Somatotype identification of middle-aged women based on decision tree algorithm

PurposeBody type classification has a great influence on plate making and garment sizing system, and the accuracy of body type classification method will greatly affect the fit of garment production. The purpose of this paper is to use the decision tree algorithm to study body classification rules, develop a decision tree body recognition model and judge the body shape of middle-aged women in Xinjiang.Design/methodology/approachFirst, perform dimensionless processing on the collected data of 256 middle-aged women in Xinjiang, and the dimensionless data were used for K-means body clustering; Then, quantitatively analyze the effectiveness of different classification clusters based on the silhouette coefficients. Second, the decision tree algorithm is used to divide the classified sample data into a training set and a test set at a ratio of 70/30, and select the best node and the best branch based on the Gini coefficient to construct a classification tree. Last, the overall optimal decision tree is generated by means of hyperparameter pruning.FindingsThe body shape of middle-aged women in Xinjiang can be divided into three types: standard body, plump body and obese body. The decision tree model has an excellent effect on body classification of middle-aged women in Xinjiang (precision (macro), 95.46%; precision (micro), 95.95%; recall (macro), 95.46%; recall (micro), 95.95%; F1 (macro), 95.46%; F1 (micro), 95.95%).Originality/valueFor scientific research, this paper is conducive to increasing the regional body type theory and stimulating the establishment of a garment sizing subdivision system in Xinjiang. In terms of production practice, this paper not only establishes a model for judging the shape of middle-aged women in Xinjiang, but also provides reference data for intermediates of various sizes. In addition, to facilitate pattern-making and the establishment of a subdivision system for the size of middle-aged women's garments in Xinjiang, this paper provides the grading values of various body control parts of middle-aged women in Xinjiang.

Download Full-text

Safety performance prediction and modification strategies for construction projects via machine learning techniques

Engineering Construction & Architectural Management ◽

10.1108/ecam-04-2021-0303 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Hamidreza Abbasianjahromi ◽

Mehdi Aghakarimi

Keyword(s):

Machine Learning ◽

Decision Tree ◽

Performance Prediction ◽

Construction Projects ◽

Safety Performance ◽

Performance Criteria ◽

Second Phase ◽

Decision Tree Algorithm ◽

Tree Algorithm ◽

Content Type

PurposeUnsafe behavior accounts for a major part of high accident rates in construction projects. The awareness of unsafe circumstances can help modify unsafe behaviors. To improve awareness in project teams, the present study proposes a framework for predicting safety performance before the implementation of projects.Design/methodology/approachThe machine learning approach was adopted in this work. The proposed framework consists of two major phases: (1) data collection and (2) model development. The first phase involved several steps, including the identification of safety performance criteria, using a questionnaire to collect data, and converting the data into useful information. The second phase, on the other hand, included the use of the decision tree algorithm coupled with the k-Nearest Neighbors algorithm as the predictive tool along with the proposing modification strategies.FindingsA total of nine safety performance criteria were identified. The results showed that safety employees, training, rule adherence and management commitment were key criteria for safety performance prediction. It was also found that the decision tree algorithm is capable of predicting safety performance.Originality/valueThe main novelty of the present study is developing an integrated model to propose strategies for the safety enhancement of projects in the case of incorrect predictions.

Download Full-text

The Suit Pattern Optimal Design Based on the Features of Middle-Aged Women’s Body Shape

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.215-216.544 ◽

2012 ◽

Vol 215-216 ◽

pp. 544-546

Author(s):

Bin Lin

Keyword(s):

Optimal Design ◽

Body Shape ◽

The Body ◽

Middle Aged ◽

Body Type ◽

Pattern Design ◽

Pattern Structure ◽

Reference Parameters ◽

The Way

The current clothes for standard body type are difficult to meet the middle-aged female. Through measuring and analysising the body for the middle-aged female (40 - 59years old) and the dataes，this paper offers a statistics summary. Aiming at the defects in the applying female suit，we adjust the reference parameters of pattern structure and improve the way of processing. The conclusion can be the guidance for pattern design of special type suit.

Download Full-text

A Data-Driven Assessment of the Metabolic Syndrome Criteria for Adult Health Management in Taiwan

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph16010092 ◽

2018 ◽

Vol 16 (1) ◽

pp. 92 ◽

Cited By ~ 2

Author(s):

Ming-Shu Chen ◽

Shih-Hsin Chen

Keyword(s):

Metabolic Syndrome ◽

Decision Tree ◽

Older People ◽

Information Gain ◽

Data Driven ◽

Decision Tree Algorithm ◽

Middle Aged ◽

Tree Structures ◽

Tree Algorithm ◽

The Metabolic Syndrome

According to the modified Adult Treatment Panel III, five indices are used to define metabolic syndrome (MetS): waist circumference (WC), high blood pressure, fasting glucose, triglycerides (TG), and high-density lipoprotein cholesterol. Our work evaluates the importance of these indices. In addition, we attempted to identify whether trends and patterns existed among young, middle-aged, and older people. Following the analysis, a decision tree algorithm was used to analyze the importance of the five criteria for MetS because the algorithm in question selects the attribute with the highest information gain as the split node. The most important indices are located on the top of the tree, indicating that these indices can effectively distinguish data in a binary tree and the importance of this criterion. That is, the decision tree algorithm specifies the priority of the influence factors. The decision tree algorithm examined four of the five indices because one was excluded. Moreover, the tree structures differed among the three age groups. For example, the first key index for middle-aged and older people was TG whereas for younger people it was WC. Furthermore, the order of the second to fourth indices differed among the groups. Because the key index was identified for each age group, researchers and practitioners could provide different health care strategies for individuals based on age. High-risk middle-aged and healthy older people maintained low values of TG, which might be the most crucial index. When a person can avoid the first and second indices provided by the decision tree, they are at lower risk of MetS. Therefore, this paper provides a data-driven guideline for MetS prevention.

Download Full-text