National University of Defense Technology

About: National University of Defense Technology is a education organization based out in Changsha, China. It is known for research contribution in the topics: Computer science & Radar. The organization has 39430 authors who have published 40181 publications receiving 358979 citations. The organization is also known as: Guófáng Kēxuéjìshù Dàxué & NUDT.

A rapid SERS method for label-free bacteria detection using polyethylenimine-modified Au-coated magnetic microspheres and Au@Ag nanoparticles.

Abstract: A rapid, sensitive, and label-free SERS detection method for bacteria pathogens is reported for the first time. The method, which is based on the combination of polyethylenimine (PEI)-modified Au-coated magnetic microspheres (Fe3O4@Au@PEI) and concentrated Au@Ag nanoparticles (NPs), was named the capture-enrichment-enhancement (CEE) three-step method. A novel Fe3O4@Au microsphere with monodispersity and strong magnetic responsiveness was synthesized as a magnetic SERS substrate and amino functionalized by PEI self-assembly. The negatively charged bacteria were quickly captured and enriched by the positively charged Fe3O4@Au@PEI microspheres, and the bacteria SERS signal was synergistically enhanced by using Fe3O4@Au@PEI microspheres and Au@Ag NPs in conjunction. The CEE three-step method proved useful in tap water and milk samples, and the total assay time required was only 10 min. Results further demonstrated that the CEE three-step method could be a common approach for detecting a wide range of bacteria, as verified by its detection of the Gram-positive bacterium E. coli and Gram-positive bacterium S. aureus at a detection limit of as low as 103 cells per mL. Therefore, our CEE three-step method offered the significant advantages of short assay time, simple operating procedure, and higher sensitivity than previously reported methods of SERS-based bacteria detection.

Understanding and Summarizing Answers in Community-Based Question Answering Services

Abstract: Community-based question answering (cQA) services have accumulated millions of questions and their answers over time. In the process of accumulation, cQA services assume that questions always have unique best answers. However, with an in-depth analysis of questions and answers on cQA services, we find that the assumption cannot be true. According to the analysis, at least 78% of the cQA best answers are reusable when similar questions are asked again, but no more than 48% of them are indeed the unique best answers. We conduct the analysis by proposing taxonomies for cQA questions and answers. To better reuse the cQA content, we also propose applying automatic summarization techniques to summarize answers. Our results show that question-type oriented summarization techniques can improve cQA answer quality significantly.

Online Learning Control Using Adaptive Critic Designs With Sparse Kernel Machines

Abstract: In the past decade, adaptive critic designs (ACDs), including heuristic dynamic programming (HDP), dual heuristic programming (DHP), and their action-dependent ones, have been widely studied to realize online learning control of dynamical systems. However, because neural networks with manually designed features are commonly used to deal with continuous state and action spaces, the generalization capability and learning efficiency of previous ACDs still need to be improved. In this paper, a novel framework of ACDs with sparse kernel machines is presented by integrating kernel methods into the critic of ACDs. To improve the generalization capability as well as the computational efficiency of kernel machines, a sparsification method based on the approximately linear dependence analysis is used. Using the sparse kernel machines, two kernel-based ACD algorithms, that is, kernel HDP (KHDP) and kernel DHP (KDHP), are proposed and their performance is analyzed both theoretically and empirically. Because of the representation learning and generalization capability of sparse kernel machines, KHDP and KDHP can obtain much better performance than previous HDP and DHP with manually designed neural networks. Simulation and experimental results of two nonlinear control problems, that is, a continuous-action inverted pendulum problem and a ball and plate control problem, demonstrate the effectiveness of the proposed kernel ACD methods.

DrAcc: a DRAM based accelerator for accurate CNN inference

Abstract: Modern Convolutional Neural Networks (CNNs) are computation and memory intensive. Thus it is crucial to develop hardware accelerators to achieve high performance as well as power/energy-efficiency on resource limited embedded systems. DRAM-based CNN accelerators exhibit great potentials but face inference accuracy and area overhead challenges. In this paper, we propose DrAcc, a novel DRAM-based processing-in-memory CNN accelerator. DrAcc achieves high inference accuracy by implementing a ternary weight network using in-DRAM bit operation with simple enhancements. The data partition and mapping strategies can be flexibly configured for the best trade-off among performance, power and energy consumption, and DRAM data reuse factors. Our experimental results show that DrAcc achieves 84.8 FPS (frame per second) at 2W and 2.9× power efficiency improvement over the process-near-memory design.

Deep Video Super-Resolution Using HR Optical Flow Estimation

Abstract: Video super-resolution (SR) aims at generating a sequence of high-resolution (HR) frames with plausible and temporally consistent details from their low-resolution (LR) counterparts. The key challenge for video SR lies in the effective exploitation of temporal dependency between consecutive frames. Existing deep learning based methods commonly estimate optical flows between LR frames to provide temporal dependency. However, the resolution conflict between LR optical flows and HR outputs hinders the recovery of fine details. In this paper, we propose an end-to-end video SR network to super-resolve both optical flows and images. Optical flow SR from LR frames provides accurate temporal dependency and ultimately improves video SR performance. Specifically, we first propose an optical flow reconstruction network (OFRnet) to infer HR optical flows in a coarse-to-fine manner. Then, motion compensation is performed using HR optical flows to encode temporal dependency. Finally, compensated LR inputs are fed to a super-resolution network (SRnet) to generate SR results. Extensive experiments have been conducted to demonstrate the effectiveness of HR optical flows for SR performance improvement. Comparative results on the Vid4 and DAVIS-10 datasets show that our network achieves the state-of-the-art performance.