Selected work

Representative Papers

Synthetic data in cryptocurrencies using generative models

Apr 17, 2026

This study addresses the challenge posed by limited access to real-world financial data due to privacy constraints and access barriers, which hinders research in the cryptocurrency domain. To overcome this, the authors propose a synthetic data generation method based on conditional generative adversarial networks (CGANs), employing an LSTM-based generator and an MLP-based discriminator. The approach effectively preserves key market trends and dynamic statistical properties while substantially reducing computational overhead. Experimental results demonstrate that the generated data successfully replicates critical temporal patterns across multiple crypto-assets and outperforms existing sophisticated generative models in downstream tasks such as market behavior analysis and anomaly detection. This work thus offers an efficient and viable alternative for financial modeling in privacy-sensitive scenarios.

0 citationsRead paper

A Parametric Bi-Directional Curvature-Based Framework for Image Artifact Classification and Quantification

Aug 12, 2025

To address insufficient artifact-type discrimination and quantification accuracy in no-reference image quality assessment (NR-IQA), this paper proposes a novel framework based on directional image curvature analysis. It pioneers the use of bidirectional curvature difference responses to distinguish degradation types—including blur and noise—and introduces an adjustable-threshold anisotropic texture richness (ATR) metric for pixel-level degradation modeling. A classification–regression two-stage system is developed: the first stage achieves 97.2% artifact classification accuracy; the second stage maps ATR to perceptual quality scores, attaining R² = 0.892 and RMSE = 5.17 DMOS (7.4% of the full scale) on a composite dataset. The method achieves Spearman correlation coefficients of −0.93 and −0.95 with human judgments for Gaussian blur and white noise, respectively—demonstrating superior discriminability and perceptual consistency.

0 citationsRead paper

Recent publications

Latest Papers

Synthetic data in cryptocurrencies using generative models

Apr 17, 2026

This study addresses the challenge posed by limited access to real-world financial data due to privacy constraints and access barriers, which hinders research in the cryptocurrency domain. To overcome this, the authors propose a synthetic data generation method based on conditional generative adversarial networks (CGANs), employing an LSTM-based generator and an MLP-based discriminator. The approach effectively preserves key market trends and dynamic statistical properties while substantially reducing computational overhead. Experimental results demonstrate that the generated data successfully replicates critical temporal patterns across multiple crypto-assets and outperforms existing sophisticated generative models in downstream tasks such as market behavior analysis and anomaly detection. This work thus offers an efficient and viable alternative for financial modeling in privacy-sensitive scenarios.

0 citationsRead paper

A Parametric Bi-Directional Curvature-Based Framework for Image Artifact Classification and Quantification

Aug 12, 2025

To address insufficient artifact-type discrimination and quantification accuracy in no-reference image quality assessment (NR-IQA), this paper proposes a novel framework based on directional image curvature analysis. It pioneers the use of bidirectional curvature difference responses to distinguish degradation types—including blur and noise—and introduces an adjustable-threshold anisotropic texture richness (ATR) metric for pixel-level degradation modeling. A classification–regression two-stage system is developed: the first stage achieves 97.2% artifact classification accuracy; the second stage maps ATR to perceptual quality scores, attaining R² = 0.892 and RMSE = 5.17 DMOS (7.4% of the full scale) on a composite dataset. The method achieves Spearman correlation coefficients of −0.93 and −0.95 with human judgments for Gaussian blur and white noise, respectively—demonstrating superior discriminability and perceptual consistency.

0 citationsRead paper