Yingjun Zhao

Message from the Co-Guest Editor

The rapid evolution of computational methodologies and data analytics has fundamentally transformed modern scientific discovery. From biostatistics and biometrics to artificial intelligence and large-scale data modeling, data-driven approaches are now central to advancing research across biomedical, engineering, and life sciences disciplines.

The Special Issue “Data-Driven Discovery: Biostatistics, Biometrics & Computational Science” aims to explore innovative methodologies and interdisciplinary applications that leverage advanced statistical modeling, machine learning, signal processing, and computational frameworks to address complex real-world problems. With the growing availability of large and heterogeneous datasets, the integration of intelligent algorithms with domain-specific knowledge has become essential for extracting meaningful insights and supporting precision decision-making.

Particular emphasis is placed on methodological rigor, interpretability, and translational relevance. We welcome contributions involving statistical innovation, intelligent diagnostics, predictive modeling, computational optimization, health data analytics, industrial big data applications, and AI-driven decision support systems. Interdisciplinary studies bridging engineering intelligence and biomedical analytics are especially encouraged.

Through this Special Issue, we aim to foster collaboration between statisticians, engineers, computational scientists, and applied researchers, promoting scientific advances grounded in robust data analysis and intelligent computation.

I warmly invite researchers worldwide to contribute their latest findings and join us in advancing data-driven scientific innovation.

Dr. Yingjun Zhao
Co-Guest Editor
Department of Intelligent Manufacturing Engineering
Xinjiang University, China

Dr. Yingjun Zhao has long been engaged in research within the field of intelligent condition monitoring and fault diagnosis. His primary focus lies in the theoretical foundations and methodologies for intelligent diagnostics of rotating machinery and industrial equipment, as well as key technologies involving artificial intelligence and deep learning in engineering applications. His research encompasses signal processing, feature extraction, intelligent classification algorithms, and industrial big data analysis, dedicated to addressing challenges in equipment health management under complex operating conditions. This work supports the development strategies for high-end equipment manufacturing and intelligent manufacturing. He has published multiple papers in international journals such as Measurement and serves as an invited reviewer for several international journals, including Mechanical Systems and Signal Processing, Measurement, Engineering Applications of Artificial Intelligence, Expert Systems with Applications, and Neurocomputing.

ORCID | LinkedIn | ResearchGate

1. SGNT-ASA: A multimodal process industrial system fault diagnosis framework based on graph construction and causal association
2. A PCDN-ATDC multimodal diagnosis method based on a novel AMReLU function with MiWPFE images for bearing fault diagnosis
3. Bearing Fault Diagnosis Based on Time–Frequency Dual Domains and Feature Fusion of ResNet-CACNN-BiGRU-SDPA
4. Fault Monitoring Method for the Process Industry System Based on the Improved Dense Connection Network.