Dandan Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Dandan Song has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Xiuhua Liu
Department of Pathophysiology, Chinese PLA General Hospital, Beijing 100853, P.R. China
2 shared publications Chao Liu
Affiliation Xinjiang Institute of Technology, Aksu, China
1 shared publication- Hong Gong
Wuhan University
1 shared publication - Jian Jiao
Department of Stomatology, Tianjin Medical University General Hospital, Tianjin 300052, China
1 shared publication Mi Liu
Department of Pathophysiology Chinese PLA General Hospital Beijing China
1 shared publicationRu-Qin Yu
State Key Laboratory of Chemo/Biosensing and Chemometrics College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, PR China
1 shared publication
Latest Publications
- Open Access
- 16 January 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (1) , e0312359
A facial expression recognition network using hybrid feature extraction
Facial expression recognition faces great challenges due to factors such as face similarity, image quality, and age variation. Although various existing end-to-end Convolutional Neural Network (CNN) architectures have achieved good classification results in facial expression recognition tasks, these network architectures share a common drawback that the convolutional kernel can only compute the correlation between elements of a localized region when extracting expression features from an image. This leads to difficulties for the network to explore the relationship between all the elements that make up a complete expression. In response to this issue, this article proposes a facial expression recognition network called HFE-Net. In order to capture the subtle changes of expression features and the whole facial expression information at the same time, HFE-Net proposed a Hybrid Feature Extraction Block. Specifically, Hybrid Feature Extraction Block consists of parallel Feature Fusion Device and Multi-head Self-attention. Among them, Feature Fusion Device not only extracts the local information in expression features, but also measures the correlation between distant elements in expression features, which helps the network to focus more on the target region while realizing the information interaction between distant features. And Multi-head Self-attention can calculate the correlation between the overall elements in the feature map, which helps the network to extract the overall information of the expression features. We conducted a lot of experiments on four publicly available facial expression datasets and verified that the Hybrid Feature Extraction Block constructed in this paper can improve the network’s recognition ability for facial expressions.
- 16 January 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (1) , e0312359
Open AccessA facial expression recognition network using hybrid feature extraction
Facial expression recognition faces great challenges due to factors such as face similarity, image quality, and age variation. Although various existing end-to-end Convolutional Neural Network (CNN) architectures have achieved good classification results in facial expression recognition tasks, these network architectures share a common drawback that the convolutional kernel can only compute the correlation between elements of a localized region when extracting expression features from an image. This leads to difficulties for the network to explore the relationship between all the elements that make up a complete expression. In response to this issue, this article proposes a facial expression recognition network called HFE-Net. In order to capture the subtle changes of expression features and the whole facial expression information at the same time, HFE-Net proposed a Hybrid Feature Extraction Block. Specifically, Hybrid Feature Extraction Block consists of parallel Feature Fusion Device and Multi-head Self-attention. Among them, Feature Fusion Device not only extracts the local information in expression features, but also measures the correlation between distant elements in expression features, which helps the network to focus more on the target region while realizing the information interaction between distant features. And Multi-head Self-attention can calculate the correlation between the overall elements in the feature map, which helps the network to extract the overall information of the expression features. We conducted a lot of experiments on four publicly available facial expression datasets and verified that the Hybrid Feature Extraction Block constructed in this paper can improve the network’s recognition ability for facial expressions.
- RetractedOpen Access
- 1 January 2021
- Published by Wiley in Oxidative Medicine and Cellular Longevity
- Vol. 2021 (1) , 8877296
[Retracted] Effects of Xuefu Zhuyu Granules on Patients with Stable Coronary Heart Disease: A Double‐Blind, Randomized, and Placebo‐Controlled Study
Despite advances in the drug treatment strategy for stable coronary heart disease (CHD), the mortality of CHD continues to rise. New or adjuvant treatments would be desirable for CHD. Xuefu Zhuyu granules are derived from the formula of traditional Chinese medicine. To determine whether Xuefu Zhuyu granules might have adjuvant effects on stable CHD, we conducted a controlled clinical trial. Patients with stable CHD were enrolled and randomly assigned to receive Xuefu Zhuyu granules or placebo for 12 weeks in addition to their standard medications for the treatment of CHD. The primary endpoints comprise the Canadian Cardiovascular Society Angina Grading Scale (CCS class), echocardiographic measures, Seattle Angina Questionnaire (SAQ), and coronary artery CT. The secondary endpoints included the parameters of nailfold capillary measurement and cutaneous blood perfusion (CBP). After 12 weeks of follow‐up, there was a great improvement of the Canadian Cardiovascular Society Angina Grading Scale (CCS class) in the Xuefu Zhuyu group compared with the placebo group (p < 0.01). Also, a decrease was found in the percentage of patients with CCS class II in the Xuefu Zhuyu group between follow‐up at 12 weeks and baseline (p < 0.01). We observed a significant increase in SAQ scores of physical limitation (p < 0.01) and treatment satisfaction (p < 0.05) in patients receiving Xuefu Zhuyu treatment at 12 weeks in comparison with those at baseline, but not in placebo treatment (p > 0.05). Amelioration in coronary artery stenosis in the Xuefu Zhuyu group was noted (p < 0.05). Xuefu Zhuyu granule treatment led to great improvements in cutaneous blood perfusion at follow‐up of 12 weeks compared with placebo (p < 0.05). These findings suggest that on a background of standard medications, Xuefu Zhuyu granules have the ability to further improve the prognosis of patients with stable CHD.
- 1 January 2021
- Published by Wiley in Oxidative Medicine and Cellular Longevity
- Vol. 2021 (1) , 8877296
RetractedOpen Access[Retracted] Effects of Xuefu Zhuyu Granules on Patients with Stable Coronary Heart Disease: A Double‐Blind, Randomized, and Placebo‐Controlled Study
Despite advances in the drug treatment strategy for stable coronary heart disease (CHD), the mortality of CHD continues to rise. New or adjuvant treatments would be desirable for CHD. Xuefu Zhuyu granules are derived from the formula of traditional Chinese medicine. To determine whether Xuefu Zhuyu granules might have adjuvant effects on stable CHD, we conducted a controlled clinical trial. Patients with stable CHD were enrolled and randomly assigned to receive Xuefu Zhuyu granules or placebo for 12 weeks in addition to their standard medications for the treatment of CHD. The primary endpoints comprise the Canadian Cardiovascular Society Angina Grading Scale (CCS class), echocardiographic measures, Seattle Angina Questionnaire (SAQ), and coronary artery CT. The secondary endpoints included the parameters of nailfold capillary measurement and cutaneous blood perfusion (CBP). After 12 weeks of follow‐up, there was a great improvement of the Canadian Cardiovascular Society Angina Grading Scale (CCS class) in the Xuefu Zhuyu group compared with the placebo group (p < 0.01). Also, a decrease was found in the percentage of patients with CCS class II in the Xuefu Zhuyu group between follow‐up at 12 weeks and baseline (p < 0.01). We observed a significant increase in SAQ scores of physical limitation (p < 0.01) and treatment satisfaction (p < 0.05) in patients receiving Xuefu Zhuyu treatment at 12 weeks in comparison with those at baseline, but not in placebo treatment (p > 0.05). Amelioration in coronary artery stenosis in the Xuefu Zhuyu group was noted (p < 0.05). Xuefu Zhuyu granule treatment led to great improvements in cutaneous blood perfusion at follow‐up of 12 weeks compared with placebo (p < 0.05). These findings suggest that on a background of standard medications, Xuefu Zhuyu granules have the ability to further improve the prognosis of patients with stable CHD.
- 6 August 2014
- Published by Wiley in Microcirculation
- Vol. 21 (6) , 506-515
Calreticulin Protects Rat Microvascular Endothelial Cells against Microwave Radiation‐induced Injury by Attenuating Endoplasmic Reticulum Stress
Objective: This study was designed to evaluate whether exogenous CRT was beneficial for alleviating MR‐induced injury by suppressing ER stress in rat MMECs.Methods: MMECs were pretreated with CRT (25 pg/mL) for 12 hours, followed by the exposure to 2.856 GHz radiation at a mean power density of 30 mW/cm2 for six minutes. MR‐induced injury in MMECs was evaluated by LDH leakage, apoptosis, and cell viability analysis. The expression of GRP78, CRT, CHOP, Bcl‐2, and Bax were examined by Western blot analysis to reflect ER stress response and ER stress‐related apoptosis.Results: MR induced marked MMECs injury, as shown by increased LDH leakage and apoptosis rate and decreased cell viability. MR also induced excessive ER stress, characterized by increased expression of GRP78 and CRT, and ER stress‐related apoptotic signaling as well, as shown by the upregulation of CHOP and Bax and the downregulation of Bcl‐2. Exogenous CRT pretreatment remarkably attenuated MR‐induced cell apoptosis and LDH leakage, ER stress, and activation of the ER stress‐related apoptotic signaling.Conclusions: Exogenous CRT attenuates MR‐induced ER stress‐related apoptosis by suppressing CHOP‐mediated apoptotic signaling pathways in MMECs.
- 6 August 2014
- Published by Wiley in Microcirculation
- Vol. 21 (6) , 506-515
Calreticulin Protects Rat Microvascular Endothelial Cells against Microwave Radiation‐induced Injury by Attenuating Endoplasmic Reticulum Stress
Objective: This study was designed to evaluate whether exogenous CRT was beneficial for alleviating MR‐induced injury by suppressing ER stress in rat MMECs.Methods: MMECs were pretreated with CRT (25 pg/mL) for 12 hours, followed by the exposure to 2.856 GHz radiation at a mean power density of 30 mW/cm2 for six minutes. MR‐induced injury in MMECs was evaluated by LDH leakage, apoptosis, and cell viability analysis. The expression of GRP78, CRT, CHOP, Bcl‐2, and Bax were examined by Western blot analysis to reflect ER stress response and ER stress‐related apoptosis.Results: MR induced marked MMECs injury, as shown by increased LDH leakage and apoptosis rate and decreased cell viability. MR also induced excessive ER stress, characterized by increased expression of GRP78 and CRT, and ER stress‐related apoptotic signaling as well, as shown by the upregulation of CHOP and Bax and the downregulation of Bcl‐2. Exogenous CRT pretreatment remarkably attenuated MR‐induced cell apoptosis and LDH leakage, ER stress, and activation of the ER stress‐related apoptotic signaling.Conclusions: Exogenous CRT attenuates MR‐induced ER stress‐related apoptosis by suppressing CHOP‐mediated apoptotic signaling pathways in MMECs.
- 1 October 2010
- Published by Elsevier in Chemometrics and Intelligent Laboratory Systems
- Vol. 103 (2) , 184-190
QSAR studies of a diverse series of antimicrobial agents against Candida albicans by classification and regression trees
- 1 October 2010
- Published by Elsevier in Chemometrics and Intelligent Laboratory Systems
- Vol. 103 (2) , 184-190
QSAR studies of a diverse series of antimicrobial agents against Candida albicans by classification and regression trees