Deep neural networks versus support vector machines for ECG arrhythmia classification

Xu, Sean Shensheng; Mak, Man‐Wai; Cheung, Chun Shun

doi:10.1109/icmew.2017.8026250

Cited by 15 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be seen from Table 6 that all the other works achieved less accuracy while utilizing more features than our proposed method. The authors of [ 11 , 14 , 15 ] selected a very large number of features (236, 135, and 169 features, respectively) as an optimal feature set and achieved 82.96%, 74.77%, and 88.72% accuracies, respectively. Authors of the work [ 12 ] succeeded in selecting a comparatively lesser number of features (30 features), but the accuracy obtained was 85.58%.…”

Section: Resultsmentioning

confidence: 99%

“…Xu et al [ 11 ] experimented with different feature selection methods and classification algorithms to increase the classification accuracy of the heart arrhythmia dataset. They achieved best accuracies by using neural networks only, deep neural networks only, Fisher discriminant ratio + deep neural network, and principal component analysis + deep neural network, and they used 10-fold cross-validation with each method to achieve 82.22%, 81.42%, 82.96%, and 75.22% accuracies, respectively, for each method.…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

A Tri-Stage Wrapper-Filter Feature Selection Framework for Disease Classification

Mandal

Singh

Ijaz

et al. 2021

Sensors

View full text Add to dashboard Cite

In machine learning and data science, feature selection is considered as a crucial step of data preprocessing. When we directly apply the raw data for classification or clustering purposes, sometimes we observe that the learning algorithms do not perform well. One possible reason for this is the presence of redundant, noisy, and non-informative features or attributes in the datasets. Hence, feature selection methods are used to identify the subset of relevant features that can maximize the model performance. Moreover, due to reduction in feature dimension, both training time and storage required by the model can be reduced as well. In this paper, we present a tri-stage wrapper-filter-based feature selection framework for the purpose of medical report-based disease detection. In the first stage, an ensemble was formed by four filter methods—Mutual Information, ReliefF, Chi Square, and Xvariance—and then each feature from the union set was assessed by three classification algorithms—support vector machine, naïve Bayes, and k-nearest neighbors—and an average accuracy was calculated. The features with higher accuracy were selected to obtain a preliminary subset of optimal features. In the second stage, Pearson correlation was used to discard highly correlated features. In these two stages, XGBoost classification algorithm was applied to obtain the most contributing features that, in turn, provide the best optimal subset. Then, in the final stage, we fed the obtained feature subset to a meta-heuristic algorithm, called whale optimization algorithm, in order to further reduce the feature set and to achieve higher accuracy. We evaluated the proposed feature selection framework on four publicly available disease datasets taken from the UCI machine learning repository, namely, arrhythmia, leukemia, DLBCL, and prostate cancer. Our obtained results confirm that the proposed method can perform better than many state-of-the-art methods and can detect important features as well. Less features ensure less medical tests for correct diagnosis, thus saving both time and cost.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Literature Surveymentioning

confidence: 99%

A Tri-Stage Wrapper-Filter Feature Selection Framework for Disease Classification

Mandal

Singh

Ijaz

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Mustaqeem et al [27] achieved 78.26% accuracy by selecting the best features using a wrapper algorithm and various machine-learning classifiers. Shensheng et al [28] achieved an accuracy of 80.6% using the Fisher discriminant ratio and deep neural networks using tenfold cross-validation. Özçift [29] proposed a resampling strategy based on RFs using an ensemble of classifiers and achieved 90% accuracy for 16 classes.…”

Section: Comparison Studymentioning

confidence: 99%

Cardiac Arrhythmia Disease Classifier Model Based on a Fuzzy Fusion Approach

Taher¹,

Alshammari²,

Osman³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Cardiac diseases are one of the greatest global health challenges. Due to the high annual mortality rates, cardiac diseases have attracted the attention of numerous researchers in recent years. This article proposes a hybrid fuzzy fusion classification model for cardiac arrhythmia diseases. The fusion model is utilized to optimally select the highest-ranked features generated by a variety of well-known feature-selection algorithms. An ensemble of classifiers is then applied to the fusion's results. The proposed model classifies the arrhythmia dataset from the University of California, Irvine into normal/abnormal classes as well as 16 classes of arrhythmia. Initially, at the preprocessing steps, for the miss-valued attributes, we used the average value in the linear attributes group by the same class and the most frequent value for nominal attributes. However, in order to ensure the model optimality, we eliminated all attributes which have zero or constant values that might bias the results of utilized classifiers. The preprocessing step led to 161 out of 279 attributes (features). Thereafter, a fuzzy-based feature-selection fusion method is applied to fuse high-ranked features obtained from different heuristic feature-selection algorithms. In short, our study comprises three main blocks: (1) sensing data and preprocessing; (2) feature queuing, selection, and extraction; and (3) the predictive model. Our proposed method improves classification performance in terms of accuracy, F1 measure, recall, and precision when compared to state-of-the-art techniques. It achieves 98.5% accuracy for binary class mode and 98.9% accuracy for categorized class mode.

show abstract

“…End-to-end recognition is difficult for DNN, because it has limited abstraction ability, whereas CNN has a high abstraction power and can analyze the image features to examine the situation. At the beginning of a fire, the flame is of a small size and interval; in this situation, it is difficult to capture image features from flame video data [41]. Fuzzy algorithms utilize membership functions to represent proximity to situations that cannot be clearly divided.…”

Section: Literature Reviewmentioning

confidence: 99%

Early Fire Detection Using Long Short-Term Memory-Based Instance Segmentation and Internet of Things for Disaster Management

Malebary

2023

Sensors

View full text Add to dashboard Cite

Fire outbreaks continue to cause damage despite the improvements in fire-detection tools and algorithms. As the human population and global warming continue to rise, fires have emerged as a significant worldwide issue. These factors may contribute to the greenhouse effect and climatic changes, among other detrimental consequences. It is still challenging to implement a well-performing and optimized approach, which is sufficiently accurate, and has tractable complexity and a low false alarm rate. A small fire and the identification of a fire from a long distance are also challenges in previously proposed techniques. In this study, we propose a novel hybrid model, called IS-CNN-LSTM, based on convolutional neural networks (CNN) to detect and analyze fire intensity. A total of 21 convolutional layers, 24 rectified linear unit (ReLU) layers, 6 pooling layers, 3 fully connected layers, 2 dropout layers, and a softmax layer are included in the proposed 57-layer CNN model. Our proposed model performs instance segmentation to distinguish between fire and non-fire events. To reduce the intricacy of the proposed model, we also propose a key-frame extraction algorithm. The proposed model uses Internet of Things (IoT) devices to alert the relevant person by calculating the severity of the fire. Our proposed model is tested on a publicly available dataset having fire and normal videos. The achievement of 95.25% classification accuracy, 0.09% false positive rate (FPR), 0.65% false negative rate (FNR), and a prediction time of 0.08 s validates the proposed system.

show abstract

Deep neural networks versus support vector machines for ECG arrhythmia classification

Cited by 15 publications

References 12 publications

A Tri-Stage Wrapper-Filter Feature Selection Framework for Disease Classification

A Tri-Stage Wrapper-Filter Feature Selection Framework for Disease Classification

Cardiac Arrhythmia Disease Classifier Model Based on a Fuzzy Fusion Approach

Early Fire Detection Using Long Short-Term Memory-Based Instance Segmentation and Internet of Things for Disaster Management

Contact Info

Product

Resources

About