Hyperspectral image classification remains challenging despite its potential due to the high dimensionality of the data and its limited spatial resolution. To address the limited data samples and less spatial resolution issues, this research paper presents a two-scale module-based CTNet (convolutional transformer network) for the enhancement of spatial and spectral features. In the first module, a virtual RGB image is created from the HSI dataset to improve the spatial features using a pre-trained ResNeXt model trained on natural images, whereas in the second module, PCA (principal component analysis) is applied to reduce the dimensions of the HSI data. After that, spectral features are improved using an EAVT (enhanced attention-based vision transformer). The EAVT contained a multiscale enhanced attention mechanism to capture the long-range correlation of the spectral features. Furthermore, a joint module with the fusion of spatial and spectral features is designed to generate an enhanced feature vector. Through comprehensive experiments, we demonstrate the performance and superiority of the proposed approach over state-of-the-art methods. We obtained AA (average accuracy) values of 97.87%, 97.46%, 98.25%, and 84.46% on the PU, PUC, SV, and Houston13 datasets, respectively.

Hyperspectral imaging (HSI) contains several land cover objects with rich spatial and spectral features. By utilizing these features, deep convolution neural networks (CNN) improved HSI classification accuracy. However, shallow CNN lacks global co-relation of the spatial and spectral features. Further, by increasing the convolution layers, trainable parameters also increase. Hence, computation cost significantly increases. In this study, a fusion-based HFTNet model is designed that extracts features via convolution and transformer block to improve classification performance. In the proposed HFTNet, the convolution block extracts local semantic features, and the transformer block captures the attention-based global features. We reduced the computation costs by dividing the query vector into two parts and passing it to convolution and transformer blocks for feature extraction. Finally, features are combined to generate enhanced semantic local and global features. The effectiveness of the proposed method is tested on four datasets and achieved an accuracy of 99.34% (UP), 97.95% (IP), 99.70% (SV), and 84.23% (KSC). We found that HFTNet takes less computation time and achieves much better classification accuracy than other methods.

In recent years, biosensing for the different types of substances affecting our day-to-day life has been evolving to a great extent. The sensing of the glucose level in food as well as the detection of blood sugar levels, are two essential steps for a healthy life. The glucose molecules, on oxidation in the presence of Ferricyanide, generate a current when connected to electrodes. In this paper, the method of current generation due to the oxidation of glucose molecules has been used and a sensor based on the principle of electrochemical sensing has been designed using COMSOL Multiphysics. Furthermore, the variation of current in the range 0-3μA with the concentration of the adsorbed glucose molecules in the range 0-100mgdl-1 on the sensing surface as well as time has been analyzed to achieve a sensitivity of 37.88μAmg-1dl for the sensor. The calculated value of sensitivity for the designed sensor is 37.88μAmg-1dl. The high sensitivity of the sensor is the key factor for its wide range of applications in the field of biosensing.

Rotary ultrasonic machining (RUM) is a feasible solution for the cost-effective machining of brittle and hard materials.This study aims to provide new information based on the drilling of hybrid composites of natural fibre and glass fibre using RUM (rotary ultrasonic machining) to improve the quality of machined holes while reducing machining costs, as well as to investigate the effects of machining and tool factors on output variables.To explore the properties of smalldiameter drilling for hybrid composite, the surface roughness along the feed direction of the drilled hole is measured.During RUM drilling, the influence of the process parameters (feed rate, depth of cut, tool rotation speed, and ultrasonic power) and output variables (MRR and SR) on the manufactured composites were analysed.In addition, the composite has undergone mechanical testing to analyse and compare its mechanical properties.The results indicate that MRR grows as a function of all process factors, with material combination and feed rate being the most effective and important.SR rises with feed rate, whereas frequency has the opposite effect.All process factors except ultrasonic power have a considerable influence on SR variation.Comparing the mechanical properties of composite materials, it was discovered that the combination material C2 had more hardness and flexural strength than all other composite combinations.But in terms of tensile strength, C3 material is superior to other composite materials.

In recent years, biosensors are being used for various medical and pharmaceutical purposes. For the formation of biosensors, one of the most commonly used phenomena is Surface Plasmon Resonance. Usually, biosensors are fabricated from optical fibers. However, when optical fibers are replaced with Photonic crystal fibers, the sensing properties are enhanced in a great way. These sensors are designed in such a way that a thin nanofilm of plasmonic metals like Gold, Silver, copper, aluminium, and plasmonic metal alloy gold-tin surround a surface containing air holes that are filled by a suitable analyte. This paper is aimed at designing an internal type PCF sensor with the analyte and multiple micrometer-sized holes in the middle. The different plasmonic materials are taken one by one and their properties are analyzed. The amplitude and wavelength sensitivities for each plasmonic material are calculated. The wavelength sensitivities for Silver, Gold, Aluminium, and copper are 1799nmRIU−1, 1830.76nmRIU−1, 1732nmRIU−1 and 1652 nm/RIU respectively. For the Gold-Tin alloy, the calculated value of the Sensitivity in the wavelength measurement is 1532.2nmRIU−1. The properties of these different sensors are then compared with each other. With the same set of chosen parameters, the best results are observed for Gold but the thickness of the gold film cannot be reduced below a few nanometers. Thus, in terms of stability and a wide range of parameters, silver has been observed to be the most suitable.

The fiber reinforced polymer composites filled with industrial stone waste was fabricated using vacuum assisted resin transfer molding (VARTM). The fabricated samples of composite plates were subjected to parametric studies of dry abrasion wear test. The control factors considered for parametric studies of were load, abrading velocity, percentage of stone waste and size of abrasive particles.

The wear characteristics of the aluminium alloy (Al-4032) matrix-based hybrid composites (AMHCs) has been investigated through the DUCOM pin-on-disc tribometer. The AMHCs have been fabricated through the bottom pouring vacuum stir casting set up, using the mixture of silicon carbide (SiC) and granite marble powder ceramic particles in equal proportion, as the hybrid reinforcement at 0, 3, 6, 9 weight%. The mass loss has been considered as the response parameter and ‘Smaller-the-Better’ criteria has been adopted as the objective model in the study. The optimization of the control parameters i.e., composition, normal load, sliding time and sliding speed has been produced using main effect of means and Analysis of Variance (ANOVA) methods. It is observed that all four control parameters have considerable influence on the wear characteristics of the AMHCs. The wear resistance of the AMHCs increases with increase in the amount of reinforcement up to 6%, followed by a decreasing trend beyond this value. This may be due to agglomeration of the reinforced particles at higher weight fraction. The percentage contribution of the control parameters such as composition, normal load, sliding time and sliding speed is 39.78%, 20.91%, 17.39% and 20.02% respectively.

The pattern of metal matrix composites can be enhanced by integrating the concept of hybrid metal matrix composite to produce newer engineering materials with improved properties. The morphological and mechanical characteristics of Al-4032/SiC/GP hybrid composites have been investigated. The aluminium alloy (Al-4032) based hybrid composites have been fabricated through the bottom pouring stir casting set up, by reinforcing the silicon carbide (SiC) and granite powder ceramic particles as the reinforcement material at various fraction levels i.e. 0, 3, 6, 9 weight% in equal proportion. The reinforcement particle size is up to 54μm. The microstructural characterization of the hybrid composite samples has been carried out using an optical microscope, SEM, and XRD. The study reveals that the reinforcement hybrid particles (SiC + GP) are almost uniformly distributed throughout the matrix phase. The mechanical properties (tensile strength, impact strength, and microhardness) of the hybrid composite samples have been obtained and found to be better than the unreinforced alloy.

The Al-4032/SiC metal matrix composites are quite useful for low density, high corrosion resistance and improved mechanical properties. Usually, 2-8% SiC reinforcement has been researched for various industrial applications. Progressive increase in the reinforcement (SiC) composition in the Al-4032 matrix causes reduction in ductility and increase in brittleness. This paper presents the research on machining aspects of the Al-4032 with 3% SiC reinforcement. Work has been carried out to study the response of cutting speed (CS), feed rate (FR) and depth of cut (DOC) upon the material removal rate (MRR) and surface roughness (SR). The experiments have been done on the Computer Numeric Control (CNC) vertical machine centre. The machining (end milling) experiments have been conducted following the Taguchi's L-9 orthogonal array. For attempting the bi-objective optimisation (i.e. maximisation of MRR and minimisation of the surface roughness), Taguchi's grey relational analysis (TGRA) has been implemented using equal weightage to both the response parameters (W-1 = W-2 = 0.5). The model so obtained has been tested through ANOVA to discover the statistically significant elements. The CS (52.40%) appears to make the largest percentage contribution to the composite response, followed by the FR (26.60%), and the DOC (19.45%).

The composites are renowned for better properties than base alloy. In general, 2-8% weight fraction of reinforcement has been researched for various industrial applications. The addition of reinforcement gives improvement in mechanical properties but badly affects ductility. Liquid route method (casting) has been employed for fabrication of SiC reinforced aluminum composites. Machining has been performed by controlling input parameters such as cutting speed, feed rate and depth of cut. Roughness parameter (R a ) and material removal rate (MRR) have been considered for evaluation of surface quality and productivity respectively. Only MRR has been given consideration for rough machining conditions. Whereas, both surface roughness and MRR have been considered for the finish machining conditions. Standard L 9 orthogonal array have been employed for the experimentation. The occurrence of hard reinforcement in the base alloy creates the casted composite tough to machine. The confirmation experiments have been performed with the optimal settings of process parameters to confirm the output responses.

This paper presents the study on effect of control parameters (composition, normal load, sliding time and sliding speed) on dry sliding wear properties (tribological behaviour) of the aluminium alloy (Al-4032)-based metal matrix composites at room temperature (25 °C). The AMCs have been fabricated through the bottom pouring vacuum stir casting set up, using the granite powder (GP), an industrial waste material, as the reinforcement at various weight fraction i.e., 0, 3, 6, 9% by weight. The mass loss has been considered as the response parameter with ‘Smaller-the-Better’ model criteria. The main effect of means and analysis of variance (ANOVA) approaches has been used to optimize the control parameters. It is observed that all four control parameters have considerable influence on the wear characteristics of the AMCs. The wear resistance of the AMCs increases with increase in the amount of reinforcement up to 6%, followed by a decreasing trend beyond this value. This may be due to agglomeration of the reinforced particles at higher weight fraction. The percentage contribution of the control parameters such as composition, normal load, sliding time and sliding speed is 32.17%, 24.97%, 24.17% and 17.93%, respectively.

The main motive of this paper is to prepare a newer composite material using non-conventional reinforcement (industrial waste) for various industrial applications. The aluminium alloy (Al-4032) matrix based composites (AMCs) have been fabricated through bottom pouring stir casting method. The granite powder (GP, ceramic particles) obtained from waste (normally available from construction site) has been used as reinforcement, at 0, 3, 6, 9 % by weight. The particle size of the reinforcement has been up to 54μm. The morphological (microstructure, SEM, XRD) and mechanical (tensile strength, micro-hardness, impact strength) characterization of the AMCs have been carried out. The morphological study reveals that the reinforcement particles (GP) are almost uniformly distributed throughout the matrix phase. The mechanical properties of the AMCs have been observed to be better than the unreinforced alloy. It is expected that the fabricated Al-4032-GP composites will be useful for the automobile parts like piston, disc brakes, high speed machinery and high-speed rotating parts etc.

The recognition of object in remotely sensed images is a complex task. The immense research is running in the field of remote sensing due to the availability of high resolution satellite images. The detection of object is a challenging task due to the complex background and small object size in remotely sensed images. The object detection in remote sensing images has a vital role in the field of navigation, salvage, and military. The performance of traditional algorithms is very less due to the usage of handcrafted features. With the initiation of Deep Learning algorithms, various Convolutional Neural Networks (CNN) based model have been utilized to detect the objects with high-resolution remotely sensed images. in this research paper various CNN based models has been compared and analyzed. Object detection approaches are broadly categorized in two ways-one based on the region matching and second based on the one-stage target detection. The researchers have compared the result of R-CNN, SPP Net, fast R-CNN, faster R-CNN, R-FCN, Mask R-CNN SSD (Single Shot Multibox Detector), DSSD (Deconvolution Single Shot Multibox Detector), FSSD, YOLO v1, YOLO v2, YOLO v3, Gaussian YOLO v3, RetinaNet which conclude that the minimal average precision for the region based category is best shown by Mask R-CNN with 39.8 mAP in the COCO parameter test and for the one stage detector YOLO v3 shows the best case for the COCO parameter test with 69.1 mAR In the second phase of the review the researchers found that in comparison to the region based and one stage detector the YOLO v3 model from one stage detector shows the best detection precision percentage with the highest 87% in identifying the object called ship.

Hyperspectral images (HSI) contain a rich set of high-dimensional features. Although these features are widely used for land cover classification. However, extraction of spectral and special features is difficult due to several bands of HSI. In the proposed study, a novel hybrid deep convolution model FHSINet (Fusion Hyperspectral Image Network) efficiently extracts features from HSI. This model has two scale feature extraction modules, each with 4 convolutions layers followed by feature fusion and classification blocks. At each scale, spatial features are extracted from HSI. After that, these features are fused to form a pool of features. We investigated the performance of HFSINet on two datasets. It achieved competitive performance compared to state-of-the-art models. Our model classification accuracy on the Pavia University dataset and Pavia Centre scenes are 94.40% and 98.72% rest reactively. In addition, the Kappa score is more than 98% on the Pavia centre scene dataset. Furthermore, the training and validation loss of the proposed model is less compared to state-of-the-art models.

This paper proposed the D-shaped photonic crystal fiber-based surface plasmon resonance sensor with high sensitivity used for sensing in medical and biochemical fields. The plasmonic material taken for this work is gold which is known for its stable configuration and the photocatalyst taken is ZnO. The confinement losses have been calculated for different refractive indices and different gold and ZnO layers. The refractive index for the analyte was varied from 1.31 to 1.36, and the wavelength was varied from 1.5 to 1.7 µm. The thickness of the gold layer is taken near about 60 nm, and the thickness of ZnO is taken around 15 nm. The wavelength sensitivity of the sensor is 1325 nm RIU−1, and the maximum amplitude sensitivity of the sensor is 240.2 RIU−1. With the thorough study of literature, it is deduced that both the sensitivities are the highest for this range of refractive indices among the existing PCF-SPR-based sensors. The designed sensors can further be used for sensing applications in the medical field for the detection of diseases, as immunosensors, and for the detection of harmful compounds.

This paper aims to demonstrate the sensing of different materials based on their refractive indices. The Surface Plasmon Resonance(SPR) phenomenon shown by Photonic Crystal Fiber(PCF) is proving to be quite useful among the sensor markets and thus, it becomes really important to design a flexible and affordable sensor of this kind with high sensitivity. SPR based PCF sensor with plasmonic material, silver embedded on it has been designed with the implementation of the Finite element method. We have modeled SPR sensors with multiple air holes and silica is the background material. The basic principle of using the analyte is that it binds the immobile molecules of silver to its own molecules which get mobilized in presence of the incident light and finally cause the variation of the refractive index. When the refractive indices of the analyte are varied from 1.25 to 1.30, a range of variation in the loss curves is seen. The core and Surface Plasmon Polaritons modes are matched based on their phases and it is done by plotting the refractive indices of core and SPP modes against the wavelength in um along with the confinement loss against wavelength. The sensor that is obtained is highly sensitive with a wavelength sensitivity of around 1932.09 RIU-1. The resolution of the sensor is 3 x 10(-5) RIU. On comparison with the literature, it is found that the sensitivity of the sensor so achieved is highly suitable for the detection purposes in the field of pharmacy and this Ag-based photonic crystal fiber sensor proves to be a revolutionary sensor in the field of biosensors. Copyright (C) 2022 Elsevier Ltd. All rights reserved.