Subspace Regularized Sparse Multitask Learning for Multiclass Neurodegenerative Disease Identification

Zhu, Xiaofeng,Suk, Heung-Il,Lee, Seong-Whan,Shen, Dinggang IEEE 2016 IEEE Transactions on Biomedical Engineering Vol.63 No.3

<P>The high feature-dimension and low sample-size problem is one of the major challenges in the study of computer-aided Alzheimer's disease (AD) diagnosis. To circumvent this problem, feature selection and subspace learning have been playing core roles in the literature. Generally, feature selection methods are preferable in clinical applications due to their ease for interpretation, but subspace learning methods can usually achieve more promising results. In this paper, we combine two different methodological approaches to discriminative feature selection in a unified framework. Specifically, we utilize two subspace learning methods, namely, linear discriminant analysis and locality preserving projection, which have proven their effectiveness in a variety of fields, to select class-discriminative and noise-resistant features. Unlike previous methods in neuroimaging studies that mostly focused on a binary classification, the proposed feature selection method is further applicable for multiclass classification in AD diagnosis. Extensive experiments on the Alzheimer's disease neuroimaging initiative dataset showed the effectiveness of the proposed method over other state-of-the-art methods.</P>

Enhanced room-temperature HCHO decomposition activity of highly-dispersed Pt/Al2O3 hierarchical microspheres with exposed {110} facets

Xiaofeng Zhu,Jiaguo Yu,Chuanjia Jiang,Bei Cheng 한국공업화학회 2017 Journal of Industrial and Engineering Chemistry Vol.45 No.-

Formaldehyde (HCHO) catalytic decomposition at room temperature is an important method for HCHOremoval in indoor environment. Herein,flower-like g-Al2O3 microspheres with high specific surface area,special textural structure, and abundant surface defects were prepared through a one-pot hydrothermalmethod by using aluminum foil as Al source. And it was used as oxide support to prepare highly-dispersed Pt catalyst (Pt/Al2O3). Compared with Pt supported on commercial g-Al2O3, the as-prepared Pt/Al2O3 showed enhanced catalytic activity for HCHO decomposition at room temperature. This workprovides new insights into designing and fabricating highly-dispersed Pt catalysts for efficient indoor airpurification.

Discriminative self-representation sparse regression for neuroimaging-based alzheimer’s disease diagnosis

Zhu, Xiaofeng,Suk, Heung-Il,Lee, Seong-Whan,Shen, Dinggang SPRINGER SCIENCE AND BUSINESS MEDIA 2019 BRAIN IMAGING AND BEHAVIOR Vol.13 No.1

A novel relational regularization feature selection method for joint regression and classification in AD diagnosis

Zhu, Xiaofeng,Suk, Heung-Il,Wang, Li,Lee, Seong-Whan,Shen, Dinggang Elsevier 2017 Medical image analysis Vol.38 No.-

<P><B>Abstract</B></P> <P>In this paper, we focus on joint regression and classification for Alzheimer’s disease diagnosis and propose a new feature selection method by embedding the relational information inherent in the observations into a sparse multi-task learning framework. Specifically, the relational information includes three kinds of relationships (such as feature-feature relation, response–response relation, and sample-sample relation), for preserving three kinds of the similarity, such as for the features, the response variables, and the samples, respectively. To conduct feature selection, we first formulate the objective function by imposing these three relational characteristics along with an ℓ<SUB>2,1</SUB>-norm regularization term, and further propose a computationally efficient algorithm to optimize the proposed objective function. With the dimension-reduced data, we train two support vector regression models to predict the clinical scores of ADAS-Cog and MMSE, respectively, and also a support vector classification model to determine the clinical label. We conducted extensive experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset to validate the effectiveness of the proposed method. Our experimental results showed the efficacy of the proposed method in enhancing the performances of both clinical scores prediction and disease status identification, compared to the state-of-the-art methods.</P> <P><B>Highlights</B></P> <P> <UL> <LI> A novel graph feature selection method for the AD/MCI diagnosis. </LI> <LI> A novel regularization exploiting the relational information inherent in the observations. </LI> <LI> First work considering three relationships for joint classification and regression. </LI> <LI> High accuracy of 95.7% for AD classification and 79.9% for MCI classification. </LI> </UL> </P> <P><B>Graphical abstract</B></P> <P>[DISPLAY OMISSION]</P>

A Continuous Regional Current-Voltage Model for Short-channel Double-gate MOSFETs

Zhu Zhaomin,Yan Dawei,Xu Guoqing,Peng Yong,Gu Xiaofeng 대한전자공학회 2013 Journal of semiconductor technology and science Vol.13 No.3

A continuous, explicit drain-current equation for short-channel double-gate (DG) MOSFETs has been derived based on the explicit surface potential equation. The model is physically derived from Poisson’s equation in each region of operation and adopted in the unified regional approach. The proposed model has been verified with numerical solutions, physically scalable with channel length and gate/oxide materials as well as oxide/channel thicknesses.

Transcriptome analysis of colchicine-induced tetraploid Kiwifruit leaves with increased biomass and cell size

Zhu Yanyan,Tang Wei,Tang Xiaofeng,Wang Lihuan,Li Wei,Zhang Qian,Li Mingzhang,Fang Congbing,Liu Yongsheng,Wang Songhu 한국식물생명공학회 2021 Plant biotechnology reports Vol.15 No.5

Colchicine-induced polyploidization has been extensively utilized in plant-breeding programs to increase biomass and overall yield of various crop species. Chromosome doubling usually increases the plant size and cell size. However, the underly- ing mechanisms remain elusive. In this study, we showed that 0.1% colchicine is an optimized concentration for inducing tetraploidization of Actinidia chinensis var. chinensis ‘Hongyang’, a commercially important diploid kiwifruit cultivar. The tetraploid plants showed increased plant height, leaf size, and biomass, as compared with the corresponding diploid plants. Scanning electron microscopy and histological analysis indicated that the leaf cell size was significantly increased in the tetraploid plants. Our further transcriptome analysis revealed the 5922 differentially expressed genes between the diploid and tetraploid plants. Gene Ontology analysis enriched the cell wall-related genes, including the pectin methylesterases (PMEs) and expansins (EXPs), both of which play a critical role in cell wall loosening and extension. The increased expression of PME and EXP genes might contribute to the increased cell size in the tetraploid plants. Together, our work indicated that tetraploidization increases the organ and cell size in kiwifruit, possibly by enhancing the cell wall extensibility.

Inhibiting N-Cadherin-Mediated Adhesion Affects Gap Junction Communication in Isolated Rat Hearts

Zhu, Hongjun,Wang, Hegui,Zhang, Xiwen,Hou, Xiaofeng,Cao, Kejiang,Zou, Jiangang Korean Society for Molecular and Cellular Biology 2010 Molecules and cells Vol.30 No.3

Cadherin-mediated adherens junctions is impaired concomitant with a decrease in connexin 43 (Cx43) in diseases or pathological processes. We have investigated the acute effects of adherens junction impairment in isolated rat hearts by introducing Ala-His-Ala-Val-Asp-$NH_2$ (AHAVD, a synthetic peptide) as a specific inhibitor of N-cadherin. Effect of AHAVD on N-cadherin mediated adhension was analyzed by Cardiomy-ocyte aggregation assay. Laser confocal microscopy showed disrupted cell-cell contacts in cultured neonatal cardiomyocytes co-incubated with 0.2 mM AHAVD. In isolated adult rat hearts, Cx43 was redistributed along the bilateral of cardiomyocytes from the intercalated discs and significant dephosphorylation of Cx43 on serine368 occurred concomitantly with decreased gap junction (GJ) function in dose dependent manner after 1 h perfusion with AHAVD. These results indicate that impairing cad-herin-mediated adhesion by AHAVD rapidly results in Cx43 redistribution and dephosphorylation of serine368, thereby impairing GJ communication function.

Inhibiting N-Cadherin-Mediated Adhesion Affects Gap Junction Communication in Isolated Rat Hearts

Hongjun Zhu,Hegui Wang,Xiwen Zhang,Xiaofeng Hou,Kejiang Cao,Jiangang Zou 한국분자세포생물학회 2010 Molecules and cells Vol.30 No.3

Cadherin-mediated adherens junctions is impaired conco-mitant with a decrease in connexin 43 (Cx43) in diseases or pathological processes. We have investigated the acute effects of adherens junction impairment in isolated rat hearts by introducing Ala-His-Ala-Val-Asp-NH2 (AHAVD, a synthetic peptide) as a specific inhibitor of N-cadherin. Effect of AHAVD on N-cadherin mediated adhension was analyzed by Cardiomy-ocyte aggregation assay. Laser confocal microscopy showed disrupted cell-cell contacts in cultured neonatal cardiomyocytes co-incubated with 0.2 mM AHAVD. In isolated adult rat hearts, Cx43 was redis-tributed along the bilateral of cardiomyocytes from the intercalated discs and significant dephosphorylation of Cx43 on serine368 occurred concomitantly with decreased gap junction (GJ) function in dose dependent manner after 1 h perfusion with AHAVD. These results indicate that im-pairing cad-herin-mediated adhesion by AHAVD rapidly results in Cx43 redistribution and dephosphorylation of serine368, thereby impairing GJ communication function.

Electrochemical Determination of Artemisinin Using a Multi-wall Carbon Nanotube Film-modified Electrode

Yang, Xiaofeng,Gan, Tian,Zheng, Xiaojiang,Zhu, Dazhai,Wu, Kangbing Korean Chemical Society 2008 Bulletin of the Korean Chemical Society Vol.29 No.7

Artemisinin, the effective ingredient of Chinese herb Artemisia annua L (Qinghao in Chinese), has been proved to be effective to antimalarial. Herein, a reliable, sensitive and convenient electrochemical method was developed for the determination of artemisinin utilizing the excellent properties of multi-wall carbon nanotube (MWNT). The electrochemical behavior of artemisinin was investigated. It is found that the reduction peak current of artemisinin remarkably increases and the peak potential shifts positively by 240 mV at the MWNT film-modified electrode. These phenomena indicate that the MWNT film exhibits efficient catalytic activity to the electrochemical reduction of artemisinin. The effects of pH value, amount of MWNT, scan rate and accumulation time were examined. The limit of detection (S/N = 3) is as low as 10 $\mu$ g $L^{-1}$. Finally, this newly developed method was used to determine the content of artemisinin in Artemisia annua L.

Thermal error prediction of motorized spindle for five-axis machining center based on analytical modeling and BP neural network

Yang Liu,Xiaofeng Wang,Xiaogang Zhu,Ying Zhai 대한기계학회 2021 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.35 No.1

To ensure the stability of precision of the motorized spindle for five-axis machining center, the thermal error of five-axis machining center was investigated, and the temperature rise-thermal deformation model of a thin-wall ring type rotary elastomer was built on the basis of thermo-elastic property. Thus, a model of radial thermal error was con-structed. The relationship between radial error and axial error was also investigated in this paper and the total radial errors were gotten. In addition, the thermal error of the motorized spindle of five-axis machining center was measured by the ball bar in the experiment of thermal error. The motorized spindle total radial error was achieved by this experiment and radial total error analytical model. Finally, a BP neural network algorithm was introduced for thermal error prediction of five-axis machining center, and the precision of prediction of these models was compared and analyzed. The analysis shows that this method is practical and effective.