Search results

1 – 10 of 837
Open Access
Article
Publication date: 23 January 2024

Wang Zengqing, Zheng Yu Xie and Jiang Yiling

With the rapid development of railway-intelligent video technology, scene understanding is becoming more and more important. Semantic segmentation is a major part of scene…

Abstract

Purpose

With the rapid development of railway-intelligent video technology, scene understanding is becoming more and more important. Semantic segmentation is a major part of scene understanding. There is an urgent need for an algorithm with high accuracy and real-time to meet the current railway requirements for railway identification. In response to this demand, this paper aims to explore a variety of models, accurately locate and segment important railway signs based on the improved SegNeXt algorithm, supplement the railway safety protection system and improve the intelligent level of railway safety protection.

Design/methodology/approach

This paper studies the performance of existing models on RailSem19 and explores the defects of each model through performance so as to further explore an algorithm model dedicated to railway semantic segmentation. In this paper, the authors explore the optimal solution of SegNeXt model for railway scenes and achieve the purpose of this paper by improving the encoder and decoder structure.

Findings

This paper proposes an improved SegNeXt algorithm: first, it explores the performance of various models on railways, studies the problems of semantic segmentation on railways and then analyzes the specific problems. On the basis of retaining the original excellent MSCAN encoder of SegNeXt, multiscale information fusion is used to further extract detailed features such as multihead attention and mask, solving the problem of inaccurate segmentation of current objects by the original SegNeXt algorithm. The improved algorithm is of great significance for the segmentation and recognition of railway signs.

Research limitations/implications

The model constructed in this paper has advantages in the feature segmentation of distant small objects, but it still has the problem of segmentation fracture for the railway, which is not completely segmented. In addition, in the throat area, due to the complexity of the railway, the segmentation results are not accurate.

Social implications

The identification and segmentation of railway signs based on the improved SegNeXt algorithm in this paper is of great significance for the understanding of existing railway scenes, which can greatly improve the classification and recognition ability of railway small object features and can greatly improve the degree of railway security.

Originality/value

This article introduces an enhanced version of the SegNeXt algorithm, which aims to improve the accuracy of semantic segmentation on railways. The study begins by investigating the performance of different models in railway scenarios and identifying the challenges associated with semantic segmentation on this particular domain. To address these challenges, the proposed approach builds upon the strong foundation of the original SegNeXt algorithm, leveraging techniques such as multi-scale information fusion, multi-head attention, and masking to extract finer details and enhance feature representation. By doing so, the improved algorithm effectively resolves the issue of inaccurate object segmentation encountered in the original SegNeXt algorithm. This advancement holds significant importance for the accurate recognition and segmentation of railway signage.

Details

Smart and Resilient Transportation, vol. 6 no. 1
Type: Research Article
ISSN: 2632-0487

Keywords

Open Access
Article
Publication date: 18 October 2023

Mohammad Rahiminia, Jafar Razmi, Sareh Shahrabi Farahani and Ali Sabbaghnia

Supplier segmentation provides companies with suitable policies to control each segment, thereby saving time and resources. Sustainability has become a mandatory requirement in…

Abstract

Purpose

Supplier segmentation provides companies with suitable policies to control each segment, thereby saving time and resources. Sustainability has become a mandatory requirement in competitive business environments. This study aims to develop a clustering-based approach to sustainable supplier segmentation.

Design/methodology/approach

The characteristics of the suppliers and the aspects of the purchased items were considered simultaneously. The weights of the sub-criteria were determined using the best-worst method. Then, the K-means clustering algorithm was applied to all company suppliers based on four criteria. The proposed model is applied to a real case study to test the performance of the proposed approach.

Findings

The results prove that supplier segmentation is more efficient when using clustering algorithms, and the best criteria are selected for sustainable supplier segmentation and managing supplier relationships.

Originality/value

This study integrates sustainability considerations into the supplier segmentation problem using a hybrid approach. The proposed sustainable supplier segmentation is a practical tool that eliminates complexity and presents the possibility of convenient execution. The proposed method helps business owners to elevate their sustainable insights.

Details

Modern Supply Chain Research and Applications, vol. 5 no. 3
Type: Research Article
ISSN: 2631-3871

Keywords

Open Access
Article
Publication date: 11 October 2022

Jon Engström, Olof Norin, Serge de Gosson de Varennes and Aku Valtakoski

The study aims to explore how segmentation as a methodology can be adapted to the healthcare context to provide a more nuanced understanding of the served population and to…

3291

Abstract

Purpose

The study aims to explore how segmentation as a methodology can be adapted to the healthcare context to provide a more nuanced understanding of the served population and to facilitate the design of patient-centric services.

Design/methodology/approach

The study was based on a collaborative project with a national healthcare organization following the principles of action design research. The study describes the quantitative segmentation performed during the project, followed by a qualitative interview study of how segments correspond with patient behaviors in an actual healthcare setting, and service design workshops facilitated by segments. A number of design principles are outlined based on the learnings of the project.

Findings

The segmentation approach increased understanding of patient variability within the service provider organization and was considered an effective foundation for modular service design. Patient characteristics and life circumstances were related to specific patterns of health behaviors, such as avoidance or passivity, or a persistent proactivity. These patterns influenced the patients' preferred value co-creation role and what type of support patients sought from the care provider.

Practical implications

The proposed segmentation approach is immediately generalizable to further healthcare contexts and similar services: improved understanding of patients, vulnerable patients in particular, improves the fit and inclusivity of services.

Originality/value

The segmentation approach to service design was demonstrated to be effective in a large-scale context. The approach allows service providers to design service options that improve the fit with individual patients' needs for support and autonomy. The results illuminate how patient characteristics influence health and value co-creation behaviors.

Details

Journal of Service Management, vol. 33 no. 6
Type: Research Article
ISSN: 1757-5818

Keywords

Open Access
Article
Publication date: 14 March 2022

Mitja Garmut and Martin Petrun

This paper presents a comparative study of different stator-segmentation topologies of a permanent magnet synchronous machine (PMSM) used in traction drives and their effect on…

1106

Abstract

Purpose

This paper presents a comparative study of different stator-segmentation topologies of a permanent magnet synchronous machine (PMSM) used in traction drives and their effect on iron losses. Using stator segmentation allows one to achieve more significant copper fill factors, resulting in increased power densities and efficiencies. The segmentation of the stators creates additional air gaps and changes the soft magnetic material’s material properties due to the cut edge effect. The aim of this paper is to present an in-depth analysis of the influence of stator segmentation on iron losses. The main goal was to compare various segmentation methods under equal excitation conditions in terms of their influence on iron loss.

Design/methodology/approach

A transient finite element method analysis combined with an extended iron-loss model was used to evaluate discussed effects on the stator’s iron losses. The workflow to obtain a homogenized airgap length accounting for cut edge effects was established.

Findings

The paper concludes that the segmentation in most cases slightly decreases the iron losses in the stator because of the overall reduced magnetic flux density B due to the additional air gaps in the magnetic circuit. An increase of the individual components, as well as total power loss, was observed in the Pole Chain segmentation design. In general, segmentation did not change the total iron losses significantly. However, different segmentation methods resulted in the different distortion of the magnetic field and, consequently, in different iron loss compositions. The analysed segmentation methods exhibited different iron loss behaviour with respect to the operation points of the machine. The final finding is that analysed stator segmentations had a negligible influence on the total iron loss. Therefore, applying segmentation is an adequate measure to improve PMSMs as it enables, e.g. increase of the winding fill factor or simplifying the assembly processes, etc.

Originality/value

The influence of stator segmentation on iron losses was analysed. An in-depth evaluation was performed to determine how the discussed changes influence the individual iron loss components. A workflow was developed to achieve a computationally cheap homogenized model.

Details

COMPEL - The international journal for computation and mathematics in electrical and electronic engineering , vol. 41 no. 2
Type: Research Article
ISSN: 0332-1649

Keywords

Open Access
Article
Publication date: 15 December 2020

Soha Rawas and Ali El-Zaart

Image segmentation is one of the most essential tasks in image processing applications. It is a valuable tool in many oriented applications such as health-care systems, pattern…

Abstract

Purpose

Image segmentation is one of the most essential tasks in image processing applications. It is a valuable tool in many oriented applications such as health-care systems, pattern recognition, traffic control, surveillance systems, etc. However, an accurate segmentation is a critical task since finding a correct model that fits a different type of image processing application is a persistent problem. This paper develops a novel segmentation model that aims to be a unified model using any kind of image processing application. The proposed precise and parallel segmentation model (PPSM) combines the three benchmark distribution thresholding techniques to estimate an optimum threshold value that leads to optimum extraction of the segmented region: Gaussian, lognormal and gamma distributions. Moreover, a parallel boosting algorithm is proposed to improve the performance of the developed segmentation algorithm and minimize its computational cost. To evaluate the effectiveness of the proposed PPSM, different benchmark data sets for image segmentation are used such as Planet Hunters 2 (PH2), the International Skin Imaging Collaboration (ISIC), Microsoft Research in Cambridge (MSRC), the Berkley Segmentation Benchmark Data set (BSDS) and Common Objects in COntext (COCO). The obtained results indicate the efficacy of the proposed model in achieving high accuracy with significant processing time reduction compared to other segmentation models and using different types and fields of benchmarking data sets.

Design/methodology/approach

The proposed PPSM combines the three benchmark distribution thresholding techniques to estimate an optimum threshold value that leads to optimum extraction of the segmented region: Gaussian, lognormal and gamma distributions.

Findings

On the basis of the achieved results, it can be observed that the proposed PPSM–minimum cross-entropy thresholding (PPSM–MCET)-based segmentation model is a robust, accurate and highly consistent method with high-performance ability.

Originality/value

A novel hybrid segmentation model is constructed exploiting a combination of Gaussian, gamma and lognormal distributions using MCET. Moreover, and to provide an accurate and high-performance thresholding with minimum computational cost, the proposed PPSM uses a parallel processing method to minimize the computational effort in MCET computing. The proposed model might be used as a valuable tool in many oriented applications such as health-care systems, pattern recognition, traffic control, surveillance systems, etc.

Details

Applied Computing and Informatics, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 2634-1964

Keywords

Open Access
Article
Publication date: 5 December 2022

Kittisak Chotikkakamthorn, Panrasee Ritthipravat, Worapan Kusakunniran, Pimchanok Tuakta and Paitoon Benjapornlert

Mouth segmentation is one of the challenging tasks of development in lip reading applications due to illumination, low chromatic contrast and complex mouth appearance. Recently…

Abstract

Purpose

Mouth segmentation is one of the challenging tasks of development in lip reading applications due to illumination, low chromatic contrast and complex mouth appearance. Recently, deep learning methods effectively solved mouth segmentation problems with state-of-the-art performances. This study presents a modified Mobile DeepLabV3 based technique with a comprehensive evaluation based on mouth datasets.

Design/methodology/approach

This paper presents a novel approach to mouth segmentation by Mobile DeepLabV3 technique with integrating decode and auxiliary heads. Extensive data augmentation, online hard example mining (OHEM) and transfer learning have been applied. CelebAMask-HQ and the mouth dataset from 15 healthy subjects in the department of rehabilitation medicine, Ramathibodi hospital, are used in validation for mouth segmentation performance.

Findings

Extensive data augmentation, OHEM and transfer learning had been performed in this study. This technique achieved better performance on CelebAMask-HQ than existing segmentation techniques with a mean Jaccard similarity coefficient (JSC), mean classification accuracy and mean Dice similarity coefficient (DSC) of 0.8640, 93.34% and 0.9267, respectively. This technique also achieved better performance on the mouth dataset with a mean JSC, mean classification accuracy and mean DSC of 0.8834, 94.87% and 0.9367, respectively. The proposed technique achieved inference time usage per image of 48.12 ms.

Originality/value

The modified Mobile DeepLabV3 technique was developed with extensive data augmentation, OHEM and transfer learning. This technique gained better mouth segmentation performance than existing techniques. This makes it suitable for implementation in further lip-reading applications.

Details

Applied Computing and Informatics, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 2634-1964

Keywords

Open Access
Article
Publication date: 18 November 2019

Wang Yabin and Jiagui Li

The purpose of this paper is to explore China’s online wine market segmentation on the basis of the wine-related lifestyle (WRL). Moreover, this study can provide further…

6790

Abstract

Purpose

The purpose of this paper is to explore China’s online wine market segmentation on the basis of the wine-related lifestyle (WRL). Moreover, this study can provide further understanding and reference about China’s wine market segmentation research, which is limited at present. This work can be helpful for those who want to do further research in the Chinese wine market. It is good for wine importers wanting to import wine to China to understand the Chinese wine consumers.

Design/methodology/approach

Survey data were obtained from a sample of 3,369 participants through cooperation between the College of Enology and the Yesmywine.com website. Questionnaire items included gender, age, area distribution, unit price, bottles consumed, drinking frequency, drinking time, wine-related knowledge, etc. Combined with the influence factors of the WRL, a structural equation model was developed. The data analysis, particularly employing principal component analysis, enabled the identification of five market segments.

Findings

Five distinct segments were identified within the wine market and designated as follows: wine official consumption type enthusiastic fancier; enjoyment consumption; fashionable consumption; and new, young wine drinkers.

Research limitations/implications

The research data were derived from Yesmywine, one of the largest online wine sale platforms. However, the impact of yesmywine is much smaller compared with Tmall and Taobao and Jingdong. In this paper, we can see that WRL is increasingly becoming a part of Chinese people’s daily lives, especially for the enthusiastic and fancier wine consumers, which is the official type of wine consumer. Next, an analysis of time series under the data of the near future years should be conducted to find the online wine segmentation market variation trend. Moreover, it is important to conduct cross-culture comparison between the Chinese and Australians. Brand positioning can be improved by better understanding China’s online wine market segmentation.

Practical implications

WRL segmentation is valuable for the wine importers and producers in west France, Italian, Germany and so on, as they want to develop China’s wine market and understand the mindset of Chinese wine consumers. The wine importers in China should focus more on consumers that enjoy wine along with newer and younger wine drinkers.

Originality/value

This paper analyzes a large sample (3,369) and therefore is useful for understanding online wine market segmentation and wine consumption behavior in China owing to China’s limited wine market segmentation literature. This paper is the first to use WRL tool to segment China’s online wine market. Moreover, the research data have reference value for those who want to learn more about China’s online wine market, as yesmywine is one of the largest online wine-sale platforms. It also gives some managerial implications for wineries and wine marketers that will be helpful to wine companies in understanding the emerging Chinese wine market and in enacting wine marketing strategies more effectively.

Details

British Food Journal, vol. 122 no. 8
Type: Research Article
ISSN: 0007-070X

Keywords

Open Access
Article
Publication date: 8 June 2020

Lesedi Tomana Nduna and Cine van Zyl

The purpose of this study is to investigate benefits tourist seek when visiting a nature-based tourism destination to develop a benefit segmentation framework.

3827

Abstract

Purpose

The purpose of this study is to investigate benefits tourist seek when visiting a nature-based tourism destination to develop a benefit segmentation framework.

Design/methodology/approach

The study used quantitative research methods, with 400 self-administered survey administered to a sample of 400 tourists visiting the Kruger, Panorama, and Lowveld areas in Mpumalanga.

Findings

Cluster analysis produced two benefit segments. Binary logistic regression benefits that emerged from the cluster analysis were statistically significant predictors of the attractions tourists visited and the activities in which they participated during their stays in Mpumalanga. Factor-cluster analysis and binary logistic regression results were used to develop a benefit segmentation framework as a marketing planning tool.

Research limitations/implications

The study was only based on Mpumalanga Province and therefore, the results cannot be generalised. The study was conducted over one season, the Easter period

Practical implications

The proposed benefit segmentation framework provides a tool that destination management organisations can use to plan effectively for marketing.

Social implications

Effective marketing may lead to increased tourism growth which can have a multiplier effect on the destination.

Originality/value

This article is based on a master’s study conducted in Mpumalanga and results are presented on this paper.

Details

International Journal of Tourism Cities, vol. 6 no. 4
Type: Research Article
ISSN: 2056-5607

Keywords

Open Access
Article
Publication date: 18 April 2023

Worapan Kusakunniran, Pairash Saiviroonporn, Thanongchai Siriapisith, Trongtum Tongdee, Amphai Uraiverotchanakorn, Suphawan Leesakul, Penpitcha Thongnarintr, Apichaya Kuama and Pakorn Yodprom

The cardiomegaly can be determined by the cardiothoracic ratio (CTR) which can be measured in a chest x-ray image. It is calculated based on a relationship between a size of heart…

2489

Abstract

Purpose

The cardiomegaly can be determined by the cardiothoracic ratio (CTR) which can be measured in a chest x-ray image. It is calculated based on a relationship between a size of heart and a transverse dimension of chest. The cardiomegaly is identified when the ratio is larger than a cut-off threshold. This paper aims to propose a solution to calculate the ratio for classifying the cardiomegaly in chest x-ray images.

Design/methodology/approach

The proposed method begins with constructing lung and heart segmentation models based on U-Net architecture using the publicly available datasets with the groundtruth of heart and lung masks. The ratio is then calculated using the sizes of segmented lung and heart areas. In addition, Progressive Growing of GANs (PGAN) is adopted here for constructing the new dataset containing chest x-ray images of three classes including male normal, female normal and cardiomegaly classes. This dataset is then used for evaluating the proposed solution. Also, the proposed solution is used to evaluate the quality of chest x-ray images generated from PGAN.

Findings

In the experiments, the trained models are applied to segment regions of heart and lung in chest x-ray images on the self-collected dataset. The calculated CTR values are compared with the values that are manually measured by human experts. The average error is 3.08%. Then, the models are also applied to segment regions of heart and lung for the CTR calculation, on the dataset computed by PGAN. Then, the cardiomegaly is determined using various attempts of different cut-off threshold values. With the standard cut-off at 0.50, the proposed method achieves 94.61% accuracy, 88.31% sensitivity and 94.20% specificity.

Originality/value

The proposed solution is demonstrated to be robust across unseen datasets for the segmentation, CTR calculation and cardiomegaly classification, including the dataset generated from PGAN. The cut-off value can be adjusted to be lower than 0.50 for increasing the sensitivity. For example, the sensitivity of 97.04% can be achieved at the cut-off of 0.45. However, the specificity is decreased from 94.20% to 79.78%.

Details

Applied Computing and Informatics, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 2634-1964

Keywords

Open Access
Article
Publication date: 20 December 2022

Quivine Ndomo, Ilona Bontenbal and Nathan A. Lillie

The purpose of this paper is to characterise the position of highly educated African migrants in the Finnish labour market and to examine the impact of the COVID-19 pandemic on…

Abstract

Purpose

The purpose of this paper is to characterise the position of highly educated African migrants in the Finnish labour market and to examine the impact of the COVID-19 pandemic on that position.

Design/methodology/approach

The paper is based on the biographical work stories of 17 highly educated African migrant workers in four occupation areas in Finland: healthcare, cleaning, restaurant and transport. The sample was partly purposively and partly theoretically determined. The authors used content driven thematic analysis technique, combined with by the biographical narrative concept of turning points.

Findings

Using the case of highly educated African migrants in the Finnish labour market, the authors show how student migration policies reinforce a pattern of division of labour and occupations that allocate migrant workers to typical low skilled low status occupations in the secondary sector regardless of level of education, qualification and work experience. They also show how the unique labour and skill demands of the COVID-19 pandemic incidentally made these typical migrant occupations essential, resulting in increased employment and work security for this group of migrant workers.

Research limitations/implications

This research and the authors’ findings are limited in scope owing to sample size and methodology. To improve applicability of findings, future studies could expand the scope of enquiry using e.g. quantitative surveys and include other stakeholders in the study group.

Originality/value

The paper adds to the knowledge on how migration policies contribute to labour market dualisation and occupational segmentation in Finland, illustrated by the case of highly educated African migrant workers.

Details

International Journal of Sociology and Social Policy, vol. 43 no. 3/4
Type: Research Article
ISSN: 0144-333X

Keywords

1 – 10 of 837