Pulmonary diseases, including pneumonia, tuberculosis, asthma, COPD, fibrosis, emphysema, and COVID-19, pose significant diagnostic challenges. Traditional machine learning models often produce suboptimal classification accuracy. To tackle this challenge, an enhanced version of AlexNet, termed Improved AlexNet with Convolutional Neural Networks (IANET), is introduced as a deep transfer learning framework specifically optimized for pulmonary disease classification. IANET incorporates enhanced preprocessing techniques such as median and Wiener filtering and CLAHE enhancement, refining image quality for better diagnostic performance. Using NIH chest X-ray datasets and real-time hospital data, IANET achieved classification accuracies of 96% and 96.8%, respectively, surpassing existing methods. Unlike a direct application of AlexNet, IANET includes targeted architectural modifications-such as reduced kernel sizes, optimized stride values, and refined filter numbers-designed to preserve local image details while reducing complexity. Combined with our novel fusion filter, this customized approach significantly improves diagnostic accuracy for pulmonary disease classification. The results demonstrate IANET's potential in assisting specialists with precise, automated pulmonary disease diagnoses.

Pulmonary emphysema is one of the lung disorders that are caused owing to the uncharacteristic enhancement of alveoli. Some early emphysema detection medical analyses are CT scanning and spirometry to minimize mortality. Thus, to resolve the drawbacks presented in the existing approach, a new pulmonary emphysema detection model will be developed in this paper. Initially, the required images related to pulmonary emphysema were collected from standard resources and fed to pre-processing stage. Further, the pre-processing is done with Gabor filtering, adaptive contrast and histogram equalization. The parameters of adaptive contrast and histogram equalization are tuned by utilizing a developed hybrid approach named Hybrid Mud Ring Tunicate Swarm Algorithm (H-MRTSA). Additionally, the pre-processed images are offered to the phase of segmentation, where it is performed using the Deep U-net model. Further, the input segmented images are given to the pulmonary emphysema disease detection region. In this phase, pulmonary emphysema is detected using an Attention-based Residual Network (A-ResNet), in which the parameters in the network are tuned using MR-TSA. The performance of the developed H-MRTSA-A-ResNet model achieves superior performance like 97

Emphysema is a type of chronic disorder that occurs due to the abnormal expansion of the alveoli in the lungs. This causes several difficulties to breathe, and the final stage of emphysema leads to lung cancer. By using pulmonary function tests and Computed Tomography (CT) scans, the progressive destruction of emphysema disease can be addressed. The early-stage detection of emphysema may help to reduce the risk of the patients. The primary diagnosis should be carried out with the help of CT and spirometry analysis to reduce mortality rates. In the computer vision-based approaches, the inter-observer and intra-observer variations are difficult to analyze. To overcome these complications, an enhanced emphysema disease detection model with adaptive deep-structured architecture is implemented. At first, the input images are undergone, where histogram equalization, pre-processing stage, filtering technique, and Contrast Limited Adaptive Histogram Equalization methods are utilized. Then, the pre-processed images are fed into the lung segmentation process by using Fuzzy C-Means Clustering (FCM) and Adaptive Region Growing. Those segmented images are provided as input for the proposed emphysema detection by utilizing Adaptive Multi-Scale Dilation Assisted Residual Network with Bi-LSTM Layer (AMSD-RN-Bi-LSTM) layer, in which the constraints are optimized by using Improved Honey Badger Algorithm (IHBA). Through the experimental analysis, the proposed pulmonary emphysema detection model shows the tendency to give a rapid diagnosis of a disease that aids to identify the disease and diagnose them effectively.

In recent years, Digital holography has emerged as an exceptional imaging technology for tracking high-contrast object particles and, interestingly, analyzing 3D object data in real time. The best quality images can be obtained effectively using the auto-focusing algorithm. In this paper, the focus location of the object is traced with a deep learning-based auto-focusing algorithm. The proposed model constructs a large feature pool by considering different focus measures to reconstruct objects from two out-of-focus images. The preferred features are selected through the proposed Support vector Machine-based Recursive Feature Elimination (SVM-RFE) method. Therefore, the inappropriate features are eliminated, and the reconstruction distance is obtained by the suggested stacked autoencoder with sparse Bayesian regression (SAE-SBR) model training. It is common to find a twin image in the reconstructed image, and such noise interference is minimized with the presented high-speed iterative shrinkage/thresholding (HS-IST) based compressive sensing (CS) algorithm. Reconstruction distances are predicted by the proposed method with a standard variation of about 0.036μm. The proposed SAE-SBR predicts the right reconstruction distance of a single hologram, and it is 600 times faster than traditional autofocusing techniques like Dubois and Tamura of Gradient (ToG). Also, the computation time of the proposed model is 33.3

Chronic obstructive pulmonary disease (COPD) is a general clinical issue in numerous countries considered the fifth reason for inability and the third reason for mortality on a global scale within 2021. From recent reviews, a deep convolutional neural network (CNN) is used in the primary analysis of the deadly COPD, which uses the computed tomography (CT) images procured from the deep learning tools. Detection and analysis of COPD using several image processing techniques, deep learning models, and machine learning models are notable contributions to this review. This research aims to cover the detailed findings on pulmonary diseases or lung diseases, their causes, and symptoms, which will help treat infections with high performance and a swift response. The articles selected have more than 80% accuracy and are tabulated and analyzed for sensitivity, specificity, and area under the curve (AUC) using different methodologies. This research focuses on the various tools and techniques used in COPD analysis and eventually provides an overview of COPD with coronavirus disease 2019 (COVID-19) symptoms.

Lung disease (LD) is a dreadful disease that affects numerous people in various ways; hence, it is considered the foremost reason for death around the globe. To reduce LDs, affording earlier treatment is highly required. However, learning lung features and finding abnormalities are highly complex due to the lack of enhanced diagnosing techniques. Hence, this article introduces a novel hybridized deep learning (DL) scheme for automatically classifying LDs with improved accuracy. The proposed study undergoes three major stages: pre-processing, feature extraction, and LD classification. Initially, the pre-processing stage reduces the noises from the inputs using an improved Diffusion-based unsharp masking filtering and crispening (ID-UMFC) scheme, where the image quality is improved. Then, to reduce the complexity problems, an Extended Two-Dimensional Wavelet Transform (E-2DWT) technique is proposed in the feature extraction stage to extract useful features efficiently. Finally, the Deep Bidirectional Long short-term Term Memory-Spiking Neural Network (DBLSTM-SNN) based DL technique is introduced to classify multiple classes of LDs accurately. The proposed method is implemented in Python, and a publicly available chest X-ray 14 dataset is utilized in this study. The various performance measures such as accuracy, precision, false discovery rate (FDR), time complexity, kappa and positive predictive value (PPV) are analyzed. In addition, statistical analysis is also studied and compared with different existing studies. The proposed method obtains an overall accuracy of 99.7%, precision of 98.9%, kappa of 98.2%, FDR of 1.05%, PPV of 98.9% and time complexity of 64.4 s.

Speech recognition has been an active research topic for more than 50 years. Interacting with the computer through speech is one of the active scientific research fields particularly for the disable community who face variety of difficulties to use the computer. Such research in Automatic Speech Recognition (ASR) is investigated for different languages because each language has its specific features. Especially the need for ASR system in Tamil language has been increased widely in the last few years. In this paper, a speech recognition system for individually spoken word in Tamil language using multilayer feed forward network is presented. To implement the above system, initially the input signal is preprocessed using four types of filters namely preemphasis, median, average and Butterworth bandstop filter in order to remove the background noise and to enhance the signal. The performance of these filters are measured based on MSE and PSNR values. The best filtered signal is taken as the input for the further process of ASR system. The speech features being the major part of speech recognition system, are analyzed and extracted via Linear Predictive Cepstral Coefficients (LPCC). These feature vectors are given as the input to the Feed-Forward Neural Network for classifying and recognizing Tamil spoken word. Experiments are done with sample Tamil speech signals and its performance are measured based on Mean Square Error (MSE) rate. The adopted network with the above specified parameters has produced the best result for limited vocabulary.

One of the largest obstacles in treating chronic illnesses, according to the medical community, is identifying and treating cancer. Before beginning advanced treatment techniques, experts must identify and classify nodules in the patient's Chest radiograph or crunched tomography scan pictures. Modern deep learning model advancements can be applied to create advanced computer-aided diagnosis methods to find malignant nodules. The suggested method classifies nodules seen in CT scan pictures as malignant or benign utilizing a Particle Swarm Optimization-RNN. The identification and categorization of malignant nodules has made substantial use of image analysis and neural networks. RNNs are therefore more suited for the job of classifying and detecting nodules. Additional characteristics of PSO-RNNs include multiple feature extraction. The suggested PSO-RNN model, which makes use of the domain expertise of the CT scan pictures of the lung in the department of medicine and Multilayer Perceptron, will be appropriate for the early recognition and characterization of CT images including nodules with an accuracy of 93.52%.

In 2019, chronic obstructive pulmonary disease (COPD) led to 3.23 million deaths on a global scale, positioning it as the third most prevalent cause of mortality. Emphysema and chronic bronchitis are termed the World Health Organization (WHO) uses to describe COPD. The typical depiction of emphysema involves the damage to the tiny air sacs located at the ends of the lung airways. Chronic bronchitis causes airway irritation, coughing, and phlegm. Deep learning was applied to multiple CNN architectures (AlexNet, ResNet 50, ResNet 101, and DenseNet 201) to extract features from chest X-rays. Chest x-rays were classified as having or not having emphysema using machine learning classifiers, including nearest neighbor classifiers (kNN), kernel approximation classifiers (SVM kernel and logistic regression), neural network classifiers (NN), decision tree classifiers, Naive Bayes classifiers, discriminant analysis, and support vector machines (SVM). Densenet201+ SVM achieved 93.1% total validation accuracy across all 7548 images with an AUC of 0.9781, and test accuracy is 100% with an AUC of 1.0 across all 1510 images. Therefore, DenseNet 201+ SVM is the highest of the four methods across all 7548 images.

Lung diseases are the leading causes of early death and disability worldwide. Each year, they kill 4 million people and make them unable to work. One of the pulmonary diseases is emphysema. Emphysema, caused by the breakdown of alveolar walls and a lack of elasticity, is one of the most prevalent diseases responsible for this condition. Many algorithms have been developed in the past to classify emphysema. The objective of this article is to create a transfer learning-based model to determine whether a patient has emphysema based on chest X-rays. DenseNet201, a CNN classifier based on transfer learning, is proposed in this research. The suggested approach was tested using the NIH chest X-ray dataset (7540 samples). Finally, the experiments revealed that the DenseNet201 has a classification accuracy of 98.87%, an AUC of 99.7%, an F1-score of 98.88%, a precision of 97.80%, an AUC of 99.7%, a sensitivity of 100%, a precision of 97.80%, a validation accuracy of 98%, and a specificity of 97.75%, which is higher than other models. Other hyperparameters, such as learning rates, epochs, batch size, number of filters, and activation function, have been tuned repeatedly to improve results. The main goal is to have a low number of false positives and a 0% false negative rate.

Easy modular I action is one of the benefits of a cascaded H-bridge (CHB) inverter. This study proposes an only one multilevel inverter comes with a unique H-bridge unit. The structure of the proposed topology is then enhanced in order to make use of switching devices and DC-link voltage inputs while creating a massive number of voltage steps. A cooperative active and reactive power control strategy is offered to earn a better real and reactive power management for every DC voltage source of a photovoltaic (PV) module, as well as boost systems power quality and reliability. A unique control approach and proportional pulse width modulation (PWM) modulation are described for the cascaded H-bridge multilevel inverters for grid-connected systems. Each Hbridge module can give different power levels thanks to this control. To supply the DC source, use the system's proportional, integral and derivative (PID) controller. The functionality and achievements of the proposed scheme with its associated algorithms in production of all operating voltage have been proven using experimental data from a nine-level single-phase inverter. Finally, to construct a cascaded H-bridge nine-level inverter, the proposed control strategy is developed and implemented in MATLAB software.

Emphysema is one of the lung diseases that comprise COPD. Emphysema is a long-term lung illness that results in alveolar destruction, which destroys tiny air sacs in the lung that allow fast gas exchange or exchange of oxygen and carbon dioxide molecules between the bloodstream and the alveoli. It is one of the two most common kinds of COPD. Another significant COPD consequence is chronic bronchitis. Heart failure collapsed lungs, and big holes in the lungs are all possible consequences of emphysema. Emphysema is an incurable lung airway condition. This research chooses chest X-rays rather than CT scans. This article aims to create a deep learning model that can identify emphysema patients from chest radiographic images. This paper chooses 1696 chest X-ray images from an NIH Chest X-ray dataset. ResN et50 is used as a deep learning model since it is proved effective in medical image classification. This model is trained using multiple epochs and mini-batch sizes. It achieved 98.82 percent accuracy, 1.0 value precision for emphysema, 0.9885 for AUC, 97.70 percent recall/sensitivity for emphysema, 100 percent specificity, 98.85 percent balanced accuracy, and an 18.3303 geometric mean. Additionally, we obtained a false-positive rate of 0%.

Chronic kidney disease (CKD), also referred to as chronic kidney failure, is a medical condition defined by a gradual loss of kidney function over a period of time. It is characterized by conditions that inhibit or worsen the ability of the kidneys to filter wastes from human blood. If the disease worsens, wastes could build up to alarming levels in our blood and lead to organ failure, after which dialysis or kidney transplant would be needed to maintain life. It could further cause complications such as high blood pressure, low blood count (also known as anaemia), reduced bone strength, poor health and nutrition, and neurological damage. Since these symptoms usually slowly develop over time, early diagnosis can help chronic kidney disease from getting worse. This paper aims to use a set of medical attributes and analyse different machine learning algorithms to develop a model that would help predict whether or not a patient has chronic kidney disease. It also aims to perform a comparative analysis of multiple classification algorithms along with ensemble stacking method by testing their performance.

Extracting text from an image and reproducing them can often be a laborious task. We took it upon ourselves to solve the problem. Our work is aimed at designing a robot which can perceive an image shown to it and reproduce it on any given area as directed. It does so by first taking an input image and performing image processing operations on the image to improve its readability. Then the text in the image is recognized by the program. Points for each letter are taken, then inverse kinematics is done for each point with MATLAB/Simulink and the angles in which the servo motors should be moved are found out and stored in the Arduino. Using these angles, the control algorithm is generated in the Arduino and the letters are drawn.

Abstract Chronic obstructive pulmonary disease (COPD), a common lung disease is caused due to damages in small air sacs at the end of lung airways that affects both genders. Detecting and treating pulmonary emphysema at earlier stage can reduce the mortality. The lung Computer Tomography (CT) images obtained from Computed Tomography Emphysema Database (CTED) is utilized for emphysema classification. In this paper, the automated Neural Networks (NN) based Pulmonary Emphysema Classification System (PECS) is proposed to identify and classify the emphysema lung diseases using three phases. The preprocessing phase employs the Contrast Limited Adaptive Histogram Equalization (CLAHE) technique for contrast enhancement of images. Then the image feature extraction phase uses the Laws Local Binary Pattern (L2BP) for extracting the texture descriptor images. Finally, the classification is done using two stage Neural Network classifiers (NN-1 and NN-2) to classify the emphysema images. The NN-1 classifier is used to classify the as Normal Tissue (NT), or abnormal (CLE & PLE) class and then NN-2 classifier identify the abnormal CT images into either CLE or PLE.

COVID-19 different individuals different ways affects Most of the affected and disease being admitted to hospital. headache, or taste Loss of smell, rash on the skin, fingers or toes discoloration COVID-19 virus Most infected People mild and moderate respiratory illness experience special treatment need without recover Elderly and heart problems, Diabetes, chronic respiratory disease and For those with medical problems such as cancer The chances of getting a serious illness are high. COVID-19 virus, it causes disease it how spreads find out. By washing your hands without touching your face or by frequent use of alcohol-based scrubs protect yourself and others from infection. The COVID-19 virus is transmitted saliva or comes out the affected person when coughing or sneezing Nose, so you need to observe breathing habits as well. Be informed: Protect yourself: Public consultation, Myth Busters, Questions and Answers, situational reports. The Union Health Ministry clarified on Saturday that its procurement price for the vaccines Coaxing and Covishield remains the same at 150 a dose and it will continue to provide them free to States. "It is clarified that the Government's procurement price for both Covid-19 vaccines remains 150 per dose. Kobayashi noted that experts still do not know whether a person who has been vaccinated can spread the virus. U.S. Department of Disease Control and Prevention Centers "keep an eye" on COVID-19 cases in fully vaccinated people. The vaccines can cause tiredness achiness, and fever, side effects, vast majority a only day or two and serious or dangerous Side effects actually working vaccine normal signs They are different from some of the symptoms that people experience when they are vaccinated, such as fatigue, sore throat or joint pain. These types of things are common, they appear soon after vaccination and usually go away after three to five days.

A denoising method for medical images through hybrid technique is presented in this paper. The hybrid technique is the combination of wavelet and neural network (WaveNet). Proposed algorithm has been validated through benchmark image, and medical images both are degraded by the variety of noise density through Gaussian noise and visual property. The performances of denoised images are also analyzed with wavelet techniques and compare the results with proposed technique. The proposed strategy is developed in MATLAB platform. Simulation results are evidence for the proposed work

Received Oct 20, 2021 Revised Aug 3, 2022 Accepted Sep 6, 2022 Chronic obstructive pulmonary disease (COPD) is a general clinical issue in numerous countries considered the fifth reason for inability and the third reason for mortality on a global scale within 2021. From recent reviews, a deep convolutional neural network (CNN) is used in the primary analysis of the deadly COPD, which uses the computed tomography (CT) images procured from the deep learning tools. Detection and analysis of COPD using several image processing techniques, deep learning models, and machine learning models are notable contributions to this review. This research aims to cover the detailed findings on pulmonary diseases or lung diseases, their causes, and symptoms, which will help treat infections with high performance and a swift response. The articles selected have more than 80% accuracy and are tabulated and analyzed for sensitivity, specificity, and area under the curve (AUC) using different methodologies. This research focuses on the various tools and techniques used in COPD analysis and eventually provides an overview of COPD with coronavirus disease 2019 (COVID-19) symptoms.

Object identification is the one of the most developing area in image processing. In this paper proposed a neural network based object identification for aerial images. The computer is able to understand high level image are video for processing. Convolution neural network is detected the single object first and then detects the multiple objects. The input to an R-CNN is an image consisting of various instances, and output will be bounding boxes with the class label of the object. The input images are passed through discrete wavelet transform for pre processing. In this paper, it is mainly focused on object detection with segmentation.