检索结果-南通市图书馆

New Spam Filtering Method with Hadoop Tuning-Based MapReduce Naïve Bayes

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4期45卷 201-214页

作者： Keungyeup Ji Youngmi Kwon department of radio and information communications engineering Chungnam National UniversityDaejeon34134Korea

As the importance of email increases,the amount of malicious email is also increasing,so the need for malicious email filtering is *** it is more economical to combine commodity hardware consisting of a medium server or PC with a virtual environment to use as a single server resource and filter malicious email using machine learning techniques,we used a Hadoop MapReduce framework and Naïve Bayes among machine learning methods for malicious email ***ïve Bayes was selected because it is one of the top machine learning methods(Support Vector Machine(SVM),Naïve Bayes,K-Nearest Neighbor(KNN),and Decision Tree)in terms of execution time and *** email was filtered with MapReduce programming using the Naïve Bayes technique,which is a supervised machine learning method,in a Hadoop framework with optimized performance and also with the Python program technique with the Naïve Bayes technique applied in a bare metal server environment with the Hadoop environment not *** to the results of a comparison of the accuracy and predictive error rates of the two methods,the Hadoop MapReduce Naïve Bayes method improved the accuracy of spam and ham email identification 1.11 times and the prediction error rate 14.13 times compared to the non-Hadoop Python Naïve Bayes method.

关键词： Hadoop hadoop distributed file system(HDFS) MapReduce configuration parameter malicious email filtering Naïve Bayes

Beacon-Less Geographic Routing in Real Wireless 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

Journal of Computer Science & Technology 2008年第3期23卷 438-450页

作者： Juan A.Sánchez Rafael Marín-Pérez Pedro M.Ruiz department of information and communications engineering University of MurciaSpain

Geographic Routing （GR） algorithms require nodes to periodically transmit HELLO messages to allow neighbors to know their positions （beaconing mechanism）. Beacon-less routing algorithms have recently been proposed to reduce the control overheads due to these messages. However, existing beacon-less algorithms have not considered realistic physical layers. Therefore, those algorithms cannot work properly in realistic scenarios. In this paper we present a new beacon-less routing protocol called BOSS. Its design is based on the conclusions of our open-field experiments using Tmote-sky sensors. BOSS is adapted to error-prone networks and incorporates a new mechanism to reduce collisions and duplicate messages produced during the selection of the next forwarder node. We compare BOSS with Beacon-Less Routing （BLR） and Contention-Based Forwarding （CBF） algorithms through extensive simulations. The results show that our scheme is able to *** almost perfect packet delivery ratio （like BLR） while having a low bandwidth consumption （even lower than CBF）. Additionally, we carried out an empirical evaluation in a real testbed that shows the correctness of our simulation results.

关键词： geographic routing beacon-less forwarding performance evaluation real deployment

Efficient nonlinear companding scheme for substantial reduction in peak-to-average power ratio of OFDM

在线全文

学校读者我要写书评

暂无评论

Journal of Systems engineering and Electronics 2015年第5期26卷 924-931页

作者： Kasun Bandara Atul Sewaiwar Yeon-Ho Chung department of information and communications engineering Pukyong National University

Orthogonal frequency division multiplexing(OFDM)produces a high peak-to-average power ratio(PAPR) that adversely affects high-speed OFDM data transmission. In order to reduce the high PAPR, an efficient nonlinear companding transform(NCT) function is proposed. With the proposed NCT function,the compression and expansion weights can be applied independently with suitably chosen function parameter values. As a result, the proposed function can easily maintain the average signal power approximately unchanged during the companding *** this regard, the proposed function is superior to previously proposed schemes. Also, the simulations show the outstanding PAPR reduction performance of the proposed function. It is demonstrated that the proposed scheme performs well with nonlinear transmitter amplifiers and delivers superior error performance, compared with error function and exponential function based schemes.

关键词： companding orthogonal frequency division multiplexing(OFDM) peak-to-average power ratio(PAPR)

Discovering High-Quality Threaded Discussions in Online Forums

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2014年第3期29卷 519-531页

作者： Jung-Tae Lee Min-Chul Yang Hae-Chang Rim department of Computer and radio communications engineering Korea UniversitySeoul 136-713Korea

Archives of threaded discussions generated by users in online forums and discussion boards contain valuable knowledge on various topics. However, not all threads are useful because of deliberate abuses, such as trolling and flaming, that are commonly observed in online conversations. The existence of various users with different levels of expertise also makes it difficult to assume that every discussion thread stored online contains high-quality contents. Although finding high-quality threads automatically can help both users and search engines sift through a huge amount of thread archives and make use of these potentially useful resources effectively, no previous work to our knowledge has performed a study on such task. In this paper, we propose an automatic method for distinguishing high-quality threads from low-quality ones in online discussion sites. We first suggest four different artificial measures for inducing overall quality of a thread based on ratings of its posts. We then propose two tasks involving prediction of thread quality without using post rating information. We adopt a popular machine learning framework to solve the two prediction tasks. Experimental results on a real world forum archive demonstrate that our method can significantly improve the prediction performance across all four measures of thread quality on both tasks. We also compare how different types of features derived from various aspects of threads contribute to the overall performance and investigate key features that play a crucial role in discovering high-quality threads in online discussion sites.

关键词： online forum discussion board thread quality

Dark channel prior based blurred image restoration method using total variation and morphology

在线全文

学校读者我要写书评

暂无评论

Journal of Systems engineering and Electronics 2015年第2期26卷 359-366页

作者： Yibing Li Qiang Fu Fang Ye Hayaru Shouno College of information and Communication engineering Harbin Engineering University department of information and Communication engineering University of Electro-Communications

The blurred image restoration method can dramatically highlight the image details and enhance the global contrast, which is of benefit to improvement of the visual effect during practical ap- plications. This paper is based on the dark channel prior principle and aims at the prior information absent blurred image degradation situation. A lot of improvements have been made to estimate the transmission map of blurred images. Since the dark channel prior principle can effectively restore the blurred image at the cost of a large amount of computation, the total variation （TV） and image morphology transform （specifically top-hat transform and bottom- hat transform） have been introduced into the improved method. Compared with original transmission map estimation methods, the proposed method features both simplicity and accuracy. The es- timated transmission map together with the element can restore the image. Simulation results show that this method could inhibit the ill-posed problem during image restoration, meanwhile it can greatly improve the image quality and definition.

关键词： image restoration dark channel prior total variation (TV) morphology transform

Color image encryption scheme based on chaotic systems

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2018年第2期25卷 39-48页

作者： Min Xiangshen Fan Jiulun Zhang Xuefeng Ren Fang department of communications and information engineering Xi'an University of Posts and Telecommunications

To improve the security of the color image encryption scheme,a color image encryption scheme based on chaotic systems is proposed. Firstly, the proposed scheme sets the color image as a three-dimensional matrix which is scrambled by affine transformation. Second, the Logistic chaotic sequence applied to generate the control parameter and auxiliary key is used to encrypt the three-dimensionaL matrix. Here, we mainly focus on two methods for encryption processes. One is to generate a chaotic sequence by Logistic map and Henon map, which is used to perform XOR operation with the scrambled components R＇, G＇, B＇ respectively. The other one is to adopt a binary Logistic sequence to select the pixel position for the scrambled components R＇, G＇, B＇ image, and then applying the Henon map and Logistic map with the auxiliary key to perform the replacement encryption. Based on this, an encrypted image is synthesized. Simulation results show that the proposed image encryption scheme can implement better encryption and achieve higher security performance.

关键词： color image cncryption chaotic systems affine transformation Logistic map Henon map security performance

Cancelable palmprint template generating algorithm based on adaptive threshold

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2019年第1期26卷 1-11页

作者： Min Xiangshen Fan Jiulun Zhang Xuefeng department of communications and information engineering Xi'an University of Posts and Telecommunications

Aiming at the problem of low recognition rate and poor security in the process of palmprint identity authentication,a cancelable palmprint template generating algorithm is proposed,which is based on local Gabor directional pattern with adaptive threshold by mean(m LGDP),difference local Gabor directional pattern with adaptive threshold by mean(m DLGDP)and feature fusion of *** this method,the feature code of the image is segmented and the feature vectors are extracted and *** the Bloom filter is used to achieve many-toone mapping and the location scrambling of palmprint ***,the scrambling result matrix and the user key are irreversibly transformed by the convolution operation to obtain a revocable template of the palmprint *** theoretical and experimental results analysis show that,in the case of key loss,the method of feature fusion can enhance the diversity of the original palmprint template effectively,improve the recognition rate efficiently,and have better security.

关键词： cancelable palmprint template Gabor adaptive threshold feature fusion

A Lightweight ABE Security Protection Scheme in Cloud Environment Based on Attribute Weight

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第8期76卷 1929-1946页

作者： Lihong Guo Jie Yang Haitao Wu department of information and communications engineering Nanjing Institute of TechnologyNanjing211167China

Attribute-based encryption(ABE)is a technique used to encrypt data,it has the flexibility of access control,high security,and resistance to collusion attacks,and especially it is used in cloud security ***,a large number of bilinear mappings are used in ABE,and the calculation of bilinear pairing is *** there is the problem of low *** the other hand,the decryption key is not uniquely associated with personal identification information,if the decryption key is maliciously sold,ABE is unable to achieve accountability for the *** practical applications,shared message requires hierarchical sharing in most cases,in this paper,we present a message security hierarchy ABE scheme for this ***,attributes were grouped and weighted according to the importance of attributes,and then an access structure based on a threshold tree was constructed according to attribute *** method saved the computing time for decryption while ensuring security and on-demand access to information for *** addition,with the help of computing power in the cloud,two-step decryption was used to complete the access,which relieved the computing and storage burden on the client ***,we simulated and tested the scheme based on CP-ABE,and selected different security levels to test its *** security proof and the experimental simulation result showthat the proposed scheme has high efficiency and good performance,and the solution implements hierarchical access to the shared message.

关键词： Attribute-based encryption cloud security message hierarchy attribute weight access control

Research on Federated Learning Data Sharing Scheme Based on Differential Privacy

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 2023年第3期74卷 5069-5085页

作者： Lihong Guo department of information and communications engineering Nanjing Institute of TechnologyNanjing211167China

To realize data sharing,and to fully use the data value,breaking the data island between institutions to realize data collaboration has become a new sharing *** paper proposed a distributed data security sharing scheme based on C/S communication mode,and constructed a federated learning architecture that uses differential privacy technology to protect training *** do not need to share local data,and they only need to upload the trained model parameters to achieve data *** the process of training,a distributed parameter update mechanism is *** server is mainly responsible for issuing training commands and parameters,and aggregating the local model parameters uploaded by the *** client mainly uses the stochastic gradient descent algorithm for gradient trimming,updates,and transmits the trained model parameters back to the server after differential *** test the performance of the scheme,in the application scenario where many medical institutions jointly train the disease detection system,the model is tested from multiple perspectives by taking medical data as an *** the testing results,we can know that for this specific test dataset,when the parameters are properly configured,the lowest prediction accuracy rate is 90.261%and the highest accuracy rate is up to *** shows that the performance of the model is *** results also show that this scheme realizes data sharing while protecting data privacy,completes accurate prediction of diseases,and has a good effect.

关键词： Federated learning C/S mode differential privacy gradient descent prediction accuracy