Search alternatives:
post » most (Expand Search)
Showing 61 - 80 results of 155 for search 'improve post optimization algorithm', query time: 0.10s Refine Results
  1. 61
  2. 62
  3. 63

    A Data Resource Trading Price Prediction Method Based on Improved LightGBM Ensemble Model by Wan Nie, Bingliang Shen, Desheng Li

    Published 2025-01-01
    “…To address the key challenges of limited practical application, high implementation difficulty, and poor generalization capability in existing theoretical models for data resource pricing, this study employs generative adversarial network (GAN) to augment the dataset and constructs a DRV-LightGBM model based on a Bayesian parameter optimization algorithm that maximizes the coefficient of determination (<inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula>) to predict data resource transaction prices and provide post-hoc explanations for the prediction model. …”
    Get full text
    Article
  4. 64

    Comparative Study on Hyperparameter Tuning for Predicting Concrete Compressive Strength by Jeonghyun Kim, Donwoo Lee

    Published 2025-06-01
    “…This study assesses the impact of hyperparameter optimization algorithms on the performance of machine learning-based concrete compressive strength prediction models. …”
    Get full text
    Article
  5. 65

    Study on the parameters of the matrix NTRU cryptosystem by LI Zichen, WU Qinghao, SONG Jiashuo, PENG Haipeng

    Published 2025-03-01
    “…With the rapid development of quantum computers, post-quantum cryptography has emerged as a prominent area of research in cryptography.ObjectivesIn order to avoid the decryption failure in matrix NTRU as NTRU, the Matrix NTRU algorithm was optimized.MethodsBased on the method of constraining the parameter space in congruent cryptographic algorithms, a method for optimal selection of the parameter space of matrix NTRU cryptographic regimes was proposed. …”
    Get full text
    Article
  6. 66
  7. 67
  8. 68
  9. 69
  10. 70

    FLIP: A Novel Feedback Learning-Based Intelligent Plugin Towards Accuracy Enhancement of Chinese OCR by Xinyue Tao, Yueyue Han, Yakai Jin, Yunzhi Wu

    Published 2025-07-01
    “…This study develops FLIP (Feedback Learning-based Intelligent Plugin), a lightweight post-processing plugin designed to improve Chinese OCR accuracy across different systems without external dependencies. …”
    Get full text
    Article
  11. 71
  12. 72
  13. 73
  14. 74

    Application of Improved LSTM Model in Runoff Simulation in Arid Region of Northwest China: A Case Study of the Zuli River by SONG Haiping, TANG Yiran, DANG Wentao, WANG Yibo

    Published 2025-01-01
    “…The results indicate that: ① The improved LSTM model demonstrates superior performance in simulating the Zuli River, validating the adaptability of the improved strategies for complex hydrological processes. ② The GWO algorithm significantly enhances the model's prediction accuracy in the basin, confirming the effectiveness of optimization algorithms in parameter calibration. ③The GWO-LSTM-Attention model requires further validation and optimization for future daily-scale simulations and monthly runoff reconstruction.…”
    Get full text
    Article
  15. 75
  16. 76
  17. 77

    Distribution Generation Network Arrangement by Capacitor Placement and Sizing in Renewable Energy Sources with Uncertainties Based on Self-adaption Kho-Kho Optimizer by Lu Xingxing

    Published 2024-09-01
    “…Post-optimization results indicated a reduction in power loss costs from 4.11 × 10^5 to 1.05 × 10^5 units, representing a 25.54% decrease. …”
    Get full text
    Article
  18. 78

    Transfer Learning based Image Classification of Diseased Tomato Leaves with Optimal Fine-Tuning combined with Heat Map Visualization by Sivakumar Palanıswamy, Vijayakumar Vaıthyam Rengarajan, Sandhya Devi Ramıah Subburaj

    Published 2023-11-01
    “…Further, activations are used to generate an attention map in the form of Heat Maps which are included as a post-processing step before the classification of the output. …”
    Get full text
    Article
  19. 79
  20. 80