Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 3

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
EN
Around the world, several lung diseases such as pneumonia, cardiomegaly, and tuberculosis (TB) contribute to severe illness, hospitalization or even death, particularly for elderly and medically vulnerable patients. In the last few decades, several new types of lungrelated diseases have taken the lives of millions of people, and COVID-19 has taken almost 6.27 million lives. To fight against lung diseases, timely and correct diagnosis with appropriate treatment is crucial in the current COVID-19 pandemic. In this study, an intelligent recognition system for seven lung diseases has been proposed based on machine learning (ML) techniques to aid the medical experts. Chest X-ray (CXR) images of lung diseases were collected from several publicly available databases. A lightweight convolutional neural network (CNN) has been used to extract characteristic features from the raw pixel values of the CXR images. The best feature subset has been identified using the Pearson Correlation Coefficient (PCC). Finally, the extreme learning machine (ELM) has been used to perform the classification task to assist faster learning and reduced computational complexity. The proposed CNN-PCC-ELM model achieved an accuracy of 96.22% with an Area Under Curve (AUC) of 99.48% for eight class classification. The outcomes from the proposed model demonstrated better performance than the existing state-of-the-art (SOTA) models in the case of COVID-19, pneumonia, and tuberculosis detection in both binary and multiclass classifications. For eight class classification, the proposed model achieved precision, recall and fi-score and ROC are 100%, 99%, 100% and 99.99% respectively for COVID-19 detection demonstrating its robustness. Therefore, the proposed model has overshadowed the existing pioneering models to accurately differentiate COVID-19 from the other lung diseases that can assist the medical physicians in treating the patient effectively.
2
Content available remote Bonding of graphite to Cu with metal multi‑foils
EN
Graphite/Cu bonding is essential for the fabrication of graphite-based plasma-facing parts and graphite-type commutators. Transient liquid phase bonding of graphite/Cu has been conducted separately with Ti/Cu/Ti and Ti/Cu/Ni/Ti multi-foils. The interfacial microstructure and mechanical properties of the bonded joints have been characterized. For the joint with Ti/Cu/Ti multi-foils, complete melting of the Ti/Cu/Ti multi-foils and interdiffusion between the molten zone and the Cu substrate occur during the bonding process, leading to formation of Ti-Cu intermetallics in the bonding area. The liquid phase flowing toward the sidewall of the Cu substrate gives rise to a thickness of the bonding area far less than those of the as-received multi-foils. For the joint with Ti/Cu/Ni/Ti multi-foils, the bonding area can be divided into three parts (areas I, II and III). The bonding areas I and III comprise Ti-Cu intermetallics and Ti(CuxNi1-x)2, while the bonding area II consists of an Ni layer and two thin TiNi3 reaction layers. The thickness of the whole bonding area is similar to those of the as-received multi-foils, indicating that addition of Ni foil can prevent the loss of liquid phase zone by inhibiting the excessive liquid phase formation. The addition of a Ni foil in bonding of the graphite/Cu may alleviate the joint residual stress by its intermediate coefficient of thermal expansion (CTE) to accommodate any thermal mismatch in the joint and by its superior ductility and plasticity, thus resulting in shear strength promotion of the joint with the Ti/Cu/Ni/Ti multi-foils by approximately 35% when compared to the Ti/Cu/Ti multi-foils.
EN
In this paper, a study was carried out to investigate the surface roughness and material removal rate of low carbon NiTi shape memory alloy (SMA) machined by Wire Electro Spark Erosion (WESE) technique. Experiments are designed considering three parameters viz, spark ON time (SON), spark OFF time (SOFF), and voltage (V) at three levels each. The surface roughness increased from 2.1686 μm to 2.6869 μm with an increase in both SON time, SOFF time and a decrease in voltage. The material removal rate increased from 1.272 mm3/min to 1.616 mm3/min with an increase in SON time but a varying effect was observed the SOFF time and voltage were varied. The analysis revealed that the intensity and duration of the spark had an unswerving relation with the concentration of the microcracks and micropores. More microcracks and micropores were seen in the combination of SON = 120 μs, voltage = 30 V. The concentration of the microcracks and micropores could be minimised by using an appropriate parameter setting. Therefore, considering the surface analysis and material removal, the low carbon NiTi alloy is recommended to machine with 110 μs - 55 μs - 30 V (SON - SOFF - V respectively), to achieve better surface roughness with minimal surface damage.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.