检索结果-南通市图书馆

维普期刊数据库

A Robust Framework for Multimodal Sentiment Analysis with Noisy Labels Generated from Distributed Data Annotation

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第6期139卷 2965-2984页

作者： Kai Jiang bin cao Jing Fan School of Computer Science and Technology Zhejiang University of TechnologyHangzhou310023China

Multimodal sentiment analysis utilizes multimodal data such as text,facial expressions and voice to detect people’s attitudes.With the advent of distributed data collection and annotation,we can easily obtain and share such multimodal data.However,due to professional discrepancies among annotators and lax quality control,noisy labels might be introduced.Recent research suggests that deep neural networks(DNNs)will overfit noisy labels,leading to the poor performance of the DNNs.To address this challenging problem,we present a Multimodal Robust Meta Learning framework(MRML)for multimodal sentiment analysis to resist noisy labels and correlate distinct modalities simultaneously.Specifically,we propose a two-layer fusion net to deeply fuse different modalities and improve the quality of the multimodal data features for label correction and network training.Besides,a multiple meta-learner(label corrector)strategy is proposed to enhance the label correction approach and prevent models from overfitting to noisy labels.We conducted experiments on three popular multimodal datasets to verify the superiority of ourmethod by comparing it with four baselines.

关键词： Distributed data collection multimodal sentiment analysis meta learning learn with noisy labels

MTCR-CR Routing Strategy for Connection-Oriented Routing over Satellite Networks

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 2024年第5期21卷 280-296页

作者： Li Changhao Sun xue Yan Lei cao Suzhi The University of Chinese Academy of Sciences Beijing 100094China Key Laboratory of Space Utilization Chinese Academy of SciencesBeijing 100094China Technology and Engineering Center for Space Utilization Chinese Academy of SciencesBeijing 100094China

The high-speed movement of satellites makes it not feasible to directly apply the mature routing scheme on the ground to the satellite network.DT-DVTR in the snapshot-based connectionoriented routing strategy is one of the representative solutions,but it still has room for improvement in terms of routing stability.In this paper,we propose an improved scheme for connection-oriented routing strategy named the Minimal Topology Change Routing based on Collaborative Rules(MTCR-CR).The MTCR-CR uses continuous time static topology snapshots based on satellite status to search for intersatellite link(ISL)construction solutions that meet the minimum number of topology changes to avoid route oscillations.The simulation results in Beidou-3 show that compared with DT-DVTR,MTCR-CR reduces the number of routing changes by about 92%,the number of path changes caused by routing changes is about38%,and the rerouting time is reduced by approximately 47%.At the same time,in order to show our algorithm more comprehensively,the same experimental index test was also carried out on the Globalstar satellite constellation.

关键词： ISL routing stability satellite networks satellite routing dynamic strategy

维普期刊数据库

PURP: A Scalable System for Predicting Short-Term Urban TrafficFlow Based on License Plate Recognition Data

在线全文

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2024年第1期7卷 171-187页

作者： Shan Zhang Qinkai Jiang Hao Li bin cao Jing Fan School of Computer Science and Technology Zhejiang University of TechnologyHangzhou 310000China

Accurate and efficient urban traffic flow prediction can help drivers identify road traffic conditions in real-time,consequently helping them avoid congestion and accidents to a certain extent.However,the existing methods for real-time urban traffic flow prediction focus on improving the model prediction accuracy or efficiency while ignoring the training efficiency,which results in a prediction system that lacks the scalability to integrate real-time traffic flow into the training procedure.To conduct accurate and real-time urban traffic flow prediction while considering the latest historical data and avoiding time-consuming online retraining,herein,we propose a scalable system for Predicting short-term URban traffic flow in real-time based on license Plate recognition data(PURP).First,to ensure prediction accuracy,PURP constructs the spatio-temporal contexts of traffic flow prediction from License Plate Recognition(LPR)data as effective characteristics.Subsequently,to utilize the recent data without retraining the model online,PURP uses the nonparametric method k-Nearest Neighbor(namely KNN)as the prediction framework because the KNN can efficiently identify the top-k most similar spatio-temporal contexts and make predictions based on these contexts without time-consuming model retraining online.The experimental results show that PURP retains strong prediction efficiency as the prediction period increases.

关键词： traffic flow prediction k-Nearest Neighbor(KNN) License Plate Recognition(LPR)data spatio-temporalcontext

Stackelberg Game for Wireless Powered and Backscattering Enabled Sensor Networks

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 2024年第3期21卷 189-204页

作者： Lyu bin cao Yi Wang Shuai Guo Haiyan Hao Chengyao Key Laboratory of Ministry of Education in Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and TelecommunicationsNanjing 210003China Jiangsu Engineering Research Center of Novel Optical Fiber Technology and Communication Network Suzhou 215006China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

This paper investigates a wireless powered and backscattering enabled sensor network based on the non-linear energy harvesting model, where the power beacon(PB) delivers energy signals to wireless sensors to enable their passive backscattering and active transmission to the access point(AP). We propose an efficient time scheduling scheme for network performance enhancement, based on which each sensor can always harvest energy from the PB over the entire block except its time slots allocated for passive and active information delivery. Considering the PB and wireless sensors are from two selfish service providers, we use the Stackelberg game to model the energy interaction among them. To address the non-convexity of the leader-level problem, we propose to decompose the original problem into two subproblems and solve them iteratively in an alternating manner. Specifically, the successive convex approximation, semi-definite relaxation(SDR) and variable substitution techniques are applied to find a nearoptimal solution. To evaluate the performance loss caused by the interaction between two providers, we further investigate the social welfare maximization problem. Numerical results demonstrate that compared to the benchmark schemes, the proposed scheme can achieve up to 35.4% and 38.7% utility gain for the leader and the follower, respectively.

关键词： backscatter communication energy interaction stackelberg game wireless powered sensor network

维普期刊数据库

Secoemestrin C Ameliorates Psoriasis-like Skin Inflammation in Mice by Suppressing the TNF-α/NF-κB Signaling Pathway

在线全文

学校读者我要写书评

暂无评论

Current Medical Science 2024年第1期44卷 232-240页

作者： Zhi-bin ZHU Meng-jie LIU Jing WANG Zhou SHU Jie cao Department of Stomatology Chengdu Seventh People's HospitalChengdu 610044China Department of Pharmacy Union HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430022China

Objective Secoemestrin C(SC),an epitetrathiodioxopiperazine isolated from Aspergillus nidulans,has been previously reported to have immunomodulatory and hepatoprotective effects against acute autoimmune hepatitis.However,the effect of SC on regulating the inflammation and its underlying mechanisms in the pathogenesis of psoriasis remain unclear.This study aimed to evaluate the effects of SC on inflammatory dermatosis both in vitro and in vivo.Methods In vitro,HaCaT cells were induced with tumor necrosis factor-alpha(TNF-α,10 ng/mL)to establish an inflammatory injury model,and the expression of nuclear transcription factor-κB(NF-κB)pathway components was measured using qRT-PCR and Western blotting.An in vivo mouse model of imiquimod(IMQ)-induced psoriasis-like skin inflammation was used to evaluate the effectiveness of SC in alleviating psoriasis.Results SC significantly blocked the activation of NF-κB signaling in TNF-α-stimulated HaCaT cells.In addition,systemic and local administration of SC improved psoriatic dermatitis in the IMQ-induced mouse model.SC reduced skin scale and significantly inhibited the secretion of inflammatory factors in skin lesions.Conclusion The protective effect of SC against psoriatic-associated inflammation reveals its potential therapeutic value for treating psoriasis.

关键词： secoemestrin C(SC) psoriasis tumor necrosis factor-alpha(TNF-α) nuclear transcription factor-kB(NF-kB) inflammation

Targeting oxidative stress with natural products: A novel strategy for esophageal cancer therapy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Gastrointestinal Oncology 2024年第2期16卷 287-299页

作者： Fang cao Han-Ling Zhang Cui Guo xue-Liang Xu Qiang Yuan Department of Rehabilitation III Hospital of Chengdu University of Traditional Chinese MedicineChengdu 610072Sichuan ProvinceChina Department of Rehabilitation Chongqing Fuling District Maternal and Child Health HospitalChongqing 408000China Department of Rehabilitation Hospital of Chengdu University of Traditional Chinese MedicineChengdu 610072Sichuan ProvinceChina

Esophageal cancer(ESC)is a malignant tumor that originates from the mucosal epithelium of the esophagus and is part of the digestive tract.Although the exact pathogenesis of ESC has not been fully elucidated,excessive oxidative stress is an important characteristic that leads to the development of many cancers.Abnormal expression of several proteins and transcription factors contributes to oxidative stress in ESCs,which alters the growth and proliferation of ESCs and promotes their metastasis.Natural compounds,including alkaloids,terpenes,polyphenols,and xanthine compounds,can inhibit reactive oxygen species production in ESCs.These compounds reduce oxidative stress levels and subsequently inhibit the oc-currence and progression of ESC through the regulation of targets and pathways such as the cytokine interleukins 6 and 10,superoxide dismutase,the NF-+ACY-kappa+ADs-B/MAPK pathway,and the mammalian Nrf2/ARE target pathway.Thus,targeting tumor oxidative stress has become a key focus in anti-ESC therapy.This review discusses the potential of Natural products(NPs)for treating ESCs and summarizes the application prospects of oxidative stress as a new target for ESC treatment.The findings of this review provide a reference for drug development targeting ESCs.Nonetheless,further high-quality studies will be necessary to determine the clinical efficacy of these various NPs.

关键词： Oxidative stress Natural products Esophageal cancer Reactive oxygen species

Adaptive 5G-and-beyond network-enabled interpretable federated learning enhanced by neuroevolution

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第7期67卷 107-132页

作者： bin cao Jianwei ZHAO Xin LIU Yun LI State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology School of Artificial Intelligence Hebei University of Technology School of Economics and Management Hebei University of Technology Industrial Artificial Intelligence Centre Shenzhen Institute for Advanced StudyUniversity of Electronic Science and Technology of China

Mobile telemedicine systems based on the next-generation communication will significantly enhance deep fusion of network automation and federated learning(FL), but data privacy is a paramount issue in sectors like healthcare. This work hence considers FL augments 5G-and-beyond networks by training deep learning(DL) models without the need to exchange raw data. The substantial communication loads imposed on by extensive parameters involved in DL models are managed through adaptive scheduling mechanisms effectively. To address the opaque nature of DL models and to improve the interpretability of FL models, we introduce a convolutional fuzzy rough neural network specifically designed for medical image processing. We also develop a multiobjective memetic evolutionary algorithm to streamline and optimize the neural network architectures. Our comprehensive FL framework integrates smart scheduling, interpretable fuzzy rough logic,and neuroevolution. This framework is shown to improve communication efficiency, increase interpretability of diagnosis with protected privacy, and generate low-complexity neural architectures.

关键词： 5G-and-beyond network interpretable federated learning mobile telemedicine system fuzzy rough set theory neuroevolution

Comprehensive prognostic and immune analysis of sterol Oacyltransferase 1 in patients with hepatocellular carcinoma

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

World Journal of Hepatology 2024年第3期16卷 439-451页

作者： Chang-Jiao Gan Yue Zheng bin Yang Li-Min cao Development Research Department National Medical Products Administration Institute of Executive DevelopmentBeijing 100071China School of Medicine Nankai University Affiliated Third Center HospitalTianjin 300070China Tianjin Institute of Hepatobiliary Disease The Third Central Hospital of TianjinTianjin 300170China Department of Science and Technology Tianjin Third Central HospitalTianjin 300170China

BACKGROUND Sterol O-acyltransferase 1(SOAT1)is an important target in the diagnosis and treatment of liver cancer.However,the prognostic value of SOAT1 in patients with hepatocellular carcinoma(HCC)is still not clear.AIM To investigate the correlation of SOAT1 expression with HCC,using RNA-seq and gene expression data of The Cancer Genome Atlas(TCGA)-liver hepatocellular carcinoma(LIHC)and pan-cancer.METHODS The correlation between SOAT1 expression and HCC was analyzed.Cox hazard regression models were conducted to investigate the prognostic value of SOAT1 in HCC.Overall survival and disease-specific survival were explored based on TCGA-LIHC data.Biological processes and functional pathways mediated by SOAT1 were characterized by gene ontology(GO)analysis and the Kyoto Encyclopedia of Genes and Genomes(KEGG)analysis of differentially expressed genes.In addition,the protein-protein interaction network and co-expression analyses of SOAT1 in HCC were performed to better understand the regulatory mechanisms of SOAT1 in this malignancy.RESULTS SOAT1 and SOAT2 were highly expressed in unpaired samples,while only SOAT1 was highly expressed in paired samples.The area under the receiver operating characteristic curve of SOAT1 expression in tumor samples from LIHC patients compared with para-carcinoma tissues was 0.748,while the area under the curve of SOAT1 expression in tumor samples from LIHC patients compared with GTEx was 0.676.Patients with higher SOAT1 expression had lower survival rates.Results from GO/KEGG and gene set enrichment analyses suggested that the PI3K/AKT signaling pathway,the IL-18 signaling pathway,the calcium signaling pathway,secreted factors,the Wnt signaling pathway,the Jak/STAT signaling pathway,the MAPK family signaling pathway,and cell–cell communication were involved in such association.SOAT1 expression was positively associated with the abundance of macrophages,Th2 cells,T helper cells,CD56bright natural killer cells,and Th1 cells,and negatively linked to the abundance of Th17 cells,dendritic

关键词： Sterol O-acyltransferase 1 Hepatocellular carcinoma Prognostic Immune

Flashover Characteristics of Dry Band-water band on Hydrophobic Surfaces

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2024年第1期10卷 392-400页

作者： Xiaohan Wu Fanghui Yin bin cao Daiming Yang Shichao Shao Liming Wang Tsinghua-Berkeley Shenzhen Institute(TBSI) Shenzhen 518055China Shenzhen International Graduate School Tsinghua UniversityShenzhen 518055China Shenzhen Polytechnic School Shenzhen 518055China

Due to their outstanding anti-flashover characteristics,composite insulators have been extensively applied in power systems.A lot of research has investigated flashover characteristics of hydrophobic specimens with artificial water droplets.However,the phenomenon is not consistent with that of the contaminated composite insulators.On the test specimens covered with water droplets,there is no obvious leakage current before the flashover and no obvious relationship between flashover voltage and the conductivity of water droplets.On the contaminated composite insulator surface,there are short continuous arcs on the insulators before critical flashover,making insulators look like a luminous lantern.Considering that under these two conditions,the proportion of water along the insulation distance is different,the flashover characteristic of“dry band-water band”on a hydrophobicity surface is analyzed in the present study.The influence of the water band parameter(including length,width,and conductivity)as well as the length of dry band is studied.On this basis,the arc generation and development process of the surface covered with“dry band-water band”is analyzed.The research results improve the understanding of the flashover process on contaminated composite insulators.

关键词： Flashover characteristics hydrophobicity partial arc water band