Journal: Physics and Imaging in Radiation Oncology

Article Title: A systematic review of the role of artificial intelligence in automating computed tomography-based adaptive radiotherapy for head and neck cancer

doi: 10.1016/j.phro.2025.100731

Figure Lengend Snippet: Summary of 3 radiomics studies (above) and 3 non-radiomic studies (below) included in the radiomics and predictive models section.

Article Snippet: Iliadou V et al. , Cancers (2022) , Handcrafted (Pyradiomics) , SVM, KNN (MATLAB) , The need of ART , Clinical Target Volume (CTV) and Parotid Glands (PG) , 40 (n.d.) , Shape, first-order, GLCM, GLDM, GLRLM, GLSZM, NGTDM (104) , 24 (36.4 %).

Techniques: Biomarker Discovery, Imaging

Journal: PeerJ Computer Science

Article Title: A systematic review of literature on credit card cyber fraud detection using machine and deep learning

doi: 10.7717/peerj-cs.1278

Figure Lengend Snippet: Selected research articles.

Article Snippet: A157 , SMOTE MLP, KNN, SVM OSE, NN, GAN , Accuracy F1-score , The results point out that the model using stacking classifier which combines GAN-improved MLP with SVM and KNN. OSE is preferred because of its ability to harness the abilities of MLP which works better in finding hidden patterns. The accuracy of OSE is 99.8% , Real dataset/Europeans cardholders/Kaggle , Apply weighted voting and boosting algorithms.

Techniques: Selection, Comparison, Isolation, Plasmid Preparation, Sampling, Modification

Journal: PeerJ Computer Science

Article Title: A systematic review of literature on credit card cyber fraud detection using machine and deep learning

doi: 10.7717/peerj-cs.1278

Figure Lengend Snippet: Usage frequency of ML and DL techniques in credit card fraud.

Article Snippet: A157 , SMOTE MLP, KNN, SVM OSE, NN, GAN , Accuracy F1-score , The results point out that the model using stacking classifier which combines GAN-improved MLP with SVM and KNN. OSE is preferred because of its ability to harness the abilities of MLP which works better in finding hidden patterns. The accuracy of OSE is 99.8% , Real dataset/Europeans cardholders/Kaggle , Apply weighted voting and boosting algorithms.

Techniques: Plasmid Preparation, Isolation, Sampling

Journal: PeerJ Computer Science

Article Title: A systematic review of literature on credit card cyber fraud detection using machine and deep learning

doi: 10.7717/peerj-cs.1278

Figure Lengend Snippet: Comparisons of selected article on cyber fraud detection in credit card.

Article Snippet: A157 , SMOTE MLP, KNN, SVM OSE, NN, GAN , Accuracy F1-score , The results point out that the model using stacking classifier which combines GAN-improved MLP with SVM and KNN. OSE is preferred because of its ability to harness the abilities of MLP which works better in finding hidden patterns. The accuracy of OSE is 99.8% , Real dataset/Europeans cardholders/Kaggle , Apply weighted voting and boosting algorithms.

Techniques: Sampling, Isolation, Plasmid Preparation, Injection, Preserving, Selection, Produced, Construct, Comparison