COVID-19 Chest X-RAY detection : A transfer learning approach

Rachha, Ashwin

doi:10.22541/au.160513358.82993050/v1

Cited by 3 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pre-trained models, known as the Transfer Learning Method, were developed to get around the DL models' limitations. With the innovation of Transfer Learning, it has been shown that language model pretraining helps make universal language representations [7]. Several DL-based architectures, including Transformers and BERT family classifiers, were applied for this procedure.…”

Section: A Quora Questions Classificationmentioning

confidence: 99%

“…Researchers used pre-trained models to improve performance and accuracy with less processing power when problem-solving methods changed. BERT's multi-layer, bidirectional Transformer encoder employs Transformer [7]. Many BERT designs improved performance.…”

Section: Insincere Question Classificationmentioning

confidence: 99%

“…Many BERT designs improved performance. The original model is slower than RoBERTa, DistilBERT, and ALBERT [7]. The model proposed by Vaswani et al [12] outperformed the CNN and RNN models in NLP and synthesis-training data scale design.…”

Section: Insincere Question Classificationmentioning

confidence: 99%

“…Although an ML strategy can produce decent results, meticulous feature extraction for text data is still required. While classic ML techniques like naive Bayes, logistic regression, and decision trees can legitimately solve this issue, they have significant flaws in how their constructions work [7]. The effectiveness of a system is significantly influenced by the retrieved features [4].…”

Section: A Why Deep Learning Algorithms?mentioning

confidence: 99%

See 3 more Smart Citations

A Review of Classification of Insincere Questions in Quora Using Deep Learning Approaches

Ahamed,

Ahangama

2023

2023 IEEE 17th International Conference on Industrial and Information Systems (ICIIS)

View full text Add to dashboard Cite

The rise of online question-and-answer platforms like Quora and Stack Overflow has transformed knowledge acquisition, offering a vast repository of collective information. However, this has also led to the proliferation of insincere questions, which lack a neutral undertone and are not intended for learning. The posting of such queries can lead to chaos, necessitating the need for monitoring and discerning which questions should be published to maintain the platform's quality. The classification of insincere questions is crucial for maintaining the quality of these platforms. Detecting insincere questions can enhance user experience and foster a healthy and safe environment for online discussions. While Quora previously relied on manual reviews, the application of algorithms, particularly those from the field of Deep Learning, a subset of Machine Learning, has made this process more efficient and accessible. This paper reviews various approaches and algorithms used in classifying insincere questions on Quora, their benefits, and drawbacks. It provides insights into how Deep Learning can enhance the accuracy and effectiveness of insincere question classification on online platforms. The review findings indicate that class imbalance is a common issue in this type of research, highlighting the need for further exploration in future work.

show abstract

Section: A Quora Questions Classificationmentioning

confidence: 99%

Section: Insincere Question Classificationmentioning

confidence: 99%

Section: Insincere Question Classificationmentioning

confidence: 99%

Section: A Why Deep Learning Algorithms?mentioning

confidence: 99%

See 2 more Smart Citations

A Review of Classification of Insincere Questions in Quora Using Deep Learning Approaches

Ahamed,

Ahangama

2023

2023 IEEE 17th International Conference on Industrial and Information Systems (ICIIS)

View full text Add to dashboard Cite

show abstract

“…Within a short time, this disease engulfed the whole world, infecting about 305 million people worldwide and claiming more than 5.48 million lives as of this writing. As a result, on March 11, 2020, the World Health Organization (WHO) declared COVID-19 a worldwide epidemic [1][2][3]. Most countries tried to implement restrictive measures to contain COVID-19, including physical distancing, preventing mass meetings and events, wearing face masks, stopping all unnecessary activities, and closing educational institutions.…”

Section: Introductionmentioning

confidence: 99%

A Novel Fusion System Based on Iris and Ear Biometrics for E-exams

Shaban¹,

Ahmed²,

Elsheweikh³

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

With the rapid spread of the coronavirus epidemic all over the world, educational and other institutions are heading towards digitization. In the era of digitization, identifying educational e-platform users using ear and iris based multimodal biometric systems constitutes an urgent and interesting research topic to preserve enterprise security, particularly with wearing a face mask as a precaution against the new coronavirus epidemic. This study proposes a multimodal system based on ear and iris biometrics at the feature fusion level to identify students in electronic examinations (E-exams) during the COVID-19 pandemic. The proposed system comprises four steps. The first step is image preprocessing, which includes enhancing, segmenting, and extracting the regions of interest. The second step is feature extraction, where the Haralick texture and shape methods are used to extract the features of ear images, whereas Tamura texture and color histogram methods are used to extract the features of iris images. The third step is feature fusion, where the extracted features of the ear and iris images are combined into one sequential fused vector. The fourth step is the matching, which is executed using the City Block Distance (CTB) for student identification. The findings of the study indicate that the system's recognition accuracy is 97%, with a 2% False Acceptance Rate (FAR), a 4% False Rejection Rate (FRR), a 94% Correct Recognition Rate (CRR), and a 96% Genuine Acceptance Rate (GAR). In addition, the proposed recognition system achieved higher accuracy than other related systems.

show abstract

COVID-19 Detection through Transfer Learning using Multimodal Imaging Data

Magar¹,

Mali²,

Thakare³

et al. 2022

IJARSCT

View full text Add to dashboard Cite

Late Reverse Transcription - Polymerase Chain Reaction (RT-PCR) structure for the acknowledgment of COVID-19 needs behind as a result of limited openness of test units and for the most part low certain signs in the first place periods of the disease, empowering the necessity for elective plans. To foster COVID-19 infection forecast instrument in light of Artificial Intelligence might benefit from some intervention. In the proposed framework CT pictures of X-beams are prepared utilizing Convolutional Neural Network strategies, which can assist framework with naturally anticipating the COVID-19 identification. The precision has demonstrated to be higher than different methods. Our proposed framework can accomplish close by 93-94% of precision for recognition of Coronavirus on bases of X-beam.

show abstract

COVID-19 Chest X-RAY detection : A transfer learning approach

Cited by 3 publications

References 9 publications

A Review of Classification of Insincere Questions in Quora Using Deep Learning Approaches

A Review of Classification of Insincere Questions in Quora Using Deep Learning Approaches

A Novel Fusion System Based on Iris and Ear Biometrics for E-exams

COVID-19 Detection through Transfer Learning using Multimodal Imaging Data

Contact Info

Product

Resources

About