Machine Learning Approach Using HOG and LBP Features of Spectrograms-Based Heart Sounds Analysis for the Detection of Heart Diseases

Lecture notes in networks and systems, Год журнала: 2025, Номер unknown, С. 342 - 352

Опубликована: Янв. 1, 2025

Язык: Английский

---

The fusion feature wavelet pyramid based on FCIS and GLCM for texture classification

International Journal of Machine Learning and Cybernetics, Год журнала: 2023, Номер 15(5), С. 1907 - 1926

Опубликована: Ноя. 6, 2023

Язык: Английский

---

An automated diagnosis model for classifying cardiac abnormality utilizing deep neural networks

Multimedia Tools and Applications, Год журнала: 2023, Номер 83(13), С. 39563 - 39599

Опубликована: Окт. 3, 2023

Язык: Английский

---

An Attention‐Driven Hybrid Deep Neural Network for Enhanced Heart Disease Classification

Expert Systems, Год журнала: 2024, Номер 42(2)

Опубликована: Ноя. 19, 2024

ABSTRACT Heart disease continues to be a primary cause of mortality globally, highlighting the critical necessity for efficient early prediction and classification techniques. This study presents new hybrid model attention‐based CNN‐Bi‐LSTM that integrates SMOTE with an attention‐driven improved convolutional neural network‐recurrent network architecture improve heart sounds, especially from imbalanced datasets. sounds are difficult classify because their complex acoustic properties variability characteristics across frequency temporal domains. The proposed utilises advanced CNN effectively extract global local features, in conjunction bidirectional long short‐term memory by capturing contextual information both preceding subsequent time sequences. incorporation spatial attention within RNN enables concentrate on most pertinent audio segments. To address challenges presented noisy datasets may impede efficacy deep learning algorithms, our employs data representation. outperformed popular models such as CNN, LSTM CNN‐LSTM, achieving accuracy more than 97% PCG PASCAL sound findings demonstrate model's reliability initial evaluation tool clinical settings, thereby improving support cardiovascular diagnosis.

Язык: Английский

---

Image Binary Matrix Processing to Encrypt-Decrypt Digital Images

International Journal of Advanced Computer Science and Applications, Год журнала: 2024, Номер 15(3)

Опубликована: Янв. 1, 2024

This research study presents a simple cryptographic solution for protecting grayscale and colored digital images, which are commonly used in computer applications. Due to their widespread use, these photos is crucial preventing unauthorized access. article's methodology manipulates an image's binary matrix using basic operations. These specified actions include increasing the 8-column 64 columns, reorganizing it into separating four blocks, shuffle columns secret index keys. keys produced sets of common chaotic logistic parameters. Each set executes map model generate key, then translated key. key shuffles during encryption reverses decryption. The approach promises large space that can withstand hacking. encrypted image secure since decryption procedure sensitive precise private values. Private frequently parameters, making resilient. method convenient supports images any size kind without modifying or techniques. Shuffling replaces difficult logical procedures typical data methods, simplifying process. Experiments with several will evaluate proposed strategy. decrypted be examined ensure meets standards. Speed tests also compare existing methods show its potential speed up picture cryptography by lowering times.

Язык: Английский

---

Heart Sound Classification Using Harmonic and Percussive Spectral Features from Phonocardiograms with a Deep ANN Approach

Applied Sciences, Год журнала: 2024, Номер 14(22), С. 10201 - 10201

Опубликована: Ноя. 6, 2024

Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide, with particularly high burden in India. Non-invasive methods like Phonocardiogram (PCG) analysis capture the acoustic activity heart. This holds significant potential for early detection and diagnosis heart conditions. However, complexity variability PCG signals pose considerable challenges accurate classification. Traditional signal analysis, including time-domain, frequency-domain, time-frequency domain techniques, often fall short capturing intricate details necessary reliable diagnosis. study introduces an innovative approach that leverages harmonic–percussive source separation (HPSS) to extract distinct harmonic percussive spectral features from signals. These then utilized train deep feed-forward artificial neural network (ANN), classifying conditions as normal or abnormal. The methodology involves advanced digital processing techniques applied recordings PhysioNet 2016 dataset. feature set comprises 164 attributes, Chroma STFT, CENS, Mel-frequency cepstral coefficients (MFCCs), statistical features. refined using ROC-AUC selection method ensure optimal performance. ANN model was rigorously trained validated on balanced Techniques such noise reduction outlier were used improve training. proposed achieved validation accuracy 93.40% sensitivity specificity rates 82.40% 80.60%, respectively. results underscore effectiveness harmonic-based robustness sound research highlights deploying models non-invasive cardiac diagnostics, resource-constrained settings. It also lays groundwork future advancements analysis.

Язык: Английский

---

HeartBeatNet: Unleashing the Power of Attention in Cardiology

Communications in computer and information science, Год журнала: 2023, Номер unknown, С. 14 - 25

Опубликована: Дек. 15, 2023

Язык: Английский

---