YPYan Peng

Yan Peng

*This is an algorithmically generated author record based on publicly available information.

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


Yan Peng has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Novel Framework for Risk Warning That Utilizes an Improved Generative Adversarial Network and Categorical Boosting

    by Yan Peng, Yue Liu, Jie Wang, Xiao Li

    To address the problems of inadequate training and low precision in prediction models with small-sample-size and incomplete data, a novel SALGAN-CatBoost-SSAGA framework is proposed in this paper. We utilize the standard K-nearest neighbor algorithm to interpolate missing values in incomplete data, and employ EllipticEnvelope to identify outliers. SALGAN, a generative adversarial network with a self-attention mechanism of label awareness, is utilized to generate virtual samples and increase the diversity of the training data for model training. To avoid local optima and improve the accuracy and stability of the standard CatBoost prediction model, an improved Sparrow Search Algorithm (SSA)–Genetic Algorithm (GA) combination is adopted to construct an effective CatBoost-SSAGA model for risk warning, in which the SSAGA is used for the global parameter optimization of CatBoost. A UCI heart disease dataset is used for heart disease risk prediction. The experimental results show the superiority of the proposed model in terms of accuracy, precision, recall, and F1-values, as well as the AUC.


  • Open Access

    Health Information Needs of Young Chinese People Based on an Online Health Community: Topic and Statistical Analysis

    by Jie Wang, Xin Wang, Lei Wang, Yan Peng

    Background: The internet has been widely accessible and well accepted by young people; however, there is a limited understanding of the internet usage patterns and characteristics on issues related to health problems. The contents posted on online health communities (OHCs) are valuable resources to learn about youth's health information needs. Objective: In this study, we concurrently exploited statistical analysis and topic analysis of online health information needs to explore the distribution, impact factors, and topics of interest relevant to Chinese young people. Methods: We collected 60,478 health-related data sets posted by young people from a well-known Chinese OHC named xywy.com. Descriptive statistical analysis and correlation analysis were applied to find the distribution and influence factors of the information needs of Chinese young people. Furthermore, a general 4-step topic mining strategy was presented for sparse short texts, which included sentence vectorization, dimension reduction, clustering, and keyword generation. Results: In the Chinese OHC, Chinese young people had a high demand for information in the areas of gynecology and obstetrics, internal medicine, dermatology, plastic surgery, and surgery, and they focused on topics such as treatment, symptoms, causes, pathology, and diet. Females accounted for 69.67% (42,136/60,478) and young adults accounted for 87.44% (52,882/60,478) of all data. Gender, age, and disease type all had a significant effect on young people's information needs and topic preferences (P<.001). Conclusions: We conducted comprehensive analyses to discover the online health information needs of Chinese young people. The research findings are of great practical value to carry out health education and health knowledge dissemination inside and outside of schools according to the interests of youth, enable the innovation of information services in OHCs, and improve the health literacy of young people.


  • Open Access

    Health Information Needs of Young Chinese People Based on an Online Health Community: Topic and Statistical Analysis (Preprint)

    by Jie Wang, Xin Wang, Lei Wang, Yan Peng

    BACKGROUND The internet has been widely accessible and well accepted by young people; however, there is a limited understanding of the internet usage patterns and characteristics on issues related to health problems. The contents posted on online health communities (OHCs) are valuable resources to learn about youth's health information needs. OBJECTIVE In this study, we concurrently exploited statistical analysis and topic analysis of online health information needs to explore the distribution, impact factors, and topics of interest relevant to Chinese young people. METHODS We collected 60,478 health-related data sets posted by young people from a well-known Chinese OHC named xywy.com. Descriptive statistical analysis and correlation analysis were applied to find the distribution and influence factors of the information needs of Chinese young people. Furthermore, a general 4-step topic mining strategy was presented for sparse short texts, which included sentence vectorization, dimension reduction, clustering, and keyword generation. RESULTS In the Chinese OHC, Chinese young people had a high demand for information in the areas of gynecology and obstetrics, internal medicine, dermatology, plastic surgery, and surgery, and they focused on topics such as treatment, symptoms, causes, pathology, and diet. Females accounted for 69.67% (42,136/60,478) and young adults accounted for 87.44% (52,882/60,478) of all data. Gender, age, and disease type all had a significant effect on young people's information needs and topic preferences (P<.001). CONCLUSIONS We conducted comprehensive analyses to discover the online health information needs of Chinese young people. The research findings are of great practical value to carry out health education and health knowledge dissemination inside and outside of schools according to the interests of youth, enable the innovation of information services in OHCs, and improve the health literacy of young people.

  • Research on PM2.5 Integrated Prediction Model Based on Lasso-RF-GAM

    by Tingxian Wu, Ziru Zhao, Haoxiang Wei, Yan Peng

    PM2.5 concentration is very difficult to predict, for it is the result of complex interactions among various factors. This paper combines the random forest-recursive feature elimination algorithm and lasso regression for joint feature selection, puts forward a PM2.5 concentration prediction model based on GAM. Firstly, the original data is standardized in the data input layer. Secondly, features were selected with RF-RFE and lasso regression algorithm in the feature selection layer. Meanwhile, weighted average method fused the two feature subsets to obtain the final subset, RF-lasso-T. Finally, the generalized additive models (GAM) is used to predict PM2.5 concentration on the RF-lasso-T. Simulated experiments show that feature selection allows GAM model to run more efficiently. The deviance explained by the model reaches 91.5%, which is higher than only using a subset of RF-RFE. This model also reveals the influence of various factors on PM2.5, which provides the decision-making basis for haze control.


  • A Novel Text Retrieval Algorithm for Public Crisis Cases

    by Yan Peng, Jie Wang, Lulin Jiao

    Public crisis has the characteristics of suddenness and uncertainty, and it is necessary to combine the knowledge with the experience of other similar situations to make decisions effectively and quickly. This work combines artificial intelligent theory with information technology and brings case-based reasoning to build models consisting of the features of public crisis. We explore the case-representation approach and build a case-based retrieval algorithm. Combining the specificness of Case-based reasoning (CBR) technology in the monitoring of public crisis events, a new case retrieval algorithm for public crisis cases, named as Combined multi-similarity with set of simi-larity matching algorithm based on sememe (CMSBS), is proposed to analyze the cases with high similarity to current case. The CMSBS algorithm considers the structural and semantic similarities between two public crisis cases comprehensively. Simulation experiments are performed to validate the representation method of the knowledge, and the simulation results demonstrate that the CMSBS algorithm has superior performance in the average number of matching cases and matching accuracy rate and can work well in providing reference cases for subsequent events.