Jianhua Wu

Prof. Dr. Jianhua Wu

Electronic Inform. Eng. Dept.,Inform. Eng. School, Nanchang University, Nanchang, Jiangxi, China
orcid
不积跬步, 无以至千里. 不积小流, 无以成江海. (No steps, no miles. There is no r...

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2017
Verified
Conference Paper
Closed access
LCLi Cuimei
Li Cuimei
QZQi Zhiliang
Qi Zhiliang
JNJia Nan
Jia Nan
Jianhua WuJianhua Wu
Jianhua Wu
Human face detection has been a challenging issue in the areas of image processing and patter recognition. A new human face detection algorithm by primitive Haar cascade algorithm combined with three additional weak classifiers is proposed in this paper. The three weak classifiers are based on skin hue histogram matching, eyes detection and mouth detection. First, images of people are processed by a primitive Haar cascade classifier, nearly without wrong human face rejection (very low rate of false negative) but with some wrong acceptance (false positive). Secondly, to get rid of these wrongly accepted non-human faces, a weak classifier based on face skin hue histogram matching is applied and a majority of non-human faces are removed. Next, another weak classifier based on eyes detection is appended and some residual non-human faces are determined and rejected. Finally, a mouth detection operation is utilized to the remaining non-human faces and the false positive rate is further decreased. With the help of OpenCV, test results on images of people under different occlusions and illuminations and some degree of orientations and rotations, in both training set and test set show that the proposed algorithm is effective and achieves state-of-the-art performance. Furthermore, it is efficient because of its easiness and simplicity of implementation.
1

1 September 2019 in Physica Medica
Verified
Journal Article
Closed access
CWCanhua Wang
Canhua Wang
ZXZhiyong Xiao
Zhiyong Xiao
Jianhua WuJianhua Wu
Jianhua Wu

11 June 2022 in Journal of Translational Medicine
Verified
Journal Article
Open access
PDF file
FGFei Guo
Fei Guo
XZXishun Zhu
Xishun Zhu
ZWZhiheng Wu
Zhiheng Wu
LZLi Zhu
Li Zhu
Jianhua WuJianhua Wu
Jianhua Wu
FZFan Zhang
Fan Zhang
Background: Sepsis is a life-threatening syndrome eliciting highly heterogeneous host responses. Current prognostic evaluation methods used in clinical practice are characterized by an inadequate effectiveness in predicting sepsis mortality. Rapid identification of patients with high mortality risk is urgently needed. The phenotyping of patients will assistant invaluably in tailoring treatments.Methods: Machine learning and deep learning technology are used to characterize the patients’ phenotype and determine the sepsis severity. The database used in this study is MIMIC-III and MIMIC-IV (‘Medical information Mart for intensive care’) which is a large, public, and freely available database. The K-means clustering is used to classify the sepsis phenotype. Convolutional neural network (CNN) was used to predict the 28-day survival rate based on 35 blood test variables of the sepsis patients, whereas a double coefficient quadratic multivariate fitting function (DCQMFF) is utilized to predict the 28-day survival rate with only 11 features of sepsis patients.Results: The patients were grouped into four clusters with a clear survival nomogram. The first cluster (C_1) was characterized by low white blood cell count, low neutrophil, and the highest lymphocyte proportion. C_2 obtained the lowest Sequential Organ Failure Assessment (SOFA) score and the highest survival rate. C_3 was characterized by significantly prolonged PTT, high SIC, and a higher proportion of patients using heparin than the patients in other clusters. The early mortality rate of patients in C_3 was high but with a better long-term survival rate than that in C_4. C_4 contained septic coagulation patients with the worst prognosis, characterized by slightly prolonged partial thromboplastin time (PTT), significantly prolonged prothrombin time (PT), and high septic coagulation disease score (SIC). The survival rate prediction accuracy of CNN and DCQMFF models reached 92% and 82%, respectively. The models were tested on an external dataset (MIMIC-IV) and achieved good performance. A DCQMFF-based application platform was established for fast prediction of the 28-day survival rate.Conclusion: CNN and DCQMFF accurately predicted the sepsis patients’ survival, while K-means successfully identified the phenotype groups. The distinct phenotypes associated with survival, and significant features correlated with mortality were identified. The findings suggest that sepsis patients with abnormal coagulation had poor outcomes, abnormal coagulation increase mortality during sepsis. The anticoagulation effects of appropriate heparin sodium treatment may improve extensive micro thrombosis-caused organ failure.

13 June 2016 in IETE Technical Review
Verified
Journal Article
Closed access
JMJian Ma
Jian Ma
JZJun Zhang
Jun Zhang
LXLuxin Xiao
Luxin Xiao
KCKexu Chen
Kexu Chen
Jianhua WuJianhua Wu
Jianhua Wu
In this paper, a deep learning-based method is introduced into the classification of power quality disturbances (PQDs). Stacked autoencoder, as a deep learning framework, is employed to extract high-level features of PQDs for classification. In this context, a previously unsolved issue regarding optimal features’ selection for PQDs can be addressed. Besides, variances of signals and a particle swarm optimization algorithm are applied to assist classification of the PQDs. To sufficiently validate the effectiveness of the proposed classification scheme, a 10-fold cross-validation has been done. Experimental results indicate that the proposed approach is robust against noise and reaches a desirable classification accuracy rate.

1 August 2014 in Optik
Verified
Journal Article
Closed access
Jianhua WuJianhua Wu
Jianhua Wu
FGFangfang Guo
Fangfang Guo
YLYaru Liang
Yaru Liang
NZNanrun Zhou
Nanrun Zhou

1 January 2006
Verified
Conference Paper
Closed access
Jianhua WuJianhua Wu
Jianhua Wu
PZPingping Zeng
Pingping Zeng
YZYuan Zhou
Yuan Zhou
COChristian Olivier
Christian Olivier
According to the fact that the H component in HSI color space contains most of the white blood cell information, and the S component contains the structure information of the white blood cell nucleus, we develop an iterative Otsu's approach based on circular histogram for the leukocyte segmentation by taking full advantage of this knowledge. Experimental results show that this method works successfully in the segmentation of color smear microscopic images