Choose of wart treatment method using Naive Bayes and k-nearest neighbors classifiers

Uzun, Ruhiye; İşler, Yalçın; Toksan, Mualla

doi:10.1109/siu.2018.8404398

Cited by 7 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature related to prediction of the success of wart treatment method, classifier algorithms of Fuzzy Rules (Khozeimeh et al 2017b), support vector machines (Uzun et al 2018a), Naive Bayes (Uzun et al 2018b) and k-Nearest Neighbors (Uzun et al 2018b) were used previously. We explored the use of multi-layer perceptron and extremelearning machine on solving this problem.…”

Section: Resultsmentioning

confidence: 99%

“…Khozeimeh et al (2017b) prepared the database and obtained prediction accuracies of 83.3% for immunotherapy method and 80.7% for cryotherapy method. Uzun et al (2018aUzun et al ( , 2018bUzun et al ( , 2019 Putra et al (2018) proposed the AdaBoost algorithm to determine the success of the selected wart treatment method and achieved the maximum classification performance of an accuracy of 93.89%, a sensitivity of 96.64%, and a specificity of 93.10%. Khatri et…”

Section: Validation and Performance Measuresmentioning

confidence: 99%

“…They found a similar classifier performance by using the 7-nearest neighbor classifiers. They also obtained higher classifier performances of (85.46%) by using the support vector machine (Uzun et al 2018b). Abdar et al (2019) proposed a new computeraided diagnosis (CAD) system, which is combined by improved adaptive particle swarm optimization algorithm and artificial immune recognition system, using machine learning to classify the wart treatment methods.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Untitled

Uzun¹,

İşler²,

Toksan³

2020

KSEJ

View full text Add to dashboard Cite

groups according to their differences about colors, sizes, and constitutional structure: Common warts, Plantar warts, Flat warts, and Genital warts. Common and plantar warts are the most common types among them. Common warts are a type of wart seen on hands, fingers, and nails. They are harmful but painless. Plantar warts are painful warts embedded in the skin in single or multiple groups (Hosrik 2010). Almost all age groups, especially children and young adults (between 10 and 20 years of age) suffer from warts. It is estimated that about 10% of the public population suffer from warts in Turkey (Carman et al. 2013, Hosrik 2010. To eliminate this type of dermatoses, several treatment methods have been developed. Surgical treatment, cryotherapy,

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Validation and Performance Measuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Untitled

Uzun¹,

İşler²,

Toksan³

2020

KSEJ

View full text Add to dashboard Cite

show abstract

“…Then, we compared the proposed model with the existing prediction model -knearest neighbor classifier (KNN) [27], support vector machine (SVM) [28] and linear regression with L1 regularization (Lasso) [29], random forest (RF) [30], gradient tree boosting-based classifier implemented in the XGBoost package (XGBoost) [31], graph neural networks (GNN) [32] and graph convolution networks (GCN) [33]. As shown in Table 3, the above prediction models are trained directly with VAE.…”

Section: Combined Model Performancementioning

confidence: 99%

Combining VAE with GTCN for Pan-cancer Prediction and Biomarker Identification using Multi-omics Data

Chen

Tie

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

Objective: To overcome the phenomenon of “dimensionality curse” and class imbalance existing in biomolecule data and take full advantage of it to realize pan-cancer prediction and biomarker identification. Methods: We collected a total of 6133 samples with 33 types of tumor from the cancer genome atlas (TCGA), which had been classified and labeled for training,validation and testing, composed of multi-omics data, including DNA methylation,RNA expression and reverse phase protein array (RPPA). Then, we integrate variational autoencoder (VAE) and graph convolution neural networks (GTCN) as an entity capable of projecting high-dimensional features to low latent space, generating samples similar to input data, fulfilling pan-cancer prediction and vital biomarkers associated with specific tumor types. The suggested model’s performance was tested following 10-fold cross validation and then compared to main-flow relevant models. Results: The average accuracy of the proposed model reached 93.90±1.01% after 10-fold cross validation in pan-cancer prediction task. Additional relevant evaluation metrics F1 score, precision and recall were 92.03±0.3%, 90.05±1.02% and 91.08±1.0%, respectively. For the prediction performance of single type of cancer,such as LGG and BRCA datasets, the proposed model achieved 83.46±0.19% and 84.02±0.25% prediction accuracy, separately. Furthermore, the model also identified a few essential biomarkers which were proved by the survival curve analysis. Conclusion: We developed a pan-cancer prediction and biomarker identificationsystem based on joining VAE and GTCN using multi-omics data. This approach indicates multi-omics data have close relationship with cancer and is conducive to understanding of the mechanism of cancer formation. The predictive results canbe consulted by doctors. Keywords: Multi-omics data; Variational auto-encoder; Graph tree convolutionnetwork; Pan-cancer prediction; Biomarker identification

show abstract