主持纵向项目: 1.国家自然科学基金面上项目《代价敏感学习的粗糙集方法》,编号:61379098,经费75万元。 发表SCI检索论文100余篇,一区30余篇,高被引论文10篇,h-index=31,入选斯坦福大学发布的“2022全球前2%顶尖科学家榜”。代表性论文包括: [1] 闵帆, 何华平, 钱宇华, 祝峰, Test-cost-sensitive attribute reduction, Information Sciences, 181(22), pp. 4928–4942, 2011.(300+次引用) [2] 张恒汝, 闵帆, Three-way recommender systems based on random forests, Knowledge-Based Systems. 91(2016)275–286.(200+次引用) [3] 张恒汝, 闵帆, 石兵, Regression-based three-way recommendation, Information Sciences. 378(1)(2017)444–461.(100+次引用) [4] 闵帆, 胡清华, 祝峰, Feature selection with test cost constraint, International Journal of Approximate Reasoning, 55(1), pp. 167–179, 2014(100+次引用) [5] 闵帆, 刘启和, A hierachical model for cost-sensitive decision systems, Information Sciences 179(14), pp. 2442–2452, 2009.(100+次引用) [6] 闵帆, 祝峰, Attribute reduction of data with error ranges and test costs, Information Sciences, 211, pp. 48–67, 2012.(100+次引用) [7] 汪敏, 闵帆, 吴彦学, 张智恒, Active learning through density clustering, Expert Systems with Applications. 85(1)(2017)305–317.(100+次引用) [8] 杨梅, 张雨轩, 王熙照, 闵帆. Multi-instance ensemble learning with discriminative bags. IEEE Transactions on Systems Man Cybernetics-Systems. 52(9)(2022)5456–5467. [9] 汪敏, 杨春宇, 赵飞, 闵帆, 王熙照. Cost-sensitive active learning for incomplete data. IEEE Transactions on Systems Man Cybernetics-Systems. 53(1)(2023)405–416. [10] 汪敏, 赵鹏, 陆欣, 闵帆, 王熙照. Fine-grained visual categorization: A spatial–frequency feature fusion perspective. IEEE Transactions on Circuits and Systems for Video Technology. (2023). [11] 钱坤, 闵雪阳, 程玉胜, 闵帆. Weight matrix sharing for multi-label learning. Pattern Recognition. 136(2023)109156. [12] 张恒汝, 秋颖, 朱科霖, 闵帆. Lower bound estimation of recommendation error through user uncertainty modeling. Pattern Recognition. 136(2023)109171 [13] 闵帆, 王林蓉, 潘树林, 宋国杰. Fast convex set projection with deep prior for seismic interpolation. Expert Systems with Applications. 213(2023)119256. [14] 闵帆, 王林蓉, 潘树林, 宋国杰. D2UNet: Dual decoder U-Net for seismic image super-resolution reconstruction. IEEE Transactions on Geoscience and Remote Sensing (2023). |