Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : knowledge engineering and data science

Backpropagation Neural Network with Combination of Activation Functions for Inbound Traffic Prediction Purnawansyah, Purnawansyah; Haviluddin, Haviluddin; Darwis, Herdianti; Azis, Huzain; Salim, Yulita
Knowledge Engineering and Data Science
Publisher : citeus

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Predicting network traffic is crucial for preventing congestion and gaining superior quality of network services. This research aims to use backpropagation to predict the inbound level to understand and determine internet usage. The architecture consists of one input layer, two hidden layers, and one output layer. The study compares three activation functions: sigmoid, rectified linear unit (ReLU), and hyperbolic Tangent (tanh). Three learning rates: 0.1, 0.5, and 0.9 represent low, moderate, and high rates, respectively. Based on the result, in terms of a single form of activation function, although sigmoid provides the least RMSE and MSE values, the ReLu function is more superior in learning the high traffic pattern with a learning rate of 0.9. In addition, Re-LU is more powerful to be used in the first order in terms of combination. Hence, combining a high learning rate and pure ReLU, ReLu-sigmoid, or ReLu-Tanh is more suitable and recommended to predict upper traffic utilization.
Optimal Strategy for Handling Unbalanced Medical Datasets: Performance Evaluation of K-NN Algorithm Using Sampling Techniques Salim, Yulita; Utami, Aulia Putri; Manga, Abdul Rachman; Azis, Huzain; Admojo, Fadhila Tangguh
Knowledge Engineering and Data Science
Publisher : citeus

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study addresses the critical role of medical image classification in enhancing healthcare effectiveness and tackling the challenges of imbalanced medical datasets. It focuses on optimizing classification performance by integrating Canny edge detection for segmentation and Hu-moment feature extraction and applying oversampling and undersampling techniques. Five diverse medical datasets were utilized, covering Alzheimer’s and Parkinson’s diseases, COVID-19, brain tumours, and lung cancer. The K-Nearest Neighbors (K-NN) algorithm was implemented to enhance classification accuracy, aiming to develop a more robust framework for medical image analysis. The evaluation, conducted using cross-validation, demonstrated notable improvements in key metrics. Specifically, oversampling significantly enhanced lung cancer detection accuracy, while undersampling contributed to balanced performance gains in the COVID-19 class. Metrics, including accuracy, precision, recall, and F1-score, provided insights into the model’s effectiveness. These findings highlight the positive impact of data balancing techniques on K-NN performance in imbalanced medical image classification. Continued research is essential to refine these techniques and improve medical diagnostics.