Machine learning method to ensure robust decision-making of AVs

2020 ◽

Author(s):

Qiaoman Yang ◽

Chunyu Liu

Keyword(s):

Machine Learning ◽

Decision Making ◽

Objective Function ◽

Sentiment Analysis ◽

Support Vector ◽

Machine Learning Method ◽

Learning Method ◽

Key Issues ◽

Single Objective ◽

Accuracy And Stability

Classification modeling is one of the key issues in sentiment analysis. Support vector machine (SVM) has been widely used in classification as an effective machine learning method. Generally, a common SVM is only for decision-making that sacrifices the distribution of data. In practice, sentiment data are big and mazy, which results in the deficiency of accuracy and stability when common SVM is used. The study investigates sentiment analysis by applying the twin objective function SVM, including nonparallel SVM(NPSVM) and twin SVM (TWSVM). From the experiments, we concluded that twin objective function SVMs are superior to NB and single objective function SVM in accuracy and stability.

Download Full-text

Machine learning method to solve the credit decision-making problem of small and medium-sized enterprises

10.1117/12.2626456 ◽

2021 ◽

Author(s):

Wanmei Cui ◽

Xiaji Ye ◽

Yaling Huang ◽

Zhiji Yang

Keyword(s):

Machine Learning ◽

Decision Making ◽

Machine Learning Method ◽

Learning Method ◽

Decision Making Problem

Download Full-text

Big social data and customer decision making in vegetarian restaurants: A combined machine learning method

Journal of Retailing and Consumer Services ◽

10.1016/j.jretconser.2021.102630 ◽

2021 ◽

Vol 62 ◽

pp. 102630

Author(s):

Mehrbakhsh Nilashi ◽

Hossein Ahmadi ◽

Goli Arji ◽

Khalaf Okab Alsalem ◽

Sarminah Samad ◽

...

Keyword(s):

Machine Learning ◽

Decision Making ◽

Machine Learning Method ◽

Learning Method ◽

Social Data

Download Full-text

Sociodemographic risk factors of under-five stunting in Bangladesh: Assessing the role of interactions using a machine learning method

PLoS ONE ◽

10.1371/journal.pone.0256729 ◽

2021 ◽

Vol 16 (8) ◽

pp. e0256729

Author(s):

Mohaimen Mansur ◽

Awan Afiaz ◽

Md. Saddam Hossain

Keyword(s):

Machine Learning ◽

Risk Factors ◽

Decision Making ◽

Parental Education ◽

Classification Tree ◽

Individual Risk ◽

Machine Learning Method ◽

Learning Method ◽

Sociodemographic Risk ◽

Childhood Stunting

This paper aims to demonstrate the importance of studying interactions among various sociodemographic risk factors of childhood stunting in Bangladesh with the help of an interpretable machine learning method. Data used for the analyses are extracted from the Bangladesh Demographic and Health Survey (BDHS) 2014 and pertain to a sample of 6,170 under-5 children. Social and economic determinants such as wealth, mother’s decision making on healthcare, parental education are considered in addition to geographic divisions and common demographic characteristics of children including age, sex and birth order. A classification tree was first constructed to identify important interaction-based rules that characterize children with different profiles of risk for stunting. Then binary logistic regression models were fitted to measure the importance of these interactions along with the individual risk factors. Results revealed that, as individual factors, living in Sylhet division (OR: 1.57; CI: 1.26–1.96), being an urban resident (OR: 1.28; CI: 1.03–1.96) and having working mothers (OR: 1.21; CI: 1.02–1.44) were associated with higher likelihoods of childhood stunting, whereas belonging to the richest households (OR: 0.56; CI: 0.35–0.90), higher BMI of mothers (OR: 0.68 CI: 0.56–0.84) and mothers’ involvement in decision making about children’s healthcare with father (OR: 0.83, CI: 0.71–0.97) were linked to lower likelihoods of stunting. Importantly however, risk classifications defined by the interplay of multiple sociodemographic factors showed more extreme odds ratios (OR) of stunting than single factor ORs. For example, children aged 14 months or above who belong to poor wealth class, have lowly educated fathers and reside in either Dhaka, Barisal, Chittagong or Sylhet division are the most vulnerable to stunting (OR: 2.52, CI: 1.85–3.44). The findings endorse the need for tailored-intervention programs for children based on their distinct risk profiles and sociodemographic characteristics.

Download Full-text

COVID-19: Face Mask Detector with Open CV and CNN Algorithm

10.3233/apc210234 ◽

2021 ◽

Author(s):

Tambe Pragati ◽

Tanpure Akshada ◽

Wakchaure Asmita ◽

Zaware Prachi ◽

S.A. Bhosale

Keyword(s):

Neural Network ◽

Machine Learning ◽

Decision Making ◽

Face Mask ◽

Machine Learning Method ◽

Learning Method ◽

Infected Person ◽

Public Places ◽

The Public ◽

Reduce Risk

Now a day, covering our faces with a mask has become a new normal habit in this pandemic, as face masks are effective in preventing the virus outbreak. Masks reduce risk from an infected person whether they have symptoms or not. In this paper, we propose a system that restrict the growth of COVID-19 by finding out peoples with mask and without mask. Where all the public places are monitored with CCTV cameras. A deep learning architecture is trained on a dataset which consists of images of people with wearing mask and without wearing is masks collected from various sources. By using image processing analysis and machine learning method we can find out face mask wearied or not. Face mask detection can be done using various methods. Mainly convolutional neural network and OpenCV method is used. The accuracy and decision making of CNN algorithm is higher than other algorithms.

Download Full-text