Beihang University

About: Beihang University is a education organization based out in Beijing, China. It is known for research contribution in the topics: Control theory & Microstructure. The organization has 67002 authors who have published 73507 publications receiving 975691 citations. The organization is also known as: Beijing University of Aeronautics and Astronautics.

Exploiting internal and external semantics for the clustering of short texts using world knowledge

Abstract: Clustering of short texts, such as snippets, presents great challenges in existing aggregated search techniques due to the problem of data sparseness and the complex semantics of natural language. As short texts do not provide sufficient term occurring information, traditional text representation methods, such as ``bag of words" model, have several limitations when directly applied to short texts tasks. In this paper, we propose a novel framework to improve the performance of short texts clustering by exploiting the internal semantics from original text and external concepts from world knowledge. The proposed method employs a hierarchical three-level structure to tackle the data sparsity problem of original short texts and reconstruct the corresponding feature space with the integration of multiple semantic knowledge bases -- Wikipedia and WordNet. Empirical evaluation with Reuters and real web dataset demonstrates that our approach is able to achieve significant improvement as compared to the state-of-the-art methods.

RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment

Abstract: RGB-Infrared (IR) person re-identification is an important and challenging task due to large cross-modality variations between RGB and IR images. Most conventional approaches aim to bridge the cross-modality gap with feature alignment by feature representation learning. Different from existing methods, in this paper, we propose a novel and end-to-end Alignment Generative Adversarial Network (AlignGAN) for the RGB-IR RE-ID task. The proposed model enjoys several merits. First, it can exploit pixel alignment and feature alignment jointly. To the best of our knowledge, this is the first work to model the two alignment strategies jointly for the RGB-IR RE-ID problem. Second, the proposed model consists of a pixel generator, a feature generator and a joint discriminator. By playing a min-max game among the three components, our model is able to not only alleviate the cross-modality and intra-modality variations, but also learn identity-consistent features. Extensive experimental results on two standard benchmarks demonstrate that the proposed model performs favourably against state-of-the-art methods. Especially, on SYSU-MM01 dataset, our model can achieve an absolute gain of 15.4% and 12.9% in terms of Rank-1 and mAP.

Modeling and solving the dynamic user equilibrium route and departure time choice problem in network with queues

Abstract: This paper considers a simultaneous route and departure (SRD) time choice equilibrium assignment problem in network with queues The problem is modeled on discrete-time basis and formulated as an equivalent “zero-extreme value” minimization problem, in which the first-in-first-out (FIFO) behavior at intersection is guaranteed by proper formulation of the dynamic link travel times A heuristic solution algorithm is proposed, which simulates a normal day-to-day dynamic system by a route/time-swapping process, thereby reaching to an extreme point of the minimization problem The existence of discrete-time dynamic user-equilibrium (UE) solutions is investigated The iteration-to-iteration stability of the proposed algorithm is discussed, together with numerical results on two example networks

Designing Advanced Catalysts for Energy Conversion Based on Urea Oxidation Reaction.

Abstract: Urea oxidation reaction (UOR) is the underlying reaction that determines the performance of modern urea-based energy conversion technologies. These technologies include electrocatalytic and photoelectrochemical urea splitting for hydrogen production and direct urea fuel cells as power engines. They have demonstrated great potentials as alternatives to current water splitting and hydrogen fuel cell systems with more favorable operating conditions and cost effectiveness. At the moment, UOR performance is mainly limited by the 6-electron transfer process. In this case, various material design and synthesis strategies have recently been reported to produce highly efficient UOR catalysts. The performance of these advanced catalysts is optimized by the modification of their structural and chemical properties, including porosity development, heterostructure construction, defect engineering, surface functionalization, and electronic structure modulation. Considering the rich progress in this field, the recent advances in the design and synthesis of UOR catalysts for urea electrolysis, photoelectrochemical urea splitting, and direct urea fuel cells are reviewed here. Particular attention is paid to those design concepts, which specifically target the characteristics of urea molecules. Moreover, challenges and prospects for the future development of urea-based energy conversion technologies and corresponding catalysts are also discussed.

Predicting EGFR mutation status in lung adenocarcinoma on computed tomography image using deep learning

Abstract: Epidermal growth factor receptor (EGFR) genotyping is critical for treatment guidelines such as the use of tyrosine kinase inhibitors in lung adenocarcinoma. Conventional identification of EGFR genotype requires biopsy and sequence testing which is invasive and may suffer from the difficulty of accessing tissue samples. Here, we propose a deep learning model to predict EGFR mutation status in lung adenocarcinoma using non-invasive computed tomography (CT). We retrospectively collected data from 844 lung adenocarcinoma patients with pre-operative CT images, EGFR mutation and clinical information from two hospitals. An end-to-end deep learning model was proposed to predict the EGFR mutation status by CT scanning. By training in 14 926 CT images, the deep learning model achieved encouraging predictive performance in both the primary cohort (n=603; AUC 0.85, 95% CI 0.83–0.88) and the independent validation cohort (n=241; AUC 0.81, 95% CI 0.79–0.83), which showed significant improvement over previous studies using hand-crafted CT features or clinical characteristics (p Since CT is routinely used in lung cancer diagnosis, the deep learning model provides a non-invasive and easy-to-use method for EGFR mutation status prediction.