检索结果-南通市图书馆

DWT BASED HMM FOR FACE RECOGNITION

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of electronics(china) 2007年第6期24卷 835-837页

作者： Shen linlin Ji Zhen Bai li Xu Chen TI DSPs Lab Faculty of Information Engineering Shenzhen University Shenzhen 518050 China school of computer science ＆ Information Technology University of Nottingham NG8 1BB UK Institute of Intelligent Computing science Shenzhen University Shenzhen 518060 China

A novel Discrete Wavelet Transform (DWT) based Hidden Markov Module (HMM) for face recognition is presented in this letter. To improve the accuracy of HMM based face recognition algorithm, DWT is used to replace Discrete Cosine Transform (DCT) for observation sequence ex- traction. Extensive experiments are conducted on two public databases and the results show that the proposed method can improve the accuracy significantly, especially when the face database is large and only few training images are available.

关键词： Discrete Wavelet Transform (DWT) Hidden Markov Model (HMM) Face recognition

Spatio-Temporal Adaptive Super-Resolution Reconstruction Model Based on Zemike Moment for Spatial Video Sequences

在线全文

学校读者我要写书评

暂无评论

china Communications 2012年第12期9卷 93-107页

作者： liang Meiyu du Junping JangMyung Lee liu Honggang Zhang Yun beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing 100876 P. R. China Department of electronics engineering Pusan Nation University Busan Korea

Video Super-Resolution （SR） reconstruction produces video sequences with High Resolution （HR） via the fusion of several Low-Resolution （LR） video frames. Traditional methods rely on the accurate estimation of subpixel motion, which constrains their applicability to video sequences with relatively simple motions such as global translation. We propose an efficient iterative spatio-temporal adaptive SR reconstruction model based on Zemike Moment （ZM）, which is effective for spatial video sequences with arbitrary motion. The model uses region correlation judgment and self-adaptive threshold strategies to improve the effect and time efficiency of the ZM-based SR method. This leads to better mining of non-local self-similarity and local structural regularity, and is robust to noise and rotation. An efficient iterative curvature-based interpolation scheme is introduced to obtain the initial HR estimation of each LR video frame. Experimental results both on spatial and standard video sequences demonstrate that the proposed method outperforms existing methods in terms of both subjective visual and objective quantitative evaluations, and greatly improves the time efficiency.

关键词： video super-resolution fuzzy registration scheme Zemike moment non-local self-similarity self-adaptive threshold

在线全文

学校读者我要写书评

暂无评论

波分复用系统中偏振模色散特性的研究

中国激光 2001年第12期28卷 1103-1107页

作者：刘秀敏杨伯君张晓光北京邮电大学理学院基础部

推导了双折射光纤中两个波长的光波所满足的耦合非线性薛定谔方程。建立了研究两信道波分复用(WDM)系统中偏振模色散效应的模型。基于这一模型,在考虑偏振模色散情况下,数值模拟了在两信道WDM系统中光信号的传输变化。

关键词：偏振模色散波分复用耦合非线性薛定谔方程数值模拟光纤通信

A New Mathematic Method for Fingerprint Identification

在线全文

学校读者我要写书评

暂无评论

A New Mathematic Method for Fingerprint Identification

2011 IEEE International Conference on Information Theory and Information Security(ICITIS 2011)

作者： Zhao Ma 1) Ren Gao 2) 1) school of computer science china university of Geosciences Wuhan P.R.china 2) Department of Electronic engineering hubei university of Economics Wuhan china

Fingerprint identification technology is an important technology in the areas of network security and identity *** paper studies on fingerprint identification by using a new mathematic method of binary function and its partial derivative and directional *** method not only emphasizes on the characteristic of fingerprint,but also concerns about the singularity characteristic of fingerprint images,which increases the accuracy of fingerprint *** the end of the paper,simulation was done to test the algorithm with the use of Matlab,thereby the feasibility and rationality of the method were confirmed.

关键词： Identity authentication fingerprint identification binary function partial derivative directional derivative

ADAPTIVE COPY AND DATA DISSEMINATION IN VEHICULAR AD-HOC NETWORKS

在线全文

cnki会议

学校读者我要写书评

暂无评论

ADAPTIVE COPY AND DATA DISSEMINATION IN VEHICULAR AD-HOC NET...

2009 IEEE International Conference on Communication Technology and Applications（ICCTA2009）

作者： Jianwei Niu~1 Chang liu~1 Canfeng Chen~2 Jian Ma~2 1school of computer science and engineering Beihang university beijing 100191 china 2 Nokia Research Center beijing 100176 china

＜正＞Vehicular ad-hoc networks（VANETs） are promising for more and more intelligent transportation applications,where information is disseminated over a group of *** are characterized for its unstable framework,in which the isolated vehicles communicate with others only when the unexpected meetings occur. As a result,some available data dissemination schemes do not work well in VANETs. In this paper,we propose an opportunistic auto-adaptive dissemination scheme-Adaptive Copy and Spread（ACS） Algorithm - for VANETs,which makes use of the moving patterns of vehicles like direction and velocity,and dynamically adjusts the dissemination *** scheme dynamically increases or decreases the number of message copies inside the broadcast area,and vehicles can intelligently decide when to start or stop broadcast a *** is designed to keep the message at the effective area’s boundary to inform the entering vehicles as soon as *** simulation results show that ACS enhance the data dissemination performance significantly with a smaller network load compared with random choice algorithm and Epidemic dissemination algorithm over a series of scenarios.

关键词： Adaptive Copy and Spread Vehicular Ad hoc Networks Opportunistic Networks Data Dissemination

NOVEL ITERATIVE APPA CARRIER PHASE RECOVERY AND DETECTION FOR TURBO-CODED SYSTEMS

在线全文

cnki会议

学校读者我要写书评

暂无评论

NOVEL ITERATIVE APPA CARRIER PHASE RECOVERY AND DETECTION FO...

2009 IEEE International Conference on Communication Technology and Applications（ICCTA2009）

作者： Bo He~1,Jun li~(2,3),mingming li~3,Meng Hou~(2,3) 1.school of Information science and engineering,Shandong university,Ji’nan 250100,china 2.Shandong Institute of light Industry,Ji’nan 250353,china 3.beijing university of posts and telecommunications,beijing 100876,china

This paper introduced a novel a priori probability aided(APPA) carrier phase recovery and signal detection *** algorithm utilized the soft value of the extrinsic information generated by iterative MAP decoders by means of iteration after *** method provided robust carrier phase estimation along with reliable signal decoding with a wide range of phase errors at such low signal-to-noise ratio(SNR) conditions that turbo coded systems operate *** order to take full advantage of turbo iterative decoding structure and the output soft information,we improved turbo decoding iterative structure and proposed a novel turbo iterative scheme which include iterative calculation of both information and parity bits Log-likelihood Ratio(LLR).We applied the above iterative structure into APPA carrier *** with traditional turbo iteration methods,the novel turbo iteration algorithm can improve the acquisition region from -40 to 40 degrees while acquisition region is from -30 to 30 degrees in traditional methods at the same 3 iteration stage. The overall BER decreases greatly at the same number of turbo *** algorithm has additional advantages including reasonable hardware complexity and easy to be implemented.

关键词： turbo iteration carrier synchronization A priori probability aided(APPA) extrinsic information log-likelihood function(LLF)

A Cognitive Model with Growing Structure and Its Application to Learning to Control the Inverted Pendulum

在线全文

cnki会议

学校读者我要写书评

暂无评论

A Cognitive Model with Growing Structure and Its Application...

2009中国控制与决策会议

作者： Zhang Shao-bai~(1,2),Ruan Xiao-gang~2,Cheng Xie-feng~1,Feng Zhi-quan~3 1.College of computer,Nanjing university of posts and telecommunications,Nanjing,jiangsu 210003,Chma 2.College of Electronic Information and Control engineering,beijing university of Technology,beijing 100022,china 3.school of Information science and engineering Jinan university,Jinan,Shandong 250022,china

＜正＞A growing cognitive model of motor balance skill,which simulates the manners of human beings and animals in motor balance skill learning,is constructed.A neuro-controller based on the model is proposed to balance an inverted *** cognitive model,whose architecture is similar to the reflex arc of the biologic nerve,adopts a growing algorithm from reference to Growing Cell Structures in order to perform the pattern classification in the nerve center. This growing mechanism is able to be evolved through the continuous growing of the new nerve *** reinforcement Hebbian Synaptic Modification is used as the self-learning method in the cognitive model to make the neurons in difference fields to respond to the different stimulus in the best *** experimental results are shown that the growing cognitive model can interact autonomously with the environment and develop the motor balance skill by the growing manners of neural system itself.

关键词： Cognitive model Growing Cell Structures Inverted Pendulum

DCEL:classifier fusion model for Android malware detection

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Systems engineering and electronics 2024年第1期35卷 163-177页

作者： XU Xiaolong jiang Shuai ZHAO Jinbo WANG Xinheng jiangsu Key Laboratory of Big Data Security&Intelligent Processing Nanjing University of Posts and TelecommunicationsNanjing 210023China school of computer science Nanjing University of Posts and TelecommunicationsNanjing 210023China school of Computing and engineering University of West LondonLondon W55RFUK

The rapid growth of mobile applications,the popularity of the Android system and its openness have attracted many hackers and even criminals,who are creating lots of Android ***,the current methods of Android malware detection need a lot of time in the feature engineering ***,these models have the defects of low detection rate,high complexity,and poor practicability,*** analyze the Android malware samples,and the distribution of malware and benign software in application programming interface(API)calls,permissions,and other *** classify the software’s threat levels based on the correlation of ***,we propose deep neural networks and convolutional neural networks with ensemble learning(DCEL),a new classifier fusion model for Android malware ***,DCEL preprocesses the malware data to remove redundant data,and converts the one-dimensional data into a two-dimensional gray ***,the ensemble learning approach is used to combine the deep neural network with the convolutional neural network,and the final classification results are obtained by voting on the prediction of each single *** based on the Drebin and Malgenome datasets show that compared with current state-of-art models,the proposed DCEL has a higher detection rate,higher recall rate,and lower computational cost.

关键词： Android malware detection deep learning ensemble learning model fusion

The Development of Integrated Simulation Model for Prediction

在线全文

学校读者我要写书评

暂无评论

The Development of Integrated Simulation Model for Predictio...

2009中国控制与决策会议

作者： Juanfei li~1,Pengfei li~2,lin liu~1 1.school of science,Xi''an university of Architecture & Technology,Xi''an,710055,china 2.Department of Information and Management engineering,Xi''an Institute of posts and telecommunications,Xi''an,710061,china

＜正＞We used both linear regression models（RM） and grey model（GM） to predict the gross domestic product （GDP） of Shaanxi province for last few *** we proposed a new combination grey model（CGM） based on RM and GM to predict GDP of Shaanxi province *** simulation results from CGM are much more precise than those from simple models（RM and GM）.The whole calculation process can be conducted by MATLAB computer software.

关键词： Grey Model(1,1) Regression Analysis Least Squared Criterion Weight-coefficient Combination Grey Model