Sri Manakula Vinayagar Educational Trust

Transfer learning techniques are recently preferred for the computer aided diagnosis (CAD) of variety of diseases, as it makes the classification feasible from limited training dataset. In this work, an ensemble FCNet classifier is proposed to classify hepatic lesions from the deep features extracted using GoogleNet-LReLU transfer learning approachs. In the existing GoogLeNet architecture three modifications are done: ReLU activation functions in the inception modules are replaced by leaky ReLU activation function; a stack of three fully connected layers are included before the classification layer; and deep features of different level of abstraction extracted from the output of every inception layer given as classifier input in order to significantly enhance the classifier performance. The performance of the proposed classifier by the virtue of the above mentioned modifications is tested on six classes of liver CT images namely normal, hepatocellular carcinoma, hemangioma, cyst, abscess and liver metastasis. The results presented in this work demonstrate the efficacy of the proposed classifier design in achieving better classification accuracy.

Nanoparticles nickel ferrite of size 6 - 8 nm, synthesized by the coprecipitation method with x varying from 0 to 1.0. The powder samples were characterized by XRD, VSM and FTIR. The average crystallite sizes of the particles were determined from X-ray diffraction. X-ray analysis showed that the samples were cubic spinel. The lattice constant (a o) increased with the increase in zinc substitution. The specific saturation magnetization (M S) of the particles was measured at room temperature. The magnetic parameter of M S, was found to decrease with the increase in zinc substitution. Fourier transform infrared spectroscopy (FTIR) spectra of the Ni1-xZn xFe2O4 with x = 0, 0.5, 1 in the range 400 - 4000 cm-1 were reported. The spinel structure and the crystalline water adsorption of Ni1-xZn xFe2O4 nanoparticles were studied by using FTIR.

The enhanced electrocatalytic activity of an electrode developed with a perovskite-type inorganic material is witnessed very often because of its unique properties.

Puducherry is a coastal region in India where the growth of Chaetomorpha antennina is very abundant on all marine concrete structures. Though the detrimental effect of this Macro algaeChaetomorpha antennina is secondary, its effect has to be ascertained. To know its effect, M20 grade concrete cubes were cast and kept in the coastal area where there is abundant growth of Chaetomorpha antennina and also laboratory simulation has been carried out. The basic mechanism by which Chaetomorpha antennina deteriorates concrete structures has been highlighted and also the detrimental effect on the algal grown concrete surface were ascertained using SEM, EDX and XRD. The result showed that there is sustainable effect by the marine algae on the concrete surface.

The cancer is a dangerous disease and untreated cancer lead to death. Breast Cancer (BC) mostly affects women community due to various reasons ranging from the genetic to the lifestyle. The screening of BC normally involves in a personal check followed by a clinical level confirmation with a biopsy test and the imaging procedures. The biopsy is a commonly employed invasive technique considered to identify the occurrence and the stage of the cancer. The imaging procedure based on a chosen modality is widely preferred in clinics, due to its non-invasive nature. The proposed work aims to develop a tumor segmentation system to examine the BC tumors using the breast MRI. The proposed technique implements the Cuckoo-Search (CS) based Kapur's thresholding and the Active-Contour (AC) segmentation to extract the tumor from the threshold breast MRI. Finally, a comparison among the ground-truth and the extracted BC tumor is performed to authenticate the performance of the proposed methodology. The outcome of this research confirms that, proposed system helps to attain a segmentation accuracy of >99% on the chosen breast MRIs.

This paper investigates about water quality monitoring system through a wireless sensor network. Due to the rapid development and urbanization, the quality of water is getting degrade over year by year, and it leads to water-borne diseases, and it creates a bad impact. Water plays a vital role in our human society and India 65% of the drinking water comes from underground sources, so it is mandatory to check the quality of the water. In this model used to test the water samples and through the data it analyses the quality of the water. This paper delivers a power efficient, effective solution in the domain of water quality monitoring it also provides an alarm to a remote user, if there is any deviation of water quality parameters.

Abstract A multi-component category of an alloy containing very specific properties revolutionized the area of material science and the present engineering era. Laser cladding, a technique for surface coating, enhances surface quality and modifies properties using advanced coating technologies. In current trends, Laser cladding is mainly used in equipment and machine parts for enhancing surface properties, repairing damaged parts and surface coating caused by its advantages such as small heat-affected zone, low substrate damage, low dilution rate and exceptional metallurgical material bonding among coating and used substrate. Laser cladding improves substrates’ mechanical and various functional-specific properties, ensuring a high-quality balance between mechanical and surface attributes. The research society was able to investigate laser-cladding HEAs coatings because of the superior attributes of HEAs compared to ordinary alloys. This paper reviews current developments in laser-cladding HEAs coatings and the application of laser-cladding technology to HEAs materials. The laser cladding high-entropy alloy coatings have potential applications in corrosion, wear, and oxidation resistance, as well as their respective substrates. Cladded coatings composed of HEAs materials are measured to have shown potential applications in recent technology, opening exciting possibilities for the future. The study also discusses current trends and future prospects.

Strategic combination of<bold>CQDs</bold>/f-MWCNTs/<bold>GO</bold>/GCE for pico-molar arsenic sensing.

The current study reports a new, simple and fast method using a flake-like dysprosium molybdate (Dy2MoO6; FL-DyM) nanostructured material to detect the antibiotic drug metronidazole (METZ). This nanocomposite material was employed on the surface of a glassy carbon electrode (GCE) to develop the electrode (FL-DyM/GCE). Further, the synthesized FL-DyM was systematically characterized by powder X-ray diffraction (XRD), Raman spectroscopy, scanning electron microscopy (SEM), transmission electron microscopy (TEM), energy-dispersive X-ray diffraction (EDS), elemental mapping, X-ray photoelectron spectroscopy (XPS), and Brunauer-Emmett-Teller (BET) analyses. Cyclic (CV) and differential pulse voltammetry (DPV) techniques were used to study the electrochemical properties. The FL-DyM/GCE-based sensor demonstrated excellent selectivity and sensitivity for the detection of the drug METZ, which could be attributed to the strong affinity of FL-DyM towards the -NO2 group in METZ, and the good electrocatalytic activity and conductivity of FL-DyM. The fabrication and optimization of the working electrode were accomplished with CV and DPV obtained by scan rate and pH studies. Compared to the bare GCE and other rare-earth metal molybdates, the FL-DyM/GCE sensor displayed a superior electrocatalytic activity response for METZ detection. The sensor demonstrated a good linear relationship over the concentration range of 0.01-2363 μM. The quantification and detection limits were found to be 0.010 μM and 0.0030 μM, respectively. The FL-DyM/GCE sensor displayed excellent selectivity, repeatability, reproducibility, and stability for the detection of METZ in human urine and commercial METZ tablet samples, which validates the new technique for efficient drug sensing in practical applications.

Glaucoma, a severe eye disease leading to irreversible vision loss if untreated, remains a significant challenge in healthcare due to the complexity of its detection. Traditional methods rely on clinical examinations of fundus images, assessing features like optic cup and disc sizes, rim thickness, and other ocular deformities. Recent advancements in artificial intelligence have introduced new opportunities for enhancing glaucoma detection. This research explores a hybrid approach combining UNet++ and Capsule Network (CapsNet) architectures for accurate glaucoma diagnosis. UNet++ is employed for semantic segmentation, focusing on defining optic discs and cups, which are crucial for detecting the disease. CapsNet leverages its ability to recognize hierarchical patterns, providing more sensitive detection of glaucomatous changes than conventional Convolutional Neural Networks. Pre-processing of retinal images involves advanced techniques like Histogram Equalization and Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance image quality. The model is trained and tested on benchmark datasets, showing superior performance in optic cup/disc segmentation and glaucoma detection accuracy compared to existing state-of-the-art models.•Hybrid Model Efficiency: The combined use of UNet++ and CapsNet offers improved accuracy in optic cup and disc segmentation.•Enhanced Image Quality: Application of Histogram Equalization and CLAHE techniques significantly boosts the quality of retinal images.•Superior Performance: The hybrid approach outperforms traditional and contemporary models in glaucoma detection accuracy.

The performance of wireless sensor networks strongly depends on their network lifetime. As a result, Dynamic Power Management approaches with the purpose of reduction of energy consumption in sensor node, after deployment and designing of the network, have drawn attentions of many research studies. Recently, there have been a strong interest to use the intelligent tools especially neural networks in energy efficient approach of Wireless sensor networks, due to their simple parallel distributed computation, distributed storage, data robustness, auto-classification off sensor nodes and sensor reading. Dimensionality reduction and prediction of classification of sensor data obtained simply from the outputs of the neural-networks algorithms can lead to lower communication costs and energy conservation. All these characteristics are well considered in the neural network based algorithms such as ART, ART1, FUZZY ART, IVEBF and EBCS. These algorithms and their performance in improving the lifetime of the WSN are discussed in this paper.

Skin cancer is the uncontrolled growth of irregular cancer cells in the human-skin's outer layer. Skin cells commonly grow in an uneven pattern on exposed skin surfaces. The majority of melanomas, aside from this variety, form in areas that are rarely exposed to sunlight. Harmful sunlight, which results in a mutation in the DNA and irreparable DNA damage, is the primary cause of skin cancer. This demonstrates a close connection between skin cancer and molecular biology and genetics. Males and females both experience the same incidence rate. Avoiding revelation to ultraviolet (UV) emissions can lower the risk rate. This needed to be known about in order to be prevented from happening. To identify skin cancer, an improved image analysis technique was put forth in this work. The skin alterations are routinely monitored by this proposed skin cancer categorization approach. Therefore, early detection of suspicious skin changes can aid in the early discovery of skin cancer, increasing the likelihood of a favourable outcome. Due to the blessing of diagnostic technology and recent advancements in cancer treatment, the survival rate of patients with skin cancer has grown. The strategy for detecting skin cancer using image processing technologies is presented in this paper. The system receives the image of the skin lesion as an input and analyses it using cutting-edge image processing methods to determine whether skin cancer is present. The Lesion Image Analysis Tools use texture, size, and shape assessment for image segmentation and feature phases to check for various cancer criteria including asymmetries, borders, pigment, and diameter. The image is classified as Normal skin and a lesion caused by skin cancer using the derived feature parameters.

The Cz-DEPVI device showed high efficiencies of <italic>L</italic>: 13955 cd m⁻², <italic>η</italic>_ex: 4.90%, <italic>η</italic>_c: 6.0 cd A⁻¹, <italic>η</italic>_p: 5.4 lm W⁻¹ and CIE coordinates of (0.15, 0.06) at 2.8 V.

Island tourism, while offering unique and picturesque experiences, is often accompanied by a distinct set of transportation challenges that can significantly impact the overall visitor experience. These challenges stem from the geographical isolation of islands, which can complicate the movement of tourists and goods, and can influence both the efficiency and accessibility of travel to and within these destinations. Understanding and addressing these transportation challenges is crucial for ensuring a smooth and enjoyable experience for visitors while supporting the sustainable development of island tourism. One of the primary challenges in island tourism transportation is the dependency on limited and often expensive modes of transport. Many islands rely heavily on air travel and ferries as their primary means of connecting with the mainland and other destinations. This reliance can lead to issues such as high travel costs, limited flight or ferry schedules, and potential delays due to weather conditions or operational constraints.

In recent years, a considerable number of approaches have been proposed by the researchers to evaluate infectious diseases by examining the digital images of peripheral blood cell (PBC) recorded using microscopes. In this chapter, a semi-automated approach is proposed by integrating the Shannon's entropy (SE) thresholding and DRLS-based segmentation procedure to extract the stained blood cell from digital PBC pictures. This work implements a two-step practice with cuckoo search (CS) and SE-based pre-processing and DRLS-based post-processing procedure to examine the PBC pictures. During the experimentation, the PBC pictures are adopted from the database leukocyte images for segmentation and classification (LISC). The proposed approach is implemented by considering the RGB scale and gray scale version of the PBC pictures, and the performance of the proposed approach is confirmed by computing the picture similarity and statistical measures computed with the extracted stained blood cell with the ground truth image.

Chronic Obstructive Pulmonary Disease (COPD) is a dreadful disease which is a wide umbrella comprises of emphysema, bronchitis etc. It threatens the life of almost nearly 3 million people all over the world. The diagnosis of COPD can be detected in a better manner based on the lung sound analysis with the help of deep learning models such as convolutional neural network (CNN). In this work, the presence of COPD with different class of the sound like normal breathe sounds and abnormal breathe sounds such as wheeze, crackle and rhonchi are classified by using multi-class classifier. Spectral descriptor features from linear spectrum and MFCC from Mel spectrum are extracted. For experimentation and classification, a total of 596 lung sound signals are considered in this work. The classifier such as K-NN and decision tree are used to obtain an improved accuracy compared to binary machine learning classifier. The results indicates than an overall accuracy of 96.7% is obtained with multi-class classifiers using deep learning CNN model. The multi-class classifier results are also compared with SVM classifier.

A CAD system for diagnosing the mammograms is proposed in this work. The mammogram image is preprocessed using adaptive median filter and ROI is segmented using otsu's thresholding technique. Then the extracted GLCM features from ROI were given to the classifier. The classifiers such as SVM and KNN were used in this CAD system and the performance metrics were analyzed. The classification accuracy of SVM is 95.7% and sensitivity is 0.91 which is higher than KNN classifier. This demonstrates that the automated detection of breast cancer with greater accuracy and sensitivity in our CAD system is reliable as an aid to radiologists.

Ni1-xZn xFe2O4 (x = 0 to 1) nanoparticles of size less than 9 nm were prepared by a chemical coprecipitation method which could be used for ferrofluid preparation. XRD, VSM and DTA-TG (STA) were used to study the effect of variation in Zn substitution and its influence on particle size, magnetic properties such as M S, H C and Curie temperature, as well as on the water content. ICP was used to estimate Ni, Zn and Fe concentrations. The average crystallite size (DaveXR) of the particles was found to decrease from 8.95 to 6.92 nm with increasing zinc substitution. The lattice constant (a o) increased with increasing zinc substitution. The specific saturation magnetization (M S) of the particles was measured at room temperature. Magnetic parameters such as M S, Hc, and Mr were found to decrease with increasing zinc substitution. Estimation of the water content, which varies the Zn concentration, plays a vital role for the correct determination of cation contents. The Curie temperature was found to decrease with increasing zinc substitution.

Optimizing the impact properties of polymer composites is essential in aircraft industries. Hybridization of fibres is one of the efficient methods to enhance the impact properties of polymer composites. Dispersion of nanoparticles into epoxy resin improves the toughness of composites. This study examines the low-velocity impact (LVI) behaviour of hybrid epoxy-based carbon/glass fibre-reinforced laminates. Initially, the epoxy resin was modified with 0, 0.5, 1, 1.5, and 2 wt% of nanoclay and TiO 2 nanoparticles using mechanical stirring followed by an ultrasonication method. To investigate the influence of stacking sequences, laminates were fabricated with (90 G/0 G/90 C) S , (90 G/0 C/90 G) S, and (90 C/0 G/90 G) S . The samples used for this study are six-ply symmetric laminates. Laminates were impacted with different impact energies between 30 and 80 J with an impact velocity of 7 m/s to generate damages. The residual strength of damaged specimens is determined using compression after the impact test. The order of stacking, fibre orientation, and the presence of nanoparticles all have a significant impact on the residual strength of laminates. By using C-scan images, layer-wise damage mechanisms were identified. The specimen with (90 C/0 G/90 G) S sequence has very high damage resistance compared to other laminates.

Ailments of the gastrointestinal tract (GIT), including bleeding, ulcers, polyps, Crohn's disease, and cancer, are becoming more prevalent. Ulcers and bleeding in the small and large bowels are two of them that are particularly common. Medical experts find the manual diagnostic process to be both time-consuming and difficult. As a result, experts have suggested computerised techniques for the identification and classification of certain disorders. Medical video endoscopy produces a huge volume of images, thus it takes a long time for specialists to look over them all. Early detection and diagnosis of certain illnesses can result in successful therapy. SqueezeNet, ResNet-101, and DenseNet-169 are three deep learning-based models that we introduce in this paper and assess for their capacity to diagnose a dataset of lower gastrointestinal disorders. There are 5,000 images in the Kvasir dataset, similarly distributed among five different lower gastrointestinal conditions, including ulcerative colitis, polyps, normal cecum, and normal pylorus. The deep feature vector is processed using the softmax activation function, which divides the input images into five groups. Surprisingly, all of the convolutional neural network (CNN) models had exceptional performance, with DenseNet-169 reaching accuracy, specificity, precision, recall, and F1 Score values of 97.8%, 98.07%, 97.5%, 96.02% and 97.6%.