Beibei Zhang

Dr. Beibei Zhang


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
17 January 2023 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
WWWei Wei
Wei Wei
XLXiaowan Li
Xiaowan Li
BZBeibei Zhang
Beibei Zhang
LLLinfeng Li
Linfeng Li
RDRobertas Damaševičius
Robertas Damaševičius
Rafal SchererRafal Scherer
Rafal Scherer

28 May 2021
Verified
Conference Paper
Closed access
XDXiangxiang Ding
Xiangxiang Ding
WWWei Wei
Wei Wei
BZBeibei Zhang
Beibei Zhang
Rafal SchererRafal Scherer
Rafal Scherer
RDRobertas Damasevicius
Robertas Damasevicius
With the development of the economy, people's living standards are constantly improving, the demand for fruit is getting bigger and bigger, the demand is also getting higher and higher, and the Luochuan apple is favored by consumers because of its delicious taste, economical, convenient transportation and storage, sales are through the roof. At present, apple packaging on the market is prone to rotten fruit, not environmental protection and other issues, it is necessary to re-design the existing apple packaging in Luochuan. The concept of sustainable packaging has been recognized by many countries, regions and organizations since its emergence. Packaging waste is also an important cause of pollution. Many scholars, designers and institutions have invested in the research and design of sustainable packaging, sustainable packaging is the only way of packaging development. Based on the analysis of the current situation of Luochuan's apple packaging, the paper focuses on the design process of new Luochuan apple packaging, aiming at the existing problems and combining with the concept of sustainable packaging. First of all, the existing apple packaging analysis, mainly can be divided into plastic packaging and paper packaging two kinds, there are some problems, such as insufficient protective performance, insufficient air permeability, some wastes can not be degraded, which brings burden to the environment, imperfect information and so on. Secondly, in view of the circulation environment, product characteristics and deficiencies of the existing packaging of Luochuan Apples, we redesigned them in combination with the concept of sustainable packaging, including packaging paper that directly touches Apples, cushioning pads, and corrugated boxes that are used as transportation packaging and sales packaging at the same time. Design, through the design of materials, structure, size, and decoration, a complete set of apple packaging is obtained. Finally, the pallet stacking situation is compared with the existing packaging, and the cost is estimated. The results show that the designed packaging has good protection performance, high space utilization, environmentally friendly, more complete information, and the cost is only 72.2% of the existing packaging.

1 January 2021 in Complexity
Verified
Journal Article
Open access
PDF file
XXXiaoyan Xu
Xiaoyan Xu
WLWei Lv
Wei Lv
BZBeibei Zhang
Beibei Zhang
SZShuaipeng Zhou
Shuaipeng Zhou
WWWei Wei
Wei Wei
YLYusen Li
Yusen Li
With the fast development of web 2.0, information generation and propagation among online users become deeply interweaved. How to effectively and immediately discover the new emerging topic and further how to uncover its evolution law are still wide open and urgently needed by both research and practical fields. This paper proposed a novel early emerging topic detection and its evolution law identification framework based on dynamic community detection method on time‐evolving and scalable heterogeneous social networks. The framework is composed of three major steps. Firstly, a time‐evolving and scalable complex network denoted as KeyGraph is built up by deeply analyzing the text features of all kinds of data crawled from heterogeneous online social network platforms; secondly, a novel dynamic community detection method is proposed by which the new emerging topic is detected on the modeled time‐evolving and scalable KeyGraph network; thirdly, a unified directional topic propagation network modeled by a great number of short texts including microblogs and news titles is set up, and the topic evolution law of the previously detected early emerging topic is identified by fully utilizing local network variations and modularity optimization of the “time‐evolving” and directional topic propagation network. Our method is proved to yield preferable results on both a huge amount of computer‐generated test data and a great amount of real online network data crawled from mainstream heterogeneous social networks.

14 September 2025 in AI
Verified
Journal Article
Open access
PDF file
XZXintong Zhang
Xintong Zhang
BZBeibei Zhang
Beibei Zhang
HLHaoru Li
Haoru Li
HWHelin Wang
Helin Wang
YHYunqiao Huang
Yunqiao Huang
Traditional Reinforcement Learning (RL) struggles in dynamic decision-making due to data dependence, limited generalization, and imbalanced subjective/objective factors. This paper proposes an intelligent model combining the Model-Agnostic Meta-Learning (MAML) framework with the Actor–Critic algorithm to address these limitations. The model integrates the AHP-CRITIC weighting method to quantify strategic weights from both subjective expert experience and objective data, achieving balanced decision rationality. The MAML mechanism enables rapid generalization with minimal samples in dynamic environments via cross-task parameter optimization, drastically reducing retraining costs upon environmental changes. Evaluated on enterprise indicator anomaly decision-making, the model achieves significantly higher task reward values than traditional Actor–Critic, PG, and DQN using only 10–20 samples. It improves time efficiency by up to 97.23%. A proposed Balanced Performance Index confirms superior stability and adaptability. Currently integrated into an enterprise platform, the model provides efficient support for dynamic, complex scenarios. This research offers an innovative solution for intelligent decision-making under data scarcity and subjective-objective conflicts, demonstrating both theoretical value and practical potential.

28 May 2021
Verified
Conference Paper
Closed access
WWWei Wei
Wei Wei
HLHuiqing Liang
Huiqing Liang
BZBeibei Zhang
Beibei Zhang
RDRobertas Damasevicius
Robertas Damasevicius
Rafal SchererRafal Scherer
Rafal Scherer
In recent years, the rapid development of big data has made people's daily life very convenient, and at the same time, tasting all kinds of food has become an important activity for people to travel. Due to the vast territory of China, there are many types of cuisines with great differences, it is very important for travelers to understand the special regional cuisines in the area. This project aggregates regional food data based on big data, and provides tourists with efficient, stable and professional data retrieval and analysis services through a visual data interface, and provides intuitive, accurate, and real-time data support for the decision-making of finding characteristic regional food. This thesis first conducted a relevant understanding of big data and the overall situation of regional cuisine, analyzed the distribution of food in the sub-provincial city of Xi'an, explored the research methods and implementation methods of related projects at home and abroad, based on this, summarized the research of this project the goal. At the same time, the focus of this project is to analyze the price, score and popularity of regional food data analysis in my country, and to summarize, proofread and organize the data obtained before into standard and standardized data. Through the classification of basic information, the visual analysis and display of data is realized, and the key data urgently needed by decision makers are extracted from it. To analyze the needs of decision makers, establish corresponding strategies and measures to improve the quality of data services. The establishment of this system provides a useful supplement and improvement to the existing industry data analysis system. The system is mainly divided into six modules, which are data collection, data review, data summary, and visual data display modules. Among them, data collection includes crawling relevant data from the Internet and retrieving key data. The data audit function includes classifying the crawled data and reviewing its effectiveness. Data aggregation includes summarizing the filtered data in an excel table and passing Excel generates a visual chart that you want to know, and at the same time generates a word cloud by associating certain two related items in the data in the excel table. The visual data display module can more clearly show the results of data analysis to users, so that users can make better decisions. The visualization data uses AmChart Flash charts. The implementation of this system adopts Django Python Web framework, the development language chooses Python, the development tool adopted is PyCharm, and the database tool adopts MySQL.

1 November 2017
Verified
Conference Paper
Closed access
FYFulian Yin
Fulian Yin
BZBeibei Zhang
Beibei Zhang
GSGe Su
Ge Su
RZRuizhe Zhang
Ruizhe Zhang
At present, public opinion research on early warning model always use almost all history data, which can't predict the development trend of events timely. The paper presents an early warning model of public opinion based on the logistic model to dynamically describe the propagation rule and warn timely on public opinion. Regarding the hot words in micro-index as the research object, the paper studied the logistic model by mathematical modeling method, researched the characteristic point-in-time calculation of public opinion diffusion curve and monitoring and early warning of public opinion. The method was verified correctly and efficiently with the time series of the development trend of an incident in Sina micro-blog and the result showed that the study is practically useful.