The Bayesian CNN-LSTM classification model to predict and evaluate learner’s performance DOI Creative Commons

G. Sudhamathy,

N. Valliammal

International Journal of Applied Science and Engineering, Journal Year: 2023, Volume and Issue: 20(4), P. 1 - 9

Published: Jan. 1, 2023

Learning analytics (LA) is a research domain that leverages the analysis of data from learning process to gain deeper understanding and enhance outcomes. To classify learner performance, model has been proposed combines various deep techniques, including convolutional neural network (CNN), Long Short-Term Memory (LSTM), Bayesian models. The integration these approaches aims improve accuracy effectiveness performance classification. CNN used for capturing local information LSTM long-distance dependencies. effective classification learners' achieved by combining strengths LSTM, along with model. estimated using metrics like Accuracy, Precision, Recall F1-Score. showed improvements in F1-Score are 98.18%, 97.09%, 96.38% 95.35% respectively. compared another existing such as collaborative machine (ML) models terms metrics. method attained 98.18% which higher than other

Language: Английский

CoTCoNet: An optimized coupled transformer-convolutional network with an adaptive graph reconstruction for leukemia detection DOI
Chandravardhan Singh Raghaw, Arnav Sharma, Shubhi Bansal

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 179, P. 108821 - 108821

Published: July 6, 2024

Language: Английский

Citations

8
Advancing Early Leukemia Diagnostics: A Comprehensive Study Incorporating Image Processing and Transfer Learning DOI Creative Commons
Rezaul Haque,

Abdullah Al Sakib,

Md. Forhad Hossain

et al.

BioMedInformatics, Journal Year: 2024, Volume and Issue: 4(2), P. 966 - 991

Published: April 1, 2024

Disease recognition has been revolutionized by autonomous systems in the rapidly developing field of medical technology. A crucial aspect diagnosis involves visual assessment and enumeration white blood cells microscopic peripheral smears. This practice yields invaluable insights into a patient’s health, enabling identification conditions malignancies such as leukemia. Early leukemia subtypes is paramount for tailoring appropriate therapeutic interventions enhancing patient survival rates. However, traditional diagnostic techniques, which depend on assessment, are arbitrary, laborious, prone to errors. The advent ML technologies offers promising avenue more accurate efficient classification. In this study, we introduced novel approach classification integrating advanced image processing, diverse dataset utilization, sophisticated feature extraction coupled with development TL models. Focused improving accuracy previous studies, our utilized Kaggle datasets binary multiclass classifications. Extensive processing involved LoGMH method, complemented augmentation techniques. Feature employed DCNN, subsequent utilization extracted features train various Rigorous evaluation using metrics revealed Inception-ResNet’s superior performance, surpassing other models F1 scores 96.07% 95.89% classification, respectively. Our results notably surpass research, particularly cases involving higher number classes. These findings promise influence clinical decision support systems, guide future potentially revolutionize cancer diagnostics beyond leukemia, impacting broader imaging oncology domains.

Language: Английский

Citations

5
Solving time cost optimization problem with adaptive multi-verse optimizer DOI
Vu Hong Son Pham, Nghiep Trinh Nguyen Dang

OPSEARCH, Journal Year: 2024, Volume and Issue: 61(2), P. 662 - 679

Published: Jan. 24, 2024

Language: Английский

Citations

5
Fuzzy Attention-Based Deep Neural Networks for Acute Lymphoblastic Leukemia Diagnosis DOI
Tairan Zhang, Gang Xue

Applied Soft Computing, Journal Year: 2025, Volume and Issue: unknown, P. 112810 - 112810

Published: Jan. 1, 2025

Language: Английский

Citations

0
Transfer Learning for Cancer Diagnosis in Medical Images: A Compendious Study DOI Creative Commons
Navreet Kaur, Rahul Hans

International Journal of Computational Intelligence Systems, Journal Year: 2025, Volume and Issue: 18(1)

Published: March 20, 2025

Language: Английский

Citations

0
VNLU-Net: Visual Network with Lightweight Union-net for Acute Myeloid Leukemia Detection on Heterogeneous Dataset DOI

Rabul Saikia,

Roopam Deka,

Anupam Sarma

et al.

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 107, P. 107840 - 107840

Published: March 29, 2025

Language: Английский

Citations

0
Incremental Learning for Acute lymphoblastic Leukemia Classification Based on Hybrid Deep Learning Using Blood Smear Image DOI
Smritilekha Das,

K. Padmanaban

Computational Biology and Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 108456 - 108456

Published: April 1, 2025

Language: Английский

Citations

0
Computational insights into human UCP1 activation by wide virtual screening as new anti-obesity: a study utilizing molecular docking and molecular dynamics simulations DOI

Esmail Karami,

Fatemeh Rostamkhani, Mohammad Reza Abdollahi

et al.

Network Modeling Analysis in Health Informatics and Bioinformatics, Journal Year: 2025, Volume and Issue: 14(1)

Published: May 14, 2025

Language: Английский

Citations

0
A hybrid detection model for acute lymphocytic leukemia using support vector machine and particle swarm optimization (SVM-PSO) DOI Creative Commons

Lama K. Alsaykhan,

Mashael Maashi

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 8, 2024

Leukemia, a hematological disease affecting the bone marrow and white blood cells (WBCs), ranks among top ten causes of mortality worldwide. Delays in decision-making often hinder timely application suitable medical treatments. Acute lymphoblastic leukemia (ALL) is one primary forms, constituting approximately 25% childhood cancer cases. However, automated ALL diagnosis challenging. Recently, machine learning (ML) has emerged as an important tool for building detection models. In this study, we present hybrid model that improves accuracy process by combining support vector (SVM) particle swarm optimization (PSO) approaches to automatically identify ALL. We use SVM represent two-dimensional image complete classification process. PSO employed enhance performance model, reducing error rates enhancing result accuracy. The input images are obtained from two public datasets (ALL-IDB1 ALL-IDB2), online utilized training testing proposed model. results indicate our SVM-PSO high accuracy, outperforming stand-alone algorithms demonstrating superior performance, enhanced confusion matrix, higher rate. This advancement holds promise quality technical software field using learning.

Language: Английский

Citations

3
An AI-based automatic leukemia classification system utilizing dimensional Archimedes optimization DOI Creative Commons

Warda M. Shaban

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 16, 2025

Leukemia is a common type of blood cancer marked by the abnormal and uncontrolled proliferation expansion white cells. This anomaly impacts bone marrow, diminishing marrow's capacity to generate platelets red Abnormal cells in bloodstream harm various organs, such as kidneys, liver, spleen. Detection classification infected patients at an early stage can save their lives. In this paper, new Artificial Intelligence (AI) system proposed. The proposed called Classification System (LCS). LCS composed five stages, which are; (i) Image Processing Stage (IPS), (ii) Segmentation (ISS), (iii) Feature Extraction (FES), (iv) Selection (FSS), (v) (CS). During IPS, input images are preprocessed through several processes: resizing, enhancement, filtering. Next, segmented ISS. Then, two types features, texture morphological extracted. We feed these extracted features FSS, uses method select most important effective features. Dimensional Archimedes Optimization Algorithm (DAOA). DAOA based on (AOA) Learning Strategy (DLS). Actually, DLS transmits valuable information about ideal position population every generation personal best each individual particle. improves both precision efficiency convergence while reducing likelihood "two steps forward, one step back" phenomenon. problem offers more precise solution. Finally, selected fed model. Experimental results show that outperforms others.

Language: Английский

Citations

0