Search results

Thin cracks on the surface, such as those found in nuclear power plant concrete structures, are difficult to identify because they tend to be thin. This paper aims to design a novel segmentation network, called U-shaped contextual aggregation network (UCAN), for better recognition of weak cracks.

UCAN uses dilated convolutional layers with exponentially changing dilation rates to extract additional contextual features of thin cracks while preserving resolution. Furthermore, this paper has developed a topology-based loss function, called ℓ_cl Dice, which enhances the crack segmentation’s connectivity.

This paper generated five data sets with varying crack widths to evaluate the performance of multiple algorithms. The results show that the UCAN network proposed in this study achieves the highest F1-Score on thinner cracks. Additionally, training the UCAN network with the ℓ_cl Dice improves the F1-Scores compared to using the cross-entropy function alone. These findings demonstrate the effectiveness of the UCAN network and the value of incorporating the ℓ_cl Dice in crack segmentation tasks.

In this paper, an exponentially dilated convolutional layer is constructed to replace the commonly used pooling layer to improve the model receptive field. To address the challenge of preserving fracture connectivity segmentation, this paper introduces ℓ_cl Dice. This design enables UCAN to extract more contextual features while maintaining resolution, thus improving the crack segmentation performance. The proposed method is evaluated using extensive experiments where the results demonstrate the effectiveness of the algorithm.

Traditional visual simultaneous localization and mapping (SLAM) systems are primarily based on the assumption that the environment is static, which makes them struggle with the interference caused by dynamic objects in complex industrial production environments. This paper aims to improve the stability of visual SLAM in complex dynamic environments through semantic segmentation and its optimization.

This paper proposes a real-time visual SLAM system for complex dynamic environments based on YOLOv5s semantic segmentation, named YLS-SLAM. The system combines semantic segmentation results and the boundary semantic enhancement algorithm. By recognizing and completing the semantic masks of dynamic objects from coarse to fine, it effectively eliminates the interference of dynamic feature points on the pose estimation and enhances the retention and extraction of prominent features in the background, thereby achieving stable operation of the system in complex dynamic environments.

Experiments on the Technische Universität München and Bonn data sets show that, under monocular and Red, Green, Blue - Depth modes, the localization accuracy of YLS-SLAM is significantly better than existing advanced dynamic SLAM methods, effectively improving the robustness of visual SLAM. Additionally, the authors also conducted tests using a monocular camera in a real industrial production environment, successfully validating its effectiveness and application potential in complex dynamic environment.

This paper combines semantic segmentation algorithms with boundary semantic enhancement algorithms to effectively achieve precise removal of dynamic objects and their edges, while ensuring the system's real-time performance, offering significant application value.

The study aims to enhance the detection and classification of conjunctival eye diseases' severity through the development of ConjunctiveNet, an innovative deep learning framework. This model incorporates advanced preprocessing techniques and utilizes a modified Otsu’s method for improved image segmentation, aiming to improve diagnostic accuracy and efficiency in healthcare settings.

ConjunctiveNet employs a convolutional neural network (CNN) enhanced through transfer learning. The methodology integrates rescaling, normalization, Gaussian blur filtering and contrast-limited adaptive histogram equalization (CLAHE) for preprocessing. The segmentation employs a novel modified Otsu’s method. The framework’s effectiveness is compared against five pretrained CNN architectures including AlexNet, ResNet-50, ResNet-152, VGG-19 and DenseNet-201.

The study finds that ConjunctiveNet significantly outperforms existing models in accuracy for detecting various severity stages of conjunctival eye conditions. The model demonstrated superior performance in classifying four distinct severity stages – initial, moderate, high, severe and a healthy stage – offering a reliable tool for enhancing screening and diagnosis processes in ophthalmology.

ConjunctiveNet represents a significant advancement in the automated diagnosis of eye diseases, particularly conjunctivitis. Its originality lies in the integration of modified Otsu’s method for segmentation and its comprehensive preprocessing approach, which collectively enhance its diagnostic capabilities. This framework offers substantial value to the field by improving the accuracy and efficiency of conjunctival disease severity classification, thus aiding in better healthcare delivery.

The study aims to provide a reference for market segmentation in a relatively new market. Esports consumer profiles are developed based on consumption motives, structural factors, game genres, interests, demographics and behavioral intentions. It delivers managerial advice for a growing esports market.

A quantitative approach using an online survey was implemented to identify homogenous groups. The study employed the Motivation Scale for Sports Consumption (MSSC) to investigate the consumption motives of esports consumers. A two-step market segmentation was conducted based on the motives, applying hierarchical clustering. Moreover, descriptor variables were used to create distinct esports consumer profiles.

This research divides the esports market into four clusters based on MSSC, which is new and relevant in a constantly changing environment. The clusters are named Low Intention Novices, Leisure Warriors, Socializing Learners and Dedicated Enthusiasts.

This adds to the limited literature on esports market segmentation and highlights the theoretical and practical implications of the findings.

The purpose of this study is to analyse the gender wage gap (GWG) in Spain adopting a labour market segmentation approach. Once we obtain the different labour segments (or idiosyncratic labour markets), we are able to decompose the GWG into its observed and unobserved heterogeneity components.

We use the data from the Continuous Sample of Working Lives for the year 2021 (matched employer–employee [EE] data). Contingency tables and clustering techniques are applied to employment data to identify idiosyncratic labour markets where men and/or women of different ages tend to match/associate with different sectors of activity and occupation groups. Once this “heatmap” of labour associations is known, we can analyse its hottest areas (the idiosyncratic labour markets) from the perspective of wage discrimination by gender (Oaxaca-Blinder model).

In Spain, in general, men are paid more than women, and this is not always justified by their respective attributes. Among our results, the fact stands out that women tend to move to those idiosyncratic markets (biclusters) where the GWG (in favour of men) is smaller.

It has not been possible to obtain remuneration data by job-placement, but an annual EE relationship is used. Future research should attempt to analyse the GWG across the wage distribution in the different idiosyncratic markets.

Our combination of methodologies can be adapted to other economies and variables and provides detailed information on the labour-matching process and gender wage discrimination in segmented labour markets.

Our contribution is very important for labour market policies, trying to reduce unfair inequalities.

The study of the GWG from a novel labour segmentation perspective can be interesting for other researchers, institutions and policy makers.

The digital marketing landscape is rapidly evolving, but the integration of visual content still heavily depends on human expertise. Driven by the quest for innovative marketing strategies that resonate with family-oriented consumers, this study seeks to bridge this gap by applying machine learning to analyze visual content in the maternity and baby care product sector.

This study incorporates a range of machine learning techniques – including open science framework feature detection, panoptic segmentation, customized instance segmentation, and face detection calculation methods – to analyze and predict the appeal of images, thereby enhancing user engagement and parent-child intimacy.

The exploration of various ML models, such as DT, LightGBM, RIPPER algorithm, and CNNs, has offered a comparative analysis that addresses a methodological gap in the existing literature, which frequently depends on isolated model evaluations. According to our quadrant analysis with respect to engagement rate and parent-child intimacy, the selection of a model for real-world applications depends on balancing performance and interpretability.

The proposed system offers a series of actionable recommendations designed to enhance customer engagement and foster brand loyalty. This study contributes to image design in maternity and baby care marketing and provides analytical insights for recommendation systems.

This study aims to explore and segment consumer preferences for electric and hybrid vehicles in Germany, Sweden, the Netherlands and Turkey, focusing on understanding the various factors that influence consumer decisions in these markets.

Using latent class analysis (LCA) on data collected through online surveys and discrete choice experiments, this research categorizes consumers into distinct segments. The approach allows for a nuanced understanding of how various factors such as income level, fuel cost, age, CO₂ emissions, purchase price, vehicle range, policy policies and environmental concerns interact with shape consumer preferences.

The analysis uncovers significant heterogeneity in consumer preferences for electric and hybrid vehicles across Germany, Sweden, the Netherlands and Turkey, revealing four key segments: “Eco-Driven Innovators,” “Value-Focused Pragmatists,” “Tech-Savvy Early Adopters” and “Reluctant Traditionalists.” “Eco-Driven Innovators” prioritize environmental benefits and are less sensitive to price, demonstrating a strong inclination toward vehicle CO₂ emissions and policy policies. “Value-Focused Pragmatists” weigh economic factors heavily, showing a sharp interest in fuel costs and purchase prices but are open to considering electric and hybrid vehicles if they present clear long-term savings. Technology-savvy early adopters are attracted by the latest technological advancements in vehicles, regardless of the type, and are motivated by factors beyond just environmental concerns or cost savings. Lastly, “Reluctant Traditionalists” exhibit minimal interest in electric and hybrid vehicles due to concerns over charging infrastructure and upfront costs. This detailed segmentation illustrates the diverse motivations and barriers influencing consumer choices, from governmental policies and environmental concerns to individual financial considerations and technological appeal.

This study stands out for its pioneering application of LCA to dissect the complexity of consumer preferences for electric and hybrid vehicles, a methodological approach not widely used in this research domain. Using LCA, the authors are able to uncover nuanced consumer segments, each with distinct preferences and motivations, providing a depth of insight into market dynamics that traditional analysis methods may overlook. This approach enables a more granular understanding of how diverse factors – ranging from environmental concerns to economic considerations and technological attributes – interact to shape consumer choices in different countries. The findings not only fill a critical gap in the existing literature by mapping the intricate landscape of consumer preferences, but also offer a novel perspective on strategizing market interventions. Therefore, the application of LCA enriches the discourse on sustainable transportation, offering stakeholders, manufacturers, policymakers and researchers – a refined toolkit for navigating the evolving market dynamics and fostering the adoption of electric and hybrid vehicles.

As laser scanning technology becomes readily available and affordable, there is an increasing demand of using point cloud data collected from a laser scanner to create as-built building information modeling (BIM) models for quality assessment, schedule control and energy performance within construction projects. To enhance the as-built modeling efficiency, this study explores an integrated system, called Auto-Scan-To-BIM (ASTB), with an aim to automatically generate a complete Industry Foundation Classes (IFC) model consisted of the 3D building elements for the given building based on its point cloud without requiring additional modeling tools.

ASTB has been developed with three function modules. Taking the scanned point data as input, Module 1 is built on the basis of the widely used region segmentation methodology and expanded with enhanced plane boundary line detection methods and corner recalibration algorithms. Then, Module 2 is developed with a domain knowledge-based heuristic method to analyze the features of the recognized planes, to associate them with corresponding building elements and to create BIM models. Based on the spatial relationships between these building elements, Module 3 generates a complete IFC model for the entire project compatible with any BIM software.

A case study validated the ASTB with an application with five common types of building elements (e.g. wall, floor, ceiling, window and door).

First, an integrated system, ASTB, is developed to generate a BIM model from scanned point cloud data without using additional modeling tools. Second, an enhanced plane boundary line detection method and a corner recalibration algorithm are developed in ASTB with high accuracy in obtaining the true surface planes. At last, the research contributes to develop a module, which can automatically convert the identified building elements into an IFC format based on the geometry and spatial relationships of each plan.

This paper aims to determine the type of supplier involvement in terms of time and extent of supplier involvement in automobile product development based on the characteristics of parts in the Iranian automotive industry.

The paper proposes the clustering and analytic hierarchy process (AHP) methods. Combining the K-means clustering method and metaheuristic algorithms, the genetic algorithm (GA) and particle swarm optimization (PSO) algorithm are applied to achieve better clustering results.

The results show that lack of internal knowledge, high technology change and complexity of parts increase the need to outsource the design process. In addition to these reasons, high development costs and high interface complexity justify suppliers’ early involvement.

Most research only presents a conceptual framework for understanding the various levels of supplier involvement in new product development (NPD). However, in the automotive industry, numerous parts have differing degrees of importance and priority, and experts may have varying opinions based on different criteria. Therefore, the existing conceptual model for analyzing the types of involvement of each supplier is not practical. We have formulated a problem-solving approach that utilizes the clustering and AHP methods to analyze data obtained from qualitative research and determine the type of supplier involvement.

The aim of this study was to investigate consumer preferences and profile their food-related lifestyles, as well as to identify consumer groups with similar attitudes/behaviours in the Euro-Mediterranean fruit and vegetable market.

A structured questionnaire was designed drawing from the food related lifestyles instrument and including other factors relevant to fruit and vegetable consumer preferences. The data were collected in an online survey with 925 participants in France, Greece, and Italy. A principal component analysis was conducted to interpret and examine consumers' fruit and vegetable related lifestyles. In addition, a cluster analysis was performed to identify different consumer segments, based on the core dimensions of the food-related lifestyle approach.

In each country, three primary consumer segments were distinguished. Health-conscious individuals were predominant in France and Greece, while quality-conscious consumers were prevalent in Italy. These classifications were determined considering various factors such as purchase motivation, perception of product quality, health concerns, environmental certifications, and price sensitivity.

The food-related lifestyle approach has been adapted instrument to create a customised survey instrument specifically designed to capture the intricacies of fruit and vegetable consumer preferences and priorities in three Euro-Mediterranean Countries.