Main challenges (generation and returned energy) in a deep intelligent analysis technique for renewable energy applications. DOI Creative Commons
Samaher Al-Janabi, Ghada S. Mohammed, Thekra Abbas

et al.

Iraqi Journal for Computer Science and Mathematics, Journal Year: 2023, Volume and Issue: unknown, P. 34 - 47

Published: June 11, 2023

In recent years, there has been an increasing demand for Renewable Energy (RE), which refers to energy generated from natural sources such as solar and wind power. Consequently, numerous scientific studies have conducted explore various approaches controlling this type of energy. This work aims highlight the main challenges associated with generation return RE by employing intelligent data analysis techniques, specifically deep learning. These are examined different perspectives, including pre-processing, methodology techniques used in learning, evaluation measures employed. Some research area is focused on predicting highest amount that can be at a particular time location, while others aim predict largest electrical returned electricity grid optimize use surplus resources maximize their benefits. efforts crucial ensure effective continuous operation grid. However, despite efficiency high accuracy these models, they hindered complex calculations require considerable produce desired outcomes. Additionally, employed evaluate models' performance, assessing completion rate, quality results, efficiency, error feasibility investing RE, network.

Language: Английский

Thermal deformation behavior investigation of Ti–10V–5Al-2.5fe-0.1B titanium alloy based on phenomenological constitutive models and a machine learning method DOI Creative Commons
Shuai Zhang, Haoyu Zhang,

Xuejia Liu

et al.

Journal of Materials Research and Technology, Journal Year: 2024, Volume and Issue: 29, P. 589 - 608

Published: Jan. 17, 2024

The two-phase titanium alloy Ti–10 V–5Al-2.5Fe-0.1 B was taken as the experimental material, and thermal compression experiments were carried out at a deformation temperature of 770–920 °C strain rate 0.0005–0.5 s−1. An Arrhenius model, modified Johnson-Cook an improved BP neural network model based on sparrow search algorithm (SSA-BP) established to predict high rheological stress alloy. A comparison prediction accuracy three models made. When partial random data in curves used for building relatively independent predicting stress, SSA-BP had higher accuracy, which exhibits highest mean square correlation coefficient (R2) value 0.9992 lowest root error (RMSE) average absolute relative (AARE) values 1.3031, 2.0947 %, respectively. ability new process parameters verified. Results show that still has better ability, 0.9720 5.0099, 6.0382 predicted construct hot processing map. trend power dissipation factor (η) from map by can well agree with microstructure evolution

Language: Английский

Citations

22
An automatic teeth arrangement method based on an intelligent optimization algorithm and the Frenet–Serret formula DOI

Hong-an Li,

Man Liu

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 105, P. 107606 - 107606

Published: Feb. 5, 2025

Language: Английский

Citations

2
Efficient city supply chain management through spherical fuzzy dynamic multistage decision analysis DOI
Muhammad Riaz, Hafiz Muhammad Athar Farid, Chiranjibe Jana

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 126, P. 106712 - 106712

Published: July 27, 2023

Language: Английский

Citations

30
Stock ranking prediction using a graph aggregation network based on stock price and stock relationship information DOI

Guowei Song,

Tianlong Zhao, Suwei Wang

et al.

Information Sciences, Journal Year: 2023, Volume and Issue: 643, P. 119236 - 119236

Published: May 29, 2023

Language: Английский

Citations

23
Self-attention (SA) temporal convolutional network (SATCN)-long short-term memory neural network (SATCN-LSTM): an advanced python code for predicting groundwater level DOI

Mohammad Ehteram,

Elham Ghanbari-Adivi

Environmental Science and Pollution Research, Journal Year: 2023, Volume and Issue: 30(40), P. 92903 - 92921

Published: July 27, 2023

Language: Английский

Citations

23
Intelligent deep analysis of DNA sequences based on FFGM to enhancement the performance and reduce the computation DOI Creative Commons

Zena A. Kadhuim,

Samaher Al-Janabi

Egyptian Informatics Journal, Journal Year: 2023, Volume and Issue: 24(2), P. 173 - 190

Published: March 7, 2023

In an attempt to improve the analysis DNA sequence, a new intelligent deep algorithm called reduce frequency bast on fast graph mining (RF-FFGM) is established; This at beginning converts sequence into RNA sequences after that split these multi subsequence through determined specific equation for start and end point of each sequence. After represent as subgraph label bonds between pair components related (i.e., A, G, U, C) bounds include 16 labels used Knowledge Constructions (KC)) this work. apply steps FFGM select techniques (GSpan, FFSM, Hybrid-Tree-Miner, Approximate Frequent Sub-graph, CloGraMi FFSM) focus (the main programming steps, parameters, advantages, disadvantages) algorithm. We discovery finds frequent in short time, because it building matrix code connection edge transforming matrices incidence matrix, also; we found can get all edges have highest contact with other edges, so from second stage therefore avoids us going sequential path find duplicate edges. RF-FFGM appears pragmatic algorithm, proves their robust work computation time.

Language: Английский

Citations

17
Investigating the impact of data heterogeneity on the performance of federated learning algorithm using medical imaging DOI Creative Commons
Muhammad Ali Babar, Basit Qureshi, Anis Koubâa

et al.

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(5), P. e0302539 - e0302539

Published: May 15, 2024

In recent years, Federated Learning (FL) has gained traction as a privacy-centric approach in medical imaging. This study explores the challenges posed by data heterogeneity on FL algorithms, using COVIDx CXR-3 dataset case study. We contrast performance of Averaging (FedAvg) algorithm non-identically and independently distributed (non-IID) against identically (IID) data. Our findings reveal notable decline with increased heterogeneity, emphasizing need for innovative strategies to enhance diverse environments. research contributes practical implementation FL, extending beyond theoretical concepts addressing nuances imaging applications. uncovers inherent due diversity. It sets stage future advancements effectively manage especially sensitive fields like healthcare.

Language: Английский

Citations

8
A comprehensive survey on the chicken swarm optimization algorithm and its applications: state-of-the-art and research challenges DOI Creative Commons

Binhe Chen,

Li Cao,

Changzu Chen

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(7)

Published: June 11, 2024

Abstract The application of optimization theory and the algorithms that are generated from it has increased along with science technology's continued advancement. Numerous issues in daily life can be categorized as combinatorial issues. Swarm intelligence have been successful machine learning, process control, engineering prediction throughout years shown to efficient handling An intelligent system called chicken swarm algorithm (CSO) mimics organic behavior flocks chickens. In benchmark problem's objective function, outperforms several popular methods like PSO. concept advancement flock algorithm, comparison other meta-heuristic algorithms, development trend reviewed order further enhance search performance quicken research algorithm. fundamental model is first described, enhanced based on parameters, chaos quantum optimization, learning strategy, population diversity then summarized using both domestic international literature. use group areas feature extraction, image processing, robotic engineering, wireless sensor networks, power. Second, evaluated terms benefits, drawbacks, algorithms. Finally, direction anticipated.

Language: Английский

Citations

8
Explainable Machine Learning for Real-Time Payment Fraud Detection: Building Trustworthy Models to Protect Financial Transactions DOI

Ahmed Abbas Jasim Al-Hchaimi,

Mohammed F. Alomari, Yousif Raad Muhsen

et al.

Lecture notes in networks and systems, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 25

Published: Jan. 1, 2024

Language: Английский

Citations

7
Echo State Networks: Novel reservoir selection and hyperparameter optimization model for time series forecasting DOI Creative Commons
César Hernando Valencia Niño, Marley Vellasco, Karla Figueiredo

et al.

Neurocomputing, Journal Year: 2023, Volume and Issue: 545, P. 126317 - 126317

Published: May 12, 2023

The use of computational intelligence models for multi-step time series forecasting tasks has presented satisfactory results in such a way that they are considered with an excellent future this type problem. From the point view cost, current alternatives combined classical generating hybrid present even better results. Within AutoML category, optimization hyperparameters and selection network topologies become challenge. Reservoir Computing, which is within area ​​Recurrent Neural Networks (RNN), proposes particular model called Echo State Networks. been tested different applications results; however, difficulty specifying subject continuous study given random nature set neurons Reservoir. Based on Separation Ratio Graph (SRG) performance analysis, paper new model, Network - Genetic Algorithm (ESN-GA-SRG), optimizes at same selects best topology using SRG coefficient, to find reservoir offers most suitable dynamic behavior. evaluated two sets benchmarks characteristics sampling periodicity, skewness, stationarity. obtained show ESN-GA-SRG was superior predicting these cases, statistical significance, when compared other have problem literature.

Language: Английский

Citations

15