检索结果-南通市图书馆

Wrapper Based Linear Discriminant Analysis(LDA)for Intrusion Detection in IIoT

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computer Systems Science & Engineering 2023年第5期45卷 1625-1640页

作者： B.Yasotha T.Sasikala M.Krishnamurthy Department of computer Science and Engineering MNM Jain Engineering CollegeChennai600097India Department of School of Computing Sathyabama Institute of Science and TechnologyChennai600119India Department of computer Science and Engineering KCG College of TechnologyChennai600097India

The internet has become a part of every human ***,various devices that are connected through the internet are ***,the Industrial Internet of things(IIoT)is an evolutionary technology interconnecting various industries in digital platforms to facilitate their ***,IIoT is being used in various industrial fields such as logistics,manufacturing,metals and mining,gas and oil,transportation,aviation,and energy *** is mandatory that various industrial fields require highly reliable security and preventive measures against *** detection is defined as the detection in the network of security threats targeting privacy information and sensitive *** Detection Systems(IDS)have taken an important role in providing security in the field of computer *** of intrusion is completely based on the detection functions of the *** an IIoT network expands,it generates a huge volume of data that needs an IDS to detect intrusions and prevent network *** research works have been done for preventing network *** day,the challenges and risks associated with intrusion prevention are increasing while their solutions are not properly *** this regard,this paper proposes a training process and a wrapper-based feature selection With Direct Linear Discriminant Analysis LDA(WDLDA).The implemented WDLDA results in a rate of detection accuracy(DRA)of 97%and a false positive rate(FPR)of 11%using the Network Security Laboratory-Knowledge Discovery in Databases(NSL-KDD)dataset.

关键词： Intrusion detection IIoT wrapper support vector machine(SVM) LDA random forest(RF) feature selection

TCPW BR: A Wireless Congestion Control Scheme Base on RTT

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 2020年第1期62卷 233-244页

作者： Liwei Tian Jinfeng Li Longqing Zhang Yu Sun Lei Yang college of computer Science Guangdong University of Science and TechnologyDongguan523083China college of Information Technology Macao University of Science and TechnologyMacao SAR Department of Information Technology Huizhou City CollegeHuizhou516025China college of Information Engineering Guangdong Innovative Technical CollegeDongguan523960China

The wireless network is limited by the transmission medium,and the transmission process is subject to large interference and *** jitter can cause sporadic loss and is mistaken for congestion by the congestion control *** TCP Westwood protocol(referred to as TCPW)is such that it cannot distinguish between congestion loss and wireless jitter loss,which makes the congestion mechanism too sensitive and reduces bandwidth *** on this,the TCPW protocol is modified based on the estimate of the Round-Trip Time(referred to as RTT)value-called TCPW *** algorithm uses the measured smooth RTT value and divides the congestion level according to the weighted average idea to determine congestion loss and wireless jitter *** simulation results show that the TCPW BR algorithm enhances the wireless network’s ability to judge congestion and random errors.

关键词： Congestion control RTT TCP Westwood

Intracavity frequency-doubled green vertical external cavity surface emitting laser

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 Optics Letters 2008年第4期6卷 271-273页

作者：宋晏蓉张鹏张新平颜博霞周翊毕勇张志刚 college of Applied Sciences Beijing University of Technology Beijing 100022 Academy of Opto-Electronics Chinese Academy of Sciences Beijing 100080 college of Electronic Engineering and computer Science Peking University Beijing 100871

An intracavity frequency-doubled vertical external cavity surface emitting laser （VECSEL） with green light is demonstrated. The fundamental frequency laser cavity consists of a distributed Bragg reflector （DBR） of the gain chip and an external mirror. A 12-mW frequency-doubled output has been reached at 540 nm with a nonlinear crystal LBO when the fundamental frequency output is 44 mW at 1080 nm. The frequency doubling efficiency is about 30%.

关键词： Distributed Bragg reflectors Mirrors

Deep Learning Enabled Object Detection and Tracking Model for Big Data Environment

在线全文

学校读者我要写书评

暂无评论

computers, Materials & Continua 2022年第11期73卷 2541-2554页

作者： K.Vijaya Kumar E.Laxmi Lydia Ashit Kumar Dutta Velmurugan Subbiah Parvathy Gobi Ramasamy Irina V.Pustokhina Denis A.Pustokhin Department of computer Science and Engineering Vignan’s Institute of Engineering for WomenVisakhapatnam530049India Department of computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of computer Science and Information System College of Applied SciencesAlMaarefa UniversityRiyadh11597Kingdom of Saudi Arabia Department of Electronics and communication Engineering Kalasalingam Academy of Research and EducationKrishnankoil626126TamilnaduIndia Department of computer Science Christ UniversityBangalore560029India Department of Entrepreneurship and Logistics Plekhanov Russian University of Economics117997MoscowRussia Department of Logistics State University of ManagementMoscow109542Russia

Recently,big data becomes evitable due to massive increase in the generation of data in real time ***,object detection and tracking applications becomes popular among research communities and finds useful in different applications namely vehicle navigation,augmented reality,surveillance,*** paper introduces an effective deep learning based object tracker using Automated Image Annotation with Inception v2 based Faster RCNN(AIA-IFRCNN)model in big data *** AIA-IFRCNN model annotates the images by Discriminative Correlation Filter(DCF)with Channel and Spatial Reliability tracker(CSR),named DCF-CSRT *** AIA-IFRCNN technique employs Faster RCNN for object detection and tracking,which comprises region proposal network(RPN)and Fast *** addition,inception v2 model is applied as a shared convolution neural network(CNN)to generate the feature ***,softmax layer is applied to perform classification *** effectiveness of the AIA-IFRCNN method undergoes experimentation against a benchmark dataset and the results are assessed under diverse aspects with maximum detection accuracy of 97.77%.

关键词： Object detection tracking convolutional neural network inception v2 image annotation

LSTM-in-LSTM for generating long descriptions of images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2016年第4期2卷 379-388页

作者： Jun Song Siliang Tang Jun Xiao Fei Wu Zhongfei(Mark)Zhang college of computer Science and Technology Zhejiang UniversityHangzhou 310027China Department of computer Science Watson School of Engineering and Applied SciencesBinghamton UniversityBinghamtonNYUSA

In this paper, we propose an approach for generating rich fine-grained textual descriptions of images. In particular, we use an LSTM-in-LSTM(long short-term memory) architecture, which consists of an inner LSTM and an outer LSTM. The inner LSTM effectively encodes the long-range implicit contextual interaction between visual cues(i.e., the spatiallyconcurrent visual objects), while the outer LSTM generally captures the explicit multi-modal relationship between sentences and images(i.e., the correspondence of sentences and images). This architecture is capable of producing a long description by predicting one word at every time step conditioned on the previously generated word, a hidden vector(via the outer LSTM),and a context vector of fine-grained visual cues(via the inner LSTM). Our model outperforms state-of-theart methods on several benchmark datasets(Flickr8k,Flickr30 k, MSCOCO) when used to generate long rich fine-grained descriptions of given images in terms of four different metrics(BLEU, CIDEr, ROUGE-L, and METEOR).

关键词： long short-term memory(LSTM) image description generation computer vision neural network

Forecasting of Stock Returns by Using Manifold Wavelet Support Vector Machine

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2010年第1期15卷 49-53页

作者：汤凌冰盛焕烨汤凌霄 Department of computer Science and Engineering Shanghai Jiaotong University Department of computer and Electronic Engineering Hunan Business College School of Economics Changsha University of Science & Technology

An admissible manifold wavelet kernel is proposed to construct manifold wavelet support vector machine(MWSVM) for stock returns *** manifold wavelet kernel is obtained by incorporating manifold theory into wavelet technique in support vector machine(SVM).Since manifold wavelet function can yield features that describe of the stock time series both at various locations and at varying time granularities,the MWSVM can approximate arbitrary nonlinear functions and forecast stock returns *** applicability and validity of MWSVM for stock returns forecasting is confirmed through experiments on real-world stock data.

关键词： stock returns forecasting kernel manifold wavelet support vector machine (MWSVM)

A Multi-Threaded Semantic Focused Crawler

在线全文

学校读者我要写书评

暂无评论

Journal of computer Science & Technology 2012年第6期27卷 1233-1242页

作者： Punam Bedi Anjali Thukral Hema Banati Abhishek Behl Varun Mendiratta Department of computer Science University of DelhiDelhi-110007India Department of computer Science Keshav MahavidyalayaUniversity of DelhiDelhi-110007India Department of computer Science Dyal Singh CollegeUniversity of DelhiDelhi-110007India

The Web comprises of voluminous rich learning content. The volume of ever growing learning resources however leads to the problem of information overload. A large number of irrelevant search results generated from search engines based on keyword matching techniques further augment the problem. A learner in such a scenario needs semantically matched learning resources as the search results. Keeping in view the volume of content and significance of semantic knowledge, our paper proposes a multi-threaded semantic focused crawler （SFC） specially designed and implemented to crawl on the WWW for educational learning content. The proposed SFC utilizes domain ontology to expand a topic term and a set of seed URLs to initiate the crawl. The results obtained by multiple iterations of the crawl on various topics are shown and compared with the results obtained by executing an open source crawler on the similar dataset. The results are evaluated using Semantic Similarity, a vector space model based metric, and the harvest ratio.

关键词： eLearning semantic focused crawler semantically expanded term ontology

Intelligent Financial Fraud Detection Using Artificial Bee Colony Optimization Based Recurrent Neural Network

在线全文

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第8期37卷 1483-1498页

作者： T.Karthikeyan M.Govindarajan V.Vijayakumar Department of computer Science and Engineering Annamalai UniversityAnnamalai NagarTamil NaduIndia Department of computer Science and Engineering Sri Manakula Vinayagar Engineering CollegePuducherryIndia

Frauds don’t follow any recurring *** require the use of unsupervised learning since their behaviour is continually ***-sters have access to the most recent technology,which gives them the ability to defraud people through online *** make assumptions about consumers’routine behaviour,and fraud develops *** learning must be used by fraud detection systems to recognize online payments since some fraudsters start out using online channels before moving on to other *** a deep convolutional neural network model to identify anomalies from conventional competitive swarm optimization pat-terns with a focus on fraud situations that cannot be identified using historical data or supervised learning is the aim of this paper Artificial Bee Colony(ABC).Using real-time data and other datasets that are readily available,the ABC-Recurrent Neural Network(RNN)categorizes fraud behaviour and compares it to the current *** compared to the current approach,the findings demonstrate that the accuracy is high and the training error is minimal in ABC_*** this paper,we measure the Accuracy,F1 score,Mean Square Error(MSE)and Mean Absolute Error(MAE).Our system achieves 97%accuracy,92%precision rate and F1 score 97%.Also we compare the simulation results with existing methods.

关键词： Fraud activity optimization deep learning classification online transaction neural network credit card

Three-order form invariance and conserved quantity

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 Physics B 2006年第8期15卷 1672-1677页

作者：杨学慧马善钧 college of Physics and communication Electronics Jiang Xi Normal University Nanchang 330022 China

In this paper, the definition of three-order form invariance is given. Then the relation between the three-order form invariance and the three-order Lie symmetry is discussed and the sufficient and necessary condition of Lie symmetry, which comes from the three-order form invariance, is obtained. Finally a three-order Hojman conserved quantity is studied and an example is given to illustrate the application of the obtained results.

关键词： three-order form invariance Hojman conserved quantity three-order Lie symmetry