Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: F1-score

Sortuj według:

Ogranicz wyniki do:

A new approach for diabetes risk detection using quadratic interpolation flower pollination neural network

Polly Yulianto Triwahyuadi, Fanggidae Adriana, Ledoh Juan Rizky Mannuel, Pah Clarissa Elfira Amos, Djahi Bertha S., Tupen Kisan Emiliano Rape

Applied Computer Science

2025

Vol. 21, no. 2

63--81

This study aims to evaluate and compare five algorithms in diabetes detection, namely Flower Pollination Neural Network (FPNN), Particle Swarm Optimization Neural Network (PSONN), Bat Artificial Neural Network (BANN), Stochastic Gradient Descent (SGD), and Quadratic Interpolation Flower Pollination Neural Network (QIFPNN). These algorithms were tested on a diabetes risk dataset divided into training, validation, and testing subsets. The evaluation was based on three main aspects: accuracy, F1 score, and training time. Experimental results showed that QIFPNN outperformed others with an average accuracy of 97.90% and an F1 score of 98.30%, although it required the longest training time (4107.89 seconds). FPNN and BANN achieved competitive accuracy (97.34% and 97.43%) and F1 scores (97.84% and 97.91%), while SGD offered a favorable trade-off with accuracy of 96.87%, F1 score of 97.42%, and the shortest training time (584.50 seconds). PSONN performed less well with an average accuracy of 89.26% and an F1 score of 91.45%. These results indicate that QIFPNN can be relied upon as an effective diabetes risk detection model with superior predictive performance. Although the training time of QIFPNN is longer due to its sophisticated optimization process, this is only a concern during model development, as the final trained model can be efficiently used for real-time prediction in practical applications.

An Ensemble Transfer Learning Model for Brain Tumors Classification using Convolutional Neural Networks

Sterniczuk Bartosz Piotr, Charytanowicz Małgorzata

Advances in Science and Technology. Research Journal

2024

Vol. 18, no. 8

204--216

Convolutional neural networks (CNNs) are a specialized class of deep neural networks. In the present era, these have emerged as highly effective tools for a variety of computer vision tasks. Nonetheless, for classification tasks, the application of a single CNN model is often not sufficient to achieve high precision and robustness. Ensemble learning is a machine learning technique that can improve classification performance through combining multiple models into one. With this method, individual models exchange each other's best performance for each class, resulting in improved overall accuracy. In this work, we studied the performance of CNN models for brain tumor classification. As an outcome, we propose a novel ensemble CNN model for this purpose. We utilized the dataset comes from Nanfang Hospital, which include 3064 MRI images categorized into three types of brain tumor (glioma, meningioma and pituitary). First, we assessed well-known CNN models for their ability to classify brain tumors. Next, we tested several ensemble transfer learning models and created one that utilizes the strengths of the most efficient CNN models. The comparative analysis of model performance demonstrated that the examined ensemble CNN models outperformed all single models. Moreover, regarding evaluation metrics, the proposed model achieved global accuracy of 94% and the highest precision and recall, the F1 score of being 94%. Experimental results revealed that model architecture and ensemble methods have a significant impact on brain tumor classification performance.

Phonetic Segmentation using a Wavelet-based Speech Cepstral Features and Sparse Representation Classifier

Al-Hassani Ihsan, Al-Dakkak Oumayma, Assami Abdlnaser

Journal of Telecommunications and Information Technology

2021

nr 4

12--22

Speech segmentation is the process of dividing speech signal into distinct acoustic blocks that could be words, syllables or phonemes. Phonetic segmentation is about finding the exact boundaries for the different phonemes that composes a specific speech signal. This problem is crucial for many applications, i.e. automatic speech recognition (ASR). In this paper we propose a new model-based text independent phonetic segmentation method based on wavelet packet speech parametrization features and using the sparse representation classifier (SRC). Experiments were performed on two datasets, the first is an English one derived from TIMIT corpus, while the second is an Arabic one derived from the Arabic speech corpus. Results showed that the proposed wavelet packet decomposition features outperform the MFCC features in speech segmentation task, in terms of both F1-score and R-measure on both datasets. Results also indicate that the SRC gives higher hit rate than the famous k-Nearest Neighbors (k-NN) classifier on TIMIT dataset.