期刊:
IEEE Transactions on Vehicular Technology,2015年64(10):4701-4711 ISSN:0018-9545
通讯作者:
Liao, Shengbin
作者机构:
[Liao, Shengbin] Huazhong Normal Univ, Natl Engn Ctr E Learning, Wuhan 430079, Peoples R China.;[Zhang, Qingfu] City Univ Hong Kong, Sch Comp Sci, Hong Kong, Hong Kong, Peoples R China.
通讯机构:
[Liao, Shengbin] H;Huazhong Normal Univ, Natl Engn Ctr E Learning, Wuhan 430079, Peoples R China.
作者机构:
[Liu, Tingting; Zhang, Zhaoli; Liu, Sanya; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;[Yan, Luxin; Zhang, Tianxu] Huazhong Univ Sci & Technol, Sch Automat, Wuhan 430074, Hubei, Peoples R China.
通讯机构:
[Liu, Hai] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.
关键词:
Raman spectroscopy;Optical data processing;Baseline correction;Denoising;Morphological operation;Regularization
摘要:
Laser instruments often suffer from the problem of baseline drift and random noise, which greatly degrade spectral quality. In this article, we propose a variation model that combines baseline correction and denoising. First, to guide the baseline estimation, morphological operations are adopted to extract the characteristics of the degraded spectrum. Second, to suppress noise in both the spectrum and baseline, Tikhonov regularization is introduced. Moreover, we describe an efficient optimization scheme that alternates between the latent spectrum estimation and the baseline correction until convergence. The major novel aspect of the proposed algorithms is the estimation of a smooth spectrum and removal of the baseline simultaneously. Results of a comparison with state-of-the-art methods demonstrate that the proposed method outperforms them in both qualitative and quantitative assessments.
期刊:
Measurement Science And Technology,2015年26(11):115502 ISSN:0957-0233
通讯作者:
Huang, Tao
作者机构:
[Shen, Xiaoxuan; Liu, Sanyan; Liu, Tingting; Zhang, Jianfeng; Zhang, Zhaoli; Huang, Tao; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;[Zhang, Tianxu] Huazhong Univ Sci & Technol, Sch Automat, Wuhan 430074, Hubei, Peoples R China.
通讯机构:
[Huang, Tao] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
关键词:
blind deconvolution;digital signal processing;infrared spectral data;multiscales;spectral super-resolution
摘要:
Band overlap and random noise exist widely when the spectra are captured using an infrared spectrometer, especially since the aging of instruments has become a serious problem. In this paper, via introducing the similarity of multiscales, a blind spectral deconvolution method is proposed. Considering that there is a similarity between latent spectra at different scales, it is used as prior knowledge to constrain the estimated latent spectrum similar to pre-scale to reduce artifacts which are produced from deconvolution. The experimental results indicate that the proposed method is able to obtain a better performance than state-of-the-art methods, and to obtain satisfying deconvolution results with fewer artifacts. The recovered infrared spectra can easily extract the spectral features and recognize unknown objects.
摘要:
In view of the problem of the low efficiency in traditional classroom teaching due to the limitation in time and space, an exploration which combines real classroom with virtual classroom in hybrid learning was proposed. We chose the teaching of a software engineering course and used starC as the teaching support tool for analysis. In our study, the teaching process was divided into several teaching units, and each teaching unit was further divided into several activity units. The content was organized in the form of topicalities, where students are allowed to choose the learning content according to their study plans and preferences. Through the questionnaire survey which includes the indicators of participation and satisfaction among the students on both traditional learning and hybrid learning, it is found that the students on hybrid learning have higher participation and satisfaction than that on traditional learning. This indicated that hybrid learning could effectively improve teaching effectiveness.
摘要:
Disease-causing genes prioritization is very important to understand disease mechanisms and biomedical applications, such as design of drugs. Previous studies have shown that promising candidate genes are mostly ranked according to their relatedness to known disease genes or closely related disease genes. Therefore, a dangling gene (isolated gene) with no edges in the network can not be effectively prioritized. These approaches tend to prioritize those genes that are highly connected in the PPI network while perform poorly when they are applied to loosely connected disease genes. To address these problems, we propose a new disease-causing genes prioritization method that based on network diffusion and rank concordance (NDRC). The method is evaluated by leave-one-out cross validation on 1931 diseases in which at least one gene is known to be involved, and it is able to rank the true causal gene first in 849 of all 2542 cases. The experimental results suggest that NDRC significantly outperforms other existing methods such as RWR, VAVIEN, DADA and PRINCE on identifying loosely connected disease genes and successfully put dangling genes as potential candidate disease genes. Furthermore, we apply NDRC method to study three representative diseases, Meckel syndrome 1, Protein C deficiency and Peroxisome biogenesis disorder 1A (Zellweger). Our study has also found that certain complex disease-causing genes can be divided into several modules that are closely associated with different disease phenotype.
作者机构:
[刘袁缘; 俞侃; 陈超原] Wenhua College, Wuhan;430074, China;[陈靓影] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan;430079, China;[Qin, Jie] Wuhan Huazhong Numerical Control Co., Ltd, Wuhan
通讯机构:
[Chen, J.-Y.] N;National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China
摘要:
This study proposes a highly interactive model with the new technology of wireless projector to provide an ideal environment for presenting and discussing by multiple users including the teacher and students during lecture hour of flipped classroom. This model can definitely reduce the transition time and the presentation burden switching among a variety of learning activities to achieve a seamless learning. The TAM statistical analysis method is then exploited in the assessment for ease of use and usefulness for the proposed model. Finally, the experimental results demonstrated that the proposed model could readily support highly interactive learning activities for the flipped learning and have high acceptance of intent of use and usage behavior.
作者:
Cheng, Jun;Yu, Xinguo(余新国);Liao, Shengbin;Zhao, Gang
期刊:
ACM International Conference Proceeding Series,2015年2015-August:244-247
作者机构:
[Yu, Xinguo; Liao, Shengbin; Zhao, Gang] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China;Computer School, Hubei Polytechnic University, Huangshi, China;[Cheng, Jun] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China<&wdkj&>Computer School, Hubei Polytechnic University, Huangshi, China
会议名称:
7th International Conference on Internet Multimedia Computing and Service, ICIMCS 2015
会议名称:
9th International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR) - Multispectral Image Acquisition, Processing, and Analysis
会议时间:
OCT 31-NOV 01, 2015
会议地点:
Enshi, PEOPLES R CHINA
会议主办单位:
[Wang, Hailei;Gui, Yuanmiao] Univ Sci & Technol China, Dept Automat, Hefei 230026, Peoples R China.^[Wang, Hailei;Sun, Bingyun;Gui, Yuanmiao] Chinese Acad Sci, Inst Intelligent Machines, Hefei 230031, Peoples R China.^[Wang, Hailei;Sun, Bingyun;Wu, Xuelian] Chinese Acad Sci, Hefei Inst Technol Innovat, Hefei 230031, Peoples R China.^[Chen, Yanping] Hefei Univ, Dept Comp Sci & Technol, Hefei 230601, Peoples R China.^[Zhou, Dongbo] E Learning Cent China Normal Univ, Natl Engn Res Ctr, Wuhan 430079, Peoples R China.
摘要:
Hyperspectral images belong to high-dimensional data having a lot of redundancy information when they are directly used to classification. Support vector machine (SVM) can be employed to map hyperspectral data to high dimensional space effectively and make them linearly separable. In this paper, spectral and spatial information of hyperspectral images were used to construct SVM kernel function respectively. This paper proposed a hyperspectral image classification method utilization spatial-spectral combined kernel SVM in order to improve classification accuracy. The proposed method was used to classify AVIRIS hyperspectral images. The results demonstrated that the proposed SVM method can achieve 96.13% overall accuracy for the single category classification and 84.81% overall accuracy for multi-class classification only using ten percent of the total samples as the training samples. That is to say, the proposed method can make full use of the spectral information and spatial information of hyperspectral data, and effectively distinguish different categories compared with the traditional SVM for classification.
期刊:
International Journal of Embedded Systems,2015年7(1):34-42 ISSN:1741-1068
通讯作者:
Wang, Tai
作者机构:
[Tai Wang] National Engineering Research Center for E.learning, Central China Normal University, Science Hall, Room 417, Luoyu Road 152, Wuhan, Hubei, China;[Yang Wei] National Engineering Research Center for E.learning, Central China Normal University, Science Hall, Room 302, Luoyu Road 152, Wuhan, Hubei, China;[Tingshao Zhu] Computational CyberPsychology Lab, Institute of Psychology, Chinese Academy of Sciences, Lincui Road 16, Chaoyang District, Beijing, China;[Zongkui Zhou] Department of Psychology, Key Laboratory of Ministry of Education of Juveniles CyberPsychology and Behaviour, Central China Normal University, Room 703, Luoyu Road 152, Wuhan, Hubei, China
通讯机构:
National Engineering Research Center for E.learning, Central China Normal University, Science Hall, Room 417, Luoyu Road 152, Wuhan, Hubei, China
摘要:
People's language features are exhibited on their online social network websites, such as Twitter, Weibo in Sina or ShuoShuo in QQ (a former version of microblog). Several leading labs have already made remarkable breakthroughs in the area of collecting and analysing texts generated by a huge population. In this paper, a novel research topic is presented, with the assumption that different kinds of people may exhibit their unique language features, especially mood disorder patients and normal people. The best efforts have been carried out to verify this assumption. Three mood disorder patients and 32 normal people are invited into this test, with their four-year short texts on their microblogs. The results show that though there is no obvious difference between their neither positive nor negative emotion expressions, a sharp gap does exist in the dimension of anger. The authors expect their findings can be tested in a much larger dataset in the future. If the conclusion still holds, a promising auxiliary toolkit for mood disorder diagnosis can thus be developed.
期刊:
International Journal of Pattern Recognition and Artificial Intelligence,2015年29(8):1556011 ISSN:0218-0014
通讯作者:
Chen, Jingying
作者机构:
[Shan, Cunjie; Cai, Pei; Su, Zhiming; Liu, Yuanyuan; Chen, Jingying] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;Wenhua Coll, CICET, Wuhan, Peoples R China.
通讯机构:
[Chen, Jingying] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.
关键词:
D-RF;unconstrained face analysis;hierarchical regression;head pose estimation;facial feature detection
摘要:
Head pose and facial feature detection are important for face analysis. However, many studies reported good results in constrained environment, the performance could be decreased due to the high variations in facial appearance, poses, illumination, occlusion, expression and make-up. In this paper, we propose a hierarchical regression approach, Dirichlet-tree enhanced random forests (D-RF) for face analysis in unconstrained environment. D-RF introduces Dirichlet-tree probabilistic model into regression RF framework in the hierarchical way to achieve the efficiency and robustness. To eliminate noise influence of unconstrained environment, facial patches extracted from face area are classified as positive or negative facial patches, only positive facial patches are used for face analysis. The proposed hierarchical D-RF works in two iterative procedures. First, coarse head pose is estimated to constrain the facial features detection, then the head pose is updated based on the estimated facial features. Second, the facial feature localization is refined based on the updated head pose. In order to further improve the efficiency and robustness, multiple probabilitic models are learned in leaves of the D-RF, i.e. the patch’s classification, the head pose probabilities, the locations of facial points and face deformation models (FDM). Moreover, our algorithm takes a composite weight voting method, where each patch extracted from the image can directly cast a vote for the head pose or each of the facial features. Extensive experiments have been done with different publicly available databases. The experimental results demonstrate that the proposed approach is robust and efficient for head pose and facial feature detection.
期刊:
International Journal of Computers and Applications,2015年37(3-4):94-101 ISSN:1206-212X
通讯作者:
Liu, Sanya(lsy5918@gmail.com)
作者机构:
[Jianwen Sun; Zhi Liu; Sanya Liu; Lin Liu; Meng Wang; Xian Peng] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, P.R. China
通讯机构:
[Sanya Liu] N;National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, P.R. China
作者:
Yu, Xinguo(余新国);Ding, Wan;Zeng, Zhizhong*;Leong, Hon Wai
期刊:
International Journal of Pattern Recognition and Artificial Intelligence,2015年29(4):1555006 ISSN:0218-0014
通讯作者:
Zeng, Zhizhong
作者机构:
[Yu, Xinguo; Zeng, Zhizhong; Ding, Wan] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;[Leong, Hon Wai] Natl Univ Singapore, Dept Comp Sci, Singapore 117417, Singapore.;[Zeng, Zhizhong] Cent China Normal Univ, Natl Engn Res Ctr E Learning, 152 Luoyu Rd, Wuhan 430079, Peoples R China.
通讯机构:
[Zeng, Zhizhong] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, 152 Luoyu Rd, Wuhan 430079, Peoples R China.
关键词:
Digit localization;digit recognition;digital video clock;second-pixel periodicity;deep learning;conditional random field
摘要:
This paper presents an algorithm for reading digital video clocks reliably and quickly. Reading digital clocks from videos is difficult due to the challenges such as color variety, font diversity, noise, and low resolution. The proposed algorithm overcomes these challenges by using the novel methods derived from the domain knowledge. This algorithm first localizes the digits of a digital video clock and then recognizes the digits representing the time of digital video clock. It is a robust three-step algorithm. The first step is an efficient procedure that directly identifies the region of the second digit at a very low computational cost, which replaces the traditional tedious image processing procedure of identifying the second digit region. The success of the first step mainly leverages on the novel second-pixel periodicity method. Using the acquired second digit region as input, the second step is a clock digit localization procedure. It first acquires the colors of the digits of the digital video clock and performs the color conversion. Then it localizes the remaining clock digits. Finally, the last step is a clock digit recognition procedure. It first employs an enhanced digit-sequence recognition method to robustly recognize the digits on the second; it then adopts a deep learning procedure to recognize the remaining digits. The proposed algorithm is tested on a prepared benchmark of 1000 videos that is publicly available and the experimental results show that it can read digital video clocks with a 100% accuracy at a low computational cost.
摘要:
The normalized difference water indices (NDWIs) were successfully used in map land surface water mapping (LSWM) from Landsat series multispectral images. This paper evaluates the potential of the recent Landsat satellite (Landsat-8) Operational Land Imager (OLI) multispectral images for LSWM using three NDWI models. We tested the accuracy and robustness of the three OLI NDWI models in the Yangtze River Basin and the Huaihe River Basin in China. The results demonstrate that the three OLI NDWI models achieve an overall accuracy of more than 95%, a kappa coefficient of 0.89 and a producer's accuracy of 95% for LSWM. The results also demonstrate that the NDWI model using the green band (Band 3) and the SWIR1 band (Band 6) (referred to as NDWIO6,3) of the OLI sensor has a higher LSWM accuracy than the other two NDWI models.