Search

Your search keyword '"Lu, Xiaohua"' showing total 1,843 results
Start Over Author "Lu, Xiaohua"
1,843 results on '"Lu, Xiaohua"'

1. A Methodological Report on Anomaly Detection on Dynamic Knowledge Graphs

Author

Lu, Xiaohua and Yang, Leshanshui

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

In this paper, we explore different approaches to anomaly detection on dynamic knowledge graphs, specifically in a Micro-services environment for Kubernetes applications. Our approach explores three dynamic knowledge graph representations: sequential data, hierarchical data and inter-service dependency data, with each representation incorporating increasingly complex structural information of dynamic knowledge graph. Different machine learning and deep learning models are tested on these representations. We empirically analyse their performance and propose an approach based on ensemble learning of these models. Our approach significantly outperforms the baseline on the ISWC 2024 Dynamic Knowledge Graph Anomaly Detection dataset, providing a robust solution for anomaly detection in dynamic complex data.

Published
2024

2. Integrating Chemical Language and Molecular Graph in Multimodal Fused Deep Learning for Drug Property Prediction

Author

Lu, Xiaohua, Xie, Liangxu, Xu, Lei, Mao, Rongzhi, Chang, Shan, and Xu, Xiaojun

Subjects
Computer Science - Machine Learning, Physics - Biological Physics, Quantitative Biology - Biomolecules
Abstract

Accurately predicting molecular properties is a challenging but essential task in drug discovery. Recently, many mono-modal deep learning methods have been successfully applied to molecular property prediction. However, the inherent limitation of mono-modal learning arises from relying solely on one modality of molecular representation, which restricts a comprehensive understanding of drug molecules and hampers their resilience against data noise. To overcome the limitations, we construct multimodal deep learning models to cover different molecular representations. We convert drug molecules into three molecular representations, SMILES-encoded vectors, ECFP fingerprints, and molecular graphs. To process the modal information, Transformer-Encoder, bi-directional gated recurrent units (BiGRU), and graph convolutional network (GCN) are utilized for feature learning respectively, which can enhance the model capability to acquire complementary and naturally occurring bioinformatics information. We evaluated our triple-modal model on six molecule datasets. Different from bi-modal learning models, we adopt five fusion methods to capture the specific features and leverage the contribution of each modal information better. Compared with mono-modal models, our multimodal fused deep learning (MMFDL) models outperform single models in accuracy, reliability, and resistance capability against noise. Moreover, we demonstrate its generalization ability in the prediction of binding constants for protein-ligand complex molecules in the refined set of PDBbind. The advantage of the multimodal model lies in its ability to process diverse sources of data using proper models and suitable fusion methods, which would enhance the noise resistance of the model while obtaining data diversity.

Published
2023
Full Text
View/download PDF

12. Clinical characteristics of patients with puerperal schizophrenia

Author

Lu Xiaohua, Li Haijing, Kuang Qijie, Yi Wenying, Xia Yu, Zhou Nyunan, Zheng Yingjun, and She Shenglin

Subjects
puerperal schizophrenia, clinical characteristics, positive symptoms, negative symptoms, Psychology, BF1-990, Psychiatry, RC435-571
Abstract

BackgroundWomen may develop severe symptoms of stress disorder following childbirth， which may be exposed to a risk of developing mental health problems， and even lead to the recurrence of the illness in female patients with schizophrenia， while comparatively limited research has been undertaken concerning the clinical characteristics and treatment of puerperal schizophrenia in China.ObjectiveTo explore the clinical characteristics of puerperal schizophrenia， so as to provide references for the clinical treatment.MethodsA total of 24 patients with puerperal schizophrenia who were hospitalized in the female ward of adult psychiatry department of the Affiliated Brain Hospital of Guangzhou Medical University from 2012 to 2020 and met the Diagnostic and Statistical Manual of Mental Disorders， fourth edition （DSM-IV） diagnostic criteria for schizophrenia were included as puerperal group. Another 48 non-puerperal women with schizophrenia were concurrently enrolled as control group. Then the basic data， scores on Positive and Negative Symptom Scale （PANSS） and the discharge medication were recorded.ResultsThe percentages of newly onset and positive family history of psychosis in puerperal group were larger than those in control group， with statistical significance （χ2=9.321， 5.240， P

Published
2024
Full Text
View/download PDF

38. Research on Social Media, Short Video, Digitization and International Communication of Chinese Culture

Author

Lu Xiaohua and Ba Ningrui

Subjects
six-degree communication model, social media, social network analysis, tiktok, 97p10, Mathematics, QA1-939
Abstract

Social media have become a pivotal platform for countries to engage in international discourse in the context of globalization and integration. In this study, a six-degree communication model is utilized to construct the online communication body of Chinese culture. Based on the social network analysis method, a communication analysis is completed for Chinese culture’s international communication. As a final step, 434 effective communication samples are chosen as research objects on the TikTok platform, which combines social media, short videos, and digital technology to facilitate the international communication of Chinese culture. The results show that on the TikTok platform, the global communication distance effect of Chinese culture is reflected in the network distance of 0.3900, the content distance of 0.2971, and the emotional distance of 0.3129, all of which are much smaller than the communication distance of traditional methods. The way Chinese culture spreads on TikTok, a platform that combines social media, short videos, and digitization, exhibits a degree of efficacy and feasibility.

Published
2024
Full Text
View/download PDF

46. A drug repurposing approach for individualized cancer therapy based on transcriptome sequencing and virtual drug screening

Author

Kadioglu, Onat, Bahramimehr, Faranak, Dawood, Mona, Mahmoud, Nuha, Elbadawi, Mohamed, Lu, Xiaohua, Bülbül, Yagmur, Schulz, Jana Agnieszka, Krämer, Lisa, Urschel, Marie-Kathrin, Künzli, Zoe, Abdulrahman, Leila, Aboumaachar, Fadwa, Kadalo, Lajien, Nguyen, Le Van, Shaidaei, Sara, Thaher, Nawal, Walter, Kathrin, Besler, Karolin Christiane, Spuller, Andreas, Munder, Markus, Greten, Henry Johannes, and Efferth, Thomas

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results