the field of decision-making is the ease solutions of complex relationships. To show how multivariate tree boosting method can be used to identify important features and feature-time interaction, we used the data, which was collected retrospectively from Ankara University Chest Diseases Department records. Dataset includes repeated PF ratio measurements. The follow-up time is planned for 120 hours. A set of different models is tested. In conclusion, main idea of classification with weighed combination of classifiers is a reliable method which was shown with simulations several times. Furthermore, time varying variables will be taken into consideration within this concept and it could be possible to make accurate decisions about regression and survival problems.

Keywords: boosted multivariate trees, longitudinal data, multivariate regression tree, panel data

Procedia PDF Downloads 203

Authors: Gustavo G. Shimamoto, Matthieu Tubino

Abstract:

The characterization and the quality of biodiesel samples are checked by determining several parameters. Considering a large number of analysis to be performed, as well as the disadvantages of the use of toxic solvents and waste generation, multivariate calibration is suggested to reduce the number of tests. In this work, hydrogen nuclear magnetic resonance (1H NMR) spectra were used to build multivariate models, from partial least squares (PLS) regression, in order to determine simultaneously six important characterizing and/or quality parameters of biodiesels: density at 20 ºC, kinematic viscosity at 40 ºC, iodine value, acid number, oxidative stability, and water content. Biodiesels from twelve different oils sources were used in this study: babassu, brown flaxseed, canola, corn, cottonseed, macauba almond, microalgae, palm kernel, residual frying, sesame, soybean, and sunflower. 1H NMR reflects the structures of the compounds present in biodiesel samples and showed suitable correlations with the six parameters. The PLS models were constructed with latent variables between 5 and 7, the obtained values of r(cal) and r(val) were greater than 0.994 and 0.989, respectively. In addition, the models were considered suitable to predict all the six parameters for external samples, taking into account the analytical speed to perform it. Thus, the alliance between 1H NMR and PLS showed to be appropriate to characterize and evaluate the quality of biodiesels, reducing significantly analysis time, the consumption of reagents/solvents, and waste generation. Therefore, the proposed methods can be considered to adhere to the principles of green chemistry.

Keywords: biodiesel, multivariate calibration, nuclear magnetic resonance, quality parameters

Procedia PDF Downloads 539

Authors: Elizabeth Behrens, Anne Timmermann, Alexander Yerkan, Joshua Thomas, Deborah Katz, Agne Paner, Melissa Larson, Shivi Jain, Seo-Hyun Kim, Celalettin Ustun, Ankur Varma, Parameswaran Venugopal, Jamile Shammo

Abstract:

Coronavirus Disease-2019 (COVID-19) causes persistent concern for poor outcomes in vulnerable populations. Patients with hematologic malignancies (HM) have been found to have higher COVID-19 case fatality rates compared to those without malignancy. While cytopenias are common in patients with HM, especially in those undergoing chemotherapy treatment, hemoglobin (Hgb) and platelet count have not yet been studied, to our best knowledge, as potential prognostic indicators for patients with HM and COVID-19. The goal of this study is to identify factors that may increase the risk of mortality in patients with HM and COVID-19. In this single-center, retrospective, observational study, 65 patients with HM and laboratory confirmed COVID-19 were identified between March 2020 and January 2021. Information on demographics, laboratory data the day of COVID-19 diagnosis, and prognosis was extracted from the electronic medical record (EMR), chart reviewed, and analyzed using the statistical software SAS version 9.4. Chi-square testing was used for categorical variable analyses. Risk factors associated with mortality were established by logistic regression models. Non-Hodgkin lymphoma (37%), chronic lymphocytic leukemia (20%), and plasma cell dyscrasia (15%) were the most common HM. Higher Hgb level upon COVID-19 diagnosis was related to decreased mortality, odd ratio=0.704 (95% confidence interval [CI]: 0.511-0.969; P = .0263). Platelet count the day of COVID-19 diagnosis was lower in patients who ultimately died (mean 127 ± 72K/uL, n=10) compared to patients who survived (mean 197 ±92K/uL, n=55) (P=.0258). Female sex was related to decreased mortality, odd ratio=0.143 (95% confidence interval [CI]: 0.026-0.785; P = .0353). There was no mortality difference between the patients who were on treatment for HM the day of COVID-19 diagnosis compared to those who were not (P=1.000). Lower Hgb and male sex are independent risk factors associated with increased mortality of HM patients with COVID-19. Clinicians should be especially attentive to patients with HM and COVID-19 who present with cytopenias. Larger multi-center studies are urgently needed to further investigate the impact of anemia, thrombocytopenia, and demographics on outcomes of patients with hematologic malignancies diagnosed with COVID-19.

Keywords: anemia, COVID-19, hematologic malignancy, prognosis

Procedia PDF Downloads 149

Authors: Shivam Kushwaha, Veena Bansal

Abstract:

Timeshare refers to real estate that is owned simultaneously by many, for a specified time in a year, for a specified numbers of years and is maintained and managed by an agency. Timeshare falls under the umbrella of tourism and is often used for vacation. Timeshare industry has attracted significantly less number of customers in India as compared to the US and Europe. In more than 40 years of existence of timeshare industry, it has not been able to grow its roots among Indian customers. The purpose of the study: To explore perception of Indian customers towards the adoption of timeshare segment of the hospitality industry and identify the factors. Source of data: Survey has been done on existing owners of holidays memberships, resorts or those who at least tourism experience in their past purchases. Methodology: Logistic Regression is used to predict binary responses of the customers based on identified critical factors which might influence timeshare purchases. Result: The study identified four factors: discretionary income, exchange options, ownership pride, risk, and measured their influence on intention to purchases in India. It is recognized that is all four variables are statistically significant while explaining in purchase intentions of customers in India.

Keywords: timeshare, holiday, tourism, customer perception, intent to use, Indian tourism

Procedia PDF Downloads 297

Authors: Haftay Abraha Tadesse, Dawit Gebreegziabiher Hagos, Atsebaha Gebrekidan Kahsay, Mahumd Abdulkader

Abstract:

Background: Salmonella species and Escherichia coli (E. coli) are important foodborne pathogens affecting humans and animals. They are among the most important causes of infection that are associated with the consumption of contaminated food. This study was aimed to determine the prevalence, antimicrobial susceptibility patterns and associated risk factors for Salmonella species and E. coli in raw meat from butchery houses of Mekelle, Northern Ethiopia. Method: A cross-sectional study was conducted from January to December 2019. Socio-demographic data and risk factors were collected using a predesigned questionnaire. Meat samples were collected aseptically from the butchery houses and transported using icebox to Mekelle University, College of Veterinary Sciences for the isolation and identification of Salmonella species and E. coli. Antimicrobial susceptibility patterns were determined using Kirby disc diffusion method. Data obtained were cleaned and entered into Statistical Package for the Social Sciences version 22 and logistic regression models with odds ratio were calculated. P-value < 0.05 was considered as statistically significant. Results: A total of 153 out of 384 (39.8%) of the meat specimens were found to be contaminated. The contamination of Salmonella species and E. coli were 15.6% (n=60) and 20.8%) (n=80), respectively. Mixed contamination (Salmonella species and E. coli) was observed in 13 (3.4 %) of the analyzed. Poor washing hands regularly (AOR = 8.37; 95% CI: 2.75-25.50) and not using gloves during meat handling (AOR=11. 28; 95% CI:(4.69 27.10) were associated with overall bacterial contamination. About 100% of the tested isolates were sensitive to ciprofloxacin, gentamicin, Co trimoxazole , sulphamethoxazole, ceftriaxone, and trimethoprim and ciprofloxacin, gentamicin, and norfloxacine of E. coli and Salmonella species, respectively, while the resistance of amoxyclav_amoxicillin and erythromycin were both isolated bacteria species. The overall multidrug resistance pattern for Salmonella and E. coli were 51.4% (n=19) and 31.8% (14), respectively. Conclusion: Of the 153 (153/384) contaminated raw meat, 60 (15.6%) and 80 (20.8%) were contaminated by Salmonella species and E. coli, respectively. Poor handwashing practice and not using glove during meat handling showed a significant association with bacterial contamination. Multidrug-resistant showed in Salmonella species, and E. coli were 19 (51.4%) and 14 (31.8%), respectively.

Keywords: antimicrobial susceptibility test, butchery houses, E. coli, raw meat, salmonella species

Procedia PDF Downloads 173

Authors: Aaditya U. Jhamb

Abstract:

Due to the current energy crisis that many countries are battling, energy-efficient buildings are the subject of extensive research in the modern technological era because of growing worries about energy consumption and its effects on the environment. The paper explores 8 factors that help determine energy efficiency for a building: (relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, and glazing area distribution), with Tsanas and Xifara providing a dataset. The data set employed 768 different residential building models to anticipate heating and cooling loads with a low mean squared error. By optimizing these characteristics, machine learning algorithms may assess and properly forecast a building's heating and cooling loads, lowering energy usage while increasing the quality of people's lives. As a result, the paper studied the magnitude of the correlation between these input factors and the two output variables using various statistical methods of analysis after determining which input variable was most closely associated with the output loads. The most conclusive model was the Decision Tree Regressor, which had a mean squared error of 0.258, whilst the least definitive model was the Isotonic Regressor, which had a mean squared error of 21.68. This paper also investigated the KNN Regressor and the Linear Regression, which had to mean squared errors of 3.349 and 18.141, respectively. In conclusion, the model, given the 8 input variables, was able to predict the heating and cooling loads of a residential building accurately and precisely.

Keywords: energy efficient buildings, heating load, cooling load, machine learning models

Procedia PDF Downloads 95

Authors: Wajiha Javed, Arsalan Jabbar, Nelofer Mehboob, Muhammad Tafseer, Zahid Memon

Abstract:

Introduction: Researchers globally have strived to explore diverse factors that augment the continuation and uptake of family planning methods. Clients’ satisfaction is one of the core determinants facilitating continuation of family planning methods. There is a major debate yet scanty evidence to contrast public and private sectors with respect to client satisfaction. The objective of this study is to compare quality-of-care provided by public and private sectors of Pakistan through a client satisfaction lens. Methods: We used Pakistan Demographic Heath Survey 2012-13 dataset (Sindh province) on a total of 3133 Married Women of Reproductive Age (MWRA) aged 15-49 years. Source of family planning (public/private sector) was the main exposure variable. Outcome variable was client satisfaction judged by ten different dimensions of client satisfaction. Means and standard deviations were calculated for continuous variable while for categorical variable frequencies and percentages were computed. For univariate analysis, Chi-square/Fisher Exact test was used to find an association between clients’ satisfaction in public and private sectors. Ten different multivariate models were made. Variables were checked for multi-collinearity, confounding, and interaction, and then advanced logistic regression was used to explore the relationship between client satisfaction and dependent outcome after adjusting for all known confounding factors and results are presented as OR and AOR (95% CI). Results: Multivariate analyses showed that clients were less satisfied in contraceptive provision from private sector as compared to public sector (AOR 0.92,95% CI 0.63-1.68) even though the result was not statistically significant. Clients were more satisfied from private sector as compared to the public sector with respect to other determinants of quality-of-care (follow-up care (AOR 3.29, 95% CI 1.95-5.55), infection prevention (AOR 2.41, 95% CI 1.60-3.62), counseling services (AOR 2.01, 95% CI 1.27-3.18, timely treatment (AOR 3.37, 95% CI 2.20-5.15), attitude of staff (AOR 2.23, 95% CI 1.50-3.33), punctuality of staff (AOR 2.28, 95% CI 1.92-4.13), timely referring (AOR 2.34, 95% CI 1.63-3.35), staff cooperation (AOR 1.75, 95% CI 1.22-2.51) and complications handling (AOR 2.27, 95% CI 1.56-3.29).

Keywords: client satisfaction, family planning, public private partnership, quality of care

Procedia PDF Downloads 419

Authors: Alfonso Ippolito, Cristiana Bartolomei

Abstract:

A growing demand is felt today for realistic 3D models enabling the cognition and popularization of historical-artistic heritage. Evaluation and preservation of Cultural Heritage is inextricably connected with the innovative processes of gaining, managing, and using knowledge. The development and perfecting of techniques for acquiring and elaborating photorealistic 3D models, made them pivotal elements for popularizing information of objects on the scale of architectonic structures.

Keywords: cultural heritage, databases, non-contact survey, 2D-3D models

Procedia PDF Downloads 423

Authors: Ting Lu, Ya-Ru Diao, Fei Fan, Ye Xue, Lei Shi, Xian-e Tang, Meng-jun Zhan, Zhen-hua Deng

Abstract:

Accurate adult age estimation (AAE) is a significant and challenging task in forensic and archeology fields. Attempts have been made to explore optimal adult age metrics, and the rib is considered a potential age marker. The traditional way is to extract age-related features designed by experts from macroscopic or radiological images followed by classification or regression analysis. Those results still have not met the high-level requirements for practice, and the limitation of using feature design and manual extraction methods is loss of information since the features are likely not designed explicitly for extracting information relevant to age. Deep learning (DL) has recently garnered much interest in imaging learning and computer vision. It enables learning features that are important without a prior bias or hypothesis and could be supportive of AAE. This study aimed to develop DL models for AAE based on CT images and compare their performance to the manual visual scoring method. Chest CT data were reconstructed using volume rendering (VR). Retrospective data of 2500 patients aged 20.00-69.99 years were obtained between December 2019 and September 2021. Five-fold cross-validation was performed, and datasets were randomly split into training and validation sets in a 4:1 ratio for each fold. Before feeding the inputs into networks, all images were augmented with random rotation and vertical flip, normalized, and resized to 224×224 pixels. ResNeXt was chosen as the DL baseline due to its advantages of higher efficiency and accuracy in image classification. Mean absolute error (MAE) was the primary parameter. Independent data from 100 patients acquired between March and April 2022 were used as a test set. The manual method completely followed the prior study, which reported the lowest MAEs (5.31 in males and 6.72 in females) among similar studies. CT data and VR images were used. The radiation density of the first costal cartilage was recorded using CT data on the workstation. The osseous and calcified projections of the 1 to 7 costal cartilages were scored based on VR images using an eight-stage staging technique. According to the results of the prior study, the optimal models were the decision tree regression model in males and the stepwise multiple linear regression equation in females. Predicted ages of the test set were calculated separately using different models by sex. A total of 2600 patients (training and validation sets, mean age=45.19 years±14.20 [SD]; test set, mean age=46.57±9.66) were evaluated in this study. Of ResNeXt model training, MAEs were obtained with 3.95 in males and 3.65 in females. Based on the test set, DL achieved MAEs of 4.05 in males and 4.54 in females, which were far better than the MAEs of 8.90 and 6.42 respectively, for the manual method. Those results showed that the DL of the ResNeXt model outperformed the manual method in AAE based on CT reconstruction of the costal cartilage and the developed system may be a supportive tool for AAE.

Keywords: forensic anthropology, age determination by the skeleton, costal cartilage, CT, deep learning

Procedia PDF Downloads 73

Authors: Rebecca S. Hock, Cyralene P. Bryce, Kevin Williams, Arielle G. Rabinowitz, Janina R. Galler

Abstract:

Background: Findings have been mixed regarding whether offspring of parents who were abused or neglected as children have a greater risk of experiencing abuse or neglect themselves. In addition, many studies on this topic are restricted to physical abuse and take place in a limited number of countries, representing a small segment of the world's population. Methods: We examined relationships between childhood maltreatment history assessed in a subset (N=68) of the original longitudinal birth cohort (G1) of the Barbados Nutrition Study and their now-adult offspring (G2) (N=111) using the Childhood Trauma Questionnaire-Short Form (CTQ-SF). We used Pearson correlations to assess relationships between parent and offspring CTQ-SF total and subscale scores (physical, emotional, and sexual abuse; physical and emotional neglect). Next, we ran multiple regression analyses, using the parental CTQ-SF total score and the parental Sexual Abuse score as primary predictors separately in our models of G2 CTQ-SF (total and subscale scores). Results: G1 total CTQ-SF scores were correlated with G2 offspring Emotional Neglect and total scores. G1 Sexual Abuse history was significantly correlated with G2 Emotional Abuse, Sexual Abuse, Emotional Neglect, and Total Score. In fully-adjusted regression models, parental (G1) total CTQ-SF scores remained significantly associated with G2 offspring reports of Emotional Neglect, and parental (G1) Sexual Abuse was associated with offspring (G2) reports of Emotional Abuse, Physical Abuse, Emotional Neglect, and overall CTQ-SF scores. Conclusions: Our findings support a link between parental exposure to childhood maltreatment and their offspring's self-reported exposure to childhood maltreatment. Of note, there was not an exact correspondence between the subcategory of maltreatment experienced from one generation to the next. Compared with other subcategories, G1 Sexual Abuse history was the most likely to predict G2 offspring maltreatment. Further studies are needed to delineate underlying mechanisms and to develop intervention strategies aimed at preventing intergenerational transmission.

Keywords: trauma, family, adolescents, intergenerational trauma, child abuse, child neglect, global mental health, North America

Procedia PDF Downloads 84

Authors: Hassan Barau Singhry

Abstract:

Purpose: Leadership or the absence of it is an important behaviour affecting employees’ job satisfaction. Although, there are many models of leadership, one that stands out in a period of change is the transformational behaviour. The aim of this study is to investigate the role of an organizational justice on the relationship between transformational leadership and employee job satisfaction. The study is based on the assumption that change begins with leaders and leaders should be fair and just. Methodology: A cross-sectional survey through structured questionnaire was employed to collect the data of this study. The population is selected the three tiers of government such as the local, state, and federal governments in Nigeria. The sampling method used in this research is stratified random sampling. 418 middle managers of public organizations respondents to the questionnaire. Multiple regression aided by structural equation modeling was employed to test 4 hypothesized relationships. Finding: The regression results support for the mediating role of organizational justice such as distributive, procedural, interpersonal and informational justice in the link between transformational leadership and job satisfaction. Originality/value: This study adds to the literature of human resource management by empirically validating and integrating transformational leadership behaviour with the four dimensions of organizational justice theory. The study is expected to be beneficial to the top and middle-level administrators as well as theory building and testing.

Keywords: distributive justice, job satisfaction, organizational justice, procedural justice, transformational leadership

Procedia PDF Downloads 174

Authors: Sheldon Liu, Gordon Wang, Lei Liu, Xuefeng Liu

Abstract:

Anomaly detection, also referred to as one-class classification, plays a crucial role in identifying product images that deviate from the expected distribution. This study introduces Data-centric Anomaly Detection with Diffusion Models (DCADDM), presenting a systematic strategy for data collection and further diversifying the data with image generation via diffusion models. The algorithm addresses data collection challenges in real-world scenarios and points toward data augmentation with the integration of generative AI capabilities. The paper explores the generation of normal images using diffusion models. The experiments demonstrate that with 30% of the original normal image size, modeling in an unsupervised setting with state-of-the-art approaches can achieve equivalent performances. With the addition of generated images via diffusion models (10% equivalence of the original dataset size), the proposed algorithm achieves better or equivalent anomaly localization performance.

Keywords: diffusion models, anomaly detection, data-centric, generative AI

Procedia PDF Downloads 82

Authors: Septiany Trisnaningtyas

Abstract:

Purpose: This research aims to examine the factors affecting the profitability of pharmaceutical company during the Covid-19 Pandemic in Indonesia. A sharp decline in the number of patients coming to the hospital for treatment during the pandemic has an impact on the growth of the pharmaceutical sector and brought major changes in financial position and business performance. Pharmaceutical companies that provide products related to the Covid-19 pandemic can survive and continue to grow. This study investigates the factors affecting the profitability of pharmaceutical company during the Covid-19 Pandemic in Indonesia associated with the number of Covid-19 cases. Design/methodology/approach: This study uses panel-data regression models to evaluate the influence of the number of Covid-19 confirmed cases on profitability of ninelisted pharmaceuticalcompanies in Indonesia. This research is based on four independent variables that were empirically examined for their relationship with profitability. These variables are liquidity (current ratio), growth rate (sales growth), firm size (total sales), and market power (the Lerner index). Covid-19 case is used as moderating variable. Data of nine pharmaceutical companies listed on the Indonesia Stock Exchange covering the period of 2018–2021 were extracted from companies’ quarterly annual reports. Findings: In the period during Covid-19, company growth (sales growth) and market power (lerner index) have a positive and significant relationship to ROA and ROE. Total of confirmed Covid-19 cases has a positive and significant relationship to ROA and is proven to have a moderating effect between company’s growth (sales growth) to ROA and ROE and market power (Lerner index) to ROA. Research limitations/implications: Due to data availability, this study only includes data from nine listed pharmaceutical companies in Indonesian Stock exchange and quarterly annual reportscovering the period of 2018-2021. Originality/value: This study focuses onpharmaceutical companies in Indonesia during Covid-19 pandemic. Previous study analyzes the data from pharmaceutical companies’ annual reports since 2014 and focus on universal health coverage (national health insurance) implementation from the Indonesian government. This study analyzes the data using fixed effect panel-data regression models to evaluate the influence of Covid-19 confirmed cases on profitability. Pooled ordinary least squares regression and fixed effects were used to analyze the data in previous study. This study also investigate the moderating effect of Covid-19 confirmed cases to profitability in relevant with the pandemic situation.

Keywords: profitability, indonesia, pharmaceutical, Covid-19

Procedia PDF Downloads 123

Authors: Rene Valdiviezo-Issa

Abstract:

In this paper, we use Mexico’s Households Income and Expenditures (ENIGH) survey to explain the behaviour that the urban-rural expenditure gap has had since Mexico’s incorporation to the North American Free Trade Agreement (NAFTA) in 1994 and we compare it with the latest available survey, which took place in 2014. We use real trimestral expenditure per capita (RTEPC) as the measure of welfare. We use quantile regressions and a quantile regression decomposition to describe the gap between urban and rural distributions of log RTEPC. We discover that the decrease in the difference between the urban and rural distributions of log RTEPC, or inequality, is motivated because of a deprivation of the urban areas, in very specific characteristics, rather than an improvement of the urban areas. When using the decomposition we observe that the gap is primarily brought about because differences in returns to covariates between the urban and rural areas.

Keywords: quantile regression, urban-rural inequality, inequality in Mexico, income decompositon

Procedia PDF Downloads 282

Authors: Li Wang, Dan Shu, Shiguang Pang, Lixiu Wang, Bing Xiang Yang, Qian Liu

Abstract:

Background: Cancer is one of the most severe diseases in childhood; long-term treatment and its side effects significantly impact the patient's physical, psychological, social functioning and quality of life while also placing substantial physical and psychological burdens on caregivers and families. Family resilience is crucial for children with cancer, helping them cope better with the disease and supporting the family in facing challenges together. As a family-level variable, family resilience requires information from multiple family members. However, to our best knowledge, there is currently no research investigating family resilience from both the perspectives of pediatric cancer patients and their caregivers. Therefore, this study aims to investigate the family resilience and quality of life of pediatric cancer patients from a patient–caregiver dyadic perspective. Methods: A total of 149 dyads of patients diagnosed with pediatric cancer patients and their principal caregivers were recruited from oncology departments of 4 tertiary hospitals in Wuhan and Taiyuan, China. All participants completed questionnaires that identified their demographic and clinical characteristics as well as assessed their family resilience and quality of life for both the patients and their caregivers. K-means cluster analysis was used to identify different clusters of family resilience based on the reports from patients and caregivers. Multivariate logistic regression and linear regression are used to analyze the factors influencing family resilience and quality of life, as well as the relationship between the two. Results: Three clusters of family resilience were identified: a cluster of high family resilience (HR), a cluster of low family resilience (LR), and a cluster of discrepant family resilience (DR). Most (67.1%) families fell into the cluster with low resilience. Characteristics such as the types of caregivers perceived social support of the patient were different among the three clusters. Compared to the LR group, families where the mother is the caregiver and where the patient has high social support are more likely to be assigned to the HR. The quality of life for caregivers was consistently highest in the HR cluster and lowest in the LR cluster. The patient's quality of life is not related to family resilience. In the linear regression analysis of the patient's quality of life, patients who are the first-born have higher quality of life, while those living with their parents have lower quality of life. The participants' characteristics were not associated with the quality of life for caregivers. Conclusions: In most families, family resilience was low. Families with maternal caregivers and patients receiving high levels of social support are more inclined to be higher levels of family resilience. Family resilience was linked to the quality of life of caregivers of pediatric cancer patients. The clinical implications of this findings suggest that healthcare and social support organizations should prioritize and support the participation of mothers in caregiving responsibilities. Furthermore, they should assist families in accessing social support to enhance family resilience. This study also emphasizes the importance of promoting family resilience for enhancing family health and happiness, as well as improving the quality of life for caregivers.

Keywords: pediatric cancer, cluster analysis, family resilience, quality of life

Procedia PDF Downloads 37

Authors: Giriraj Achari, Malay Bhattacharyya

Abstract:

In this paper, the effectiveness of Copula Markov Switching Multifractal (MSM) models at forecasting Value-at-Risk of a two-stock portfolio is studied. The innovations are allowed to be drawn from distributions that can capture skewness and leptokurtosis, which are well documented empirical characteristics observed in financial returns. The candidate distributions considered for this purpose are Johnson-SU, Pearson Type-IV and α-Stable distributions. The two univariate marginal distributions are combined using the Student-t copula. The estimation of all parameters is performed by Maximum Likelihood Estimation. Finally, the models are compared in terms of accurate Value-at-Risk (VaR) forecasts using tests of unconditional coverage and independence. It is found that Copula-MSM-models with leptokurtic innovation distributions perform slightly better than Copula-MSM model with Normal innovations. Copula-MSM models, in general, produce better VaR forecasts as compared to traditional methods like Historical Simulation method, Variance-Covariance approach and Copula-Generalized Autoregressive Conditional Heteroscedasticity (Copula-GARCH) models.

Keywords: Copula, Markov Switching, multifractal, value-at-risk

Procedia PDF Downloads 164

Authors: Elina Bakhtieva

Abstract:

The variety of available digital tools, strategies and activities might confuse and disorient even an experienced marketer. This applies in particular to B2B companies, which are usually less flexible in uptaking of digital technology than B2C companies. B2B companies are lacking a framework that corresponds to the specifics of the B2B business, and which helps to evaluate a company’s capabilities and to choose an appropriate path. A B2B digital marketing maturity model helps to fill this gap. However, modern marketing offers no widely approved digital marketing maturity model, and thus, some marketing institutions provide their own tools. The purpose of this paper is building an optimized B2B digital marketing maturity model based on a SWOT (strengths, weaknesses, opportunities, and threats) analysis of existing models. The current study provides an analytical review of the existing digital marketing maturity models with open access. The results of the research are twofold. First, the provided SWOT analysis outlines the main advantages and disadvantages of existing models. Secondly, the strengths of existing digital marketing maturity models, helps to identify the main characteristics and the structure of an optimized B2B digital marketing maturity model. The research findings indicate that only one out of three analyzed models could be used as a separate tool. This study is among the first examining the use of maturity models in digital marketing. It helps businesses to choose between the existing digital marketing models, the most effective one. Moreover, it creates a base for future research on digital marketing maturity models. This study contributes to the emerging B2B digital marketing literature by providing a SWOT analysis of the existing digital marketing maturity models and suggesting a structure and main characteristics of an optimized B2B digital marketing maturity model.

Keywords: B2B digital marketing strategy, digital marketing, digital marketing maturity model, SWOT analysis

Procedia PDF Downloads 344

Authors: Farzad Jalilian, Mehdi Mirzaei Alavijeh, Fazel Zinat Motlagh

Abstract:

Social support is an important benchmark of health for people in avoidance conditions. The main goal of this study was to determine the three kinds of social support (family, friend and other significant) to drug cessation among male addicts, in Kermanshah, the west of Iran. This cross-sectional study was conducted among 132 addicts, randomly selected to participate voluntarily in the study. Data were collected from conduct interviews based on standard questionnaire and analyzed by using SPSS-18 at 95% significance level. The majority of addicts were young (Mean: 30.4 years), and with little education. Opium (36.4%), Crack (21.2%), and Methamphetamine (12.9%) were the predominant drugs. Inabilities to reject the offer and having addict friends are the most often reasons for drug usage. Almost, 18.9% reported history of drug injection. 43.2% of the participants already did drug cessation at least once. Logistic regression showed the family support (OR = 1.110), age (OR = 1.106) and drug use initiation age (OR = 0.918) was predicting drug cessation. Our result showed; family support is a more important effect among types of social support in drug cessation. It seems that providing educational program to addict’s families for more support of patients at drug cessation can be beneficial.

Keywords: drug cessation, family support, drug use, initiation age

Procedia PDF Downloads 550

Authors: Majdi M. Alomari, Nafesah I. Alshdaifat, Mohammad S. Widyan

Abstract:

Different countries have introduced different schemes and policies to counter global warming. The rationale behind the proposed policies and the potential barriers to successful implementation of the policies adopted by the countries were analyzed and estimated based on different models. It is argued that these models enhance the transparency and provide a better understanding to the policy makers. However, these models are underpinned with several structural and baseline assumptions. These assumptions, modeling features and future prediction of emission reductions and other implication such as cost and benefits of a transition to a low-carbon economy and its economy wide impacts were discussed. On the other hand, there are potential barriers in the form political, financial, and cultural and many others that pose a threat to the mitigation options.

Keywords: energy models, environmental policy instruments, mitigating CO2 emission, economic wide impact

Procedia PDF Downloads 524

Authors: Yuri Teraoka, Cheerawit Rattanapan, Aroonsri Mongkolchati

Abstract:

This cross sectional analytic study was carried out to determine factors related to protective behavior on indoor pollution among pregnant women in Nakhon Pathom province, Thailand. A total of 319 pregnant women were enrolled at three antenatal care clinics in community hospital. Data were collected using simple random sampling from April 2015 to May 2015 using a structured self-administration questionnaire by well-trained research assistants. The result showed that around 73% pregnant women showed low level of low protective behavior on indoor pollution. Chi-square and multiple logistic regression were used to examine the factors and protective behavior on indoor pollution. After adjusting for confounding factors, this study found that tobacco smoking before pregnancy (AOR=2.15, 95% CI: 0.78-5.95) and low environmental health hazard (AOR=1.94, 95% CI: 1.09-3.49) were significant factors related to protective behavior on indoor pollution among pregnant women (p-value < 0.05). In conclusion, this study suggested that environmental health education campaign and environmental implementation program among pregnant woman are needed.

Keywords: Thailand, environmental health, protective behavior, pregnant women

Procedia PDF Downloads 364

Authors: Şule Turhan, Özlem Turan

Abstract:

Permanence in the international markets for many global companies is about being known as having effective logistics which targets customer satisfaction management and lower costs. Under competitive conditions, the necessity of providing the products to customers quickly and on time for the companies which constantly aim to improve their profitability increased the strategic importance of the logistics concept. Food logistic is one of the most difficult areas in logistics. In the process from manufacturer to final consumer, quality and hygiene standards must be provided constantly. In food logistics, reliable and extensive service network has great importance and on time delivery is the target. Developing logistics industry provide the supply of foods in the country and the development of export markets more quickly and has an important role in providing added value to the country's economy. Turkey that creates a bridge between the east and the west is an attractive market for logistics companies. In this study, by examining both the place and the importance of logistics in Turkish food sector, recommendations will be made for the food industry.

Keywords: logistics, Turkish food industry, competition, food industry

Procedia PDF Downloads 370

Authors: Gabriel Dwomoh, Williams Kwasi Boachie, Kofi Kwarteng

Abstract:

The study looked at the relationship between organizations’ acquired knowledge, skills, abilities, and shareholders wealth with training playing the mediating role. The sample of the study consisted of organizations that spent 10% or more of its annual budget on training and those whose training budget is less than 10% of the organization’s annual budget. A total of 620 questionnaires were distributed to employees working in various organizations out of which 580 representing 93.5% were retrieved. The respondents that constitute the sample were drawn using convenience sampling. The researchers used regression models for their analyses with the help of SPSS 16.0. Analyzing multiple models, it was discovered that organizations training investment plays a considerable indirect and direct effect with partial mediation between organizations acquired skills, knowledge, abilities, and shareholders wealth. Shareholders should allow their agents to invest part of their holdings to develop the human capital of the organization but this should be done with caution since shareholders returns do not depend much on how much organizations spend in developing its human resource capital.

Keywords: skills, knowledge, abilities, shareholders wealth, training investment

Procedia PDF Downloads 240

Authors: Dražen Cvitanić, Biljana Maljković

Abstract:

This paper presents models for predicting operating speeds on tangent sections of two-lane rural roads developed on continuous speed data. The data corresponds to 20 drivers of different ages and driving experiences, driving their own cars along an 18 km long section of a state road. The data were first used for determination of maximum operating speeds on tangents and their comparison with speeds in the middle of tangents i.e. speed data used in most of operating speed studies. Analysis of continuous speed data indicated that the spot speed data are not reliable indicators of relevant speeds. After that, operating speed models for tangent sections were developed. There was no significant difference between models developed using speed data in the middle of tangent sections and models developed using maximum operating speeds on tangent sections. All developed models have higher coefficient of determination then models developed on spot speed data. Thus, it can be concluded that the method of measuring has more significant impact on the quality of operating speed model than the location of measurement.

Keywords: operating speed, continuous speed data, tangent sections, spot speed, consistency

Procedia PDF Downloads 452