AutYOLO-ATT: an attention-based YOLOv8 algorithm for early autism diagnosis through facial expression recognition

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: 36(27), P. 17199 - 17219

Published: June 6, 2024

Abstract Autism Spectrum Disorder (ASD) is a developmental condition resulting from abnormalities in brain structure and function, which can manifest as communication social interaction difficulties. Conventional methods for diagnosing ASD may not be effective the early stages of disorder. Hence, diagnosis crucial to improving patient's overall health well-being. One alternative method autism facial expression recognition since autistic children typically exhibit distinct expressions that aid distinguishing them other children. This paper provides deep convolutional neural network (DCNN)-based real-time emotion system kids. The proposed designed identify six emotions, including surprise, delight, sadness, fear, joy, natural, assist medical professionals families recognizing intervention. In this study, an attention-based YOLOv8 (AutYOLO-ATT) algorithm proposed, enhances model's performance by integrating attention mechanism. outperforms all classifiers metrics, achieving precision 93.97%, recall 97.5%, F1-score 92.99%, accuracy 97.2%. These results highlight potential real-world applications, particularly fields where high essential.

Language: Английский

---

Enhanced handwriting recognition through hybrid UNet-based architecture with global classical features

Journal of Ambient Intelligence and Humanized Computing, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 18, 2025

Language: Английский

---

Enhanced COVID-19 Optimization Algorithm for Solving Multi-Objective Optimal Power Flow Problems with Uncertain Renewable Energy Sources: A Case Study of the Iraqi High-Voltage Grid

Energies, Journal Year: 2025, Volume and Issue: 18(3), P. 478 - 478

Published: Jan. 22, 2025

The optimal power flow (OPF) problem is a critical component in the design and operation of transmission systems. Various optimization algorithms have been developed to address this issue. This paper expands use coronavirus disease algorithm (COVIDOA) solve multi-objective OPF (MO-OPF), incorporating renewable energy sources as distributed generation (DG) across multiple scenarios. main objective minimize fuel costs, emissions, voltage deviations, losses. Due its non-convex nature computational complexity, poses significant challenges. While COVIDOA has utilized engineering problems, it faces difficulties with non-linear issues. introduces an enhanced version, COVID-19 (ENHCOVIDOA), designed improve performance original method. effectiveness proposed validated through testing on IEEE 30-bus, 57-bus, 118-bus systems, well real-world 28-bus system representing Iraq’s standard Iraq super grid high (SISGHV 28-bus). two-point estimation method (TPEM) also applied manage uncertainties some cases, leading cost reductions annual savings ($70,909.344, $817,676.64, $5,608,782.144) for reality respectively. Thirteen different cases were analyzed, results demonstrate that ENHCOVIDOA notably more efficient effective than other literature.

Language: Английский

---

Advancing Engineering Solutions with Protozoa-Based Differential Evolution: A Hybrid Optimization Approach

Automation, Journal Year: 2025, Volume and Issue: 6(2), P. 13 - 13

Published: March 28, 2025

This paper presents a novel Hybrid Artificial Protozoa Optimizer with Differential Evolution (HPDE), combining the biologically inspired principles of (APO) powerful optimization strategies (DE) to address complex and engineering design challenges. The HPDE algorithm is designed balance exploration exploitation features, utilizing innovative features such as autotrophic heterotrophic foraging behaviors, dormancy, reproduction processes alongside DE strategy. performance was evaluated on CEC2014 benchmark functions, it compared against two sets state-of-the-art optimizers comprising 23 different algorithms. results demonstrate HPDE’s good performance, outperforming competitors in 24 functions out 30 from first set second set. Additionally, has been successfully applied range problems, including robot gripper optimization, welded beam pressure vessel spring speed reducer cantilever three-bar truss optimization. consistently showcase solving these problems when competing

Language: Английский

---

Integration of machine learning and CFD for modeling mass transfer in water treatment using membrane separation process

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

Published: Oct. 14, 2024

This study aims to assess the efficacy of machine learning models in predicting solute concentration (C) distribution a membrane separation process, using input parameters which are spatial coordinates. Computational fluid dynamics (CFD) was employed with for simulation process. The evaluated include Kernel Ridge Regression (KRR), Radius nearest neighbor regression (RNN), K-nearest neighbors (KNN), LASSO, and Multi-Layer Perceptron (MLP). Additionally, Harris Hawks Optimization (HHO) utilized fine-tune hyperparameters these models. Leading way is MLP model, achieves remarkable test R

Language: Английский

---

Enhancement Method Based on Multi-Strategy Improved Pelican Optimization Algorithm and Application to Low-Illumination Forest Canopy Images

Forests, Journal Year: 2024, Volume and Issue: 15(10), P. 1783 - 1783

Published: Oct. 11, 2024

Enhancement is a crucial step in the field of image processing, as it significantly improves analysis and understanding. One most commonly used methods for contrast enhancement incomplete beta function (IBF). However, key challenge lies determining optimal parameters IBF. This paper introduces multi-strategy improved pelican optimization algorithm (MIPOA) to address low-illumination color problem. The MIPOA utilizes nonlinear decreasing coefficient boost exploration ability convergence speed, whereas Hardy–Weinberg principle compensates unsound exploitation mechanism. Additionally, diversity variation operation escape local solutions. performance proposed was evaluated using benchmark found outperform five variant algorithms extensive comparisons. To further harness potential algorithm, authors propose low-light forest canopy method based on algorithm. searches IBF, leading fast image. segmented gamma correction designed enhance brightness images. In demonstrates superior compared other intelligent feature similarity index (FSIM), entropy, improvement (CII) 75%, 58.33%, respectively. MIPOA-based achieves moderate pixel mean surpasses conventional with an average gradient 91.67%. experimental results indicate that effectively addresses limitations low accuracy IBF parameters, provides more efficacious approach enhancing

Language: Английский

---

Optimizing Wind Power Forecasting with RNN-LSTM Models through Grid Search Cross-validation

Sustainable Computing Informatics and Systems, Journal Year: 2024, Volume and Issue: unknown, P. 101054 - 101054

Published: Nov. 1, 2024

Language: Английский

---

Solving the maximum cut problem using Harris Hawk Optimization algorithm

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(12), P. e0315842 - e0315842

Published: Dec. 30, 2024

The objective of the max-cut problem is to cut any graph in such a way that total weight edges are off maximum both subsets vertices divided due edges. Although it an elementary partitioning problem, one most challenging combinatorial optimization-based problems, and tons application areas make this highly admissible. Due its admissibility, solved using Harris Hawk Optimization algorithm (HHO). Though HHO effectively some engineering optimization sensitive parameter settings may converge slowly, potentially getting trapped local optima. Thus, additional operators used solve problem. Crossover refinement modify fitness hawk they can provide precise results. A mutation mechanism along with adjustment operator has improvised outcome obtained from updated hawk. To accept potential result, acceptance criterion been used, then repair applied proposed approach. system provided comparatively better outcomes on G-set dataset than other state-of-the-art algorithms. It 533 cuts more discrete cuckoo search 9 instances, 1036 PSO-EDA 14 1021 TSHEA instances. But for four lower TSHEA. Besides, statistical significance also tested Wilcoxon signed rank test proof superior performance method. In terms solution quality, MC-HHO produce quite competitive when compared related

Language: Английский

---

Information interconnection Harris hawks hybrid optimization algorithm

2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Journal Year: 2024, Volume and Issue: unknown, P. 3838 - 3841

Published: Dec. 3, 2024

Language: Английский

---