Panimalar Engineering College

Stroke is considered a cerebrovascular disorder that causes severe damage to brain tissues, leading to complete loss of motor abilities in patients, if left untreated. Clinically, information from brain images, like computed tomography (CT) and magnetic resonance imaging (MRI), is used to provide a better diagnosis by identifying abnormal areas in the brain. Nowadays, various techniques are used to detect stroke with high accuracy by extracting essential information from the images. Meanwhile, the existing methods often struggle to combine multimodal data and are affected by the inherent noise in the images. This paper presents a convolutional log cross-entropy Taylor network (Conv-LCTNet) for brain stroke detection. Here, the input CT and MRI images are acquired from the dataset, and then, the images are augmented using a generative adversarial network (GAN). The augmented images are separately used for image preprocessing. Further, the preprocessed images are segmented using the dual adaptive cuckoo catfish optimizer network (DCCO-Net), and multiple features are extracted using various extractors. Following this, the features are concatenated and applied to Conv-LCTNet for detecting brain stroke. Evaluations show that the Conv-LCTNet attained a high recall of 97.031

The objective of the study is to develop a reliable and energy-efficient urban UAV navigation system capable of overcoming GPS degradation, localization errors, dynamic obstacles, and inefficient flight trajectories by leveraging cellular network signals and advanced deep learning strategies. This research introduces a hybrid deep learning-based navigation system to enhance UAV reliability through cellular network signals. A multi-objective cost function is designed to optimize the uncertainty in motion, smoothness in trajectory, distance traveled, and the avoidance of collisions. A three-dimensional geometry-based channel propagation model (3DGCPM) is used to reduce the amount of inter-cellular interference. The federated meta multi-agent graph deep reinforcement learning (F2MGDRL) framework enables UAVs to adapt and learn in a decentralized and distributed manner by combining federated learning to allow for privacy-preserving decentralized training, meta-learning for fast adaptation to the changing environment in which the UAV is located. An adaptive enzyme action optimizer (AEAO) module provides for efficient and smooth trajectories with minimal abrupt turns. Experimental results show a success rate of 98.7

This study introduces a new method for classifying Diabetic Retinopathy (DR) with enhanced accuracy, focusing on addressing the limitations of existing approaches. DR classification is still a difficult task due to the presence of various complex and overlapping lesions in the retinal images. The primary goal is to develop an extremely effective model that can identify the different phases of diabetic retinopathy (DR) very accurately from the fundus images, therefore reducing the misclassification rates and helping in the very early diagnosis. The focus of our inquiry is on the determination of whether the new Hierarchical Auto-Associative Inception Polynomial Transformer Convolutional Neural Network with Snake Optimizer (HAutoAIPTCNNet + SO) will result in a significantly higher level of accuracy when compared with the existing methods. Fundus images from the EyePACS and DIARETDB1 datasets are processed using Gradient Domain Guided Filtering (GDGF) for enhanced contrast, noise reduction, and normalization. Segmentation of DR-affected regions is achieved with the EfficientNet and Cascaded Visual Attention Network (ENet-CVAN) framework. The classification process then employs the Hierarchical Auto-Associative Inception Polynomial Transformer Convolutional Neural Network (HAutoAIPTCNNet) further refined through the Snake Optimizer (SO). The HAutoAIPTCNNet + SO model, developed in Python, features both hierarchical and polynomial transformations for the precise imaging of retinal characteristics. The suggested HAutoAIPTCNNet + SO approach reached a classification accuracy of 99.8

Utilizing smart materials sourced from bio-resources is essential in the context of the circular economy and the increasing societal desire for digitization. This work outlines the development of resistive sensor applications utilizing composites of gelatin and copper nanowires (CuNWs), aiming to replace synthetic polymers with natural alternatives in multifunctional composites. The physical interactions between the copper nanowires and the hydroxyl groups in gelatin have been demonstrated, and the copper nanowires are uniformly dispersed throughout the gelatin matrix. The incorporation of CuNWs into the gelatin matrix enhances the thermal stability of the gelatin, however, the amount of CuNWs did not alter triple helix configuration of polymer matrix. Composites containing 6 wt

This study investigates the parametric optimization of friction stir welding (FSW) for joining AA1100 alloys using the (MOGOA) multi-objective grasshopper optimization algorithm the non-dominated sorting genetic algorithm II (NSGA-II). Regression equations was employed to determine to forecast hardness and tensile strength of frictional stir welding joints, whereas tensile testing and hardness measurements were conducted to acquire the empirical evidence. The SECA–COCOSO framework, together with the empirical model, was utilized to structure experimental methodology, while empirical results and the adequacy of the predicted were evaluated through a systematic examination of difference. Five distinct instrument categories was evaluated for various amounts of input parametric rates. Optimum input parameters included a tool rotation speed of 1300 rpm, a welding speed of 60 mm/min, an axial force of 5.5 kN, and a cylindrical threaded tool pin, which demonstrated the maximum. The axial force emerged as the predominant input parameter affecting microhardness and the output tensile strength, succeeded by the tool pin shape and welding speed. NSGA-II demonstrated superior optimization relative to MOGOA. Fractography study revealed a ductile fracture in sample ‘2’, which had the highest UTS of 173.36 MPa and an improved Vickers hardness of 99.13 HV, whereas maximum hardness recorded were 93.75 HV in samples 30 throughout the empirical experiments.