Artificial intelligence (AI) is revolutionizing the textile industry by improving the prediction of fabric properties and handfeel, which are essential for assessing textile quality and performance. However, the practical application and translation of AI-predicted results into real-world textile production remain unclear, posing challenges for widespread adoption. This paper systematically reviews AI-driven techniques for predicting these characteristics by focusing on model mechanisms, dataset diversity, and prediction accuracy. Among 899 papers initially identified, 39 were selected for in-depth analysis through both bibliometric and content analysis. The review categorizes and evaluates various AI approaches, including machine learning, deep learning, and hybrid models, across different types of fabric. Despite significant advances, challenges remain, such as ensuring model generalization and managing complex fabric behavior. Future research should focus on developing more robust models, integrating sustainability, and refining feature extraction techniques. This review highlights the critical gaps in the literature and provides practical insights to enhance AI-driven prediction of fabric properties, thus guiding future textile innovations.

Objective The treatment effect of orthoses for hallux valgus (HV) is unclear with little interventional studies, the design involves multiple complex factors, and therefore a systematic analysis with meta-analysis is necessary. The objective of this systematic review and meta-analysis is to determine whether current foot orthoses are effective in treating HV. Design Systematic review with meta-analysis. Data sources Electronic databases (PubMed, Scopus, Cinahl and Medline) are searched up to February 2020. Eligibility criteria for selecting studies Interventional studies with content focus on HV orthosis design and any of the outcomes related to effectiveness for treating HV are included. The standardised mean differences are calculated. The risk of bias in included studies is assessed using the Cochrane Collaboration’s risk of bias tools. Results In total, 2066 articles are identified. Among them, nine are selected and quality rated, and data are extracted and closely examined. A meta-analysis is conducted, where appropriate. The main causes of potential bias are missing outcome data and outcome measurement error. The results show that orthosis with a toe separator has the best effect of correcting the HV angle (standardised mean difference: 0.50, 95% CI: 0.189 to 0.803). Conclusion The orthoses design with a toe separator or an element that allows for the foot anatomic alignment is critical for reducing the HV angle and relieving foot pain. The results contribute to a better selection of treatment for patients. PROSPERO registration number CRD42021260403.

Compression stockings have long been manufactured in a single color without patterns, but enhancing their aesthetic appeal through knitted designs can improve user compliance. This study explores the potential of punch lace knitted structures to create patterns in compression textiles by seamless knitting technology while maintaining sufficient pressure. The effects of yarn material, number of yarns used, and knitted patterns on pressure and thermal comfort will be studied. The fabric pressure was evaluated using pressure sensors with a leg mannequin, while the thermal properties were measured according to the textile standard. This study found that the pressure and thermal conductivity of fabric are significantly influenced by the number of yarn and yarn materials, but not the knitted pattern. Cupro/cotton/polyurethane yarn (A) exhibits the strongest positive impact on pressure, increasing by 2.03 mmHg with the addition of one end of yarn A while polyamide/lycra yarn (C) exhibits a higher thermal conductivity than yarn A. For air permeability, the number of yarn and knitted patterns significantly affects the ventilation resistance. Pattern B with an additional needle in a float stitch shows 0.023 kPa·s/m lower resistance than pattern A. The findings from this study can be widely used in health, medical, and sports applications.

The pursuit of materials that offer both wear comfort and protection for functional and protective clothing has led to the exploration of weft-knitted spacer structures. Traditional cushioning materials such as spacer fabrics and laminated foam often suffer from deformation under compression stresses, thus compromising their protective properties_. This study investigates the enhancement of the force absorption, stress–strain, and thermal properties of weft-knitted spacer fabrics with inlays. Surface yarns with superior stretchability and thermal properties are used and combined with elastic yarns in various patterns to fabricate nine different inlay samples. The mechanical and thermal properties of these samples are systematically analyzed, including their compression, stretchability, thermal comfort, and surface properties. The results show that the inlay spacer fabric exhibits superior compression properties and thermal conductivity compared to traditional laminated foam and spacer fabrics while maintaining stretchability, thus providing better performance than traditional fabrics for protective clothing and wearable cushioning products. This study further confirms that the type of inlay yarn and inlay structure are crucial factors that significantly influence the thermal, tensile, and compressive properties of the fabric. This research provides valuable insights into the design and development of advanced textile structures to improve wear comfort and protection in close-fitting apparel applications.

Artificial intelligence (AI) is revolutionizing the textile industry by improving the prediction of fabric properties and handfeel, which are essential for assessing textile quality and performance. However, the practical application and translation of AI-predicted results into real-world textile production remain unclear, posing challenges for widespread adoption. This paper systematically reviews AI-driven techniques for predicting these characteristics by focusing on model mechanisms, dataset diversity, and prediction accuracy. Among 811 papers initially identified, 26 were selected for in-depth analysis through both bibliometric and content analysis. The review categorizes and evaluates various AI approaches, including machine learning, deep learning, and hybrid models, across different types of fabric. Despite significant advances, challenges remain, such as ensuring model generalization and managing complex fabric behavior. Future research should focus on developing more robust models, integrating sustainability, and refining feature extraction techniques. This review highlights the critical gaps in the literature and provides practical insights to enhance AI-driven prediction of fabric properties, thus guiding future textile innovations.