Comparison of ML/DL Approaches for Detecting DDoS Attacks in SDN

Article Computer Science, Hardware & Architecture

Breast Cancer Diagnosis Using Multi-Stage Weight Adjustment In The MLP Neural Network

Amin Rezaeipanah et al.

Summary: Breast cancer is the most common type of cancer among women worldwide. Early detection and treatment are crucial for improving the survival rate. This paper proposes an automatic breast cancer diagnosis technique using a genetic algorithm to optimize the Multi Layer Perceptron neural network. The algorithm achieves high accuracy in classifying breast cancer and compares favorably with other methods in the literature.

COMPUTER JOURNAL (2022)

Add to Collection

Article Computer Science, Information Systems

MLCM: Multi-Label Confusion Matrix

Mohammadreza Heydarian et al.

Summary: In multi-label classification tasks, traditional confusion matrix is not applicable for performance assessment. Current assessment techniques calculate performance averages for evaluation, but suffer from ambiguity. To address this, we propose a method of creating multi-label confusion matrix based on problem categories and demonstrate its effectiveness through experiments.

IEEE ACCESS (2022)

Add to Collection

Article Multidisciplinary Sciences

Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction

Shahadat Uddin et al.

Summary: This paper studies different variants of the k-nearest neighbour (KNN) algorithm and compares their performance in disease prediction. By implementing and experimenting on eight datasets, the study found that accuracy values ranged from 64.22% to 83.62%, with Hassanaat KNN showing the highest accuracy. The study also proposes a relative performance index based on accuracy, precision, and recall measures, identifying Hassanaat KNN as the best performing variant.

SCIENTIFIC REPORTS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep reinforcement learning with the confusion-matrix-based dynamic reward function for customer credit scoring

Yadong Wang et al.

Summary: The study introduces a deep Q-network model with a confusion-matrix-based dynamic reward function, which is proven to effectively improve customer credit scoring performance, accelerate model convergence, and enhance stability.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

Add to Collection

Review Medicine, General & Internal

Convolutional Neural Network Techniques for Brain Tumor Classification (from 2015 to 2022): Review, Challenges, and Future Perspectives

Yuting Xie et al.

Summary: This article provides a comprehensive review of studies using CNN architectures to classify brain tumors. The study found that performance varied widely depending on the classification problem and network choice. Due to inconsistencies in validation methods, performance metrics, and training data reporting, there is currently no clear best method choice. Few studies have focused on clinical usability.

DIAGNOSTICS (2022)

Add to Collection

Article Computer Science, Information Systems