@article{su2023,
  author = {Su, Zhan and Yang, Haochuan and Ai, Jun},
  title = {FPLV: Enhancing recommender systems with fuzzy preference, vector similarity, and user community for rating prediction},
  year = {2023},
  label = {su2023},
  doi = {10.1371/journal.pone.0290622},
  journal = {PLOS ONE},
  publisher = {Public Library of Science},
  month = {08},
  volume = {18},
  url = {https://doi.org/10.1371/journal.pone.0290622},
  pages = {e0290622},
  abstract = {Rating prediction is crucial in recommender systems as it enables personalized recommendations based on different models and techniques, making it of significant theoretical importance and practical value. However, presenting these recommendations in the form of lists raises the challenge of improving the list’s quality, making it a prominent research topic. This study focuses on enhancing the ranking quality of recommended items in user lists while ensuring interpretability. It introduces fuzzy membership functions to measure user attributes on a multi-dimensional item label vector and calculates user similarity based on these features for prediction and recommendation. Additionally, the user similarity network is modeled to extract community information, leading to the design of a set of corresponding recommendation algorithms. Experimental results on two commonly used datasets demonstrate the effectiveness of the proposed algorithm in enhancing list ranking quality, reducing prediction errors, and maintaining recommendation diversity and accurate user preference classification. This research highlights the potential of integrating heuristic methods with complex network theory and fuzzy techniques to enhance recommendation system performance with interpretability in mind.},
  number = {8},
}
@article{AI2023106842,
  author = {Jun Ai and Yifang Cai and Zhan Su and Dunlu Peng and Fengyu Zhao},
  title = {Measuring similarity based on user activeness in recommender systems to improve algorithm scalability},
  year = {2023},
  label = {AI2023106842},
  journal = {Engineering Applications of Artificial Intelligence},
  volume = {126},
  pages = {106842},
  issn = {0952-1976},
  doi = {https://doi.org/10.1016/j.engappai.2023.106842},
  url = {https://www.sciencedirect.com/science/article/pii/S0952197623010266},
  keywords = {Recommender systems, Scalability, Collaborative filtering, User activeness, Prediction accuracy},
  abstract = {Recommender systems analyze user preferences and predict their preferred products based on available data, saving users time in the search for preferred products. However, accurate recommendations for both the system and the user may require complicated computations or the need to store more neighbors, leading to a less scalable algorithm. To address this issue, we define user activity coefficients and then analyze the relationship between different activity coefficients and similarity to design a novel approach for measuring user activity-based similarity in recommender systems. By examining the similarity of inactive user groups, our approach considers the accurate calculation of their similarity as one of the keys to influencing the number of required neighbors for optimal performance. As compared to several advanced collaborative filtering algorithms on two datasets, the algorithm developed in this paper can reduce the number of neighbors by 35.58%–75.38% while maintaining high prediction accuracy. The results indicate that user activity in recommender systems has a significant impact on similarity evaluation, which should be considered in relevant models.},
}
@article{AI2023similarity,
  author = {Jun Ai and Tao He and Zhan Su},
  title = {Identifying influential nodes in complex networks based on resource allocation similarity},
  year = {2023},
  label = {AI2023similarity},
  journal = {Physica A: Statistical Mechanics and its Applications},
  volume = {627},
  pages = {129101},
  issn = {0378-4371},
  doi = {https://doi.org/10.1016/j.physa.2023.129101},
  url = {https://www.sciencedirect.com/science/article/pii/S0378437123006568},
  keywords = {Complex networks, Virtual node, Resource allocation, Node similarity},
  abstract = {With the shift in the focus of network science research from macroscopic statistical regularities to microscopic scales, identifying influential nodes in networks has become a commonly discussed and challenging problem in network science. There has been substantial research on identifying the influential nodes, but most methods generally suffer from the incompatibility between time complexity and computational accuracy. This study aims to alleviate the contradiction between time complexity and computational accuracy. Therefore, the novel method based on resource allocation similarity(RAS) is proposed to improve degree centrality by creatively introducing a virtual node and combining it with similarity theory. We simulate the epidemic spreading experiment based on the Susceptible–Infected (SI) model, the static attacking experiment, and the node differentiation experiment on six classical networks. Four typical methods are used to compare with our methods. The experimental results show that, in most cases, the proposed method has a dominant advantage over other comparison methods.},
}
@article{ai2023user_classified,
  author = {艾均 and 戴兴龙 and 苏湛},
  title = {基于用户复杂网络特征分类的协同过滤模型},
  year = {2023},
  label = {ai2023user_classified},
  journal = {计算机应用研究},
  volume = {40},
  number = {2},
  pages = {493-497,510},
  month = {2},
  url = {http://dx.chinadoi.cn/10.19734/j.issn.1001-3695.2022.07.0329},
  abstract = {协同过滤算法被广泛应用的同时一直存在着伸缩性和可扩展性困难的问题.针对该问题,提出了一种基于用户复杂网络特征分类的推荐系统协同过滤模型.首先,在用户集中基于度值选择特征用户,建立相似性阈值实现非特征用户分组;然后,构建用户—用户相似性网络,通过K-core分解完成网络中的社区标记;最后,目标用户在组内选择邻居,实现电影评分预测.基于MovieLens和Netflix数据集的实验结果表明,该算法与经典协同过滤算法相比,提升了时间和空间的性能,展现了更为出色的伸缩性和可扩展性.},},
}
@article{su2022,
  author = {Su, Zhan and Huang, Zhong and Ai, Jun and Zhang, Xuanxiong and Shang, Lihui and Zhao, Fengyu},
  title = {Enhancing the scalability of distance-based link prediction algorithms in recommender systems through similarity selection},
  year = {2022},
  label = {su2022},
  doi = {10.1371/journal.pone.0271891},
  journal = {PLOS ONE},
  publisher = {Public Library of Science},
  month = {07},
  volume = {17},
  url = {https://doi.org/10.1371/journal.pone.0271891},
  pages = { e0271891},
  abstract = {Slope One algorithm and its descendants measure user-score distance and use the statistical score distance between users to predict unknown ratings, as opposed to the typical collaborative filtering algorithm that uses similarity for neighbor selection and prediction. Compared to collaborative filtering systems that select only similar neighbors, algorithms based on user-score distance typically include all possible related users in the process, which needs more computation time and requires more memory. To improve the scalability and accuracy of distance-based recommendation algorithm, we provide a user-item link prediction approach that combines user distance measurement with similarity-based user selection. The algorithm predicts unknown ratings based on the filtered users by calculating user similarity and removing related users with similarity below a threshold, which reduces 26 to 29 percent of neighbors and improves prediction error, ranking, and prediction accuracy overall.},
  number = {7},
}
@article{ai2022identifying,
  author = {Ai, Jun and He, Tao and Su, Zhan and Shang, Lihui},
  title = {Identifying influential nodes in complex networks based on spreading probability},
  year = {2022},
  label = {ai2022identifying},
  journal = {Chaos, Solitons \& Fractals},
  volume = {164},
  pages = {112627},
  publisher = {Elsevier},
  url = {https://doi.org/10.1016/j.chaos.2022.112627},
  abstract = {The identification of node importance is a challenging topic in network science, and plays a critical role in understanding the structure and function of networks. Various centrality methods have been proposed to define the influence of nodes. However, most existing works do not directly use the node propagation capacity for measuring the importance of nodes. Moreover, those methods do not have a high enough ability to distinguish nodes with minor differences, and are not applicable to a wide range of network types. To address the issues, we first define a method to calculate the propagation capability of nodes and divide the nodes in the network into an infected source and the uninfected nodes. The propagation capability of a source node is calculated from the probability that uninfected nodes are infected by the source, either directly or indirectly. Based on measuring the propagation ability of each node in the network, we propose a novel centrality method based on node spreading probability (SPC). Empirical analysis is performed by Susceptible–Infected–Recovered (SIR) model and static attacking simulation. We use six classical networks, and five typical methods to validate SPC. The results demonstrate that our method balances the measurement of node importance in the network connectivity and propagation structure with superior ability to discriminate nodes.},},
}
@article{ai2022,
  author = {Ai, Jun and Cai, Yifang and Su, Zhan and Zhang, Kuan and Peng, Dunlu and Chen, Qingkui},
  title = {Predicting User-Item Links in Recommender Systems Based on Similarity-Network Resource Allocation},
  year = {2022},
  label = {ai2022},
  date = {2022-04-02},
  journal = {Chaos, Solitons \& Fractals},
  shortjournal = {Chaos, Solitons \& Fractals},
  volume = {158},
  pages = {112032},
  issn = {0960-0779},
  doi = {10.1016/j.chaos.2022.112032},
  url = {https://www.sciencedirect.com/science/article/pii/S0960077922002429},
  urldate = {2022-05-04},
  abstract = {Recommender systems and link prediction techniques have been widely used in areas such as online information filtering and improving user retrieval efficiency, and their performance and principles are of significant research interest. However, existing mainstream recommendation algorithms still face many challenges, such as the contradiction between prediction accuracy and recommendation diversity, and the limited scalability of algorithms due to the need to use a large number of neighbors for prediction. To address these two issues, this paper designs a user-item link prediction algorithm based on resource allocation within the user similarity network to enhance prediction accuracy while maintaining recommendation diversity and using as few neighbors as possible to achieve better algorithm scalability. We first calculate inter-user similarity based on user history ratings and construct a similarity network among users by filtering the similarity results; subsequently, based on the centrality and community features in this network, we design a similarity measure for resource allocation that incorporates the bipartite graph model and the similarity network; finally, we use this similarity method to select the set of prediction target neighbors, synthesize and use the similarity results, centrality, and community features for the prediction of user-item links. Experimental results on two well-known datasets with three state-of-the-art algorithms show that the proposed approach can improve the prediction accuracy by 2.34\% to 15.76\% in a shorter time and maintain a high recommendation diversity, and the ranking accuracy of recommendation is also improved. Compared with the benchmark algorithm with the second highest performance ranking, the method designed in this paper can further reduce the number of neighbors required at optimal prediction error by 25\% to 56\%. The study reveals that resource allocation in similarity networks successfully mines the features embedded in the recommender system, laying the foundation for further understanding the recommender system and improving the performance of related prediction methods.},
  langid = {english},
  keywords = {Centrality,Collaborative filtering,Community,Link prediction,Recommender systems,Resource allocation},
  file = {C\:\\Users\\aijun\\Zotero\\storage\\IILR3VNR\\S0960077922002429.html},
}
@article{su2021b,
  author = {苏, 湛 and 林, 祖夷 and 艾, 均},
  title = {类型相似性与品味影响力的推荐系统评分预测},
  year = {2021},
  label = {su2021b},
  date = {2021-12},
  journal = {小型微型计算机系统},
  volume = {42},
  number = {12},
  pages = {2530--2537},
  url = {http://xwxt.sict.ac.cn/CN/abstract/abstract6052.shtml},
  abstract = {电影推荐算法依靠计算用户的偏好差异进行推荐,以解决互联网时代的信息过载问题.传统协同过滤等推荐算法主要基于用户间对相同电影的评分差异计算用户偏好的相似性.这类方法忽视了用户的评分行为是一种实际上的选择行为,即便评分不高也体现出用户对该类型电影的兴趣.针对这一问题,本文设计了基于电影类型标签选择概率的用户间相似性计算方法,并建立了以用户为节点,以用户之间的相似性为边的推荐系统的复杂网络模型,并根据上述网络拓扑结构中的节点中心性数据,进一步设计了平衡用户品味影响力函数,调整了用户协同偏好的结果,提出了基于用户偏好相似性和用户品味影响力的电影评分预测方法.在MovieLens数据集上的实验结果表明,本文提出的算法与几种典型的现有方法相比较,可以有效的度量用户偏好的相似性以及抵消用户大众化品味影响力被高估在评分预测中带来的负面影响,与现有算法相比预测误差平均降低了2\%至5\%.},
}
@article{su2021a,
  author = {苏, 湛 and 王, 佳伟 and 艾, 均 and 沈, 昱明},
  title = {相似性与置信系数为基础的推荐系统评分预测},
  year = {2021},
  label = {su2021a},
  date = {2021-05},
  journal = {小型微型计算机系统},
  volume = {42},
  number = {05},
  pages = {984--989},
  issn = {1000-1220},
  url = {http://xwxt.sict.ac.cn/CN/abstract/abstract5817.shtml},
  urldate = {2022-07-29},
  abstract = {邻居选择和邻居数量对于推荐系统评分预测具有关键作用.本文采用复杂网络模型中多种聚类方法,针对现有方法通常基于单一相似性选择邻居的问题,建立用户为节点,相似性与置信系数为边的复杂网络模型,设计基于两个因素聚类的推荐系统评分预测算法,以提高推荐系统的预测准确性并减少最优预测所需的邻居数量.实验通过折十验证仿真用户对电影进行评分.结果表明,本文方法达到最优预测准确度时,预测所需邻居数量减少60\%.研究揭示了基于置信系数和相似性对邻居进行聚类,可以更加有效选出适当邻居,且聚类方法进行适当化简对性能影响较小.},
  langid = {chinese},
  keywords = {confidence coefficient,neighbor clustering,rating prediction,recommender systems,similarity,推荐系统,相似度,置信系数,评分预测,邻居聚类},
}
@article{su2021,
  author = {Su, Zhan and Lin, Zuyi and Ai, Jun and Li, Hui},
  title = {Rating {{Prediction}} in {{Recommender Systems Based}} on {{User Behavior Probability}} and {{Complex Network Modeling}}},
  year = {2021},
  label = {su2021},
  date = {2021-02-18},
  journal = {IEEE Access},
  volume = {9},
  pages = {30739--30749},
  issn = {2169-3536},
  doi = {10.1109/ACCESS.2021.3060016},
  abstract = {In recommender systems, measuring user similarity is essential for predicting a user’s ratings on items. Most traditional works calculate the similarity based on historical ratings shared between two users, without considering the probability of users’ different behaviors. To address this issue, our work designs a similarity measure based on the users’ historical behavior probabilities. Based on the similarity method, a complex network of user relationships is modeled. The user degree and community information of the modeled network, as well as the number of shared ratings between users, are used with the proposed similarity measure to design a rating prediction algorithm for recommender systems. Experiments based on MovieLens and Netflix data sets show that this method is effective and can successfully improve the accuracy of rating predictions and reduce the number of neighbors required to achieve the optimal prediction accuracy. Our research shows that in a complex system, the relationship between users can be effectively measured by the users’ historical behavior probability, providing a new perspective for future research on similarity measurement.},
  eventtitle = {{{IEEE Access}}},
  keywords = {\#ALL,\#SCI,\#SU,Complex network modeling,Complex networks,Correlation,degree centrality,link prediction,Motion pictures,Prediction algorithms,Predictive models,Probability,recommender systems,Recommender systems,user behavior probability},
  annotation = {WOS:000622088100001},
  file = {C\:\\Users\\aijun\\Zotero\\storage\\4HG5ESZK\\Su et al. - 2021 - Rating Prediction in Recommender Systems Based on .pdf;C\:\\Users\\aijun\\Zotero\\storage\\SU9P5SGK\\9357332.html},
}
@article{ai2021a,
  author = {Ai, Jun and Liu, Yayun and Su, Zhan and Zhao, Fengyu and Peng, Dunlu},
  title = {K-Core Decomposition in Recommender Systems Improves Accuracy of Rating Prediction},
  year = {2021},
  label = {ai2021a},
  date = {2021-03-17},
  journal = {International Journal of Modern Physics C},
  shortjournal = {Int. J. Mod. Phys. C},
  volume = {32},
  number = {07},
  pages = {2150087},
  issn = {0129-1831, 1793-6586},
  doi = {10.1142/S012918312150087X},
  url = {https://www.worldscientific.com/doi/abs/10.1142/S012918312150087X},
  urldate = {2021-06-24},
  abstract = {Users’ ratings in recommender systems can be predicted by their historical data, item content, or preferences. In recent literature, scientists have used complex networks to model a user–user or an item–item network of the RS. Also, community detection methods can cluster users or items to improve the prediction accuracy further. However, the number of links in modeling a network is too large to do proper clustering, and community clustering is an NP-hard problem with high computation complexity. Thus, we combine fuzzy link importance and K-core decomposition in complex network models to provide more accurate rating predictions while reducing the computational complexity. The experimental results show that the proposed method can improve the prediction accuracy by 4.64[Formula: see text] to 5.71[Formula: see text] on the MovieLens data set and avoid solving NP-hard problems in community detection compared with existing methods. Our research reveals that the links in a modeled network can be reasonably managed by defining fuzzy link importance, and that the K-core decomposition can provide a simple clustering method with relatively low computation complexity.},
  langid = {english},
  annotation = {WOS:000664643300002},
}
@article{su2020a,
  author = {Su, Zhan and Zheng, Xiliang and Ai, Jun and Shen, Yuming and Zhang, Xuanxiong},
  title = {Link Prediction in Recommender Systems Based on Vector Similarity},
  year = {2020},
  label = {su2020a},
  date = {2020-08-28},
  journal = {Physica A: Statistical Mechanics and its Applications},
  volume = {560},
  pages = {125154},
  issn = {0378-4371},
  doi = {10.1016/j.physa.2020.125154},
  url = {https://doi.org/10.1016/j.physa.2020.125154},
  abstract = {Link prediction provides methods for estimating potential connections in complex networks that have theoretical and practical relevance for personalized recommendations and various other applications. Traditional collaborative filtering algorithms treat similarity as a scalar value causing some information loss. This paper is primarily a novel approach to calculating user similarity that uses a vector to measure user similarity across multiple dimensions based on the items' characteristics. Our approach defines global similarity, local similarity and meta similarity to calculate vector similarity as indicators of similarity between users, revealing and measuring the difference between users' general preferences in different scenarios. The experimental results show that the presented similarity methods improve prediction accuracy in recommender systems compared to some state-of-art approaches. Our results confirm that user similarity can be measured differently when considering different classes of items, which extends our understanding of similarity measurement.},
  copyright = {All rights reserved},
  langid = {english},
  keywords = {\#ALL,\#SCI,\#SU,Collaborative filtering,Complex networks,Link prediction,Recommender system,Vector similarity},
  annotation = {WOS:000580429800023},
  file = {C\:\\Users\\aijun\\Zotero\\storage\\3XY3ID8P\\S0378437120306038.html},
}
@article{ai2020b,
  author = {Ai, Jun and Su, Zhan and Wang, Kaili and Wu, Chunxue and Peng, Dunlu},
  title = {Decentralized {{Collaborative Filtering Algorithms Based}} on {{Complex Network Modeling}} and {{Degree Centrality}}},
  year = {2020},
  label = {ai2020b},
  ids = {ai2020},
  date = {2020-08-18},
  journal = {IEEE Access},
  volume = {8},
  pages = {151242--151249},
  issn = {2169-3536},
  doi = {10.1109/ACCESS.2020.3017701},
  url = {https://doi.org/10.1109/ACCESS.2020.3017701},
  abstract = {Given that everyone online is saturated with information, the theoretical significance of recommendation algorithms is evident in the fact that users need help finding products and content they care about. Collaborative filtering predicts a user’s rating on an item by finding similar users that rated the item or similar items that were rated by the user, and using the selected similar neighbors to “collaboratively filter” the recommendation. In the process, selected neighbors are considered equally important despite their differences in popularity. Here, we explore a method of modeling recommender systems as networks that can be constructed by considering items as nodes and similarity between them as links. Our research shows that item centrality has a negative impact on the accuracy of rating predictions, which needs to be considered for better algorithm performance. Experiments show that collaborative filtering algorithms can be decentralized by our method and provide a better accuracy of rating prediction. Furthermore, the relationship between the prediction target and its neighbors can be further evaluated based on both their similarity and their centrality.},
  copyright = {All rights reserved},
  keywords = {\#AI,\#ALL,\#SCI,complex networks,decentralized collaborative filtering,degree centrality,network modeling,Recommender systems},
  annotation = {WOS:000565175000001},
  file = {C\:\\Users\\aijun\\Zotero\\storage\\GW9NYP69\\Ai 等。 - 2020 - Decentralized Collaborative Filtering Algorithms B.pdf;C\:\\Users\\aijun\\Zotero\\storage\\KITCXNIR\\9170514.html},
}
@article{wangkaili2019a,
  author = {{王凯莉} and {邬春学} and {艾均} and {苏湛}},
  title = {基于多阶邻居壳数的向量中心性度量方法研究},
  year = {2019},
  label = {wangkaili2019a},
  date = {2019-10-01},
  journal = {物理学报},
  volume = {68},
  number = {19},
  pages = {196402},
  issn = {1000-3290},
  doi = {10.7498/aps.68.20190662},
  url = {https://doi.org/10.7498/aps.68.20190662},
  issue = {19},
  keywords = {\#AI,\#ALL,\#SCI},
  annotation = {WOS:000489563400025},
}
@article{su2019,
  author = {Su, Zhan and Zheng, Xiliang and Ai, Jun and Shang, Lihui and Shen, Yuming},
  title = {Link Prediction in Recommender Systems with Confidence Measures},
  year = {2019},
  label = {su2019},
  date = {2019-08-30},
  journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
  volume = {29},
  number = {8},
  pages = {083133},
  issn = {1054-1500},
  doi = {10.1063/1.5099565},
  url = {https://doi.org/10.1063/1.5099565},
  abstract = {The link prediction aims at predicting missing or future links in networks, which provides theoretical significance and extensive applications in the related field. However, the degree of confidence in the prediction results has not been fully discussed in related works. In this article, we propose a similarity confidence coefficient and a confidence measure for link prediction. The former is used to balance the reliability of similarity calculation results, which might be untrustworthy due to the information asymmetry in the calculation, and also makes it easier to achieve the optimal accuracy with a smaller number of neighbors. The latter is used to quantify our confidence in the prediction results of each prediction. The experimental results based on the Movie-Lens data set show that prediction accuracy is improved when the similarity between the nodes is corrected by the similarity confidence coefficient. Second, the experiments also confirm that the confidence degree of the link prediction results can be measured quantitatively. Our research indicates that the confidence level on each prediction is determined by the amount of data used in the corresponding calculation, which can be measured quantitatively.},
  copyright = {All rights reserved},
  issue = {8},
  keywords = {\#ALL,\#SCI,\#SU},
  annotation = {WOS:000489227100020},
}
@article{ai2019c,
  author = {Ai, Jun and Liu, Yayun and Su, Zhan and Zhang, Hui and Zhao, Fengyu},
  title = {Link {{Prediction}} in {{Recommender Systems}} Based on {{Multi-factor Network Modeling}} and {{Community Detection}}},
  year = {2019},
  label = {ai2019c},
  ids = {ai2019a},
  date = {2019-06-10},
  journal = {EPL (Europhysics Letters)},
  volume = {126},
  number = {3},
  pages = {38003},
  publisher = {{IOP Publishing}},
  issn = {0295-5075},
  doi = {10.1209/0295-5075/126/38003},
  abstract = {Link prediction provides methods to estimate potential connections in complex networks, which has theoretical and practical significance for personalized recommendation and various other applications. Traditional collaborative filtering and other similar approaches have not utilized sufficient information on the community structure of networks. Therefore, this paper presents a link prediction model based on complex network modeling and community detection. In the approach, complex networks are constructed by considering the similarity among users' preference for genre selection, the similarity among users' rating distribution, and the similarity among items based on users' ratings. And the similarity calculation results are taken as weight of links as well as objects are considered as nodes in networks. On this basis, the community detection results can be obtained, and link prediction is performed with the community information considered. Multi-factor community detection based on node similarity improves the prediction process effectively and increases accuracy in our experiments. The result infers that users' behaviors, including rating an item and selecting an item over others, indicate a hidden community structure in the system, which can be used for link prediction and even for better understanding of complex systems.},
  copyright = {All rights reserved},
  issue = {3},
  keywords = {\#AI,\#ALL,\#SCI},
  annotation = {WOS:000471166600001},
}
@article{ai2019b,
  author = {Ai, Jun and Su, Zhan and Li, Yan and Wu, Chunxue},
  title = {Link Prediction Based on a Spatial Distribution Model with Fuzzy Link Importance},
  year = {2019},
  label = {ai2019b},
  ids = {ai2019},
  date = {2019-04-25},
  journal = {Physica A: Statistical Mechanics and its Applications},
  volume = {527},
  pages = {121155},
  publisher = {{Elsevier}},
  issn = {0378-4371},
  doi = {10.1016/j.physa.2019.121155},
  url = {https://doi.org/10.1016/j.physa.2019.121155},
  abstract = {Most of link prediction methods in recommender systems focuse on selecting neighbors according to similarities between objects. And the prediction of ratings is calculated based on the selected neighbors’ ratings. Thus, a novel model of link prediction is proposed in this paper. With the construction of an object network, neighbor selection can be obtained by the distance between two different objects, which are given positions in a spatial distribution topology by algorithm. A fuzzy link importance measure is also presented to balance the topology density and spatial distribution of the network. We use number of tags shared by objects, as well as ratings on objects given by different users, to measure the weight between each pair of nodes. Moreover, the method based on shared tags avoids cold start for new objects. And the algorithm considering rating information improves the accuracy of prediction compared to some existing results.},
  copyright = {All rights reserved},
  keywords = {\#AI,\#ALL,\#SCI,Complex networks,Fuzzy link importance,Link prediction,Recommender systems,Spatial distribution},
  annotation = {WOS:000480625700028},
}
@article{su2017a,
  author = {Su, Zhan and Ai, Jun and Zhang, Qingling and Xiong, Naixue},
  title = {An Improved Robust Finite-Time Dissipative Control for Uncertain Fuzzy Descriptor Systems with Disturbance},
  year = {2017},
  label = {su2017a},
  ids = {su2017},
  date = {2017-01-13},
  journal = {International Journal of Systems Science},
  volume = {48},
  number = {8},
  pages = {1581--1596},
  publisher = {{Taylor \& Francis}},
  issn = {0020-7721},
  doi = {10.1080/00207721.2016.1277405},
  url = {https://doi.org/10.1080/00207721.2016.1277405},
  copyright = {All rights reserved},
  issue = {8},
  keywords = {\#ALL,\#SCI,\#SU},
  annotation = {WOS:000396823800002},
}
@article{su2015b,
  author = {Su, Zhan and Zhang, Qingling and Ai, Jun and Sun, Xin},
  title = {Finite-Time Fuzzy Stabilisation and Control for Nonlinear Descriptor Systems with Non-Zero Initial State},
  year = {2015},
  label = {su2015b},
  ids = {su2015},
  date = {2015-04-02},
  journal = {International Journal of Systems Science},
  volume = {46},
  number = {2},
  pages = {364--376},
  publisher = {{Taylor \& Francis}},
  issn = {0020-7721},
  doi = {10.1080/00207721.2013.783949},
  url = {https://doi.org/10.1080/00207721.2013.783949},
  copyright = {All rights reserved},
  issue = {2},
  keywords = {\#ALL,\#SCI,\#SU},
  annotation = {WOS:000343212300015},
}
@article{ai2013c,
  author = {Ai, Jun and Zhao, Hai and Carley, Kathleen M and Su, Zhan and Li, Hui},
  title = {Neighbor Vector Centrality of Complex Networks Based on Neighbors Degree Distribution},
  year = {2013},
  label = {ai2013c},
  ids = {ai2013a},
  date = {2013-04-18},
  journal = {The European Physical Journal B},
  volume = {86},
  number = {4},
  pages = {163},
  publisher = {{Springer}},
  issn = {1434-6028},
  doi = {10.1140/epjb/e2013-30812-2},
  url = {https://link.springer.com/article/10.1140/epjb/e2013-30812-2},
  copyright = {All rights reserved},
  issue = {4},
  keywords = {\#AI,\#ALL,\#SCI},
  annotation = {WOS:000318408100048},
}
@article{ai2013b,
  author = {Ai, Jun and Zhao, Hai and Carley, Kathleen M. and Su, Zhan and Li, Hui},
  title = {Evolution of {{IPv6 Internet}} Topology with Unusual Sudden Changes},
  year = {2013},
  label = {ai2013b},
  ids = {ai2013,jun2013},
  date = {2013-07-01},
  journal = {Chinese Physics B},
  volume = {22},
  number = {7},
  pages = {078902},
  publisher = {{IOP Publishing}},
  issn = {1674-1056},
  doi = {10.1088/1674-1056/22/7/078902},
  url = {https://doi.org/10.1088%2F1674-1056%2F22%2F7%2F078902},
  abstract = {The evolution of Internet topology is not always smooth but sometimes with unusual sudden changes. Consequently, identifying patterns of unusual topology evolution is critical for Internet topology modeling and simulation. We analyze IPv6 Internet topology evolution in IP-level graph to demonstrate how it changes in uncommon ways to restructure the Internet. After evaluating the changes of average degree, average path length, and some other metrics over time, we find that in the case of a large-scale growing the Internet becomes more robust; whereas in a top—bottom connection enhancement the Internet maintains its efficiency with links largely decreased.},
  copyright = {All rights reserved},
  issue = {7},
  keywords = {\#AI,\#ALL,\#SCI},
  annotation = {WOS:000321898100104},
}
@article{su2012b,
  author = {Su, Zhan and Zhang, Qingling and Ai, Jun},
  title = {Practical and Finite-Time Fuzzy Adaptive Control for Nonlinear Descriptor Systems with Uncertainties of Unknown Bound},
  year = {2012},
  label = {su2012b},
  ids = {su2013},
  date = {2012-05-21},
  journal = {International Journal of Systems Science},
  volume = {44},
  number = {12},
  pages = {2223--2233},
  publisher = {{Taylor \& Francis Group}},
  url = {https://doi.org/10.1080/00207721.2012.687784},
  copyright = {All rights reserved},
  issue = {12},
  keywords = {\#ALL,\#SCI,\#SU},
}