Application of Deep Learning for Level of Engagement in Civic Activities Prediction in Emerging Adulthood for Smart City Development

2021 ◽  
Author(s):  
Hyemin Han
Keyword(s):  
Deep Learning ◽  
Emerging Adulthood ◽  
Data Science ◽  
Logistic Regression Model ◽  
Smart Cities ◽  
Multinomial Logistic Regression ◽  
Outcome Variable ◽  
City Development ◽  
Multinomial Logistic Regression Model ◽  
Political Purpose

We applied the deep learning method, which has been developed in the fields of computer and data science for accurate prediction, to predict political purpose development during emerging adulthood. We tested whether deep learning more accurately predicted Wave 2 political purpose with Wave 1 predictors compared with traditional regression. A convolutional neural network consisting of two dense and dropout layers was trained to predict the outcome variable. For comparison, we also estimated a multinomial logistic regression model. The result demonstrated that deep learning outperformed traditional regression in general while effectively minimizing overfitting. Moreover, from exploratory analysis, we found that deep learning might be able to model the non-linear relationship between the predictors and outcome variable. Based on the findings, we discussed the implications of the present study within the context of improving citizens’ lives in smart cities.

IMPLEMENTASI MODEL REGRESI LOGISTIK MULTINOMIAL PADA PENGELOMPOKAN PENYAKIT TUBERKULOSIS

2021 ◽  
Vol 13 (1) ◽  
pp. 27
Author(s):  
Mella Apriyani ◽  
Jajang Jajang ◽  
Agustini Tripena Br. Sb.
Keyword(s):  
Logistic Regression Model ◽  
Basic Education ◽  
Multinomial Logistic Regression ◽  
Education Level ◽  
Dominant Factor ◽  
Multinomial Logistic Regression Model ◽  
Factor Level ◽  
Level Of Education ◽  
Pulmonary Tb ◽  
Extra Pulmonary

There are three types of  Tuberculosis (TB) patients at Banyumas Region Hospital, namely negative  pulmonary TB, positive pulmonary TB, and extra pulmonary TB. Types of TB generally caused by age, cae of history, gender, level of education, and domicile. One of the methods that used to find a correlation between types of TB with the affect is regression analysis. This study used multinomial logistic regession analysis because types of TB is categorical and the data is 156 TB’s patients recorded at 2018/2019. The result showed that the level of education be a dominant factor to affect TB. Here, we noted that patients with basic education level have a 5,843 time odds for getting positive pulmonary TB and 2,224 times for getting extra pulmonary TB. The multinomial logistic regression model is then given as probability for getting positive pulmonary TB with factor level of education is greather than negative pulmonary TB and extra pulmonary TB.

scholarly journals Burden and predictors ofStaphylococcus aureusandS. pseudintermediusinfections among dogs presented at an academic veterinary hospital in South Africa (2007–2012)

PeerJ ◽  
2017 ◽  
Vol 5 ◽  
pp. e3198 ◽  
Author(s):  
Daniel N. Qekwana ◽  
James Wabwire Oguttu ◽  
Fortune Sithole ◽  
Agricola Odoi
Keyword(s):  
South Africa ◽  
Logistic Regression ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Multinomial Logistic Regression ◽  
Risk Of Infection ◽  
Multinomial Logistic Regression Model ◽  
Tract Infections ◽  
Veterinary Hospital ◽  
Isolated Species

BackgroundStaphylococci are commensals of the mucosal surface and skin of humans and animals, but have been implicated in infections such as otitis externa, pyoderma, urinary tract infections and post-surgical complications. Laboratory records provide useful information to help investigate these infections. Therefore, the objective of this study was to investigate the burdens of these infections and use multinomial regression to examine the associations between variousStaphylococcusinfections and demographic and temporal factors among dogs admitted to an academic veterinary hospital in South Africa.MethodsRecords of 1,497 clinical canine samples submitted to the bacteriology laboratory at a veterinary academic hospital between 2007 and 2012 were included in this study. Proportions of staphylococcal positive samples were calculated, and a multinomial logistic regression model was used to identify predictors of staphylococcal infections.ResultsTwenty-seven percent of the samples tested positive forStaphylococcusspp. The species ofStaphylococcusidentified wereS. pseudintermedius(19.0%),S. aureus(3.8%),S. epidermidis(0.7%) andS. felis(0.1%). The remaining 2.87% consisted of unspeciatedStaphylococcus. Distribution of the species by age of dog showed thatS. pseudintermediuswas the most common (25.6%) in dogs aged 2–4 years whileS. aureuswas most frequent (6.3%) in dogs aged 5–6 years.S. pseudintermedius(34.1%) andS. aureus(35.1%) were the most frequently isolated species from skin samples. The results of the multivariable multinomial logistic regression model identified specimen, year and age of the dog as significant predictors of the risk of infection withStaphylococcus. There was a significant temporal increase (RRR = 1.17; 95% CI [1.06–1.29]) in the likelihood of a dog testing positive forS. pseudintermediuscompared to testing negative. Dogs ≤ 8 years of age were significantly more likely to test positive forS. aureusthan those >8 years of age. Similarly, dogs between 2–8 years of age were significantly more likely to test positive forS. pseudintermediusthan those >8 years of age. In addition, dogs 2–4 years of age (RRR = 1.83; 1.09–3.06) were significantly more likely to test positive forS. pseudintermediuscompared to those <2 years of age. The risk of infection withS. pseudintermediusorS. aureuswas significantly higher in ear canal and skin specimens compared to other specimens.ConclusionsThe findings suggest thatS. pseudintermediusandS. aureuswere the most commonly isolated species from dogs presented at the study hospital. Age of the dog and the location of infection were significant predictors of infection with bothStaphylococcusspecies investigated. Significant increasing temporal trend was observed forS. pseudintermediusbut notS. aureus. This information is useful for guiding clinical decisions as well as future research.

scholarly journals Social determinants of malnutrition in Chilean children aged up to five

2022 ◽  
Vol 22 (1) ◽  
Author(s):  
Sandra Alvear-Vega ◽  
Héctor Vargas-Garrido
Keyword(s):  
Social Determinants ◽  
Reference Group ◽  
Multinomial Logistic Regression ◽  
Geographical Location ◽  
Vulnerable Groups ◽  
Outcome Variable ◽  
Multinomial Logistic Regression Model ◽  
The North ◽  
The Social ◽  
Child Nutritional Status

Abstract Background This study aimed to ascertain the Social Determinants (SDs) of malnutrition (over and undernutrition) of Chilean children aged up to five. Methods The study was carried out using a sample of children from zero to five years old (n = 1,270,485; 52.2% female) from the National Socioeconomic Characterization Survey (CASEN) 2017. A multinomial logistic regression model was used, where the “child nutritional status” outcome variable assumed three possible values: normal nutrition, overnutrition, and undernutrition, while taking those variables reported in previous literature as independent variables. Results The model, by default, set normal nutrition as the reference group, Count R2 = 0.81. Results show a higher likelihood of both overnutrition and undernutrition among male children from the lowest quintiles, with native ethnic backgrounds, reporting health problems, having public health insurance, and who attend kindergarten. Additionally, higher probabilities of undernutrition in younger than two and living in the north of the country, while overnutrition is more likely in the south. Conclusions Socioeconomic variables are fundamentally related to both over and undernutrition; the current single schema program to prevent malnutrition should consider SDs such as ethnicity and geographical location, among others; moreover, successful nutritional programs—which focused on the lowest quintiles, need to be expanded to other vulnerable groups and pay more attention to overnutrition.

Diachronic frame analysis

2019 ◽  
Vol 11 (1) ◽  
pp. 43-78
Author(s):  
James Law
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Multinomial Logistic Regression ◽  
Frame Analysis ◽  
Semantic Change ◽  
Frame Semantics ◽  
Multinomial Logistic Regression Model ◽  
Grammatical Category

Abstract Frame Semantics offers a valuable perspective on mechanisms of semantic change, particularly metonymy. However, corpus-based frame analysis has rarely been applied to diachronic data. The potential of this approach is illustrated with a diachronic description of the Purpose frame in French, based on 1,429 tokens of 17 frame-evoking words. Metonymic mappings in the frame allow Means and Medium to replace Agent. A multinomial logistic regression model shows that usage of these mappings has increased since 1600 and is conditioned by genre and the frequency and grammatical category of the frame-evoking word. The approach may inform how metonymy leads to lexicalized semantic change.

Sign in / Sign up

Export Citation Format

Share Document