Conductive elastic fabrics are desirable in wearable electronics and related applications. Highly elastic conductive polyamide/lycra knitted fabric was prepared using intrinsically conductive polymer poly (3,4-ethylenedioxythiophene) (PEDOT) blended with polyelectrolyte poly (styrene sulfonate) (PSS) using easily scalable coating and immersion methods. The effects of these two methods of treatments on uniformity, electromechanical property, stretchability, and durability were investigated. Different grades of waterborne polyurethanes (PU) were employed in different concentrations to improve the coating and adhesion of the PEDOT:PSS on the fabric. The immersion method gave better uniform treatment, high conductivity, and durability against stretching and cyclic tension than the coating process. The surface resistance increased from ~ 1.7 and ~ 6.4 Ω/square at 0% PU to ~ 3.7 and ~ 12.6 Ω/square at 50% PU for immersion and coating methods, respectively. The treatment methods as well as the acidic PEDOT:PSS did not affect the mechanical properties of the fabric and the fabric showed high strain at break of ~ 650% and remained conductive until break. Finally, to assess the practical applicability of the treated fabric for wearable e-textiles, the change in surface resistance was assessed by cyclically stretching 10 times at 100% strain and washing in a domestic laundry for 10 cycles. The resistance increased only by a small amount when samples were stretched cyclically at 100% strain, and the samples showed good durability against washing.

Compared to other industries, fashion apparel retail faces many challenges in predicting future demand for its products with a high degree of precision. Fashion products’ short life cycle, insufficient historical information, highly uncertain market demand, and periodic seasonal trends necessitate the use of models that can contribute to the efficient forecasting of products’ sales and demand. Many researchers have tried to address this problem using conventional forecasting models that predict future demands using historical sales information. While these models predict product demand with fair to moderate accuracy based on previously sold stock, they cannot fully be used for predicting future demands due to the transient behaviour of the fashion industry. This paper proposes an intelligent forecasting system that combines image feature attributes of clothes along with its sales data to predict future demands. The data used for this empirical study is from a European fashion retailer, and it mainly contains sales information on apparel items and their images. The proposed forecast model is built using machine learning and deep learning techniques, which extract essential features of the product images. The model predicts weekly sales of new fashion apparel by finding its best match in the clusters of products that we created using machine learning clustering based on products’ sales profiles and image similarity. The results demonstrated that the performance of our proposed forecast model on the tested or test items is promising, and this model could be effectively used to solve forecasting problems.

3D printing utilized as a direct deposition of conductive polymeric materials onto textiles reveals to be an attractive technique in the development of functional textiles. However, the conductive fillers—filled thermoplastic polymers commonly used in the development of functional textiles through 3D printing technology and most specifically through Fused Deposition Modeling (FDM) process—are not appropriate for textile applications as they are excessively brittle and fragile at room temperature. Indeed, a large amount of fillers is incorporated into the polymers to attain the percolation threshold increasing their viscosity and stiffness. For this reason, this study focuses on enhancing the flexibility, stress and strain at rupture and electrical conductivity of 3D-printed conductive polymer onto textiles by developing various immiscible polymer blends. A phase is composed of a conductive polymer composite (CPC) made of a carbon nanotubes (CNT) and highly structured carbon black (KB)- filled low-density polyethylene (LDPE) and another one of propylene-based elastomer (PBE) blends. Two requirements are essential to create flexible and highly conductive monofilaments for 3D-printed polymers onto textile materials applications. First, the co-continuity of both the thermoplastic and the elastomer phases and the location of the conductive fillers in the thermoplastic phase or at the interface of the two immiscible polymers are necessary to preserve the flexibility of the elastomer while decreasing the global amount of charges in the blends. In the present work based on theoretical models, when using a two-step melt process, the KB and CNT particles are found to be both preferentially located at the LDPE/PBE interface. Moreover, in the case of the two-step extrusion, SEM characterization showed that the KB particles were located in the LDPE while the CNT were mainly at the LDPE/PBE interface and TEM analysis demonstrated that KB and CNT nanoparticles were in LDPE and at the interface. For one-step extrusion, it was found that both KB and CNT are in the PBE and LDPE phases. These selective locations play a key role in extending the co-continuity of the LDPE and PBE phases over a much larger composition range. Therefore, the melt flow index and the electrical conductivity of monofilament, the deformation under compression, the strain and stress and the electrical conductivity of the 3D-printed conducting polymer composite onto textiles were significantly improved with KB and CNT-filled LDPE/PBE blends compared to KB and CNT-filled LDPE separately. The two-step extrusion processed $60\%({\mathrm{LDPE}}_{16.7\%\mathrm{KB}+4.2\%\mathrm{CNT}})/40\mathrm{PBE}$ blends presented the best properties and almost similar to the ones of the textile materials and henceforth, could be a better material for functional textile development through 3D printing onto textiles.

Purpose: The purpose of this paper is to present a new collaborative design-based method for designing customized garments, aimed at the physically disabled people with scoliosis. Design/methodology/approach: The proposed method is based on the virtual human model created using a 3D body scanner, permitting to simulate the consumer’s morphological shape with atypical physical deformations. Next, customized 2D and 3D virtual garment prototyping tools will be used to create products through interactions between the consumer, designer and pattern maker. The general principle of the proposed design method is based on the following sequence: design-display-evaluation-adjustment. After running the sequence for a number of times, the final design solution, which will be approved by both the designer and consumer, can be easily identified. Findings: Design knowledge, which is already applied to normal body shapes successfully can be applied to 3D garment design using the concept which is based on collaborative design. Through this process, the classical 2D garment design knowledge, especially 2D patterns and design rules, can be modified and applied according to a normalized virtual garment sensory evaluation procedure quantitatively. This evaluation procedure, interactively performed by the designer and consumer, can permit to adapt the finished product to disabled people afflicted with severe scoliosis. The proposed method is also validated to be more advanced compared to 2D-to-3D virtual CAD design method, especially for atypical morphologies. Originality/value: As a co-design method, 3D virtual draping and sensory evaluation can fully satisfy the interaction between the garment design technical space and perceptual space of the finished garments ensuring desired 3D garment fit effect by adjustment of technical parameters. 3D scanning technology is used to generate a complete digitalized 3D human model, permitting to extract the main features of body shapes without accurate measurements. As a knowledge-based design process, both the fashion design knowledge and the pattern making knowledge will be extracted to provide inspirations and references. Successful design solutions will be incorporated into the fashion design knowledge base in order to generate new design rules and enhance professional design knowledge.

Functional finishing brings an alteration on the mechanical and surface properties of textile materials and henceforth influences the tactile properties. In this work, Kawabata evaluation systems (KES) for fabrics were utilized to notice the changes in the tactile properties of fabrics resulting from different finishing types such as inkjet printing, screen printing, and coating. The effects of functional finishing on the fabric’s tactile property were inconsistent with reference to the course of decrease or increase being dependent on the types of finishes. The findings showed that KES can be employed as a promising tool to sort out the suitable functional finishing types in terms of tactile properties. Amongst the implemented finishing types, inkjet printing offered superior tactile properties with respect to tensile energy (softness), shear rigidity, compressional softness, bending stiffness (drapability), and surface properties. The KES results confirmed that low-stress mechanical properties are strongly associated with the tactile property and might assist as a quality profile data source for guaranteeing the production and development of a virtuous quality product. The result encourages further utilization of the KES for functional fabric tactile property evaluation.

As fashion mass customization has been developing rapidly in the recent decade, supply chain in apparel industry was required to be more flexible for meeting the need of quick response toward the dynamic changes in the fashion market. Forecast-based make-to-stock production strategy was not suitable anymore. Make-to-order strategy was employed by more and more apparel companies. However, there were still many defects in traditional make-to-order apparel supply chain, e.g., sustainability is still at a low level. In this study, we proposed a collaborative cloud service platform to develop a novel model of sustainable make-to-order apparel supply chain. A service provider selection heuristic was designed for this platform to optimally select suppliers corresponding to each received demand. Multi-agent-based simulation technology was utilized to build the proposed platform and to evaluate the new sustainable supply chain model. Experiment was conducted in the simulation to compare our new model to traditional apparel make-to-order model and model with outsourcing mechanism. Based on simulation results, the remarkable improvement in terms of sustainability of the proposed platform and corresponding supply chain model was demonstrated.