Search results

Diagnosing brain tumors is a process that demands a significant amount of time and is heavily dependent on the proficiency and accumulated knowledge of radiologists. Over the traditional methods, deep learning approaches have gained popularity in automating the diagnosis of brain tumors, offering the potential for more accurate and efficient results. Notably, attention-based models have emerged as an advanced, dynamically refining and amplifying model feature to further elevate diagnostic capabilities. However, the specific impact of using channel, spatial or combined attention methods of the convolutional block attention module (CBAM) for brain tumor classification has not been fully investigated.

To selectively emphasize relevant features while suppressing noise, ResNet50 coupled with the CBAM (ResNet50-CBAM) was used for the classification of brain tumors in this research.

The ResNet50-CBAM outperformed existing deep learning classification methods like convolutional neural network (CNN), ResNet-CBAM achieved a superior performance of 99.43%, 99.01%, 98.7% and 99.25% in accuracy, recall, precision and AUC, respectively, when compared to the existing classification methods using the same dataset.

Since ResNet-CBAM fusion can capture the spatial context while enhancing feature representation, it can be integrated into the brain classification software platforms for physicians toward enhanced clinical decision-making and improved brain tumor classification.

This research has not been published anywhere else.

Developed countries control pandemics using smart decisions and processes based on medical standards and modern technologies. Studies on risk-reduction and humantechnology interaction are scarce. This study developed a model to examine the relationship between citizens, pandemic-related technology and official safety practices.

This study investigated the mediating role of new health regulations and moderating role of safety incentives due to COVID-19 case reduction in pandemic severity control. This study included 407 operations managers, nursing staff conducting pandemic testing and reporting, doctors and security personnel in China. An artificial neural network (ANN) was used to check nonlinear regressions and model predictability.

The results demonstrated the impact of the introduction of new technology protocols on the implementation of new health regulations and aided pandemic severity control. The safety incentive of case reductions moderated the relationship between new health regulations and pandemic severity control. New health regulations mediated the relationship between the introduction of new technology protocols and pandemic severity control.

Further research should be conducted on pandemic severity in diversely populated cities, particularly those that require safety measures and controls. Future studies should focus on cloud computing for nurses, busy campuses and communal living spaces.

Authorities should involve citizens in pandemic-related technical advances to reduce local viral transmission and infection. New health regulations improved people's interactions with new technological protocols and understanding of pandemic severity. Pandemic management authorities should work with medical and security employees.

This study is the first to demonstrate that a safety framework with technology-oriented techniques could reduce future pandemics using managerial initiatives.

Good abandonment behavior refers to users obtaining direct answers via search engine results pages (SERPs) without clicking any search result, which occurs commonly in mobile search. This study aims to better understand users' good abandonment behavior and perception, and then construct a good abandonment prediction model for mobile search with improved performance.

In this study, an in situ user mobile search experiment (N = 43) and a crowdsourcing survey (N = 1,379) were conducted. Good abandonment behavior was analyzed from a quantitative perspective, exploring users' search behavior characteristics from four aspects: session and query, SERPs, gestures and eye-tracking data.

Users show less engagement with SERPs in good abandonment, spending less time and using fewer gestures, and they pay more visual attention to answer-like results. It was also found that good abandonment behavior is often related to users' perceived difficulty of the searching tasks and trustworthiness in the search engine. A good abandonment prediction model in mobile search was constructed with a high accuracy (97.14%).

This study is the first to explore eye-tracking characteristics of users' good abandonment behavior in mobile search, and to explore users' perception of their good abandonment behavior. Visual attention features are introduced into good abandonment prediction in mobile search for the first time and proved to be important predictors in the proposed model.

Based on sensory marketing theory and cognitive appraisal theory, this study investigates whether and how the background visual complexity of live-streaming affects consumers' purchase intention and reveals the underlying mechanisms through which background visual complexity influences consumers' purchase decisions.

The experiment was conducted with 180 college students, using eye-tracking technology to explore the impact mechanism of live background visual complexity on consumers' purchase intention, considering three types of background visual complexity (high vs medium vs low) and two levels of need for cognitive closure (high vs low).

Firstly, the background visual complexity of live-streaming positively influences consumers' purchase intention by eliciting positive emotions (pleasure and arousal), and the relationship between consumer emotions and purchase intention is nonlinear. Secondly, need for cognitive closure to significantly moderate the influence of background visual complexity on purchase intention.

The limited sample size makes it difficult to generalize to other consumer groups. Also, the study only focuses on one visual factor, lacking comprehensive analysis from multiple perspectives.

It is recommended that live e-commerce companies optimize the visual design of live-streaming backgrounds and identify consumer traits to match the visual complexity with consumers' level of need for cognitive closure, thereby stimulating positive emotions and facilitating more satisfactory shopping decisions.

This paper addresses an interesting and practical issue related to the effects of live background visual complexity on consumers' purchase intention.

The purpose of this study is to investigate and demonstrate the advancements achieved in the field of chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Typical convolutional neural networks (CNNs) are unable to capture both local and global contextual information effectively and apply a uniform operation to all pixels in an image. To address this, we propose an innovative approach that integrates a dynamic convolution operation at the encoder stage, improving image encoding quality and disease detection. In addition, a decoder based on the gated recurrent unit (GRU) is used for language modeling, and an attention network is incorporated to enhance consistency. This novel combination allows for improved feature extraction, mimicking the expertise of radiologists by selectively focusing on important areas and producing coherent captions with valuable clinical information.

In this study, we have presented a new report generation approach that utilizes dynamic convolution applied Resnet-101 (DyCNN) as an encoder (Verelst and Tuytelaars, 2019) and GRU as a decoder (Dey and Salemt, 2017; Pan et al., 2020), along with an attention network (see Figure 1). This integration innovatively extends the capabilities of image encoding and sequential caption generation, representing a shift from conventional CNN architectures. With its ability to dynamically adapt receptive fields, the DyCNN excels at capturing features of varying scales within the CXR images. This dynamic adaptability significantly enhances the granularity of feature extraction, enabling precise representation of localized abnormalities and structural intricacies. By incorporating this flexibility into the encoding process, our model can distil meaningful and contextually rich features from the radiographic data. While the attention mechanism enables the model to selectively focus on different regions of the image during caption generation. The attention mechanism enhances the report generation process by allowing the model to assign different importance weights to different regions of the image, mimicking human perception. In parallel, the GRU-based decoder adds a critical dimension to the process by ensuring a smooth, sequential generation of captions.

The findings of this study highlight the significant advancements achieved in chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Experiments conducted using the IU-Chest X-ray datasets showed that the proposed model outperformed other state-of-the-art approaches. The model achieved notable scores, including a BLEU_1 score of 0.591, a BLEU_2 score of 0.347, a BLEU_3 score of 0.277 and a BLEU_4 score of 0.155. These results highlight the efficiency and efficacy of the model in producing precise radiology reports, enhancing image interpretation and clinical decision-making.

This work is the first of its kind, which employs DyCNN as an encoder to extract features from CXR images. In addition, GRU as the decoder for language modeling was utilized and the attention mechanisms into the model architecture were incorporated.

This study aims to explore image-based visual price determinants (image features and visual aesthetic perception) and how image features affect Airbnb listing price on a sharing accommodation platform.

The study uses an SOR model and a hedonic price model to examine the connections between the characteristics of image features, visual aesthetic perception and Airbnb listing prices. The model is then examined by an econometric model using data from Insideairbnb.com.

Empirical results revealed that image features have a significant positive effect on visual aesthetic perception, visual aesthetic perception has a significant positive effect on Airbnb listing price and visual aesthetic perception has a significant mediating effect between image features and Airbnb listing price.

This study contributes to the relationship and effect mechanism among image features, visual aesthetic perception and Airbnb listing price and has some implications for both property operators and the sharing accommodation platform.

本研究探讨了基于图像的视觉价格决定因素（图像特征和视觉美学感知）以及图像特征如何影响共享住宿平台Airbnb价格。

本研究采用SOR模型和hedonic价格模型来检验图像特征特征、视觉美感与Airbnb房源价格之间的关系。然后使用Insideairbnb.com上的数据, 通过计量经济学模型对该模型进行检验。

实证结果显示：1）图像特征对视觉美学感知有显著的正向影响; 2）视觉美学感知对Airbnb价格有显著的正向影响; 3）视觉美学感知在图像特征和Airbnb价格之间有显著的中介效应。

本研究有助于探讨图像特征、视觉美学感知和Airbnb价格之间的关系和影响机制, 对房源经营者和共享住宿平台都有一定的借鉴意义。

Este estudio explora los determinantes visuales del precio basados en las imágenes (características de las imágenes y percepción estética visual) y cómo afectan las características de las imágenes al precio de los anuncios de Airbnb en una plataforma de alojamiento compartido.

El estudio emplea un modelo SOR y un modelo de precios hedónicos para examinar las conexiones entre las características de los rasgos de la imagen, la percepción estética visual y los precios de Airbnb. A continuación, se examina el modelo mediante un modelo econométrico utilizando datos de Insideairbnb.com.

Los resultados empíricos revelan que 1) las características de la imagen tienen un efecto positivo significativo sobre la percepción estética visual, 2) la percepción estética visual tiene un efecto positivo significativo sobre el precio de los anuncios de Airbnb, y 3) la percepción estética visual tiene un efecto mediador significativo entre las características de la imagen y el precio de los anuncios de Airbnb.

Este estudio contribuye al mecanismo de relación y efecto entre las características de la imagen, la percepción estética visual y el precio del anuncio de Airbnb, y tiene algunas implicaciones tanto para los operadores inmobiliarios como para la plataforma de alojamiento compartido.

While prior studies have explored the relationship between visual appeal and purchasing decisions, the role of bookmarking has largely been underemphasized. This research aims to address this gap by focusing on the impact of bookmarking on consumer behavior, guided by the cognitive load theory and dual-system theory.

The authors executed a controlled experiment and analyzed the results using a two-stage regression method that linked visual appeal, bookmarking and purchase intent. Further empirical analysis was conducted to authenticate the authors' proposed model, utilizing real-world mobile commerce data from a clothing company.

This study's findings suggest that visual appeal influences purchase intent primarily through the full mediation of bookmarking, rather than exerting a direct influence. Furthermore, an increase in colorfulness corresponds positively with visual appeal, while visual complexity exhibits an inverted U-shaped relationship with it.

This study provides novel insights into the choice-set formation process through the theoretical lens of dual-system theory. Additionally, the authors employed an image processing technique to quantify a product's visual appeal as depicted in a photograph. This study also incorporates a comprehensive econometric analysis to connect the objective aspects of visual appeal with subjective responses.

This study aims to explore the intelligibility of communication with stakeholders as a result of accrual accounting adoption. It focuses on changes in the use of visual forms and the readability of text that occurred immediately after the adoption of accrual accounting in performance reports of Italian public universities.

The authors collect the stakeholder section of performance reports published before and after accrual accounting adoption. Then, the authors use manual and computer-assisted textual analysis. Finally, the authors explore the data using principal component analysis and qualitative comparative analysis.

This study demonstrates that switching from cash to accrual accounting provokes immediate changes in communication patterns. It confirms the significant reduction of readability and increase in visual forms after accruals accounting adoption. The results indicate that smaller universities especially put effort into increasing intelligibility while implementing a more complex accounting system. This study also finds a relation between the change in readability and the change in visual forms that are complementary, with the exception of several very large universities.

The findings underline the possibility of neutralising the adverse effects of accounting reform associated with its complexity and difficulties in understanding by the use of visual forms and attention to the document’s readability.

This paper adds a new dimension to the study of public sector accounting from the external stakeholder perspective. It provides further insight into the link between accrual accounting adoption and readability, together with the use of visual forms by universities.

This research explores the differential effects of pixel-level and object-level visual complexity in firm-generated content (FGC) on consumer engagement in terms of the number of likes and shares, and further investigates the moderating role of image brightness.

Drawing on a deep learning analysis of 85,975 images on a social media platform in China, this study investigates visual complexity in FGC.

The results indicate that pixel-level complexity increases both the number of likes and shares. Object-level complexity has a U-shaped relationship with the number of likes, while it has an inverted U-shaped relationship with the number of shares. Moreover, image brightness mitigates the effect of pixel-level complexity on likes but amplifies the effect on shares; contrarily, it amplifies the effect of object-level complexity on likes, while mitigating its effect on shares.

Although images play a critical role in FGC, visual data analytics has rarely been used in social media research. This study identified two types of visual complexity and investigated their differential effects. We discuss how the processing of information embedded in visual content influences consumer engagement. The findings enrich the literature on social media and visual marketing.

This research analyses the searching, interacting and purchasing behavior of shoppers seeking semidurable and fast-moving consumer goods in an immersive virtual reality (VR) store, showing how physical examinations and visual inspections relate to purchases.

Around 60 participants completed two forced-purchase tasks using a head-mounted display with visual and motor-tracking systems. A second study using a pictorial display of the products complemented the VR study.

The findings indicate differences in shopping behavior for the two product categories, with semidurable goods requiring greater inspection and deliberation than fast-moving consumer goods. In addition, visual inspection of the shelf and products was greater than a physical examination through virtual handling for both product categories. The paper also presents relationships between visual inspections and product interactions during the searching stage of purchase decisions.

The research consists of two types of implicit measures in this study: eye-tracking and hand-product interactions. This study reveals the suitability of implicit measures for evaluating consumer behavior in VR stores.