COVID-19 pneumonia level detection using deep learning algorithm and transfer learning

Ali, Abbas M.; Ghafoor, Kayhan Zrar; Mulahuwaish, Aos; Maghdid, Halgurd S.

doi:10.1007/s12065-022-00777-0

Cited by 14 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To minimize the amount of training epochs, the batch normalization layer is seen to be a crucial component of CNN. As a result, the CNN's learning process becomes stable [3]. At this point, the output is 11 x 32 in size.…”

Section: Figure 5 the Architecture Of The Cnn Modelmentioning

confidence: 99%

BiLSTM-CNN Hybrid Intrusion Detection System for IoT Application

Sadhwani,

Khan,

Muthalagu

et al. 2024

Preprint

View full text Add to dashboard Cite

Intrusions in computer networks have increased significantly in recent times and network security mechanisms are not being developed at the same pace at which intrusion attacks are evolving. Therefore, a need has arisen to improve intrusion detection systems (IDS) to make network secure. This research focuses on anomaly-based IDS for security assaults. In this research, deep learning techniques such as Bi-directional Long Short-Term Memory (Bi-LSTM) and Convolutional Neural Networks (CNN) are implemented and subsequently used to design a novel BiLSTM-CNN hybrid IDS for the Internet of Things (IoT). The hybrid intrusion detection system model is created by utilizing the advantages of both the BiLSTM and the CNN's ability to extract temporal and spatial features respectively. The research uses the UNSW-NB 15 dataset for proposed deep learning IDS for IoT networks. The dataset has been split into training and testing data for classifying traffic into normal or attack classes. The models are run on GPU and CPU to illustrate their efficacy and match real-world IoT network communication behavior. The BiLSTM, CNN, and hybrid BiLSTM-CNN models are assessed on various aspects like Precision, Sensitivity, F1-Score, Miscalculation Rate, False Positive Rate, False Negative Rate, and Matthews Correlation Coefficient to evaluate the model’s robustness. The findings revealed that the hybrid model surpassed the BiLSTM and CNN models in all aspects. Additionally, the proposed model is compared with the cutting-edge existing approaches in terms of different performance metrics and proved to be better than state-of-the-art models.

show abstract

Section: Figure 5 the Architecture Of The Cnn Modelmentioning

confidence: 99%

BiLSTM-CNN Hybrid Intrusion Detection System for IoT Application

Sadhwani,

Khan,

Muthalagu

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Authors in [7] used ML models to obtain accuracy of 83.67%. Authors in [8] focused on diagnosing lung inflammation severity in COVID-19 patients using CNN, KNN, and other classification algorithms achieving 92.80% testing accuracy. Authors in [9] developed a mobile app utilizing deep learning techniques to classify pneumonia in patients.…”

Section: Related Workmentioning

confidence: 99%

Pneumonia Detection in Chest X-Rays using Transfer Learning and TPUs

Kundur,

Anil,

Dhulavvagol

et al. 2023

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

Pneumonia is a severe respiratory disease with potentially life-threatening consequences if not promptly diagnosed and treated. Chest X-rays are commonly employed for pneumonia detection, but interpreting the images can pose challenges. This study explores the efficacy of four popular transfer learning models, namely VGG16, ResNet, InceptionNet, and DenseNet, alongside a custom CNN model for this task. The model performance is evaluated using Mean Absolute Error (MAE) as the performance metric. The findings reveal that VGG16 outperforms the other transfer learning models, achieving the lowest MAE (66.19). To optimize the model training process, a distributed training strategy utilizing TensorFlow's TPU (Tensor Processing Unit) strategy is implemented. The custom CNN model is parallelized using TPU's multiple instances available over the cloud, enabling efficient computation parallelization and significantly reducing model training times. The experimental results demonstrate a remarkable decrease of 68.36% and 54.74% in model training times for the CNN model when trained using TPU compared to training on a CPU and GPU, respectively.

show abstract

“…Because one sign of COVID-19 is pneumonia, which can be assessed through X-rays [6,7] or CT scans [8,9], these techniques provide an essential diagnostic tool. In some confirmed positive cases of people infected with COVID-19, the infection does not appear on the radiograph, so an accurate result cannot be determined without an additional clinical symptom diagnosis [10].…”

Section: Introductionmentioning

confidence: 99%

Deep learning‐based COVID‐19 diagnosis using CT scans with laboratory and physiological parameters

Sameer

Mutlag

Gharghan

2023

IET Image Processing

View full text Add to dashboard Cite

The global economy has been dramatically impacted by COVID‐19, which has spread to be a pandemic. COVID‐19 virus affects the respiratory system, causing difficulty breathing in the patient. It is crucial to identify and treat infections as soon as possible. Traditional diagnostic reverse transcription‐polymerase chain reaction (RT‐PCR) methods require more time to find the infection. A high infection rate, slow laboratory analysis, and delayed test results caused the widespread and uncontrolled spread of the disease. This study aims to diagnose the COVID‐19 epidemic by leveraging a modified convolutional neural network (CNN) to quickly and safely predict the disease's appearance from computed tomography (CT) scan images and a laboratory and physiological parameters dataset. A dataset representing 500 patients was used to train, test, and validate the CNN model with results in detecting COVID‐19 having an accuracy, sensitivity, specificity, and F1‐score of 99.33%, 99.09%, 99.52%, and 99.24%, respectively. These experimental results suggest that our strategy performs better than previously published approaches.

show abstract

COVID-19 pneumonia level detection using deep learning algorithm and transfer learning

Cited by 14 publications

References 18 publications

BiLSTM-CNN Hybrid Intrusion Detection System for IoT Application

BiLSTM-CNN Hybrid Intrusion Detection System for IoT Application

Pneumonia Detection in Chest X-Rays using Transfer Learning and TPUs

Deep learning‐based COVID‐19 diagnosis using CT scans with laboratory and physiological parameters

Contact Info

Product

Resources

About