Search

The heart disease is one of the most serious health problems in today's world. Over 50 million persons have cardiovascular diseases around the world. Our proposed work based on 744 segments of ECG signal is obtained from the MIT-BIH Arrhythmia database (strongly imbalanced data) for one lead (modified lead II), from 29 people. In this work, we have used long-duration (10 s) ECG signal segments (13 times less classifications/analysis). The spectral power density was estimated based on Welch's method and discrete Fourier transform to strengthen the characteristic ECG signal features. Our main contribution is the design of a novel three-layer (48 + 4 + 1) deep genetic ensemble of classifiers (DGEC). Developed method is a hybrid which combines the advantages of: (1) ensemble learning, (2) deep learning, and (3) evolutionary computation. Novel system was developed by the fusion of three normalization types, four Hamming window widths, four classifiers types, stratified tenfold cross-validation, genetic feature (frequency components) selection, layered learning, genetic optimization of classifiers parameters, and new genetic layered training (expert votes selection) to connect classifiers. The developed DGEC system achieved a recognition sensitivity of 94.62% (40 errors/744 classifications), accuracy = 99.37%, specificity = 99.66% with classification time of single sample = 0.8736 (s) in detecting 17 arrhythmia ECG classes. The proposed model can be applied in cloud computing or implemented in mobile devices to evaluate the cardiac health immediately with highest precision. [ABSTRACT FROM AUTHOR]

Many visually meaningful image encryption (VMIE) methods have been proposed in the literature using reference encryption. However, the most important problems of these methods are low visual quality and blindness. Owing to the low visual quality, the pre-encrypted image can be analyzed simply from the reference image and, in order to decrypt nonblind methods, users should use original reference images. In this paper, two novel reference image encryption methods based on the integer DWT (discrete wavelet transform) using 2K correction are proposed. These methods are blind and have high visual quality, as well as short execution times. The main aim of the proposed methods is to solve the problem of the three VMIE methods existing in the literature. The proposed methods mainly consist of the integer DWT, pre-encrypted image embedding by kLSBs (k least significant bits) and 2K correction. In the decryption phase, the integer DWT and preencrypted image extraction with the mod operator are used. Peak signal-to-noise ratio (PSNR) measures the performances of the proposed methods. Experimental results clearly illustrate that the proposed methods improve the visual quality of the reference image encryption methods. Overall, 2K correction and kLSBs provide high visual quality and blindness. [ABSTRACT FROM AUTHOR]

Digital watermarking of images is an essential method for copyright protection and image security. This paper presents an innovative, robust watermarking system for color images based on moment and wavelet transformations, algebraic decompositions, and chaotic systems. First, we extended classical Charlier moments to quaternary Charlier moments (QCM) using quaternion algebra. This approach eliminates the need to decompose color images before applying the discrete wavelet transform (DWT), reducing the computational load. Next, we decompose the resulting DWT matrix using QR and singular value decomposition (SVD). To enhance the system's security and robustness, we introduce a modified version of Henon's 2D chaotic map. Finally, we integrate the arithmetic optimization algorithm to ensure dynamic and adaptive watermark insertion. Our experimental results demonstrate that our approach outperforms current color image watermarking methods in security, storage capacity, and resistance to various attacks, while maintaining a high level of invisibility. [ABSTRACT FROM AUTHOR]

To build datasets containing useful information from drug databases and recommend a list of drugs to physicians and patients with high accuracy by considering a wide range of features of people, diseases, and chemicals. A comprehensive pharmaceutical recommendation system was designed based on the features of people, diseases, and medicines extracted from two major drug databases and the created datasets of patients and drug information. Then, the recommendation was given based on recommender system algorithms using patient and caregiver ratings and the knowledge obtained from drug specifications and interactions. Sentiment analysis was employed by natural language processing approaches in pre-processing, along with neural network-based methods and recommender system algorithms for modelling the system. Patient conditions and medicine features were used to make two models based on matrix factorization. Then, we used drug interaction criteria to filter drugs with severe or mild interactions with other drugs. We developed a deep learning model for recommending drugs using data from 2304 patients as a training set and 660 patients as our validation set. We used knowledge from drug information and combined the model's outcome into a knowledge-based system with the rules obtained from constraints on taking medicine. Our recommendation system can recommend an acceptable combination of medicines similar to the existing prescriptions available in real life. Compared with conventional matrix factorization, our proposed model improves the accuracy, sensitivity, and hit rate by 26 %, 34 %, and 40 %, respectively. In addition, it improves the accuracy, sensitivity, and hit rate by an average of 31 %, 29 %, and 28 % compared to other machine learning methods. We have open-sourced our implementation in Python. Compared to conventional machine learning approaches, we obtained average accuracy, sensitivity, and hit rates of 31 %, 29 %, and 28 %, respectively. Compared to conventional matrix factorisation our proposed method improved the accuracy, sensitivity, and hit rate by 26 %, 34 %, and 40 %, respectively. However, it is acknowledged that this is not the same as clinical accuracy or sensitivity, and more accurate results can be obtained by gathering larger datasets. • Sentiment analysis was employed by NLP approaches in pre-processing. • Neural network-based methods and RS algorithms were employed for modelling the system. • We used knowledge from drug information and combined the model's outcome into a knowledge-based system. • Compared with other machine learning methods, our proposed model improved the accuracy, sensitivity, and hit rate. [ABSTRACT FROM AUTHOR]

Electrocardiography (ECG) is widely used for arrhythmia detection nowadays. The machine learning methods with signal processing algorithms have been used for automated diagnosis of cardiac health using ECG signals. In this article, discrete wavelet transform (DWT) coupled with novel 1-dimensional hexadecimal local pattern (1D-HLP) technique are employed for automated detection of arrhythmia detection. The ECG signals of 10 s duration are subjected to DWT to decompose up to five levels. The 1D-HLP extracts 512 dimensional features from each level of the five levels of low pass filter. Then, these extracted features are concatenated to obtain 512 × 6 = 3072 dimensional feature set. These fused features are subjected to neighborhood component analysis (NCA) feature reduction technique to obtain 64, 128 and 256 features. Finally, these features are subjected to 1 nearest neighborhood (1NN) classifier for classification with 4 distance metrics namely city block, Euclidean, spearman and cosine. We have obtained a classification accuracy of 95.0% in classifying 17 arrhythmia classes using MIT-BIH Arrhythmia ECG dataset. Our results show that the proposed method is more superior than other already reported classical ensemble learning and deep learning methods for arrhythmia detection using ECG signals. • Classification 17 ECG classes is proposed. • A novel hexadecimal ternary pattern is employed. • Multilevel wavelet is used to extract features deeply. • Obtained classification accuracy of 95.0%. • Proposed method is computationally less intensive and fast. [ABSTRACT FROM AUTHOR]