Estimating Human Body Dimensions Using RBF Artificial Neural Networks Technology and Its Application in Activewear Pattern Making

Abstract

Nowadays, the popularity of the internet has continuously increased. Predicting human body dimensions intelligently would be beneficial to improve the precision and efficiency of pattern making for enterprises in the apparel industry. In this study, a new predictive model for estimating body dimensions related to garment pattern making is put forward based on radial basis function (RBF) artificial neural networks (ANNs). The model presented in this study was trained and tested using the anthropometric data of 200 adult males between the ages 20 and 48. The detailed body dimensions related to pattern making could be obtained by inputting four easy-to-measure key dimensions into the RBF ANN model. From the simulation results, when spreading parameter σ and momentum factor α were set to 0.012 and 1, the three-layer model with 4, 72, and 8 neurons in the input, hidden, and output layers, respectively, showed maximum accuracy, after being trained by a dataset with 180 samples. Moreover, compared with a classic linear regression model and the back propagation (BP) ANN model according to mean squared error, the predictive performance of the RBF ANN model put forward in this study was better than the other two models. Therefore, it is feasible for the presented predictive model to design garment patterns, especially for tight-fitting garment patterns like activewear. The estimating accuracy of the proposed model would be further improved if trained by more appropriate datasets in the future.

Construction of the PSO-LSSVM prediction model for sleeve pattern dimensions based on garment flat recognition

“…And the pure LSSVM, RBF and BP models were selected for comparison. For the RBF model, a 5-96-3 structure with a spreading of 850 was chosen according to Wang's method (Wang et al, 2019b). Where the 5-13-3 structure with the…”

“…However, the prediction results were still unsatisfactory due to the small sample sizes. It directly results in insufficient training (Wang et al, 2019b). Thus, it is necessary to search for a data-driven model to establish the mapping relationship based on small sample sizes, short training cycle and high accuracy.…”

Magnetization‐Switchable Implant System to Target Delivery of Stem Cell‐Loaded Bioactive Polymeric Microcarriers

“…Therefore, the inner diameter was determined based on knee and thigh girth circumferences (averages, 13.18 and 16.84 cm, respectively). [51,52] In terms of magnetic field generation, instead of using a permanent magnet in the form of a single-cylinder with heavyweight, an array of modules made up of small magnets was used for weight reduction, low manufacturing cost, and optimization of magnetic field generation. One single magnet within the magnet array device has a width of 20 mm, a length of 20 mm, and a thickness of 10 mm.…”

Automatic Estimation of Anthropometric Human Body Measurements

“…In theory, there are no predefined vertices on the surface of human body to guide the processing; as it is when analyzing standard 3D objects with corners and edges. Considering the theoretical and practical issues with the algorithmic approaches, in many environments, they have been replaced with machine learning techniques, such as random forests (Xiaohui et al, 2018) or neural networks (Yan and Kämäräinen, 2021;Wang et al, 2019).…”

“…Regarding the human body measurements estimation, several existing approaches formulate the task as estimating an extended list of advanced body measures from a set of predefined basic body measurements on the input, thus having the 1D statistical input data (Wang et al, 2019;Liu et al, 2017). Usually, the estimation is based on an end-to-end learning neural network, mapping from the input easy-to-measure body dimensions to the detailed body dimensions on the output.…”