检索结果-南通市图书馆

Impacts of multi-scenario land use change on ecosystem services and ecological security pattern: A case study of the Yellow River Delta

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Research in Cold and Arid Regions 2024年第1期16卷 30-44页

作者： XueHua cen Hua Zhang College of Geography and Environmental Science Northwest Normal UniversityLanzhouGansu 730070China

The Yellow River Delta(YRD), a critical economic zone along China's eastern coast, also functions as a vital ecological reserve in the lower Yellow River. Amidst rapid industrialization and urbanization, the region has witnessed significant land use/cover changes(LUCC), impacting ecosystem services(ES) and ecological security patterns(ESP). Investigating LUCC's effects on ES and ESP in the YRD is crucial for ecological security and sustainable development. This study utilized the PLUS model to simulate 2030 land use scenarios, including natural development(NDS), economic development(EDS), and ecological protection scenarios(EPS). Subsequently, the InVEST model and circuit theory were applied to assess ES and ESP under varying LUCC scenarios from 2010 to 2030. Findings indicate:(1) Notable LUCC from 2010 to 2030, marked by decreasing cropland and increasing construction land and water bodies.(2) From 2010 to 2020, improvements were observed in carbon storage,water yield, soil retention, and habitat quality, whereas 2020–2030 saw increases in water yield and soil retention but declines in habitat quality and carbon storage. Among the scenarios, EPS showed superior performance in all four ES.(3) Between 2010 and 2030, ecological sources, corridors, and pinchpoints expanded, displaying significant spatial heterogeneity. The EPS scenario yielded the most substantial increases in ecological sources,corridors, and pinchpoints, totaling 582.89 km^(2), 645.03 km^(2),and 64.43 km^(2), respectively. This study highlights the importance of EPS, offering insightful scientific guidance for the YRD's sustainable development.

关键词： Land use change Multi-scenario simulation Ecosystem services Ecological security pattern The Yellow River Delta Circuit theory

Multi-Smart Meter Data Encryption Scheme Basedon Distributed Differential Privacy

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 131-141页

作者： Renwu Yan Yang Zheng Ning Yu cen Liang School of Electronic Electrical Engineering and PhysicsFujian University of TechnologyFuzhou 350118China Department of Computing Sciences at The College at Brockport State University of New YorkNew YorkNY 14420USA

Under the general trend of the rapid development of smart grids,data security and privacy are facing serious challenges;protecting the privacy data of single users under the premise of obtaining user-aggregated data has attracted widespread *** this study,we propose an encryption scheme on the basis of differential privacy for the problem of user privacy leakage when aggregating data from multiple smart ***,we use an improved homomorphic encryption method to realize the encryption aggregation of users’***,we propose a double-blind noise addition protocol to generate distributed noise through interaction between users and a cloud platform to prevent semi-honest participants from stealing data by colluding with one ***,the simulation results show that the proposed scheme can encrypt the transmission of multi-intelligent meter data under the premise of satisfying the differential privacy *** if an attacker has enough background knowledge,the security of the electricity information of one another can be ensured.

关键词： smart grid homomorphic encryption data aggregation differential privacy cloud computing

Accelerating BERT inference with GPU-efficient exit prediction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第3期18卷 31-42页

作者： Lei LI Chengyu WANG Minghui QIU cen CHEN Ming GAO Aoying ZHOU Shanghai Engineering Research center of Big Data Management School of Data Science and EngineeringEast China Normal UniversityShanghai 200062China Alibaba Group Hangzhou 311121China KLATASDS-MOE School of StatisticsEast China Normal UniversityShanghai 200062China

BERT is a representative pre-trained language model that has drawn extensive attention for significant improvements in downstream Natural Language Processing(NLP)*** complex architecture and massive parameters bring BERT competitive performance but also result in slow speed at model inference *** speed up BERT inference,FastBERT realizes adaptive inference with an acceptable drop in accuracy based on knowledge distillation and the early-exit ***,many factors may limit the performance of FastBERT,such as the teacher classifier that is not knowledgeable enough,the batch size shrinkage and the redundant computation of student *** overcome these limitations,we propose a new BERT inference method with GPU-Efficient Exit Prediction(GEEP).GEEP leverages the shared exit loss to simplify the training process of FastBERT from two steps into only one step and makes the teacher classifier more knowledgeable by feeding diverse Transformer outputs to the teacher *** addition,the exit layer prediction technique is proposed to utilize a GPU hash table to handle the token-level exit layer distribution and to sort test samples by predicted exit *** this way,GEEP can avoid batch size shrinkage and redundant computation of student *** results on twelve public English and Chinese NLP datasets prove the effectiveness of the proposed *** source codes of GEEP will be released to the public upon paper acceptance.

关键词： BERT FastBERT inference acceleration model distillation early exit text classification

Scale offers the possibility of identifying adherence to lifestyle interventions in patients with non-alcoholic fatty liver disease

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 Gastroenterology 2024年第25期30卷 3179-3181页

作者： cen-Qin Liu Bing Hu Department of Gastroenterology and Hepatology West China HospitalSichuan UniversityChengdu 610041Sichuan ProvinceChina Department of Gastroenterology and Hepatology/Medical Engineering Integration Laboratory of Digestive Endoscopy West China HospitalSichuan UniversityChengdu 610041Sichuan ProvinceChina

Nonalcoholic fatty liver disease(NAFLD)is the most common chronic liver disorder,and dietary and lifestyle interventions remain the mainstays of NAFLD *** et al established a prediction system to evaluate adherence to lifestyle interventions in patients with NAFLD and choose optimal ***,we discuss the application scenarios of the scale and the areas warranting further attention,aiming to provide a possible reference for clinical recommend-ations.

关键词： Nonalcoholic fatty liver disease Dietary and lifestyle interventions Scale Adherence Exercise

Structured Multi-Head Attention Stock Index Prediction Method Based Adaptive Public Opinion Sentiment Vector

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第1期78卷 1503-1523页

作者： Cheng Zhao Zhe Peng Xuefeng Lan Yuefeng cen Zuxin Wang School of Economics Zhejiang University of TechnologyHangzhouChina College of Management Zhejiang University of TechnologyHangzhouChina Informatization Office Zhejiang University of TechnologyHangzhouChina School of Information and Electronic Engineering Zhejiang University of Science&TechnologyHangzhouChina School of Economics and Management Universiti Putra MalaysiaDaerah PetalingNegeri SelangorMalaysia

The present study examines the impact of short-term public opinion sentiment on the secondary market,with a focus on the potential for such sentiment to cause dramatic stock price fluctuations and increase investment *** quantification of investment sentiment indicators and the persistent analysis of their impact has been a complex and significant area of *** this paper,a structured multi-head attention stock index prediction method based adaptive public opinion sentiment vector is *** proposedmethod utilizes an innovative approach to transform numerous investor comments on social platforms over time into public opinion sentiment vectors expressing complex *** then analyzes the continuous impact of these vectors on the market through the use of aggregating techniques and public opinion data via a structured multi-head attention *** experimental results demonstrate that the public opinion sentiment vector can provide more comprehensive feedback on market sentiment than traditional sentiment polarity ***,the multi-head attention mechanism is shown to improve prediction accuracy through attention convergence on each type of input information *** absolute percentage error(MAPE)of the proposedmethod is 0.463%,a reduction of 0.294% compared to the benchmark attention ***,the market backtesting results indicate that the return was 24.560%,an improvement of 8.202% compared to the benchmark *** results suggest that themarket trading strategy based on thismethod has the potential to improve trading profits.

关键词： Public opinion sentiment structured multi-head attention stock index prediction deep learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

色素血管性斑痣性错构瘤病的诊治进展

中华整形外科杂志 2021年第7期37卷 831-834页

作者：岑卿卿蔡韧马刚林晓曦上海交通大学医学院附属第九人民医院整复外科 200011 上海交通大学Bio-X研究院 200030

色素血管性斑痣性错构瘤病(PPV)是一种以血管畸形合并色素沉积异常为特征的罕见疾病,可仅表现为皮肤病变,也可合并多器官系统的损害。由于临床少见,医生对其了解甚少,随着基因检测和医学技术的发展,近年来对于PPV的研究有了进一步深入... 详细信息

色素血管性斑痣性错构瘤病(PPV)是一种以血管畸形合并色素沉积异常为特征的罕见疾病,可仅表现为皮肤病变,也可合并多器官系统的损害。由于临床少见,医生对其了解甚少,随着基因检测和医学技术的发展,近年来对于PPV的研究有了进一步深入。该文总结了近年来的有关PPV的研究进展,从病因、发病机制、临床表现、诊断以及治疗进行概述,为该类疾病的诊断及治疗提供参考。

关键词：色素血管性斑痣性错构瘤病基因病因学治疗

Performance and mechanism of CO_(2) absorption during the simultaneous removal of SO_(2) and NO_(x) by wet scrubbing process

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2024年第1期135卷 534-545页

作者： Peng Lu Xianhui Yan Lyumeng Ye Dingsheng Chen Dongyao Chen Jianhang Huang Chaoping cen Guangdong Province Engineering Laboratory for Air Pollution Control South China Institute of Environmental SciencesMinistry of Ecology and EnvironmentGuangzhou 510655China Guangdong Provincial Key Laboratory of Water and Air Pollution Control Guangzhou 510655China School of Environmental Science and Engineering Sun Yat-sen UniversityGuangzhou 510275China

The co-removal of CO_(2)while removing SO_(2)and NOxfrom industrial flue gas has great potential of carbon emission reduction but related research is *** this study,a wet scrubbing process with various urea solutions for desulfurization and denitrification was explored for the possibility of CO_(2)*** results showed that the urea-additive solutions were efficient for NOxand SO_(2)abatement,but delivered<10%CO_(2)absorption *** addition of Ca(OH)_(2)dramatically enhanced the CO_(2)absorption,remained the desulfurization efficiency,unfortunately restricted the denitrification *** various operating parameters,pH of solution played a determining role during the *** contradictory pH demands of CO_(2)absorption and denitrification were observed and discussed in detail.A higher pH of solution than 10 was favorable for CO_(2)absorption,while the oxidizing of NO to NO_(2),NO_(2)^(-)or NO_(3)^(-)by NaClO_(2)was inhibited in this ***7

关键词： CO_(2)absorption Synergistic desulfurization and denitrification Wet scrubbing process Urea-NaClO_(2)-Ca(OH)_(2)absorbent Carbonation reaction

B-COPNA resin formation from ethylene tar light fractions:Process development and mechanical exploration by molecular simulation

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2024年第6期70卷 118-129页

作者： Hongyan Shen Lingrui Cui Xingguo Wei Yuanqin Zhang Lian cen Jun Xu Fahai Cao Engineering Research center of Large Scale Reactor East China University of Science and TechnologyShanghai 200237China

An efficient utilization strategy of ethylene tar(ET),the main by-product of the ethylene cracking unit,is urgently required to meet demands for modern petrochemical *** the other hand,condensed polynuclear aromatic resin of moderate condensation degree(B-COPNA)is a widely used carbon material due to its superb processability,the production of which is,however,seriously limited by the high cost of raw *** such context,an interesting strategy was proposed in this study for producing B-COPNA resin using crosslinked light fractions of ethylene tar(ETLF,boiling point<260℃)facilitated by molecular simulation.1,4-Benzenedimethanol(PXG)was first selected as the crosslinking agent according to the findings of molecular *** effects of operating conditions,including reactions temperature,crosslinking agent,and catalyst content on the softening point and yield of B-COPNA resin products were then investigated to optimize the *** reaction mechanism of resin production was studied by analyzing the molecular structure and transition state of ETLF and crosslinking *** was shown that PXG exhibited a superior capacity of withdrawing electrons and a higher electrophilic reactivity than other crosslinking *** addition to the highest yield and greatest heat properties,PXG-prepared resin contained the most condensed *** corresponding optimized conditions of resin preparation were 180℃,1:1.9(PXG:ETLF),and 3%(mass)of catalyst content with a resin yield of 78.57%.It was the electrophilic substitution reaction that occurred between the ETLF and crosslinking agent molecules that were responsible for the resin formation,according to the experimental characterization and molecular ***,it was confirmed that the proposed strategy and demonstrated process can achieve a clean and high value-added utilization of ETLF via B-COPNA resin preparation,bringing huge economic value to the current petrochemical industry.

关键词： Ethylene tar Crosslinking COPNA resin Molecular simulation Transient state

HEN:a novel hybrid explainable neural network based framework for robust network intrusion detection

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第7期67卷 72-90页

作者： Wei WEI Sijin CHEN cen CHEN Heshi WANG Jing LIU Zhongyao CHENG Xiaofeng ZOU School of Computer Science and Engineering Xi'an University of TechnologyShaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and Technology Wuhan University of Science and Technology School of Future Technology South China University of Technology Shenzhen Research Institute of Hunan University School of Computer Science Hunan University of Technology and Business Institute for Infocomm Research (I2R) Agency for Science Technology and Reseach (A*STAR)

With the rapid development of network technology and the automation process for 5G, cyberattacks have become increasingly complex and threatening. In response to these threats, researchers have developed various network intrusion detection systems(NIDS) to monitor network traffic. However, the incessant emergence of new attack techniques and the lack of system interpretability pose challenges to improving the detection performance of NIDS. To address these issues, this paper proposes a hybrid explainable neural network-based framework that improves both the interpretability of our model and the performance in detecting new attacks through the innovative application of the explainable artificial intelligence(XAI)method. We effectively introduce the Shapley additive explanations(SHAP) method to explain a light gradient boosting machine(Light GBM) model. Additionally, we propose an autoencoder long-term short-term memory(AE-LSTM) network to reconstruct SHAP values previously generated. Furthermore, we define a threshold based on reconstruction errors observed during the training phase. Any network flow that surpasses the specified threshold is classified as an attack flow. This approach enhances the framework's ability to accurately identify attacks. We achieve an accuracy of 92.65%, a recall of 95.26%, a precision of 92.57%,and an F1-score of 93.90% on the dataset NSL-KDD. Experimental results demonstrate that our approach generates detection performance on par with state-of-the-art methods.

关键词： explainable artificial intelligence light gradient boosting machine machine learning network intrusion detection Shapley additive explanation hybrid explainable neural network (HEN)