In recent years, with the development of smart devices, mobile users can use them to sense the environment. In order to improve the data quality and achieve maximum profits, incentive mechanism is needed to motivate users to participate. In this paper, reputation mechanism, participant selection, task allocation and joint pricing in mobile crowdsourcing system are studied. A user reputation evaluation method is proposed, and a participant selection algorithm(PSA) based on user reputation is proposed. Besides, a social welfare maximization algorithm(SWMA) is proposed, which achieves task pricing with maximizing the interests of all parties, including both task publishers and mobile users. The social welfare maximization problem is divided into local optimization sub-problems which can be solved by double decomposition. It is proved that the algorithm converges to the optimal solution. Results of simulations verify that algorithms PSA and SWMA are effective.
Tri-Training算法是半监督算法中的一种,其初始分类器性能受有标记样本影响较大,当样本数目不足时,分类器性能相对较弱,会直接影响后续迭代.为此提出IFS-Tri-Training(Tri-Training based on intuitionistic fuzzy sets)算法,引入SOM算法构建直觉模糊集,使得分类器在多因素下综合判别无标记样本,提高无标记样本的使用率,从而在迭代中扩展有标记样本集.在多个UCI数据上进行实验,结果数据表明,分类器的性能得到提高,学习无标记样本过程是影响分类器的关键点.
