A5016815271- Machine Fault Diagnosis Techniques
- Fault Detection and Control Systems
- Engineering Diagnostics and Reliability
- Acute Myeloid Leukemia Research
- Hematopoietic Stem Cell Transplantation
- Hematological disorders and diagnostics
- Complement system in diseases
- Neurogenetic and Muscular Disorders Research
- Blood groups and transfusion
- Bone and Joint Diseases
- Imbalanced Data Classification Techniques
- Immunodeficiency and Autoimmune Disorders
- Monoclonal and Polyclonal Antibodies Research
- Myeloproliferative Neoplasms: Diagnosis and Treatment
- Anomaly Detection Techniques and Applications
- Cancer-related gene regulation
- Chronic Lymphocytic Leukemia Research
- Mesenchymal stem cell research
- Immune Response and Inflammation
- Power Systems Fault Detection
- Gear and Bearing Dynamics Analysis
- Lymphoma Diagnosis and Treatment
- Exercise and Physiological Responses
Xinjiang University
2024-2025
Institute of Hematology & Blood Diseases Hospital
1997-1998
Abstract Deep learning-based methods have shown promising results in fault diagnosis, but research on interpretability and noise robustness still needs to be done. A multi-channel wide-kernel wavelet convolutional neural network is proposed address these issues. Firstly, a first layer of convolution designed fuse different weight information suppress high-frequency noise. Secondly, discrete transform block retain the low-frequency components for signal denoising feature dimension reduction....
In complex industrial scenarios, high-quality fault data of rotating machinery are scarce and costly to collect. Therefore, small sample diagnosis needs further research. To solve this problem, in work is proposed a minimum variance auxiliary classifier generation adversarial network based on multi-scale convolutional block attention mechanism. Firstly, the mechanism designed extract information perform weighted fusion enhance ability model capture effective features. Secondly, term minimize...
Abstract In practical scenarios, gearbox fault diagnosis faces the challenge of extremely scarce labeled data. Additionally, variations in operating conditions and differences sensor installations exacerbate data distribution shifts, significantly increasing difficulty diagnosis. To address above issues, this paper proposes a wavelet dynamic joint self-adaptive network guided by pseudo-label alignment mechanism (MDJSN-DFL). First, wavelet-efficient convolution module is designed based on...
获得性再生障碍性贫血发病的主要环节是抗原介导的细胞毒性T细胞功能亢进。其发病机制涉及辅助性T细胞（Th）1/Th2、Th17/调节性T细胞、髓系树突状细胞/淋系树突状细胞失衡，自然杀伤细胞数量及功能异常。记忆T细胞、骨髓间充质干细胞及血细胞端粒相关蛋白等也可能参与其中。近年有关获得性再生障碍性贫血遗传学异常研究增多，包括细胞遗传学异常、体细胞突变等。有些报道的"克隆性再生障碍性贫血"应诊断为"意义未明的克隆性血细胞减少症"。.
Objective: To investigate the change of NIX level bone marrow nucleated red blood cells in anemia patients with myelodysplastic syndromes (MDS), to explore significance NIX-mediated mitochondrial autophagy pathogenesis MDS anemia. Methods: A total 54 diagnosed Department Hematology General Hospital, Tianjin Medical University from July 2015 2016 were enrolled into group, 33 cases immune thrombocytopenia or idiopathic leukopenia as controls.The NIX, number mitochondria, membrane potential,...