检索结果-南通市图书馆

IDS-INT:Intrusion detection system using transformer-based transfer learning for imbalanced network traffic

Digital Communications and Networks 2024年第1期10卷 190-204页

作者： Farhan Ullah Shamsher Ullah Gautam Srivastava jerry Chun-Wei lin School of Software Northwestern Polytechnical UniversityXian710072ShaanxiChina Knowledge Unit of Systems and Technology University of Management and TechnologySialkot 51040Pakistan Department of Math and Computer Science Brandon UniversityBrandonMB R7A 6A9Canada Department of Computer Science and Math Lebanese American UniversityBeirut1102Lebanon Western Norway University of Applied Sciences BergenNorway Research Centre for Interneural Computing China Medical UniversityTaichungTaiwanChina

A network intrusion detection system is critical for cyber security against llegitimate *** terms of feature perspectives,network traffic may include a variety of elements such as attack reference,attack type,a subcategory of attack,host information,malicious scripts,*** terms of network perspectives,network traffic may contain an imbalanced number of harmful attacks when compared to normal *** is challenging to identify a specific attack due to complex features and data imbalance *** address these issues,this paper proposes an Intrusion Detection System using transformer-based transfer learning for Imbalanced Network Traffic(IDS-INT).IDS-INT uses transformer-based transfer learning to learn feature interactions in both network feature representation and imbalanced ***,detailed information about each type of attack is gathered from network interaction descriptions,which include network nodes,attack type,reference,host information,***,the transformer-based transfer learning approach is developed to learn detailed feature representation using their semantic ***,the Synthetic Minority Oversampling Technique(SMOTE)is implemented to balance abnormal traffic and detect minority ***,the Convolution Neural Network(CNN)model is designed to extract deep features from the balanced network ***,the hybrid approach of the CNN-Long Short-Term Memory(CNN-LSTM)model is developed to detect different types of attacks from the deep *** experiments are conducted to test the proposed approach using three standard datasets,i.e.,UNsWNB15,CIC-IDS2017,and *** explainable AI approach is implemented to interpret the proposed method and develop a trustable model.

关键词： Network intrusion detection Transfer learning Features extraction Imbalance data Explainable AI Cybersecurity

来源：

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

A Parallel High-Utility Itemset Mining Algorithm Based on Hadoop

引用

Complex System Modeling and Simulation 2023年第1期3卷 47-58页

作者： Zaihe Cheng Wei Shen Wei Fang jerry Chun-Wei lin School of Internet of Things Wuxi Institute of TechnologyWuxi 214121China School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi 214122China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan UniversityWuxi 214122China Department of Computer Science Electrical Engineering and Mathematical SciencesWestern Norway University of Applied SciencesBergen 5020Norway

High-utility itemset mining(HUIM)can consider not only the profit factor but also the profitable factor,which is an essential task in data ***,most HUIM algorithms are mainly developed on a single machine,which is inefficient for big data since limited memory and processing capacities are available.A parallel efficient high-utility itemset mining(P-EFIM)algorithm is proposed based on the Hadoop platform to solve this problem in this *** P-EFIM,the transaction-weighted utilization values are calculated and ordered for the itemsets with the MapReduce *** the ordered itemsets are renumbered,and the low-utility itemsets are pruned to improve the dataset *** the Map phase,the P-EFIM algorithm divides the task into multiple independent *** uses the proposed S-style distribution strategy to distribute the subtasks evenly across all nodes to ensure ***,the P-EFIM uses the EFIM algorithm to mine each subtask dataset to enhance the performance in the Reduce *** are performed on eight datasets,and the results show that the runtime performance of P-EFIM is significantly higher than that of the PHUI-Growth,which is also HUIM algorithm based on the Hadoop framework.

关键词： pattern mining data mining Hadoop parallel high-utility itemset mining big data

来源：

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

A robust deformed convolutional neural network(CNN)for image denoising

引用

CAAI Transactions on Intelligence Technology 2023年第2期8卷 331-342页

作者： Qi Zhang Jingyu Xiao Chunwei Tian jerry Chun‐Wei lin Shichao Zhang School of Economics and Management Harbin Institute of Technology at WeihaiWeihaiChina School of Computer Science Central South UniversityChangshaChina School of Software Northwestern Polytechnical UniversityXi'anShaanxiChina Research&Development Institute Northwestern Polytechnical UniversityShenzhenChina Yangtze River Delta Research Institute Northwestern Polytechnical UniversityTaicangChina Department of Computer Science Electrical Engineering and Mathematical SciencesWestern Norway University of Applied SciencesBergenNorway

Due to strong learning ability,convolutional neural networks(CNNs)have been developed in image ***,convolutional operations may change original distributions of noise in corrupted images,which may increase training difficulty in image *** relations of surrounding pixels can effectively resolve this *** by that,we propose a robust deformed denoising CNN(RDDCNN)in this *** proposed RDDCNN contains three blocks:a deformable block(DB),an enhanced block(EB)and a residual block(RB).The DB can extract more representative noise features via a deformable learnable kernel and stacked convolutional architecture,according to relations of surrounding *** EB can facilitate contextual interaction through a dilated convolution and a novel combination of convolutional layers,batch normalisation(BN)and ReLU,which can enhance the learning ability of the proposed *** address long-term dependency problem,the RB is used to enhance the memory ability of shallow layer on deep layers and construct a clean ***,we implement a blind denoising *** results demonstrate that our denoising model outperforms popular denoising methods in terms of qualitative and quantitative *** can be obtained at https://***/hellloxiaotian/RDDCNN.

关键词： blind denoising CNN deformed block enhanced block

来源：

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

A Study on the Effects of Carrier Gases on the Structure and Morphology of Carbon Nanotubes Prepared by Pyrolysis of Ferrocene and C_2H_2 Mixture

引用

Journal of Natural Gas Chemistry 2005年第3期14卷 151-155页

作者： Wanliang Mi jerry Yuesheng lin Qian Mao Yongdan Li Baoquan Zhang School of Chemical Engineering and Technology Tianjin University Tianjin 300072 China Department of Chemical and Materials Engineering Arizona State University Tempe AZ 85287-6006 United States

Carbon nanotubes （CNTs） were prepared using different carrier gases, with ferrocene as the catalyst precusor and acetylene as the carbon source. The effects of ammonia and nitrogen as carrier gases on the structure and morphology of CNTs were investigated. Transmission electron microscope （TEM）, high-resolution electron microscope （HRTEM）, scanning electron microscope （SEM） and X-ray diffraction （XRD） were employed to characterize the products and the catalyst. Experiment results show that the CNTs grown in N2 gas exhibited cylindrical and tubular structure, while a bamboo-like structure was observed for the CNTs grown in NH3 gas. Moreover, vertically aligned CNTs were obtained on an A12O3 disk when NH3 was used as the carrier gas. The carrier gas also exerted influence on the shape of the catalyst. Based on the theory of active centers of catalysis and combined with the particle shape of the catalyst, a growth model for the vertically aligned CNTs on the substrate is given.

关键词： carbon nanotube ferrocene vertically aligned bamboo-like carrier gas growth model

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Effect of a high strength chemical industry wastewater on microbial community dynamics and mesophilic methane generation

引用

Journal of Environmental Sciences 2014年第4期26卷 875-884页

作者： Harish Venkatakrishnan Youming Tan Maszenan bin Abdul Majid Santosh Pathak Antonius Yudi Sendjaja Dongzhe Li jerry Jian lin Liu Yan Zhou Wun Jern Ng School of Civil and Environmental Engineering Nanyang Technological University Advanced Environmental Biotechnology Center Nanyang Environment and Water Research Institute Nanyang Technological University School of Public Health Shanghai Jiaotong University Nanyang Environment and Water Research Institute Nanyang Technological University Sembcorp Industries Ltd.

A high strength chemical industry wastewater was assessed for its impact on anaerobic microbial com- munity dynamics and consequently mesophilic methane generation. Cumulative methane production was 251 mL/g total chemical oxygen demand removed at standard temperature and pressure at the end of 30 days experimental period with a highest recorded methane percentage of 80.6% of total biogas volume. Volatile fatty acids （VFAs） analysis revealed that acetic acid was the major intermediate VFAs produced with propionic acid accumulating over the experimental period. Quantitative analysis of microbial communities in the test and control groups with quantitative real time polymerase chain reaction highlighted that in the test group, Eubacteria （96.3%） was dominant in comparison with methanogens （3.7%）. The latter were dominated by Methanomicrobiales and Methanobacteriales while in test groups increased over the experimental period, reaching a maximum on day 30. Denaturing gradient gel electrophoresis profile was performed, targeting the 16S rRNA gene of Eubacteria and Archaea, with the DNA samples extracted at 3 different time points from the test groups. A phylogenetic tree was constructed for the sequences using the neighborhood joining method. The analysis revealed that the presence of organisms resembling Syntrophomonadaceae could have contributed to increased production of acetic and propionic acid intermediates while decrease of organisms resembling Pelotomaculum sp. could have most likely contributed to accumulation of propionic acid. This study suggested that the degradation of organic components within the high strength industrial wastewater is closely linked with the activity of certain niche microbial communities within eubacteria and methanogens.

关键词： biochemical methane potential biogas community dynamics denaturing gradient gel electrophoresis industrial chemical wastewater quantitative real-time PCR

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Responses of growth performance,antioxidant function,small intestinal morphology and mRNA expression of jejunal tight junction protein to dietary iron in yellow-feathered broilers

引用

Journal of Integrative Agriculture 2024年第4期23卷 1329-1337页

作者： Kaiwen Lei Hao Wu jerry W Spears Xi lin Xi Wang Xue Bai Yanling Huang Key Laboratory of Animal Science of State Ethnic Affairs Commission Southwest Minzu UniversityChengdu 610041China Key Laboratory of Qinghai-Tibetan Plateau Animal Genetic Resource Reservation and Utilization Southwest Minzu UniversityChengdu 610041China Department of Animal Science North Carolina State UniversityRaleighNC 27695-7621USA

This study aimed to investigate the dose-effect of iron on growth performance,antioxidant *** morphology,and mRNA expression of jejunal tight junction protein in 1-to21-d-old yellow-feathered broilers.A total of 7201-d-old yellow-feathered maleb roilers were allocated to 9 treatments with 8 replicate cages of 10 birds per *** dietary treatments were consisted of a basal diet(contained 79.6 mg Fe kg^(-1))supplemented with 0,20,40,60,80,160,320,640,and 1,280 mg Fe kg^(-1)in the form of FeSO_(4)·7H_(2)*** with the birds in the control group,birds supplemented with 20mg Fe kg^(-1)had higher average daily gain(ADG)(Plinearly(Plinearly(Plinearly(P?0.05)as dietary *** dietary Fe increased,the jejunal relative mRNA abundance of claudin-1 decreased linearly(P=0.001),but the jejunal relative mRNA abundance of zona occludens-1(ZO-1)and occludin decreased linearly(P?0.05)or quadratically(P?0.05).Compared with the supplementation of 20 mg Fe kg^(-1),the supplementation of640 mg Fe kg^(-1)or higher increased(P?0.05)MDA concentrations in plasma,duodenum,and jejunum,decreased VH in the duodenum and jejunum,and the addition of 1,280 mg Fe kg^(-1)reduced(P?0.05)the jejunal tight junction protein(claudin-1,ZO-1,occludin)mRNA *** summary,640 mg of supplemental Fe kg^(-1)or greater was associated with decreased growth performance,increased oxidative stress,disrupted intestinal morphology,and reduced mRNA expression of jejunal tight junction protein.

关键词： iron yellow-feathered broiler antioxidant function intestinal morphology tight junction protein

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

The genetic basis of grape and wine aroma

引用

Horticulture Research 2019年第1期6卷 716-739页

作者： jerry lin Mélanie Massonnet Dario Cantu Department of Viticulture and Enology University of California DavisOne Shields AveDavisCA 95616USA

The grape is one of the oldest and most important horticultural *** and wine aroma has long been of cultural and scientific *** diverse compound classes comprising aroma result from multiple biosynthetic *** fairly recently have researchers begun to elucidate the genetic mechanisms behind the biosynthesis and metabolism of grape volatile *** review summarizes current findings regarding the genetic bases of grape and wine aroma with an aim towards highlighting areas in need of further *** the literature,we compiled a list of functionally characterized genes involved in berry aroma biosynthesis and present them with their corresponding annotation in the grape reference genome.

关键词： Grape aroma metabolism

来源：

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

Improvement of an Anonymous and Lightweight Authentication Scheme for TMIS

引用

Journal of Applied Mathematics and Physics 2018年第1期6卷 18-28页

作者： Chien-Ming Chen Bin Xiang Eric Wang Ke Tsu-Yang Wu jerry Chun-Wei lin Department of Computer Science and Technology Harbin Institute of Technology Shenzhen Graduate School Shenzhen China Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China National Demonstration Center for Experimental Electronic Information and Electrical Technology Education Fujian University of Technology Fuzhou China

Telecare Medicine Information Systems (TMIS) provides flexible and convenient healthcare for patients. However, the medical data transmitted between patients and doctors are exposed to unsecure public networks. To protect the patient’s personal information, many authentication schemes are designed. Recently, Kang et al. proposed a hash based authentication schemes for TMIS and claimed that it could resist various attacks. However, we find that their proposed scheme is unsecure to traceability attack and user impersonation attack. In order to enhance the security and preserve the efficiency of Kang et al.’s, we proposed a new anonymous and lightweight scheme. The analysis demonstrates that our proposed scheme is superior to Kang et al.’s and the related schemes in security.

关键词： Authentication TMIS Smart Card

来源：

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

地表自然过程排汞研究进展及展望

引用

生态学杂志 2011年第5期30卷 845-856页

作者：冯新斌付学吾 SOMMAR Jonas lin Jery 商立海仇广乐中国科学院地球化学研究所环境地球化学国家重点实验室贵阳550002 Department of Civil Engineering LamarUniversity Beaumont TX 77710-0024 USA

地表自然过程排汞包括了自然源排汞过程和先前排放的汞沉降到地表后的再排放过程。已有证据显示,地表自然过程向大气的排汞量可能远大于人为活动直接向大气的排汞量。准确确定自然过程汞的释放通量,不仅对正确评价目前减少人为活动向大... 详细信息

地表自然过程排汞包括了自然源排汞过程和先前排放的汞沉降到地表后的再排放过程。已有证据显示,地表自然过程向大气的排汞量可能远大于人为活动直接向大气的排汞量。准确确定自然过程汞的释放通量,不仅对正确评价目前减少人为活动向大气排汞对全球环境汞污染的影响程度具有重要的意义,而且可为全球大气汞的减排政策的制定提供重要科学理论依据。本综述通过对国内外地表自然排放源相关文献的调研分析发现:由于缺少可靠的观测技术、对地表与大气间汞交换过程和机理的准确认识及大气汞沉降对地表自然排汞过程影响的认识还不清楚,因此目前还难以准确估算地表自然过程向大气的排汞量。近年来,随着技术手段的进步,已具备了开展地表自然排汞及先前排汞沉降后的再释放过程、机理和通量研究的可行性。地表自然过程排汞的研究将是汞的生物地球化学循环演化研究领域的前沿之一。

关键词：汞自然来源交换通量微气象方法汞同位素示踪

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

基于图像语义分割与图卷积的选区激光熔融成形过程羽流运动特征分析

引用

机械工程学报 2024年第12期60卷 168-182页

作者：林昕毛杨坤傅盈西朱锟鹏武汉科技大学精密制造研究院武汉430081 武汉科技大学冶金装备及其控制教育部重点实验室武汉430081 中国科学院合肥物质科学研究院智能机械研究所合肥230031 新加坡国立大学新国大苏州研究院苏州215123

现有的研究中羽流已被证明与选区激光熔融加工过程有着密切关系且影响了最终成形质量,如何利用羽流等监测信息揭示选区激光熔融成形过程中熔融状态,是选区激光熔融成形过程监测被广泛关注的重要原因之一。为了更加完善地描述羽流信息,采... 详细信息

现有的研究中羽流已被证明与选区激光熔融加工过程有着密切关系且影响了最终成形质量,如何利用羽流等监测信息揭示选区激光熔融成形过程中熔融状态,是选区激光熔融成形过程监测被广泛关注的重要原因之一。为了更加完善地描述羽流信息,采用Deeplabv3+网络对图像进行语义分割,并使用标记图法建立一维的羽流形态特征;同时结合时序信号,构建图卷积自编码器与分类器,提出一种基于图结构的羽流运动特征,并进行聚类,得到熔融状态分类,讨论加工过程中羽流运动特征和熔融状态的关系。采用图卷积编码羽流动态特征,实现特征建立与熔融状态识别,并通过输出图卷积表征值,对图卷积在羽流特征提取中的应用进行可解释性分析。结果表明,提出的羽流特征能够实现五类熔融状态的识别且准确率达到了81.52%,并通过可解释性分析了羽流动态特征与熔融状态的内在关系,为选区激光熔融成形过程中监测信号与成形质量映射关系研究提供了新的思路。

关键词：选区激光熔融图卷积过程监测羽流运动特征深度学习

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：