Mechanical intelligent fault diagnosis is an important method to accurately identify the health status of mechanical equipment. Traditional fault diagnosis methods perform poorly in the diagnosis of rolling bearings under complex conditions. In this paper, a feature transfer learning model based on improved DenseNet and joint distribution adaptation (FT-IDJ) is proposed. With this model, we apply it to implement rolling bearing fault diagnosis. A lightweight DenseNet model is firstly proposed to extract the transferable features of the raw vibration signal. Furthermore, the parameters in the DenseNet are constrained by the domain adaptive regularization term and pseudo label learning. The marginal distribution discrepancy and the conditional distribution discrepancy of the learned transferable features are reduced by this way. The proposed method is validated by the diagnosis experiments with CWRU and Jiangnan University rolling bearing datasets. The experimental results showed that the proposed FT-IDJ has higher classification accuracy than DAN and other eight methods, which demonstrated its effectively learning transferable features from auxiliary data.
Exosomes are essential early biomarkers for health monitoring and cancer diagnosis. A prerequisite for further investigation of exosomes is the isolation, which is technically challenging due to the complexity of body fluids. This paper presents the development of an integrated microfluidic chip for exosomes isolation, which combines the traditional immunomagnetic bead-based protocol and the recently emerging microfluidic approach, resulting in benefits from both the high-purity of the former and the automated continuous superiority of the latter. The chip was designed based on an S-shaped micromixer with embedded baffle. The excellent mixing efficiency of this micromixer compared with Y-shaped and S-shaped micromixers was verified by simulation and experiments. The photolithography technique was employed to fabricate the integrated microfluidic chip, and the manufacturing process was elucidated. We finally established an experimental platform for exosomes isolation with the fabricated microfluidic chip built in. Exosomes isolation experiments were conducted using this platform. The distribution and morphology of the isolated exosomes were observed by transmission electron microscopy (TEM) and scanning electron microscopy (SEM). Quantitative size analyses based on transmission electron micrographs indicated that most of the obtained particles were between 30 and 150 nm. Western blot analyses of the isolated exosomes and the serum were conducted to verify the platform’s capability of isolating a certain subpopulation of exosomes corresponding to specified protein markers (CD63). The complete time for isolation of 150 μL serum samples was approximately 50 min, which was highly competitive with the reported existing protocols. Experimental results proved the capacity of the established integrated microfluidic chip for exosomes isolation with high purity, high integrity, and excellent efficiency. The platform can be further developed to make it possible for practical use in clinical applications as a universal exosomes isolation and characterization tool.
Lymphomatoid granulomatosis (LYG) is an angiocentric and angiodestructive lymphoproliferative disease which can involve multiple organs of the body and is most common in the lungs. Its pathological features are proliferation of large atypical B‐cells related to Epstein–Barr virus, T‐cell infiltration and tissue necrosis. This disease is rare, and LYG which uniquely involves the central nervous system (CNS) is extremely rare. In this paper, we report a case of isolated lymphomatoid granulomatosis of the CNS (iCNS‐LYG) diagnosed by histological biopsy and we review the clinical features of all similar cases reported in the past 46 years. A total of 49 cases of iCNS‐LYG have been reported to date. The clinical, imaging and pathological features of iCNS‐LYG are discussed in combination with a literature review.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.