Xi Sun
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
Xi Sun has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Giovannipaolo Ferrari
Department of Human, Philosophical and Educational Sciences (DISUFF), University of Salerno, Fisciano, Italy
1 shared publication - Hang Zhang
School of Economics and Management, University of Science and Technology Beijing, Beijing 100083, China
1 shared publication J. Yan
National laboratory of radar signal processing Xidian university, Xi’an, Shanxi, China
1 shared publication- Li Ma
School of Information Engineering, China University of Geosciences, Beijing, Beijing 100083, China
1 shared publication - Mingxin Gan
School of Economics and Management, University of Science and Technology Beijing, Beijing, China
1 shared publication - Yingxin Tan
Department of Philosophy, Sociology, Education, and Applied Psychology, University of Padua, Padova 35139, Italy
1 shared publication
Latest Publications
- Open Access
- 15 October 2024
- Published by Institute of Central Computation and Knowledge Inc. in ICCK Transactions on Sensing, Communication, and Control
- Vol. 1 (1) , 30-51
Recommender System: A Comprehensive Overview of Technical Challenges and Social Implications
The proliferation of Recommender Systems (RecSys), driven by their expanding application domains, explosive data growth, and exponential advancements in computing capabilities, has cultivated a dynamic and evolving research landscape. This paper comprehensively reviews the foundational concepts, methodologies, and challenges associated with RecSys from technological and social scientific lenses. Initially, it categorizes personalized RecSys technical solutions into five paradigms: collaborative filtering, scenario-aware, knowledge & data co-driven approaches, large language models, and hybrid models integrating diverse data sources. Subsequently, the paper analyses the key challenges and future trajectories in five technical domains: general technologies, recommendation accuracy, cold-start problems, explainability, and privacy protection. The review also explores the intersection between RecSys and social sciences, emphasizing how RecSys is shaped by and, in turn, shapes social structures, cultural norms, and societal biases, alongside its influence on decision-making, behaviour, and identity formation. Identified research gaps highlight the need for deeper investigations into cross-cultural variations and long-term effects, as well as for integrating sociological and psychological insights with technical designs. This review systematically encapsulates the current research landscape of RecSys across technological and sociological domains, thereby guiding researchers toward identifying potential advancements and future research directions.
- 15 October 2024
- Published by Institute of Central Computation and Knowledge Inc. in ICCK Transactions on Sensing, Communication, and Control
- Vol. 1 (1) , 30-51
Open AccessRecommender System: A Comprehensive Overview of Technical Challenges and Social Implications
The proliferation of Recommender Systems (RecSys), driven by their expanding application domains, explosive data growth, and exponential advancements in computing capabilities, has cultivated a dynamic and evolving research landscape. This paper comprehensively reviews the foundational concepts, methodologies, and challenges associated with RecSys from technological and social scientific lenses. Initially, it categorizes personalized RecSys technical solutions into five paradigms: collaborative filtering, scenario-aware, knowledge & data co-driven approaches, large language models, and hybrid models integrating diverse data sources. Subsequently, the paper analyses the key challenges and future trajectories in five technical domains: general technologies, recommendation accuracy, cold-start problems, explainability, and privacy protection. The review also explores the intersection between RecSys and social sciences, emphasizing how RecSys is shaped by and, in turn, shapes social structures, cultural norms, and societal biases, alongside its influence on decision-making, behaviour, and identity formation. Identified research gaps highlight the need for deeper investigations into cross-cultural variations and long-term effects, as well as for integrating sociological and psychological insights with technical designs. This review systematically encapsulates the current research landscape of RecSys across technological and sociological domains, thereby guiding researchers toward identifying potential advancements and future research directions.
- 22 September 2023
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 24 (9) , 1273-1286
Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation
Next point-of-interest (POI) recommendation is an important personalized task in location-based social networks (LBSNs) and aims to recommend the next POI
- 22 September 2023
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 24 (9) , 1273-1286
Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation
Next point-of-interest (POI) recommendation is an important personalized task in location-based social networks (LBSNs) and aims to recommend the next POI
- 3 June 2021
- Published by Institution of Engineering and Technology (IET) in IET Conference Proceedings
- Vol. 2020 (9) , 1296-1301
Research on multi-sensor mission planning in target tracking system based on SVM
In target tracking mission planning, one of the difficulties is to generate Multi-sensor mission planning under the guidance of resources information. This paper proposes a SVM-based target tracking multi-sensor mission planning method. The method firstly generates a mission-planning database as a training set based on typical mission scenarios. Then, the hierarchical learning model was established by SVM algorithm, and the sensor-target allocation and sensor resource allocation were carried out respectively. After the model was trained by the scheme database, the intelligent generation of mission planning scheme can be realized. So that the feasibility and robustness of the method are verified by simulation
- 3 June 2021
- Published by Institution of Engineering and Technology (IET) in IET Conference Proceedings
- Vol. 2020 (9) , 1296-1301
Research on multi-sensor mission planning in target tracking system based on SVM
In target tracking mission planning, one of the difficulties is to generate Multi-sensor mission planning under the guidance of resources information. This paper proposes a SVM-based target tracking multi-sensor mission planning method. The method firstly generates a mission-planning database as a training set based on typical mission scenarios. Then, the hierarchical learning model was established by SVM algorithm, and the sensor-target allocation and sensor resource allocation were carried out respectively. After the model was trained by the scheme database, the intelligent generation of mission planning scheme can be realized. So that the feasibility and robustness of the method are verified by simulation
- Open Access
- 15 January 2021
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 10 (1) , 36
Incorporating Memory-Based Preferences and Point-of-Interest Stickiness into Recommendations in Location-Based Social Networks
In location-based social networks (LBSNs), point-of-interest (POI) recommendations facilitate access to information for people by recommending attractive locations they have not previously visited. Check-in data and various contextual factors are widely taken into consideration to obtain people’s preferences regarding POIs in existing POI recommendation methods. In psychological effect-based POI recommendations, the memory-based attenuation of people’s preferences with respect to POIs, e.g., the fact that more attention is paid to POIs that were checked in to recently than those visited earlier, is emphasized. However, the memory effect only reflects the changes in an individual’s check-in trajectory and cannot discover the important POIs that dominate their mobility patterns, which are related to the repeat-visit frequency of an individual at a POI. To solve this problem, in this paper, we developed a novel POI recommendation framework using people’s memory-based preferences and POI stickiness, named U-CF-Memory-Stickiness. First, we used the memory-based preference-attenuation mechanism to emphasize personal psychological effects and memory-based preference evolution in human mobility patterns. Second, we took the visiting frequency of POIs into consideration and introduced the concept of POI stickiness to identify the important POIs that reflect the stable interests of an individual with respect to their mobility behavior decisions. Lastly, we incorporated the influence of both memory-based preferences and POI stickiness into a user-based collaborative filtering framework to improve the performance of POI recommendations. The results of the experiments we conducted on a real LBSN dataset demonstrated that our method outperformed other methods.
- 15 January 2021
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 10 (1) , 36
Open AccessIncorporating Memory-Based Preferences and Point-of-Interest Stickiness into Recommendations in Location-Based Social Networks
In location-based social networks (LBSNs), point-of-interest (POI) recommendations facilitate access to information for people by recommending attractive locations they have not previously visited. Check-in data and various contextual factors are widely taken into consideration to obtain people’s preferences regarding POIs in existing POI recommendation methods. In psychological effect-based POI recommendations, the memory-based attenuation of people’s preferences with respect to POIs, e.g., the fact that more attention is paid to POIs that were checked in to recently than those visited earlier, is emphasized. However, the memory effect only reflects the changes in an individual’s check-in trajectory and cannot discover the important POIs that dominate their mobility patterns, which are related to the repeat-visit frequency of an individual at a POI. To solve this problem, in this paper, we developed a novel POI recommendation framework using people’s memory-based preferences and POI stickiness, named U-CF-Memory-Stickiness. First, we used the memory-based preference-attenuation mechanism to emphasize personal psychological effects and memory-based preference evolution in human mobility patterns. Second, we took the visiting frequency of POIs into consideration and introduced the concept of POI stickiness to identify the important POIs that reflect the stable interests of an individual with respect to their mobility behavior decisions. Lastly, we incorporated the influence of both memory-based preferences and POI stickiness into a user-based collaborative filtering framework to improve the performance of POI recommendations. The results of the experiments we conducted on a real LBSN dataset demonstrated that our method outperformed other methods.