Search results

Software defect prediction (SDP) is a critical aspect of software quality assurance, aiming to identify and manage potential defects in software systems. In this paper, we have proposed a novel hybrid approach that combines Gray Wolf Optimization with Feature Selection (GWOFS) and multilayer perceptron (MLP) for SDP. The GWOFS-MLP hybrid model is designed to optimize feature selection, ultimately enhancing the accuracy and efficiency of SDP. Gray Wolf Optimization, inspired by the social hierarchy and hunting behavior of gray wolves, is employed to select a subset of relevant features from an extensive pool of potential predictors. This study investigates the key challenges that traditional SDP approaches encounter and proposes promising solutions to overcome time complexity and the curse of the dimensionality reduction problem.

The integration of GWOFS and MLP results in a robust hybrid model that can adapt to diverse software datasets. This feature selection process harnesses the cooperative hunting behavior of wolves, allowing for the exploration of critical feature combinations. The selected features are then fed into an MLP, a powerful artificial neural network (ANN) known for its capability to learn intricate patterns within software metrics. MLP serves as the predictive engine, utilizing the curated feature set to model and classify software defects accurately.

The performance evaluation of the GWOFS-MLP hybrid model on a real-world software defect dataset demonstrates its effectiveness. The model achieves a remarkable training accuracy of 97.69% and a testing accuracy of 97.99%. Additionally, the receiver operating characteristic area under the curve (ROC-AUC) score of 0.89 highlights the model’s ability to discriminate between defective and defect-free software components.

Experimental implementations using machine learning-based techniques with feature reduction are conducted to validate the proposed solutions. The goal is to enhance SDP’s accuracy, relevance and efficiency, ultimately improving software quality assurance processes. The confusion matrix further illustrates the model’s performance, with only a small number of false positives and false negatives.

The main purpose of this study is to provide a comprehensive review and critical insights of the application of fuzzy methods in modeling, assessing and understanding the various aspects of green and sustainable supply chains (SSCs).

The present study conducts a systematic literature review (SLR) and bibliometric analysis of 252 research articles. This study employs various tools such as VOSviewer version 1.6.10, Publish or Perish, Mendeley and Excel that aid in descriptive analysis, bibliometric analysis and network visualization. These tools have been used for performing citation analysis, top authors' analysis, co-occurrence of keywords, cluster and content analysis.

The authors have divided the literature into seven application areas and discussed detailed insights. This study has observed that research in the social sustainability area, including various issues like health and safety, labor rights, discrimination, etc. is scarce. Integration of the Industry 4.0 technologies like blockchain, big data analytics, Internet of Things (IoT) with the sustainable and green supply chain (GSC) is a promising field for future research.

The authors' contribution primarily lies in providing the integrated framework which shows the changing trends in the use of fuzzy methods in the sustainability area classifying and consolidating green and sustainable supply chain management (SSCM) literature in seven major areas where fuzzy methods are predominantly applied. These areas have been obtained after the analysis of clusters and content analysis of the literature presenting key insights from the past and developing the conceptual framework for future research studies.

The review paper aims to understand the development of workplace ostracism as a field in organizational studies from 2000 to the present. The study provides a comprehensive synthesis of the current state of the domain by exploring its antecedents, consequences, underlying mechanisms and buffering mechanisms.

The present study analyses 134 published peer-reviewed empirical and non-empirical articles retrieved from the Scopus database. A systematic literature review and bibliometric analyses (using VOS viewer) have been used to gain insights into the development and trends within the field. Bibliometric analyses involved science mapping techniques such as co-citation analysis, co-occurrence of keywords and bibliographic coupling. Combining these three techniques, the study aimed to provide a comprehensive overview of the workplace ostracism research domain's historical, current and future landscape.

In the present study, through descriptive analyses, the authors uncovered publishing trends, productive journals, countries and industries that contribute to this research field. The systematic review enabled the showcasing of the current landscape of workplace ostracism. The bibliometric analyses shed light on major authors, influential articles, prominent journals and significant keywords in workplace ostracism.

This study enriches the existing literature by offering a comprehensive research framework for workplace ostracism. It goes beyond that by presenting significant bibliographic insights by applying bibliometric analyses. Furthermore, this study identifies and emphasizes future research directions using the theory, characteristics, construct and methodologies framework, aiming to expand the knowledge base and understanding of this topic.

COVID-19 has occurred in more than 150 countries and causes a huge impact on the health of many people. The main purpose of this work is, COVID-19 has occurred in more than 150 countries and causes a huge impact on the health of many people. The COVID-19 diagnosis is required to detect at the beginning stage and special attention should be given to them. The fastest way to detect the COVID-19 infected patients is detecting through radiology and radiography images. The few early studies describe the particular abnormalities of the infected patients in the chest radiograms. Even though some of the challenges occur in concluding the viral infection traces in X-ray images, the convolutional neural network (CNN) can determine the patterns of data between the normal and infected X-rays that increase the detection rate. Therefore, the researchers are focusing on developing a deep learning-based detection model.

The main intention of this proposal is to develop the enhanced lung segmentation and classification of diagnosing the COVID-19. The main processes of the proposed model are image pre-processing, lung segmentation and deep classification. Initially, the image enhancement is performed by contrast enhancement and filtering approaches. Once the image is pre-processed, the optimal lung segmentation is done by the adaptive fuzzy-based region growing (AFRG) technique, in which the constant function for fusion is optimized by the modified deer hunting optimization algorithm (M-DHOA). Further, a well-performing deep learning algorithm termed adaptive CNN (A-CNN) is adopted for performing the classification, in which the hidden neurons are tuned by the proposed DHOA to enhance the detection accuracy. The simulation results illustrate that the proposed model has more possibilities to increase the COVID-19 testing methods on the publicly available data sets.

From the experimental analysis, the accuracy of the proposed M-DHOA–CNN was 5.84%, 5.23%, 6.25% and 8.33% superior to recurrent neural network, neural networks, support vector machine and K-nearest neighbor, respectively. Thus, the segmentation and classification performance of the developed COVID-19 diagnosis by AFRG and A-CNN has outperformed the existing techniques.

This paper adopts the latest optimization algorithm called M-DHOA to improve the performance of lung segmentation and classification in COVID-19 diagnosis using adaptive K-means with region growing fusion and A-CNN. To the best of the authors’ knowledge, this is the first work that uses M-DHOA for improved segmentation and classification steps for increasing the convergence rate of diagnosis.

The purpose of the paper is to present research trends in the food supply chain in the context of changes in food systems due to globalization, urbanization, environmental concerns, technological changes and changes in food consumption patterns in the world.

The present investigation was performed by bibliometric analysis using the VOSviewer software, visualization software developed by Nees and Waltman (2020). In this work we performed co-citation, bibliographic coupling and keyword evolution analyses.

The results show that research in the food supply chain is rapidly changing and growing. By applying co-citation analysis, The authors found that the intellectual structure of the food supply chain has evolved around six clusters, namely, (a) collaboration and integration in the supply chain (b) sustainable supply chain management, (c) food supply chain management (FSCM), (d) models for decision-making in the food supply chain, (e) risk management in the supply chain and (g) quality and food logistics in the supply chain. However, based on bibliographic coupling analysis, The authors find that new or emerging research niches are moving toward food supply market access, innovation and technology, food waste management and halal FSCM. Nevertheless, the authors found that the existing research in each of the thematic clusters is not exhaustive.

The limitation of the research is that the analysis mainly relates only to the bibliometric approach and only one database, namely, Scopus. Broader inclusion of databases and deeper application of content analysis could expand the results of this research.

There are limited studies that have examined research trends in food supply chains in both developed and developing countries using bibliometric analysis. The present investigation is novel in identifying the thematic research clusters in the food supply chain, emerging issues and likely future research directions. This is important given the dynamics, consumer demand for quality food, technological changes and environmental sustainability issues in food systems.

The healthcare sector increasingly recognizes how critical sustainable supply chains are to lowering environmental impact, boosting productivity and satisfying public expectations for morally and responsibly provided healthcare. Consequently, the current study aims to thoroughly evaluate the literature on the sustainability of healthcare supply chain management.

The paper uses a systematic literature review (SLR) technique and bibliometric review to examine the benefactions of different authors, nations and organizations to healthcare sustainability through bibliometric and network analyses.

The study concludes that the healthcare industry may advance sustainability on all levels by incorporating technology into the fundamentals of sustainability. Patient care is given priority in this proposed approach, which can also help healthcare executives create strategies that support efficient healthcare supply chains.

The research study can serve as a basis for future investigations into additional healthcare management domains, where integrating a sustainable supply chain can yield superior and observable results and bridge deficiencies in management protocols.

Using bibliometric visualization, this study shows the relevance of sustainability in the healthcare supply chain. By identifying its advantages, present-day circumstances, applications and prospective future research fields, the study took up the review and relevance of sustainability in many parts of the healthcare industry.

Identifying and prioritizing supply chain risk is significant from any product’s quality and reliability perspective. Under an input-process-output workflow, conventional risk prioritization uses a risk priority number (RPN) aligned to the risk analysis. Imprecise information coupled with a lack of dealing with hesitancy margins enlarges the scope, leading to improper assessment of risks. This significantly affects monitoring quality and performance. Against the backdrop, a methodology that identifies and prioritizes the operational supply chain risk factors signifies better risk assessment.

The study proposes a multi-criteria model for risk prioritization involving multiple decision-makers (DMs). The methodology offers a robust, hybrid system based on the Intuitionistic Fuzzy (IF) Set merged with the “Technique for Order Performance by Similarity to Ideal Solution.” The nature of the model is robust. The same is shown by applying fuzzy concepts under multi-criteria decision-making (MCDM) to prioritize the identified business risks for better assessment.

The proposed IF Technique for Order Preference by Similarity to the Ideal Solution (TOPSIS) for risk prioritization model can improve the decisions within organizations that make up the chains, thus guaranteeing a “better quality in risk management.” Establishing an efficient representation of uncertain information related to traditional failure mode and effects analysis (FMEA) treatment involving multiple DMs means identifying potential risks in advance and providing better supply chain control.

In a company’s supply chain, blockchain allows data storage and transparent transmission of flows with traceability, privacy, security and transparency (Roy et al., 2022). They asserted that blockchain technology has great potential for traceability. Since risk assessment in supply chain operations can be treated as a traceability problem, further research is needed to use blockchain technologies. Lastly, issues like risk will be better assessed if predicted well; further research demands the suitability of applying predictive analysis on risk.

The study proposes a hybrid framework based on the generic risk assessment and MCDM methodologies under a fuzzy environment system. By this, the authors try to address the supply chain risk assessment and mitigation framework better than the conventional one. To the best of their knowledge, no study is found in existing literature attempting to explore the efficacy of the proposed hybrid approach over the traditional RPN system in prime sectors like steel (with production planning data). The validation experiment indicates the effectiveness of the results obtained from the proposed IF TOPSIS Approach to Risk Prioritization methodology is more practical and resembles the actual scenario compared to those obtained using the traditional RPN system (Kim et al., 2018; Kumar et al., 2018).

This study provides mathematical models to simulate the supply chain risk assessment, thus helping the manufacturer rank the risk level. In the end, the authors apply this model in a big-sized organization to validate its accuracy. The authors validate the proposed approach to an integrated steel plant impacting the production planning process. The model’s outcome substantially adds value to the current risk assessment and prioritization, significantly affecting better risk management quality.

This review paper aims to explore and investigate the Quality 4.0 current knowledge, emerging areas, and trends available in the literature and provide insights for future research directions. The bibliometric analysis determines the most prominent journals, authors, countries, articles, and themes. The Citation and PageRank analysis identifies the most influential and prestigious articles. The author's keyword analysis identifies the research theme, patterns, and trends within a particular area of research.

This study utilised the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analysis) declaration as a review protocol, and the data is retrieved accordingly. Therefore, 104 articles from Scopus and 28 from Web of Science were combined in R-Environment, and 25 duplicates were removed using RStudio. Finally, 107 papers were selected for further analysis. After the abstract level screening, the study reviewed 99 articles bibliographically published in peer-reviewed journals from prominent academic databases Scopus and WoS between 2011 to April 2023. We used the VOSviewer software tool for analysing bibliometric networks that allow the construction, visualisation, and exploration of maps based on any form of network data.

The review identified emerging themes: artificial intelligence, digitalization, sustainability, root cause analysis, topic modelling, and digital voice-of-customers. To establish the intellectual structure of the field and identify gaps, co-citation and content analysis were used. The content of 49 papers in the identified clusters was then carefully analysed. The four primary themes are the relationship of Quality 4.0 with Industry 4.0, the conceptualization of Quality 4.0, recommendations for the new Quality 4.0 model, and the impact of Quality 4.0. The findings provide an excellent foundation for future research in this field for policymakers, managers, practitioners, and academia.

This is the first systematic literature review-cum-bibliometric analysis on quality 4.0 that covers the field comprehensively. Based on the present review, the paper proposes six possible future research directions to investigate.

The purpose of this paper is to review the literature on Central Bank Digital Currencies (CBDCs) in light of the increasing demand for digital payments globally. It aims to assess the global research landscape, methodologies and data utilized in CBDC studies as their popularity grows.

The paper employs a systematic literature review (SLR) framework, utilizing the Scopus database to identify 323 studies related to Central Bank Digital Currency or CBDC. Through a thorough manual screening process, 169 studies were selected for inclusion. The research employs R, Biblioshiny and Excel for data evaluation, classifying the studies into three methodological categories: quantitative, qualitative and mixed approaches. This classification allows for a detailed assessment of the research techniques and data used in the literature on CBDCs.

The findings include a diverse range of research methodologies and data employed in CBDCs literature, highlighting the growing interest and depth of academic investigation into this area. By categorizing papers according to research technique, the study provides a comprehensive evaluation of the academic landscape regarding CBDC research. It offers valuable insights for researchers, policymakers and stakeholders, contributing to an enhanced understanding of the complexities and opportunities presented by the development and implementation of CBDCs.

This study’s originality lies in its rigorous and transparent methodology for data from CBDC studies, offering a solid framework for future research. By evaluating global research growth within an SLR framework and categorizing studies by research technique, it contributes uniquely to the academic discourse on digital currencies. The paper provides a critical resource for researchers, lawmakers and stakeholders, enriching the knowledge base on CBDCs and supporting informed decision-making in the context of digital financial innovation.