Over the past few months, the campaign against COVID-19 has developed into one of the world's most sought anti-toxin treatment scheme. It is fundamental to distinguish cases of COVID-19 precisely and quickly to help avoid this pandemic from taking a wrong turn with a proper medical reasoning and solution. While Reverse-Transcription Polymerase Chain Reaction (RT-PCR) has been useful in detection of corona virus, chest X-Ray techniques has proven to be more successful and beneficial at detection of the effects of virus. With the increase in COVID patients and the X-Rays done, it is currently possible to classify the X-Ray reports with transfer learning. This paper presents a novel approach, i.e., Hybrid Convolutional Neural Network (HDCNN), which integrates Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) architecture for the finding of COVID-19 using the chest X-Ray. The transfer learning approach, namely slope weighted activation class planning (Grad-CAMs), is used with HDCNN to display images responsible for taking decisions. In this study, HDCNN is compared with other CNNs such as Inception-v3, ShuffleNet, SqueezeNet, VGG-19 and DenseNet. As a result, HDCNN has achieved an accuracy of 98.20%, precision of 97.31%, recall of 97.1% and F1 score of 0.97. Compared to other current deep learning models, the HDCNN has achieved better results, and this can be used for diagnosis purpose after proper approvals.

No abstract

Mechanical Alloying (MA) or High Energy Milling has been a subject of great interest for last few decades. However, in the majority of the cases the investigations are confined to areas like alloying in binary or multi-component systems from premixed powders. Very little work has been reported on high-energy milling of pure metals. There are some reports on mechanical alloying of pure metals that undergo polymorphic transformation on milling, but relatively few papers have been reported in the literature pertaining to attrition milling of pure metals, which do not fall under this category. One such attempt has been made in this investigation by subjecting a noble metal like silver with fcc crystal structure to attrition milling. The present work deals with the investigation of the effect of addition of a process control agent (PCA) on the nanocrystalline behavior of elemental silver powder subjected to high energy milling in an attritor. Elemental silver powder was subjected to attrition milling with and without addition of stearic acid as PCA. The powder samples drawn at periodic intervals during the course of milling were subjected to characterization using techniques like XRD, SEM and DSC. The variation in particle shape morphology, crystallite size and lattice strain as a function of PCA was studied.

A steel of composition Fe-0.2C-3Mn-2Si-0.5Al was fully austenized followed by a quench and partitioning heat treatment process (Q&P). The quench temperature was varied, which resulted in different volume fractions of retained austenite (RA) and martensite. Analysis of the phase evolution and the resulting microstructures during the Q&P process were carried out using different techniques namely, - dilatometry, FEG SEM, EBSD, and neutron diffraction. Mechanical properties were evaluated by standard tensile tests on samples quenched to different temperatures. The partitioning process was evaluated by dilatometry. The volume fraction of the RA was determined by neutron diffraction. It was found that the volume fraction of RA increased with an increase in the quench temperature contrary to the Speer model. It was also observed that the presence of bainite, which formed during the quench and partitioning temperature significantly stabilized the RA by carbon partitioning. The tensile test results indicated the optimum quench temperature for the best combination of strength and ductility and contrary to expectation, this did not occur in the specimen with the maximum amount of RA. In other words, the mechanical properties of the steel undergoing a Q&P process is influenced by the quench temperatures and is also affected the phase evolution which occurs during both the quench and partitioning process.

This study evaluated the microstructural evolution in a medium carbon high silicon steel during one-step, and two-step quench and partition (Q&P) processes using dilatometry experiments. The two-step Q&P process was carried out using different quench temperatures ranging from 180 to 260 °C. In the one-step process, Q&P heat treatment samples were held isothermally for ten minutes after quenching at specified temperatures ranging between 200 and 4°50 C. The two-step Q&P process yielded a higher fraction of retained austenite than a one-step Q&P process. During the isothermal hold step, the volume expansion due to carbon partitioning and austenite decomposition behavior was interpreted by experimentally determined strain values. For the one-step Q&P process, the austenite decomposition kinetics above and below the Ms temperature differed, as evidenced by the JMAK parameters. The TTT diagram generated for the one-step Q & P process showed a “swing back” at a temperature of around 355 °C.