Cardiovascular Classification Using Efficient Net on Electrocardiogram Images DOI Open Access

N. Jothiaruna,

Bandla Pavan Babu, Nagoor Basha Shaik

и другие.

Engineering Journal, Год журнала: 2024, Номер 28(12), С. 67 - 78

Опубликована: Дек. 1, 2024

Cardiovascular disease ranks among the top causes of mortality, frequently caused by sudden obstructions within blood vessels.Timely identification and intervention are essential for minimizing impact disease.This research employs image augmentation techniques to correct class imbalance in an ECG dataset divided into five categories: Normal, Abnormal Heartbeat, Myocardial Infarction, Previous History COVID-19.The balanced includes 6,322 images.To improve classification accuracy cardiovascular diseases, three pre-trained models visual Geometric Group, Residual, Dense, Efficient Network with Version 2, were trained on dataset.Critical hyper parameters fine-tuned, yielding optimal performance a learning rate set at 0.00001, dropout 0.3, utilizing Adam optimizer.EfficientNet-V2 outperformed other models, reaching level accuracies 96.22%, precision 96.34%, recall 96.31%, 95.89%, 94.75%, F1-Score 96.33%, thus exceeding Densenet 161, 201, ResNet50 VGG16.

Язык: Английский

Impact of Aggregate Characteristics on Frictional Performance of Asphalt-Based High Friction Surface Treatments DOI Creative Commons
Alireza Roshan, Magdy Abdelrahman

CivilEng, Год журнала: 2025, Номер 6(1), С. 4 - 4

Опубликована: Янв. 14, 2025

High Friction Surface Treatments (HFST) are recognized for their effectiveness in enhancing skid resistance and reducing road accidents. While Epoxy-based HFSTs widely applied, they present limitations such as compatibility issues with existing pavements, high installation removal costs, durability concerns tied to substrate quality. As an alternative traditional HFSTs, this study investigated the effects of aggregate gradation designated by agencies on performance asphalt-based HFST. Various types were assessed evaluate friction impact polishing cycles non-Epoxy It was found that adjustments size may be necessary when transitioning given different nature asphalt more temperature susceptible compared Epoxy. binder grades considered study. A series tests, including British Pendulum Test (BPT), Dynamic Tester (DFT), Circular Track Meter (CTM), Micro-Deval (MD), Aggregate Imaging Measurement System (AIMS), conducted measure Coefficient (COF), Mean Profile Depth (MPD), texture, angularity before after cycles. The results showed COF slabs decreased significantly than increased HFST medium gradations. However, coarse gradation, using matched or even surpassed Epoxy polishing. Notably, PG88-16 Calcined Bauxite (CB) had smallest reduction 140K cycles, only a 19% decrease 23%

Язык: Английский

Процитировано

1

Improving Aggregate Abrasion Resistance Prediction via Micro-Deval Test Using Ensemble Machine Learning Techniques DOI Open Access
Alireza Roshan, Magdy Abdelrahman

Engineering Journal, Год журнала: 2024, Номер 28(3), С. 15 - 24

Опубликована: Март 1, 2024

Aggregate is the most extracted material from world's mines and widely used in civil construction projects.The Micro-Deval abrasion test (MD) one of important tests that provides characteristics crushed aggregates show their resistance against mechanical abrasive factors such as repeated impact loading.The various on properties has led researchers to seek correlations, often focusing limited data samples, leading reduced accuracy.This study employs machine learning (ML) methods predict MD values, considering diverse aggregate properties.Various ensemble ML were applied, revealing exceptional performance stacking model, which achieved an R 2 score 0.95 predicting resistance.The feature importance analysis highlights influence Magnesium Sulfate Soundness (MSS), Water Absorption (ABS), Los Angeles Abrasion (LAA) suggesting use multiple could yield a more dependable assessment durability.

Язык: Английский

Процитировано

5

Evaluating Friction Characteristics of High Friction Surface Treatment Application Under Varied Polishing and Slippery Conditions DOI
Alireza Roshan, Magdy Abdelrahman

Transportation Research Record Journal of the Transportation Research Board, Год журнала: 2024, Номер unknown

Опубликована: Июль 24, 2024

The frictional attributes of high friction surface treatment (HFST) play a crucial role in ensuring optimal traffic safety, particularly wet weather conditions. Friction consists two important components: adhesion and hysteresis. This research focuses on evaluating these essential factors HFST using different aggregates distinct sizes by considering various abrasion polishing methods. To isolate components for assessment, testing was carried out under slippery conditions, including dry, with water, water + soap. inclusion liquid hand soap the test procedure effectively minimized or even eliminated component’s influence, making it possible to primarily focus hysteresis component. Consequently, British Pendulum Number (BPN) measured this predominantly reflected hysteresis-related friction. analysis variance results emphasized substantial impact methods BPN values obtained Notably, Micro-Deval Abrasion (MDA) 105, 180, 240 min exhibited most pronounced influence variation higher F-value MDA 105 indicated that specific time exerted more significant than other factors. Furthermore, utilization Aggregate Image Measurement System yielded valuable insights into micro-texture aggregates. It revealed calcined bauxite size is anticipated provide rougher morphology (texture) pavement compared sources study, thereby contributing findings from study contribute deeper understanding characteristics scenarios, providing optimizing applications enhance road safety skid resistance.

Язык: Английский

Процитировано

3

Influence of Aggregate Properties on Skid Resistance of Pavement Surface Treatments DOI Open Access
Alireza Roshan, Magdy Abdelrahman

Coatings, Год журнала: 2024, Номер 14(8), С. 1037 - 1037

Опубликована: Авг. 15, 2024

Skid resistance is a critical aspect for traffic safety since it significantly influences vehicle control and minimizes the distance required emergency braking. The surface characteristics of pavements play pivotal role in determining skid resistance. To achieve optimal performance, pavement must sustain specific level friction. Thus, advantageous to apply treatments areas that require enhanced This study investigate impact factors such as aggregate source, size, morphological properties, abrasion levels on frictional high-friction treatment (HFST). A complete investigation was conducted HFST samples by analyzing morphology using Aggregate Image Measurement System performing Micro-Deval testing. evaluated with British Pendulum Tester (BPT). findings revealed different aggregates sizes exhibited varying behaviors post-polishing. Notably, fine-sized demonstrated higher pendulum number (BPN) values, which indicate superior performance. Models predicted numbers based average texture angularity indices initially balanced both properties before polishing. However, after polishing, emerged primary determinant resistance, overshadowed angularity’s impact.

Язык: Английский

Процитировано

3

Comparative Analysis of Lab-Data-Driven Models for International Friction Index Prediction in High Friction Surface Treatment (HFST) DOI Creative Commons
Alireza Roshan, Magdy Abdelrahman

Applied Sciences, Год журнала: 2025, Номер 15(11), С. 6249 - 6249

Опубликована: Июнь 2, 2025

High Friction Surface Treatments (HFSTs) are often utilized as a spot treatment to enhance selected areas with high friction demand rather than extended pavement sections and helpful in increasing skid resistance minimizing road accidents. A laboratory design approach was created assess the fundamental ideas behind international index (IFI) concept update present IFI model parameters for HFST applications based on test findings gain better understanding of performance. Two aggregate types three sizes were tested under controlled polishing cycles. texture measured using Dynamic Tester (DFT) Circular Track Meter (CTM). Three physics-informed empirical models, including logarithmic, power law, polynomial represent effects, nonlinear scaling, complex interactions between COF MPD. Results show that performance varies type, gradation, polishing, traditional may not fully capture behavior. Model refinements suggested surface characteristics lowest testing Root Mean Squared Error (RMSE) (0.049) highest predictive accuracy R2 (0.821); logarithmic found be best. Sensitivity analysis revealed predictions more sensitive (ΔIFI: 14.3–17.7%) MPD 1.5–6.0%) across all models. These results demonstrate how these models can improve assessment while providing useful information enhancing safety. This process is tool evaluating lab setting since it calculates lab.

Язык: Английский

Процитировано

0

Cardiovascular Classification Using Efficient Net on Electrocardiogram Images DOI Open Access

N. Jothiaruna,

Bandla Pavan Babu, Nagoor Basha Shaik

и другие.

Engineering Journal, Год журнала: 2024, Номер 28(12), С. 67 - 78

Опубликована: Дек. 1, 2024

Cardiovascular disease ranks among the top causes of mortality, frequently caused by sudden obstructions within blood vessels.Timely identification and intervention are essential for minimizing impact disease.This research employs image augmentation techniques to correct class imbalance in an ECG dataset divided into five categories: Normal, Abnormal Heartbeat, Myocardial Infarction, Previous History COVID-19.The balanced includes 6,322 images.To improve classification accuracy cardiovascular diseases, three pre-trained models visual Geometric Group, Residual, Dense, Efficient Network with Version 2, were trained on dataset.Critical hyper parameters fine-tuned, yielding optimal performance a learning rate set at 0.00001, dropout 0.3, utilizing Adam optimizer.EfficientNet-V2 outperformed other models, reaching level accuracies 96.22%, precision 96.34%, recall 96.31%, 95.89%, 94.75%, F1-Score 96.33%, thus exceeding Densenet 161, 201, ResNet50 VGG16.

Язык: Английский

Процитировано

0