检索结果-南通市图书馆

Journal of Systems Science and Systems Engineering 2021年第1期30卷 85-104页

作者： jiachen sun Peter Gloor MIT Center for Collective Intelligence 245 First StreetCambridgeMA02142USA School of Electronics and Information Technology Sun Yat-Sen UniversityGuangzhou510275China

Rapid advances in machine learning combined with wide availability of online social media have created considerable research activity in predicting what might be the news of tomorrow based on an analysis of the *** this work,we present a deep learning forecasting framework which is capable to predict tomorrow’s news topics on Twitter and news feeds based on yesterday’s content and topic-interaction *** proposed framework starts by generating topics from words using word embeddings and K-means *** temporal topic-networks are constructed where two topics are linked if the same user has worked on both *** and dynamic metrics calculated from networks along with content features and past activity,are used as input of a long short-term memory(LSTM)model,which predicts the number of mentions of a specific topic on the subsequent *** dependencies among topics,our experiments on two Twitter datasets and the HuffPost news dataset demonstrate that selecting a topic’s historical local neighbors in the topic-network as extra features greatly improves the prediction accuracy and outperforms existing baselines.

关键词： Topic’s popularity trend forecasting social media

Topology tracking of dynamic UAV wireless networks

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2022年第11期35卷 322-335页

作者： Yehui SONG Guoru DING jiachen sun Jinghua LI Yitao XU College of Communications Engineering Army Engineering University of PLANanjing 210007China

Wireless network is the communication foundation that supports the intelligentization of Unmanned Aerial Vehicle(UAV) swarm. The topology of UAV communication network is the key to understanding and analyzing the behavior of UAV swarm, thus supporting the further prediction of UAV operations. However, the UAV swarm network topology varies over time due to the high mobility and diversified mission requirements of UAVs. Therefore, it is important but challenging to research dynamic topology inference for tracking the topology changes of the UAV network,especially in non-cooperative manner. In this paper, we study the problem of inferring UAV swarm network topology based on external observations, and propose a dynamic topology inference method. First, we establish a sensing framework for acquiring the communication behavior of the target network over time. Then, we expand the multi-dimensional dynamic Hawkes process to model the communication event sequence in a dynamic wireless network. Finally, combining the sliding time window mechanism, the maximum weighted likelihood estimation is applied to inferring the network topology. Extensive simulation results demonstrate the effectiveness of the proposed method.

关键词： Dynamic topology inference Event detection Hawkes process UAV swarm Wireless networks

A comprehensive review on the effects of green tea and its components on the immune function

在线全文

学校读者我要写书评

暂无评论

Food Science and Human Wellness 2022年第5期11卷 1143-1155页

作者： jiachen sun Shengjie Dong Jianying Li Hui Zhao School of Biotechnology and Food Science Tianjin University of CommerceTianjin 300133China School of Pharmaceutical Science and Technology Tianjin UniversityTianjin 300072China Faculty of Education and Sports Guangdong Baiyun UniversityGuangzhou 510450China

Green tea and its bioactive components possess many health-promoting and disease-preventing benefits,especially anti-inflammatory,antioxidant,anticancer,and metabolic modulation effects with multi-target modes of *** contrast,the effects and mechanisms of tea and its components on the immune system are rarely *** study aimed to review the most potent compounds in tea that affect the immune systems and mechanisms associated with *** a result of in vitro studies,animal models,and human trials,researchers have found that green tea extracts and compounds have the possibility of modulating the innate immune system,adaptive immune system,and intestinal immune *** immune-related diseases,tea polyphenols are the most significant compounds that modify immune functions,though other compounds are being investigated and cannot be ruled *** review provides a new perspective on how the immune-regulatory effects of tea and its components are exerted on immune systems,as well as how they affect the emergence and treatment of diseases.

关键词： Green tea Active components Innate immune system Adaptive immune system Intestinal immune system

Cross-Band Spectrum Prediction Based on Deep Transfer Learning

在线全文

学校读者我要写书评

暂无评论

China Communications 2020年第2期17卷 66-80页

作者： Fandi Lin Jin Chen jiachen sun Guoru Ding Ling Yu College of Communications Engineering Army Engineering University

Spectrum prediction is a promising technology to infer future spectrum state by exploiting inherent patterns of historical spectrum *** practice,for a given spectrum band of interest,when facing relatively scarce historical data,spectrum prediction based on traditional learning methods does not work ***,this paper proposes a cross-band spectrum prediction model based on transfer ***,by analysing service activities and computing the distances between various frequency points based on Dynamic Time Warping,the similarity between spectrum bands has been ***,the features,which mainly affect the performance of transfer learning in the crossband spectrum prediction,are explored by leveraging transfer component ***,the effectiveness of transfer learning for the cross-band spectrum prediction has been ***,experimental results with real-world spectrum data demonstrate that the performance of the proposed model is better than the state-of-theart models when the historical spectrum data is limited.

关键词： cross-band spectrum prediction deep transfer learning long short-term memory dynamic time warping transfer component analysis

Deep Spectrum Prediction in High Frequency Communication Based on Temporal-Spectral Residual Network

在线全文

学校读者我要写书评

暂无评论

China Communications 2018年第9期15卷 25-34页

作者： Ling Yu Jin Chen Yuming Zhang Huaji Zhou jiachen sun College of Communications Engineering Army Engineering University of PLA Nanjing 210000 China Science and Technology on Communication Information Security Control Laboratory Jiaxing 314033 China

High frequency(HF) communication is widely spread due to some merits like easy deployment and wide communication coverage. Spectrum prediction is a promising technique to facilitate the working frequency selection and enhance the function of automatic link establishment. Most of the existing spectrum prediction algorithms focus on predicting spectrum values in a slot-by-slot manner and therefore are lack of timeliness. Deep learning based spectrum prediction is developed in this paper by simultaneously predicting multi-slot ahead states of multiple spectrum points within a period of time. Specifically, we first employ supervised learning and construct samples depending on longterm and short-term HF spectrum data. Then, advanced residual units are introduced to build multiple residual network modules to respectively capture characteristics in these data with diverse time scales. Further, convolution neural network fuses the outputs of residual network modules above for temporal-spectral prediction, which is combined with residual network modules to construct the deep temporal-spectral residual network. Experiments have demonstrated that the approach proposed in this paper has a significant advantage over the benchmark schemes.

关键词： HF communication deep learning spectrum prediction temporal-spectral residual network

Selenomethionine in gelatin methacryloyl hydrogels:Modulating ferroptosis to attenuate skin aging

在线全文

学校读者我要写书评

暂无评论

Bioactive Materials 2024年第5期35卷 495-516页

作者： jiachen sun Xiaoye Xie Yaoyao Song Tianjun sun Xinzhu Liu Huageng Yuan Chuanan Shen Department of Burns and Plastic Surgery Fourth Medical Center of Chinese PLA General HospitalBeijing100048China

During skin aging,the degeneration of epidermal stem cells(EpiSCs)leads to diminished wound healing capabilities and epidermal *** study tackles this issue through a comprehensive analysis combining transcriptomics and untargeted metabolomics,revealing age-dependent alterations in the Gpx gene family and arachidonic acid(AA)metabolic networks,resulting in enhanced ***(Se-Met)could enhance GPX4 expression,thereby assisting EpiSCs in countering AA-induced mitochondrial damage and ***,Se-Met demonstrates antioxidative characteristics and extensive ultraviolet *** the sustained and controllable release of Se-Met,it was covalently grafted to UV-responsive GelMA hydrogels via AC-PEG-NHS *** Se-Met@GelMA hydrogel effectively accelerated wound healing in a chronological aging mice model,by inhibiting lipid peroxidation and ferroptosis with augmented GPX4 ***,in a photoaging model,this hydrogel significantly mitigated inflammatory responses,extracellular matrix remodeling,and ferroptosis in UV-exposed *** characteristics render Se-Met@GelMA hydrogel valuable in practical clinical applications.

关键词： Chronic wounds Photoaging Hydrogels Ferroptosis

Spectrum Prediction Based on GAN and Deep Transfer Learning:A Cross-Band Data Augmentation Framework

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2021年第1期18卷 18-32页

作者： Fandi Lin Jin Chen Guoru Ding Yutao Jiao jiachen sun Haichao Wang College of Communications Engineering Army Engineering UniversityNanjing 210007China

This paper investigates the problem of data scarcity in spectrum prediction.A cognitive radio equipment may frequently switch the target frequency as the electromagnetic environment *** previously trained model for prediction often cannot maintain a good performance when facing small amount of historical data of the new target ***,the cognitive radio equipment usually implements the dynamic spectrum access in real time which means the time to recollect the data of the new task frequency band and retrain the model is very *** address the above issues,we develop a crossband data augmentation framework for spectrum prediction by leveraging the recent advances of generative adversarial network(GAN)and deep transfer ***,through the similarity measurement,we pre-train a GAN model using the historical data of the frequency band that is the most similar to the target frequency ***,through the data augmentation by feeding the small amount of the target data into the pre-trained GAN,temporal-spectral residual network is further trained using deep transfer learning and the generated data with high similarity from ***,experiment results demonstrate the effectiveness of the proposed framework.

关键词： cognitive radio cross-band spectrum prediction deep transfer learning generative adversarial network cross-band data augmentation framework

Functional mechanism on stem cells by tea(Camellia sinensis)bioactive compounds

在线全文

学校读者我要写书评

暂无评论

Food Science and Human Wellness 2022年第3期11卷 579-586页

作者： Yao Cheng jiachen sun Hui Zhao Hongxing Guo Jianying Li School of Biotechnology and Food Science Tianjin University of CommerceTianjin 300134China The Third Central Clinical College Tianjin Medical UniversityTianjin 300170China

Camellia sinensis(tea),one of the most popular commercial crops,is commonly applied in all parts of the *** main active ingredients of tea include polyphenols,alkaloids,polysaccharides,amino acids,aroma and volatile constitutes,all of which are potentially responsible for the activities of *** cells(SCs)are the immature and undifferentiated cells by a varying capacity for proliferation,self-renewal and the capability to differentiate into one or more different derivatives with specialized function or maintain their stem cell ***,a thorough review is conducted of the functional mechanism on SCs by tea bioactive compounds.

关键词： Functional mechanism Stem cell Camellia sinensis Bioactive compounds

Synthesis and catalytic performance of macroporous La1-xCexCoO3 perovskite oxide catalysts with high oxygen mobility for catalytic combustion of soot

在线全文

学校读者我要写书评

暂无评论

Journal of Rare Earths 2020年第6期38卷 584-593页

作者： jiachen sun Zhen Zhao Yazhao Li Xuehua Yu Linlin Zhao Jianmei Li Yuechang Wei Jian Liu State Key Laboratory of Heavy Oil Processing China University of Petroleum-BeijingBeijing 102249China Institute of Catalysis for Energy and Environment College of Chemistry and Chemical EngineeringShenyang Normal UniversityShenyang 110034China

The disordered macroporous-mesoporous La1-xCexCoO3 catalysts were prepared by complexcombustion method with ethylene glycol as complexing agent at relatively low calcination *** samples were characterized by means of X-ray diffraction,N2 adsorption-ndash;desorption,Xray photoelectron spectroscopy,transmission electron microscopy,hydrogen temperature-programmed reduction and soot temperature-programmed reduction,and so *** results show that the use of complexing agent and relatively low calcination temperature increase the specific surface area of the catalyst and have abundant pore *** Ce ions introduced into lattice of LaCoO3 mainly exist in the form of *** the same time,Ce ions enhance the redox performance of the catalyst and the mobility of active oxygen species,which enhances the catalytic activity of the catalyst for soot *** results of activity test show that La0.9Ce0.1CoO3 catalyst exhibits the highest activity in the absence of NO and NO2,and its T10,T50 and T90 are 371,444,and 497℃,*** the same time,a possible reaction mechanism is proposed in this study based on the turnover frequency(TOF) calculated by isothermal anaerobic titrations,XPS and XRD results.

关键词： Macroporous structure La1-xCexCoO3 perovskite oxide Reaction mechanism Soot combustion Rare earths

Synthesis of Pt-SnOx/TS-1@SBA-16 Composites and Their High Catalytic Performance for Propane Dehydrogenation

在线全文

学校读者我要写书评

暂无评论

Chemical Research in Chinese Universities 2019年第5期35卷 866-873页

作者： LI Hongda ZHAO Zhen LI jiacheng LI Jianmei ZHAO Linlin sun jiachen FAN Xiaoqiang State Key Laboratory of Heavy Oil Processing China University of PetroleumBeijing 102249P.R.China Institute of Catalysis for Energy and Environment College of Chemistry and Chemical EngineeringShenyang Normal UniversityShenyang 110034P.R.China

A novel composite material of TS-1@SBA-16 was synthesized by enwrapping TS-1 zeolite crystals with mesoporous SBA-16 silica. This composite was used as catalyst support for loading Pt-SnOx in the propane dehydr genation(PDH) reaction. Catalysts were characterized by means ofN2 adsorption-desorption, XRD, SEM, TEM, XPS, UV-Vis, and Raman spectroscopy. The effect of different contents of TS-1 on PDH was investigated, and the optimal amount of TS-1 was determined to be 10%. The catalyst with TS-1 content of 10% showed the highest PDH activity and the initial conversion of propane over it can achieve 54.5%, higher than those over TS-1 or SB A-16-supported ones. The superior catalytic performance of Pt-SnOx/TS-1 @SBA-16 is related to the synergistic effect of the excellent mass transfer performance through the hierarchical porous structure, suitable acid acidity and electronic effect of Ti species.

关键词： Catalyst Pt-SnOx Propane Dehydrogenation TS-1 zeolite Micro- and meso-porous material