Improvement of confusion matrix for Hand Vein Recognition Based On Deep- Learning multi-classifier Decisions

Nawwar, Nadia.M.; Kasban, H.; Salama, M.

doi:10.21608/ajnsa.2021.70450.1460

Cited by 4 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6-confusion matrix: The confusion matrix is a table that summarizes the performance of a classification model by representing the counts of true positive (TP), true negative (TN), false positive (FP), and false negative (FN) predictions. The confusion matrix provides valuable information about the performance of a classification model [36], allowing for the calculation of various evaluation metrics such as accuracy, precision, recall, and F1 score.…”

Section: Decision Fusion Using Majority Voting Algorithmmentioning

confidence: 99%

Liver cancer detection using Artificial Intelligence

Badrawy,

.T.Khalil,

.M.Amer

2024

Preprint

View full text Add to dashboard Cite

A noticeable increase in statistics of liver cancer in Egypt and all over the world. Therefore, using Artificial Intelligence (AI) to increase the detection accuracy and minimize human errors during manual classification of liver images. Where the manual classification of liver Computed Tomography (CT) scan images require a very great effort and time-consuming tasks. This study aims to improve a high-performance computer detection system. The proposed model used to detect liver tumor is based on Convolutional Neural Network (CNN) techniques and the machine learning techniques, which are of the most application of AI that used in biomedical image classification and recognition. The dataset used in this study is composed of 9255 CT scan images. The proposed model consists of three main steps. The first step aims to compare between three deep learning model which that Liver Tuned High-Resolution Network (LTHR-Net), Deep Residual Network (ResNet50) and Visual Geometry Group Network (VGG19-Net) to get the most suitable deep learning model that improve the system detection accuracy. The next step aims to apply three machine learning classifiers and compare their performance to increase the system detection accuracy. These classifiers are Logistic Regression (LR), Random Forest (RF) and Support Vector Machine (SVM). The final step improves the system detection accuracy by applying decision fusion techniques at the classifiers classification result using majority voting algorithm. The accuracy of the proposed model achieved 99.9% by using LTHR-Net as based model and applied majority voting algorithm on the classification output of the three machine learning classifiers.

show abstract

Section: Decision Fusion Using Majority Voting Algorithmmentioning

confidence: 99%