-
1641
An End-to-End Relearning Framework for Building Energy Optimization
Published 2025-03-01“…Current approaches are limited: physics-based models are expensive and inflexible, while data-driven methods require extensive data collection and ongoing maintenance. …”
Get full text
Article -
1642
MixRformer: Dual-Branch Network for Underwater Image Enhancement in Wavelet Domain
Published 2025-05-01“…Experiments show that the model outperforms mainstream methods in color restoration and detail enhancement, while optimizing computational efficiency.…”
Get full text
Article -
1643
Information Bottleneck Driven Deep Video Compression—IBOpenDVCW
Published 2024-09-01“…Our results demonstrate that the proposed model and training technique outperform existing state-of-the-art video compression methods, delivering competitive rate-distortion performance compared to the AVC/H.264 and HEVC/H.265 codecs.…”
Get full text
Article -
1644
Multimodal Medical Image Fusion in NSST Domain in Coupled Neural Systems
Published 2025-05-01“…The proposed method proves superior in merging MRI and PET brain image pairs through experimental testing of 48 pairs when evaluated against seven mainstream fusion methods including CNN-based and neuro-fuzzy models. …”
Get full text
Article -
1645
Research on Hybrid Wind Speed Prediction System Based on Artificial Intelligence and Double Prediction Scheme
Published 2020-01-01“…Regarding point prediction in the developed double prediction system, a novel nonlinear integration method based on a backpropagation network optimized using the multiobjective evolutionary algorithm based on decomposition was successfully implemented to derive the final prediction results, which enable further improvement of the accuracy of point prediction. …”
Get full text
Article -
1646
An Integrated Electricity–Gas–Heat Energy System Based on the Synergy of Long- and Short-Term Energy Storage
Published 2024-12-01“…Therefore, this paper proposes an integrated energy system planning and optimization method based on hybrid energy storage. Firstly, an adaptive noise integration empirical modal decomposition method based on the optimization improvement of the grey wolf algorithm is designed for the power allocation strategy of the hybrid energy storage system; secondly, for the electric–gas system, an energy management strategy for the hybrid electric–gas energy storage system, taking into account the operating characteristics of the alkaline electrolyzer, is proposed in order to strengthen the complementary mechanism between electric energy storage and gas energy storage. …”
Get full text
Article -
1647
Effects of Ca2+ on the Cross-linking of Sea Cucumber Collagen Fibers during Thermal Processing
Published 2025-07-01“…Subsequently, the extracted CFs were served as a simplified model, and after undergoing the same thermal processing, the contents of protein, polysaccharides and TCA soluble oligopeptides in the dissolution were determined by BCA, phenol sulfuric acid and Folin-method, respectively. …”
Get full text
Article -
1648
Ambient Vibration Testing for Story Stiffness Estimation of a Heritage Timber Building
Published 2013-01-01“…As for the ambient vibration testing, measured structural responses are analyzed by two output-only system identification methods (i.e., frequency domain decomposition and stochastic subspace identification) to estimate modal parameters. …”
Get full text
Article -
1649
The etiological relationship between the general factors of psychopathology and personality; a longitudinal twin study from adolescence into young adulthood
Published 2025-07-01“…Data was analyzed using a genetically informative random intercept cross-lagged panel model and Cholesky decomposition modeling.ResultsNegligible cross-lagged effects were observed between the general factors. …”
Get full text
Article -
1650
Does the hierarchical medical system enhance healthcare utilization and equity in China? a longitudinal study 2012–2018
Published 2025-08-01“…A multiple-period difference-in-differences method was employed to explore the impact on outpatient and inpatient utilization across socioeconomic dimensions. …”
Get full text
Article -
1651
Study of unusable liquid propellant residues evaporation processes parameters in the tanks of launch vehicle worked-off stage in microgravity
Published 2019-06-01“…A method is proposed for studying the evaporation process of unusable rocket propellant residues in worked-off stage under weightless conditions. …”
Get full text
Article -
1652
Trend analysis and epidemiological forecasting of colorectal Cancer mortality among reproductive-age women in sub-Saharan Africa
Published 2025-08-01“…The Das Gupta decomposition method quantified the contributions of aging, population growth, and epidemiological changes. …”
Get full text
Article -
1653
Deep learning and wavelet packet transform for fault diagnosis in double circuit transmission lines
Published 2025-08-01“…The WPT technique extracts approximation coefficients from current and voltage signals, which serve as inputs to deep learning models, particularly using the mother wavelet packet db10 for optimal decomposition. …”
Get full text
Article -
1654
Quantum Heisenberg Spin Chains with Inversely Linear Correlated Disorder: Localization Effects and State Transfer Protocols
Published 2025-04-01“…The Cholesky decomposition method is employed to generate the spin-spin coupling that adheres to this correlation structure. …”
Get full text
Article -
1655
Aquaporins as Membrane Proteins: The Current Status
Published 2025-03-01“…Aquaporins are transmembrane proteins responsible for primarily transporting water and low-molecular-weight compounds. Methods: The fuzzy oil drop (FOD) model was applied in its modified form, FOD-M, for the analysis. …”
Get full text
Article -
1656
Research on filter-based adversarial feature selection against evasion attacks
Published 2023-07-01“…With the rapid development and widespread application of machine learning technology, its security has attracted increasing attention, leading to a growing interest in adversarial machine learning.In adversarial scenarios, machine learning techniques are threatened by attacks that manipulate a small number of samples to induce misclassification, resulting in serious consequences in various domains such as spam detection, traffic signal recognition, and network intrusion detection.An evaluation criterion for filter-based adversarial feature selection was proposed, based on the minimum redundancy and maximum relevance (mRMR) method, while considering security metrics against evasion attacks.Additionally, a robust adversarial feature selection algorithm was introduced, named SDPOSS, which was based on the decomposition-based Pareto optimization for subset selection (DPOSS) algorithm.SDPOSS didn’t depend on subsequent models and effectively handles large-scale high-dimensional feature spaces.Experimental results demonstrate that as the number of decompositions increases, the runtime of SDPOSS decreases linearly, while achieving excellent classification performance.Moreover, SDPOSS exhibits strong robustness against evasion attacks, providing new insights for adversarial machine learning.…”
Get full text
Article -
1657
Regional Differences and Dynamic Evolution of Agricultural Product Market Integration in China
Published 2025-04-01“…We use the Dagum–Gini coefficient and its decomposition and the σ convergence and β convergence models to analyze regional variations, time trends, and convergence. …”
Get full text
Article -
1658
Enhanced “Wind‐Evaporation Effect” Drove the “Deep‐Tropical Contraction” in the Early Eocene
Published 2024-10-01“…Based on the energetics framework of the Intertropical Convergence Zone (ITCZ) and the decomposition method of the latent heat flux along with the simulations of a climate system model, CESM1.2, we proposed a novel mechanism responsible for the “deep‐tropical contraction” in the early Eocene. …”
Get full text
Article -
1659
Optimization of an Intelligent Music-Playing System Based on Network Communication
Published 2021-01-01“…The recommendation engine module in this paper is designed and optimized using Spark to implement incremental matrix decomposition on data streams, online collaborative topic model, and improved item-based collaborative filtering algorithm. …”
Get full text
Article -
1660
Advancing nitrocellulose thermal stability through the incorporation of ion-exchanged ZSM-5 zeolite for enhanced performance
Published 2025-06-01“…Furthermore, the influence of diverse stabilizers on the thermal decomposition kinetics of NC was studied based on advanced model-free kinetic approaches, namely TAS and VYA/CE. …”
Get full text
Article