Genetic algorithm for the optimization of features and neural networks in ECG signals classification

A new particle swarm optimization-enhanced deep neural network for automatic ECG arrhythmias classification

This study proposes an ECG classification system using particle swarm optimization (PSO) for automated deep neural network hyperparameter tuning. PSO optimizes five key parameters: neuron counts in two fully connected layers, dropout rate, learning rate, and optimizer selection. ECG signals undergo wavelet decomposition for feature extraction, with classification performed on the MIT-BIH Arrhythmia Database across five heartbeat classes. The PSO-optimized model achieves superior performance with 99.76% accuracy, 99.34% precision, and 99.21% F1 score, demonstrating PSO's effectiveness in improving model reliability while reducing manual effort.

Identification and classification of arrhythmic heartbeats from electrocardiogram signals using feature induced optimal extreme gradient boosting algorithm

Arrhythmic heartbeat classification has gained a lot of attention to accelerate the detection of cardiovascular diseases and mitigating the potential cause of one-third of deaths worldwide. In this article, a computer-aided diagnostic (CAD) approach has been proposed for the automated identification and classification of arrhythmic heartbeats from electrocardiogram (ECG) signals using multiple features aided supervised learning model. For proper diagnosis of arrhythmic heartbeats, MIT-BIH Arrhythmia database has been used to train and test the proposed approach. The ECG signals, extracted from sensor leads, have undergone pre-processing via discrete wavelet transform. Three sets of features, i.e. statistical, temporal, and spectral, are extracted from the processed ECG signals followed by random forest aided recursive feature elimination strategy to select the prominent features for proper classification of arrhythmic heartbeats by the proposed optimal extreme gradient boosting (O-XGBoost) classifier. Hyperparameters such as learning rate, tree-specific parameters, and regularization parameters have been optimized to improve the performance of the XGBoost classifier. Moreover, the synthetic minority over-sampling technique has been employed for balancing the dataset in order to improve the classification performance. Quantitative results reveal the remarkable performance over state-of-the-art methods. The proposed model can be implemented in any computer-aided diagnostic system with similar topological structures.

Arrhythmia classification for non-experts using infinite impulse response (IIR)-filter-based machine learning and deep learning models of the electrocardiogram

Arrhythmias are a leading cause of cardiovascular morbidity and mortality. Portable electrocardiogram (ECG) monitors have been used for decades to monitor patients with arrhythmias. These monitors provide real-time data on cardiac activity to identify irregular heartbeats. However, rhythm monitoring and wave detection, especially in the 12-lead ECG, make it difficult to interpret the ECG analysis by correlating it with the condition of the patient. Moreover, even experienced practitioners find ECG analysis challenging. All of this is due to the noise in ECG readings and the frequencies at which the noise occurs. The primary objective of this research is to remove noise and extract features from ECG signals using the proposed infinite impulse response (IIR) filter to improve ECG quality, which can be better understood by non-experts. For this purpose, this study used ECG signal data from the Massachusetts Institute of Technology Beth Israel Hospital (MIT-BIH) database. This allows the acquired data to be easily evaluated using machine learning (ML) and deep learning (DL) models and classified as rhythms. To achieve accurate results, we applied hyperparameter (HP)-tuning for ML classifiers and fine-tuning (FT) for DL models. This study also examined the categorization of arrhythmias using different filters and the changes in accuracy. As a result, when all models were evaluated, DenseNet-121 without FT achieved 99% accuracy, while FT showed better results with 99.97% accuracy.

Deep Learning Modeling of Cardiac Arrhythmia Classification on Information Feature Fusion Image with Attention Mechanism

The electrocardiogram (ECG) is a crucial tool for assessing cardiac health in humans. Aiming to enhance the accuracy of ECG signal classification, a novel approach is proposed based on relative position matrix and deep learning network information features for the classification task in this paper. The approach improves the feature extraction capability and classification accuracy via techniques of image conversion and attention mechanism. In terms of the recognition strategy, this paper presents an image conversion using relative position matrix information. This information is utilized to describe the relative spatial relationships between different waveforms, and the image identification is successfully applied to the Gam-Resnet18 deep learning network model with a transfer learning concept for classification. Ultimately, this model achieved a total accuracy of 99.30%, an average positive prediction rate of 98.76%, a sensitivity of 98.90%, and a specificity of 99.84% with the relative position matrix approach. To evaluate the effectiveness of the proposed method, different image conversion techniques are compared on the test set. The experimental results demonstrate that the relative position matrix information can better reflect the differences between various types of arrhythmias, thereby improving the accuracy and stability of classification.

Signal Processing Framework for the Detection of Ventricular Ectopic Beat Episodes

The Holter monitor captures the electrocardiogram (ECG) and detects abnormal episodes, but physicians still use manual cross-checking. It takes a considerable time to annotate a long-term ECG record. As a result, research continues to be conducted to produce an effective automatic cardiac episode detection technique that will reduce the manual burden. The current study presents a signal processing framework to detect ventricular ectopic beat (VEB) episodes in long-term ECG signals of cross-database. The proposed study has experimented with the cross-database of open-source and proprietary databases. The ECG signals were preprocessed and extracted the features such as pre-RR interval, post-RR interval, QRS complex duration, QR slope, and RS slope from each beat. In the proposed work, four models such as support vector machine, k-means nearest neighbor, nearest mean classifier, and nearest RMS (NRMS) classifiers were used to classify the data into normal and VEB episodes. Further, the trained models were used to predict the VEB episodes from the proprietary database. NRMS has reported better performance among four classification models. NRMS has shown the classification accuracy of 98.68% and F1-score of 94.12%, recall rate of 100%, specificity of 98.53%, and precision of 88.89% with an open-source database. In addition, it showed an accuracy of 99.97%, F1-score of 94.54%, recall rate of 98.62%, specificity of 99.98%, and precision of 90.79% to detect the VEB cardiac episodes from the proprietary database. Therefore, it is concluded that the proposed framework can be used in the automatic diagnosis system to detect VEB cardiac episodes.

Coronavirus herd immunity optimizer to solve classification problems

Classification is a technique in data mining that is used to predict the value of a categorical variable and to produce input data and datasets of varying values. The classification algorithm makes use of the training datasets to build a model which can be used for allocating unclassified records to a defined class. In this paper, the coronavirus herd immunity optimizer (CHIO) algorithm is used to boost the efficiency of the probabilistic neural network (PNN) when solving classification problems. First, the PNN produces a random initial solution and submits it to the CHIO, which then attempts to refine the PNN weights. This is accomplished by the management of random phases and the effective identification of a search space that can probably decide the optimal value. The proposed CHIO-PNN approach was applied to 11 benchmark datasets to assess its classification accuracy, and its results were compared with those of the PNN and three methods in the literature, the firefly algorithm, African buffalo algorithm, and β-hill climbing. The results showed that the CHIO-PNN achieved an overall classification rate of 90.3% on all datasets, at a faster convergence speed as compared outperforming all the methods in the literature.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00500-022-06917-z.

Development of a Convolutional Neural Network Model to Predict Coronary Artery Disease Based on Single-Lead and Twelve-Lead ECG Signals

Coronary artery disease (CAD) is one of the most common causes of heart ailments; many patients with CAD do not exhibit initial symptoms. An electrocardiogram (ECG) is a diagnostic tool widely used to capture the abnormal activity of the heart and help with diagnoses. Assessing ECG signals may be challenging and time-consuming. Identifying abnormal ECG morphologies, especially in low amplitude curves, may be prone to error. Hence, a system that can automatically detect and assess the ECG and treadmill test ECG (TMT-ECG) signals will be helpful to the medical industry in detecting CAD. In the present work, we developed an intelligent system that can predict CAD, based on ECG and TMT signals more accurately than any other system developed thus far. The distinct convolutional neural network (CNN) architecture deals with single-lead and multi-lead (12-lead) ECG and TMT-ECG data effectively. While most artificial intelligence-based systems rely on the universal dataset, the current work used clinical lab data collected from a renowned hospital in the neighborhood. ECG and TMT-ECG graphs of normal and CAD patients were collected in the form of scanned reports. One-dimensional ECG data with all possible features were extracted from the scanned report with the help of a modified image processing method. This feature extraction procedure was integrated with the optimized architecture of the CNN model leading to a novel prediction system for CAD. The automated computer-assisted system helps in the detection and medication of CAD with a high prediction accuracy of 99%.

DE-PNN: Differential Evolution-Based Feature Optimization with Probabilistic Neural Network for Imbalanced Arrhythmia Classification

In this research, a heartbeat classification method is presented based on evolutionary feature optimization using differential evolution (DE) and classification using a probabilistic neural network (PNN) to discriminate between normal and arrhythmic heartbeats. The proposed method follows four steps: (1) preprocessing, (2) heartbeat segmentation, (3) DE feature optimization, and (4) PNN classification. In this method, we have employed direct signal amplitude points constituting the heartbeat acquired from the ECG holter device with no secondary feature extraction step usually used in case of hand-crafted, frequency transformation or other features. The heartbeat types include normal, left bundle branch block, right bundle branch block, premature ventricular contraction, atrial premature, ventricular escape, ventricular flutter and paced beat. Using ECG records from the MIT-BIH, heartbeats are identified to start at 250 ms before and end at 450 ms after the respective R-peak positions. In the next step, the DE method is applied to reduce and optimize the direct heartbeat features. Although complex and highly computational ECG heartbeat classification algorithms have been proposed in the literature, they failed to achieve high performance in detecting some minority heartbeat categories, especially for imbalanced datasets. To overcome this challenge, we propose an optimization step for the deep CNN model using a novel classification metric called the Matthews correlation coefficient (MCC). This function focuses on arrhythmia (minority) heartbeat classes by increasing their importance. Maximum MCC is used as a fitness function to identify the optimum combination of features for the uncorrelated and non-uniformly distributed eight beat class samples. The proposed DE-PNN scheme can provide better classification accuracy considering 8 classes with only 36 features optimized from a 253 element feature set implying an 85.77% reduction in direct amplitude features. Our proposed method achieved overall 99.33% accuracy, 94.56% F1, 93.84% sensitivity, and 99.21% specificity.

Automatic detection of arrhythmias from an ECG signal using an auto-encoder and SVM classifier

Millions of people around the world are affected by arrhythmias, which are abnormal activities of the functioning of the heart. Most arrhythmias are harmful to the heart and can suddenly become life-threatening. The electrocardiogram (ECG) is an important non-invasive tool in cardiology for the diagnosis of arrhythmias. This work proposes a computer-aided diagnosis (CAD) system to automatically classify different types of arrhythmias from ECG signals. First, the auto-encoder convolutional network (ACN) model is used, which is based on a one-dimensional convolutional neural network (1D-CNN) that automatically learns the best features from the raw ECG signals. After that, the support vector machine (SVM) classifier is applied to the features learned by the ACN model to improve the detection of arrhythmic beats. This classifier detects four different types of arrhythmias, namely the left bundle branch block (LBBB), right bundle branch block (RBBB), paced beat (PB), and premature ventricular contractions (PVC), along with the normal sinus rhythms (NSR). Among these arrhythmias, PVC is particularly a dangerous type of heartbeat in ECG signals. The performance of the model is measured in terms of accuracy, sensitivity, and precision using a tenfold cross-validation strategy on the MIT-BIH arrhythmia database. The obtained overall accuracy of the SVM classifier was 98.84%. The result of this model is portrayed as a better performance than in other literary works. Thus, this approach may also help in further clinical studies of cardiac cases.

Proposal of Multidimensional Data Driven Decomposition Method for Fault Identification of Large Turbomachinery

High-power turbomachines are equipped with flexible rotors and journal bearings and operate above their first and sometimes even second critical speed. The transient response of such a system is complex but can provide valuable information about the dynamic state and potential malfunctions. However, due to the high complexity of the signal and the nonlinearity of the system response, the analysis of transients is a highly complex process that requires expert knowledge in diagnostics, machine dynamics, and extensive experience. The article proposes the Multidimensional Data Driven Decomposition (MD3) method, which allows decomposing a complex transient into several simpler, easier to analyze functions. These functions have physical meaning. Thus, the method belongs to the Explainable Artificial Intelligence area. The MD3 method proposes three scenarios and chooses the best based on the MSE quality index. The approach was first verified on a test rig and then validated on data from a real object. The results confirm the correctness of the method assumptions and performance. Furthermore, the MD3 method successfully identified the failure of rotor unbalance, both on the test rig and the real object data (large generator rotor in the power plant). Finally, further directions for research and development of the method are proposed.

[Electrocardiogram signal classification algorithm of nested long short-term memory network based on focal loss function]

Electrocardiogram (ECG) can visually reflect the physiological electrical activity of human heart, which is important in the field of arrhythmia detection and classification. To address the negative effect of label imbalance in ECG data on arrhythmia classification, this paper proposes a nested long short-term memory network (NLSTM) model for unbalanced ECG signal classification. The NLSTM is built to learn and memorize the temporal characteristics in complex signals, and the focal loss function is used to reduce the weights of easily identifiable samples. Then the residual attention mechanism is used to modify the assigned weights according to the importance of sample characteristic to solve the sample imbalance problem. Then the synthetic minority over-sampling technique is used to perform a simple manual oversampling process on the Massachusetts institute of technology and Beth Israel hospital arrhythmia (MIT-BIH-AR) database to further increase the classification accuracy of the model. Finally, the MIT-BIH arrhythmia database is applied to experimentally verify the above algorithms. The experimental results show that the proposed method can effectively solve the issues of imbalanced samples and unremarkable features in ECG signals, and the overall accuracy of the model reaches 98.34%. It also significantly improves the recognition and classification of minority samples and has provided a new feasible method for ECG-assisted diagnosis, which has practical application significance.

Transcranial Magnetic Stimulation Indices of Cortical Excitability Enhance the Prediction of Response to Pharmacotherapy in Late-Life Depression

BACKGROUND

Older adults with late-life depression (LLD) often experience incomplete or lack of response to first-line pharmacotherapy. The treatment of LLD could be improved using objective biological measures to predict response. Transcranial magnetic stimulation (TMS) can be used to measure cortical excitability, inhibition, and plasticity, which have been implicated in LLD pathophysiology and associated with brain stimulation treatment outcomes in younger adults with depression. TMS measures have not yet been investigated as predictors of treatment outcomes in LLD or pharmacotherapy outcomes in adults of any age with depression.

METHODS

We assessed whether pretreatment single-pulse and paired-pulse TMS measures, combined with clinical and demographic measures, predict venlafaxine treatment response in 76 outpatients with LLD. We compared the predictive performance of machine learning models including or excluding TMS predictors.

RESULTS

Two single-pulse TMS measures predicted venlafaxine response: cortical excitability (neuronal membrane excitability) and the variability of cortical excitability (dynamic fluctuations in excitability levels). In cross-validation, models using a combination of these TMS predictors, clinical markers of treatment resistance, and age classified patients with 73% ± 11% balanced accuracy (average correct classification rate of responders and nonresponders; permutation testing, p < .005); these models significantly outperformed (corrected t test, p = .025) models using clinical and demographic predictors alone (60% ± 10% balanced accuracy).

CONCLUSIONS

These preliminary findings suggest that single-pulse TMS measures of cortical excitability may be useful predictors of response to pharmacotherapy in LLD. Future studies are needed to confirm these findings and determine whether combining TMS predictors with other biomarkers further improves the accuracy of predicting LLD treatment outcome.

Heart disease diagnosis using optimized features of hybridized ALCSOGA algorithm and LSTM classifier

Cardiac disease is the predominant cause of global death mainly due to its hidden symptoms and late diagnosis. Hence, early detection is important to improve quality of life. Though traditional researches attempted to predict heart disease, most of them lacked with respect to accuracy. To solve this, the present study proposes a hybridized Ant Lion Crow Search Optimization Genetic Algorithm (ALCSOGA) to perform effective feature selection. This hybrid optimization encompasses Ant Lion, Crow Search and Genetic Algorithm. Ant lion algorithm determines the elite position. While, the Crow Search Algorithm utilizes the phenomenon of position and memory of each crow for evaluating the objective function. Both these algorithms are fed into Genetic Algorithm to improve the performance of feature selection process. Then, Stochastic Learning rate optimized Long Short Term Memory (LSTM) is proposed to classify the extracted optimized features. Finally, comparative analysis is performed in terms of accuracy, recall, F1-score, and precision. Moreover, statistical analysis is performed with respect to Sum of Squares (SS), degree of freedom (df), F Critical (F crit), F Statistics (F), p, and Mean Square (MS) value. Analytical results revealed the efficiency of proposed system over conventional methods and thereby confirming its efficiency for predicting heart disease.

Expert-enhanced machine learning for cardiac arrhythmia classification

We propose a new method for the classification task of distinguishing atrial fibrillation (AFib) from regular atrial tachycardias including atrial flutter (AFlu) based on a surface electrocardiogram (ECG). Recently, many approaches for an automatic classification of cardiac arrhythmia were proposed and to our knowledge none of them can distinguish between these two. We discuss reasons why deep learning may not yield satisfactory results for this task. We generate new and clinically interpretable features using mathematical optimization for subsequent use within a machine learning (ML) model. These features are generated from the same input data by solving an additional regression problem with complicated combinatorial substructures. The resultant can be seen as a novel machine learning model that incorporates expert knowledge on the pathophysiology of atrial flutter. Our approach achieves an unprecedented accuracy of 82.84% and an area under the receiver operating characteristic (ROC) curve of 0.9, which classifies as "excellent" according to the classification indicator of diagnostic tests. One additional advantage of our approach is the inherent interpretability of the classification results. Our features give insight into a possibly occurring multilevel atrioventricular blocking mechanism, which may improve treatment decisions beyond the classification itself. Our research ideally complements existing textbook cardiac arrhythmia classification methods, which cannot provide a classification for the important case of AFib↔AFlu. The main contribution is the successful use of a novel mathematical model for multilevel atrioventricular block and optimization-driven inverse simulation to enhance machine learning for classification of the arguably most difficult cases in cardiac arrhythmia. A tailored Branch-and-Bound algorithm was implemented for the domain knowledge part, while standard algorithms such as Adam could be used for training.

Improving Automatic Detection of ECG Abnormality with Less Manual Annotations using Siamese Network

Electrocardiography is a very common, non-invasive diagnostic procedure and its interpretation is increasingly supported by automatic interpretation algorithms. Recently many works also focused on the design of automatic ECG abnormality detection algorithms. However, clinical electrocardiogram datasets often suffer from their heavy needs for expert annotations, which are often expensive and hard to obtain. In this work, we proposed a weakly supervised pretraining method based on the Siamese neural network, which utilizes the original diagnostic information written by physicians to produce useful feature representations of the ECG signal which improves performance of ECG abnormality detection algorithms with fewer expert annotations. The experiment showed that with the proposed weekly supervised pretraining, the performance of ECG abnormality detection algorithms that was trained with only 1/8 annotated ECG data outperforms classical models that was trained with fully annotated ECG data, which implies a large proportion of annotation resource could be saved. The proposed technique could be easily extended to other tasks beside abnormality detection provided that the text similarity metric is specifically designed for the given task.Clinical Relevance-This work proposes a novel framework for the automatic detection of cardiovascular disease based on electrocardiogram.

ARRHYTHMIA CLASSIFICATION USING DEEP RESIDUAL NEURAL NETWORKS

Arrhythmia classification with electrocardiogram (ECG) is of great importance for the identification of arrhythmia diseases. However, since the variance of ECG signal in wave appears frequently, it is still a very challenging task to obtain a very good classification result. In this paper, an arrhythmia classification with ECG based on deep residual networks is proposed, of which two improved residual blocks are used to combine soft and hard subsampling. With such blocks, the network can well hold spatial information and improve the classification performance with a simple model structure. Experiments on the MIT-BIH arrhythmia database show that the proposed method obtained an average classification accuracy of 99.59% and an average classification specificity 99.63%, which are 0.26% and 0.57% higher than that of the most state-of-art method based on deep learning.

V. Machine learning based pervasive analytics for ECG signal analysis

Purpose

Pervasive analytics act as a prominent role in computer-aided prediction of non-communicating diseases. In the early stage, arrhythmia diagnosis detection helps prevent the cause of death suddenly owing to heart failure or heart stroke. The arrhythmia scope can be identified by electrocardiogram (ECG) report.

Design/methodology/approach

The ECG report has been used extensively by several clinical experts. However, diagnosis accuracy has been dependent on clinical experience. For the prediction methods of computer-aided heart disease, both accuracy and sensitivity metrics play a remarkable part. Hence, the existing research contributions have optimized the machine-learning approaches to have a great significance in computer-aided methods, which perform predictive analysis of arrhythmia detection.

Findings

In reference to this, this paper determined a regression heuristics by tridimensional optimum features of ECG reports to perform pervasive analytics for computer-aided arrhythmia prediction. The intent of these reports is arrhythmia detection. From an empirical outcome, it has been envisioned that the project model of this contribution is more optimal and added a more advantage when compared to existing or contemporary approaches.

Originality/value

In reference to this, this paper determined a regression heuristics by tridimensional optimum features of ECG reports to perform pervasive analytics for computer-aided arrhythmia prediction. The intent of these reports is arrhythmia detection. From an empirical outcome, it has been envisioned that the project model of this contribution is more optimal and added a more advantage when compared to existing or contemporary approaches.

Classification of ECG signals using multi-cumulants based evolutionary hybrid classifier

Every human being has a different electro-cardio-graphy (ECG) waveform that provides information about the well being of a human heart. Therefore, ECG waveform can be used as an effective identification measure in biometrics and many such applications of human identification. To achieve fast and accurate identification of human beings using ECG signals, a novel robust approach has been introduced here. The databases of ECG utilized during the experimentation are MLII, UCI repository arrhythmia and PTBDB databases. All these databases are imbalanced; hence, resampling techniques are helpful in making the databases balanced. Noise removal is performed with discrete wavelet transform (DWT) and features are obtained with multi-cumulants. This approach is mainly based on features extracted from the ECG data in terms of multi-cumulants. The multi-cumulants feature based ECG data is classified using kernel extreme learning machine (KELM). The parameters of multi-cumulants and KELM are optimized using genetic algorithm (GA). Excellent classification rate is achieved with 100% accuracy on MLII and UCI repository arrhythmia databases, and 99.57% on PTBDB database. Comparison with existing state-of-art approaches has also been performed to prove the efficacy of the proposed approach. Here, the process of classification in the proposed approach is named as evolutionary hybrid classifier.

An Intelligent Heartbeat Classification System Based on Attributable Features with AdaBoost+Random Forest Algorithm

Arrhythmia is a common cardiovascular disease that can threaten human life. In order to assist doctors in accurately diagnosing arrhythmia, an intelligent heartbeat classification system based on the selected optimal feature sets and AdaBoost + Random Forest model is developed. This system can acquire ECG signals through the Holter and transmit them to the cloud platform for preprocessing and feature extraction, and the features are input into AdaBoost + Random Forest for heartbeat classification. The analysis results are output in the form of reports. In this system, by comparing and analyzing the classification accuracy of different feature sets and classifiers, the optimal classification algorithm is obtained and applied to the system. The algorithm accuracy of the system is tested based on the MIT-BIH data set. The result shows that AdaBoost + Random Forest achieved 99.11% accuracy with optimal feature sets. The intelligent heartbeat classification system based on this algorithm has also achieved good results on clinical data.

Exploring photoacoustic spectroscopy-based machine learning together with metabolomics to assess breast tumor progression in a xenograft model ex vivo

In the current study, a breast tumor xenograft was established in athymic nude mice by subcutaneous injection of the MCF-7 cell line and assessed the tumor progression by photoacoustic spectroscopy combined with machine learning tools. The advancement of breast tumors in nude mice was validated by tumor volume kinetics and histopathology and corresponding image analysis by TissueQuant software compared to controls. The ex vivo tumors in progressive conditions belonging to time points, day 5th, 10th, 15th & 20th, were excited with 281 nm pulsed laser light and recorded the corresponding photoacoustic spectra in time domain. The spectra were then pre-processed, augmented for a 10-fold increase in the data strength, and subjected to wavelet packet transformation for feature extraction and selection using MATLAB software. In the present study, the top 10 features from all the time point groups under study were selected based on their prediction ranking values using the mRMR algorithm. The chosen features of all the time-point groups were then subjected to multi-class Support Vector Machine (SVM) algorithms for learning and classifying into respective time point groups under study. The analysis demonstrated accuracy values of 95.2%, 99.5%, and 80.3% with SVM- Radial Basis Function (SVM-RBF), SVM-Polynomial & SVM-Linear, respectively. The serum metabolomic levels during tumor progression complemented photoacoustic patterns of tumor progression, depicting breast cancer pathophysiology.

Transmission Quality Classification with Use of Fusion of Neural Network and Genetic Algorithm in Pay&Require Multi-Agent Managed Network

Modern computer systems practically cannot function without a computer network. New concepts of data transmission are emerging, e.g., programmable networks. However, the development of computer networks entails the need for development in one more aspect, i.e., the quality of the data transmission through the network. The data transmission quality can be described using parameters, i.e., delay, bandwidth, packet loss ratio and jitter. On the basis of the obtained values, specialists are able to state how measured parameters impact on the overall quality of the provided service. Unfortunately, for a non-expert user, understanding of these parameters can be too complex. Hence, the problem of translation of the parameters describing the transmission quality appears understandable to the user. This article presents the concept of using Machine Learning (ML) to solve the above-mentioned problem, i.e., a dynamic classification of the measured parameters describing the transmission quality in a certain scale. Thanks to this approach, describing the quality will become less complex and more understandable for the user. To date, some studies have been conducted. Therefore, it was decided to use different approaches, i.e., fusion of a neural network (NN) and a genetic algorithm (GA). GA’s were choosen for the selection of weights replacing the classic gradient descent algorithm. For learning purposes, 100 samples were obtained, each of which was described by four features and the label, which describes the quality. In the reasearch carried out so far, single classifiers and ensemble learning have been used. The current result compared to the previous ones is better. A relatively high quality of the classification was obtained when we have used 10-fold stratified cross-validation, i.e., SEN = 95% (overall accuracy). The incorrect classification was 5/100, which is a better result compared to previous studies.

Interpatient ECG Heartbeat Classification with an Adversarial Convolutional Neural Network

Discovering shared, invariant feature representations across subjects in electrocardiogram (ECG) classification tasks is crucial for improving the generalization of models to unknown patients. Although deep neural networks have recently been emerging in extracting generalizable ECG features, they usually rely on labeled samples from a large number of subjects to guarantee generalization. Extracting invariant representations to intersubject variabilities from a small number of subjects is still a challenge today due to individual physical differences. To address this problem, we propose an adversarial deep neural network framework for interpatient heartbeat classification by integrating adversarial learning into a convolutional neural network to learn subject-invariant, class-discriminative features. The proposed method was evaluated on the MIT-BIH arrhythmia database which is a publicly available ECG dataset collected from 47 patients. Compared with the state-of-the-art methods, the proposed method achieves the highest performance for detecting supraventricular ectopic beats (SVEBs), which are very challenging to identify, and also gains comparable performance on the detection of ventricular ectopic beats (VEBs). The sensitivities of SVEBs and VEBs are 78.8% and 92.5%, respectively. The precisions of SVEBs and VEBs are 90.8% and 94.3%, respectively. With high performance in the detection of pathological classes (i.e., SVEBs and VEBs), this work provides a promising method for ECG classification tasks when the number of patients is limited.

Optimized Feature Subset Selection Using Genetic Algorithm for Preterm Labor Prediction Based on Electrohysterography

Electrohysterography (EHG) has emerged as an alternative technique to predict preterm labor, which still remains a challenge for the scientific-technical community. Based on EHG parameters, complex classification algorithms involving non-linear transformation of the input features, which clinicians found difficult to interpret, were generally used to predict preterm labor. We proposed to use genetic algorithm to identify the optimum feature subset to predict preterm labor using simple classification algorithms. A total of 203 parameters from 326 multichannel EHG recordings and obstetric data were used as input features. We designed and validated 3 base classifiers based on k-nearest neighbors, linear discriminant analysis and logistic regression, achieving F1-score of 84.63 ± 2.76%, 89.34 ± 3.5% and 86.87 ± 4.53%, respectively, for incoming new data. The results reveal that temporal, spectral and non-linear EHG parameters computed in different bandwidths from multichannel recordings provide complementary information on preterm labor prediction. We also developed an ensemble classifier that not only outperformed base classifiers but also reduced their variability, achieving an F1-score of 92.04 ± 2.97%, which is comparable with those obtained using complex classifiers. Our results suggest the feasibility of developing a preterm labor prediction system with high generalization capacity using simple easy-to-interpret classification algorithms to assist in transferring the EHG technique to clinical practice.

Diagnostic Interpretation of Non-Uniformly Sampled Electrocardiogram

We present a set of three fundamental methods for electrocardiogram (ECG) diagnostic interpretation adapted to process non-uniformly sampled signal. The growing volume of ECGs recorded daily all over the world (roughly estimated to be 600 TB) and the expectance of long persistence of these data (on the order of 40 years) motivated us to challenge the feasibility of medical-grade diagnostics directly based on arbitrary non-uniform (i.e., storage-efficient) ECG representation. We used a refined time-independent QRS detection method based on a moving shape matching technique. We applied a graph data representation to quantify the similarity of asynchronously sampled heartbeats. Finally, we applied a correlation-based non-uniform to time-scale transform to get a multiresolution ECG representation on a regular dyadic grid and to find precise P, QRS and T wave delimitation points. The whole processing chain was implemented and tested with MIT-BIH Database (probably the most referenced cardiac database) and CSE Multilead Database (used for conformance testing of medical instruments) signals arbitrarily sampled accordingly to a perceptual model (set for variable sampling frequency of 100-500 Hz, compression ratio 3.1). The QRS detection shows an accuracy of 99.93% with false detection ratio of only 0.18%. The classification shows an accuracy of 99.27% for 14 most frequent MIT-BIH beat types and 99.37% according to AAMI beat labels. The wave delineation shows cumulative (i.e., sampling model and non-uniform processing) errors of: 9.7 ms for P wave duration, 3.4 ms for QRS, 6.7 ms for P-Q segment and 17.7 ms for Q-T segment, all the values being acceptable for medical-grade interpretive software.

Estimation and Improvement of Recovery of Low Grade Copper Oxide Using Sulfide Activation Flotation Method Based on GA–BPNN

Copper oxide ore is an important copper ore resource. For a certain copper oxide ore in Yunnan, China, experiments have been conducted on the grinding fineness, collector dosage, sodium sulfide dosage, inhibitor dosage, and activator dosage. The results showed that, by controlling the above conditions, better sulfide flotation indices of copper oxide ore are obtained. Additionally, ammonium bicarbonate and ethylenediamine phosphate enhanced the sulfide flotation of copper oxide ore, whereas the combined activator agent exhibited a better performance than either individual activator. In addition, to optimize all of the conditions in a more reasonable way, a combination of the 5-11-1 genetic algorithm and back propagation neural network (GA–BPNN) was used to set up a mathematical optimization model. The results of the back propagation neural network (BPNN) model showed that the R2 value was 0.998, and the results were in accordance with the requirement model. After 4169 iterations, the error in the objective function was 0.001, which met the convergence requirements for the final solution. The genetic algorithm (GA) model was used to optimize the BPNN model. After 100 generations, a copper recovery of 87.62% was achieved under the following conditions: grinding fineness of 0.074 mm, which accounted for 91.7%; collector agent dosage of 487.7 g/t; sodium sulfide dosage of 1157.2 g/t; combined activator agent dosage of 537.8 g/t; inhibitor dosage of 298.9 g/t. Using the combined amine and ammonium salt to enhance the sulfide activation efficiency, a GA–BPNN model was used to achieve the goal of global optimizations of copper oxide ore and good flotation indices were obtained.

A Novel 1-D CCANet for ECG Classification

This paper puts forward a 1-D convolutional neural network (CNN) that exploits a novel analysis of the correlation between the two leads of the noisy electrocardiogram (ECG) to classify heartbeats. The proposed method is one-dimensional, enabling complex structures while maintaining a reasonable computational complexity. It is based on the combination of elementary handcrafted time domain features, frequency domain features through spectrograms and the use of autoregressive modeling. On the MIT-BIH database, a 95.52% overall accuracy is obtained by classifying 15 types, whereas a 95.70% overall accuracy is reached when classifying 7 types from the INCART database.

Automated detection of arrhythmia from electrocardiogram signal based on new convolutional encoded features with bidirectional long short-term memory network classifier

Early detection of cardiac arrhythmia is needed to reduce mortality. Automatically detecting the cardiac arrhythmias is a very challenging task. In this paper, a new deep convolutional encoded feature (CEF) based on non-linear compression composition is applied to diminish the ECG signal segment size. Bidirectional long short-term memory (BLSTM) network classifier has been proposed to detect arrhythmias from the ECG signal, which is encoded by the convolutional encoder. These encoded features are used as the input to BLSTM network classifier. For performance comparison, three other classifiers, namely unidirectional long short-term memory (ULSTM) network, gated recurrent Unit (GRU) and multilayer perceptron, are designed. The experimental studies detect and classify arrhythmias present in the MIT-BIH arrhythmia database into five different heartbeat classes. These heartbeat classes are normal (N), left bundle branch block (L), right bundle branch block(R), paced (P) and premature ventricular contraction (V). Evaluation of performance and system efficiency has been done with the help of four different types of evaluation criteria which are overall accuracy, precision, recall, and F-score. The experimental results indicate that the BLSTM network has achieved an overall accuracy of 99.52% with the processing time of only 6.043 s.

Computational Diagnostic Techniques for Electrocardiogram Signal Analysis

Cardiovascular diseases (CVDs), including asymptomatic myocardial ischemia, angina, myocardial infarction, and ischemic heart failure, are the leading cause of death globally. Early detection and treatment of CVDs significantly contribute to the prevention or delay of cardiovascular death. Electrocardiogram (ECG) records the electrical impulses generated by heart muscles, which reflect regular or irregular beating activity. Computer-aided techniques provide fast and accurate tools to identify CVDs using a patient's ECG signal, which have achieved great success in recent years. Latest computational diagnostic techniques based on ECG signals for estimating CVDs conditions are summarized here. The procedure of ECG signals analysis is discussed in several subsections, including data preprocessing, feature engineering, classification, and application. In particular, the End-to-End models integrate feature extraction and classification into learning algorithms, which not only greatly simplifies the process of data analysis, but also shows excellent accuracy and robustness. Portable devices enable users to monitor their cardiovascular status at any time, bringing new scenarios as well as challenges to the application of ECG algorithms. Computational diagnostic techniques for ECG signal analysis show great potential for helping health care professionals, and their application in daily life benefits both patients and sub-healthy people.

Arrhythmia Classification with ECG signals based on the Optimization-Enabled Deep Convolutional Neural Network

Arrhythmia classification is the need of the hour as the world is reporting a higher death troll as a cause of cardiac diseases. Most of the existing methods developed for arrhythmia classification face a hectic challenge of classification accuracy and they raised the challenge of automatic monitoring and classification methods. Accordingly, the paper proposes the automatic arrhythmia classification strategy using the optimization-based deep convolutional neural network (deep CNN). The optimization algorithm named, Bat-Rider optimization algorithm (BaROA) is newly developed using the multi-objective bat algorithm (MOBA) and Rider Optimization Algorithm (ROA).At first, the wave and gabor features are extracted from the ECG signals in such a way that these features represent the individual ECG features. Finally, the signals are provided to the BaROA-based DCNN classifier that identifies conditions of the individual as arrhythmia and no-arrhythmia from the ECG signals. The methods are analyzed using the MIT-BIH Arrhythmia Database and the analysis is performed based on the evaluation parameters, like accuracy, specificity, and sensitivity, which are found to be 93.19 %, 95 %, and 93.98 %, respectively.

Myocardial infarction evaluation from stopping time decision toward interoperable algorithmic states in reinforcement learning

BACKGROUND

The Elliot wave principle commonly characterizes the impulsive and corrective wave trends for both financial market trends and electrocardiograms. The impulsive wave trends of electrocardiograms can annotate several wave components of heart-beats including pathological heartbeat waveforms. The stopping time inquires which ordinal element satisfies the assumed mathematical condition within a numerical set. The proposed work constitutes several algorithmic states in reinforcement learning from the stopping time decision, which determines the impulsive wave trends. Each proposed algorithmic state is applicable to any relevant algorithmic state in reinforcement learning with fully numerical explanations. Because commercial electrocardiographs still misinterpret myocardial infarctions from extraordinary electrocardiograms, a novel algorithm needs to be developed to evaluate myocardial infarctions. Moreover, differential diagnosis for right ventricle infarction is required to contraindicate a medication such as nitroglycerin.

METHODS

The proposed work implements the stopping time theory to impulsive wave trend distribution. The searching process of the stopping time theory is equivalent to the actions toward algorithmic states in reinforcement learning. The state value from each algorithmic state represents the numerically deterministic annotated results from the impulsive wave trend distribution. The shape of the impulsive waveform is evaluated from the interoperable algorithmic states via least-first-power approximation and approximate entropy. The annotated electrocardiograms from the impulsive wave trend distribution utilize a structure of neural networks to approximate the isoelectric baseline amplitude value of the electrocardiograms, and detect the conditions of myocardial infarction. The annotated results from the impulsive wave trend distribution consist of another reinforcement learning environment for the evaluation of impulsive waveform direction.

RESULTS

The accuracy to discern myocardial infarction was found to be 99.2754% for the data from the comma-separated value format files, and 99.3579% for those containing representative beats. The clinical dataset included 276 electrocardiograms from the comma-separated value files and 623 representative beats.

CONCLUSIONS

Our study aims to support clinical interpretation on 12-channel electrocardiograms. The proposed work is suitable for a differential diagnosis under infarction in the right ventricle to avoid contraindicated medication during emergency. An impulsive waveform that is affected by myocardial infarction or the electrical direction of electrocardiography is represented as an inverse waveform.

Automated detection of cardiovascular disease by electrocardiogram signal analysis: a deep learning system

Automated electrocardiogram (ECG) diagnosis could be a useful aid for clinical use. We applied a deep learning method to build a system for automated detection and classification of ECG signals. We first trained a convolutional neural network (CNN) to detect cardiovascular disease in ECG signals using a training data set of 259,789 ECG signals collected from the cardiac function rooms of a tertiary care hospital. The CNN classification was validated using an independent test data set of 18,018 ECG signals. The labels used covered >90% of clinical diagnoses. The system grouped ECGs into 18 classifications-17 different types of abnormalities and normal ECG. The overall accuracy of the model was tested and found to be close to 95%; the accuracy for diagnosis of normal rhythm/atrial fibrillation was 99.15%. The proposed CNN model could help reduce misdiagnosis and missed diagnosis in primary care settings and also improve efficiency and save manpower cost for large general hospitals.

A Review of Algorithm & Hardware Design for AI-Based Biomedical Applications

This paper reviews the state of the arts and trends of the AI-Based biomedical processing algorithms and hardware. The algorithms and hardware for different biomedical applications such as ECG, EEG and hearing aid have been reviewed and discussed. For algorithm design, various widely used biomedical signal classification algorithms have been discussed including support vector machine (SVM), back propagation neural network (BPNN), convolutional neural networks (CNN), probabilistic neural networks (PNN), recurrent neural networks (RNN), Short-term Memory Network (LSTM), fuzzy neural network and etc. The pros and cons of the classification algorithms have been analyzed and compared in the context of application scenarios. The research trends of AI-Based biomedical processing algorithms and applications are also discussed. For hardware design, various AI-Based biomedical processors have been reviewed and discussed, including ECG classification processor, EEG classification processor, EMG classification processor and hearing aid processor. Various techniques on architecture and circuit level have been analyzed and compared. The research trends of the AI-Based biomedical processor have also been discussed.

An Effective LSTM Recurrent Network to Detect Arrhythmia on Imbalanced ECG Dataset

To reduce the high mortality rate from cardiovascular disease (CVD), the electrocardiogram (ECG) beat plays a significant role in computer-aided arrhythmia diagnosis systems. However, the complex variations and imbalance of ECG beats make this a challenging issue. Since ECG beat data exist in heavily imbalanced category, an effective long short-term memory (LSTM) recurrence network model with focal loss (FL) is proposed. For this purpose, the LSTM network can disentangle the timing features in complex ECG signals, while the FL is used to resolve the category imbalance by downweighting easily identified normal ECG examples. The advantages of the proposed network have been verified in the MIT-BIH arrhythmia database. Experimental results show that the LSTM network with FL achieved a reliable solution to the problem of imbalanced datasets in ECG beat classification and was not sensitive to quality of ECG signals. The proposed method can be deployed in telemedicine scenarios to assist cardiologists into more accurately and objectively diagnosing ECG signals.

Percept-related EEG classification using machine learning approach and features of functional brain connectivity

Machine learning is a promising approach for electroencephalographic (EEG) trials classification. Its efficiency is largely determined by the feature extraction and selection techniques reducing the dimensionality of input data. Dimensionality reduction is usually implemented via the mathematical approaches (e.g., principal component analysis, linear discriminant analysis, etc.) regardless of the origin of analyzed data. We hypothesize that since EEG features are determined by certain neurophysiological processes, they should have distinctive characteristics in spatiotemporal domain. If so, it is possible to specify the set of EEG principal features based on the prior knowledge about underlying neurophysiological processes. To test this hypothesis, we consider the classification of EEG trials related to the perception of ambiguous visual stimuli. We observe that EEG features, underlying the different ambiguous stimuli interpretations, are defined by the network properties of neuronal activity. Having analyzed functional neural interactions, we specify the brain area in which neural network architecture exhibits differences for different classes of EEG trials. We optimize the feedforward multilayer perceptron and develop a strategy for the training set selection to maximize the classification accuracy, being 85% when all channels are used. The revealed localization of the percept-related features allows about 95% accuracy, when the number of channels is reduced up to 90%. Obtained results can be used for classification of EEG trials associated with more complex cognitive tasks. Taking into account that cognitive activity is subserved by a distributed functional cortical network, its topological properties have to be considered when selecting optimal features for EEG trial classification.

A Novel Approach for Multi-Lead ECG Classification Using DL-CCANet and TL-CCANet

Cardiovascular disease (CVD) has become one of the most serious diseases that threaten human health. Over the past decades, over 150 million humans have died of CVDs. Hence, timely prediction of CVDs is especially important. Currently, deep learning algorithm-based CVD diagnosis methods are extensively employed, however, most such algorithms can only utilize one-lead ECGs. Hence, the potential information in other-lead ECGs was not utilized. To address this issue, we have developed novel methods for diagnosing arrhythmia. In this work, DL-CCANet and TL-CCANet are proposed to extract abstract discriminating features from dual-lead and three-lead ECGs, respectively. Then, the linear support vector machine specializing in high-dimensional features is used as the classifier model. On the MIT-BIH database, a 95.2% overall accuracy is obtained by detecting 15 types of heartbeats using DL-CCANet. On the INCART database, overall accuracies of 94.01% (II and V1 leads), 93.90% (V1 and V5 leads) and 94.07% (II and V5 leads) are achieved by detecting seven types of heartbeat using DL-CCANet, while TL-CCANet yields a higher overall accuracy of 95.52% using the above three leads. In addition, all of the above experiments are implemented using noisy ECG data. The proposed methods have potential to be applied in the clinic and mobile devices.

A NOVEL TWO-LEAD ARRHYTHMIA CLASSIFICATION SYSTEM BASED ON CNN AND LSTM

Arrhythmia classification is useful during heart disease diagnosis. Although well-established for intra-patient diagnoses, inter-patient arrhythmia classification remains difficult. Most previous work has focused on the intra-patient condition and has not followed the Association for the Advancement of Medical Instrumentation (AAMI) standards. Here, we propose a novel system for arrhythmia classification based on multi-lead electrocardiogram (ECG) signals. The core of the design is that we fuse two types of deep learning features with some common traditional features and select discriminating features using a binary particle swarm optimization algorithm (BPSO). Then, the feature vector is classified using a weighted support vector machine (SVM) classifier. For a better generalization of the model and to draw fair comparisons, we carried out inter-patient experiments and followed the AAMI standards. We found that, when using common metrics aimed at multi-classification either macro- or micro-averaging, our system outperforms most other state-of-the-art methods.

A Personalized Arrhythmia Monitoring Platform

Arrhythmia detection is the core of cardiovascular disease diagnosis. Though, there is no such generic solution for detecting the arrhythmias at the moment they occur which is due to the non-stationary nature and inter-patient variations of ECG signals. The feature extraction and classification techniques are significant tools widely used in the automated classification of arrhythmias. This study aims to develop a personalized arrhythmia monitoring platform allowing real-time detection of arrhythmias from the subject’s electrocardiogram (ECG) signal for point-of-care usage. A novel method, i.e. discrete orthogonal stockwell transform (DOST) technique for feature extraction is employed to capture the significant time-frequency coefficients to constitute the feature set representing each of the ECG signals. These coefficients or features are classified using artificial bee colony (ABC) optimized twin least-square support vector machine (LSTSVM) for classifying the different categories of ECG signals. The ABC optimizes the dimension of the feature set and the learning parameters of the classifier. The proposed method is prototyped on the commercially available ARM-based embedded platform and validated on the benchmark MIT-BIH arrhythmia database. Further, the prototype is evaluated under two schemes, i.e. class and personalized schemes which reported a higher overall accuracy of 96.29% and 96.08% in the respective schemes than the existing works to the state-of-art CVDs diagnosis.

An improved genetic algorithm for designing optimal temporal patterns of neural stimulation

OBJECTIVE

Electrical neuromodulation therapies typically apply constant frequency stimulation, but non-regular temporal patterns of stimulation may be more effective and more efficient. However, the design space for temporal patterns is exceedingly large, and model-based optimization is required for pattern design. We designed and implemented a modified genetic algorithm (GA) intended for design optimal temporal patterns of electrical neuromodulation.

APPROACH

We tested and modified standard GA methods for application to designing temporal patterns of neural stimulation. We evaluated each modification individually and all modifications collectively by comparing performance to the standard GA across three test functions and two biophysically-based models of neural stimulation.

MAIN RESULTS

The proposed modifications of the GA significantly improved performance across the test functions and performed best when all were used collectively. The standard GA found patterns that outperformed fixed-frequency, clinically-standard patterns in biophysically-based models of neural stimulation, but the modified GA, in many fewer iterations, consistently converged to higher-scoring, non-regular patterns of stimulation.

SIGNIFICANCE

The proposed improvements to standard GA methodology reduced the number of iterations required for convergence and identified superior solutions.

Non-Uniform Sample Assignment in Training Set Improving Recognition of Hand Gestures Dominated with Similar Muscle Activities

So far, little is known how the sample assignment of surface electromyogram (sEMG) features in training set influences the recognition efficiency of hand gesture, and the aim of this study is to explore the impact of different sample arrangements in training set on the classification of hand gestures dominated with similar muscle activation patterns. Seven right-handed healthy subjects (24.2 ± 1.2 years) were recruited to perform similar grasping tasks (fist, spherical, and cylindrical grasping) and similar pinch tasks (finger, key, and tape pinch). Each task was sustained for 4 s and followed by a 5-s rest interval to avoid fatigue, and the procedure was repeated 60 times for every task. sEMG were recorded from six forearm hand muscles during grasping or pinch tasks, and 4-s sEMG from each channel was segmented for empirical mode decomposition analysis trial by trial. The muscle activity was quantified with zero crossing (ZC) and Wilson amplitude (WAMP) of the first four resulting intrinsic mode function. Thereafter, a sEMG feature vector was constructed with the ZC and WAMP of each channel sEMG, and a classifier combined with support vector machine and genetic algorithm was used for hand gesture recognition. The sample number for each hand gesture was designed to be rearranged according to different sample proportion in training set, and corresponding recognition rate was calculated to evaluate the effect of sample assignment change on gesture classification. Either for similar grasping or pinch tasks, the sample assignment change in training set affected the overall recognition rate of candidate hand gesture. Compare to conventional results with uniformly assigned training samples, the recognition rate of similar pinch gestures was significantly improved when the sample of finger-, key-, and tape-pinch gesture were assigned as 60, 20, and 20%, respectively. Similarly, the recognition rate of similar grasping gestures also rose when the sample proportion of fist, spherical, and cylindrical grasping was 40, 30, and 30%, respectively. Our results suggested that the recognition rate of hand gestures can be regulated by change sample arrangement in training set, which can be potentially used to improve fine-gesture recognition for myoelectric robotic hand exoskeleton control.