|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Isolation of antioxidants from Psoralea corylifolia fruits using high-speed counter-current chromatography guided by thin layer chromatography-antioxidant autographic assay显示文摘 | Guodong Xiao Guowen Li Liang Chen Zijia Zhang Jun-Jie Yin Tao Wu Zhihong Cheng Xiaohui Wei Zhengtao Wang | 2010 | Journal of Chromatography A2010，，34： | 1 |
| 2 | Endogenous Security-Aware Resource Management for Digital Twin and 6G Edge Intelligence Integrated Smart Park显示文摘The integration of digital twin(DT)and 6G edge intelligence provides accurate forecasting for distributed resources control in smart park.However,the adverse impact of model poisoning attacks on DT model training cannot be ignored.To address this issue,we firstly construct the models of DT model training and model poisoning attacks.An optimization problem is formulated to minimize the weighted sum of the DT loss function and DT model training delay.Then,the problem is transformed and solved by the proposed Multi-timescAle endogenouS securiTy-aware DQN-based rEsouRce management algorithm(MASTER)based on DT-assisted state information evaluation and attack detection.MASTER adopts multi-timescale deep Q-learning(DQN)networks to jointly schedule local training epochs and devices.It actively adjusts resource management strategies based on estimated attack probability to achieve endogenous security awareness.Simulation results demonstrate that MASTER has excellent performances in DT model training accuracy and delay. | Sunxuan Zhang Zijia Yao Haijun Liao Zhenyu Zhou Yilong Chen Zhaoyang You | 2023 | China Communications2023，20，2： | 0 |
| 3 | Scalable and Robust Bio-inspired Organogel Coating by Spraying Method Towards Dynamic Anti-scaling显示文摘Scaling usually causes serious problems in daily life and industrial production.Currently,developing passive anti-scaling coatings has shown promises to overcome this problem.In this work,we fabricated a scalable and robust bio-inspired organogel(BIO)coating,showing dynamic scale resistance in the oil/brine mixture.The oil layer of the BIO coating was utilized as a barrier to inhibit scale nucleation and reduce scale adhesion.The mechanical strength of the coating was optimized by regulating nanoparticle contents.Moreover,the universality of scale resistance was demonstrated by varying the types of nanoparticles,oils and scales.Compared with commercial pipeline materials,such as copper,this BIO coating significantly reduces scale deposition after 240-h scaling test(ca.93%reduction).Therefore,this study designs scalable and robust organogel coatings for sustainable scale resistance,which may be used for practical application in oil production. | ZANG Ruhua CHEN Zijia YANG Hui WANG Yixuan WANG Shutao MENG Jingxin | 2023 | Chemical Research in Chinese Universities2023，39，1： | 0 |
| 4 | ADC-DL:Communication-Efficient Distributed Learning with Hierarchical Clustering and Adaptive Dataset Condensation显示文摘The rapid growth of modern mobile devices leads to a large number of distributed data,which is extremely valuable for learning models.Unfortunately,model training by collecting all these original data to a centralized cloud server is not applicable due to data privacy and communication costs concerns,hindering artificial intelligence from empowering mobile devices.Moreover,these data are not identically and independently distributed(Non-IID)caused by their different context,which will deteriorate the performance of the model.To address these issues,we propose a novel Distributed Learning algorithm based on hierarchical clustering and Adaptive Dataset Condensation,named ADC-DL,which learns a shared model by collecting the synthetic samples generated on each device.To tackle the heterogeneity of data distribution,we propose an entropy topsis comprehensive tiering model for hierarchical clustering,which distinguishes clients in terms of their data characteristics.Subsequently,synthetic dummy samples are generated based on the hierarchical structure utilizing adaptive dataset condensation.The procedure of dataset condensation can be adjusted adaptively according to the tier of the client.Extensive experiments demonstrate that the performance of our ADC-DL is more outstanding in prediction accuracy and communication costs compared with existing algorithms. | Zhipeng Gao Yan Yang Chen Zhao Zijia Mo | 2022 | China Communications2022，19，12： | 0 |
| 5 | Decision-Making Models Based on Meta-Reinforcement Learning for Intelligent Vehicles at Urban Intersections显示文摘Behavioral decision-making at urban intersections is one of the primary difficulties currently impeding the development of intelligent vehicle technology.The problem is that existing decision-making algorithms cannot effectively deal with complex random scenarios at urban intersections.To deal with this,a deep deterministic policy gradient(DDPG)decision-making algorithm(T-DDPG)based on a time-series Markov decision process(T-MDP)was developed,where the state was extended to collect observations from several consecutive frames.Experiments found that T-DDPG performed better in terms of convergence and generalizability in complex intersection scenarios than a traditional DDPG algorithm.Furthermore,model-agnostic meta-learning(MAML)was incorporated into the T-DDPG algorithm to improve the training method,leading to a decision algorithm(T-MAML-DDPG)based on a secondary gradient.Simulation experiments of intersection scenarios were carried out on the Gym-Carla platform to verify and compare the decision models.The results showed that T-MAML-DDPG was able to easily deal with the random states of complex intersection scenarios,which could improve traffic safety and efficiency.The above decision-making models based on meta-reinforcement learning are significant for enhancing the decision-making ability of intelligent vehicles at urban intersections. | Xuemei Chen Jiahe Liu Zijia Wang Xintong Han Yufan Sun Xuelong Zheng | 2022 | Journal of Beijing Institute of Technology2022，31，4： | 0 |
| 6 | Optimal Location and Sizing ofMulti-Resource Distributed Generator Based onMulti-Objective Artificial Bee Colony Algorithm显示文摘Distribution generation(DG)technology based on a variety of renewable energy technologies has developed rapidly.A large number of multi-type DG are connected to the distribution network(DN),resulting in a decline in the stability of DN operation.It is urgent to find a method that can effectively connect multi-energy DG to DN.photovoltaic(PV),wind power generation(WPG),fuel cell(FC),and micro gas turbine(MGT)are considered in this paper.A multi-objective optimization model was established based on the life cycle cost(LCC)of DG,voltage quality,voltage fluctuation,system network loss,power deviation of the tie-line,DG pollution emission index,and meteorological index weight of DN.Multi-objective artificial bee colony algorithm(MOABC)was used to determine the optimal location and capacity of the four kinds of DG access DN,and compared with the other three heuristic algorithms.Simulation tests based on IEEE 33 test node and IEEE 69 test node show that in IEEE 33 test node,the total voltage deviation,voltage fluctuation,and system network loss of DN decreased by 49.67%,7.47%and 48.12%,respectively,compared with that without DG configuration.In the IEEE 69 test node,the total voltage deviation,voltage fluctuation and system network loss of DN in the MOABC configuration scheme decreased by 54.98%,35.93%and 75.17%,respectively,compared with that without DG configuration,indicating that MOABC can reasonably plan the capacity and location of DG.Achieve the maximum trade-off between DG economy and DN operation stability. | Qiangfei Cao Huilai Wang Zijia Hui Lingyun Chen | 2024 | Energy Engineering2024，121，2： | 0 |
| 7 | TO–YOLOX: a pure CNN tiny object detection model for remotesensing images显示文摘Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention.However,due to interference occasioned by density,overlap,and coverage,the tiny object detection in remote sensing images has always been a difficult problem.Therefore,we propose a novel TO–YOLOX(Tiny Object–You Only Look Once)model.TO–YOLOX possesses a MiSo(Multiple-in-Singleout)feature fusion structure,which exhibits a spatial-shift structure,and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images.TO–YOLOX utilizes an adaptive IOU-T(Intersection Over Uni-Tiny)loss to enhance the localization accuracy of tiny objects,and it applies attention mechanism Group-CBAM(group-convolutional block attention module)to enhance the perception of tiny objects in remote sensing images.To verify the effectiveness and efficiency of TO–YOLOX,we utilized three aerial-photography tiny object detection datasets,namely VisDrone2021,Tiny Person,and DOTA–HBB,and the following mean average precision(mAP)values were recorded,respectively:45.31%(+10.03%),28.9%(+9.36%),and 63.02%(+9.62%).With respect to recognizing tiny objects,TO–YOLOX exhibits a stronger ability compared with Faster R-CNN,RetinaNet,YOLOv5,YOLOv6,YOLOv7,and YOLOX,and the proposed model exhibits fast computation. | Zhe Chen Yuan Liang Zhengbo Yu Ke Xu Qingyun Ji Xueqi Zhang Quanping Zhang Zijia Cui Ziqiong He Ruichun Chang Zhongchang Sun Keyan Xiao Huadong Guo | 2023 | International Journal of Digital Earth2023，16，1： | 0 |
| 8 | Targeted trace ingredients coupled with chemometric analysis for consistency evaluation of Panax notoginseng saponins injectable formulations显示文摘Evaluating the consistency of herb injectable formulations could improve their product quality and clinical safety,particularly concerning the composition and content levels of trace ingredients.Panax notoginseng Saponins Injection(PNSI),widely used in China for treating acute cardiovascular diseases,contains low-abundance(10%-25%)and trace saponins in addition to its five main constituents(notoginsenoside R1,ginsenoside Rg1,ginsenoside Re,ginsenoside Rb1,and ginsenoside Rd).This study aimed to establish a robust analytical method and assess the variability in trace saponin levels within PNSI from different vendors and formulation types.To achieve this,a liquid chromatography-triple quadrupole mass spectrometry(LC-MS/MS)method employing multiple ions monitoring(MIM)was developed.A“post-column valve switching”strategy was implemented to eliminate highly abundant peaks(NR_(1),Rg_(1),and Re)at 26 min.A total of 51 saponins in PNSI were quantified or relatively quantified using 18 saponin standards,with digoxin as the internal standard.This study evaluated 119 batches of PNSI from seven vendors,revealing significant variability in trace saponin levels among different vendors and formulation types.These findings highlight the importance of consistent content in low-abundance and trace saponins to ensure product control and clinical safety.Standardization of these ingredients is crucial for maintaining the quality and effectiveness of PNSI in treating acute cardiovascular diseases. | ZHANG Jingxian ZHANG Zijia WANG Zhaojun ZHANG Tengqian ZHOU Yang CHEN Ming HUANG Zhanwen HE Qingqing LONG Huali HOU Jinjun WU Wanying GUO Dean | 2023 | Chinese Journal of Natural Medicines2023，21，8： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员