Search results

Diabetic retinopathy (DR) is one of the dangerous complications of diabetes. Its grade level must be tracked to manage its progress and to start the appropriate decision for treatment in time. Effective automated methods for the detection of DR and the classification of its severity stage are necessary to reduce the burden on ophthalmologists and diagnostic contradictions among manual readers.

In this research, convolutional neural network (CNN) was used based on colored retinal fundus images for the detection of DR and classification of its stages. CNN can recognize sophisticated features on the retina and provides an automatic diagnosis. The pre-trained VGG-16 CNN model was applied using a transfer learning (TL) approach to utilize the already learned parameters in the detection.

By conducting different experiments set up with different severity groupings, the achieved results are promising. The best-achieved accuracies for 2-class, 3-class, 4-class and 5-class classifications are 86.5, 80.5, 63.5 and 73.7, respectively.

In this research, VGG-16 was used to detect and classify DR stages using the TL approach. Different combinations of classes were used in the classification of DR severity stages to illustrate the ability of the model to differentiate between the classes and verify the effect of these changes on the performance of the model.

This paper aims to propose an enhanced densely dehazing network to suit railway scenes’ features and improve the visual quality degraded by haze and fog.

It is an end-to-end network based on DenseNet. The authors design enhanced dense blocks and fuse them in a pyramid pooling module for visual data’s local and global features. Multiple ablation studies have been conducted to show the effects of each module proposed in this paper.

The authors have compared dehazed results on real hazy images and railway hazy images of state-of-the-art dehazing networks with the dehazed results in data quality. Finally, an object-detection test is taken to judge the edge information preservation after haze removal. All results demonstrate that the proposed dehazing network performs better under railway scenes in detail.

This study provides a new method for image enhancing in the railway monitoring system.

The authors analyze the relationship between different consumer attitudinal variables and a number of variables related to consumer perception of the store and purchasing behavior, in assortments composed exclusively of private labels (PLs).

The authors developed an experiment based on an online survey to test the hypotheses formulated. The model’s causal relationships are established using structural equations.

The image of stores that only offer their own brand is mainly configured by price consciousness and the attitude toward the private label. The private label purchase intention is strongly influenced by the store image and a favorable attitude toward the brand, and loyalty strategies should be aimed at securing a clear perception of providing real value.

For retailers who only offer their own brands, an assortment with price-competitive PLs is key to the strategy of differentiating them from other retailers. It is reasonable to assume that, if retailers have a favorable image, customers transfer this brand value to their PLs and trust them. Customer loyalty strategies of these retailers should be aimed at ensuring that consumers clearly perceive that their assortment provides real value and that, although it is limited in terms of number of brands, it can meet all their needs.

This research represents a significant contribution to brand management literature because, includes, together with loyalty to the store, its image and the PL purchase intention as consumer response variables. Another differentiating feature is the methodology used. Estimation of the structural equation model permits the simultaneous estimation of the relationships between the variables.

Analizamos la relación entre diferentes variables actitudinales de los consumidores y un número de variables relativas a la percepción de los consumidores con respecto al establecimiento y el comportamiento de compra, todo ello en surtidos compuestos exclusivamente por marcas de distribuidor.

Desarrollamos un experimento online, basado en una encuesta, para testar las hipótesis planteadas. Utilizamos ecuaciones estructurales para determiner las relaciones causales del modelo.

La imagen de los establecimientos que ofrecen exclusivamente su propia marca se configura, principalmente, por la conciencia de precio y por la actitud de los consumidores hacia la marca privada. La intención de compra de la marca de distribuidor está fuertemente influenciada por la imagen del establecimiento y por una actitud favorable hacia dicha marca, por lo que las estrategias de fidelización de clientes deberían estar orientadas a asegurar una clara percepción de proporcionar valor real a los consumidores.

Para los minoristas que ofertan exclusivamente sus propias marcas, un surtido con marcas de distribuidor muy competitivas en precio es fundamental en su estrategia de diferenciación de sus competidores. Además, es razonable suponer que si los minoristas cuentan con una imagen favorable, los consumidores trasladarán este valor de marca a sus propias marcas propias y confiarán en ellas. Las estrategias de fidelización de este tipo de minoristas deberían ir enfocadas a asegurarse de que los consumidores perciben claramente el valor real que aporta su surtido y que, aunque limitado en términos de número de marcas y alternativas, les permite cubrir todas sus necesidades.

Esta investigación supone una significativa contribución a la literatura sobre gestión de marcas al incluir, conjuntamente con la lealtad al establecimiento, su imagen y la intención de compra de la marca de distribuidor como variables respuesta del consumidor. Otro elemento diferenciador es la metodología empleada, ya que la estimación del modelo de ecuaciones estructurales permite la estimación simultánea de las relaciones entre las distintas variables.

This paper provides practical advice for archaeologists and heritage specialists wishing to use ML approaches to identify archaeological features in high-resolution satellite imagery (or other remotely sensed data sources). We seek to balance the disproportionately optimistic literature related to the application of ML to archaeological prospection through a discussion of limitations, challenges and other difficulties. We further seek to raise awareness among researchers of the time, effort, expertise and resources necessary to implement ML successfully, so that they can make an informed choice between ML and manual inspection approaches.

Automated object detection has been the holy grail of archaeological remote sensing for the last two decades. Machine learning (ML) models have proven able to detect uniform features across a consistent background, but more variegated imagery remains a challenge. We set out to detect burial mounds in satellite imagery from a diverse landscape in Central Bulgaria using a pre-trained Convolutional Neural Network (CNN) plus additional but low-touch training to improve performance. Training was accomplished using MOUND/NOT MOUND cutouts, and the model assessed arbitrary tiles of the same size from the image. Results were assessed using field data.

Validation of results against field data showed that self-reported success rates were misleadingly high, and that the model was misidentifying most features. Setting an identification threshold at 60% probability, and noting that we used an approach where the CNN assessed tiles of a fixed size, tile-based false negative rates were 95–96%, false positive rates were 87–95% of tagged tiles, while true positives were only 5–13%. Counterintuitively, the model provided with training data selected for highly visible mounds (rather than all mounds) performed worse. Development of the model, meanwhile, required approximately 135 person-hours of work.

Our attempt to deploy a pre-trained CNN demonstrates the limitations of this approach when it is used to detect varied features of different sizes within a heterogeneous landscape that contains confounding natural and modern features, such as roads, forests and field boundaries. The model has detected incidental features rather than the mounds themselves, making external validation with field data an essential part of CNN workflows. Correcting the model would require refining the training data as well as adopting different approaches to model choice and execution, raising the computational requirements beyond the level of most cultural heritage practitioners.

Improving the pre-trained model’s performance would require considerable time and resources, on top of the time already invested. The degree of manual intervention required – particularly around the subsetting and annotation of training data – is so significant that it raises the question of whether it would be more efficient to identify all of the mounds manually, either through brute-force inspection by experts or by crowdsourcing the analysis to trained – or even untrained – volunteers. Researchers and heritage specialists seeking efficient methods for extracting features from remotely sensed data should weigh the costs and benefits of ML versus manual approaches carefully.

Our literature review indicates that use of artificial intelligence (AI) and ML approaches to archaeological prospection have grown exponentially in the past decade, approaching adoption levels associated with “crossing the chasm” from innovators and early adopters to the majority of researchers. The literature itself, however, is overwhelmingly positive, reflecting some combination of publication bias and a rhetoric of unconditional success. This paper presents the failure of a good-faith attempt to utilise these approaches as a counterbalance and cautionary tale to potential adopters of the technology. Early-majority adopters may find ML difficult to implement effectively in real-life scenarios.

Unlike many high-profile reports from well-funded projects, our paper represents a serious but modestly resourced attempt to apply an ML approach to archaeological remote sensing, using techniques like transfer learning that are promoted as solutions to time and cost problems associated with, e.g. annotating and manipulating training data. While the majority of articles uncritically promote ML, or only discuss how challenges were overcome, our paper investigates how – despite reasonable self-reported scores – the model failed to locate the target features when compared to field data. We also present time, expertise and resourcing requirements, a rarity in ML-for-archaeology publications.

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.

Precise vehicle localization is a basic and critical technique for various intelligent transportation system (ITS) applications. It also needs to adapt to the complex road environments in real-time. The global positioning system and the strap-down inertial navigation system are two common techniques in the field of vehicle localization. However, the localization accuracy, reliability and real-time performance of these two techniques can not satisfy the requirement of some critical ITS applications such as collision avoiding, vision enhancement and automatic parking. Aiming at the problems above, this paper aims to propose a precise vehicle ego-localization method based on image matching.

This study included three steps, Step 1, extraction of feature points. After getting the image, the local features in the pavement images were extracted using an improved speeded up robust features algorithm. Step 2, eliminate mismatch points. Using a random sample consensus algorithm to eliminate mismatched points of road image and make match point pairs more robust. Step 3, matching of feature points and trajectory generation.

Through the matching and validation of the extracted local feature points, the relative translation and rotation offsets between two consecutive pavement images were calculated, eventually, the trajectory of the vehicle was generated.

The experimental results show that the studied algorithm has an accuracy at decimeter-level and it fully meets the demand of the lane-level positioning in some critical ITS applications.

The purpose of this study is to investigate the place brand building process based on multi-stakeholder perceived value. It contributes to an understanding of how place brands are developed, providing diverse benefits, and proposes a conceptual framework for place brand building and value measurement scales.

The study is based on the place brand Sud de France. Qualitative data from stakeholder interviews is used to investigate the main place brand value dimensions. A survey of consumers from the Languedoc-Roussillon region is conducted to measure consumer place brand values. Quantitative data is analyzed using structural equation modelling.

Results indicate that place brand value is a multiple-perspective and multidimensional construct that includes new measurement scales related to dimensions such as quality of life, a common local identity and local development. Brand identity is not only constructed on place identity, but should also incorporate stakeholder values and provide value to consumers.

For place brand managers, this study provides a methodology that helps identify the main place image and stakeholders values to be integrated into place brand identity construction. The place brand value measurement scales can be used to ensure a permanent match between brand identity and consumption trends.

Literature dealing with place equity has focused mostly on country-of-origin or destination image effects from a non-local consumer or tourist perspective. The originality of this study lies in analyzing the perceived benefits of a regional brand by its local stakeholders, leading to a new brand building framework and value measurement scales.

The purpose of this paper is to propose a research approach to investigate brand alignment by exploiting textual data from online brand communities in the coffee industry. Specifically, consumer brand associations from user-generated content (UGC) and company brand associations from firm-generated content (FGC) are explored to measure the alignment between brand identity and brand image. The selected context of research is the beverage industry wherein companies are called on to develop appropriate digital websites and brand communication strategies to enhance the consumers' brand experience.

The authors introduce a research approach that integrates netnography with text mining analysis. Since brand associations were the basis of the study’s analysis, the authors focused on text mining procedures, providing data (co-occurrences) corresponding to brand associations that consumers perceive and that the company communicates. Data were used to develop the measurements of brand alignment.

The main findings of this research highlight the importance for both scholars and practitioners of determining brand alignment of beverage products in online communities. Knowing the alignment between the way a company communicates its brand identity and how this is perceived by consumers allows for effectively reviewing brand communication.

Although the combined analysis of the alignment between brand image and brand identification has received attention in marketing literature, most scholars have neglected how to measure brand alignment. This is a need for many marketing managers in the coffee industry who are now moving in digital environments where the role of consumers is not that of receivers of brand communication but rather that of cocreators of brand value.

Diagnosing pain in neonates is difficult but critical. Although approximately thirty manual pain instruments have been developed for neonatal pain diagnosis, most are complex, multifactorial, and geared toward research. The goals of this work are twofold: 1) to develop a new video dataset for automatic neonatal pain detection called iCOPEvid (infant Classification Of Pain Expressions videos), and 2) to present a classification system that sets a challenging comparison performance on this dataset. The iCOPEvid dataset contains 234 videos of 49 neonates experiencing a set of noxious stimuli, a period of rest, and an acute pain stimulus. From these videos 20 s segments are extracted and grouped into two classes: pain (49) and nopain (185), with the nopain video segments handpicked to produce a highly challenging dataset. An ensemble of twelve global and local descriptors with a Bag-of-Features approach is utilized to improve the performance of some new descriptors based on Gaussian of Local Descriptors (GOLD). The basic classifier used in the ensembles is the Support Vector Machine, and decisions are combined by sum rule. These results are compared with standard methods, some deep learning approaches, and 185 human assessments. Our best machine learning methods are shown to outperform the human judges.

The aim of this research is to investigate the factors affecting consumers’ willingness to buy private label brands (PLBs). The relationships among store image, familiarity with PLBs, consumers’ perceptions of PLB quality, risk, price consciousness and attitude towards PLBs are examined. Finally, the relationship between attitude towards, and willingness to buy PLB is explored.

Self-administered questionnaire was distributed to shoppers at Carrefour operating in Cairo, Egypt. The data obtained from 265 respondents were examined using structural equation modelling (analysis of moment structures) version 22, which empirically test the hypothesised relations established in the research conceptual model.

With the exception of perceived risk, the results suggest that all consumers’ perceptual and attitudinal factors affect directly or indirectly consumers’ willingness to buy PLB.

This study is limited to international hypermarket/supermarket operating in Egypt. So the findings should be exercised with cautious while attempting to generalise the research results.

Retail managers should focus on the enhancement of both store image and familiarity with PLBs to leverage consumers’ perceptions with respect to PLBs quality and risk to achieve differentiation and to increase sales.

This is one of the few studies that investigate the role of familiarity with PLBs in a developing context. In doing so, it proposes that familiarity with PLBs directly affects consumers’ perceived quality and perceived risk, while it indirectly influences consumers’ willingness to buy PLBs.

El propósito de este trabajo es el de analizar los factores que afectan a la predisposición de los consumidores a comprar marcas de distribución. Es por ello que se examina la estructura de relaciones existentes entre la imagen de la tienda, la familiaridad con las marcas de distribución, las percepciones de calidad y riesgo así como la conciencia de precio y su posterior efecto en actitudes hacia las marcas de distribución y la predisposición de compra.

Se distribuyeron cuestionarios auto-administrados entre compradores de la cadena Carrefour en El Cairo, Egipto. Los datos proporcionados por 265 individuos fueron analizados con ecuaciones estructurales (AMOS) para contrastar empíricamente las relaciones planteadas en el modelo conceptual propuesto.

Los resultados obtenidos sugieren que todos los factores actitudinales y perceptuales de los consumidores afectan directa o indirectamente a la disposición de los consumidores a adquirir marcas de distribución, excepto la percepción del riesgo.

Este estudio se limita a las cadenas de supermercados e hipermercados que operan en Egipto, por lo que los resultados obtenidos tienen una limitada generalización fuera de este contexto.

Los directivos de los detallistas deben centrar sus esfuerzos en ensalzar la imagen de la tienda y la familiaridad con las marcas de distribución con el propósito de influir en las percepciones de calidad y riesgo que los consumidores tienen sobre ellas con el fin último de lograr una diferenciación y un incremento de las ventas.

Este estudio es uno de los pocos que investiga el papel que ejerce la familiaridad con las marcas de distribución en países en vías de desarrollo. Propone que la familiaridad afecta directamente a la percepción de calidad y riesgo de los consumidores e influye indirectamente en la disposición de los consumidores a comprar las marcas de distribución.