Journal: Multimedia Tools and Applications

Article Title: LWSNet - a novel deep-learning architecture to segregate Covid-19 and pneumonia from x-ray imagery

doi: 10.1007/s11042-022-14247-3

Figure Lengend Snippet: Layer-wise parameter details for the lightweight models

Article Snippet: Fig. 4 Training accuracy and training loss, validation accuracy and validation loss for individual lightweight models on dataset 1 The results of individual lightweight architecture: MobileNetV2 (Mbl), VGG-19 (Vgg), InceptionResNetV2 (Incp) and Custom lightweight CNN (CLCNN) are depicted in Fig. , also represent other three stacking experiment results.

Techniques: Activation Assay, Blocking Assay

Journal: Multimedia Tools and Applications

Article Title: LWSNet - a novel deep-learning architecture to segregate Covid-19 and pneumonia from x-ray imagery

doi: 10.1007/s11042-022-14247-3

Figure Lengend Snippet: The comparison of number of trainable parameters (Million) between original and lightweight versions

Article Snippet: Fig. 4 Training accuracy and training loss, validation accuracy and validation loss for individual lightweight models on dataset 1 The results of individual lightweight architecture: MobileNetV2 (Mbl), VGG-19 (Vgg), InceptionResNetV2 (Incp) and Custom lightweight CNN (CLCNN) are depicted in Fig. , also represent other three stacking experiment results.

Techniques: Comparison

Journal: Multimedia Tools and Applications

Article Title: LWSNet - a novel deep-learning architecture to segregate Covid-19 and pneumonia from x-ray imagery

doi: 10.1007/s11042-022-14247-3

Figure Lengend Snippet: Consolidated accuracy graph to single architecture to quad stack architecture. The individual model’s abbreviation within brakets is MobileNetV2(Mbl), VGG19(Vgg), InceptionResNetV2(Incp), and custom lightweight CNN (CLCNN) and ‘+’ sign indicate that models are concatenated for ensemble stacking

Article Snippet: Fig. 4 Training accuracy and training loss, validation accuracy and validation loss for individual lightweight models on dataset 1 The results of individual lightweight architecture: MobileNetV2 (Mbl), VGG-19 (Vgg), InceptionResNetV2 (Incp) and Custom lightweight CNN (CLCNN) are depicted in Fig. , also represent other three stacking experiment results.

Techniques:

Journal: Quantitative Biology

Article Title: Secure and efficient implementation of facial emotion detection for smart patient monitoring system

doi: 10.15302/J-QB-022-0312

Figure Lengend Snippet: Confusion matrix for classification performance on the FER2013 dataset by MobileNet‐v2 models with (A) floating‐point weights (FP32), MSD approximated weights with (B) p = 3, (C) p = 2 and (D) p = 1.

Article Snippet: The pretrained MobileNet‐v2 models with approximated weights were implemented on the Altera DE4 development board using the Quartus Prime Pro software package.

Techniques:

Journal: Multimedia Tools and Applications

Article Title: Bio-medical imaging (X-ray, CT, ultrasound, ECG), genome sequences applications of deep neural network and machine learning in diagnosis, detection, classification, and segmentation of COVID-19: a Meta-analysis & systematic review

doi: 10.1007/s11042-023-15029-1

Figure Lengend Snippet: Summary report of experimental setup work with technical details and performance metrics in the studied papers

Article Snippet: [ ] , ECG-CCNet (Ensemble VGG16,DenseNet201,MobileNetV2,ResNet152V2). , Conv:3,4, MP:3,4, FC:2, , 3 × 3 , 2 × 2 , Batch Size: 32 , 849 × 748 , 0.00001 , 75 , Accuracy:93.5%, Recall:87%, F1-score:87.03%, Specificity:95.66%, Precision:87.16%, AUC:95.33% , Softmax , Adam , Tensorflow.

Techniques: Activation Assay, Software, Blocking Assay

Journal: Journal of Imaging

Article Title: Automated Detection and Diagnosis of Diabetic Retinopathy: A Comprehensive Survey

doi: 10.3390/jimaging7090165

Figure Lengend Snippet: Classification-based studies in DR detection using fundus imaging.

Article Snippet: Patel, 2020 [ ] , EyePACS , Grade DR based on ICDR scale , Yes , DCNN: MobileNet v2 , 91.29% , NA , NA , NA.

Techniques: Imaging, Modification, Extraction

Journal: Journal of Imaging

Article Title: Automated Detection and Diagnosis of Diabetic Retinopathy: A Comprehensive Survey

doi: 10.3390/jimaging7090165

Figure Lengend Snippet: Classification-based studies in DR detection using OCT and OCTA.

Article Snippet: Patel, 2020 [ ] , EyePACS , Grade DR based on ICDR scale , Yes , DCNN: MobileNet v2 , 91.29% , NA , NA , NA.

Techniques: Extraction

Journal: Journal of Imaging

Article Title: Automated Detection and Diagnosis of Diabetic Retinopathy: A Comprehensive Survey

doi: 10.3390/jimaging7090165

Figure Lengend Snippet: Segmentation-based studies in DR detection using fundus images.

Article Snippet: Patel, 2020 [ ] , EyePACS , Grade DR based on ICDR scale , Yes , DCNN: MobileNet v2 , 91.29% , NA , NA , NA.

Techniques: Extraction

Journal: Journal of Imaging

Article Title: Automated Detection and Diagnosis of Diabetic Retinopathy: A Comprehensive Survey

doi: 10.3390/jimaging7090165

Figure Lengend Snippet: Segmentation-based studies in DR detection using OCT, OCTA images.

Article Snippet: Patel, 2020 [ ] , EyePACS , Grade DR based on ICDR scale , Yes , DCNN: MobileNet v2 , 91.29% , NA , NA , NA.

Techniques: Control, Extraction