A5071124814- Traditional Chinese Medicine Studies
- Rough Sets and Fuzzy Logic
- Advanced Computational Techniques and Applications
- Acupuncture Treatment Research Studies
- Liver Disease Diagnosis and Treatment
- Healthcare and Venom Research
- Infrared Thermography in Medicine
- Biomedical Text Mining and Ontologies
- Data Management and Algorithms
- Solar Energy Systems and Technologies
- Image Retrieval and Classification Techniques
- Metabolomics and Mass Spectrometry Studies
- Data Visualization and Analytics
- AI in cancer detection
- Veterinary Equine Medical Research
- Thermoregulation and physiological responses
- Face and Expression Recognition
- Advanced Text Analysis Techniques
- Advanced Chemical Sensor Technologies
- Adsorption and Cooling Systems
- Advanced Proteomics Techniques and Applications
- Wind and Air Flow Studies
- Thyroid Cancer Diagnosis and Treatment
- Simulation and Modeling Applications
- Medical Research and Treatments
Shenyang Jianzhu University
2010-2025
Southeast University
2025
Second Military Medical University
2009-2023
Shenyang Pharmaceutical University
2023
Xi'an Jiaotong University
2023
Yanshan University
2010-2022
Chinese People's Liberation Army
2021
Institute of Electrical Engineering
2015-2020
Dalian University of Technology
2013
Changzhi Medical College
2008
As an empirical medical system independent of conventional Western medicine (CWM), over thousands years, traditional Chinese (TCM) has established its own unique method diagnosis and treatment. The perspective holism in TCM is essentially different from the view Reductionism CWM. With development modern science technology, restriction reductionism more prominent, researchers begin to pay attention holistic thinking TCM. Confronted with above situation, there urgent need explore by techniques...
Recent years have witnessed the promise of coupling machine learning methods and physical domain-specific insight for solving scientific problems based on partial differential equations (PDEs). However, being data-intensive, these still require a large amount PDE data. This reintroduces need expensive numerical solutions, partially undermining original goal avoiding simulations. In this work, seeking data efficiency, we design unsupervised pretraining in-context operator learning. To reduce...
Metabolic syndrome (MS) is a clinical with multiple metabolic disorders. As the diagnostic criteria for MS still lacking of imaging laboratory method, this study aimed to explore differences between healthy people and patients through infrared thermography (IRT). However, observation region IRT image uncertain, research tried solve problem help knowledge mining technology. 43 participants were randomly included cross-sectional recruited number matching. The each participant was segmented...
Inquiring diagnosis of Traditional Chinese medicine is one the basic methods for diagnosing disease. Inquiry can collect most extensive clinical information patient. It get many disease which can't be got by any other method. This paper presents a complex system model inquiring based on combination formal concept analysis theory and medicine. Computerized gets scores symptoms syndrome elements through voice interactive way between human system. In accordance with principles analysis,...
This paper presents a computer-aided system for automatic diagnosis of cirrhosis based on ultrasound images. We first propose dynamic programming algorithm to automatically extract the liver capsule, and then continuity smoothness capsule serve as an important guideline image classification. Via decomposition in spatial gray scales, density entropy suspected nodular areas are used describe texture features parenchyma. Finally, trained SVM classifier is applied classify samples into normal,...
We endeavour to provide a novel theory evaluate environmental comfort level. A method that fuses multidimensional parameters based on radar chart representation is provided in this paper. The value of the transformed into linguistic description according linear and nonlinear membership creation method. Consequently, an integrated objective about level given. measuring testing system indoor designed here by MSP430 MCU. design given better performance achieved. It our belief can be used many...
A visualization technique based on the ideas of scatter plot matrix, star diagrams and parallel coordinates is developed in this paper. The principles algorithms these visualizations are analyzed compared from a geometrical perspective. It shows that three coordinate-bused have unified mathematical foundation presentation ways thus can he combined into single we call dual plot. new created by firstly transforming glyph, then glyph presented coordinates. Thus, approach provides point-to-point...
Syndrome elements are the smallest units of syndrome classification and basic differentiation. Introduction Traditional Chinese Medicine (TCM) can increase accuracy treatment after differentiation, this is conducive to standardization study TCM syndrome. The has significant significance for This paper presents a method pattern discovery on elements, basis principle inquiring diagnosis in TCM. clinical results very similar with research Beijing University National Basic Research Program China...
A visual pattern recognition method based on optimized parallel coordinates is proposed in this paper. We first introduce the traditional theory of and indicate that has a potential for classification tasks due to its projective transformation interpretation. Nevertheless, some optimization needed. The main aim hide valueless information reveal most valuable classification. Three interaction operations are do work. demonstrate by several examples how solve problems graphically, we also point...
Large Language Models (LLMs) show promise in code generation tasks. However, their code-writing abilities are often limited scope: while they can successfully implement simple functions, struggle with more complex A fundamental difference how an LLM writes code, compared to a human programmer, is that it cannot consistently spot and fix bugs. Debugging crucial skill for programmers enables iterative refinement towards correct implementation. In this work, we propose novel algorithm enable...
Abstract This paper introduces a new neural network architecture designed to forecast high-dimensional spatio-temporal data using only sparse measurements. The uses two-stage end-to-end framework that combines ordinary differential equations (NODEs) with vision transformers. Initially, our approach models the underlying dynamics of complex systems within low-dimensional space; and then it reconstructs corresponding spatial fields. Many traditional methods involve decoding fields before...
Predicting high-fidelity ground motions for future earthquakes is crucial seismic hazard assessment and infrastructure resilience. Conventional empirical simulations suffer from sparse sensor distribution geographically localized earthquake locations, while physics-based methods are computationally intensive require accurate representations of Earth structures sources. We propose a novel artificial intelligence (AI) simulator, Conditional Generative Modeling Ground Motion (CGM-GM), to...
Dimensionality reduction is the process of mapping high-dimension patterns to a lower dimension subspace. When done prior classification, estimates obtained in subspace are more reliable. We propose novel method based on graphical multivariate feature fusion and use it offer visual representation high dimensional data. The processing we propose, relies using multilayered structure which produces as output representation. implement by combining selection extraction. Experiments data set...