In high risk or remote environments where immediate medical assistance may not be available is a need for health monitoring with real time risk management to ensure the safety and well being of individuals. Therefore, this paper presents a water data communication for SCUBA divers health monitoring and risk management system that aims to enhance diver safety by providing real time monitoring of critical physiological and environmental parameters, with the added advantage of Electromagnetic (EM) wave communication for data transmission. In this system, various sensors such as a pulse sensor for heart rate, a MAX30102 sensor for oxygen saturation, a MS5803 depth sensor for measuring dive depth, and a DS18B20 temperature sensor for water temperature are connected to the microcontroller. The use of EM wave communication enhances the system’s reliability, ensuring that important health data is transmitted efficiently even in underwater conditions. The system is capable of monitoring critical health metrics in real time, and if any parameters such as oxygen levels, heart rate, or dive depth go beyond safe thresholds, it triggers alerts to surface personnel or emergency response teams. Overall, this system improves diver safety, providing both real time health tracking and risk management features while utilizing a more robust and efficient communication method than traditional acoustic systems.

Acute Otitis Media (AOM) is a common middle ear infection, especially in children, but it can happen at any age. Accurate and early detection is essential for successful treatment and avoiding complications. This research introduces a new method for AOM detection through an Improved Mask R CNN (IR CNN) model combined with ResNet 50. The method adopted here is systematic and starts with the preprocessing of the images, comprising Wiener filtering for denoising and K means clustering in the Lab color space for segmentation. The feature extraction step is carried out by convolution layers in the IR CNN, followed by the classification process done by a three layer Fully Connected Neural Network (FCNN) to separate between normal and AOM affected cases. Performance of the system is measured based on accuracy, sensitivity, specificity, F1 score, AUC, and IoU metrics. K Fold Cross Validation has been used to measure the strength and generalizability of the model. The system is very effective in the diagnosis of AOM with high accuracy of 99.1%, precision of 98.99%, and F score of 98.45%, highlighting its efficacy for enhancing clinical decision making.

Sentiment analysis technique is to analyse and determine the emotional tone or mood expressed in textual data. Sentiment analysis examines the individualized information expressed in a particular expression. The tentative words and phrases help to classify them as neutral, negative, or positive. In this paper, a deep learning to perform Twitter sentiment analysis by hybrid Convolutional Neural Network (CNN) with Long Short Term Memory (LSTM). Initially, using Stop words removal it eliminates the common words and stemming reduces words to their room form. Following feature extraction, text is transformed into numerical features using Term Frequency Inverse Document Frequency (TF IDF). Finally using the proposed hybrid CNN LSTM the sentiment analysis is classified. Hybrid CNN LSTM have the highest accuracy of 94% compared to the other existing methods.

Cerebral infarction is a leading cause of mortality worldwide, resulting from the blockage of an artery that restricts blood flow and oxygen to brain tissues. Computed Tomography (CT) is a widely used imaging tool for early stroke assessment. This study proposes an automated detection model for cerebral infarction in CT brain images using a 3D U Net model based on Convolutional Neural Networks (CNN).  To improve and segment the impacted brain tissues, the system uses preprocessing techniques such slice selection, picture averaging, band pass filtering, and variation model decomposition. The Medical Image Segmentation framework with CNN (MIS CNN) is used for efficient and accurate detection. The proposed model enhances diagnosis accuracy, assists radiologists in early stroke identification, and contributes to reducing the mortality rate by enabling timely medical intervention.

Vaginal deliveries have linked to less respiratory issues in the newborn. Vaginal delivery and on demand C section showed better outcomes than operatory vaginal delivery and intrapartum C sections. In this paper a Particle Swarm Optimization based One Dimensional Convolutional Neural Network the delivery type is proposed. Initially, the data is pre processed undergoing stages like handling missing values to analyse the missing values from input data, data encoding to convert unconditional variables into numerical representations. Then data balancing to balance the data and dimensionality reduction to visualize the data by enhancing data quality for detection. Next, the data are selected using the Chi square test score to extract independent variables from a large sample data for delivery type detection. Finally, a PSO based 1D CNN framework is processed to enhance the classification accuracy of delivery type. Using python software the proposed framework shows an improved accuracy of 96% is expert when compared to other methods.

Middle ear inflammatory diseases are a worldwide health concern that leads to severe effects like speech problems and hearing loss. Experts visually examine the tympanic membrane during a clinical examination. The five classes of Tympanic Membrane (TM) image inside the middle ear is predicted by using the proposed Deep Learning method called Modified VGG 19. Initially, data augmentation is applied to the TM image to eliminate the black margin and to resize, remove noise using bilateral filtering to get high quality input data. Next, the images are segmented using the Fuzzy C means clustering, allowing for partition of data. Features are then extracted from the segmented images using the Gray Level Co occurrence Matrix the TM image is textured for further analysis. Finally, a Modified VGG 19 framework is proposed to enhance the classification of TM images, in middle ear diagnosis. The assessment of proposed work using python software reveals that the proposed framework with Modified VGG 19 classifier ranks with improved accuracy of 92.09 % when compared to the other techniques.

Thyroid disorders affect millions of people worldwide, however quick treatment is vulnerable by high rates of misdiagnosis. The lack of current clinical decision support systems inspires the development of novel approaches. In mandate to increase thyroid disease prediction, this study finds a gap in the use of machine learning, optimization and deep learning algorithms. The age and gender for thyroid data is predicted by using the proposed Deep Learning method based optimization technique called Grey Wolf Optimization based hyper parameter tuning with Deep Neural Network. Initially, data cleaning is applied to the thyroid data to replace missing values and for raw data conversion. Next, the data are featured using the Recursive Feature Elimination, to identifying its most important features and eliminating others from thyroid dataset. Finally, a GWO based DNN framework is processed to enhance the classification of thyroid disease diagnosis. Using python software the proposed framework an improved accuracy of 92% is accomplished when compared to other techniques.

Gastrointestinal diseases (GIDs) are increasingly prevalent worldwide, necessitating robust methods for their early detection and diagnosis. This study proposes a novel Multi scale Attention Efficient Network (MAE Net) for identifying abnormalities in the gastric region using time–frequency analysis. The Kvasir dataset is employed as the primary source of input images. The methodology begins with a preprocessing phase where the input images are resized, converted to grayscale, and enhanced for texture. This is followed by segmentation using approximate spatial fuzzy c means clustering. Features are extracted using wavelet transform coefficients to analyze frequency and time series data. The decomposed image classes are then input into the MAE Net model for training and testing, enabling accurate classification and prediction. The performance of the proposed model is evaluated using standard metrics such as accuracy, precision, recall, and F1 score. Comparative analysis with existing methods on similar datasets demonstrates the superiority of the proposed approach in terms of classification performance. This work highlights the potential of MAE Net in advancing the detection and diagnosis of gastrointestinal abnormalities.

Air Qualities (AQ) are developed to be a serious environmental and health concern as a result of worldwide population growth. A predictive model for air quality is essential for the timely prevention and management of air pollution. This study proposes a novel Self Tuning Deep Regression Neural Network (STDRNN) for identifying air pollution in the environment using deep neural network. The Air Quality Index (AQI) dataset is employed as the primary source of input data. The methodology begins with a data pre processing phase where the input data finds the missing data and shows the duplicate AQ values using data imputation and remove outlier method. This is followed by feature construction where the each AQ label is converted into an integer AQ value and scaling the features to a similar range using feature encoding and feature scaling method. The AQI data are then given to the STDRNN model for training and testing, enabling accurate prediction. The performance of the proposed model is evaluated using standard metrics such as RMSE, MSE and R2 coefficient. Using the python software AQI dataset shows the comparative analysis with existing methods on similar datasets demonstrates the superiority of the proposed approach in terms of selection performance. This work highlights the potential of STDRNN in advancing the accuracy of the model as well as its promising potential applications.

Every country economy is depending heavily on agriculture because it produces crops. Identifying leaf diseases is one of the most crucial parts of keeping a country that is agriculturally advanced. Artificial intelligence (AI) in agriculture has emerged as the most significant application in recent years. An early prediction of the type of disease affecting the plant leaves is an essential objective. To classify the current diseases type and distinguish between healthy and infected leaves, the proposed study mainly employs the Visual Geometry Group (VGG 19) classification model. The features extraction of images using a wavelet transform for extracting the features of the leaves. The model is trained and evaluated using the Apple Leaf Disease Symptoms dataset, and the adaptive wiener filter is used to enhance the images and remove noise from the leaf images, while the k means clustering algorithm divides the regions in the leaf images. Accuracy, sensitivity, specificity, recall, and F1 score were among the performance measure parameters that were computed and tracked. This classifier is implemented using the python software. The findings show that it offers greater accuracy and the results are then contrasted with those of earlier classification methods. By identifying plant illnesses early and implementing the right treatment, this approach aims to assist farmers in protecting resources and avoiding financial loss.