AI Core

901 items

University of Twente Research Information Oct 1, 2026
Using the Multimodal Activity Sensing Dataset (MASD; 27 activities, 20 participants), the study tests whether ambient WiFi Channel State Information (CSI) can substitute for a body-worn inertial measurement unit (IMU) in human activity recognition; the authors find that the dataset's released machine-learning-ready files expose a degraded signed CSI representation rather than the documented amplitude, so they rebuild amplitude and antenna-ratio Doppler from the raw complex CSI, recover omitted participant identifiers, and re-evaluate subject-independently under a controlled multi-seed protocol, finding WiFi systematically weak: every backbone they try reaches only 6-11% weighted accuracy on the 27-class set against 73-80% for IMU, with usable accuracy on 0 of 27 activities; the corrected r
Using the Multimodal Activity Sensing Dataset (MASD; 27 activities, 20 participants), the study tests whether ambient WiFi Channel State Information (CSI) can substitute for a body-worn inertial measurement unit (IMU) in human activity recognition; the authors find that the dataset's released machine-learning-ready files expose a degraded signed CSI representation rather than the documented amplitude, so they rebuild amplitude and antenna-ratio Doppler from the raw complex CSI, recover omitted participant identifiers, and re-evaluate subject-independently under a controlled multi-seed protocol, finding WiFi systematically weak: every backbone they try reaches only 6-11% weighted accuracy on the 27-class set against 73-80% for IMU, with usable accuracy on 0 of 27 activities; the corrected r
WiFi CSI cannot substitute for wearable IMU: 6-11% weighted accuracy on 27 activities versus 73-80% for IMU
Using the Multimodal Activity Sensing Dataset (MASD; 27 activities, 20 participants), the study tests whether ambient WiFi Channel State Information (CSI) can substitute for a body-worn inertial measurement unit (IMU) in human activity recognition; the authors find that the dataset's released machine-learning-ready files expose a degraded signed CSI representation rather than the documented amplitude, so they rebuild amplitude and antenna-ratio Doppler from the raw complex CSI, recover omitted participant identifiers, and re-evaluate subject-independently under a controlled multi-seed protocol, finding WiFi systematically weak: every backbone they try reaches only 6-11% weighted accuracy on the 27-class set against 73-80% for IMU, with usable accuracy on 0 of 27 activities; the corrected r
Using the Multimodal Activity Sensing Dataset (MASD; 27 activities, 20 participants), the study tests whether ambient WiFi Channel State Information (CSI) can substitute for a body-worn inertial measurement unit (IMU) in human activity recognition; the authors find that the dataset's released machine-learning-ready files expose a degraded signed CSI representation rather than the documented amplitude, so they rebuild amplitude and antenna-ratio Doppler from the raw complex CSI, recover omitted participant identifiers, and re-evaluate subject-independently under a controlled multi-seed protocol, finding WiFi systematically weak: every backbone they try reaches only 6-11% weighted accuracy on the 27-class set against 73-80% for IMU, with usable accuracy on 0 of 27 activities; the corrected r
Retina Oct 1, 2026
The study pretrained StyleGAN3 and Medfusion on an auxiliary dataset, curated synthetic images through a domain-matched Oracle network using Latent Space Rejection Sampling and Class-Conditioned SDEdit Escalation, and evaluated downstream grading on the Indian DR Image Dataset across ConvNeXt, ResNet50, and VGG16 with five random seeds, finding that a real-data-only ConvNeXt baseline reached a quadratic weighted kappa of 0.6350 ± 0.0135, curated StyleGAN3 augmentation raised it to 0.7185 ± 0.0309, Medfusion augmentation reached 0.7695 ± 0.0254 (an absolute improvement of 0.1345), and Medfusion doubled proliferative DR recall from 0.2615 ± 0.1595 to 0.5385 ± 0.0942.
The study pretrained StyleGAN3 and Medfusion on an auxiliary dataset, curated synthetic images through a domain-matched Oracle network using Latent Space Rejection Sampling and Class-Conditioned SDEdit Escalation, and evaluated downstream grading on the Indian DR Image Dataset across ConvNeXt, ResNet50, and VGG16 with five random seeds, finding that a real-data-only ConvNeXt baseline reached a quadratic weighted kappa of 0.6350 ± 0.0135, curated StyleGAN3 augmentation raised it to 0.7185 ± 0.0309, Medfusion augmentation reached 0.7695 ± 0.0254 (an absolute improvement of 0.1345), and Medfusion doubled proliferative DR recall from 0.2615 ± 0.1595 to 0.5385 ± 0.0942.
Oracle-curated synthetic fundus images lift ConvNeXt diabetic retinopathy grading kappa from 0.6350 to 0.7695 and double proliferative DR recall
The study pretrained StyleGAN3 and Medfusion on an auxiliary dataset, curated synthetic images through a domain-matched Oracle network using Latent Space Rejection Sampling and Class-Conditioned SDEdit Escalation, and evaluated downstream grading on the Indian DR Image Dataset across ConvNeXt, ResNet50, and VGG16 with five random seeds, finding that a real-data-only ConvNeXt baseline reached a quadratic weighted kappa of 0.6350 ± 0.0135, curated StyleGAN3 augmentation raised it to 0.7185 ± 0.0309, Medfusion augmentation reached 0.7695 ± 0.0254 (an absolute improvement of 0.1345), and Medfusion doubled proliferative DR recall from 0.2615 ± 0.1595 to 0.5385 ± 0.0942.
The study pretrained StyleGAN3 and Medfusion on an auxiliary dataset, curated synthetic images through a domain-matched Oracle network using Latent Space Rejection Sampling and Class-Conditioned SDEdit Escalation, and evaluated downstream grading on the Indian DR Image Dataset across ConvNeXt, ResNet50, and VGG16 with five random seeds, finding that a real-data-only ConvNeXt baseline reached a quadratic weighted kappa of 0.6350 ± 0.0135, curated StyleGAN3 augmentation raised it to 0.7185 ± 0.0309, Medfusion augmentation reached 0.7695 ± 0.0254 (an absolute improvement of 0.1345), and Medfusion doubled proliferative DR recall from 0.2615 ± 0.1595 to 0.5385 ± 0.0942.
Urogynecology Oct 1, 2026
In this cross-sectional study, six urogynecologists developed six questions comparing two treatment options for common urogynecological conditions and entered them into ChatGPT to create decision aid tools; patients and physicians then rated understandability with a Patient Education Materials Assessment Tool, physicians rated reliability with a modified DISCERN instrument and accuracy on a 5-point Likert scale, and readability was assessed with the Flesch-Kincaid Reading Ease score, showing high patient and physician understandability for all tools, fair reliability with an average mDISCERN score of 26, accuracy below 4 (unfavorable) on 2 of the tools, and a high reading level required overall.
In this cross-sectional study, six urogynecologists developed six questions comparing two treatment options for common urogynecological conditions and entered them into ChatGPT to create decision aid tools; patients and physicians then rated understandability with a Patient Education Materials Assessment Tool, physicians rated reliability with a modified DISCERN instrument and accuracy on a 5-point Likert scale, and readability was assessed with the Flesch-Kincaid Reading Ease score, showing high patient and physician understandability for all tools, fair reliability with an average mDISCERN score of 26, accuracy below 4 (unfavorable) on 2 of the tools, and a high reading level required overall.
ChatGPT-generated surgical decision aids for pelvic floor disorders had high patient understandability, but about 30% of topics fell short on accuracy and overall readability was high
In this cross-sectional study, six urogynecologists developed six questions comparing two treatment options for common urogynecological conditions and entered them into ChatGPT to create decision aid tools; patients and physicians then rated understandability with a Patient Education Materials Assessment Tool, physicians rated reliability with a modified DISCERN instrument and accuracy on a 5-point Likert scale, and readability was assessed with the Flesch-Kincaid Reading Ease score, showing high patient and physician understandability for all tools, fair reliability with an average mDISCERN score of 26, accuracy below 4 (unfavorable) on 2 of the tools, and a high reading level required overall.
In this cross-sectional study, six urogynecologists developed six questions comparing two treatment options for common urogynecological conditions and entered them into ChatGPT to create decision aid tools; patients and physicians then rated understandability with a Patient Education Materials Assessment Tool, physicians rated reliability with a modified DISCERN instrument and accuracy on a 5-point Likert scale, and readability was assessed with the Flesch-Kincaid Reading Ease score, showing high patient and physician understandability for all tools, fair reliability with an average mDISCERN score of 26, accuracy below 4 (unfavorable) on 2 of the tools, and a high reading level required overall.
British Journal of Radiology Oct 1, 2026
This review surveys recent advances in coronary CT angiography (CCTA) for coronary artery disease: AI-driven plaque and stenosis quantification can cut analysis time from over 25 minutes to typically under 60 seconds per case with correlation coefficients of 0.92-0.95 against intravascular ultrasound, photon-counting detector CT (PCD-CT) reduces calcium blooming at ultra-high resolution and reclassifies some cases to lower CAD-RADS categories, and FFR-CT adds noninvasive lesion-specific physiologic assessment, so that combining the three can support more refined risk stratification for major adverse cardiovascular events and preventive therapy decisions.
This review surveys recent advances in coronary CT angiography (CCTA) for coronary artery disease: AI-driven plaque and stenosis quantification can cut analysis time from over 25 minutes to typically under 60 seconds per case with correlation coefficients of 0.92-0.95 against intravascular ultrasound, photon-counting detector CT (PCD-CT) reduces calcium blooming at ultra-high resolution and reclassifies some cases to lower CAD-RADS categories, and FFR-CT adds noninvasive lesion-specific physiologic assessment, so that combining the three can support more refined risk stratification for major adverse cardiovascular events and preventive therapy decisions.
Integrating AI quantitative CT, photon-counting CT, and FFR-CT brings coronary plaque burden and ischemia assessment into one CCTA workflow
This review surveys recent advances in coronary CT angiography (CCTA) for coronary artery disease: AI-driven plaque and stenosis quantification can cut analysis time from over 25 minutes to typically under 60 seconds per case with correlation coefficients of 0.92-0.95 against intravascular ultrasound, photon-counting detector CT (PCD-CT) reduces calcium blooming at ultra-high resolution and reclassifies some cases to lower CAD-RADS categories, and FFR-CT adds noninvasive lesion-specific physiologic assessment, so that combining the three can support more refined risk stratification for major adverse cardiovascular events and preventive therapy decisions.
This review surveys recent advances in coronary CT angiography (CCTA) for coronary artery disease: AI-driven plaque and stenosis quantification can cut analysis time from over 25 minutes to typically under 60 seconds per case with correlation coefficients of 0.92-0.95 against intravascular ultrasound, photon-counting detector CT (PCD-CT) reduces calcium blooming at ultra-high resolution and reclassifies some cases to lower CAD-RADS categories, and FFR-CT adds noninvasive lesion-specific physiologic assessment, so that combining the three can support more refined risk stratification for major adverse cardiovascular events and preventive therapy decisions.
SMU Scholar (Southern Methodist University) Oct 1, 2026
This dissertation integrates multimodal retinal imaging, including fundus photography, OCT, and OCTA, to build a suite of deep learning frameworks spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models for detecting early glaucomatous changes with high precision, robustness, and interpretability, and contributes several curated datasets including GSS-RetVein as standardized benchmarks for cross-domain validation, reporting that the proposed models outperform existing state-of-the-art approaches across multiple public and clinical datasets with marked improvements in diagnostic sensitivity and specificity.
This dissertation integrates multimodal retinal imaging, including fundus photography, OCT, and OCTA, to build a suite of deep learning frameworks spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models for detecting early glaucomatous changes with high precision, robustness, and interpretability, and contributes several curated datasets including GSS-RetVein as standardized benchmarks for cross-domain validation, reporting that the proposed models outperform existing state-of-the-art approaches across multiple public and clinical datasets with marked improvements in diagnostic sensitivity and specificity.
Huang Cheng's dissertation proposes a multimodal retinal AI framework for glaucoma and contributes datasets including GSS-RetVein
This dissertation integrates multimodal retinal imaging, including fundus photography, OCT, and OCTA, to build a suite of deep learning frameworks spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models for detecting early glaucomatous changes with high precision, robustness, and interpretability, and contributes several curated datasets including GSS-RetVein as standardized benchmarks for cross-domain validation, reporting that the proposed models outperform existing state-of-the-art approaches across multiple public and clinical datasets with marked improvements in diagnostic sensitivity and specificity.
This dissertation integrates multimodal retinal imaging, including fundus photography, OCT, and OCTA, to build a suite of deep learning frameworks spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models for detecting early glaucomatous changes with high precision, robustness, and interpretability, and contributes several curated datasets including GSS-RetVein as standardized benchmarks for cross-domain validation, reporting that the proposed models outperform existing state-of-the-art approaches across multiple public and clinical datasets with marked improvements in diagnostic sensitivity and specificity.
发表出处待核验 Oct 1, 2026
Using 178 thermograms from 98 patients with complex regional pain syndrome (CRPS) and 837 thermograms from 56 healthy controls, the study used a U-Net deep learning model to segment extremities automatically (mean Dice similarity coefficient 0.99), extracted 564 radiomics features per extremity per thermogram (intensity, shape, texture), and built a classification model with the WORC automated machine learning framework under 20x random-split cross-validation; the model distinguished CRPS from healthy control thermograms with a mean AUC of 0.93 (95% CI 0.90-0.97), statistically significantly better than three clinicians' 0.82, 0.79, and 0.69 (P < 0.001).
Using 178 thermograms from 98 patients with complex regional pain syndrome (CRPS) and 837 thermograms from 56 healthy controls, the study used a U-Net deep learning model to segment extremities automatically (mean Dice similarity coefficient 0.99), extracted 564 radiomics features per extremity per thermogram (intensity, shape, texture), and built a classification model with the WORC automated machine learning framework under 20x random-split cross-validation; the model distinguished CRPS from healthy control thermograms with a mean AUC of 0.93 (95% CI 0.90-0.97), statistically significantly better than three clinicians' 0.82, 0.79, and 0.69 (P < 0.001).
A radiomics model automatically separated thermograms of 98 CRPS patients from 56 healthy controls with AUC 0.93, outperforming three clinicians
Using 178 thermograms from 98 patients with complex regional pain syndrome (CRPS) and 837 thermograms from 56 healthy controls, the study used a U-Net deep learning model to segment extremities automatically (mean Dice similarity coefficient 0.99), extracted 564 radiomics features per extremity per thermogram (intensity, shape, texture), and built a classification model with the WORC automated machine learning framework under 20x random-split cross-validation; the model distinguished CRPS from healthy control thermograms with a mean AUC of 0.93 (95% CI 0.90-0.97), statistically significantly better than three clinicians' 0.82, 0.79, and 0.69 (P < 0.001).
Using 178 thermograms from 98 patients with complex regional pain syndrome (CRPS) and 837 thermograms from 56 healthy controls, the study used a U-Net deep learning model to segment extremities automatically (mean Dice similarity coefficient 0.99), extracted 564 radiomics features per extremity per thermogram (intensity, shape, texture), and built a classification model with the WORC automated machine learning framework under 20x random-split cross-validation; the model distinguished CRPS from healthy control thermograms with a mean AUC of 0.93 (95% CI 0.90-0.97), statistically significantly better than three clinicians' 0.82, 0.79, and 0.69 (P < 0.001).
Archivos Argentinos de Pediatria Oct 1, 2026
Using 1312 photographs of infant stool in diapers (1100 meeting quality criteria, of which 896 had majority agreement among three pediatric gastroenterologists as the reference set), the study trained 20 convolutional neural network models on Teachable Machine with an 85/15 training and internal-validation split and assessed agreement with specialists on the BITSS: the best seven-category model reached overall accuracy 0.56 with linear and quadratic weighted Kappa of 0.59 and 0.75, while a four-category grouping (constipated, formed, soft, liquid) reached accuracy 0.76 with weighted Kappa of 0.69 and 0.78, whereas agreement among the three specialists showed a Fleiss Kappa of only 0.24 and 24.7% complete agreement.
Using 1312 photographs of infant stool in diapers (1100 meeting quality criteria, of which 896 had majority agreement among three pediatric gastroenterologists as the reference set), the study trained 20 convolutional neural network models on Teachable Machine with an 85/15 training and internal-validation split and assessed agreement with specialists on the BITSS: the best seven-category model reached overall accuracy 0.56 with linear and quadratic weighted Kappa of 0.59 and 0.75, while a four-category grouping (constipated, formed, soft, liquid) reached accuracy 0.76 with weighted Kappa of 0.69 and 0.78, whereas agreement among the three specialists showed a Fleiss Kappa of only 0.24 and 24.7% complete agreement.
AI model reached only 0.56 accuracy on seven-category BITSS infant stool grading, rising to 0.76 when collapsed to four groups
Using 1312 photographs of infant stool in diapers (1100 meeting quality criteria, of which 896 had majority agreement among three pediatric gastroenterologists as the reference set), the study trained 20 convolutional neural network models on Teachable Machine with an 85/15 training and internal-validation split and assessed agreement with specialists on the BITSS: the best seven-category model reached overall accuracy 0.56 with linear and quadratic weighted Kappa of 0.59 and 0.75, while a four-category grouping (constipated, formed, soft, liquid) reached accuracy 0.76 with weighted Kappa of 0.69 and 0.78, whereas agreement among the three specialists showed a Fleiss Kappa of only 0.24 and 24.7% complete agreement.
Using 1312 photographs of infant stool in diapers (1100 meeting quality criteria, of which 896 had majority agreement among three pediatric gastroenterologists as the reference set), the study trained 20 convolutional neural network models on Teachable Machine with an 85/15 training and internal-validation split and assessed agreement with specialists on the BITSS: the best seven-category model reached overall accuracy 0.56 with linear and quadratic weighted Kappa of 0.59 and 0.75, while a four-category grouping (constipated, formed, soft, liquid) reached accuracy 0.76 with weighted Kappa of 0.69 and 0.78, whereas agreement among the three specialists showed a Fleiss Kappa of only 0.24 and 24.7% complete agreement.
DOAJ (DOAJ: Directory of Open Access Journals) Oct 1, 2026
Targeting problems AIGC exposes in footwear design such as generation homogeneity, low process feasibility, and disconnection from market demand, the study follows a path of theoretical analysis, technology construction, system verification, and method refinement: it reviews application status and bottlenecks through literature analysis and a questionnaire survey, extracts labels with a code detection algorithm and builds a footwear generation model on a diffusion architecture combined with LoRA, integrates core data such as materials, processes, soles, and lasts into a structured and correlated digital asset library, and forms a planning-AI creator-craftsman collaborative group for multi-end review and a marketing and data feedback loop, thereby constructing an intelligent auxiliary footw
Targeting problems AIGC exposes in footwear design such as generation homogeneity, low process feasibility, and disconnection from market demand, the study follows a path of theoretical analysis, technology construction, system verification, and method refinement: it reviews application status and bottlenecks through literature analysis and a questionnaire survey, extracts labels with a code detection algorithm and builds a footwear generation model on a diffusion architecture combined with LoRA, integrates core data such as materials, processes, soles, and lasts into a structured and correlated digital asset library, and forms a planning-AI creator-craftsman collaborative group for multi-end review and a marketing and data feedback loop, thereby constructing an intelligent auxiliary footw
Study builds a footwear generation model with diffusion plus LoRA and turns shoe design from a linear flow into a data-insight-to-dynamic-optimization loop
Targeting problems AIGC exposes in footwear design such as generation homogeneity, low process feasibility, and disconnection from market demand, the study follows a path of theoretical analysis, technology construction, system verification, and method refinement: it reviews application status and bottlenecks through literature analysis and a questionnaire survey, extracts labels with a code detection algorithm and builds a footwear generation model on a diffusion architecture combined with LoRA, integrates core data such as materials, processes, soles, and lasts into a structured and correlated digital asset library, and forms a planning-AI creator-craftsman collaborative group for multi-end review and a marketing and data feedback loop, thereby constructing an intelligent auxiliary footw
Targeting problems AIGC exposes in footwear design such as generation homogeneity, low process feasibility, and disconnection from market demand, the study follows a path of theoretical analysis, technology construction, system verification, and method refinement: it reviews application status and bottlenecks through literature analysis and a questionnaire survey, extracts labels with a code detection algorithm and builds a footwear generation model on a diffusion architecture combined with LoRA, integrates core data such as materials, processes, soles, and lasts into a structured and correlated digital asset library, and forms a planning-AI creator-craftsman collaborative group for multi-end review and a marketing and data feedback loop, thereby constructing an intelligent auxiliary footw
Journal of Cataract & Refractive Surgery Oct 1, 2026
This two-center clinical validation study recruited 127 individuals with different severities of nuclear cataract from Thailand (n = 81) and Shenzhen, China (n = 46), imaged them with AS-OCT and graded images under the LOCS III standard, developed automated machine learning models to extract nuclear region annotation and analyzed feature-based quantifiers, finding that pixel-based features such as mean, variance, root mean square, interquartile range, and percentiles significantly correlate with NC grading (P < .01), that variance, standard deviation, and median showed high consistency while kurtosis and skewness were negatively correlated, and that the prediction model achieved 0.81 accuracy at the SZRM center (F1 0.82) and 0.87 at the Thai center (F1 0.
This two-center clinical validation study recruited 127 individuals with different severities of nuclear cataract from Thailand (n = 81) and Shenzhen, China (n = 46), imaged them with AS-OCT and graded images under the LOCS III standard, developed automated machine learning models to extract nuclear region annotation and analyzed feature-based quantifiers, finding that pixel-based features such as mean, variance, root mean square, interquartile range, and percentiles significantly correlate with NC grading (P < .01), that variance, standard deviation, and median showed high consistency while kurtosis and skewness were negatively correlated, and that the prediction model achieved 0.81 accuracy at the SZRM center (F1 0.82) and 0.87 at the Thai center (F1 0.
Two-center study of 127 nuclear cataract cases: AS-OCT image features correlate with LOCS III grading, with automated grading accuracy of 0.81 and 0.87
This two-center clinical validation study recruited 127 individuals with different severities of nuclear cataract from Thailand (n = 81) and Shenzhen, China (n = 46), imaged them with AS-OCT and graded images under the LOCS III standard, developed automated machine learning models to extract nuclear region annotation and analyzed feature-based quantifiers, finding that pixel-based features such as mean, variance, root mean square, interquartile range, and percentiles significantly correlate with NC grading (P < .01), that variance, standard deviation, and median showed high consistency while kurtosis and skewness were negatively correlated, and that the prediction model achieved 0.81 accuracy at the SZRM center (F1 0.82) and 0.87 at the Thai center (F1 0.
This two-center clinical validation study recruited 127 individuals with different severities of nuclear cataract from Thailand (n = 81) and Shenzhen, China (n = 46), imaged them with AS-OCT and graded images under the LOCS III standard, developed automated machine learning models to extract nuclear region annotation and analyzed feature-based quantifiers, finding that pixel-based features such as mean, variance, root mean square, interquartile range, and percentiles significantly correlate with NC grading (P < .01), that variance, standard deviation, and median showed high consistency while kurtosis and skewness were negatively correlated, and that the prediction model achieved 0.81 accuracy at the SZRM center (F1 0.82) and 0.87 at the Thai center (F1 0.
DOAJ (DOAJ: Directory of Open Access Journals) Oct 1, 2026
Framed by the Technology Acceptance Model (TAM), this study treats perceived ease of use and perceived usefulness as mediators and, following Williams' creativity theory, divides professional creativity into curiosity, imagination, risk-taking, and challenge; using a structured questionnaire with leather product designers and testing via confirmatory factor analysis and structural equation modeling, it finds that AI application has a significant positive influence on all four creativity dimensions, that both perceived ease of use and perceived usefulness significantly mediate the curiosity, imagination, and challenge dimensions, and that for risk-taking only perceived ease of use is a significant mediator while the effect of perceived usefulness is not statistically significant.
Framed by the Technology Acceptance Model (TAM), this study treats perceived ease of use and perceived usefulness as mediators and, following Williams' creativity theory, divides professional creativity into curiosity, imagination, risk-taking, and challenge; using a structured questionnaire with leather product designers and testing via confirmatory factor analysis and structural equation modeling, it finds that AI application has a significant positive influence on all four creativity dimensions, that both perceived ease of use and perceived usefulness significantly mediate the curiosity, imagination, and challenge dimensions, and that for risk-taking only perceived ease of use is a significant mediator while the effect of perceived usefulness is not statistically significant.
A TAM-based survey and structural equation model show that AI application significantly and positively affects leather product designers' curiosity, imagination, risk-taking, and challenge, while perceived usefulness does not significantly mediate the risk-taking dimension.
Framed by the Technology Acceptance Model (TAM), this study treats perceived ease of use and perceived usefulness as mediators and, following Williams' creativity theory, divides professional creativity into curiosity, imagination, risk-taking, and challenge; using a structured questionnaire with leather product designers and testing via confirmatory factor analysis and structural equation modeling, it finds that AI application has a significant positive influence on all four creativity dimensions, that both perceived ease of use and perceived usefulness significantly mediate the curiosity, imagination, and challenge dimensions, and that for risk-taking only perceived ease of use is a significant mediator while the effect of perceived usefulness is not statistically significant.
Framed by the Technology Acceptance Model (TAM), this study treats perceived ease of use and perceived usefulness as mediators and, following Williams' creativity theory, divides professional creativity into curiosity, imagination, risk-taking, and challenge; using a structured questionnaire with leather product designers and testing via confirmatory factor analysis and structural equation modeling, it finds that AI application has a significant positive influence on all four creativity dimensions, that both perceived ease of use and perceived usefulness significantly mediate the curiosity, imagination, and challenge dimensions, and that for risk-taking only perceived ease of use is a significant mediator while the effect of perceived usefulness is not statistically significant.

Page 2 · showing 10