An improved hawks optimizer based learning algorithms for cardiovascular disease prediction

Kumar, A. Saran; Rekha, R.

doi:10.1016/j.bspc.2022.104442

Cited by 17 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…InceptionV3 [29], VGG16 [30,40], ResNet50 [31,32], DenseNet201 [33] and MobileNetV2 [33,34] models are chosen for transfer learning to figure out drowsiness recognition process. Chosen these models because they perform well in computer vision.…”

Section: Pre-trained Modelsmentioning

confidence: 99%

A Novel Approach to Detect Driver Drowsiness Using Transfer Learning and Hybrid Features

2024

Preprint

View full text Add to dashboard Cite

In worldwide, drowsiness is one of the prevalent reasons to cause accident. Statistics show that fatigued drivers are a major factor in causing many accidents. According to studies by the National Sleep Foundation, 20% of drivers feel sleepy to some extent while driving. Deep learning-based methods are the most recent ones that researchers have used to analyse videos and detect tiredness. Convolution neural networks utilizes extracted face features like yawning, eye flashing and head movements to detect exhaustion and sleepiness. Incorporating modified InceptionV3, VGG16, ResNet50, DenseNet201 and MobileNetV2 architecture over Driver Drowsiness Dataset to propose an ensemble deep learning model. Feature extraction was done using these models. The global max pooling layer is used to improve spatial robustness and dropout approach was included in these models to avoid overfitting on training data. Finally, Sigmoid classifier is used to classify positive (drowsy) or a negative (nondrowsy) result. These models outputs are given to a proposed ensemble algorithm. This model outperforms the alternative strategy with respect to performance metrics. The suggested ensemble framework performs better in identifying driver drowsiness than existing state-of-the-art techniques on basis of accuracy.

show abstract

Section: Pre-trained Modelsmentioning

confidence: 99%

A Novel Approach to Detect Driver Drowsiness Using Transfer Learning and Hybrid Features

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…It demonstrates that higher-level convolutional features cover the sufficient semantic input image information. Lower-level convolutional features encompass superior higher-level (most influencing) input images; however, they reject the non-influencing features [36].…”

Section: Analysing Non-influencing Convolutional Feature With Feature...mentioning

confidence: 99%

“…The procedure related to the microscope lies in the inspection manually [19]. Also, subjective factors like fatigue and experience this cause prone to bias and the error rates are occurred are as higher from 30% to 40% [36]. A robust system is needed in the proposed approach to manually minimize the variations and errors to detect leukaemia [20] automatically.…”

Section: Introductionmentioning

confidence: 99%

A Novel Hybrid Classifier Model for Leukemia Prediction Using Machine Learning Techniques

2024

Preprint

View full text Add to dashboard Cite

Cancer is known as the second crucial disease that causes the highest cause of mortality across the world. Earlier and accurate cancer prediction with the automated design of a clinical decision support system helps the physicians control the mortality risk and therapeutic intervention. Machine Learning (ML) based prediction approaches are used to identify the appropriate values for cancer prediction. Also, optimization is an essential factor to endeavour proper decision making. A novel convolutional non-influencing feature rejection (CNI-FR) classifier model is utilized to enhance the classifiers' prediction accuracy. In the case of gene analysis, all the features are not highly solicited, and ML provides various approaches for feature selection and classification. It is dependent on the provided input data and its feature distribution. Thus, both feature analysis and classification are required for efficient classification. The primary research objective is to optimize the learning parameters like rejection rate for appropriate cancer prediction of conventional parameters. Here, feature analysis is performed, and the rejection threshold is set for these feature analysis to examine the cancer prediction robustly. Here, various online available cancer dataset is taken, and the proposed classifier model is executed. The outcomes reveal the performance of the anticipated model with other ML classifiers. The predictions based on the proposed model specify that the ML algorithm with its dependencies is suitable for appropriate cancer prediction.

show abstract

“…Stacked ensembles have proven to generally be more accurate prediction models than any one base learner alone in clinical contexts [12] , [13] , [14] . In particular, a large number of studies have used stacked ensembles to study COVID-19 data, with many of them focusing on mortality (e.g., [15] , [16] , [17] , [18] , [19] , [20] , [21] ) and a few assessing cardiac events [22] , [23] . In spite of this progress, it remains unclear how to define the best model combinations for strong performance when using stacked generalization.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of stacked ensemble model performance to predict clinical outcomes: A COVID-19 study

Kablan,

Miller,

Suliman

et al. 2023

International Journal of Medical Informatics

View full text Add to dashboard Cite

An improved hawks optimizer based learning algorithms for cardiovascular disease prediction

Cited by 17 publications

References 29 publications

A Novel Approach to Detect Driver Drowsiness Using Transfer Learning and Hybrid Features

A Novel Approach to Detect Driver Drowsiness Using Transfer Learning and Hybrid Features

A Novel Hybrid Classifier Model for Leukemia Prediction Using Machine Learning Techniques

Evaluation of stacked ensemble model performance to predict clinical outcomes: A COVID-19 study

Contact Info

Product

Resources

About