Recurrence Plot-Based Approach for Cardiac Arrhythmia Classification Using Inception-ResNet-v2

In the current article, an automatic classification of cardiac arrhythmias is presented using a transfer deep learning approach with the help of electrocardiography (ECG) signal analysis. Now a days, an ECG waveform serves as a powerful tool used for the analysis of cardiac arrhythmias (irregularities). The goal of the present work is to implement an algorithm based on deep learning for classification of different cardiac arrhythmias. Initially, the one dimensional (1-D) ECG signals are transformed to two dimensional (2-D) scalogram images with the help of Continuous Wavelet(CWT). Four different categories of ECG waveform were selected from four PhysioNet MIT-BIH databases, namely arrhythmia database, Normal Sinus Rhythm database, Malignant Ventricular Ectopy database and BIDMC Congestive heart failure database to examine the proposed technique. The major interest of the present study is to develop a transferred deep learning algorithm for automatic categorization of the mentioned four different heart diseases. Final results proved that the 2-D scalogram images trained with a deep convolutional neural network CNN with transfer learning technique (AlexNet) pepped up with a prominent accuracy of 95.67%. Hence, it is worthwhile to say the above stated algorithm demonstrates as an effective automated heart disease detection tool

Emotions expressed by humans can be identified from facial expressions, speech signals, or physiological signals. Among them, the use of physiological signals for emotion classification is a notable emerging area of research. In emotion recognition, a person’s electrocardiogram (ECG) and galvanic skin response (GSR) signals cannot be manipulated, unlike facial and voice signals. Moreover, wearables such as smartwatches and wristbands enable the detection of emotions in people’s naturalistic environment. During the COVID-19 pandemic, it was necessary to detect people’s emotions in order to ensure that appropriate actions were taken according to the prevailing situation and achieve societal balance. Experimentally, the duration of the emotion stimulus period and the social and non-social contexts of participants influence the emotion classification process. Hence, classification of emotions when participants are exposed to the elicitation process for a longer duration and taking into consideration the social context needs to be explored. This work explores the classification of emotions using five pretrained convolutional neural network (CNN) models: MobileNet, NASNetMobile, DenseNet 201, InceptionResnetV2, and EfficientNetB7. The continuous wavelet transform (CWT) coefficients were detected from ECG and GSR recordings from the AMIGOS database with suitable filtering. Scalograms of the sum of frequency coefficients versus time were obtained and converted into images. Emotions were classified using the pre-trained CNN models. The valence and arousal emotion classification accuracy obtained using ECG and GSR data were, respectively, 91.27% and 91.45% using the InceptionResnetV2 CNN classifier and 99.19% and 98.39% using the MobileNet CNN classifier. Other studies have not explored the use of scalograms to represent ECG and GSR CWT features for emotion classification using deep learning models. Additionally, this study provides a novel classification of emotions built on individual and group settings using ECG data. When the participants watched long-duration emotion elicitation videos individually and in groups, the accuracy was around 99.8%. MobileNet had the highest accuracy and shortest execution time. These subject-independent classification methods enable emotion classification independent of varying human behavior.

Distinguishing pericarpium citri reticulatae of different origins using terahertz time-domain spectroscopy combined with convolutional neural networks

RETRACTED: Arrhythmia classification using ECG signal: A meta-heuristic improvement of optimal weighted feature integration and attention-based hybrid deep learning model

Automated detection of shockable ECG signals: A review

Cardiovascular Diseases (CVD) requires precise and efficient diagnostic tools. The manual analysis of Electrocardiograms (ECGs) is labor-intensive, necessitating the development of automated methods to enhance diagnostic accuracy and efficiency. This research aimed to develop an automated ECG classification using Continuous Wavelet Transform (CWT) and Deep Convolutional Neural Network (DCNN), and transform 1D ECG signals into 2D spectrograms using CWT and train a DCNN to accurately detect abnormalities associated with CVD. The DCNN is trained on datasets from PhysioNet and the MIT-BIH and the MIT-BIH arrhythmia dataset. The integrated CWT and DCNN enable simultaneous classification of multiple ECG abnormalities alongside normal signals. This analytical observational research employed CWT to generate spectrograms from 1D ECG signals, as input to a DCNN trained on diverse datasets. The model is evaluated using performance metrics, such as precision, specificity, recall, overall accuracy, and F1-score. The proposed algorithm demonstrates remarkable performance metrics with a precision of 100% for normal signals, an average specificity of 100%, an average recall of 97.65%, an average overall accuracy of 98.67%, and an average F1-score of 98.81%. This model achieves an approximate average overall accuracy of 98.67%, highlighting its effectiveness in detecting CVD. The integration of CWT and DCNN in ECG classification improves accuracy and classification capabilities, addressing the challenges with manual analysis. This algorithm can reduce misdiagnoses in primary care and enhance efficiency in larger medical institutions. By contributing to automated diagnostic tools for cardiovascular disorders, it can significantly improve healthcare practices in the field of CVD detection.

Coronary artery disease (CAD) is among the most prevalent and life-threatening cardiovascular conditions worldwide. Early detection is essential for improving patient outcomes and improving the efficiency of healthcare systems. Electrocardiography (ECG) is widely used for assessing cardiac function, yet manual interpretation of ECG signals can be inconsistent and prone to error. Developing reliable automated methods is therefore of great importance for enabling earlier and more consistent CAD detection. Although recent advances in deep learning have achieved strong performance in ECG analysis, many existing methods remain limited in practice. Current state-of-the-art models are often computationally complex and thus unsuitable for deployment on resource-constrained platforms. To address the limited attention given to CAD in current ECG research, various deep learning models were developed in this thesis. First, a one-dimensional convolutional neural network (1D-CNN) was proposed to detect CAD directly from raw ECG signals without manual feature extraction. The model achieved 97.3% accuracy and demonstrated strong generalisability when using 250-point ECG segments. Then, a feature engineering approach was applied to select high-quality signal segments using sample entropy and normalisation techniques, further improving both accuracy and robustness. Next, a lightweight neural network architecture (CADNet) was developed, outperforming existing lightweight models by offering lower complexity and smaller size without compromising accuracy. The fourth study focused on 12-lead ECG, introducing a depthwise, squeeze-and-excitation-based model that captured both lead-specific and inter-lead patterns, and achieved efficient deployment on an STM32 microcontroller. Finally, an attention-driven model was proposed for the detection of multiple cardiovascular diseases from a single ECG recording, demonstrating high diagnostic capability. Our qualitative evaluations in this study demonstrate that lightweight deep learning models can provide reliable ECG-based CAD diagnosis while remaining suitable for real-time deployment. The proposed approaches are robust to ECG variability and show consistent performance across different experimental and diagnostic scenarios, supporting their practical use in resource-constrained environments. Overall, the results highlight the relevance of lightweight deep learning architectures in enabling ECG-based diagnostic methods to be used as potential pre-screening tools.

The success of arrhythmia classification tasks with Machine Learning (ML) algorithms is based on the handcrafting extraction of features from Electrocardiography (ECG) signals. However, feature extraction is a time-consuming trial-and-error approach. Deep Neural Network (DNN) algorithms bypass the process of handcrafting feature extraction since the algorithm extracts the features automatically in their hidden layers. However, it is important to have access to a balanced dataset for algorithm training. In this exploratory research study, we will compare the evaluation metrics among Convolutional Neural Networks (1D-CNN) and Support Vector Machines (SVM) using a dataset based on the merged public ECG signals database TNMG and CINC17 databases. Results: Both algorithms showed good performance using the new, merged ECG database. For evaluation metrics, the 1D-CNN algorithm has a precision of 93.04%, an accuracy of 93.07%, a recall of 93.20%, and an F1-score of 93.05%. The SVM classifier (λ = 10, C = 10 × 109) achieved the best classification metrics with two combined, handcrafted feature extraction methods: Wavelet transforms and R-peak Interval features, which achieved an overall precision of 89.04%, accuracy of 92.00%, recall of 94.20%, and F1-score of 91.54%. As an unique input feature and SVM (λ=10,C=100), wavelet transforms achieved precision, accuracy, recall, and F1-score metrics of 86.15%, 85.33%, 81.16%, and 83.58%. Conclusion: Researchers face a challenge in finding a broad dataset to evaluate ML models. One way to solve this problem, especially for deep learning models, is to combine several public datasets to increase the amount of data. The SVM and 1D-CNN algorithms showed positive results with the merge of databases, showing similar F1-score, precision, and recall during arrhythmia classification. Despite the favorable results for both of them, it should be considered that in the SVM, feature selection is a time-consuming trial-and-error process; meanwhile, CNN algorithms can reduce the workload significantly. The disadvantage of CNN algorithms is that it has a higher computational processing cost; moreover, in the absence of access to powerful computational processing, the SVM can be a reliable solution.

Deep learning assisted continuous wavelet transform-based spectrogram for the detection of chlorophyll content in potato leaves

Recent user recognition technologies have focused on biometric signals to remotely identify users in the access management, medical welfare, and public sectors. The electrocardiogram (ECG) signal is an individual’s unique electrophysiological signal generated within the body and is difficult to forge or change; thus, it can be used to uniquely identify the user. Existing user identification systems based on ECG signals detect R peaks according to morphological features and use a fiducial-based segmentation process for data normalization. However, this process does not detect a distinct R peak due to motion artifacts generated by the movement of the subject, thereby degrading identification accuracy. To address the problem of decreasing peak accuracy of the fiducial-based segmentation data, this study proposes a user identification system based on one-dimensional neural networks using periodic non-fiducial-based segmentation data that do not overlap in the time domain. The proposed system comprises a preprocessing step for data denoising, a non-fiducial-based and non-overlap segmentation step, and a step for classifying users using a one-dimensional shallow neural network. In the experiment, when using self-acquired 10-second ECG signal data that were divided into non-fiducial and non-overlapping segments, the long short-term memory (LSTM), bidirectional LSTM, and one-dimensional convolutional neural network (CNN) models achieved accuracies of 92.01%, 93.13%, and 95.51%, respectively, with the 1D CNN model exhibiting the best accuracy. The proposed system demonstrated a 25.48% improvement in accuracy on non-fiducial segmented data compared to the 1D CNN model, which achieved an accuracy of 70.03% on fiducial segmented data. Moreover, when tested on publicly available ECG datasets, including MIT-BIH, ECG-ID, and PTB-XL, the proposed system exhibited a user identification accuracy of over 94%, confirming its superior performance.

The COVID-19 pandemic has exposed the vulnerability of healthcare services worldwide, raising the need to develop novel tools to provide rapid and cost-effective screening and diagnosis. Clinical reports indicated that COVID-19 infection may cause cardiac injury, and electrocardiograms (ECG) may serve as a diagnostic biomarker for COVID-19. This study aims to utilize ECG signals to detect COVID-19 automatically. We propose a novel method to extract ECG signals from ECG paper records, which are then fed into one-dimensional convolution neural network (1D-CNN) to learn and diagnose the disease. To evaluate the quality of digitized signals, R peaks in the paper-based ECG images are labeled. Afterward, RR intervals calculated from each image are compared to RR intervals of the corresponding digitized signal. Experiments on the COVID-19 ECG images dataset demonstrate that the proposed digitization method is able to capture correctly the original signals, with a mean absolute error of 28.11 ms. The 1D-CNN model (SEResNet18), which is trained on the digitized ECG signals, allows to identify between individuals with COVID-19 and other subjects accurately, with classification accuracies of 98.42% and 98.50% for classifying COVID-19 vs. Normal and COVID-19 vs. other classes, respectively. Furthermore, the proposed method also achieves a high-level of performance for the multi-classification task. Our findings indicate that a deep learning system trained on digitized ECG signals can serve as a potential tool for diagnosing COVID-19.

Over large areas, land cover classification has conventionally been undertaken using satellite time series. Typically temporal metric percentiles derived from single pixel location time series have been used to take advantage of spectral differences among land cover classes over time and to minimize the impact of missing observations. Deep convolutional neural networks (CNNs) have demonstrated potential for land cover classification of single date images. However, over large areas and using time series their application is complicated because they are sensitive to missing observations and they may misclassify small and spatially fragmented surface features due to their spatial patch-based implementation. This study demonstrates, for the first time, a one-dimensional (1D) CNN single pixel time series land classification approach that uses temporal percentile metrics and that does not have these issues. This is demonstrated for all the Conterminous United States (CONUS) considering two different 1D CNN structures with 5 and 8 layers, respectively. CONUS 30 m land cover classifications were derived using all the available Landsat-5 and -7 imagery over a seven-month growing season in 2011 with 3.3 million 30 m land cover class labelled samples extracted from the contemporaneous CONUS National Land Cover Database (NLCD) 16 class land cover product. The 1D CNNs and, a conventional random forest model, were trained using 10%, 50% and 90% samples, and the classification accuracies were evaluated with an independent 10% proportion. Temporal metrics were classified using 5, 7 and 9 percentiles for each of five Landsat reflective wavelength bands and their eight band ratios. The CONUS and detailed 150 × 150 km classification results demonstrate that the approach is effective at scale and locally. The 1D CNN classification land cover class boundaries were preserved for small axis dimension features, such as roads and rivers, with no stripes or anomalous spatial patterns. The 8-layer 1D CNN provided the highest overall classification accuracies and both the 5-layer and 8-layer 1D CNN architectures provided higher accuracies than the random forest by 1.9% - 2.8% which as all the accuracies were > 83% is a meaningful increase. The CONUS overall classification accuracies increased marginally with the number of percentiles (86.21%, 86.40%, and 86.43% for 5, 7 and 9 percentiles, respectively) using the 8-layer 1D-CNN. Class specific producer and user accuracies were quantified, with lower accuracies for the developed land, crop and pasture/hay classes, but no systematic pattern among classes with respect to the number of temporal percentiles used. Application of the trained model to a different year of CONUS Landsat ARD showed moderately decreased accuracy (80.79% for 7 percentiles) that we illustrate is likely due to different intra-annual surface variations between years. These encouraging results are discussed with recommended research for deep learning using temporal metric percentiles.

A case study on computer-aided diagnosis of nonerosive reflux disease using deep learning techniques

To develop and evaluate deep learning models for cardiac arrest rhythm classification during cardiopulmonary resuscitation (CPR), we analyzed 508 electrocardiogram (ECG) segments (each 4 s in duration, recorded at 250 Hz) from 131 cardiac arrest patients. Compression-affected segments were recorded during chest compressions, while non-compression segments were extracted during compression pauses or immediately after return of spontaneous circulation (ROSC) declaration. One-dimensional convolutional neural network (1D-CNN) and recurrent neural network (RNN) models were employed for four binary classification tasks: (1) shockable rhythms (VF and pVT) versus non-shockable rhythms (asystole and PEA) in all ECG segments; (2) the same classification in compression-affected ECG segments; (3) pulse-generating rhythms (ROSC rhythm) versus non-pulse-generating rhythms (asystole, PEA, VF and pVT) in all ECG segments; and (4) the same classification in compression-affected ECG segments. The 1D-CNN model consistently outperformed the RNN model across all classification tasks. For shockable versus non-shockable rhythm classification, the 1D-CNN achieved accuracies of 91.3% and 89.8% for all ECG segments and compression-affected ECG segments, respectively, compared to 50.6% and 54.5% for the RNN. In detecting pulse-generating rhythms, the 1D-CNN demonstrated accuracies of 90.9% and 85.7% for all ECG segments and compression-affected ECG segments, respectively, while the RNN achieved 92.2% and 84.4%. The 1D-CNN model demonstrated superior performance in cardiac arrest rhythm classification, maintaining high accuracy even with compression-affected ECG data.

S1eep apnea is the one of the most prevalent sleep disorder caused due to obstruction in breathing. Sleep apnea detection is usually done using polysomnography (PSG) which is not available for rural health care. The main objective of this work is to develop an affordable sleep apnea screening system using electrocardiography (ECG) signals as input.The baseline system was built using statistical features extracted from the time domain, frequency domain, and wavelet decomposed signals as input to a support vector machine (SVM) backend classifier. The baseline showed an accuracy of 86%, specificity of 83%, and sensitivity of 88%. Further, a Convolutional neural network (CNN) model is also implemented to check the performance of the system on wavelet decomposed signals. The best CNN model gave an accuracy of 86.6%, a sensitivity of 84.01%, and a specificity of 84.1%.To enhance the performance further, bottleneck features were extracted from the bottleneck layer of a CNN and the features thus derived are combined for feature fusion. The bottleneck layer compresses the model aiding in the extraction of lower dimensionality information. The bottleneck features from the best-performing models are fused together. The performance of the fused bottleneck features was found to show an accuracy of 87.6%, sensitivity of 86.4%, and specificity of 86.49%.