Search results

This paper aims to identify a suitable convolutional neural network (CNN) model to analyse where void(s) are formed in asymmetrical flip-chips with large amounts of the ball-grid array (BGA) during underfilling.

A set of void(s)-filled through-scan acoustic microscope (TSAM) images of BGA underfill is collected, labelled and used to train two CNN models (You Look Only Once version 5 (YOLOv5) and Mask RCNN). Otsu's thresholding method is used to calculate the void percentage, and the model's performance in generating the results with its accuracy relative to real-scale images is evaluated.

All discoveries were authenticated concerning previous studies on CNN model development to encapsulate the shape of the void detected combined with calculating the percentage. The Mask RCNN is the most suitable model to perform the image segmentation analysis, and it closely matches the void presence in the TSAM image samples up to an accuracy of 94.25% of the entire void region. The model's overall accuracy of RCNN is 96.40%, and it can display the void percentage by 2.65 s on average, faster than the manual checking process by 96.50%.

The study enabled manufacturers to produce a feasible, automated means to improve their flip-chip underfilling production quality control. Leveraging an optimised CNN model enables an expedited manufacturing process that will reduce lead costs.

BGA void formation in a flip-chip underfilling process can be captured quantitatively with advanced image segmentation.

The purpose of this study is to investigate the role of using augmented reality (AR) in the form of virtual try-on technology in consumers' purchase decision-making process.

The study, executed in a beauty industry context, uses the value-based adoption model (VAM). Data were collected by means of a survey carried out on 238 Tunisian women. Subjects performed an experimental task using the virtual try-on (VTO) application in the L’Oréal website. Web-administered questionnaires were used to collect the data, which was processed using an exploratory factor analysis and partial least squares structural equation modeling.

The findings shows that perceived value is positively related to purchase intentions and it was affected by both perceived benefits and perceived costs. In particular, perceived benefit (perceived usefulness) was found to have a strong positive effect on perceived value. Moreover, it turns out that perceived enjoyment does not have a significant effect on the perceived value. In terms of perceived costs, perceived intrusiveness was found to limit perceived value. The results also show a significant relationship between AR characteristics and perceived benefits. For personal traits, personal innovativeness is found positively influencing perceived usefulness, but it shows no significant effect on perceived enjoyment.

Companies should highlight the benefits for consumers (interactivity, informativeness and usefulness) and attempt to reduce the costs (intrusiveness) related to the use of VTO AR technology, which can play a substantial role in determining the perceived value and purchase intentions.

The existent literature, which examines the AR in e-tailing, shows weak acknowledgment of theories related to consumer barriers to AR adoption in e-tailing, they overlook the role of consumer psychology and individual differences in AR acceptance. Thus, this study contributes to the literature by enhancing the understanding of the roles that AR based VTO technology plays in determining consumers’ online purchase intentions by extending the application of perceived value theory and taking into account its characteristics and personal traits that play a role in weakening or strengthening the customer's benefits and cost perceptions.