FFCAEs: An efficient feature fusion framework using cascaded autoencoders for the identification of gliomas

Intracranial tumors arise from constituents of the brain and its meninges. Glioblastoma (GBM) is the most common adult primary intracranial neoplasm and is categorized as high-grade astrocytoma according to the World Health Organization (WHO). The survival rate for 5 and 10 years after diagnosis is under 10%, contributing to its grave prognosis. Early detection of GBM enables early intervention, prognostication, and treatment monitoring. Computer-aided diagnostics (CAD) is a computerized process that helps to differentiate between GBM and low-grade gliomas (LGG), using the perceptible analysis of magnetic resonance (MR) of the brain. This study proposes a framework consisting of a feature fusion algorithm with cascaded autoencoders (CAEs), referred to as FFCAEs. Here we utilized two CAEs and extracted the relevant features from multiple CAEs. Inspired by the existing work on fusion algorithms, the obtained features are then fused by using a novel fusion algorithm. Finally, the resultant fused features are classified with the Softmax classifier to arrive at an average classification accuracy of 96.7%, which is 2.45% more than the previously best-performing model. The method is shown to be efficacious thus, it can be useful as a utility program for doctors.     

Studies on fly ash/coir/sugarcane reinforced epoxy polymer matrix composite

In the past years studies were conducted on natural fibre reinforced polymer composites to observe their mechanical properties in order to decide their industrial applications. These composites have already been used in many applications from aerospace to sporting equipment. These green composites can be used as a replacement for synthetic composites. This is because the natural fibres are eco-friendly, biodegradable, renewable, etc. In this work, an attempt is made to reinforce fly ash, coir fibre and sugarcane fibre with epoxy polymer matrix. Central composite design under response surface methodology (RSM), one of the approaches of design of experiments (DOE) is used to determine optimum sample preparation conditions of fly ash, coir fibre and sugarcane fibre. Both tensile and flexural (three-point bending) tests are conducted on these fabricated composites to determine their materialistic characteristics. Analysis of variance (ANOVA) is carried out using Minitab software to find the influence of fly ash, coir fibre, sugarcane fibre on composites. Regression equations obtained from analysis of variance is used to calculate values. Experimental and calculated values are compared and their error % are calculated and tabulated. Response surface optimization study is carried to find the optimized parameters of composites. It is observed that, increase in wt.% of coir fibre and decrease in wt.% of fly ash and sugarcane fibre, increases yield stress and these parameters have mixed impact on ultimate tensile stress. The addition of fly ash, coir fibre and sugarcane fibre in low percentages increases Young's modulus. Increase in wt.% of fly ash and coir fibre and decrease in wt.% of sugarcane, increases flexural modulus and flexural stress.     

Controllability of fractional dynamical systems with distributed delays in control using ψ-Caputo fractional derivative

This research investigates the controllability of linear and non-linear fractional dynamical systems with distributed delays in control using the $\psi$-Caputo fractional derivative. For controllability of linear systems, the positive definiteness of Grammian matrix, which is characterized by Mittag–Leffler functions, is used to provide necessary and sufficient conditions. For the controllability of non-linear systems, the iterative technique with the completeness of $X$ is used to obtain sufficient conditions. Using the $\psi$-Caputo fractional derivative, this study is new since it investigates the ideas of controllability. A couple of numerical results are offered to explain the theoretical results.     

An efficient lightweight authentication scheme for human-centered industrial Internet of Things

Internet of Things (IoT) specifies a transparent and coherent integration of assorted and composite nodes. Unification of these nodes with large resources and servers has brought advancement in technology for industrial and government services. The industrial IoT (IIoT), with smart nodes, enhance the development and manufacturing of industrial process, which is on demand now. However, the security concern is substantial, and it is required to control to perform prosperous assimilation of IIoT. Authentication of these smart nodes and establishing mutual trust among them is essential to keep vulnerabilities and potential risks out. Hence, this paper presents an efficient lightweight secure authentication protocol from the perspective of human-centered IIoT. This proposed scheme assumes a registration center which simply generates public and secret information for a node when it initially joins the network. Once registration is done, the registration center is not needed anymore, and advanced processes like mutual authentication, secure key exchange, and communications are independently done by nodes involved. Furthermore, we show that this scheme can reduce exponential computations and computational overhead and resolves various possible attacks.