LSLijun Sun

Lijun Sun

*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


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


Latest Publications

  • Sales Forecasting Method for Inventory Replenishment Systems of Vehicle Energy Stations Without Stockouts

    by Fangfang Li, Lijun Sun, Nan Kong, Hang Zhang, Lipo Mo

    Accurate sales forecasting facilitates efficient and proactive replenishment, which is essential to inventory replenishment systems of vehicle energy stations that do not allow stockouts. Forecasting the sales in these systems becomes tricky because sales are highly uncertain and have different patterns at different periods. Traditional forecasting methods used in this case can greatly underestimate larger sales or overestimate smaller ones. We thus propose a novel sales forecasting method considering the fuzzy recognition technique of sales patterns and combining it with the forecasting technique based on deep learning. In this article, we first construct an index to describe the time dependence of sales. Subsequently, we determine sales patterns based on the index and fuzzy recognition. Finally, we select the long short-term memory based point forecasting model or quantile long and short-term memory based quantile forecasting model based on sales patterns, which can also fully capture the sales uncertainty and achieve the goal of reducing costs and ensuring no stockouts. Numerical experiments show that the proposed method has high prediction accuracy and can effectively reduce costs while ensuring no stockouts.


  • Open Access

    Hidden Addressing Encoding for DNA Storage

    by Penghao Wang, Ziniu Mu, Lijun Sun, Shuqing Si, Bin Wang

    DNA is a natural storage medium with the advantages of high storage density and long service life compared with traditional media. DNA storage can meet the current storage requirements for massive data. Owing to the limitations of the DNA storage technology, the data need to be converted into short DNA sequences for storage. However, in the process, a large amount of physical redundancy will be generated to index short DNA sequences. To reduce redundancy, this study proposes a DNA storage encoding scheme with hidden addressing. Using the improved fountain encoding scheme, the index replaces part of the data to realize hidden addresses, and then, a 10.1 MB file is encoded with the hidden addressing. First, the Dottup dot plot generator and the Jaccard similarity coefficient analyze the overall self-similarity of the encoding sequence index, and then the sequence fragments of GC content are used to verify the performance of this scheme. The final results show that the encoding scheme indexes with overall lower self-similarity, and the local thermodynamic properties of the sequence are better. The hidden addressing encoding scheme proposed can not only improve the utilization of bases but also ensure the correct rate of DNA storage during the sequencing and decoding processes.


  • Demand Forecasting for Petrol Products in Gas Stations Using Clustering and Decision Tree

    by Lijun Sun, Xiuwu Xing, Yaxian Zhou, Xiangpei Hu

    Demand forecasting for petrol products in gas stations is crucial to the planning of initiative distribution of petrol products, especially to the stability of product supply in petroleum companies. In this paper, a novel scheme of demand forecasting based on clustering and a decision tree is proposed, which uses a decision tree and integrates the results of clustering validity indices. First, the proposed scheme uses a k-means algorithm to divide the sales data into multiple disjointed clusters, evaluates the clustering result of the daily sales curve of a product according to seven validity indices and determines the optimal number of clustering. Next, the relationship between the sales pattern and the relevant influence factors is described using a decision tree, which can categorize a future day’s sales pattern with these factors into the most suitable cluster to predict the quantity of the demand and the peak demand time windows for each gas station. Finally, three months’ worth of sales data is collected from a gas station in Dalian city, China, to illustrate the proposed forecasting scheme. Experimental results demonstrate that the scheme is an effective alternative for the demand forecasting for petrol products because it outperforms three other selected methods.


  • Open Access

    Design of Green Cold Chain Networks for Imported Fresh Agri-Products in Belt and Road Development

    by Yan Fang, Yiping Jiang, Lijun Sun, Xingxing Han

    The development of Belt and Road has seen a boom of imported fresh agri-products in China. This stimulates the growth of refrigerated transport, which accounts for much more carbon emissions than traditional transport. Designing a sustainable cold chain network is of vital importance from both financial and environmental perspectives. In this research, a multi-objective linear programming model is proposed for green cold chain design for multiple imported fresh agri-products in China to balance between the two competing goals—the total cost and carbon emissions. The effect of the outdoor air temperature on the carbon emissions of transportation and maintaining distribution centers is considered. By applying the ε-constraint method, the multi-objective model is solved. Numerical examples derived from the scenario of imported fresh-agri products in China are conducted to shed light on green cold chain design under Belt and Road development.


  • An Intelligent Query System Based on Chinese Short Message Service for Restaurant Recommendation

    by Wubin. Guo, Xiangpei. Hu, Kuanjiu. Zhou, Lijun. Sun

    With the development of modern communication technology, the mobile communication market has grown impressively in China. China mobile and China Unicom have set up the largest mobile communication networks in the world. Concurrently, the number of Chinese short message service (SMS) user has been increased rapidly in recent 10 years. This huge customer infrastructure means immensurable market potential. The SMS-based restaurant recommendation is one of such services with potential market in China. With the promotion of their living level, more and more Chinese people spend their spare time on exciting trips to experience different custom and culture, especially the splendid catering culture in China. Therefore, they are most interested in where they can enjoy their favorite food while traveling in an unfamiliar city, which brings new commercial opportunities. We develop a SMS-based prototype system to help travelers find suitable restaurants. The architecture of the restaurant recommendation system. We choose SMS as the commutation technique between mobile devices and the restaurant recommendation server. As an unnecessarily advanced technology, SMS provides an agile communication way at a lower price (communication service providers charge for sending a short message much less than connecting a call between different cities in China), and is popular among Chinese people, especially among the youth. The most important feature of this system is the ability to deal with the complexities of Chinese language query. A natural language interface of database query is adopted to simplify the user's interaction with the system. Users can send their special requirements to the restaurant recommendation server in constrained Chinese natural language form. The system then analyzes the words, grammar and semantic content of the message in order to precisely determine the most adequate choice. Moreover, the intelligence of the system is enhanced to meet users' needs. Before returning the results, the server will carry out a knowledge-based reasoning process to find out the restaurants that qualify for supplying user's favorite dishes with appropriate prices. A fuzzy method is introduced to solve the problem of understanding uncertain expressions of human languages, which makes the results of reasoning fit users' requirements more closely. Furthermore, the system will also offer a user the shortest paths to the suitable restaurants if the user's mobile terminal is equipped with GIS/GPS modules. This work provides a new applicable field for mobile devices and improves the intelligence of their services. Its application will provide new opportunities for both users and providers of recommendation service in tourism industries.