DDCNN-F: double decker convolutional neural network 'F' feature fusion as a medical image classification framework.

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%.

SSH-DAuth: secret sharing based decentralized OAuth using decentralized identifier.

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.

Double hierarchy hesitant fuzzy linguistic information based framework for personalized ranking of sustainable suppliers.

With the growing appetite for reducing carbon footprint, organizations are tirelessly working towards green practices and one such crucial practice is purchasing raw materials from sustainable suppliers (SSs). Inspired by the drift in purchase habits, several sustainable suppliers emerged in the market and a rational selection of a suitable sustainable supplier is a complex decision problem. There are many criteria associated with the evaluation of sustainable suppliers, and double hierarchy hesitant fuzzy linguistic (DHHFL) structure is a popular preference style that accepts complex linguistic expressions in the natural language form. Earlier studies on sustainable supplier selection infer that (i) complex linguistic expressions are not properly modeled, (ii) interrelationship among criteria must be considered during importance assessment, (iii) direct assignment of attitudinal values of experts causes bias and subjectivity, and (iv) nature of criteria play a crucial role in ranking SSs. To overcome these limitations, a novel MCMD framework is proposed in this study in which the attitudinal characteristic values of experts are calculated by using a variance approach. Besides, importance of diverse sustainable criteria is calculated by proposing novel attitude-CRITIC approach that supports proper capturing of interrelationship among criteria along with experts' attitude values. Later, weighted distance approximation algorithm is presented to DHHFL setting for personalized and cumulative ranking of SSs by properly considering nature of criteria. These methods are integrated to form a framework under DHHFL setting, and its usefulness is exemplified by using a case study of SS selection in an automotive firm. A comprehensive sensitivity analysis as well performed to test the validity of the proposed model approves the applicability, validity, and robustness of the model. Lastly, comparison is done with other methods to understand the merits and shortcomings of the proposal.

Clean energy selection for sustainable development by using entropy-based decision model with hesitant fuzzy information.

Smart cities development is an ambitious project launched in India in 2015 with around 14 billion USD. Smart city mission program primarily aimed at reducing the carbon footprint and encouraging green and sustainable practices. Under this context, clean energy usage for demand fulfillment became the prime focus. India's geographic location gifts the nation with diverse clean energy sources (CES). Owing to the multiple sustainable criteria that are both conflicting and correlated, there is an urge for a multi-criteria decision approach. Previously, literatures on CES selection have not been able to grab the hesitation properly and handle uncertainty effectively. Since the human mind is dynamic, hesitation is an integral part of choice making. Hesitant fuzzy set (HFS) is a generic set that captures hesitation better. Driven by these claims, in this work, a new framework for CES selection is developed. Attitude-driven entropy measure is proposed for criteria weight assessment, and a mathematical model is formulated for ranking CESs. Together, these methods constitute a decision framework that (i) considers the attitude of experts and captures hesitation during rating process and (ii) acquires partial personal choices from experts before ranking CESs. To testify the framework, a case study from a smart city within Tamil Nadu (a state in India) is explained. Sensitivity analysis reveals the robustness of the framework, and comparison with other works showcases the novel innovations of the proposal.

Prioritization of zero-carbon measures for sustainable urban mobility using integrated double hierarchy decision framework and EDAS approach.

Zero-carbon is the current buzzword triggering the minds of every people in the world. The current pandemic situation has given the world an alarm to act towards the reduction/eradication of carbon footprint. Developing countries like India are striving hard to strike a balance between sustainability and global growth. To support the nation, certain measures and their prioritization would be helpful. Motivated by this notion, in this study, a new framework is proposed with double hierarchy fuzzy information, which not only gives experts a better style to articulate preferences linguistically but also makes a rational decision with methodical support. Mayor's transport strategy, 2018 is a popular document that provides valuable information towards sustainable transport practices, and the measures considered in this study are adapted from the same. In this framework, (i) a novel attitudinal evidence-based Bayesian approach is proposed for criteria weight estimation; (ii) experts' weights are determined by using variance approach, and (iii) Evaluation based on distance from average solution (EDAS) approach is extended for prioritizing zero-carbon measures. These approaches are integrated into a framework and its practicality is exemplified by considering a case example of prioritizing measures for a smart city in India. Finally, comparison with extant methods reveals the merits and shortcomings of the proposal.