Authors: Hong, Jie | Qin, Xiansheng | Li, Jing | Niu, Junlong | Wang, Wenjie
Article Type: Research Article
Abstract: Over the past two decades, motor imagery brain-computer interface (MI-BCI) system has been extensively developed. In this system signal processing algorithms are critical to robust operation. In BCI community, however, there is no comprehensive review of the recent development of signal processing algorithms. Through analyzing the latest papers, signal processing algorithms of pre-processing, feature extraction, feature selection, and classification components are discussed in detail. Besides, post-processing and other existing problems are mentioned. The following key issues are addressed: (1) which components are the key of signal processing; (2) which signal processing algorithms are frequently used in each component; (3) which …signal processing algorithms attract more attention. This information can be used as reference and guidance for further research. Show more
Keywords: Motor imagery brain-computer interface (MI-BCI), signal processing algorithms, pre-processing, feature extraction, classification
DOI: 10.3233/JIFS-181309
Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 6, pp. 6405-6419, 2018
Authors: Wang, Wenjie | Li, Huiyu | Zhou, Yan | Jie, Shenghua
Article Type: Research Article
Abstract: Background: Microvesicles (MVs) are produced through the outward vesicles budding and fission from the cell surface. Recently, it was discovered that extracellular MVs circulate in bodily fluids of cancer patients and could serve as potential diagnostic biomarkers. However, the diagnostic and prognostic roles of peripheral circulating MVs for hepatocellular carcinoma (HCC) remain unclear. Objective: The aim of this study was to investigate whether the peripheral blood MVs could serve as potential biomarkers for detection of HCC. Methods: Peripheral blood samples were obtained prior to treatment from 55 patients with HCC, 40 patients with liver cirrhosis and 21 healthy controls. MVs …were isolated from peripheral blood by centrifugation and measured by using bicinchoninic acid assay. Results: Peripheral blood MVs levels were significantly elevated in HCC patients compared to those in liver cirrhosis (p< 0.001). Furthermore, MVs levels was correlated with the HCC tumor size, pathological classification and TNM stage (p< 0.01). Of note, MVs levels were significantly reduced in the 1 month post-operative blood samples when compared to those in the pre-operative samples in the 17 HCC cases tested. MVs levels did not relate to liver enzymes, AFP levels, alcohol drinking or smoking habits (p> 0.05). In contrast, serum MVs levels correlated with the age of patients, leukocytes, platelets and prothrombin time. The results of receiver operating characteristic (ROC) analysis indicated better performance of MVs than AFP for early detection of HCC. The areas under the ROC curve of MVs for discriminating patients with early (TNM stage I) and relatively early (TNM stage II) HCC from liver cirrhosis was 0.83 (95% CI: 0.74–0.93) and 0.94 (95% CI: 0.88–1.00), respectively. Conclusions: Peripheral blood MVs levels were increased in patients with HCC and associated with the progression of disease. Serum MVs might serve as novel biomarkers for the diagnosis of HCC at early stage. Show more
Keywords: HCC, MVs, AFP, diagnosis
DOI: 10.3233/CBM-130370
Citation: Cancer Biomarkers, vol. 13, no. 5, pp. 351-357, 2013
Authors: Yang, Mengyin | Chen, Junfen | Wang, Wenjie | He, Qiang
Article Type: Research Article
Abstract: Deep unsupervised learning extracts meaningful features from unlabeled images and simultaneously serves downstream tasks in computer vision. The basic process of deep clustering methods can include features learning and clustering assignment. To enhance the discriminative ability of the features and further improve the clustering performances, a new deep clustering method namely ACMEC (asymmetric convolutional denoising autoencoder with manifold spatial embedding clustering) is proposed. In this method, an asymmetric convolution denoising autoencoder is employed to extract visual features from images, and a manifold learning algorithm is used to obtain more distinctive features, followed by a Gaussian Mixture Model (GMM) is for …clustering learning. The stability of feature space is guaranteed using separately training mechanism. In addition, reconstruction from noisy images enhances the robustness of feature networks. Experimental results on nine benchmark datasets demonstrate that the proposed ACMEC method can provide the better performances such as 0.979 clustering accuracy on the MNIST dataset and 0.668 on the fashion-MNIST dataset. ACMEC is a comparable competitor to the N2D (not too deep clustering) algorithm that is with 0.979 and 0.672 clustering accuracies respectively. Moreover, it is 16.1% higher than DEC algorithm on the fashion-MNIST dataset. Show more
Keywords: Clustering analysis, feature learning, asymmetric convolutional denoising autoencoder, manifold embedding, Gaussian mixture models (GMM)
DOI: 10.3233/JIFS-213468
Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 3, pp. 2933-2944, 2022
Authors: Li, Sinian | Shao, Yiming | Li, Kanglan | HuangFu, Changmei | Wang, Wenjie | Liu, Zhou | Cai, Zhiyou | Zhao, Bin
Article Type: Review Article
Abstract: Vascular cognitive impairment (VCI), the second most common cause of dementia in elderly people, is a term that refers to all forms of cognitive disorders that can be attributed to cerebrovascular disease such as manifestations of discrete infarctions, brain hemorrhages, and white matter lesions. The gut microbiota (GM) has emerged recently as an essential player in the development of VCI. The GM may affect the brain’s physiological, behavioral, and cognitive functions through the brain-gut axis via neural, immune, endocrine, and metabolic pathways. Therefore, microbiota dysbiosis may mediate or affect atherosclerosis, cerebrovascular disease, and endothelial dysfunction, which are the predominant risk …factors for VCI. Moreover, the composition of the GM includes the bacterial component lipopolysaccharides and their metabolic products including trimethylamine-N -oxide and short-chain fatty acids. These products may increase the permeability of the intestinal epithelium, leading to systemic immune responses, low-grade inflammation, and altered signaling pathways that are associated with the pathogenesis of VCI. In this review, we discuss the proposed mechanisms of the GM in the maintenance of VCI and how it is implicated in acquired metabolic diseases, particularly in VCI regulation. Show more
Keywords: Atherosclerosis, cerebrovascular disease, endothelial dysfunction, gut microbiota, lipopolysaccharides, short-chain fatty acids, trimethylamine-N-oxide, vascular cognitive impairment
DOI: 10.3233/JAD-171103
Citation: Journal of Alzheimer's Disease, vol. 63, no. 4, pp. 1209-1222, 2018