RESEARCH ON T - SHIRT - STYLE DESIGN BASED ON KANSEI IMAGE USING BACK - PROPAGATION NEURAL NETWORKS

: Users ’ Kansei image preferences have become one of the most important factors in ﬂ uencing purchase decisions. However, de ﬁ ning Kansei image can be complex. To address this issue, researchers have widely applied back - propagation neural networks due to their capacity to handle extensive data, adaptively adjust weights and biases, conduct multi - class classi ﬁ cation and regression predictions, and offer interpretability analysis, among other fea - tures. In this study, a clothing - style design model based on users ’ Kansei image cognition is proposed, using collarless T - shirts as an example. Furthermore, the attributes of T - shirt patterns are quanti ﬁ ed using parametric graphics principles, and a semantic scale system for emotions is established through user research. The quanti ﬁ ed sample data and corresponding semantic scale scores are then used as inputs for training a back - propagation neural network algorithm. Consequently, a design model grounded in users ’ Kansei image cognition is developed, resulting in ﬁ ve optimal clothing design forms across various Kansei image categories. Additionally, the styles are showcased through the Style 3D platform, and the design evaluation is presented using radar charts. The results demonstrate that the ﬁ ve female T - shirt designs generated by the model align with users ’ style preferences based on Kansei image.


Introduction
With the rapid development of social economy, people's consumption and aesthetic level have been comprehensively improved.The consumer concept of users has gradually transitioned from material and physiological needs to spiritual and image needs [1].Consumers are increasingly concerned about the emotional attributes presented by products.Due to the lack of exploration of users' potential emotional and imaginary needs during the product design process, designers rely solely on subjective experience and find it difficult to accurately grasp users' real, complex, and fuzzy perceptual needs and expected images [2,3].Kansei image preference has become one of the most critical factors influencing users' purchasing decisions [4].Kansei can be represented by the English word "sensitive," which is the ability to sense, recall, desire, and contemplate the beauty of objects [5].Design theories closely related to this research include Kansei engineering and affective design [6].Kansei engineering theory has an important place and influence in exploring how to translate consumers' vague emotional imagery into product design elements [7].This theory has been widely applied in many fields, such as automobiles, electrical appliances, and architecture [8].Research that applies Kansei engineering theories to garment design and development is not uncommon.Most studies have been conducted from the perspective of garment colours [9][10][11], garment fabrics [12][13][14], and prints [15][16][17].However, a few researchers have approached module development, product optimisation, and design evaluation from the perspective of garment style [18,19].However, clothing pattern design methods and principles are different from industrial design methods, such as automobiles, household appliances, and other daily necessities.Pattern design is based on the human body, while the industrial modelling design works on the object, which is indirectly related to human beings.Therefore, pattern design cannot be regarded as a purely structural design of an object.In Kansei engineering, commonly used methods such as shape structure analysis and silhouette extraction typically extract design elements directly from the outer contour characteristics of an object.When applied to the field of clothing design, this method may lead to design deviations during the pattern-making process.Therefore, when applying Kansei engineering methods, it can be advantageous to start directly from clothing pattern making.Using parametric pattern-making theories to guide the quantification of key elements and referencing relevant indicators can be a more suitable approach to style design [20].
The T-shirt is one of the clothing items that women wear on a daily basis, and it holds a relatively large market share in women's fashion.Therefore, this research takes a collarless women's T-shirt as an example and completes the sample's emotional image rating based on the results of a user questionnaire survey.Key design elements are quantified using parameterisation pattern-making methods.Finally, an artificial neural network algorithm is used to establish the mapping relationship between user Kansei image cognition and product attribute categories, in order to obtain a design model for women's T-shirts.The aim of this research is to improve the efficiency of design research and development, train and obtain optimal styles under users' Kansei image cognition, and provide clear and feasible design strategies for enterprises and designers in terms of element specification and strong feasibility.

Clothing pattern attribute category quantification method
Parametric patterning in clothing involves defining mathematical expressions by constraining the geometric and dimensional relationships of the figure, thus creating a mathematical model that interrelates the dimensions of geometric objects [21,22].In this research, we propose a method for quantifying the attribute categories of patterns based on the theory of parametric pattern making.Starting from the garment body prototype, a program is written in the MatLab software platform to draw the clothing patterns using the coordinate positions of key points and the dimensional calculation formulae based on the inherent structural relationship of the garment.The key design points are identified according to the garment's key structure, and a three-layer hierarchy of key elements, element attributes, and attribute categories is established.The final quantification process involves assigning element attributes to the key design points in the pattern and subdividing them into attribute category parameters.

Back-propagation neural network algorithm
The back-propagation neural network is a data processing system that simulates the structure of neural networks in the brain.It can generally be explained using a multi-layer perceptron model and is often used to solve complex problems [23].Back-propagation networks are suitable for learning multi-layer neural networks, where the network connection weights are stably distributed within a fixed range through repeated learning of a large number of training samples.Its topology is divided into an input layer, a hidden layer, and an output layer.In the Kansei image study of women's T-shirt styles, the normalised data of the attribute categories and the image evaluation values are used as training samples for supervised learning.After multiple rounds of training, the error oscillation converges to convergence, the research objective is considered achieved, and the model construction is completed.

Radar chart evaluation method
The radar chart evaluation method, also known as the spider chart evaluation method, determines the main evaluation indicators of the study object according to the actual needs, obtains the evaluation indicator data, and performs a dimensionless process [24].This method allows for the characterisation of multiple indicators on a two-dimensional plane and visualisation of the strengths and weaknesses of each evaluation object in that indicator.An n-dimensional coordinate system is established using a point as the origin.Each coordinate axis is divided into m segments, and the specific evaluation values of each dimension are labelled and connected on the axes to form an n-dimensional polygon.The area and perimeter of the polygon are used as parameters for a comprehensive evaluation.The user questionnaires were used to rate the ratings, and the radar chart was used to visually characterise the distribution of the rated objects in terms of each Kansei image attribute [25].

Kansei image cognitive experiment
The back-propagation neural network algorithm was used to train the optimal combination model of women's T-shirt attribute categories based on users' emotional image perception.A wide range of samples of collarless T-shirt categories for women were collected, and representative samples were selected and pre-processed.The data were normalised and quantified using parametric mapping theory, and the stepwise descent method was used to develop the classification criteria.The key Kansei image vocabulary and sample image evaluation values were obtained through user research.The key parameters were selected to build a neural network model, and the results of the design element processing and the intentional evaluation value were inputted into the model to obtain the optimal combination of design elements for women's T-shirts under the target image.

Sample collection
Sample collection was conducted through two methods: product image gathering and computer-aided simulation.Beginning with clothing styles and external features, the samples were acquired from both online platforms and physical stores.We conducted online research by reviewing and recording data from various mainstream online shopping platforms, specialised clothing retail platforms, and electronic resources.T-shirt products that ranked among the top 25 in sales and met our criteria were collected.Details, including brand, style, website, and other pertinent information, were documented and encoded and subsequently incorporated into our sample database.Simultaneously, offline surveys were conducted at three prominent shopping malls in Gusu District, Suzhou.Here, we physically recorded information about the products, encompassing brand, style, and addresses.After encoding, these data were also integrated into our sample database.Following screening for similarity and clarity, we initially selected and collected 279 images of women's T-shirts.After conducting cluster analysis and comparisons, we retained 137 T-shirt samples with distinctive features.Based on the information in our sample database, we purchased the selected 137 samples for further research.To eliminate potential interference from external factors such as brand logos, fabric, patterns, and colours during the experimentation process, we uniformly preprocessed the initially selected samples.This involved using virtual clothing modelling software to simulate and virtually showcase the product samples.
Virtual garment modelling software is an effective tool for visualising clothing designs.It allows for the quick construction of body models, virtual sewing of fabric panels, and realistic fabric simulation, all with high levels of accuracy and efficiency.Currently, mature virtual clothing design tools include the US Gerber company's V-stitcher, Germany's Assyst system, China Lingdi company's Style 3D, and South Korea's CLO Virtual Fashion company's CLO 3D.In this study, we used the V4.Note: B is the bust, N is the neck, S is the shoulder breadth, L is the length of garment, AH is the arm hole, and a 1 -a 6 and b 1 -b 4 are the variables (set based on empirical).
Table 2. Key points of women's standardised T-shirt front piece and sleeve piece Note: B is the bust, N is the neck, S is the shoulder breadth, L is the length of garment, AH is the arm hole, and a 1 -a Taking the front piece and sleeve piece of a women's T-shirt as an example, the design method of the women's clothing style and pattern series in the reference book for clothing students in Chinese higher education institutions is referred to, and the intrinsic calculation formula and parametric drawing method of the paper pattern structure are proposed.The key variables for the front piece of a women's T-shirt are the bust, collar, shoulder width, and garment length, while the key variables for the sleeve piece are the sleeve cage and sleeve length.
The standardised front piece and sleeve piece structure design is shown in Figure 2. The front piece of the garment is designed using the cage depth line as the horizontal axis and the front centre line as the vertical axis to establish a co-ordinate system with the intersection of the two lines as the origin of the front piece.For the sleeve piece, the horizontal axis is the drop line and the vertical axis is the sleeve centre line.The sizing formula is determined based on the structural relationships inherent in the garment, as shown in Table 1.The coordinate points are determined according to how the key variables and other secondary variables are plotted in the clothing pattern, as shown in Table 2.
The straight lines in the pattern were drawn using the plot function on the MatLab software platform, including the centre front line f 2 f 8 , the shoulder line f 3 f 4 , the side seam line f 6 f 9 , the hem line f 8 f 9 , the sleeve side seam lines g 7 g 10 and g 2 g 12 , and the sleeve hem lines g 10 g 11 and g 11 gg 12 .The curves in the pattern were drawn using the Bezier curve model [27,28], including the front collar curve f 2 f 11 , the front sleeve cage line f 4 f 6 , the front sleeve cage line g 2 g 4 in the sleeve, and the back sleeve cage line g 4 g 7 .Finally, the women's T-shirt front piece and sleeve piece parametric planar platemaking function program was completed in MatLab.When the program is run, the mssback function in the Command Window is called, three samples are randomly selected as examples, and the corresponding parameter values are entered as shown in Table 3, resulting in the front and sleeve paper samples for the different parameter values shown in Figure 3.

Quantification of key design elements
The pattern structure is decomposed according to four key parts: collar type, shoulder type, style and sleeve type, to obtain a total of seven elemental attributes from A to G. Further subdivisions are made according to the hierarchy to obtain the attribute categories.The reference for the subdivision includes the depth of the longitudinal direction, the width of the horizontal direction, and the squareness of the curvature range.We use Z, J, and K to denote a specific design element, Z for the specific element attribute, J for the Jth category attribute, and K for the Kth form of the attribute, as shown in Table 4.According to the proposed quantification method, three categories under seven attributes with a total of 48 attribute categories are identified as the basis for the parameterisation of the pattern structure, the samples are divided according to the attribute categories, and their optimal solutions are sought using an iterative optimisation algorithm.

Data normalisation processing
Back-propagation neural network algorithms commonly used in artificial neural networks include steepest descent method [29], gradient descent [30], and Newton method [31].Among them, gradient descent is the core training algorithm in the field of computer learning, with the advantages of small storage requirements, high operability, and low implementation difficulty.In this study, the stochastic gradient descent (SGD) [32] is used for model optimisation.Given the huge variation in size between the different features of the data, we need to normalise the mapping data of the design elements before using the gradient descent method.The min-max method is adopted to process the training set and test set data so that they fall within the interval [0,1], as shown in equation (1): Taking the subdivision category A 1 under attribute A as an example, the further subdivisions A 11 , A 12 , and A 13 under category A 1 were labelled as {0,0.5,1}.The same normalisation process was carried out for all attribute category subdivision data according to equation (1) to obtain the data for the sample as shown in Table 5.

Kansei image acquisition
The 62 T-shirt-style intention words initially collected were analysed and aggregated into 11 words with high frequency of occurrence.After the second round of cluster analysis, five basic Kansei intention words were obtained, which were avant-garde, casual, sporty, classic, and elegant.The Likert scale, the most widely used in survey research, was selected to combine the 5 words with 137 samples to build a 5-level scale, and a questionnaire on the perception of women's T-shirt style Kansei image was distributed through an online platform.A total of 76 valid questionnaires were returned, and the image evaluation values were obtained using statistical analysis, as shown in Table 6.

Construction of cognitive model for styling intention
Back-propagation neural network algorithms are trained using MatLab software.The network training results are judged on the basis of the errors in the test and validation sets.The number of iterations of the network training should be moderate, too few iterations of the algorithm are not accurate, and too many may lead to overfitting.The smaller the mean square error value of the training data, the closer the output value is to the target value.The size of the error gradient indicates the size of the change in weights and thresholds.The closer the parameter curve in the training process graph is to the target curve, the better the network is trained [33].The number of neuron layers in the input layer is 18 and the number of neuron layers in the output layer is 5, which is consistent with the structure of the training sample data.Sigmoid was chosen as the activation function of the hidden layer, linear was chosen as the activation function of the output layer, and the back-propagation method was used to perform the operation.The algorithm path is shown in   The generalisation ability of the neural network can reasonably predict the probability of a change in the same type of sample, and by combining it with the enumeration algorithm, the optimal combination form can be derived by verifying the pattern of all combinations of attribute categories.A function is created from the aforementioned back-propagation neural network model and called in the enumeration algorithm to obtain an optimisation algorithm for the combination of women's T-shirt attribute categories.The optimal combination of attribute categories under the perception of the user's target Kansei image is shown in Table 7.The optimal-style design form was modelled and displayed in the Style 3D platform, as shown in Figure 6.

Evaluation
The radar chart method is applied to visually characterise the A questionnaire survey was conducted in three large shopping malls in Suzhou, China, in the clothing shopping area.A total of 89 questionnaires were returned, 86 of which were valid, with an effective rate of 96.63%.In the questionnaire, users were invited to rate a range of optimal-style designs for the target image on five main evaluation criteria dimensions.The data collected were statistically analysed and plotted as a radar chart.As can be seen from the results in Figure 7, the five optimal women's T-shirt-style designs all fit well with the users' Kansei perceptions.Therefore, the design method proposed in this study can be better applied in product design.Summarising the technology roadmap of this study is shown in Figure 8.

Conclusions
The attribute category quantification method guided by parametric graphics theory can establish the key element breakdown hierarchy and guide the quantification process of the sample data in a more scientific and efficient way.With the aid of the MatLab software platform, we established a basic functional model of the clothing patterns using the mathematical relationship between key structural points and key parameters of the garment to obtain the parameters of the experimental samples.Building the neural network model and combining it with an enumeration algorithm allows analysing the optimal

Serial number
7.369 version of the Style 3D apparel digital modelling platform to model samples by measuring their physical dimensions.During the modelling process of the T-shirt samples, common basic cotton knitted fabric was selected.The size of the virtual model was based on the Chinese standard GB/T 1335.2-2008"Women's clothing size" for a female model with a height of 165 cm and a size of 88 A. The 21 T-shirt styles with more distinctive image and style differences among the 137 samples were mainly displayed.The samples were modelled, worn on

Figure 2 .
Figure 2. Structure of the front piece and sleeve piece of the women's standardised T-shirt.

Figure 4 .
More than 50 iterations of training were carried out during the training iteration.The network reached the optimum when the 46th training was performed, so the current network parameters were applied.The training results are shown in Figure5, where the R value indicates the prediction accuracy of the neural network (taking values in the range of 0-1).The model constructed by multiple training (R ≥ 0.81) has a high accuracy, which is in line with the experimental design research needs.

Figure 3 .
Figure 3. Women's T-shirt front and sleeve pattern based on parameter values.
weight of each indicator of the research object, quantify the contribution of each indicator to the overall morphology, and evaluate the distribution of the research object in each Kansei image attribute.Determine five evaluation indicators with the same weight based on emotional intention style.The radar diagram was constructed based on the indicators, and the average of the corresponding research scores was represented by different shaped "dots" on the indicator dimension axes.By connecting the dots on adjacent axes in the diagram, a closed polygon is formed, which represents the overall state of the sample's Kansei image.The standardised radar chart is confined to a pentagon with a radius of 1, and the indicators are divided into 0.2, 0.4, 0.6, 0.8, and 1.The closer the value of the indicator is to 1, the higher the level of the indicator.

Figure 6 .
Figure 6.Optimal-style design form under target image.

Table 1 .
Women's standardised T-shirt front piece and sleeve piece structure size relationship [26]same virtual model, and paired with consistent basic-style trousers.The results of the pre-processed modelling samples are shown in Figure1.Popular general drafting CAD software includes AutoCAD developed by Autodesk in the United States, MatLab developed by Mathworks, and Lectra developed in France.MatLab is primarily used for scientific calculation, data visualisation, and interactive programming.It features a powerful image processing toolkit that allows designers to handle complex curves in paper samples more easily and solves issues such as the inability of traditional automatic code pushing to adjust each dimension independently[26].For parametric mapping in this study, we selected the MatLab software platform to draw clothing patterns and determined the dimensional formulae for the function programs based on the intrinsic structural relationships.

Table 3 .
Corresponding parameter values

Table 4 .
Hierarchical classification of key elements, element attributes, and attribute categories

Table 5 .
Attribute category parameters

Table 6 .
Evaluation values of Kansei image

Table 7 .
The optimal combination form