Dual Multi Scale Attention Network Optimized With Archerfish Hunting Optimization Algorithm for Diabetics Prediction

Microscopy Research and Technique, Год журнала: 2024, Номер unknown

Опубликована: Дек. 2, 2024

ABSTRACT Diabetes is a chronic disease that occurs when the body cannot regulate blood sugar levels. Nowadays, screening tests for diabetes are developed using multivariate regression methods. An increasing amount of data automatically collected to provide an opportunity creating challenging and accurate prediction modes updated constantly with help machine learning techniques. In this manuscript, Dual Multi Scale Attention Network optimized Archerfish Hunting Optimization Algorithm proposed Prediction (DMSAN‐AHO‐DP). Here, gathered through PIMA Indian Dataset (PIDD). The fed towards preprocessing remove noise input improves quality by Contrast Limited Adaptive Histogram Equalization Filtering (CLAHEF) method. Then preprocessed Multi‐Level Haar Wavelet Features Fusion (MHWFFN) based feature extraction. extracted supplied (DMSAN) diabetic or non‐diabetic classification. hyper parameter tuned (AHO) algorithm, which classifies accurately. DMSAN‐AHO‐DP technique implemented in Python. efficacy approach examined some metrics, like Accuracy, F‐scores, Sensitivity, Specificity, Precision, Recall, Computational time. achieves 23.52%, 36.12%, 31.12% higher accuracy 16.05%, 21.14%, 31.02% lesser error rate compared existing models: Enhanced Deep Neural Model (EDNN‐DP), Learning (ANN‐DP), Support Vector Machine strategies (SVM‐DNN‐DP).

Язык: Английский

Disease Diagnosis Using Machine Learning on Electronic Health Records

2022 International Conference on Communication, Computing and Internet of Things (IC3IoT), Год журнала: 2024, Номер unknown, С. 1 - 6

Опубликована: Апрель 17, 2024

In healthcare, disease diagnosis is essential because it allows for timely and accurate treatment decisions. Machine learning techniques have emerged as promising tools due to the increasing amount of electronic health records (EHRs). This paper presents a comprehensive study on using machine algorithms applied addresses need efficient, accurate, personalized prediction. The research focuses leveraging patient data, including medical history, laboratory results, clinical notes, develop predictive models identification. A diverse dataset anonymized Electronic Health Records utilized experimentation evaluation. range algorithms, such random forests, KNN, naïve bayes, decision trees, support vector machines are implemented evaluated based their interpretability, computational efficiency, diagnostic accuracy. To improve model performance, specific feature selection data preprocessing also researched. results show that more efficient than conventional when comes diagnosing diseases.

Язык: Английский

Accurate Segmentation and Classification of Brain Tumor Using Deep Learning Approaches

Опубликована: Июль 24, 2024

Язык: Английский