Toward intelligent food drying: Integrating artificial intelligence into drying systems DOI
Seyed-Hassan Miraei Ashtiani, Alex Martynenko

Drying Technology, Journal Year: 2024, Volume and Issue: 42(8), P. 1240 - 1269

Published: May 24, 2024

Artificial intelligence (AI) and its data-driven counterpart, machine learning (ML), are rapidly evolving disciplines with increasing applications in modeling, simulation, control, optimization within the drying industry. This paper presents a comprehensive overview of progress made ML from shallow to deep implications for food drying. Theoretical foundations, advantages, limitations various approaches employed this domain explored. Additionally, advancements models, particularly those enhanced by algorithms, reviewed. The review underscores role intelligent configuration which affects their accuracy ability solve problems high energy consumption, nutrient degradation, uneven Drawing upon research achievements, integrating AI models real-time measuring methods is discussed, enabling dynamic determination optimal conditions parameter adjustments. integration facilitates automated decision-making, reducing human errors enhancing operational efficiency Moreover, demonstrate proficiency predicting times analyzing usage patterns, thereby minimize resource consumption while preserving product quality. Finally, identifies current obstacles technology development proposes novel avenues sustainable technologies.

Language: Английский

Different applications of machine learning approaches in materials science and engineering: Comprehensive review DOI

Yan Cao,

Ali Taghvaie Nakhjiri, Mahdi Ghadiri

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 135, P. 108783 - 108783

Published: June 20, 2024

Language: Английский

Citations

16
Advancements in hydrogen production through the integration of renewable energy sources with AI techniques: A comprehensive literature review DOI
Mohammad Abdul Baseer, Prashant Kumar, Erick Giovani Sperandio Nascimento

et al.

Applied Energy, Journal Year: 2025, Volume and Issue: 383, P. 125354 - 125354

Published: Jan. 17, 2025

Language: Английский

Citations

3
Func-Bagging: An Ensemble Learning Strategy for Improving the Performance of Heterogeneous Anomaly Detection Models DOI Creative Commons
Ruinan Qiu, Yongfeng Yin, Qingran Su

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(2), P. 905 - 905

Published: Jan. 17, 2025

In the field of ensemble learning, bagging and stacking are two widely used strategies. Bagging enhances model robustness through repeated sampling weighted averaging homogeneous classifiers, while improves classification performance by integrating multiple models using meta-learning strategies, taking advantage diversity heterogeneous classifiers. However, fixed weight distribution strategy in traditional methods often has limitations when handling complex or imbalanced datasets. This paper combines concept classifier integration with bagging, proposing a new adaptive approach to enhance bagging’s settings. Specifically, we propose three generation functions “high at both ends, low middle” curve shapes demonstrate superiority this over on Additionally, design specialized neural network, training it adequately, validate rationality proposed strategy, further improving model’s robustness. The above collectively called func-bagging. Experimental results show that func-bagging an average 1.810% improvement extreme compared base classifier, is superior methods. It also better dataset adaptability interpretability than bagging. Therefore, particularly effective scenarios class imbalance applicable tasks classes, such as anomaly detection.

Language: Английский

Citations

3
Revolutionizing Prostate Cancer Therapy: Artificial intelligence – based Nanocarriers for Precision Diagnosis and Treatment DOI
Moein Shirzad,

Afsaneh Salahvarzi,

Sobia Razzaq

et al.

Critical Reviews in Oncology/Hematology, Journal Year: 2025, Volume and Issue: unknown, P. 104653 - 104653

Published: Feb. 1, 2025

Language: Английский

Citations

3
Ensemble Machine Learning approach for evaluating the material characterization of carbon nanotube-reinforced cementitious composites DOI Creative Commons
Faramarz Bagherzadeh, Torkan Shafighfard

Case Studies in Construction Materials, Journal Year: 2022, Volume and Issue: 17, P. e01537 - e01537

Published: Oct. 7, 2022

Time and cost-efficient techniques are essential to avoid extra conventional experimental studies with large data-set for material characterization of composite materials. This study is aimed at providing a correlation between the structural performance mechanical properties carbon nano-tubes reinforced cementitious composites through efficient predictive Machine Learning (ML) models. The Flexural (FS) Compressive (CS) Strength Carbon Nanotube (CNT)-reinforced were predicted based on data-rich framework provided in literature. Two different ensembled ML methods including Random Forest (RF) Gradient Boosting (GBM) implemented those data predicting CNT-reinforced cement-based composites. Data-set utilized training proposed models employing SciKit-Learn library Python, followed by hyper-parameter tuning k-fold cross-validation method obtaining an optimum model predict target values. It was shown that CS values more accurate than FS counterparts developed GBM has less sensitivity alteration test RF model. Finally, analysis conducted Sobol algorithm parameters highest contribution identified.

Language: Английский

Citations

46
Thermo-mechanical optimization of thermoelectric generators using deep learning artificial intelligence algorithms fed with verified finite element simulation data DOI
Chika Maduabuchi

Applied Energy, Journal Year: 2022, Volume and Issue: 315, P. 118943 - 118943

Published: April 4, 2022

Language: Английский

Citations

45
Control of DSTATCOM Using ANN-BP Algorithm for the Grid Connected Wind Energy System DOI Creative Commons
Md Mujahid Irfan,

Sushama Malaji,

Chandrashekhar Patsa

et al.

Energies, Journal Year: 2022, Volume and Issue: 15(19), P. 6988 - 6988

Published: Sept. 23, 2022

Green energy sources are implemented for the generation of power due to their substantial advantages. Wind is best among renewable options generation. Generally, wind system directly connected with network supplying power. In direct connection, there an issue managing quality (PQ) concerns such as voltage sag, swells, flickers, harmonics, etc. order enhance PQ in a conversion (WECS), peripheral compensation needed. this paper, we highlight novel control technique improve WECS by adopting Artificial Neural Network (ANN)-based Distribution Static Compensator (DSTATCOM). our proposed approach, online learning-based ANN Back Propagation (BP) model used generate gate pulses DSTATCOM, which mitigate harmonics at grid side. It modelled using MATLAB platform and total harmonic distortion (THD) compared without DSTATCOM. The source side decreased less than 5% within IEEE limits. results obtained reveal that ANN-BP superior nature.

Language: Английский

Citations

43
Topology Optimization for Electromagnetics: A Survey DOI Creative Commons
Francesco Lucchini, Riccardo Torchio, Vincenzo Cirimele

et al.

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 98593 - 98611

Published: Jan. 1, 2022

The development of technologies for the additive manufacturing, in particular metallic materials, is offering possibility producing parts with complex geometries. This opens up to using topological optimization methods design electromagnetic devices. Hence, a wide variety approaches, originally developed solid mechanics, have recently become attractive also field electromagnetics. general distinction between gradient-based and gradient-free drives structure paper, latter becoming particularly last years due concepts artificial neural networks. aim this paper twofold. On one hand, aims at summarizing describing state-of-art on topology techniques while other it showing how methodologies non-electromagnetic framework (e.g., mechanics field) can be applied Discussions comparisons are both supported by theoretical aspects numerical results.

Language: Английский

Citations

41
Revolutionizing Groundwater Management with Hybrid AI Models: A Practical Review DOI Open Access
Mojtaba Zaresefat, Reza Derakhshani

Water, Journal Year: 2023, Volume and Issue: 15(9), P. 1750 - 1750

Published: May 2, 2023

Developing precise soft computing methods for groundwater management, which includes quality and quantity, is crucial improving water resources planning management. In the past 20 years, significant progress has been made in management using hybrid machine learning (ML) models as artificial intelligence (AI). Although various review articles have reported advances this field, existing literature must cover ML. This article aims to understand current state-of-the-art ML used achievements domain. It most cited employed from 2009 2022. summarises reviewed papers, highlighting their strengths weaknesses, performance criteria employed, highly identified. worth noting that accuracy was significantly enhanced, resulting a substantial improvement demonstrating robust outcome. Additionally, outlines recommendations future research directions enhance of including prediction related knowledge.

Language: Английский

Citations

33
Maximum power point tracking for grid-connected photovoltaic system using Adaptive Fuzzy Logic Controller DOI
Majid Ali,

Mujtaba Ahmad,

Mohsin Ali Koondhar

et al.

Computers & Electrical Engineering, Journal Year: 2023, Volume and Issue: 110, P. 108879 - 108879

Published: Aug. 1, 2023

Language: Английский

Citations

32