Search

In this article, we aim to prioritize barriers hindering sustainability inclusion within clean energy supply chains. Supply chain management is a crucial aspect of the clean energy sector, whereby the global supply chains can be enforced with policies to adopt sustainability/green practices. The literature infers that the adoption of sustainability is not direct, and multiple barriers impede the process, driving researchers to rank these barriers. Previous studies on prioritizing barriers cannot effectively model uncertainty; experts' reliability is directly assigned; interrelationships/hesitation of criteria/experts are usually not considered; and there is a lack of personalized ordering based on individuals' preferences. Motivated by these gaps, the authors put forward an integrated framework with a Fermatean fuzzy set, variance-based criteria importance through intercriteria correlation for determining experts' and criteria weights, and ranking procedure with complex proportional assessment-Copeland for personalized ordering of barriers. The usefulness of the developed approach is testified through a case example. Results infer that wastage/pollution reduction and profit from green production are the two top criteria considered for rating sustainability barriers, while limited governmental policies, monitoring/control issues, and expertise mismatch are the top three barriers impeding sustainability adoption. Finally, sensitivity and comparative analyses are performed to understand the framework's efficacy.

Melanoma is a severe skin cancer that involves abnormal cell development. This study aims to provide a new feature fusion framework for melanoma classification that includes a novel 'F' Flag feature for early detection. This novel 'F' indicator efficiently distinguishes benign skin lesions from malignant ones known as melanoma. The article proposes an architecture that is built in a Double Decker Convolutional Neural Network called DDCNN future fusion. The network's deck one, known as a Convolutional Neural Network (CNN), finds difficult-to-classify hairy images using a confidence factor termed the intra-class variance score. These hirsute image samples are combined to form a Baseline Separated Channel (BSC). By eliminating hair and using data augmentation techniques, the BSC is ready for analysis. The network's second deck trains the pre-processed BSC and generates bottleneck features. The bottleneck features are merged with features generated from the ABCDE clinical bio indicators to promote classification accuracy. Different types of classifiers are fed to the resulting hybrid fused features with the novel 'F' Flag feature. The proposed system was trained using the ISIC 2019 and ISIC 2020 datasets to assess its performance. The empirical findings expose that the DDCNN feature fusion strategy for exposing malignant melanoma achieved a specificity of 98.4%, accuracy of 93.75%, precision of 98.56%, and Area Under Curve (AUC) value of 0.98. This study proposes a novel approach that can accurately identify and diagnose fatal skin cancer and outperform other state-of-the-art techniques, which is attributed to the DDCNN 'F' Feature fusion framework. Also, this research ascertained improvements in several classifiers when utilising the 'F' indicator, resulting in the highest specificity of + 7.34%.

OAuth2.0 is a Single Sign-On approach that helps to authorize users to log into multiple applications without re-entering the credentials. Here, the OAuth service provider controls the central repository where data is stored, which may lead to third-party fraud and identity theft. To circumvent this problem, we need a distributed framework to authenticate and authorize the user without third-party involvement. This paper proposes a distributed authentication and authorization framework using a secret-sharing mechanism that comprises a blockchain-based decentralized identifier and a private distributed storage via an interplanetary file system. We implemented our proposed framework in Hyperledger Fabric (permissioned blockchain) and Ethereum TestNet (permissionless blockchain). Our performance analysis indicates that secret sharing-based authentication takes negligible time for generation and a combination of shares for verification. Moreover, security analysis shows that our model is robust, end-to-end secure, and compliant with the Universal Composability Framework.

The considerable improvement of technology produced for various applications has resulted in a growth in data sizes, such as healthcare data, which is renowned for having a large number of variables and data samples. Artificial neural networks (ANN) have demonstrated adaptability and effectiveness in classification, regression, and function approximation tasks. ANN is used extensively in function approximation, prediction, and classification. Irrespective of the task, ANN learns from the data by adjusting the edge weights to minimize the error between the actual and predicted values. Back Propagation is the most frequent learning technique that is used to learn the weights of ANN. However, this approach is prone to the problem of sluggish convergence, which is especially problematic in the case of Big Data. In this paper, we propose a Distributed Genetic Algorithm based ANN Learning Algorithm for addressing challenges associated with ANN learning for Big data. Genetic Algorithm is one of the well-utilized bio-inspired combinatorial optimization methods. Also, it is possible to parallelize it at multiple stages, and this may be done in an extremely effective manner for the distributed learning process. The proposed model is tested with various datasets to evaluate its realizability and efficiency. The results obtained from the experiments show that after a specific volume of data, the proposed learning method outperformed the traditional methods in terms of convergence time and accuracy. The proposed model outperformed the traditional model by almost 80% improvement in computational time.

Online reviews from the web are rich data sources that promote tourism analytics. Restaurants make a significant contribution to the growth of tourism in India. The literature studies on restaurant selection show that most decision frameworks do not handle uncertainty effectively and pay subtle attention to heterogeneous sources. Additionally, the extant models (i) cannot accept missing entries and its imputation; (ii) reliability of data source agents are not methodically determined; (iii) attributes’ interactions are not properly considered; and (iv) personalized restaurant ranking is unavailable. The research problem considered in this study is the rational selection of restaurants based on online reviews from heterogeneous sources to support travelers in the tourism process. The main objective of this study is to circumvent the challenge in the literatures by proposing a novel integrated decision framework that collects data from heterogeneous rating sources and transforms them into ‘probabilistic linguistic information (PLI)’, which effectively handles uncertainty by relating occurrence probability to each linguistic term. Due to the uncertain nature of online reviews, missing data are inevitable. For rational imputation of data, a case-based method is proposed. Later, the relative significance of each attribute and the reliability of each rating source are determined using ‘criteria importance through intercriteria correlation (CRITIC)’ and Dempster–Shafer-based Bayesian approximation methods. Furthermore, the PLIs from each source are aggregated by using the newly proposed discriminative weighted Muirhead mean operator. Personalized prioritization of restaurants is achieved by using the newly proposed probabilistic linguistic comprehensive (PLC) method that acquires expectation queries from customers. Lastly, the practicality of the developed framework is testified by a real-case example of restaurant selection based on the data collected from online sources

Cloud computing has emerged as a transformative technology in the healthcare industry, but selecting the most suitable CV (“cloud vendor”) remains a complex task. This research presents a decision framework for CV selection in the healthcare industry, addressing the challenges of uncertainty, expert hesitation, and conflicting criteria. The proposed framework incorporates FFS (“Fermatean fuzzy set”) to handle uncertainty and data representation effectively. The importance of experts is attained via the variance approach, which considers hesitation and variability. Furthermore, the framework addresses the issue of extreme value hesitancy in criteria through the LOPCOW (“logarithmic percentage change-driven objective weighting”) method, which ensures a balanced and accurate assessment of criterion importance. Personalized grading of CVs is done via the ranking algorithm that considers the formulation of CoCoSo (“combined compromise solution”) with rank fusion, providing a compromise solution that balances conflicting criteria. By integrating these techniques, the proposed framework aims to enhance the rationale and reduce human intervention in CV selection for the healthcare industry. Also, valuable insights are gained from the framework for making informed decisions when selecting CVs for efficient data management and process implementation. A case example from Tamil Nadu is presented to testify to the applicability, while sensitivity and comparison analyses reveal the pros and cons of the framework.