Harbin Engineering University

About: Harbin Engineering University is a education organization based out in Harbin, Heilongjiang, China. It is known for research contribution in the topics: Control theory & Computer science. The organization has 31149 authors who have published 27940 publications receiving 276787 citations. The organization is also known as: HEU.

SVMs Classification Based Two-side Cross Domain Collaborative Filtering by inferring intrinsic user and item features

Abstract: Recently, Cross Domain Collaborate Filtering (CDCF) is a new way to alleviate the sparsity problem in the recommender systems. CDCF solves the sparsity problem by transferring rating knowledge from auxiliary domains. Most of previous work only uses one-side (user-side or item-side) auxiliary domain information to help the recommendation in the target domain. In this paper, we propose a two-side Cross Domain Collaborate Filtering model. We assume that there exist two auxiliary domains, i.e., user-side domain and item-side domain, where the user-side auxiliary domain shares the same aligned users with the target domain, and the item-side shares the same aligned items. Also both the two auxiliary domains contain dense rating data. In this scenario, we first employ the bi-orthogonal tri-factorization model to infer the intrinsic user and item features from the user-side and item-side auxiliary domain respectively. The inferred intrinsic features are independent on domains. Then we convert the recommendation problem into a classification problem. In detail, we use the inferred user and item features to compose the feature vector, and use the corresponding rating as the class label. Thus the user-item interactions can be represented as training samples. Finally, we employ SVMs model to solve the converted classification problem. The major advantage of our model is that it can make use of both user-side and item-side shared information. Furthermore, it can infer the domain independent user and item features. Thus it can transfer knowledge from auxiliary domains more effectively. We conduct extensive experiments to show that the proposed model performs significantly better than many state-of-the-art single domain and cross domain CF methods.

Construction of nitrogen-doped porous carbon buildings using interconnected ultra-small carbon nanosheets for ultra-high rate supercapacitors

Abstract: Here, for the first time, we demonstrate a facile one-step construction of a nitrogen-doped porous carbon building (N-PCB) using interconnected ultra-small carbon nanosheets through the carbonization of biomass (Auricularia) using ZnCl2 as the activating agent and NH4Cl as the nitrogen source. Due to its high specific surface area (1607 m2 g−1) with a high mesopore ratio (91%), interconnected porous structure with short ion diffusion paths, and nitrogen doping (4.8 at%), the N-PCB electrode exhibits a high specific capacitance of 347 F g−1 at 1 A g−1, excellent rate capability (278 F g−1 at 50 A g−1, 80% of capacitance retention) and outstanding cycling stability (only 2% loss in specific capacitance after 10 000 cycles). Moreover, the assembled N-PCB symmetric supercapacitor is stabilized with excellence cycling stability (4% loss after 20 000 cycles) at 1.6 V in 1 M Na2SO4 aqueous electrolyte, delivering a high energy density of 22 W h kg−1, much higher than that of most of the reported carbon-based symmetric supercapacitors in aqueous electrolytes. Therefore, these exciting results suggest a low-cost and environmentally friendly design of electrode materials for high-performance supercapacitors.