Automated electrocardiogram (ECG) analysis can support the screening of cardiac rhythm abnormalities when standardized preprocessing and classification are applied. This work presents an image-based ECG arrhythmia classification framework for six rhythm categories: Left Bundle Branch Block (LBBB), Normal, Premature Atrial Contraction (PAC), Premature Ventricular Contractions (PVC), Right Bundle Branch Block (RBBB), and Ventricular Fibrillation. The dataset contains 22,166 ECG waveform images divided into training and test subsets. Images are resized to 64 × 64 pixels and intensity-scaled, while shear, zoom, and horizontal-flip augmentation are applied to the training subset. A sequential CNN comprising three convolutionpooling stages, a 128-unit dense layer, dropout, and a six-unit softmax output performs multiclass classification. The trained network is stored in HDF5 and native Keras formats and deployed through a Flask-based image-upload interface. Experimental evaluation includes epoch-wise learning behavior and three interface-level classification cases. A Normal ECG is classified as Normal and mapped to a healthy-rhythm status, a Ventricular Fibrillation input is classified as Ventricular Fibrillation and mapped to an abnormal-rhythm status, and an LBBB input is classified as PVC and mapped to an abnormal-rhythm status. The results demonstrate the complete inference pipeline from ECG image input to multiclass prediction and user-facing rhythm interpretation, while also revealing class-level confusion among abnormal rhythms.
Akarapu Anuhya, M. Raju, Sirisha Veluri· International Journal of AI...· 0 citations
Diabetes is a serious chronic disease affecting millions of people in the world, and if not managed properly, can cause a lot of serious health problems. The challenges of traditional healthcare systems are unable to properly manage real-time patient monitoring, temporal healthcare analysis and accurate disease prediction. This study aims to solve the issues with a hybrid approach that combines Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks and ensemble learning techniques for effective management of chronic diabetes. The design includes the use of healthcare data from wearable sensors, Internet of Things (IoT) devices, and Electronic Health Records (EHRs) that will be used to measure glucose level fluctuations and forecast future health status. The healthcare data is preprocessed for better predictive accuracy and data quality through methods such as normalization, outlier elimination, and feature extraction. The ensemble mechanism fuses the advantages of both the RNN model and the LSTM model to boost the accuracy and robustness of the prediction results. The proposed method achieves an accuracy of 98%, precision of 92%, recall of 87%, F1-score of 92% and Mean Squared Error (MSE) value of 1 with better results than the traditional databases, rule-based system, statistical approaches and standalone machine learning models. The proposed framework is designed to facilitate real-time monitoring, personalized diabetes management recommendations and enhanced clinical decision making for chronic diabetes management.
