1
|
Zhang D, Huang H, Zhao Q, Zhou G. Generalized latent multi-view clustering with tensorized bipartite graph. Neural Netw 2024; 175:106282. [PMID: 38599137 DOI: 10.1016/j.neunet.2024.106282] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2023] [Revised: 03/22/2024] [Accepted: 03/27/2024] [Indexed: 04/12/2024]
Abstract
Tensor-based multi-view spectral clustering algorithms use tensors to model the structure of multi-dimensional data to take advantage of the complementary information and high-order correlations embedded in the graph, thus achieving impressive clustering performance. However, these algorithms use linear models to obtain consensus, which prevents the learned consensus from adequately representing the nonlinear structure of complex data. In order to address this issue, we propose a method called Generalized Latent Multi-View Clustering with Tensorized Bipartite Graph (GLMC-TBG). Specifically, in this paper we introduce neural networks to learn highly nonlinear mappings that encode nonlinear structures in graphs into latent representations. In addition, multiple views share the same latent consensus through nonlinear interactions. In this way, a more comprehensive common representation from multiple views can be achieved. An Augmented Lagrangian Multiplier with Alternating Direction Minimization (ALM-ADM) framework is designed to optimize the model. Experiments on seven real-world data sets verify that the proposed algorithm is superior to state-of-the-art algorithms.
Collapse
Affiliation(s)
- Dongping Zhang
- School of Automation, Guangdong University of Technology, Guangzhou 510006, China; Guangdong Key Laboratory of IoT Information Technology, Guangdong University of Technology, Guangzhou 510006, China.
| | - Haonan Huang
- School of Automation, Guangdong University of Technology, Guangzhou 510006, China; Key Laboratory of Intelligent Information Processing and System Integration of IoT, Ministry of Education, Guangzhou 510006, China; Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing, Guangzhou 510006, China.
| | - Qibin Zhao
- School of Automation, Guangdong University of Technology, Guangzhou 510006, China; Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo 103-0027, Japan.
| | - Guoxu Zhou
- School of Automation, Guangdong University of Technology, Guangzhou 510006, China; Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing, Ministry of Education, Guangzhou 510006, China.
| |
Collapse
|
2
|
Zeng J, Zhou G, Qiu Y, Li C, Zhao Q. Bayesian tensor network structure search and its application to tensor completion. Neural Netw 2024; 175:106290. [PMID: 38626616 DOI: 10.1016/j.neunet.2024.106290] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2023] [Revised: 03/05/2024] [Accepted: 04/02/2024] [Indexed: 04/18/2024]
Abstract
Tensor network (TN) has demonstrated remarkable efficacy in the compact representation of high-order data. In contrast to the TN methods with pre-determined structures, the recently introduced tensor network structure search (TNSS) methods automatically learn a compact TN structure from the data, gaining increasing attention. Nonetheless, TNSS requires time-consuming manual adjustments of the penalty parameters that control the model complexity to achieve better performance, especially in the presence of missing or noisy data. To provide an effective solution to this problem, in this paper, we propose a parameters tuning-free TNSS algorithm based on Bayesian modeling, aiming at conducting TNSS in a fully data-driven manner. Specifically, the uncertainty in the data corruption is well-incorporated in the prior setting of the probabilistic model. For TN structure determination, we reframe it as a rank learning problem of the fully-connected tensor network (FCTN), integrating the generalized inverse Gaussian (GIG) distribution for low-rank promotion. To eliminate the need for hyperparameter tuning, we adopt a fully Bayesian approach and propose an efficient Markov chain Monte Carlo (MCMC) algorithm for posterior distribution sampling. Compared with the previous TNSS method, experiment results demonstrate the proposed algorithm can effectively and efficiently find the latent TN structures of the data under various missing and noise conditions and achieves the best recovery results. Furthermore, our method exhibits superior performance in tensor completion with real-world data compared to other state-of-the-art tensor-decomposition-based completion methods.
Collapse
Affiliation(s)
- Junhua Zeng
- School of Automation, Guangdong University of Technology, Guangzhou, 510006, China; Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, 103-0027, Japan; Key Laboratory of Intelligent Information Processing and System Integration of IoT, Ministry of Education, Guangzhou, 510006, China.
| | - Guoxu Zhou
- School of Automation, Guangdong University of Technology, Guangzhou, 510006, China; Key Laboratory of Intelligent Detection and the Internet of Things in Manufacturing, Ministry of Education, Guangzhou, 510006, China.
| | - Yuning Qiu
- School of Automation, Guangdong University of Technology, Guangzhou, 510006, China; Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, 103-0027, Japan.
| | - Chao Li
- Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, 103-0027, Japan.
| | - Qibin Zhao
- School of Automation, Guangdong University of Technology, Guangzhou, 510006, China; Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, 103-0027, Japan.
| |
Collapse
|
3
|
Huang H, Zhou G, Zhao Q, He L, Xie S. Comprehensive Multiview Representation Learning via Deep Autoencoder-Like Nonnegative Matrix Factorization. IEEE Trans Neural Netw Learn Syst 2024; 35:5953-5967. [PMID: 37672378 DOI: 10.1109/tnnls.2023.3304626] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/08/2023]
Abstract
Learning a comprehensive representation from multiview data is crucial in many real-world applications. Multiview representation learning (MRL) based on nonnegative matrix factorization (NMF) has been widely adopted by projecting high-dimensional space into a lower order dimensional space with great interpretability. However, most prior NMF-based MRL techniques are shallow models that ignore hierarchical information. Although deep matrix factorization (DMF)-based methods have been proposed recently, most of them only focus on the consistency of multiple views and have cumbersome clustering steps. To address the above issues, in this article, we propose a novel model termed deep autoencoder-like NMF for MRL (DANMF-MRL), which obtains the representation matrix through the deep encoding stage and decodes it back to the original data. In this way, through a DANMF-based framework, we can simultaneously consider the multiview consistency and complementarity, allowing for a more comprehensive representation. We further propose a one-step DANMF-MRL, which learns the latent representation and final clustering labels matrix in a unified framework. In this approach, the two steps can negotiate with each other to fully exploit the latent clustering structure, avoid previous tedious clustering steps, and achieve optimal clustering performance. Furthermore, two efficient iterative optimization algorithms are developed to solve the proposed models both with theoretical convergence analysis. Extensive experiments on five benchmark datasets demonstrate the superiority of our approaches against other state-of-the-art MRL methods.
Collapse
|
4
|
Qiu Y, Zhou G, Wang A, Zhao Q, Xie S. Balanced Unfolding Induced Tensor Nuclear Norms for High-Order Tensor Completion. IEEE Trans Neural Netw Learn Syst 2024; PP:1-14. [PMID: 38656849 DOI: 10.1109/tnnls.2024.3373384] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/26/2024]
Abstract
The recently proposed tensor tubal rank has been witnessed to obtain extraordinary success in real-world tensor data completion. However, existing works usually fix the transform orientation along the third mode and may fail to turn multidimensional low-tubal-rank structure into account. To alleviate these bottlenecks, we introduce two unfolding induced tensor nuclear norms (TNNs) for the tensor completion (TC) problem, which naturally extends tensor tubal rank to high-order data. Specifically, we show how multidimensional low-tubal-rank structure can be captured by utilizing a novel balanced unfolding strategy, upon which two TNNs, namely, overlapped TNN (OTNN) and latent TNN (LTNN), are developed. We also show the immediate relationship between the tubal rank of unfolding tensor and the existing tensor network (TN) rank, e.g., CANDECOMP/PARAFAC (CP) rank, Tucker rank, and tensor ring (TR) rank, to demonstrate its efficiency and practicality. Two efficient TC models are then proposed with theoretical guarantees by analyzing a unified nonasymptotic upper bound. To solve optimization problems, we develop two alternating direction methods of multipliers (ADMM) based algorithms. The proposed models have been demonstrated to exhibit superior performance based on experimental findings involving synthetic and real-world tensors, including facial images, light field images, and video sequences.
Collapse
|
5
|
Zhou G, Luo S, He J, Chen N, Zhang Y, Cai S, Guo X, Chen H, Song C. Corrigendum to "Effectiveness and safety of tuberculosis preventive treatment for contacts of patients with multidrug-resistant tuberculosis: a systematic review and meta-analysis" [Clin Microbiol Infect 30 (2024) 189-196]. Clin Microbiol Infect 2024:S1198-743X(24)00155-1. [PMID: 38522843 DOI: 10.1016/j.cmi.2024.03.024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/26/2024]
Affiliation(s)
- G Zhou
- Department of The Affiliated Anning First People's Hospital of Kunming University of Science and Technology, Kunming, Yunnan Province, China
| | - S Luo
- Department of The Affiliated Anning First People's Hospital of Kunming University of Science and Technology, Kunming, Yunnan Province, China
| | - J He
- Department of The Affiliated Anning First People's Hospital of Kunming University of Science and Technology, Kunming, Yunnan Province, China
| | - N Chen
- Department of The Affiliated Anning First People's Hospital of Kunming University of Science and Technology, Kunming, Yunnan Province, China
| | - Y Zhang
- Department of The Affiliated Anning First People's Hospital of Kunming University of Science and Technology, Kunming, Yunnan Province, China
| | - S Cai
- Department of The Affiliated Anning First People's Hospital of Kunming University of Science and Technology, Kunming, Yunnan Province, China
| | - X Guo
- Department of The Affiliated Anning First People's Hospital of Kunming University of Science and Technology, Kunming, Yunnan Province, China
| | - H Chen
- Department of The Affiliated Anning First People's Hospital of Kunming University of Science and Technology, Kunming, Yunnan Province, China
| | - C Song
- Department of The Affiliated Anning First People's Hospital of Kunming University of Science and Technology, Kunming, Yunnan Province, China.
| |
Collapse
|
6
|
Zhou G, Xie D, Fan R, Yang Z, Du J, Mai S, Xie L, Wang Q, Mai T, Han Y, Lai F. Comparison of Pulmonary and Extrapulmonary Models of Sepsis-Associated Acute Lung Injury. Physiol Res 2023; 72:741-752. [PMID: 38215061 PMCID: PMC10805253] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2023] [Accepted: 09/09/2023] [Indexed: 01/14/2024] Open
Abstract
To compare different rat models of sepsis at different time points, based on pulmonary or extrapulmonary injury mechanisms, to identify a model which is more stable and reproducible to cause sepsis-associated acute lung injury (ALI). Adult male Sprague-Dawley rats were subjected to (1) cecal ligation and puncture (CLP) with single (CLP1 group) or two repeated through-and-through punctures (CLP2 group); (2) tail vein injection with lipopolysaccharide (LPS) of 10mg/kg (IV-LPS10 group) or 20 mg/kg (IV-LPS20 group); (3) intratracheal instillation with LPS of 10mg/kg (IT-LPS10 group) or 20mg/kg (IT-LPS20 group). Each of the model groups had a sham group. 7-day survival rates of each group were observed (n=15 for each group). Moreover, three time points were set for additional experimental studying in each model group: 4 hours, 24 hours and 48 hours after modeling (every time point, n=8 for each group). Rats were sacrificed to collect BALF and lung tissue samples at different time points for detection of IL-6, TNF-alpha, total protein concentration in BALF and MPO activity, HMGB1 protein expression in lung tissues, as well as the histopathological changes of lung tissues. More than 50 % of the rats died within 7 days in each model group, except for the IT-LPS10 group. In contrast, the mortality rates in the two IV-LPS groups as well as the IT-LPS20 group were significantly higher than that in IT-LPS10 group. Rats received LPS by intratracheal instillation exhibited evident histopathological changes and inflammatory exudation in the lung, but there was no evidence of lung injury in CLP and IV-LPS groups. Rat model of intratracheal instillation with LPS proved to be a more stable and reproducible animal model to cause sepsis-associated ALI than the extrapulmonary models of sepsis.
Collapse
Affiliation(s)
- G Zhou
- The Second Clinical College of Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, China
| | | | | | | | | | | | | | | | | | | | | |
Collapse
|
7
|
Liao X, Zhou G, Liu H, Zhang F. An unusual case of facial cutaneous tuberculosis. J Postgrad Med 2023; 69:241-242. [PMID: 37555421 PMCID: PMC10846819 DOI: 10.4103/jpgm.jpgm_100_23] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2023] [Revised: 04/21/2023] [Accepted: 06/07/2023] [Indexed: 08/10/2023] Open
Affiliation(s)
- X Liao
- Shandong Provincial Hospital for Skin Diseases and Shandong Provincial Institute of Dermatology and Venereology, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, Shandong, China
| | - G Zhou
- Shandong Provincial Hospital for Skin Diseases and Shandong Provincial Institute of Dermatology and Venereology, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, Shandong, China
| | - H Liu
- Shandong Provincial Hospital for Skin Diseases and Shandong Provincial Institute of Dermatology and Venereology, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, Shandong, China
| | - F Zhang
- Shandong Provincial Hospital for Skin Diseases and Shandong Provincial Institute of Dermatology and Venereology, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, Shandong, China
| |
Collapse
|
8
|
Kamal K, Young K, Ly S, Manjaly P, Xiang DH, Zhou G, Mostaghimi A, Theodosakis N. Investigating the association between gender minority identity and skin cancer prevalence: A cohort study in the United States All of Us research program. J Eur Acad Dermatol Venereol 2023; 37:e1151-e1153. [PMID: 37114382 PMCID: PMC10524765 DOI: 10.1111/jdv.19156] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2023] [Accepted: 04/17/2023] [Indexed: 04/29/2023]
Affiliation(s)
- K Kamal
- Harvard Medical School, Boston, Massachusetts, USA
- Department of Dermatology, Brigham and Women's Hospital, Boston, Massachusetts, USA
- Department of Dermatology, Massachusetts General Hospital, Boston, Massachusetts, USA
| | - K Young
- Harvard Medical School, Boston, Massachusetts, USA
| | - S Ly
- Department of Dermatology, Brigham and Women's Hospital, Boston, Massachusetts, USA
- University of Arkansas for Medical Sciences, Little Rock, Arkansas, USA
| | - P Manjaly
- Department of Dermatology, Brigham and Women's Hospital, Boston, Massachusetts, USA
- Boston University School of Medicine, Boston, Massachusetts, USA
| | - D H Xiang
- Harvard Medical School, Boston, Massachusetts, USA
| | - G Zhou
- Department of Dermatology, Brigham and Women's Hospital, Boston, Massachusetts, USA
| | - A Mostaghimi
- Department of Dermatology, Brigham and Women's Hospital, Boston, Massachusetts, USA
| | - N Theodosakis
- Department of Dermatology, Massachusetts General Hospital, Boston, Massachusetts, USA
| |
Collapse
|
9
|
Zhao X, Zhao Q, Tanaka T, Solé-Casals J, Zhou G, Mitsuhashi T, Sugano H, Yoshida N, Cao J. Classification of the Epileptic Seizure Onset Zone Based on Partial Annotation. Cogn Neurodyn 2023; 17:703-713. [PMID: 37265654 PMCID: PMC10229525 DOI: 10.1007/s11571-022-09857-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2021] [Revised: 06/28/2022] [Accepted: 07/11/2022] [Indexed: 02/01/2023] Open
Abstract
Epilepsy is a chronic disorder caused by excessive electrical discharges. Currently, clinical experts identify the seizure onset zone (SOZ) channel through visual judgment based on long-time intracranial electroencephalogram (iEEG), which is a very time-consuming, difficult and experience-based task. Therefore, there is a need for high-accuracy diagnostic aids to reduce the workload of clinical experts. In this article, we propose a method in which, the iEEG is split into the 20-s segment and for each patient, we ask clinical experts to label a part of the data, which is used to train a model and classify the remaining iEEG data. In recent years, machine learning methods have been successfully applied to solve some medical problems. Filtering, entropy and short-time Fourier transform (STFT) are used for extracting features. We compare them to wavelet transform (WT), empirical mode decomposition (EMD) and other traditional methods with the aim of obtaining the best possible discriminating features. Finally, we look for their medical interpretation, which is important for clinical experts. We achieve high-performance results for SOZ and non-SOZ data classification by using the labeled iEEG data and support vector machine (SVM), fully connected neural network (FCNN) and convolutional neural network (CNN) as classification models. In addition, we introduce the positive unlabeled (PU) learning to further reduce the workload of clinical experts. By using PU learning, we can learn a binary classifier with a small amount of labeled data and a large amount of unlabeled data. This can greatly reduce the amount and difficulty of annotation work by clinical experts. All together, we show that using 105 minutes of labeled data we achieve a classification result of 91.46% on average for multiple patients.
Collapse
Affiliation(s)
- Xuyang Zhao
- Department of Electrical Engineering and Computer Science, Tokyo University of Agriculture and Technology, Tokyo, Japan
- Tensor Learning Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
| | - Qibin Zhao
- Tensor Learning Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
- School of Automation, Guangdong University of Technology, Guangzhou, China
| | - Toshihisa Tanaka
- Department of Electrical Engineering and Computer Science, Tokyo University of Agriculture and Technology, Tokyo, Japan
- Tensor Learning Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
| | - Jordi Solé-Casals
- Data and Signal Processing Research Group, Department of Engineering, University of Vic - Central University of Catalonia, Barcelona, Spain
- Department of Psychiatry, University of Cambridge, Cambridge, United Kingdom
- College of Artificial Intelligence, Nankai University, Tianjin, China
| | - Guoxu Zhou
- School of Automation, Guangdong University of Technology, Guangzhou, China
| | | | | | | | - Jianting Cao
- Tensor Learning Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
- Graduate School of Engineering, Saitama Institute of Technology, Fukaya, Japan
| |
Collapse
|
10
|
Yu Y, Zhou G, Zheng N, Qiu Y, Xie S, Zhao Q. Graph-Regularized Non-Negative Tensor-Ring Decomposition for Multiway Representation Learning. IEEE Trans Cybern 2023; 53:3114-3127. [PMID: 35468067 DOI: 10.1109/tcyb.2022.3157133] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Tensor-ring (TR) decomposition is a powerful tool for exploiting the low-rank property of multiway data and has been demonstrated great potential in a variety of important applications. In this article, non-negative TR (NTR) decomposition and graph-regularized NTR (GNTR) decomposition are proposed. The former equips TR decomposition with the ability to learn the parts-based representation by imposing non-negativity on the core tensors, and the latter additionally introduces a graph regularization to the NTR model to capture manifold geometry information from tensor data. Both of the proposed models extend TR decomposition and can be served as powerful representation learning tools for non-negative multiway data. The optimization algorithms based on an accelerated proximal gradient are derived for NTR and GNTR. We also empirically justified that the proposed methods can provide more interpretable and physically meaningful representations. For example, they are able to extract parts-based components with meaningful color and line patterns from objects. Extensive experimental results demonstrated that the proposed methods have better performance than state-of-the-art tensor-based methods in clustering and classification tasks.
Collapse
|
11
|
Yu J, Zhou G, Sun W, Xie S. Robust to Rank Selection: Low-Rank Sparse Tensor-Ring Completion. IEEE Trans Neural Netw Learn Syst 2023; 34:2451-2465. [PMID: 34478384 DOI: 10.1109/tnnls.2021.3106654] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/04/2023]
Abstract
Tensor-ring (TR) decomposition was recently studied and applied for low-rank tensor completion due to its powerful representation ability of high-order tensors. However, most of the existing TR-based methods tend to suffer from deterioration when the selected rank is larger than the true one. To address this issue, this article proposes a new low-rank sparse TR completion method by imposing the Frobenius norm regularization on its latent space. Specifically, we theoretically establish that the proposed method is capable of exploiting the low rankness and Kronecker-basis-representation (KBR)-based sparsity of the target tensor using the Frobenius norm of latent TR-cores. We optimize the proposed TR completion by block coordinate descent (BCD) algorithm and design a modified TR decomposition for the initialization of this algorithm. Extensive experimental results on synthetic data and visual data have demonstrated that the proposed method is able to achieve better results compared to the conventional TR-based completion methods and other state-of-the-art methods and, meanwhile, is quite robust even if the selected TR-rank increases.
Collapse
|
12
|
Guo Z, Zheng H, Wu H, Zhang J, Zhou G, Long J. Transferable multi-modal fusion in knee angles and gait phases for their continuous prediction. J Neural Eng 2023; 20. [PMID: 37059084 DOI: 10.1088/1741-2552/accd22] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2022] [Accepted: 04/14/2023] [Indexed: 04/16/2023]
Abstract
OBJECTIVE 
The gait phase and joint angle are two essential and complementary components of kinematics during normal walking, whose accurate prediction is critical for lower-limb rehabilitation, such as controlling the exoskeleton robots. Multi-modal signals have been used to promote the prediction performance of the gait phase or joint angle separately, but it is still few reports to examine how these signals can be used to predict both simultaneously. 
Approach.
To address this problem, we propose a new method named transferable multi-modal fusion (TMMF) to perform a continuous prediction of knee angles and corresponding gait phases by fusing multi-modal signals. Specifically, TMMF consists of a multi-modal signal fusion block, a time series feature extractor, a regressor, and a classifier. The multi-modal signal fusion block leverages the Maximum Mean Discrepancy to reduce the distribution discrepancy across different modals in the latent space, achieving the goal of transferable multi-modal fusion. Subsequently, by using the long short-term memory-based network, we obtain the feature representation from time series data to predict the knee angles and gait phases simultaneously. To validate our proposal, we design an experimental paradigm with random walking and resting to collect data containing multi-modal biomedical signals from electromyography, gyroscopes, and virtual reality.
Main results.
Comprehensive experiments on our constructed dataset demonstrate the effectiveness of the proposed method. TMMF achieves a root mean square error of 0.090±0.022 s in knee angle prediction and a precision of 83.7±7.7\% in gait phase prediction.
Significance.
We demonstrate the feasibility and validity of using TMMF to predict lower-limb kinematics continuously from multi-modal biomedical signals. This proposed method represents application potential in predicting the motor intent of patients with different pathologies.
Collapse
Affiliation(s)
- Zhenpeng Guo
- College of Information Science and Technology, Jinan University, 601 Huangpu Avenue West, Guangzhou, 510632, CHINA
| | - Huixian Zheng
- Jinan University, College of Information Science and Technology, 601 Huangpu Avenue West, Guangzhou, Guangdong, 510632, CHINA
| | - Hanrui Wu
- Jinan University, College of Information Science and Technology, 601 Huangpu Avenue West, Guangzhou, 510632, CHINA
| | - Jia Zhang
- Jinan University, No.601, West Huangpu Avenue, Guangzhou, Guangdong, 510632, CHINA
| | - Guoxu Zhou
- Guangdong University of Technology, School of automation, Guangzhou, Guangdong, 510000, CHINA
| | - Jinyi Long
- Jinan University, College of Information Science and Technology, 601 Huangpu Avenue West, Guangzhou, 510632, CHINA
| |
Collapse
|
13
|
Zhou G, Gao D, Dong Y, Wang L, Wang H, Wang X, Linkov V, Wang R. Three-dimensional nickel nanowires modified by amorphous Fe nanosheets as electrocatalyst for oxygen evolution reaction. Dalton Trans 2023; 52:5680-5686. [PMID: 37021656 DOI: 10.1039/d3dt00535f] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/29/2023]
Abstract
The development of electrode materials with abundant active surface sites is important for large-scale hydrogen production by water electrolysis. In this study, Fe/Ni NWs/NF catalysts were prepared by hydrothermal and...
Collapse
Affiliation(s)
- Guoxu Zhou
- State Key Laboratory Base for Eco-Chemical Engineering, College of Chemical Engineering, Qingdao University of Science and Technology, Qingdao, China.
| | - Denghe Gao
- State Key Laboratory Base for Eco-Chemical Engineering, College of Chemical Engineering, Qingdao University of Science and Technology, Qingdao, China.
| | - Yucheng Dong
- State Key Laboratory Base for Eco-Chemical Engineering, College of Chemical Engineering, Qingdao University of Science and Technology, Qingdao, China.
| | - Lan Wang
- Pinghu Normal College, Jiaxing University, Jiaxing, China.
| | - Hui Wang
- State Key Laboratory Base for Eco-Chemical Engineering, College of Chemical Engineering, Qingdao University of Science and Technology, Qingdao, China.
| | - Xuyun Wang
- State Key Laboratory Base for Eco-Chemical Engineering, College of Chemical Engineering, Qingdao University of Science and Technology, Qingdao, China.
| | - Vladimir Linkov
- South African Institute for Advanced Material Chemistry, University of the Western Cape, Cape Town 7535, South Africa
| | - Rongfang Wang
- State Key Laboratory Base for Eco-Chemical Engineering, College of Chemical Engineering, Qingdao University of Science and Technology, Qingdao, China.
| |
Collapse
|
14
|
Zhou Y, Bai F, Li X, Zhou G, Tian X, Li G, Zhang Y, Zhou X, Xu D, Ding Y. Genetic polymorphisms in MIR1208 and MIR5708 are associated with susceptibility to COPD in the Chinese population. Pulmonology 2023; 29:6-12. [PMID: 36115827 DOI: 10.1016/j.pulmoe.2021.07.004] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2020] [Revised: 05/06/2021] [Accepted: 07/24/2021] [Indexed: 01/12/2023] Open
Abstract
BACKGROUND Chronic obstructive pulmonary disease (COPD) is a complex disease characterized by limited airflow and is influenced by genetic and environmental factors. The purpose of this study was to investigate the effects of gene polymorphisms in MIR5708 and MIR1208 on COPD risk. METHODS Four single nucleotide polymorphisms (SNPs) in MIR5708 (rs6473227 and rs16907751) and MIR1208 (rs2608029 and rs13280095) were selected and genotyped among 315 COPD patients and 314 healthy controls using the Agena MassARRAY platform. SPSS 18.0 was used for statistical analysis and data processing. Odds ratios (ORs) and 95% confidence intervals (CIs) were calculated to assess the association between genetic variants of MIR1208 and MIR5708 and COPD risk. RESULTS The results suggested that rs16907751 variants in MIR5708 contributed to an increased susceptibility to COPD in the allelic (P = 0.001), co-dominant (homozygous) (P = 0.001), dominant (P = 0.017), recessive (P = 0.002), and additive (P = 0.002) models. The effects of MIR5708 and MIR1208 gene polymorphisms on the risk of COPD were age-, sex-, smoking status-, and BMI-related. Furthermore, the C-A and G-A haplotypes of rs2608029 and rs13280095 in MIR1208 were identified as risk factors for COPD in the population over 70 years (P = 0.029) and in women (P = 0.049), respectively. Finally, significant associations between rs16907751genotypes with pulse rate and forced expiratory volume in 1 s were found among COPD patients. CONCLUSION Genetic polymorphisms in MIR5708 and MIR1208 are associated with increased risk of COPD in China.
Collapse
Affiliation(s)
- Y Zhou
- Center of Appointment Clinic Service, Hainan General Hospital, Hainan affiliated Hospital of Hainan Medical University, Hainan, China
| | - F Bai
- Department of Science and Education Department, Hainan General Hospital, Hainan affiliated Hospital of Hainan Medical University, Hainan, China
| | - X Li
- Department of General Practice, People's Hospital of Wanning, Hainan, China
| | - G Zhou
- Department of Nursing, People's Hospital of Wanning, Hainan, China
| | - X Tian
- Department of Medical, People's Hospital of Wanning, Hainan, China
| | - G Li
- Department of General Practice, People's Hospital of Wanning, Hainan, China
| | - Y Zhang
- Department of General Practice, Hainan General Hospital, Hainan affiliated Hospital of Hainan Medical University, Hainan, China
| | - X Zhou
- Department of General Practice, Hainan General Hospital, Hainan affiliated Hospital of Hainan Medical University, Hainan, China
| | - D Xu
- Department of Emergency, Hainan General Hospital, Hainan affiliated Hospital of Hainan Medical University, Hainan, China.
| | - Y Ding
- Department of General Practice, Hainan General Hospital, Hainan affiliated Hospital of Hainan Medical University, Hainan, China.
| |
Collapse
|
15
|
Fang X, Jiang K, Han N, Teng S, Zhou G, Xie S. Average Approximate Hashing-Based Double Projections Learning for Cross-Modal Retrieval. IEEE Trans Cybern 2022; 52:11780-11793. [PMID: 34106872 DOI: 10.1109/tcyb.2021.3081615] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
Cross-modal retrieval has attracted considerable attention for searching in large-scale multimedia databases because of its efficiency and effectiveness. As a powerful tool of data analysis, matrix factorization is commonly used to learn hash codes for cross-modal retrieval, but there are still many shortcomings. First, most of these methods only focus on preserving locality of data but they ignore other factors such as preserving reconstruction residual of data during matrix factorization. Second, the energy loss of data is not considered when the data of cross-modal are projected into a common semantic space. Third, the data of cross-modal are directly projected into a unified semantic space which is not reasonable since the data from different modalities have different properties. This article proposes a novel method called average approximate hashing (AAH) to address these problems by: 1) integrating the locality and residual preservation into a graph embedding framework by using the label information; 2) projecting data from different modalities into different semantic spaces and then making the two spaces approximate to each other so that a unified hash code can be obtained; and 3) introducing a principal component analysis (PCA)-like projection matrix into the graph embedding framework to guarantee that the projected data can preserve the main energy of data. AAH obtains the final hash codes by using an average approximate strategy, that is, using the mean of projected data of different modalities as the hash codes. Experiments on standard databases show that the proposed AAH outperforms several state-of-the-art cross-modal hashing methods.
Collapse
|
16
|
Lin Q, Ding K, Zhao R, Wang H, Ren L, Wei Y, Ye Q, Cui Y, He G, Tang W, Feng Q, Zhu D, Chang W, Lv Y, Mao Y, Wang X, Liang L, Zhou G, Liang F, Xu J. 43O Preoperative chemotherapy prior to primary tumor resection for colorectal cancer patients with asymptomatic resectable primary lesion and synchronous unresectable liver-limited metastases (RECUT): A prospective, randomized, controlled, multicenter clinical trial. Ann Oncol 2022. [DOI: 10.1016/j.annonc.2022.10.075] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/07/2022] Open
|
17
|
Zhou G, Murji A, Matelski J, Shapiro J, Shirreff L. 8459 Prevalence, Predictors and Hospital- and Surgeon-Level Variation of Preoperative Anemia: A Multi-Centre Retrospective Study. J Minim Invasive Gynecol 2022. [DOI: 10.1016/j.jmig.2022.09.415] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
18
|
Yang P, Jin Y, Zhou G, Xie X, Jin H, Shi Y. A Prospective Study of Differences in the Incidence of Radiation Pneumonitis in Elderly Patients between Volumetric Arc Modulated Therapy and Step-and-Shoot Intensity-Modulated Radiation Therapy. Int J Radiat Oncol Biol Phys 2022. [DOI: 10.1016/j.ijrobp.2022.07.1562] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
19
|
Zhou G, Zhao MW, Cao YP, Lin JH, Wang WG, Guo A, Tian H. [A multicenter cross-sectional study of quality of life and nonsurgical treatment in patients with knee osteoarthritis]. Zhonghua Yi Xue Za Zhi 2022; 102:2799-2805. [PMID: 36124353 DOI: 10.3760/cma.j.cn112137-20220406-00719] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Objective: To explore the influencing factors of health-related quality of life (HRQoL) in patients with knee osteoarthritis, and to analyze the non-surgical treatment of knee osteoarthritis. Methods: Demographic variables, treatment modalities, imaging data, and 12-item short form health survey (SF-12) scores of patients with knee osteoarthritis in orthopedic outpatient departments of five hospitals in Beijing from December 2017 to November 2018 were collected to analyze influencing factors of HRQoL and non-surgical treatment. Results: A total of 2 034 patients were included. There were 530 males (26.1%) and 1 504 females (73.9%), with a mean age of (59.17±10.22) years. In terms of physical quality of life, female patients with knee osteoarthritis had lower physical components summary (PCS) compared with male patients (β=-0.521, P=0.036); patients aged ≥64 years had lower PCS than those aged<55 years (β=-0.636, P=0.026). Patients with an education of more than 12 years had higher PCS than those with less than 10 years (β=1.063, P<0.001). Compared to patients with mild clinical symptoms, the PCS of patients with moderate clinical symptoms was lower (β=-0.860, P=0.002), while the PCS of those with severe clinical symptoms was much lower (β=-1.126, P<0.001). Patients treated with combination therapy had higher PCS than untreated patients (β=0.731, P=0.005). In terms of mental quality of life, compared to patients engaged in sedentary work, the mental components summary (MCS) of patients engaged in mild manual labor jobs was lower (β=-0.712, P=0.015); Compared to patients with a Charson comorbidity index of 0, patients with a Charlson comorbidity index ≥ 2 had lower MCS (β=-1.183, P=0.007). In the past 12 months, 648 (31.9%), 143 (7.0%), 406 (20.0%), 680 (33.4%), 343 (16.9%), 681 (33.5%), 170 (8.4%) patients had used non-steroid anti-inflammatory drugs (NSAIDs), acetaminophen, glucosamine/chondroitin formulations, physical therapy, articular cavity puncture injection, traditional Chinese medicine treatment and exercise therapy, respectively. Total of 451 patients (22.2%) received monotherapy and 889 patients (43.7%) received combination therapy. Conclusions: The major non-surgical treatment methods for patients with knee osteoarthritis in Beijing are NSAIDs, physiotherapy and traditional Chinese medicine. Combination therapy is used more frequently than monotherapy. Physical quality of life is related to gender, age, education, severity of symptoms and treatment, while mental quality of life is related to occupational labor and comorbidities.
Collapse
Affiliation(s)
- G Zhou
- Department of orthopedics, Peking University Third Hospital, Engineering Research Center of Bone and Joint Precision Medicine, Ministry of Education, Beijing 100191, China
| | - M W Zhao
- Department of orthopedics, Peking University Third Hospital, Engineering Research Center of Bone and Joint Precision Medicine, Ministry of Education, Beijing 100191, China
| | - Y P Cao
- Department of Orthopedics, Peking University First Hospital, Beijing 100034, China
| | - J H Lin
- Department of Orthopedics, Peking University People's Hospital, Beijing 100044, China
| | - W G Wang
- Department of Orthopedics, China-Japan Friendship Hospital, Beijing 100029, China
| | - A Guo
- Department of Orthopedics, Beijing Friendship Hospital, Capital Medical University, Beijing 100050, China
| | - H Tian
- Department of orthopedics, Peking University Third Hospital, Engineering Research Center of Bone and Joint Precision Medicine, Ministry of Education, Beijing 100191, China
| |
Collapse
|
20
|
Qiu Y, Zhou G, Zeng J, Zhao Q, Xie S. Imbalanced low-rank tensor completion via latent matrix factorization. Neural Netw 2022; 155:369-382. [PMID: 36115163 DOI: 10.1016/j.neunet.2022.08.023] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2022] [Revised: 07/31/2022] [Accepted: 08/25/2022] [Indexed: 11/24/2022]
Abstract
Tensor completion has been widely used in computer vision and machine learning. Most existing tensor completion methods empirically assume the intrinsic tensor is simultaneous low-rank in all over modes. However, tensor data recorded from real-world applications may conflict with these assumptions, e.g., face images taken from different subjects often lie in a union of low-rank subspaces, which may result in a quite high rank or even full rank structure in its sample mode. To this aim, in this paper, we propose an imbalanced low-rank tensor completion method, which can flexibly estimate the low-rank incomplete tensor via decomposing it into a mixture of multiple latent tensor ring (TR) rank components. Specifically, each latent component is approximated using low-rank matrix factorization based on TR unfolding matrix. In addition, an effective proximal alternating minimization algorithm is developed and theoretically proved to maintain the global convergence property, that is, the whole sequence of iterates is convergent and converges to a critical point. Extensive experiments on both synthetic and real-world tensor data demonstrate that the proposed method achieves more favorable completion results with less computational cost when compared to the state-of-the-art tensor completion methods.
Collapse
Affiliation(s)
- Yuning Qiu
- School of Automation, Guangdong University of Technology, Guangzhou, 510006, China; Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing and the School of Automation, Guangzhou 510006, China.
| | - Guoxu Zhou
- School of Automation, Guangdong University of Technology, Guangzhou, 510006, China; Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing, Ministry of Education, Guangzhou 510006, China.
| | - Junhua Zeng
- School of Automation, Guangdong University of Technology, Guangzhou, 510006, China; Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing and the School of Automation, Guangzhou 510006, China.
| | - Qibin Zhao
- Tensor Learning Team, RIKEN Center for Advanced Intelligence Project (AIP), Japan; School of Automation, Guangdong University of Technology, Guangzhou, 510006, China.
| | - Shengli Xie
- School of Automation, Guangdong University of Technology, Guangzhou, 510006, China; Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing and the School of Automation, Guangzhou 510006, China.
| |
Collapse
|
21
|
Wen H, Feng Z, H. Ge, Quan C, Zhou X, Yang B, Liu F, Wang J, Y. Wang, J. Zhao, Zhou G, Wen X, Liu Y, Zhu X, Wang G, Zhang Y, Li B, Cai S, Zhang Z, Wu X. 603P Multi-cancer early detection in gynaecological malignancies based on integrating multi-omics assays by liquid biopsy: A prospective study. Ann Oncol 2022. [DOI: 10.1016/j.annonc.2022.07.731] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022] Open
|
22
|
Zhou G, Huang Z. Structure determination of a highly disordered 2D MOF by continuous-rotation electron diffraction method. Acta Cryst Sect A 2022. [DOI: 10.1107/s2053273322090696] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/19/2023]
|
23
|
Zhang Y, Zhou T, Wu W, Xie H, Zhu H, Zhou G, Cichocki A. Improving EEG Decoding via Clustering-Based Multitask Feature Learning. IEEE Trans Neural Netw Learn Syst 2022; 33:3587-3597. [PMID: 33556021 DOI: 10.1109/tnnls.2021.3053576] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
Accurate electroencephalogram (EEG) pattern decoding for specific mental tasks is one of the key steps for the development of brain-computer interface (BCI), which is quite challenging due to the considerably low signal-to-noise ratio of EEG collected at the brain scalp. Machine learning provides a promising technique to optimize EEG patterns toward better decoding accuracy. However, existing algorithms do not effectively explore the underlying data structure capturing the true EEG sample distribution and, hence, can only yield a suboptimal decoding accuracy. To uncover the intrinsic distribution structure of EEG data, we propose a clustering-based multitask feature learning algorithm for improved EEG pattern decoding. Specifically, we perform affinity propagation-based clustering to explore the subclasses (i.e., clusters) in each of the original classes and then assign each subclass a unique label based on a one-versus-all encoding strategy. With the encoded label matrix, we devise a novel multitask learning algorithm by exploiting the subclass relationship to jointly optimize the EEG pattern features from the uncovered subclasses. We then train a linear support vector machine with the optimized features for EEG pattern decoding. Extensive experimental studies are conducted on three EEG data sets to validate the effectiveness of our algorithm in comparison with other state-of-the-art approaches. The improved experimental results demonstrate the outstanding superiority of our algorithm, suggesting its prominent performance for EEG pattern decoding in BCI applications.
Collapse
|
24
|
|
25
|
Abstract
Tensor completion is a fundamental tool for incomplete data analysis, where the goal is to predict missing entries from partial observations. However, existing methods often make the explicit or implicit assumption that the observed entries are noise-free to provide a theoretical guarantee of exact recovery of missing entries, which is quite restrictive in practice. To remedy such drawback, this article proposes a novel noisy tensor completion model, which complements the incompetence of existing works in handling the degeneration of high-order and noisy observations. Specifically, the tensor ring nuclear norm (TRNN) and least-squares estimator are adopted to regularize the underlying tensor and the observed entries, respectively. In addition, a nonasymptotic upper bound of estimation error is provided to depict the statistical performance of the proposed estimator. Two efficient algorithms are developed to solve the optimization problem with convergence guarantee, one of which is specially tailored to handle large-scale tensors by replacing the minimization of TRNN of the original tensor equivalently with that of a much smaller one in a heterogeneous tensor decomposition framework. Experimental results on both synthetic and real-world data demonstrate the effectiveness and efficiency of the proposed model in recovering noisy incomplete tensor data compared with state-of-the-art tensor completion models.
Collapse
|
26
|
Zhang J, Zhou G. [Oral manifestations of sexually transmitted diseases]. Zhonghua Kou Qiang Yi Xue Za Zhi 2022; 57:547-552. [PMID: 35484680 DOI: 10.3760/cma.j.cn112144-20220319-00117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Affiliation(s)
- J Zhang
- Department of Oral Medicine, School and Hospital of Stomatology, Wuhan University, Wuhan 430079, China
| | - G Zhou
- Department of Oral Medicine, School and Hospital of Stomatology, Wuhan University, Wuhan 430079, China
| |
Collapse
|
27
|
Louie E, O’Hara A, Geahlen J, Lawrence J, Latif H, Zhou G. Gene Editing/Gene Therapies: A BREAKTHROUGH GLP AAV-ITR SANGER SEQUENCING SOLUTION FOR NEW DRUG DEVELOPMENT. Cytotherapy 2022. [DOI: 10.1016/s1465-3249(22)00381-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/03/2022]
|
28
|
O’Hara A, Qiu Y, Louie E, Latif H, Mozdzierz C, Zhou G. Gene Editing/Gene Therapies: ADVANCING AAV: NOVEL SEQUENCING SOLUTIONS FOR QUALITY CONTROL IN GENE THERAPY. Cytotherapy 2022. [DOI: 10.1016/s1465-3249(22)00369-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/03/2022]
|
29
|
Stephens M, O’Hara A, DeVito I, Turner L, Mozdzierz C, Latif H, Zhou G. Gene Editing/Gene Therapies: HIGH-THROUGHPUT RNA SEQUENCING DIRECTLY FROM CELL LYSATES ENABLES REPRODUCIBLE PHENOTYPIC PROFILING FOR CRISPR TREATMENT AND CELL RESPONSE SCREENING APPLICATIONS. Cytotherapy 2022. [DOI: 10.1016/s1465-3249(22)00367-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
30
|
Liang L, Zhang Y, Wang D, Yang F, Zhou G. 186P CIP2A modulates PKM2 dimer-tetramer transition through phosphorylation of serine 287 in non-small cell lung cancer. Ann Oncol 2022. [DOI: 10.1016/j.annonc.2022.02.219] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/01/2022] Open
|
31
|
Chen X, Zhou G, Wang Y, Hou M, Zhao Q, Xie S. Accommodating Multiple Tasks' Disparities With Distributed Knowledge-Sharing Mechanism. IEEE Trans Cybern 2022; 52:2440-2452. [PMID: 32649285 DOI: 10.1109/tcyb.2020.3002911] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Deep multitask learning (MTL) shares beneficial knowledge across participating tasks, alleviating the impacts of extreme learning conditions on their performances such as the data scarcity problem. In practice, participators stemming from different domain sources often have varied complexities and input sizes, for example, in the joint learning of computer vision tasks with RGB and grayscale images. For adapting to these differences, it is appropriate to design networks with proper representational capacities and construct neural layers with corresponding widths. Nevertheless, most of the state-of-the-art methods pay little attention to such situations, and actually fail to handle the disparities. To work with the dissimilitude of tasks' network designs, this article presents a distributed knowledge-sharing framework called tensor ring multitask learning (TRMTL), in which the relationship between knowledge sharing and original weight matrices is cut up. The framework of TRMTL is flexible, which is not only capable of sharing knowledge across heterogenous networks but also able to jointly learn tasks with varied input sizes, significantly improving performances of data-insufficient tasks. Comprehensive experiments on challenging datasets are conducted to empirically validate the effectiveness, efficiency, and flexibility of TRMTL in dealing with the disparities in MTL.
Collapse
|
32
|
Fang X, Han N, Zhou G, Teng S, Xu Y, Xie S. Dynamic Double Classifiers Approximation for Cross-Domain Recognition. IEEE Trans Cybern 2022; 52:2618-2629. [PMID: 32667889 DOI: 10.1109/tcyb.2020.3004398] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
In general, existing cross-domain recognition methods mainly focus on changing the feature representation of data or modifying the classifier parameter and their efficiencies are indicated by the better performance. However, most existing methods do not simultaneously integrate them into a unified optimization objective for further improving the learning efficiency. In this article, we propose a novel cross-domain recognition algorithm framework by integrating both of them. Specifically, we reduce the discrepancies in both the conditional distribution and marginal distribution between different domains in order to learn a new feature representation which pulls the data from different domains closer on the whole. However, the data from different domains but the same class cannot interlace together enough and thus it is not reasonable to mix them for training a single classifier. To this end, we further propose to learn double classifiers on the respective domain and require that they dynamically approximate to each other during learning. This guarantees that we finally learn a suitable classifier from the double classifiers by using the strategy of classifier fusion. The experiments show that the proposed method outperforms over the state-of-the-art methods.
Collapse
|
33
|
Wang G, Gao S, Zhou G. 175P Mutations and clinical significance of calcium voltage-gated channel subunit alpha 1E (CACNA1E) in non-small cell lung cancer. Ann Oncol 2022. [DOI: 10.1016/j.annonc.2022.02.208] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/01/2022] Open
|
34
|
Ren Q, Zhou Y, Yan M, Zheng C, Zhou G, Xia X. Imaging-guided percutaneous transthoracic needle biopsy of nodules in the lung base: fluoroscopy CT versus cone-beam CT. Clin Radiol 2022; 77:e394-e399. [DOI: 10.1016/j.crad.2022.02.005] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2021] [Accepted: 02/02/2022] [Indexed: 01/08/2023]
|
35
|
Ji Y, Zhou G. Improving Adversarial Attacks with Ensemble-Based Approaches. ARTIF INTELL 2022. [DOI: 10.1007/978-3-031-20500-2_2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/02/2023]
|
36
|
Qiu Y, Zhou G, Wang Y, Zhang Y, Xie S. A Generalized Graph Regularized Non-Negative Tucker Decomposition Framework for Tensor Data Representation. IEEE Trans Cybern 2022; 52:594-607. [PMID: 32275631 DOI: 10.1109/tcyb.2020.2979344] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Non-negative Tucker decomposition (NTD) is one of the most popular techniques for tensor data representation. To enhance the representation ability of NTD by multiple intrinsic cues, that is, manifold structure and supervisory information, in this article, we propose a generalized graph regularized NTD (GNTD) framework for tensor data representation. We first develop the unsupervised GNTD (UGNTD) method by constructing the nearest neighbor graph to maintain the intrinsic manifold structure of tensor data. Then, when limited must-link and cannot-link constraints are given, unlike most existing semisupervised learning methods that only use the pregiven supervisory information, we propagate the constraints through the entire dataset and then build a semisupervised graph weight matrix by which we can formulate the semisupervised GNTD (SGNTD). Moreover, we develop a fast and efficient alternating proximal gradient-based algorithm to solve the optimization problem and show its convergence and correctness. The experimental results on unsupervised and semisupervised clustering tasks using four image datasets demonstrate the effectiveness and high efficiency of the proposed methods.
Collapse
|
37
|
Wang X, Zhou G, Zeng J, Yang T, Chen J, Li T. Retraction notice: Effect of educational interventions on health in childhood: a meta-analysis of randomized controlled trials [Public Health Volume 164, November 2018, Pages 134-147]. Public Health 2021; 201:125. [PMID: 34895533 DOI: 10.1016/j.puhe.2021.11.024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
This article has been retracted: please see Elsevier Policy on Article Withdrawal (https://www.elsevier.com/about/our-business/policies/article-withdrawal). The article is a duplicate of a paper that has already been published in Medicine, 97 (2018) e11849 https://doi.org/10.1097/MD.0000000000011849. Redundant publications overweigh the relative importance of published findings and distort the academic record of the authors. One of the conditions of submission of a paper for publication is therefore that authors declare explicitly that the paper has not been previously published and is not under consideration for publication elsewhere. As such this article represents a misuse of the scientific publishing system. The scientific community takes a very strong view on this matter and apologies are offered to readers of the journal that this was not detected during the submission process.
Collapse
Affiliation(s)
- X Wang
- Children's Nutrition Research Center, Children's Hospital of Chongqing Medical University, Chongqing 400014, China; Third Affiliated Hospital of Zunyi Medical College, Guizhou 563000, China
| | - G Zhou
- Third Affiliated Hospital of Zunyi Medical College, Guizhou 563000, China
| | - J Zeng
- Children's Nutrition Research Center, Children's Hospital of Chongqing Medical University, Chongqing 400014, China; Ministry of Education Key Laboratory of Child Development and Disorders, Children's Hospital of Chongqing Medical University, Chongqing 400014, China; Chongqing Key Laboratory of Translational Medical Research in Cognitive Development and Learning and Memory Disorders, Chongqing 400014, China
| | - T Yang
- Children's Nutrition Research Center, Children's Hospital of Chongqing Medical University, Chongqing 400014, China; Ministry of Education Key Laboratory of Child Development and Disorders, Children's Hospital of Chongqing Medical University, Chongqing 400014, China; Chongqing Key Laboratory of Translational Medical Research in Cognitive Development and Learning and Memory Disorders, Chongqing 400014, China
| | - J Chen
- Children's Nutrition Research Center, Children's Hospital of Chongqing Medical University, Chongqing 400014, China; Ministry of Education Key Laboratory of Child Development and Disorders, Children's Hospital of Chongqing Medical University, Chongqing 400014, China; Chongqing Key Laboratory of Translational Medical Research in Cognitive Development and Learning and Memory Disorders, Chongqing 400014, China
| | - T Li
- Children's Nutrition Research Center, Children's Hospital of Chongqing Medical University, Chongqing 400014, China; Ministry of Education Key Laboratory of Child Development and Disorders, Children's Hospital of Chongqing Medical University, Chongqing 400014, China; Chongqing Key Laboratory of Translational Medical Research in Cognitive Development and Learning and Memory Disorders, Chongqing 400014, China.
| |
Collapse
|
38
|
An M, Zhou G, Li Y, Xiang T, Ma Y, Liu X, Li X, Zhao S, Zhu M. Characterization of genetic fundamentals for piglet mortality at birth in Yorkshire, Landrace, and Duroc sows. Anim Genet 2021; 53:142-145. [PMID: 34897732 DOI: 10.1111/age.13162] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/24/2021] [Indexed: 11/29/2022]
Abstract
Piglet mortality is an economically important complex trait that impacts sow prolificacy. Genetic analyses for piglet mortality at weaning have been reported in dozens of studies, but not for piglet mortality at birth. In this study, we used multi-breed data sets from Yorkshire, Landrace, and Duroc sows to characterize the genetic fundamentals of piglet mortality at birth. The heritabilities from parity I to III were estimated to be 0.0630, 0.1031, and 0.1140 respectively. By using a combined strategy, a total of 21 SNPs were detected in three parities, of which six were observed in parity I, five in parity II and 10 in parity III. Genome annotation revealed that these SNPs were harbored within or close to 19 candidate genes. The candidate genes were found to associate with the reproductive system and embryonic development in the tissue expression database, which are reasonably related to piglet mortality. These findings are expected to provide much information for understanding the genetic and genomic fundamentals of farrowing mortality.
Collapse
Affiliation(s)
- M An
- Key Lab of Agricultural Animal Genetics, Breeding, and Reproduction of Ministry of Education, Huazhong Agricultural University, Wuhan, 430070, China
| | - G Zhou
- Key Lab of Agricultural Animal Genetics, Breeding, and Reproduction of Ministry of Education, Huazhong Agricultural University, Wuhan, 430070, China
| | - Y Li
- Key Lab of Agricultural Animal Genetics, Breeding, and Reproduction of Ministry of Education, Huazhong Agricultural University, Wuhan, 430070, China
| | - T Xiang
- Key Lab of Agricultural Animal Genetics, Breeding, and Reproduction of Ministry of Education, Huazhong Agricultural University, Wuhan, 430070, China.,The Cooperative Innovation Center for Sustainable Pig Production, Huazhong Agricultural University, Wuhan, 430070, China
| | - Y Ma
- Key Lab of Agricultural Animal Genetics, Breeding, and Reproduction of Ministry of Education, Huazhong Agricultural University, Wuhan, 430070, China.,The Cooperative Innovation Center for Sustainable Pig Production, Huazhong Agricultural University, Wuhan, 430070, China
| | - X Liu
- Key Lab of Agricultural Animal Genetics, Breeding, and Reproduction of Ministry of Education, Huazhong Agricultural University, Wuhan, 430070, China.,The Cooperative Innovation Center for Sustainable Pig Production, Huazhong Agricultural University, Wuhan, 430070, China
| | - X Li
- Key Lab of Agricultural Animal Genetics, Breeding, and Reproduction of Ministry of Education, Huazhong Agricultural University, Wuhan, 430070, China.,The Cooperative Innovation Center for Sustainable Pig Production, Huazhong Agricultural University, Wuhan, 430070, China
| | - S Zhao
- Key Lab of Agricultural Animal Genetics, Breeding, and Reproduction of Ministry of Education, Huazhong Agricultural University, Wuhan, 430070, China.,The Cooperative Innovation Center for Sustainable Pig Production, Huazhong Agricultural University, Wuhan, 430070, China
| | - M Zhu
- Key Lab of Agricultural Animal Genetics, Breeding, and Reproduction of Ministry of Education, Huazhong Agricultural University, Wuhan, 430070, China.,The Cooperative Innovation Center for Sustainable Pig Production, Huazhong Agricultural University, Wuhan, 430070, China
| |
Collapse
|
39
|
Nian Y, Moloney AP, Li C, Allen P, Harrison SM, Prendiville R, Kerry JP, Zhou G. A comparison of meat composition, tenderness and the fatty acid profile of three muscles from Holstein-Friesian bulls from production system resulting in final ages of either <16 or 19 months. Anim Prod Sci 2021. [DOI: 10.1071/an20697] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
Abstract
Context The increased number of male dairy origin calves in Ireland due to the abolition of European Union milk quotas is a potential resource for the beef industry. Rearing these animals as bulls rather than steers is more efficient from a production perspective. Ensuring satisfactory quality of bull beef from dairy origin is essential. Aim To determine the effect of two production systems and three muscle types on physico-chemical characteristics and fatty acid (FA) profile of beef from Holstein-Friesian (HF) bulls. Methods Thirty HF bulls were equally assigned to two production systems, namely, slaughter at under 16 months of age or slaughter at 19 months of age. Longissimus thoracis (LT), Semitendinosus (ST) and Gluteus medius (GM) muscles were excised post-slaughter for determination of pH, colour, Warner–Bratzler (WB) variables, cook loss, chemical composition [intramuscular fat (IMF), moisture, protein, ash], collagen characteristics and FA profile. Results WB variables and cook loss after 14 days postmortem ageing, and insoluble and total collagen contents were higher, while IMF content, redness and saturation at 24 h post-blooming were lower for muscles from the 19-month production system. Muscles from the under 16-month production system had a higher saturated fatty acid (SFA) proportion and n-6:n-3 polyunsaturated fatty acid (PUFA) ratio, while muscle from the 19-month production system had a higher PUFA proportion, n-3 PUFA proportion and PUFA:SFA ratio. The GM muscle had the lowest L* value, followed by LT and ST. Yellowness, saturation and hue angle were greater in ST. LT had lower WB variables, cook loss, moisture, and a higher IMF content than ST and GM. The PUFA proportion and PUFA:SFA ratio were highest in ST, followed by GM and LT. IMF, total FA, SFA and monounsaturated fatty acid (MUFA) concentrations were higher in LT from the under 16-month production system bulls (the interaction). Conclusions Beef from the under 16-month production system compared with beef from the 19-month production system, and LT compared with ST and GM muscles had better quality characteristics. Implications Dairy bulls can produce beef of acceptable quality. The findings will guide selection of the combination of production system and muscle type most appropriate to specific market requirements.
Collapse
|
40
|
Prenen H, Kyi C, Van Lancker G, Patel S, Mittag D, Weaver A, Bol K, Stalbovskaya V, Pulini J, Zhou G, Dong Z, Asatiani E, Hodi F. 136P Phase I dose escalation study of MCLA-145, a bispecific antibody targeting CD137 and PD-L1 in solid tumors. Ann Oncol 2021. [DOI: 10.1016/j.annonc.2021.10.155] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022] Open
|
41
|
Zhou G, Wang Z, Palipana A, Andrinopoulou E, Afonso P, McPhail G, Clancy J, Gecili E, Szczesniak R. 34: Predicting declines in lung function with the U.S. CF registry: Impact of initiating highly effective modulator therapy. J Cyst Fibros 2021. [DOI: 10.1016/s1569-1993(21)01459-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
42
|
Shah S, Yu J, Liu Q, Zhou G, Yan G, Zhou H, Hussain M, Hussain A, Habiba U, Khalid F, Ullah S, Rahim F, Adil M, Zeb U, Ambrin. The Siberian pine growth dynamics in Altai Mountains, China. BRAZ J BIOL 2021; 83:e244011. [PMID: 34468510 DOI: 10.1590/1519-6984.244011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2020] [Accepted: 01/26/2021] [Indexed: 11/21/2022] Open
Abstract
Climatic factors play an essential role in the growth of tree ring width. In this study, we aimed to evaluate the correlation between climatic variables and tree-ring growth characteristics of Pinus sibirica in Altai mountains, northwestern China. This study being is first of its kind on climate growth analysis of Pinus sibirica in northwestern China. The study showed great potential to understand the species growing under the specific climatic conditions. Total of 70 tree cores collected from three sites in the sampling area, out of which 63 tree cores considered for this study. The effect of climatic variables which was studied include precipitation, temperature and PDSI. Our results showed that Tree Ring Width chronology has a significantly positive correlation with the late winter (March) temperature and significant negative correlation with the July temperatures. A significant correlation was observed with the late summer precipitation whereas no significant relation found with the Palmer Drought Severity Index. These significant correlations with temperature and precipitation suggested that this tree species had the potential for the reconstruction of the past climate in the area.
Collapse
Affiliation(s)
- S Shah
- Beijing Forestry University, College of Forestry, Beijing, China.,University of Haripur, Haripur, Khyber Pakhtunkhwa, Pakistan.,Institute of Agriculture Sciences and Forestry, University of Swat. Khyber Pakhtunkhwa, Pakistan
| | - J Yu
- School of Landscape Architecture, Jiangsu Vocational College of Agriculture and Forestry, Jurong, Jiangsu, China
| | - Q Liu
- Beijing Forestry University, College of Forestry, Beijing, China
| | - G Zhou
- Jiangxi Academy of Forestry, Nanchang, China
| | - G Yan
- Forestry Survey and Planning, Institute of Guizhou, Province Guiyang, China
| | - H Zhou
- Guizhou Academy of Forestry, No. 32, Fuyuan South Road Nanming District, Guiyang, China
| | - M Hussain
- University of Haripur, Haripur, Khyber Pakhtunkhwa, Pakistan
| | - A Hussain
- University of Haripur, Haripur, Khyber Pakhtunkhwa, Pakistan
| | - U Habiba
- University of Haripur, Haripur, Khyber Pakhtunkhwa, Pakistan
| | - F Khalid
- University of Haripur, Haripur, Khyber Pakhtunkhwa, Pakistan
| | - S Ullah
- Shaheed Benazir Bhutto University, Department of Forestry, Khyber Pakhtunkhwa, Pakistan
| | - F Rahim
- Department of Botany, Bacha Khan University Charsadda, Khyber Pakhtunkhwa, Pakistan
| | - M Adil
- Department of Chemical and Life Sciences, Qurtaba University of Science and information technology Peshawar, Pakistan
| | - U Zeb
- University of Haripur, Haripur, Khyber Pakhtunkhwa, Pakistan
| | - Ambrin
- Hadaf College, Punjab Group of Colleges, Khyber Pakhtunkhwa, Pakistan
| |
Collapse
|
43
|
Bongioví G, Häußler A, Giambrone S, Catanzaro I, Forte R, Zhou G, Di Maio P. Structural assessment of a whole toroidal sector of the HELIAS 5-B breeding blanket. Fusion Engineering and Design 2021. [DOI: 10.1016/j.fusengdes.2021.112618] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
44
|
Zhou X, Shafique K, Sajid M, Ali Q, Khalili E, Javed MA, Haider MS, Zhou G, Zhu G. Era-like GTP protein gene expression in rice. BRAZ J BIOL 2021; 82:e250700. [PMID: 34259718 DOI: 10.1590/1519-6984.250700] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2021] [Accepted: 06/19/2021] [Indexed: 11/22/2022] Open
Abstract
The mutations are genetic changes in the genome sequences and have a significant role in biotechnology, genetics, and molecular biology even to find out the genome sequences of a cell DNA along with the viral RNA sequencing. The mutations are the alterations in DNA that may be natural or spontaneous and induced due to biochemical reactions or radiations which damage cell DNA. There is another cause of mutations which is known as transposons or jumping genes which can change their position in the genome during meiosis or DNA replication. The transposable elements can induce by self in the genome due to cellular and molecular mechanisms including hypermutation which caused the localization of transposable elements to move within the genome. The use of induced mutations for studying the mutagenesis in crop plants is very common as well as a promising method for screening crop plants with new and enhanced traits for the improvement of yield and production. The utilization of insertional mutations through transposons or jumping genes usually generates stable mutant alleles which are mostly tagged for the presence or absence of jumping genes or transposable elements. The transposable elements may be used for the identification of mutated genes in crop plants and even for the stable insertion of transposable elements in mutated crop plants. The guanine nucleotide-binding (GTP) proteins have an important role in inducing tolerance in rice plants to combat abiotic stress conditions.
Collapse
Affiliation(s)
- X Zhou
- Linyi University, College of Life Science, Linyi, Shandong, China
| | - K Shafique
- Government Sadiq College Women University, Department of Botany, Bahawalpur, Pakistan
| | - M Sajid
- University of Okara, Faculty of Life Sciences, Department of Biotechnology, Okara, Pakistan
| | - Q Ali
- University of Lahore, Institute of Molecular Biology and Biotechnology, Lahore, Pakistan
| | - E Khalili
- Tarbiat Modarres University, Faculty of Science, Department of Plant Science, Tehran, Iran
| | - M A Javed
- University of the Punjab Lahore, Department of Plant Breeding and Genetics, Lahore, Pakistan
| | - M S Haider
- University of the Punjab Lahore, Department of Plant Pathology, Lahore, Pakistan
| | - G Zhou
- Yangzhou University, The Ministry of Education of China, Joint International Research Laboratory of Agriculture and Agri-Product Safety, Yangzhou, Jiangsu, China
| | - G Zhu
- Yangzhou University, The Ministry of Education of China, Joint International Research Laboratory of Agriculture and Agri-Product Safety, Yangzhou, Jiangsu, China
| |
Collapse
|
45
|
Yu J, Zhou G, Li C, Zhao Q, Xie S. Low Tensor-Ring Rank Completion by Parallel Matrix Factorization. IEEE Trans Neural Netw Learn Syst 2021; 32:3020-3033. [PMID: 32749967 DOI: 10.1109/tnnls.2020.3009210] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Tensor-ring (TR) decomposition has recently attracted considerable attention in solving the low-rank tensor completion (LRTC) problem. However, due to an unbalanced unfolding scheme used during the update of core tensors, the conventional TR-based completion methods usually require a large TR rank to achieve the optimal performance, which leads to high computational cost in practical applications. To overcome this drawback, we propose a new method to exploit the low TR-rank structure in this article. Specifically, we first introduce a balanced unfolding operation called tensor circular unfolding, by which the relationship between TR rank and the ranks of tensor unfoldings is theoretically established. Using this new unfolding operation, we further propose an algorithm to exploit the low TR-rank structure by performing parallel low-rank matrix factorizations to all circularly unfolded matrices. To tackle the problem of nonuniform missing patterns, we apply a row weighting trick to each circularly unfolded matrix, which significantly improves the adaptive ability to various types of missing patterns. The extensive experiments have demonstrated that the proposed algorithm can achieve outstanding performance using a much smaller TR rank compared with the conventional TR-based completion algorithms; meanwhile, the computational cost is reduced substantially.
Collapse
|
46
|
Jiao Y, Zhou T, Yao L, Zhou G, Wang X, Zhang Y. Multi-View Multi-Scale Optimization of Feature Representation for EEG Classification Improvement. IEEE Trans Neural Syst Rehabil Eng 2021; 28:2589-2597. [PMID: 33245696 DOI: 10.1109/tnsre.2020.3040984] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
Effectively extracting common space pattern (CSP) features from motor imagery (MI) EEG signals is often highly dependent on the filter band selection. At the same time, optimizing the EEG channel combinations is another key issue that substantially affects the SMR feature representations. Although numerous algorithms have been developed to find channels that record important characteristics of MI, most of them select channels in a cumbersome way with low computational efficiency, thereby limiting the practicality of MI-based BCI systems. In this study, we propose the multi-scale optimization (MSO) of spatial patterns, optimizing filter bands over multiple channel sets within CSPs to further improve the performance of MI-based BCI. Specifically, several channel subsets are first heuristically predefined, and then raw EEG data specific to each of these subsets bandpass-filtered at the overlap between a set of filter bands. Further, instead of solving learning problems for each channel subset independently, we propose a multi-view learning based sparse optimization to jointly extract robust CSP features with L2,1 -norm regularization, aiming to capture the shared salient information across multiple related spatial patterns for enhanced classification performance. A support vector machine (SVM) classifier is then trained on these optimized EEG features for accurate recognition of MI tasks. Experimental results on three public EEG datasets validate the effectiveness of MSO compared to several other competing methods and their variants. These superior experimental results demonstrate that the proposed MSO method has promising potential in MI-based BCIs.
Collapse
|
47
|
Webster PJ, Tavangar Ranjbar N, Turner J, El-Sharkawi A, Zhou G, Chitsabesan P. Outcomes following emergency colorectal cancer presentation in the elderly. Colorectal Dis 2020; 22:1924-1932. [PMID: 32609919 DOI: 10.1111/codi.15229] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/19/2020] [Accepted: 05/21/2020] [Indexed: 02/08/2023]
Abstract
AIM Colorectal cancer is predominantly a disease of the elderly and up to 30% of these patients will present as an emergency. We compared the outcomes of 'elderly' patients presenting to our unit with a colorectal cancer emergency over a 10-year period with those of a 'younger' cohort. METHODS A single centre retrospective review of colorectal cancer emergencies between 1 April 2007 and 1 April 2017 was performed. Patients were separated into two cohorts: 'young' (< 75 years) and 'elderly' (≥ 75 years). Data collected included demographics, disease status, treatment and outcomes. RESULTS A total of 341 patients (< 75 years: n = 154; ≥ 75 years: n = 187) presented as a colorectal cancer emergency. Significantly fewer 'elderly' patients underwent curative surgical procedures (72% vs 49%, P < 0.0001) or received adjuvant chemotherapy (56% vs 21%, P < 0.0001). 'Elderly' patients had significantly more postoperative cardio-respiratory complications (7% vs 36%, P < 0.0001), but despite this there was no significant difference in 30-day mortality (7% vs 12%) and survival rates at 1 year (75% vs 74%) or 3 years (56% vs 49%). Elderly patients treated with best supportive care had a median overall survival of just 62 (range 1-955) days. CONCLUSION Patients ≥ 75 years presenting as a colorectal cancer emergency were significantly less likely to undergo emergency curative surgery or receive adjuvant chemotherapy than those < 75 years. However, the 30-day mortality, 1- and 3-year survival rates for patients undergoing curative surgery were comparable.
Collapse
Affiliation(s)
- P J Webster
- Department of Colorectal Surgery, York Teaching Hospital, York, UK
| | | | - J Turner
- Department of Colorectal Surgery, York Teaching Hospital, York, UK
| | - A El-Sharkawi
- Department of Colorectal Surgery, York Teaching Hospital, York, UK
| | - G Zhou
- Department of Colorectal Surgery, York Teaching Hospital, York, UK
| | - P Chitsabesan
- Department of Colorectal Surgery, York Teaching Hospital, York, UK
| |
Collapse
|
48
|
Mu L, Liu J, Zhou G, Wu C, Chen B, Lu Y, Lu J, Yan X, Zhu Z, Nasir K, Spatz E, Krumholz H, Zheng X. Obesity prevalence and risks among Chinese adults: findings from China PEACE Million Persons Project, 2014–2018. Eur Heart J 2020. [DOI: 10.1093/ehjci/ehaa946.3034] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
Abstract
Abstract
Background
With demographic and epidemiologic transitions, China has become home to the greatest number of obese individuals in the world. Effective policy intervention requires a contemporary assessment of obesity across broad socio-demographic subgroups.
Purpose
We aim to assess the prevalence of overall and abdominal obesity by socio-demographic characteristics and the associations of these characteristics with obesity in China.
Methods
Using the data of 2.7-million community-dwelling participants aged 35–75 years in the China PEACE Million Persons Project, a nationwide cross-sectional screening project from 2014 to 2018, we calculated the prevalence of overall and abdominal obesity based on national guideline definitions (body mass index ≥28 kg/m2, waist circumference ≥85/90 cm for women/men). We examined 12 available socio-demographic variables that are potentially associated with obesity, in addition to self-reported co-morbidities, and quantified the associations of these socio-demographic characteristics with obesity using multivariable mixed models.
Results
The prevalence of overall and abdominal obesity were 15.8% and 37.6% in women and 15.0% and 36.3% in men (Figure). Compared to individuals with normal weight, those with overall obesity had a higher prevalence of hypertension, dyslipidemia, and diabetes (in women: by 30.4, 16.1, and 6.0 percent points; in men, by 29.9, 31.2, and 5.8 percent points). A similar pattern was observed with abdominal obesity. In women, those aged 55–64 years constituted the largest age group with overall and abdominal obesity (33.7% and 35.0%), while in men, those aged 45–54 and 55–64 years constituted the largest age group with overall obesity (30.4%) and abdominal obesity (30.5%), respectively. Older women were at substantially higher risk for obesity (e.g., adjusted relative risk [95% CI] of women aged 65–75 vs. 35–44 years: 1.29 [1.27–1.31] for overall obesity and 1.76 [1.74–1.77] for abdominal obesity) while older men were not. Higher education was associated with lower risk in women (e.g., those with college or university education vs. less than primary school: 0.47 [0.46–0.48] for overall obesity and 0.61 [0.60–0.62] for abdominal obesity) but higher risk in men (1.07 [1.05–1.10] and 1.17 [1.16–1.19]). In both women and men, current smoking was associated with lower risk for obesity, and current drinking was associated with higher risk, but the magnitude of associations was smaller in women than men.
Conclusions
In China, over one in seven individuals meet criteria for overall obesity, and one in three for abdominal obesity. Wide variation exists across socio-demographic subgroups. The associations of age and education with obesity are significant and differ by sex. Understanding obesity in contemporary China has broad domestic policy implications and provides a valuable international reference.
Figure 1
Funding Acknowledgement
Type of funding source: Other. Main funding source(s): The National Key Research and Development Program from the Ministry of Science and Technology of China, the CAMS Innovation Fund for Medical Science
Collapse
Affiliation(s)
- L Mu
- Yale New Haven Hospital, New Haven, United States of America
| | - J Liu
- Fuwai Hospital, CAMS&PUMC, National Center for Cardiovascular Diseases, Beijing, China
| | - G Zhou
- Yale New Haven Hospital, New Haven, United States of America
| | - C Wu
- Fuwai Hospital, CAMS&PUMC, National Center for Cardiovascular Diseases, Beijing, China
| | - B Chen
- Fuwai Hospital, CAMS&PUMC, National Center for Cardiovascular Diseases, Beijing, China
| | - Y Lu
- Yale New Haven Hospital, New Haven, United States of America
| | - J Lu
- Fuwai Hospital, CAMS&PUMC, National Center for Cardiovascular Diseases, Beijing, China
| | - X Yan
- Fuwai Hospital, CAMS&PUMC, National Center for Cardiovascular Diseases, Beijing, China
| | - Z Zhu
- Fuwai Hospital, CAMS&PUMC, National Center for Cardiovascular Diseases, Beijing, China
| | - K Nasir
- Yale New Haven Hospital, New Haven, United States of America
| | - E.S Spatz
- Yale New Haven Hospital, New Haven, United States of America
| | - H.M Krumholz
- Yale New Haven Hospital, New Haven, United States of America
| | - X Zheng
- Fuwai Hospital, CAMS&PUMC, National Center for Cardiovascular Diseases, Beijing, China
| |
Collapse
|
49
|
Han N, Wu J, Fang X, Teng S, Zhou G, Xie S, Li X. Projective Double Reconstructions Based Dictionary Learning Algorithm for Cross-Domain Recognition. IEEE Trans Image Process 2020; PP:9220-9233. [PMID: 32970596 DOI: 10.1109/tip.2020.3024728] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Dictionary learning plays a significant role in the field of machine learning. Existing works mainly focus on learning dictionary from a single domain. In this paper, we propose a novel projective double reconstructions (PDR) based dictionary learning algorithm for cross-domain recognition. Owing the distribution discrepancy between different domains, the label information is hard utilized for improving discriminability of dictionary fully. Thus, we propose a more flexible label consistent term and associate it with each dictionary item, which makes the reconstruction coefficients have more discriminability as much as possible. Due to the intrinsic correlation between cross-domain data, the data should be reconstructed with each other. Based on this consideration, we further propose a projective double reconstructions scheme to guarantee that the learned dictionary has the abilities of data itself reconstruction and data crossreconstruction. This also guarantees that the data from different domains can be boosted mutually for obtaining a good data alignment, making the learned dictionary have more transferability. We integrate the double reconstructions, label consistency constraint and classifier learning into a unified objective and its solution can be obtained by proposed optimization algorithm that is more efficient than the conventional l1 optimization based dictionary learning methods. The experiments show that the proposed PDR not only greatly reduces the time complexity for both training and testing, but also outperforms over the stateof- the-art methods.
Collapse
|
50
|
Zhou G, Hu W, Pei H, Chen H, Hei TK. Recent progress on the Chinese space programme and radiation research. Ann ICRP 2020; 49:213-216. [PMID: 32734778 DOI: 10.1177/0146645320940828] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Manned space exploration was initiated in China in 1992, and substantial progress has been made. The next step is to build the Chinese Space Station (CSS), which is planned to be launched in 2020. The CSS will provide an on-orbit laboratory for experimental studies including space radiation research. The health risk of space radiation, especially carcinogenesis, is a major concern for long-term space exploration. Establishing a risk assessment system suitable for Chinese astronauts and developing effective countermeasures are major tasks for Chinese space radiobiologists. The Institute of Space Life Sciences, Soochow University has focused on these topics for years. We established cancer models with low-dose-rate exposure of alpha particles, and elucidated a microRNA-TGFβ network regulating bystander effects and a lncRNA-cytoskeleton network regulating genomic instability induced by ionising radiation. We also confirmed the radioresistance of quiescent cells, which inspires a potential strategy to improve individual radioresistance during long-term space travel. However, we believe that a multi-disciplinary strategy must be developed to protect astronauts from highly energised space radiation.
Collapse
Affiliation(s)
- G Zhou
- State Key Laboratory of Radiation Medicine and Protection, School of Radiation Medicine and Protection, Institute of Life Sciences in Space, Medical College of Soochow University, Suzhou 215123, China; e-mail: .,Collaborative Innovation Centre of Radiation Medicine of Jiangsu Higher Education Institutions, Soochow University, China
| | - W Hu
- State Key Laboratory of Radiation Medicine and Protection, School of Radiation Medicine and Protection, Institute of Life Sciences in Space, Medical College of Soochow University, Suzhou 215123, China; e-mail: .,Collaborative Innovation Centre of Radiation Medicine of Jiangsu Higher Education Institutions, Soochow University, China
| | - H Pei
- State Key Laboratory of Radiation Medicine and Protection, School of Radiation Medicine and Protection, Institute of Life Sciences in Space, Medical College of Soochow University, Suzhou 215123, China; e-mail: .,Collaborative Innovation Centre of Radiation Medicine of Jiangsu Higher Education Institutions, Soochow University, China
| | - H Chen
- State Key Laboratory of Radiation Medicine and Protection, School of Radiation Medicine and Protection, Institute of Life Sciences in Space, Medical College of Soochow University, Suzhou 215123, China; e-mail: .,Collaborative Innovation Centre of Radiation Medicine of Jiangsu Higher Education Institutions, Soochow University, China
| | - T K Hei
- Columbia University Medical Center, USA
| |
Collapse
|