Grad- CAM and Grad-Cam++ visualization of optimized CNN.

<p>Grad- CAM and Grad-Cam++ visualization of optimized CNN.</p>

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Ali Raza (3558965) (author)
مؤلفون آخرون: Akhtar Ali (603199) (author), Sami Ullah (613609) (author), Yasir Nadeem Anjum (20934626) (author), Basit Rehman (20934629) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852021865942351872
author Ali Raza (3558965)
author2 Akhtar Ali (603199)
Sami Ullah (613609)
Yasir Nadeem Anjum (20934626)
Basit Rehman (20934629)
author2_role author
author
author
author
author_facet Ali Raza (3558965)
Akhtar Ali (603199)
Sami Ullah (613609)
Yasir Nadeem Anjum (20934626)
Basit Rehman (20934629)
author_role author
dc.creator.none.fl_str_mv Ali Raza (3558965)
Akhtar Ali (603199)
Sami Ullah (613609)
Yasir Nadeem Anjum (20934626)
Basit Rehman (20934629)
dc.date.none.fl_str_mv 2025-03-25T20:04:27Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0317181.g023
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Grad-_CAM_and_Grad-Cam_visualization_of_optimized_CNN_/28664948
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Medicine
Immunology
Developmental Biology
Cancer
Science Policy
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
smart healthcare application
mathematical computational cost
healthcare providers diagnosing
convolutional neural networks
evaluate model interpretability
skin cancer classification
cancer skin classification
div >< p
cross validation technique
classification accuracy rates
>) could lead
skin cancer class
model training involved
develop reliable optimized
skin cancer
model ’
skin lesions
healthy class
xai </
would assist
unseen data
unseed data
turn leads
strongly associated
skin disease
seven forms
rmsprop </
prevalent types
prediction models
patient ’
optimized cnn
offered specifically
network fitting
much smaller
key aspect
interpretational aspects
initial diagnosis
holdout validation
healthare expenditure
ham10000 </
generalization performance
generalization ability
enhanced speed
early detection
drawbacks mainly
detected early
convergence rate
cnn </
clinical examination
central component
cam </
cam ++</
better performance
better outcomes
algorithms applied
af </
adam </
activation functions
>, achieving
dc.title.none.fl_str_mv Grad- CAM and Grad-Cam++ visualization of optimized CNN.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p>Grad- CAM and Grad-Cam++ visualization of optimized CNN.</p>
eu_rights_str_mv openAccess
id Manara_eee1f5d73a75bbd540aeeffd61a1a604
identifier_str_mv 10.1371/journal.pone.0317181.g023
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/28664948
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Grad- CAM and Grad-Cam++ visualization of optimized CNN.Ali Raza (3558965)Akhtar Ali (603199)Sami Ullah (613609)Yasir Nadeem Anjum (20934626)Basit Rehman (20934629)MedicineImmunologyDevelopmental BiologyCancerScience PolicySpace ScienceEnvironmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedsmart healthcare applicationmathematical computational costhealthcare providers diagnosingconvolutional neural networksevaluate model interpretabilityskin cancer classificationcancer skin classificationdiv >< pcross validation techniqueclassification accuracy rates>) could leadskin cancer classmodel training involveddevelop reliable optimizedskin cancermodel ’skin lesionshealthy classxai </would assistunseen dataunseed dataturn leadsstrongly associatedskin diseaseseven formsrmsprop </prevalent typesprediction modelspatient ’optimized cnnoffered specificallynetwork fittingmuch smallerkey aspectinterpretational aspectsinitial diagnosisholdout validationhealthare expenditureham10000 </generalization performancegeneralization abilityenhanced speedearly detectiondrawbacks mainlydetected earlyconvergence ratecnn </clinical examinationcentral componentcam </cam ++</better performancebetter outcomesalgorithms appliedaf </adam </activation functions>, achieving<p>Grad- CAM and Grad-Cam++ visualization of optimized CNN.</p>2025-03-25T20:04:27ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0317181.g023https://figshare.com/articles/figure/Grad-_CAM_and_Grad-Cam_visualization_of_optimized_CNN_/28664948CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/286649482025-03-25T20:04:27Z
spellingShingle Grad- CAM and Grad-Cam++ visualization of optimized CNN.
Ali Raza (3558965)
Medicine
Immunology
Developmental Biology
Cancer
Science Policy
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
smart healthcare application
mathematical computational cost
healthcare providers diagnosing
convolutional neural networks
evaluate model interpretability
skin cancer classification
cancer skin classification
div >< p
cross validation technique
classification accuracy rates
>) could lead
skin cancer class
model training involved
develop reliable optimized
skin cancer
model ’
skin lesions
healthy class
xai </
would assist
unseen data
unseed data
turn leads
strongly associated
skin disease
seven forms
rmsprop </
prevalent types
prediction models
patient ’
optimized cnn
offered specifically
network fitting
much smaller
key aspect
interpretational aspects
initial diagnosis
holdout validation
healthare expenditure
ham10000 </
generalization performance
generalization ability
enhanced speed
early detection
drawbacks mainly
detected early
convergence rate
cnn </
clinical examination
central component
cam </
cam ++</
better performance
better outcomes
algorithms applied
af </
adam </
activation functions
>, achieving
status_str publishedVersion
title Grad- CAM and Grad-Cam++ visualization of optimized CNN.
title_full Grad- CAM and Grad-Cam++ visualization of optimized CNN.
title_fullStr Grad- CAM and Grad-Cam++ visualization of optimized CNN.
title_full_unstemmed Grad- CAM and Grad-Cam++ visualization of optimized CNN.
title_short Grad- CAM and Grad-Cam++ visualization of optimized CNN.
title_sort Grad- CAM and Grad-Cam++ visualization of optimized CNN.
topic Medicine
Immunology
Developmental Biology
Cancer
Science Policy
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
smart healthcare application
mathematical computational cost
healthcare providers diagnosing
convolutional neural networks
evaluate model interpretability
skin cancer classification
cancer skin classification
div >< p
cross validation technique
classification accuracy rates
>) could lead
skin cancer class
model training involved
develop reliable optimized
skin cancer
model ’
skin lesions
healthy class
xai </
would assist
unseen data
unseed data
turn leads
strongly associated
skin disease
seven forms
rmsprop </
prevalent types
prediction models
patient ’
optimized cnn
offered specifically
network fitting
much smaller
key aspect
interpretational aspects
initial diagnosis
holdout validation
healthare expenditure
ham10000 </
generalization performance
generalization ability
enhanced speed
early detection
drawbacks mainly
detected early
convergence rate
cnn </
clinical examination
central component
cam </
cam ++</
better performance
better outcomes
algorithms applied
af </
adam </
activation functions
>, achieving