Photovoltaic Farm Production Forecasting: Modified Metaheuristic Optimized Long Short-Term Memory Based Networks Approach

IEEE Access, Journal Year: 2025, Volume and Issue: 13, P. 25198 - 25222

Published: Jan. 1, 2025

Language: Английский

---

Artificial Neural Networks with Soft Attention: Natural Language Processing for Phishing Email Detection Optimized with Modified Metaheuristics

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 421 - 438

Published: Jan. 1, 2025

Language: Английский

---

Computer-Vision Unmanned Aerial Vehicle Detection System Using YOLOv8 Architectures

International Journal of Robotics and Automation Technology, Journal Year: 2024, Volume and Issue: 11, P. 1 - 12

Published: May 22, 2024

Abstract: This work aims to test the performance of you only look once version 8 (YOLOv8) model for problem drone detection. Drones are very slightly regulated and standards need be established. With a robust system detecting drones possibilities regulating their usage becoming realistic. Five different sizes were tested determine best architecture size this problem. The results indicate high across all models that each is used specific case. Smaller suited lightweight approaches where some false identification tolerable, while largest with stationary systems require precision.

Language: Английский

---

Sentiment classification for insider threat identification using metaheuristic optimized machine learning classifiers

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

Published: Oct. 28, 2024

This study examines the formidable and complex challenge of insider threats to organizational security, addressing risks such as ransomware incidents, data breaches, extortion attempts. The research involves six experiments utilizing email, HTTP, file content data. To combat threats, emerging Natural Language Processing techniques are employed in conjunction with powerful Machine Learning classifiers, specifically XGBoost AdaBoost. focus is on recognizing sentiment context malicious actions, which considered less prone change compared commonly tracked metrics like location time access. enhance detection, a term frequency-inverse document frequency-based approach introduced, providing more robust, adaptable, maintainable method. Moreover, acknowledges significant impact hyperparameter selection classifier performance employs various contemporary optimizers, including modified version red fox optimization algorithm. proposed undergoes testing three simulated scenarios using public dataset, showcasing commendable outcomes.

Language: Английский

---

Enhanced crayfish optimization algorithm: Orthogonal refracted opposition-based learning for robotic arm trajectory planning

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(2), P. e0318203 - e0318203

Published: Feb. 5, 2025

In high-dimensional scenarios, trajectory planning is a challenging and computationally complex optimization task that requires finding the optimal within domain. Metaheuristic (MH) algorithms provide practical approach to solving this problem. The Crayfish Optimization Algorithm (COA) an MH algorithm inspired by biological behavior of crayfish. However, COA has limitations, including insufficient global search capability tendency converge local optima. To address these challenges, Enhanced (ECOA) proposed for robotic arm planning. ECOA incorporates multiple novel strategies, using tent chaotic map population initialization enhance diversity replacing traditional step size adjustment with nonlinear perturbation factor improve capability. Furthermore, orthogonal refracted opposition-based learning strategy enhances solution quality efficiency leveraging dominant dimensional information. Additionally, performance comparisons eight advanced on CEC2017 test set (30-dimensional, 50-dimensional, 100-dimensional) are conducted, ECOA’s effectiveness validated through Wilcoxon rank-sum Friedman mean rank tests. experiments, demonstrated superior performance, reducing costs 15% compared best competing 10% over original COA, significantly lower variability. This demonstrates improved quality, robustness, convergence stability. study successfully introduces strategies improvement, as well verification in path results confirm potential challenges various engineering applications.

Language: Английский

---

Construction of a prediction and visualization system for cognitive impairment in elderly COPD patients based on self-assigning feature weights and residual evolution model

Frontiers in Artificial Intelligence, Journal Year: 2025, Volume and Issue: 8

Published: Feb. 7, 2025

Assessing cognitive function in patients with chronic obstructive pulmonary disease (COPD) is crucial for ensuring treatment efficacy and avoiding moderate impairment (MCI) or dementia. We aimed to build better machine learning models provide useful tools guidance assistance COPD patients' care. A total of 863 from a local general hospital were collected screened, they separated into two groups: (356 patients) cognitively normal (507 patients). The Montreal Cognitive Assessment (MoCA) was used test function. swarm intelligence optimization algorithm (SIOA) direct feature weighting hyperparameter optimization, which considered simultaneous activities. self-assigning weights residual evolution (SAFWRE) built on the concept linear nonlinear information fusion. best method SIOA circle search algorithm. On training set, SAFWRE's ROC-AUC 0.9727, its PR-AUC 0.9663; receiver operating characteristic-area under curve (ROC-AUC) 0.9243, precision recall-area (PR-AUC) 0.9059, performance much superior than that control technique. In terms external data, classification prediction various are comprehensively evaluated. SAFWRE has most excellent performance, 0.8865 pr-auc 0.8299. This work develops practical visualization system based these weight attributes strong application importance promotion value.

Language: Английский

---

IoT System Intrusion Detection with XGBoost Optimized by Modified Metaheuristics

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 345 - 359

Published: Jan. 1, 2025

Language: Английский

---

YOLOv8 Utilization in Occupational Health and Safety

Published: May 22, 2024

Language: Английский

---

Research on SAR image quality evaluation method based on improved harris hawk optimization algorithm and XGBoost

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

Published: Nov. 17, 2024

Synthetic aperture radar (SAR) is crucial for military reconnaissance and remote sensing, but image quality can be affected by various factors, impacting target detection performance. Thus, pre-evaluation of SAR essential to filter out poor-quality images, optimize resource allocation, enhance accuracy efficiency. This paper proposes a comprehensive evaluation method combining objective subjective approaches. Specifically, the processes encompassing generation series disturbed images on ship dataset (SSDD), calculation indicators those assignment label each through evaluation. Based constructed above methods, IHHO-XGBoost model was developed. uses an improved harris hawk optimization (IHHO) algorithm extreme gradient boosting (XGBoost) hyperparameters. The IHHO effectively alleviates problem getting trapped in local optima improving escape energy strategy integrating average difference evolution mechanism while maintaining diversity population, showing significant advantages over traditional HHO algorithm. Comparative experiments demonstrate model's superiority study validates scientificity practicability proposed method, offering new tools research.

Language: Английский

---

Optimizing Lightweight Recurrent Networks for Solar Forecasting in TinyML: Modified Metaheuristics and Legal Implications

Energies, Journal Year: 2024, Volume and Issue: 18(1), P. 105 - 105

Published: Dec. 30, 2024

The limited nature of fossil resources and their unsustainable characteristics have led to increased interest in renewable sources. However, significant work remains be carried out fully integrate these systems into existing power distribution networks, both technically legally. While reliability holds great potential for improving energy production sustainability, the dependence solar plants on weather conditions can complicate realization consistent without incurring high storage costs. Therefore, accurate prediction is vital efficient grid management trading. Machine learning models emerged as a prospective solution, they are able handle immense datasets model complex patterns within data. This explores use metaheuristic optimization techniques optimizing recurrent forecasting predict from substations. Additionally, modified optimizer introduced meet demanding requirements optimization. Simulations, along with rigid comparative analysis other contemporary metaheuristics, also conducted real-world dataset, best achieving mean squared error (MSE) just 0.000935 volts 0.007011 two datasets, suggesting viability usage. best-performing further examined applicability embedded tiny machine (TinyML) applications. discussion provided this manuscript includes legal framework forecasting, its integration, policy implications establishing decentralized cost-effective system.

Language: Английский

---