15 July 2025 in IEEE Transactions on Instrumentation and Measurement
Acoustic features have gained widespread popularity in machinery fault diagnosis owing to their benefits of non-contact measurements and low cost. However, most acoustic diagnostic methods focus only on specific operating conditions and show insufficient feature extraction capability when facing domain shift issues in complex scenarios. To address these problems, this paper proposes a novel hybrid attention-driven convolutional adversarial network (HA-CAN) for cross-domain fault diagnosis. First, HA-CAN employs dense convolution to enhance feature propagation, ensuring efficient information flow. Then, HA-CAN combines dual convolution attention (DCA) and squeeze-and-excitation (SE) modules to achieve global recalibration of spatial and channel features, while minimizing inter-domain differences using Wasserstein distance. Finally, a domain adversarial strategy is designed for training the features for classification, and two sets of bearing acoustic signal data are used for validating the proposed HA-CAN model. The results demonstrate that HA-CAN achieves an average diagnostic accuracy exceeding 97% in both groups of experiments, outperforming other methods in classification accuracy and fault feature extraction capability. Meanwhile, it also exhibits strong noise robustness under noisy conditions.
1 December 2019 in Journal of Thoracic Disease
Background: This study aims to explore the influence of off-pump coronary artery bypass grafting (OPCABG) on coagulation function and the effects of diabetes on coagulation function during OPCABG. Methods: Patients who met the inclusion and exclusion criteria were divided into two groups: diabetes mellitus (DM) and non-diabetes mellitus (NDM) groups. Thromboelastography (TEG) was tested at the following time points: T0, five days after aspirin and clopidogrel therapy, and before OPCABG; T1, returning to care unit after OPCABG; T2, 5 days after aspirin and clopidogrel therapy, and after OPCABG. Results: A total of 56 patients were involved. There were no deaths, or no early postoperative thrombotic events and abnormal bleeding after OPCABG. Intra-group comparison: Compared with T0, the R and K value decreased, while the α angle and MA value increased at T1 and T2, in both groups (P<0.05). A significantly statistical difference was found in the multiple comparison at T0, T1 and T2 (P0.05). Conclusions: The coagulation function of patients was at a hypercoagulable state at the early stage after OPCABG. The coagulation function was affected by diabetes at the day of OPCABG. However, there was no statistical difference after 5 days of aspirin and clopidogrel therapy following OPCABG.
1 February 2018 in Medicine
Chronic heart AQ4 failure (CHF) is the final stage of various heart diseases. YiQiFuMai injection (YQFMI) has been widely applied in the treatment of CHF. However, to our knowledge, there has been no systematic review or meta-analysis of randomized controlled trails (RCTs) regarding the effectiveness of this treatment. Here, we provide a protocol to evaluate the efficacy and safety of YQFMI for CHF. To evaluate the clinical efficacy of YQFMI in treating CHF, 2 researcher members will independently search the RCTs in the following 8 Chinese and English databases, in which the data collection will be from the time when the respective databases were established to January 2018. The databases will include MEDLINE, EMBASE, Cochrane CENTRAL, CINAHL, the Chinese Biomedical Literature Database, the China National Knowledge Infrastructure, VIP Information and Wanfang Data. The therapeutic effects according to the mortality and the New York Heart Association (NYHA) function classification will be accepted as the primary outcomes. We will use RevMan V.5.3 software as well to compute the data synthesis carefully when a meta-analysis is allowed. This study will provide a high-quality synthesis of current evidence of YQFMI for CHF from several aspects including mortality, NYHA function classification. The conclusion of our systematic review will provide evidence to judge whether YQFMI is an effective intervention for CHF. PROSPERO registration number: PROSPERO CRD42017079696.