A5086328631- Advanced Graph Theory Research
- Graph theory and applications
- Graph Labeling and Dimension Problems
- Pharmaceutical and Antibiotic Environmental Impacts
- Supercapacitor Materials and Fabrication
- Parallel Computing and Optimization Techniques
- Medical Image Segmentation Techniques
- Limits and Structures in Graph Theory
- Interconnection Networks and Systems
- Wastewater Treatment and Nitrogen Removal
- Advancements in Battery Materials
- Advanced oxidation water treatment
- Vehicle Routing Optimization Methods
- Advanced Data Storage Technologies
- Facility Location and Emergency Management
- Image and Signal Denoising Methods
- Antibiotic Resistance in Bacteria
- Optical Imaging and Spectroscopy Techniques
- Chromium effects and bioremediation
- Distributed and Parallel Computing Systems
- Advanced Image Processing Techniques
- Non-Invasive Vital Sign Monitoring
- VLSI and FPGA Design Techniques
- Low-power high-performance VLSI design
- Neural Networks Stability and Synchronization
Chinese Institute for Brain Research
2025
Beijing University of Chinese Medicine
2022-2025
Dongzhimen Hospital Affiliated to Beijing University of Chinese Medicine
2024-2025
Samsung (South Korea)
2025
Electronics and Telecommunications Research Institute
2025
Beijing Normal University
2022-2024
Northwest A&F University
2024
Yellow River Institute of Hydraulic Research
2022
Beijing University of Chemical Technology
2019-2021
Shanghai Jiao Tong University
2020-2021
The need to support various digital signal processing (DSP) and classification applications on energy-constrained devices has steadily grown. Such often extensively perform matrix multiplications using fixed-point arithmetic while exhibiting tolerance for some computational errors. Hence, improving the energy efficiency of is critical. In this brief, we propose multiplier architectures that can tradeoff accuracy with consumption at design time. Compared a precise multiplier, proposed consume...
Abstract Understanding the mechanisms of candidate drugs play an important role in drug discovery. The activating/inhibiting between and targets are major types drugs. Owing to complexity drug–target (DT) data scarcity, modelling this problem based on deep learning methods accurately predict DT remains a considerable challenge. Here, by considering network pharmacology, we propose multi-view model, DrugAI, which combines four modules, i.e. graph neural for drugs, convolutional targets,...
In this paper we first discuss the properties of minimum spanning tree and with partition constraints. We then concentrate on inverse problem constraints in which need to adjust weights edges a network as less possible so that given becomes one among all trees satisfy restriction. Based calculation maximum cost flow networks, propose strongly polynomial algorithm for solving problem.
Abstract In the recognition of pulmonary embolism, accuracy artery segmentation plays a key role. Due to irregular shape and complex adjacent tissues, it is very challenging segment using traditional convolutional neural network. Therefore, an improved Res-Unet method for proposed in this paper. To begin with, U-net structure used as basis allow efficient information flow. Secondly, order improve gradient circulation network, our model introduces residual connections based on structure, that...
Computer-aided detection of pulmonary embolism is an important technology method for diagnosing embolism, which can help doctors diagnose quickly and save a lot manpower. However, due to the small area in Computed Tomography Pulmonary Angiography (CTPA) slice images, some previous methods detecting have high number false missed detection. This study proposes based on improved faster region-based convolutional neural network (Faster R-CNN) named More Accurate Faster R-CNN (MA R-CNN). A new...
In the three-dimensional reconstruction of pulmonary artery and identification embolism, experts find it difficult to accurately estimate severity embolism in artery, due its irregular shape complex adjacent tissues. effect, segmenting is basis for assessing also a challengeable task. To solve this problem, study proposes ResD-Unet architecture segmentation. begin with, U-Net network used as basic structure, which allows efficient information flow good performance absence sufficiently large...
The morbidity of pulmonary embolism (PE) is only lower than that coronary heart disease and hypertension. Early detection, early diagnosis, timely treatment are the keys to effectively reduce risk death. Nevertheless, PE segmentation still a challenging task at present. automatic particularly important. On one hand, manual from computed tomography (CT) sequence very time-consuming prone misdiagnose. other an accurate contour location, volume, shape can help radiotherapists carry out targeted...
Shigella species are a common cause of acute diarrheal disease in China. In this study, we characterized the changing trends and serotype distribution Beijing from 1994 to 2010. A total 5999 strains were isolated serotyped 302nd Hospital Beijing. The annual number isolates reached peak (n = 1192; 19.84%) 1996 then decreased annually, reaching lowest point 24; 0.41%) S. flexneri 2a sonnei most frequently Shigella, with their respective making up 53.3% 27.6% total. Isolates 4c, 4a, x made 3%...
Keratin biosorbents were prepared by reprocessing the deposits produced from chicken feathers after soluble keratin extraction. Biosorption of Cr(VI) ions onto obtained aqueous solution was studied. Experimental factors affecting biosorption process such as pH and initial concentration investigated. Langmuir, Freundlich Dubinin–Radushkevich (D–R) isotherm models used to describe for ions. The results showed that Langmuir model better fit experimental data than D–R models, maximum monolayer...