Search results

Nowadays, artificial intelligence (AI) technology has demonstrated extensive applications in the field of art design. Attribute editing is an important means to realize clothing style and color design via computer language, which aims to edit and control the garment image based on the specified target attributes while preserving other details from the original image. The current image attribute editing model often generates images containing missing or redundant attributes. To address the problem, this paper aims for a novel design method utilizing the Fashion-attribute generative adversarial network (AttGAN) model was proposed for image attribute editing specifically tailored to women’s blouses.

The proposed design method primarily focuses on optimizing the feature extraction network and loss function. To enhance the feature extraction capability of the model, an increase in the number of layers in the feature extraction network was implemented, and the structure similarity index measure (SSIM) loss function was employed to ensure the independent attributes of the original image were consistent. The characteristic-preserving virtual try-on network (CP_VTON) dataset was used for train-ing to enable the editing of sleeve length and color specifically for women’s blouse.

The experimental results demonstrate that the optimization model’s generated outputs have significantly reduced problems related to missing attributes or visual redundancy. Through a comparative analysis of the numerical changes in the SSIM and peak signal-to-noise ratio (PSNR) before and after the model refinement, it was observed that the improved SSIM increased substantially by 27.4%, and the PSNR increased by 2.8%, serving as empirical evidence of the effectiveness of incorporating the SSIM loss function.

The proposed algorithm provides a promising tool for precise image editing of women’s blouses based on the GAN. This introduces a new approach to eliminate semantic expression errors in image editing, thereby contributing to the development of AI in clothing design.

This paper reviews the pros and cons of different parametric modeling methods, which can provide a theoretical reference for parametric reconstruction of 3D human body models for virtual fitting.

In this study, we briefly analyze the mainstream datasets of models of the human body used in the area to provide a foundation for parametric methods of such reconstruction. We then analyze and compare parametric methods of reconstruction based on their use of the following forms of input data: point cloud data, image contours, sizes of features and points representing the joints. Finally, we summarize the advantages and problems of each method as well as the current challenges to the use of parametric modeling in virtual fitting and the opportunities provided by it.

Considering the aspects of integrity and accurate of representations of the shape and posture of the body, and the efficiency of the calculation of the requisite parameters, the reconstruction method of human body by integrating orthogonal image contour morphological features, multifeature size constraints and joint point positioning can better represent human body shape, posture and personalized feature size and has higher research value.

This article obtains a research thinking for reconstructing a 3D model for virtual fitting that is based on three kinds of data, which is helpful for establishing personalized and high-precision human body models.

Spatial olfactory design in the library appears to be a practical approach to enhance the coordination between architectural spaces and user behaviors, shape immersive activity experiences and shape immersive activity experiences. Therefore, this study aims to explore the association between the olfactory elements of library space and users’ olfactory perception, providing a foundation for the practical design of olfactory space in libraries.

Using the olfactory perception semantic differential experiment method, this study collected feedback on the emotional experience of olfactory stimuli from 56 participants in an academic library. From the perspective of environmental psychology, the dimensions of pleasure, control and arousal of users’ olfactory perception in the academic library environment were semantically and emotionally described. In addition, the impact of fatigue state on users’ olfactory perception was analyzed through statistical methods to explore the impact path of individual physical differences on olfactory perception.

It was found that users’ olfactory perception in the academic library environment is likely semantically described from the dimensions of pleasure, arousal and control. These dimensions mutually influence users’ satisfaction with olfactory elements. Moreover, there is a close correlation between pleasure and satisfaction. In addition, fatigue states may impact users’ olfactory perception. Furthermore, users in a high-fatigue state may be more sensitive to the arousal of olfactory perception.

This article is an empirical exploration of users’ perception of the environmental odors in libraries. The experimental results of this paper may have practical implications for the construction of olfactory space in academic libraries.

This paper aims to propose the mechanism of cross-network effect embedded, which can help cross-border e-commerce (CBEC) platforms strengthen cooperative relationships with sellers more equitably and effectively by using the network structural characteristics of the platforms themselves.

A two-stage evolutionary game model has been used to confirm the influence factors. The mathematical derivation of evolutionary game analysis is combined with the simulation method to examine the role of cross-network effect in cooperation. The evolutionary game model based on the cross-network effect is proposed to achieve better adaptability to the study of cooperation strategy from the two-sided market perspective.

The evolutionary game model captures the interactions of cross-network effect and the influence factors from a dynamic perspective. The cross-network effect has a certain substitution on the revenue-sharing rate of SMEs. CBEC platforms can enhance the connection between consumers and the website by improving the level of construction, which is a good way to attract sellers more cost-effectively and efficiently.

This study provides a new method for the validation of the cross-network effect, especially when data collection is difficult. But this method is only a numerical simulation. So the conclusions still need to be further tested empirically. Besides, researchers are advised to explore the relationship between the added user scale and the cross-network effect in some specificCBEC platforms.

This study provides a new method for the validation of the cross-network effect, especially when data collection is difficult. But this method is only a numerical simulation. So the conclusions still need to be further tested empirically. Besides, researchers are advised to explore the relationship between the added user scale and the cross-network effect in some specific CBEC platforms.

Investigations that study cooperation strategy from the cross-network effect perspective in CBEC are limited. The research figured out which influence factors are affected by the cross-network effect in cooperation. A two-stage evolutionary game model was proposed to explain the interaction of the factors. The evolutionary game analysis with a simulation method was combined to highlight the role of cross-network effect on cooperation strategy to give a deeper investigation into the sustainable cooperation ofCBEC.

The objectives of this study are twofold: firstly, to examine the effect of job variety on employee engagement and job burnout, and the effect of employee engagement and job burnout on employee happiness and job stress, respectively. Secondly, it examines the mediating role of employee engagement between job variety and employee happiness, as well as the mediating role of job burnout between job variety and job stress.

Data were collected from front-line nurses working in the health sector in Pakistan's major cities. A total of 169 samples were collected using online and face-to-face data collection approaches. The theoretical model was tested using the Partial Least Squares Structural Equation Modeling (PLS-SEM) in SmartPLS 4.0.

The findings of this study highlight that job variety has a positive impact on employee engagement, which in turn leads to employee happiness among professional frontline nurses. Additionally, job variety as a demand increases employee burnout, which subsequently increases frontline nurses' job stress. The results also indicate that employee engagement mediates the relationship between job variety and employee happiness, while burnout mediates the relationship between job variety and job stress.

To date, there has been little research investigating the dual impact of job variety, leaving a significant gap in the existing literature. This study aims to address this gap and provide implications for both academics and HR managers by challenging the misconception that job variety is always a positive job resource.

Stock market has always been lucrative for various investors. But, because of its speculative nature, it is difficult to predict the price movement. Investors have been using both fundamental and technical analysis to predict the prices. Fundamental analysis helps to study structured data of the company. Technical analysis helps to study price trends, and with the increasing and easy availability of unstructured data have made it important to study the market sentiment. Market sentiment has a major impact on the prices in short run. Hence, the purpose is to understand the market sentiment timely and effectively.

The research includes text mining and then creating various models for classification. The accuracy of these models is checked using confusion matrix.

Out of the six machine learning techniques used to create the classification model, kernel support vector machine gave the highest accuracy of 68%. This model can be now used to analyse the tweets, news and various other unstructured data to predict the price movement.

This study will help investors classify a news or a tweet into “positive”, “negative” or “neutral” quickly and determine the stock price trends.

This paper aims to help higher education institutions (HEIs) develop a better understanding of student support and services needs, thereby enabling them to allocate limited resources for initiatives that effectively improve student experience.

An assessment framework following the Kano analysis is developed to categorize student service features based on customer satisfaction and need fulfillment. The framework is used at a local university, using 23 service features listed as minimum requirements by the national regulatory body for education. Analysis of the satisfaction survey results and prioritization are based on quality indices derived from a factor of importance and the satisfaction gap. A survey was conducted for two academic years to generate a comparison of results.

Of the list mandated as minimum requirements for HEIs, the study revealed that no features were regarded as “must-be,” eight as performing, 14 as attractive and one as indifferent by the students. As these results were disaggregated per year level, the natural decay of delight as in the Kano theory was exhibited as there were less attractive features for students who have been in the university longest. After a full-year academic cycle, results compared to the baseline figures seemed to reveal of impact of the achievement of performance targets by the units rendering specific activities on client satisfaction.

Further rounds of the study are needed to build up more data sets on the relationship between objective performance and satisfaction level for performing features, mindful that this categorization is also bound to change along the way.

As HEIs in the Philippines journey towards the establishment of their own respective internal quality assurance systems, this study provides a practical approach for institutions to transform a mere list of student services for compliance into a strategic tool to enhance the student experience.

In the context of continuous quality improvement, the study presents how the qualitative Kano model, along with simple quantitative tools in the methodology, can be utilized not only in the planning stage of service design but also in closing the planning, doing, checking and acting (PDCA) cycle and opening the quality improvement spiral.