Data augmentation strategies for the Bayesian spatial probit regression model

2012 ◽  
Vol 56 (3) ◽  
pp. 478-490 ◽  
Author(s):  
Candace Berrett ◽  
Catherine A. Calder
Keyword(s):  
Regression Model ◽  
Data Augmentation ◽  
Probit Regression ◽  
Augmentation Strategies ◽  
Spatial Probit

scholarly journals Building Damage Detection from Post-Event Aerial Imagery Using Single Shot Multibox Detector

2019 ◽  
Vol 9 (6) ◽  
pp. 1128 ◽  
Author(s):  
Yundong Li ◽  
Wei Hu ◽  
Han Dong ◽  
Xueyan Zhang
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Hurricane Sandy ◽  
Training Data ◽  
Aerial Images ◽  
Detection Methods ◽  
Single Shot ◽  
Data Set ◽  
Augmentation Strategies ◽  
Post Disaster

Using aerial cameras, satellite remote sensing or unmanned aerial vehicles (UAV) equipped with cameras can facilitate search and rescue tasks after disasters. The traditional manual interpretation of huge aerial images is inefficient and could be replaced by machine learning-based methods combined with image processing techniques. Given the development of machine learning, researchers find that convolutional neural networks can effectively extract features from images. Some target detection methods based on deep learning, such as the single-shot multibox detector (SSD) algorithm, can achieve better results than traditional methods. However, the impressive performance of machine learning-based methods results from the numerous labeled samples. Given the complexity of post-disaster scenarios, obtaining many samples in the aftermath of disasters is difficult. To address this issue, a damaged building assessment method using SSD with pretraining and data augmentation is proposed in the current study and highlights the following aspects. (1) Objects can be detected and classified into undamaged buildings, damaged buildings, and ruins. (2) A convolution auto-encoder (CAE) that consists of VGG16 is constructed and trained using unlabeled post-disaster images. As a transfer learning strategy, the weights of the SSD model are initialized using the weights of the CAE counterpart. (3) Data augmentation strategies, such as image mirroring, rotation, Gaussian blur, and Gaussian noise processing, are utilized to augment the training data set. As a case study, aerial images of Hurricane Sandy in 2012 were maximized to validate the proposed method’s effectiveness. Experiments show that the pretraining strategy can improve of 10% in terms of overall accuracy compared with the SSD trained from scratch. These experiments also demonstrate that using data augmentation strategies can improve mAP and mF1 by 72% and 20%, respectively. Finally, the experiment is further verified by another dataset of Hurricane Irma, and it is concluded that the paper method is feasible.

scholarly journals Credit Constraint and Rural Household Welfare in the Mezam Division of the North-West Region of Cameroon

2021 ◽  
Vol 13 (11) ◽  
pp. 5964
Author(s):  
Louis Atamja ◽  
Sungjoon Yoo
Keyword(s):  
Regression Model ◽  
Rural Household ◽  
Household Welfare ◽  
Switching Regression ◽  
Probit Regression ◽  
Credit Constraint ◽  
Endogenous Switching Regression ◽  
North West ◽  
The North ◽  
West Region

The purpose of this study is to examine the effect of the rural household’s head and household characteristics on credit accessibility. This study also seeks to investigate how credit constraint affects rural household welfare in the Mezam division of the North-West region of Cameroon. Using data from a household survey questionnaire, we found that 36.88% of the households were credit-constrained, while 63.13% were unconstrained. A probit regression model was used to examine the determinants of households’ credit access, while an endogenous switching regression model was used to analyze the impact of credit constraint on household welfare. The results from the probit regression model indicate the importance of the farmer’s or trader’s organization membership, occupation, and savings to the household’s likelihood of being credit-constrained. On the other hand, a prediction from the endogenous switching regression model confirms that households with access to credit have a better standard of welfare than a constrained household. From the results, it is necessary for the government to subsidize microfinance institutions, so that they can take on the risk of offering credit to rural households.

scholarly journals Allocative efficiency and adoption of improved maize variety: A case of eastern hills of Nepal

2020 ◽  
Vol 3 (1) ◽  
pp. 148-159
Author(s):  
Tilak Katel ◽  
Bhishma Raj Dahal ◽  
Sandesh Bhatta
Keyword(s):  
Regression Model ◽  
Insect Pest ◽  
Allocative Efficiency ◽  
Climatic Conditions ◽  
Probit Regression ◽  
Maize Production ◽  
Factors Affecting ◽  
Face To Face ◽  
Maize Variety ◽  
Structured Questionnaire

Production and  profit from maize farming can be substantially increased by allocating resources efficiently and adopting improved maize variety. In this context, a study was undertaken to determine the allocative efficiency and factors affecting adoption of improved maize variety in Eastern hills of Nepal. Random sampling was conducted in eastern part of Khotang district namely, Halesi municipality and Diktel Rupakot Majuwagadi municipality during month of March 2019. Pretested semi-structured questionnaire was administered among 80 randomly selected farmers cultivating maize since last two years. Face to face interview was scheduled to obtain data. Cobb Douglas production function was used to determine allocative efficiency; probit regression model was launched to determine factors affecting adoption of improved maize variety.  Significant positive relation of cost of seed, planting, and weeding with income has suggested to increase expenditure on certified maize seed over own farm seed, line sowing over broadcasting, and weeding. The model revealed that increasing all the factors of production by 100% would result in increase in income by 71.83%. Furthermore, cultivating improved maize variety is more profitable than own farm seed. Probit regression model showed that, farmers who have received training, who were member of cooperatives and who have received high schooling were more likely to adopt open-pollinated improved maize variety. Unavailability of inputs (seed, fertilizer, and labor), insect pest attack and adverse climatic conditions were major constraint of maize farming. Therefore, it would be better to suggest maize producers to increase expenditure on seed; make maize field weed free and adopt line sowing method. In addition, providing training, increasing access over inputs and encouraging farmers towards cooperatives could be virtuous for sustainable maize production.

scholarly journals Analisis Dampak Impor Cina terhadap Kebertahanan dan Pertumbuhan Industri Tekstil dan Produk Tekstil Indonesia

2012 ◽  
Vol 13 (1) ◽  
pp. 90-108
Author(s):  
Laela Dika Wulandari
Keyword(s):  
Regression Model ◽  
Firm Growth ◽  
Positive Impact ◽  
External Factors ◽  
The Other ◽  
Probit Regression ◽  
Survival And Growth ◽  
Internal And External Factors ◽  
The Impact ◽  
Test Result

AbstractWe try to analyze the impact of Chinese Textile and Garment (T&G) imports, and the internal and external factors to the firm survival and growth of T&G industry in Indonesia, for the period study of 2002 to 2007. Probit regression model is used to analyze the impact of Chinese imports to the survival of firm, while OLS regression model is used to analyze its growth. It shows that the ability of firms' survival is influenced by the internal and external factors. The Chinese imports give positive impact to the firms' survival ability. On the other hand, firm's growth is only affected by its internal characteristics, while the impact of Chinese imports is proven not significant. The Heckman test result stated that there are no correlation between firms' ability to survive and the firm growth behavior.Keywords: Growth, Survival, Chinese Imports, Textile, Indonesian Textile and Garment IndustryAbstrakStudi ini menganalisis dampak dari penetrasi impor TPT Cina, faktor internal, serta faktor eksternal terhadap kebertahanan dan pertumbuhan perusahaan dalam industri TPT Indonesia periode tahun 2002-2007. Metode probit regression digunakan untuk mengetahui dampak impor Cina terhadap kebertahanan perusahaan, sementara regresi linear sederhana (OLS) digunakan untuk menganalisis pertumbuhannya. Ditemukan bahwa kebertahanan perusahaan dipengaruhi oleh karakteristik internal dan eksternal, serta impor Cina yang memberikan dampak positif. Sementara pertumbuhan perusahaan hanya dipengaruhi oleh faktor internal, di mana impor Cina tidak memberikan dampak signikan. Hasil pengujian Heckman menyatakan tidak ada indikasi hubungan antara kebertahanan perusahaan dengan perilaku pertumbuhannya.Kata kunci: Pertumbuhan, Kebertahanan, Impor Cina, Tekstil, Industri Tekstil dan Produk Tekstil Indonesia

scholarly journals Human Trafficking and Displacement in South Asia: An Econometric Analysis

2017 ◽  
Vol 65 (1) ◽  
pp. 73-76
Author(s):  
Tanjina Rahman ◽  
Md Israt Rayhan ◽  
Nayeem Sultana
Keyword(s):  
Regression Model ◽  
South Asia ◽  
Human Trafficking ◽  
Internal Displacement ◽  
Probit Regression ◽  
Safety Nets ◽  
Internally Displaced ◽  
Internally Displaced Person ◽  
Social Safety Nets ◽  
The Relationship

Human trafficking has received increased media and national attention. Despite concerted efforts to combat human trafficking, the trade in persons persists and in fact continues to grow. This paper describes the relationship and distinction between trafficking and ethnic fragmentation, conflict, internally displaced person by different measures of control. To explain the relationship between these factors, this study uses a Probit regression model. It appears that ethnic conflict leads the internal displacement of individuals from networks of family and community, and their access to economic and social safety nets. Dhaka Univ. J. Sci. 65(1): 73-76, 2017 (January)

scholarly journals Objective Bayesian Inference in Probit Models with Intrinsic Priors Using Variational Approximations

Entropy ◽  
2020 ◽  
Vol 22 (5) ◽  
pp. 513
Author(s):  
Ang Li ◽  
Luis Pericchi ◽  
Kun Wang
Keyword(s):  
Regression Model ◽  
Binary Classification ◽  
Mean Field ◽  
Variational Approximation ◽  
Classification Problems ◽  
Probit Regression ◽  
Variational Approximations ◽  
Intrinsic Prior ◽  
Inference Methods ◽  
Bayesian Probit Regression

There is not much literature on objective Bayesian analysis for binary classification problems, especially for intrinsic prior related methods. On the other hand, variational inference methods have been employed to solve classification problems using probit regression and logistic regression with normal priors. In this article, we propose to apply the variational approximation on probit regression models with intrinsic prior. We review the mean-field variational method and the procedure of developing intrinsic prior for the probit regression model. We then present our work on implementing the variational Bayesian probit regression model using intrinsic prior. Publicly available data from the world’s largest peer-to-peer lending platform, LendingClub, will be used to illustrate how model output uncertainties are addressed through the framework we proposed. With LendingClub data, the target variable is the final status of a loan, either charged-off or fully paid. Investors may very well be interested in how predictive features like FICO, amount financed, income, etc. may affect the final loan status.

Sign in / Sign up

Export Citation Format

Share Document