Commentary: Occam's razor: The simplest solution is always the best

Orozco-Sevilla, Vicente; Coselli, Joseph S.

doi:10.1016/j.jtcvs.2020.10.087

Cited by 2 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We mix 10 ResNet18 and 20 ResNet34 as the denotation “ResNet18+34(10+20),” 15 ResNet18 and 25 ResNet34 as “ResNet18+34(15+15),” and 20 ResNet18 and 10 ResNet34 as “ResNet18+34(20+10).” The combinations of ResNet18 alone and “ResNet18+34(20+10)” achieved the best accuracies of 93.18%. According to the simplicity principle of Occam's Razor rule, 66 the proposed algorithm AcneGrader with ResNet18 can achieve the best F1‐score, and we use ResNet18 as the base model.…”

Section: Resultsmentioning

confidence: 99%

AcneGrader: An ensemble pruning of the deep learning base models to grade acne

Liu

Fan

Duan

et al. 2022

Skin Research and Technology

View full text Add to dashboard Cite

Background Acne is one of the most common skin lesions in adolescents. Some severe or inflammatory acne leads to scars, which may have major impacts on patients’ quality of life or even job prospects. Grading acne plays an important role in diagnosis, and the diagnosis is made by counting the number of acne. It is a labor‐intensive job and it is easy for dermatologists to make mistakes, so it is very important to develop automatic diagnosis methods. Ensemble learning may improve the prediction results of the base models, but its time complexity is relatively high. The ensemble pruning strategy may solve this computational challenge by removing the redundant base models. Materials and methods This study proposed a novel ensemble pruning framework of deep learning models to accurately detect and grade acne using images. First, we train multi‐base models and prune the redundancy models according to the performance and diversity of the models. Then, we construct the new features of the training data by the base models we select in the previous step. Next, we remove the redundancy models further by a feature selection algorithm. Finally, we integrate all the base models by classifiers. The ensemble pruning algorithm was proposed to prune the deep learning base models. Results The experimental data showed that the ensemble pruned framework achieved a prediction accuracy of 85.82% on the acne dataset, better than the existing studies. To verify our method's effectiveness, we test our method in a skin cancer dataset and greatly outperform the state‐of‐the‐art methods. Conclusion The method we proposed is used to grade acne. Our method's performance outperforms state‐of‐the‐art methods on two datasets, and it can also remove redundancy models to reduce computational complexity.

show abstract

Section: Resultsmentioning

confidence: 99%

AcneGrader: An ensemble pruning of the deep learning base models to grade acne

Liu

Fan

Duan

et al. 2022

Skin Research and Technology

View full text Add to dashboard Cite

show abstract

Mutation-driven parallel evolution in emergence of ACE2-utilizing sarbecoviruses

Gao

Zhu²

2023

Front. Microbiol.

View full text Add to dashboard Cite

Mutation and recombination are two major genetic mechanisms that drive the evolution of viruses. They both exert an interplay during virus evolution, in which mutations provide a first ancestral source of genetic diversity for subsequent recombination. Sarbecoviruses are a group of evolutionarily related β-coronaviruses including human severe acute respiratory syndrome coronavirus (SARS-CoV) and SARS-CoV-2 and a trove of related animal viruses called SARS-like CoVs (SL-CoVs). This group of members either use or not use angiotensin-converting enzyme 2 (ACE2) as their entry receptor, which has been linked to the properties of their spike protein receptor binding domains (RBDs). This raises an outstanding question regarding how ACE2 binding originated within sarbecoviruses. Using a combination of analyses of phylogenies, ancestral sequences, structures, functions and molecular dynamics, we provide evidence in favor of an evolutionary scenario, in which three distinct ancestral RBDs independently developed the ACE2 binding trait via parallel amino acid mutations. In this process, evolutionary intermediate RBDs might be firstly formed through loop extensions to offer key functional residues accompanying point mutations to remove energetically unfavorable interactions and to change the dynamics of the functional loops, all required for ACE2 binding. Subsequent optimization in the context of evolutionary intermediates led to the independent emergence of ACE2-binding RBDs in the SARS-CoV and SARS-CoV-2 clades of Asian origin and the clade comprising SL-CoVs of European and African descent. These findings will help enhance our understanding of mutation-driven evolution of sarbecoviruses in their early history.

show abstract

Commentary: Occam's razor: The simplest solution is always the best

Cited by 2 publications

References 7 publications

AcneGrader: An ensemble pruning of the deep learning base models to grade acne

AcneGrader: An ensemble pruning of the deep learning base models to grade acne

Mutation-driven parallel evolution in emergence of ACE2-utilizing sarbecoviruses

Contact Info

Product

Resources

About