Creat membership Creat membership
Sign in

Forgot password?

Confirm
  • Forgot password?
    Sign Up
  • Confirm
    Sign In
home > search

Now showing items 1 - 16 of 173

  • Recognizing lung cancer using a homemade e-nose: A comprehensive study

    Li, Wang   Jia, Ziru   Xie, Dandan   Chen, Ke   Cui, Jianguo   Liu, Hongying  

    In recent years, breath analysis has been used as a tool for lung cancer detection and many gas sensors were developed for this purpose. Although they are fabricated with advanced materials, for now, gas sensors are still limited in their medical application due to their unfavorable performance. Here, we hypothesized that a combination of diverse types of sensors could aid in improving the detection performance. We fabricated an e-nose based on 10 gas sensors of 4 types and directly tested it using samples from 153 healthy participants and 115 lung cancer patients, without gas pre-concentration. Additionally, we studied and compared five feature extraction algorithms. The extracted features were then used in 2 optimized clustering algorithms and 3 supervised classification strategies, and their performance was investigated. As a result, "breath-prints" for all subjects were successfully obtained. The combined features extracted by LDA and Fast ICA formed the best feature space. Within this feature space, both clustering algorithms grouped all "breath-prints" into exactly 2 clusters with an Adjusted Rand Index greater than 0.95. Among the 3 supervised classification strategies, random forest with 3-fold cross validation showed the best performance with 86.42% of mean classification accuracy and 0.87 of AUC, which was somewhat better than many recently reported sensor arrays. It can be concluded that, the diversity of sensors may play a role in improving the performance of the e-nose though to what extent still requires evaluation.
    Download Collect
  • VR-SGD:A Simple Stochastic Variance Reduction Method for Machine Learning

    Shang, Fanhua   Zhou, Kaiwen   Liu, Hongying   Cheng, James   Tsang, Ivor W.   Zhang, Lijun   Tao, Dacheng   Jiao, Licheng  

    In this paper, we propose a simple variant of the original SVRG, called variance reduced stochastic gradient descent (VR-SGD). Unlike the choices of snapshot and starting points in SVRG and its proximal variant, Prox-SVRG, the two vectors of VR-SGD are set to the average and last iterate of the previous epoch, respectively. The settings allow us to use much larger learning rates, and also make our convergence analysis more challenging. We also design two different update rules for smooth and non-smooth objective functions, respectively, which means that VR-SGD can tackle non-smooth and/or non-strongly convex problems directly without any reduction techniques. Moreover, we analyze the convergence properties of VR-SGD for strongly convex problems, which show that VR-SGD attains linear convergence. Different from most algorithms that have no convergence guarantees for non-strongly convex problems, we also provide the convergence guarantees of VR-SGD for this case, and empirically verify that VR-SGD with varying learning rates achieves similar performance to its momentum accelerated variant that has the optimal convergence rate $\mathcal {O}(1/T<^>2)$O(1/T2). Finally, we apply VR-SGD to solve various machine learning problems, such as convex and non-convex empirical risk minimization, and leading eigenvalue computation. Experimental results show that VR-SGD converges significantly faster than SVRG and Prox-SVRG, and usually outperforms state-of-the-art accelerated methods, e.g., Katyusha.
    Download Collect
  • Semisupervised PolSAR Image Classification Based on Improved Cotraining

    Hua, Wenqiang   Wang, Shuang   Liu, Hongying   Liu, Kun   Guo, Yanhe   Jiao, Licheng  

    In order to obtain good classification performance of polarimetric synthetic aperture radar (PolSAR) images, many labeled samples are needed for training. However, it is difficult, expensive, and time-consuming to obtain labeled samples in practice. On the other hand, unlabeled samples are substantially cheaper and more plentiful than labeled ones. In addressing this issue, semisupervised learning techniques are proposed. In this paper, a novel semisupervised algorithm based on an improved cotraining process is proposed for PolSAR image classification. First, we propose an indirect analysis strategy to analyze the nature of sufficiency and independence between two different views for cotraining. Then, an improved cotraining process with a new sample selection strategy is presented, which can effectively take advantage of unlabeled samples to improve the performance of classification, particularly when labeled samples are limited. Finally, a new postprocess method based on a similarity principle and a superpixel algorithm is developed to improve the consistency of the classification. Experimental results on three real PolSAR images show that our proposed method is an effective classification method, and is superior to other traditional methods.
    Download Collect
  • Lung Cancer Screening Based on Type-different Sensor Arrays

    Li, Wang   Liu, Hongying   Xie, Dandan   He, Zichun   Pi, Xititan  

    In recent years, electronic nose (e-nose) systems have become a focus method for diagnosing pulmonary diseases such as lung cancer. However, principles and patterns of sensor responses in traditional e-nose systems are relatively homogeneous. Less study has been focused on type-different sensor arrays. In this paper, we designed a miniature e-nose system using 14 gas sensors of four types and its subsequent analysis of 52 breath samples. To investigate the performance of this system in identifying and distinguishing lung cancer from other respiratory diseases and healthy controls, five feature extraction algorithms and two classifiers were adopted. Lastly, the influence of type-different sensors on the identification ability of e-nose systems was analyzed. Results indicate that when using the LDA fuzzy 5-NN classification method, the sensitivity, specificity and accuracy of discriminating lung cancer patients from healthy controls with e-nose systems are 91.58%, 91.72% and 91.59%, respectively. Our findings also suggest that type-different sensors could significantly increase the diagnostic accuracy of e-nose systems. These results showed e-nose system proposed in this study was potentially practicable in lung cancer screening with a favorable performance. In addition, it is important for type-different sensors to be considered when developing e-nose systems.
    Download Collect
  • A spectral and morphologic method for white blood cell classification

    Wang, Qian   Chang, Li   Zhou, Mei   Li, Qingli   Liu, Hongying   Guo, Fangmin  

    The identification of white blood cells is important as it provides an assay for diagnosis of various diseases. To overcome the complexity and inaccuracy of traditional methods based on light microscopy, we proposed a spectral and morphologic method based on hyperspectral blood images. We applied mathematical morphology-based methods to extract spatial information and supervised method is employed for spectral analysis. Experimental results show that white blood cells could be segmented and classified into five types with an overall accuracy of more than 90%. Moreover, the experiments including spectral features reached higher accuracy than the spatial-only cases, with a maximum improvement of nearly 20%. By combing both spatial and spectral features, the proposed method provides higher classification accuracy than traditional methods. (C) 2016 Elsevier Ltd. All rights reserved.
    Download Collect
  • New classifier based on compressed dictionary and LS-SVM

    Sun, Chen   Jiao, Licheng   Liu, Hongying   Yang, Shuyuan  

    Inspired by the compressive sensing (CS) theory, a new classifier based on compressed dictionary and Least Squares Support Vector Machine (LS-SVM) is proposed to deal with large scale problems. The coefficients of support vectors can be recovered from a few measurements if LS-SVM is approximated to sparse structure. Using the known Choleslcy decomposition, we approximate the given kernel matrix to represent the coefficients of support vectors sparsely by a low-rank matrix that we have used as a dictionary. The proposed measurement matrix being coupled with the dictionary forms a compressed dictionary that proves to satisfy the restricted isometry property (RIP). Our classifier has the quality of low storage and computational complexity, high degree of sparsity and information preservation. Experiments on benchmark data sets show that our classifier has positive performance. (C) 2016 Elsevier B.V. All rights reserved.
    Download Collect
  • SAR image target recognition via Complementary Spatial Pyramid Coding

    Wang, Shaona   Jiao, Licheng   Yang, Shuyuan   Liu, Hongying  

    Many works have been recently presented to extract efficient features for automatic target recognition of synthetic aperture radar (SAR) images. However, they are limited in the discriminative ability of similar targets and robustness to the remarkable speckle noises and background clutters existed in images. In this paper, we propose a Complementary Spatial Pyramid Coding (CSPC) approach in the framework of Spatial Pyramid Matching (SPM). Both the coding coefficients and coding residuals are explored to develop more discriminative and robust features for representing SAR images. Multiple codebooks are first built from some training example images, where each codebook is formulated by local features of a certain class of samples. Then multiple sparse coding models are developed to derive features of a target under these codebooks. Additionally, these coding residuals are further sparsely encoded in the same way to that of local features. Finally, the encoded local features and the residual features are pooled according to spatial pyramid respectively, then concatenated to form the complementary features for the subsequent classification. The experiments on Moving and Stationary Target Acquisition and Recognition (MSTAR) public database verify the superior performance of the proposed method to some related approaches. Crown Copyright (C) 2016 Published by Elsevier B.V. All rights reserved.
    Download Collect
  • Super-high speed medical micro-motor design and thermal field calculation

    Sun, Liangwei   Pi, Xitian   Liu, Hongying   Li, Jingcan  

    As the core component of a precision power operation system for Neurosurgery, medical micro-motors need to have characteristics of high reliability, high speed, high precision, low temperature rise and capability of repeated autoclave sterilization. Therefore, high requirements of design and manufacture are put forward. In view of the above, a super-high speed micro motor with a micro flow channel auxiliary cooling system was proposed in this paper. We used Ansoft to analyze the magnetic field distribution of the motor and operating performances at rated speed, and calculate the motor loss and motor temperature distribution. The results showed that the motor speed could reach 89000 Rpm in stable operation and the output power was 60 W. The temperature rise of the rotor and stator core was very low, when the temperature of the liquid coolant in cooling system was 20 degrees C, which could efficiently prolong load working hours. This research provided a new idea for the design of a super-high speed micro-motor utilized in neurosurgical power operation system.
    Download Collect
  • MicroRNA analysis in mouse neuro-2a cells after pseudorabies virus infection

    Li, Yongtao   Zheng, Guanmin   Zhang, Yujuan   Yang, Xia   Liu, Hongying   Chang, Hongtao   Wang, Xinwei   Zhao, Jun   Wang, Chuanqing   Chen, Lu  

    Pseudorabies virus (PRV), an alpha herpesvirus can enter the mammalian nervous system, causing Aujezsky's disease. Previous studies have reported an alteration of microRNA (miRNA) expression levels during PRV infections. However, knowledge regarding miRNA response in nervous cells to PRV infection is still unknown. To address this issue, small RNA libraries from infected and uninfected mouse neuroblastoma cells were assessed after Illumina deep sequencing. A total of eight viral miRNA were identified, and ten host miRNAs showed significantly different expression upon PRV infection. Among these, five were analyzed by stem-loop RT-qPCR, which confirmed the above data. Interestingly, these viral miRNAs were mainly found in the large latency transcript region of PRV, and predicted to target a variety of genes, forming a complicated regulatory network. Moreover, ten cellular miRNAs were expressed differently upon PRV infection, including nine upregulated and one downregulated miRNAs. Host targets of these miRNAs obtained by bioinformatics analysis belonged to large signaling networks, mainly encompassing calcium signaling pathway, cAMP signaling pathway, MAPK signaling pathway, and other nervous-associated pathways. These findings further highlighted miRNA features in nervous cells after PRV infection and contributed to unveil the underlying mechanisms of neurotropism as well as the neuropathogenesis of PRV.
    Download Collect
  • Achieving Optimal Traffic Engineering Using a Generalized Routing Framework

    Xu, Ke   Shen, Meng   Liu, Hongying   Liu, Jiangchuan   Li, Fan   Li, Tong  

    The open shortest path first (OSPF) protocol has been widely applied to intra-domain routing in today's Internet. Since a router running OSPF distributes traffic uniformly over equal-cost multi-path (ECMP), the OSPF-based optimal traffic engineering (TE) problem (i.e., deriving optimal link weights for a given traffic demand) is computationally intractable for large-scale networks. Therefore, many studies resort to multi-protocol label switching (MPLS) based approaches to solve the optimal TE problem. In this paper we present a generalized routing framework to realize the optimal TE, which can be potentially implemented via OSPF- or MPLS-based approaches. We start with viewing the conventional optimal TE problem in a fresh way, i. e., optimally allocating the residual capacity to every link. Then we make a generalization of network utility maximization (NUM) to close this problem, where the network operator is associated with a utility function of the residual capacity to be maximized. We demonstrate that under this framework, the optimal routes resulting from the optimal TE are also the shortest paths in terms of a set of non-negative link weights that are explicitly determined by the optimal residual capacity and the objective function. The network entropy maximization theory is employed to enable routers to exponentially, instead of uniformly, split traffic over ECMP. The shortest-path penalizing exponential flow-splitting (SPEF) is designed as a link-state protocol with hop-by-hop forwarding to implement our theoretical findings. An alternative MPLS-based implementation is also discussed here. Numerical simulation results have demonstrated the effectiveness of the proposed framework as well as SPEF.
    Download Collect
  • THIAZINE AMIDE DERIVATIVE AND PHARMACEUTICAL COMPOSITION AND USE THEREOF

    The present invention relates to a thiazine amide derivative and a pharmaceutical use thereof, and particularly to a compound of formula I (in the formula, variables are as described in the specification), a pharmaceutically acceptable salt, solvate or hydrate thereof. The present invention further relates to a method for preparing the compound, a pharmaceutical composition containing the compound and a method or a use thereof for preventing or treating a neurodegenerative disease.
    Download Collect
  • A hyperspectral vessel image registration method for blood oxygenation mapping

    Wang, Qian   Li, Qingli   Zhou, Mei   Sun, Zhen   Liu, Hongying   Wang, Yiting  

    Blood oxygenation mapping by the means of optical oximetry is of significant importance in clinical trials. This paper uses hyperspectral imaging technology to obtain in vivo images for blood oxygenation detection. The experiment involves dorsal skin fold window chamber preparation which was built on adult (8-10 weeks of age) female BALB/c nu/nu mice and in vivo image acquisition which was performed by hyperspectral imaging system. To get the accurate spatial and spectral information of targets, an automatic registration scheme is proposed. An adaptive feature detection method which combines the local threshold method and the level-set filter is presented to extract target vessels. A reliable feature matching algorithm with the correlative information inherent in hyperspectral images is used to kick out the outliers. Then, the registration images are used for blood oxygenation mapping. Registration evaluation results show that most of the false matches are removed and the smooth and concentrated spectra are obtained. This intensity invariant feature detection with outliers-removing feature matching proves to be effective in hyperspectral vessel image registration. Therefore, in vivo hyperspectral imaging system by the assistance of the proposed registration scheme provides a technique for blood oxygenation research.
    Download Collect
  • Skin cells segmentation algorithm based on spectral angle and distance score

    Li, Qingli   Chang, Li   Liu, Hongying   Zhou, Mei   Wang, Yiting   Guo, Fangmin  

    In the diagnosis of skin diseases by analyzing histopathological images of skin sections, the automated segmentation of cells in the epidermis area is an important step. Light microscopy based traditional methods usually cannot generate satisfying segmentation results due to complicated skin structures and limited information of this kind of image. In this study, we use a molecular hyperspectral imaging system to observe skin sections and propose a spectral based algorithm to segment epithelial cells. Unlike pixel-wise segmentation methods, the proposed algorithm considers both the spectral angle and the distance score between the test and the reference spectrum for segmentation. The experimental results indicate that the proposed algorithm performs better than the K-Means, fuzzy C-means, and spectral angle mapper algorithms because it can identify pixels with similar spectral angle but a different spectral distance. (C) 2015 Elsevier Ltd. All rights reserved.
    Download Collect
  • Effects of Physio-Chemical Factors on Asphalt Aging Behavior

    Liu, Hongying   Hao, Peiwen   Wang, Hainian   Adhikair, Sanjeev  

    Based on an accelerated asphalt-aging test in the laboratory, the authors evaluated the physical and chemical properties of asphalt at different aging times and temperatures for this paper. They evaluated the properties of the asphalt binder, such as saturates, aromatics, resins, asphaltenes, penetration, softening point, and molecular distribution of the asphalt, by using experimental results from the accelerated asphalt-aging tests. They employed gel permeation chromatography (GPC), Fourier transforms infrared spectroscopy, asphalt constituents fraction analysis, and rheological test techniques to analyze the effects of asphalt from different crude oil sources on antiaging performance. They used asphalt-aging tests to determine the relevant kinetic parameters needed in the aging kinetics equation. They found that the asphalt-aging reaction perfectly fits to the first order kinetics equation, and during the asphalt-aging process, the asphalt had a higher activation energy and a lower reaction rate coefficient. Moreover, the molecular weight (MW) of asphalt increased, whereas the dispersity decreased. The asphalt-aging process was divided into two stages: one stage is from aliphatic sulfide to sulfoxide and the other stage was from benzylic carbon to carbonyl. The aging resistance of asphalt was influenced by the asphalt fraction, wax content, and molecular weight.
    Download Collect
  • A smart capsule system of gastric occult blood detection.

    Liu, Hongying   Qiao, Panpan   Wu, Xueli   Wang, Li   Ao, Yilu   Jia, Ziru   Pi, Xitian  

    Prior research indicated that occult blood screening can be used to detect early gastric cancer. Based on capsule endoscopy and occult blood detection theory, an automatic detection capsule system for gastric occult blood (GOB) was proposed. This paper designed the detecting sensor, image acquisition system and wireless transmitter module respectively based on collaurum immune theory, the image sensor and radio frequency chip. In vitro experiments were conducted to testify the system, and the detecting result image information was acquired by the image acquisition (IMAQ) system and transmitted to the outside of the body through the wireless transmitter module. The receiver module received and displayed the information on the computer, from which doctors could diagnose whether there was occult blood (OB) or not. Therefore, this paper provides a new idea for the screening of early-stage gastric cancer with reliability and simplicity. =20
    Download Collect
  • Classification and saliency detection by semi-supervised low-rank representation

    Zhao, Miaoyun   Jiao, Licheng   Ma, Wenping   Liu, Hongying   Yang, Shuyuan  

    In the area of pattern recognition, Low Rank Representation (LRR) is an efficient method in recovering the subspace structure of the dataset. However, LRR is unsupervised. Without any label information, LRR constructs an informative graph which is then combined with the mature graph-based semi-supervised learning (GSSL) framework to complete the classification task. In this paper, we propose a new low rank learning method which constructs the low rank representation matrix utilizing label information to obtain a more informative graph. This method integrates the low rank graph construction and the label information propagation processes together. Thus the optimization of the low rank representation and the soft label prediction function are calculated iteratively at the same time. We name this method as Semi-Supervised Low Rank Learning (SSLRL). It enhanced the classification performance of traditional LRR-Graph based SSL by 5-30% and the running time is reduced from hundreds to less than ten seconds. Based on this method, a new outlier detection strategy is presented. This strategy succeeds with an AUC of at least 93% even if the detection condition of LRR is not satisfied. The effectiveness of SSLRL is demonstrated in semi-supervised classification, outlier detection, and salient detection tasks. These extensive experimental results highlight the outperforming of our method over state-of-the-art methods. (C) 2015 Elsevier Ltd. All rights reserved.
    Download Collect
1 2 3 4 5 6 7 8 9 10

Contact

If you have any feedback, Please follow the official account to submit feedback.

Turn on your phone and scan

Submit Feedback