|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Three‐dimensional neural differentiation of embryonic stem cells with ACM induction in microfibrous matrices in bioreactors显示文摘 | Ning Liu Anli Ouyang Yan Li Shang‐Tian Yang | 2013 | Biotechnol Progress2013，，4： | 2 |
| 2 | Kernel-based adversarial attacks and defenses on support vector classification显示文摘While malicious samples are widely found in many application fields of machine learning,suitable countermeasures have been investigated in the field of adversarial machine learning.Due to the importance and popularity of Support Vector Machines(SVMs),we first describe the evasion attack against SVM classification and then propose a defense strategy in this paper.The evasion attack utilizes the classification surface of SVM to iteratively find the minimal perturbations that mislead the nonlinear classifier.Specially,we propose what is called a vulnerability function to measure the vulnerability of the SVM classifiers.Utilizing this vulnerability function,we put forward an effective defense strategy based on the kernel optimization of SVMs with Gaussian kernel against the evasion attack.Our defense method is verified to be very effective on the benchmark datasets,and the SVM classifier becomes more robust after using our kernel optimization scheme. | Wanman Li Xiaozhang Liu Anli Yan Jie Yang | 2022 | Digital Communications and Networks2022，8，4： | 0 |
| 3 | Deciphering transcriptome alterations in bone marrow hematopoiesis at single-cell resolution in immune thrombocytopenia显示文摘Immune thrombocytopenia(ITP)is an autoimmune disorder,in which megakaryocyte dysfunction caused by an autoimmune reaction can lead to thrombocytopenia,although the underlying mechanisms remain unclear.Here,we performed single-cell transcriptome profiling of bone marrow CD34+hematopoietic stem and progenitor cells(HSPCs)to determine defects in megakaryopoiesis in ITP.Gene expression,cell-cell interactions,and transcriptional regulatory networks varied in HSPCs of ITP,particularly in immune cell progenitors.Differentially expressed gene(DEG)analysis indicated that there was an impaired megakaryopoiesis of ITP.Flow cytometry confirmed that the number of CD9+and HES1+cells from Lin−CD34+CD45RA−HSPCs decreased in ITP.Liquid culture assays demonstrated that CD9+Lin−CD34+CD45RA−HSPCs tended to differentiate into megakaryocytes;however,this tendency was not observed in ITP patients and more erythrocytes were produced.The percentage of megakaryocytes differentiated from CD9+Lin−CD34+CD45RA−HSPCs was 3-fold higher than that of the CD9−counterparts from healthy controls(HCs),whereas,in ITP patients,the percentage decreased to only 1/4th of that in the HCs and was comparable to that from the CD9−HSPCs.Additionally,when co-cultured with pre-B cells from ITP patients,the differentiation of CD9+Lin−CD34+CD45RA−HSPCs toward the megakaryopoietic lineage was impaired.Further analysis revealed that megakaryocytic progenitors(MkP)can be divided into seven subclusters with different gene expression patterns and functions.The ITP-associated DEGs were MkP subtype-specific,with most DEGs concentrated in the subcluster possessing dual functions of immunomodulation and platelet generation.This study comprehensively dissects defective hematopoiesis and provides novel insights regarding the pathogenesis of ITP. | Yan Liu Xinyi Zuo Peng Chen Xiang Hu Zi Sheng Anli Liu Qiang Liu Shaoqiu Leng Xiaoyu Zhang Xin Li Limei Wang Qi Feng Chaoyang Li Ming Hou Chong Chu Shihui Ma Shuwen Wang Jun Peng | 2022 | Signal Transduction and Targeted Therapy2022，7，11： | 0 |
| 4 | An Explanatory Strategy for Reducing the Risk of Privacy Leaks显示文摘As machine learning moves into high-risk and sensitive applications such as medical care,autonomous driving,and financial planning,how to interpret the predictions of the black-box model becomes the key to whether people can trust machine learning decisions.Interpretability relies on providing users with additional information or explanations to improve model transparency and help users understand model decisions.However,these information inevitably leads to the dataset or model into the risk of privacy leaks.We propose a strategy to reduce model privacy leakage for instance interpretability techniques.The following is the specific operation process.Firstly,the user inputs data into the model,and the model calculates the prediction confidence of the data provided by the user and gives the prediction results.Meanwhile,the model obtains the prediction confidence of the interpretation data set.Finally,the data with the smallest Euclidean distance between the confidence of the interpretation set and the prediction data as the explainable data.Experimental results show that The Euclidean distance between the confidence of interpretation data and the confidence of prediction data provided by this method is very small,which shows that the model's prediction of interpreted data is very similar to the model's prediction of user data.Finally,we demonstrate the accuracy of the explanatory data.We measure the matching degree between the real label and the predicted label of the interpreted data and the applicability to the network model.The results show that the interpretation method has high accuracy and wide applicability. | Mingting Liu Xiaozhang Liu Anli Yan Xiulai Li Gengquan Xie Xin Tang | 2021 | Journal of Information Hiding and Privacy Protection2021，3，4： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员