Open Access. Powered by Scholars. Published by Universities.®

Computer Engineering Commons™

Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 8641 - 8670 of 25627

Full-Text Articles in Computer Engineering

Svpwm Algorithm Based On Non-Orthogonal Coordinates, Shuaiqi Ma, Pengchao Zhang Jun 2020

Svpwm Algorithm Based On Non-Orthogonal Coordinates, Shuaiqi Ma, Pengchao Zhang

Journal of System Simulation

Abstract: As to the issue of complex trigonometric calculation for conventional SVPWM modulation algorithms, an SVPWM optimization algorithm in non-orthogonal coordinate system was proposed. By using Clark, Non-orthogonal Coordinate and per unit transformation, the algorithm simplified the regional judgment of reference vector in the sectors and triangle and optimized the calculation of basic vector action time. It realized normalization of three vectors times by using a normalization algorithm for mapping other sectors to I sector. The algorithm can effectively reduce the amount of SVPWM algorithm calculation, switching frequency, and switching losses. Simulation results show that the algorithm is …

Go to article

Adaptive Fuzzy Robust H∞ Control Of Flexible-Joint Space Robot, Lijiao Zhang, Chen Li Jun 2020

Adaptive Fuzzy Robust H∞ Control Of Flexible-Joint Space Robot, Lijiao Zhang, Chen Li

Journal of System Simulation

Abstract: In order to solve the problem of trajectory tracking and vibration suppression control for parameter unknown flexible-joints space robot system, a joint flexibility compensation controller was introduced to improve the equivalent stiffness of the joint; by using the singular perturbation method, the system was decomposed into a slow subsystem and a fast subsystem. For the slow subsystem, the adaptive fuzzy H∞ control algorithm was designed; by using the fuzzy logic system to approximate the system uncertainty, a robust H∞ control was used to eliminate the influence of the fuzzy approximation legacy of error to the output tracking …

Go to article

Infrared Image Segmentation Based On Improved Dimensional Otsu And Genetic Algorithm, Kun Wang, Zhang Yang, Shengbo Song, Jingchang Zhuge Jun 2020

Infrared Image Segmentation Based On Improved Dimensional Otsu And Genetic Algorithm, Kun Wang, Zhang Yang, Shengbo Song, Jingchang Zhuge

Journal of System Simulation

Abstract: In order to improve the image segmentation of circuit board, and solve the problem of circuit board fault diagnosis, a new algorithm combines adaptive genetic algorithm and improved two-dimensional OTSU algorithm was proposed. a fast sorting method, in accordance with changes in the genetic algebraic, crossover and mutation probability was improved; according to the distance between the center and neighboring pixels pixel for the neighborhood average algorithm to weight the scale factor, on the basis of judgment on noise point of thermal infrared image to reduce noise; and introduced into the class variance method to solve the equation for …

Go to article

Development Of Hybrid Electric Vehicle Hardware-In-The-Loop Testing System, Bin Yan, Ting Yan, Yang Lin, Chen Liang, Zhou Wei Jun 2020

Development Of Hybrid Electric Vehicle Hardware-In-The-Loop Testing System, Bin Yan, Ting Yan, Yang Lin, Chen Liang, Zhou Wei

Journal of System Simulation

Abstract: Control system has significant influence on Hybrid Electric Vehicles (HEV) acceleration performance, drivability and reliability. In order to ensure system reliability and safety, an elaborate test was done for different performance indexes in the process of system development. Though software-based test has some advantage in testing process and flexibility, it is only able to achieve logical verification on basic function of control strategy. Besides, it does not take into account of the effect of controller hardware, and has some limitation in real-time testing. Instead, hardware-in-the-loop (HIL) can overcome these shortages, can test systematically for controller. HEV test environment was …

Go to article

Weapon Effectiveness Simulation System (Wess), Yonglin Lei, Yao Jian, Zhu Ning, Yifan Zhu, Weiping Wang Jun 2020

Weapon Effectiveness Simulation System (Wess), Yonglin Lei, Yao Jian, Zhu Ning, Yifan Zhu, Weiping Wang

Journal of System Simulation

Abstract: Combat Systems Effectiveness Simulation (CESS) is an important supportive means to combat systems analysis and conceptual design. When confronted with issues like model reusability, simulation composability, and system evolvability, traditional approaches to develop CESS systems find their limitations. Based on years experiences in CESS field and best practices found in overseas CESS simulation systems, a model architecture based CESS modeling methodology was proposed. Around a sophisticated CESS model architecture, a generic CESS system, named WESS, was realized. The functional features, software architecture, application processes, and key aspects of WESS were introduced. A typical case study demonstrates the functionalities of …

Go to article

Research On Full-Circuit Simulation Platform For Conducted Noise Pre-Evaluation, Shangbin Ye, Jiajia Zhang, Yicheng Zhang, Yongtao Yao Jun 2020

Research On Full-Circuit Simulation Platform For Conducted Noise Pre-Evaluation, Shangbin Ye, Jiajia Zhang, Yicheng Zhang, Yongtao Yao

Journal of System Simulation

Abstract: As conducted noise frequency band of power convertor in electric vehicle is stricter than that in normal industrial equipment, a conducted noise simulation modeling method is needed which is suit for wide frequency range. A full-circuit conducted noise modeling method based on component model was proposed, in which high frequency dynamic characteristic was simulated by the active device model, complex impedance characteristic at full frequency band was described by the passive model, distributed parameter of bus structure and near-field coupling parameter were extracted to simulate their influence on coupling path of conducted noise. On the basis, full-circuit simulation platform …

Go to article

Speed-Aware-Based Reliable Probabilistic Route In Manet, Yaohua Chen, Lingxi Peng, Gu Peng Jun 2020

Speed-Aware-Based Reliable Probabilistic Route In Manet, Yaohua Chen, Lingxi Peng, Gu Peng

Journal of System Simulation

Abstract: For broadcast problem of routing in MANET, speed-aware-based reliable probabilistic route discovery (SRPR) scheme was proposed. SRPR considered speed vector and all nodes were divided into reliable nodes and un-reliable nodes. A node among reliable nodes closest to destination was assigned a high probabilistic routing decision by greedy forwarding strategy. The reliability of routing was improved and the number of routing hop was reduced by SRPR scheme. Ad Hoc On-demand Distance Vector (AODV) routing was adopted in the experiments. Simulation results show that the proposed routing protocol mitigates the broadcast storm problem and outperforms in term of number of …

Go to article

Double Bare Bones Particle Swarm Algorithm For Solving Flexible Job-Shop Scheduling Problem, Yueming Dai, Minghui Wang, Wang Chun, Wang Yan Jun 2020

Double Bare Bones Particle Swarm Algorithm For Solving Flexible Job-Shop Scheduling Problem, Yueming Dai, Minghui Wang, Wang Chun, Wang Yan

Journal of System Simulation

Abstract: To solve flexible job shop scheduling problem, a double bare bones particle swarm algorithm (DBBPSO) was proposed to minimize the makespan. Combining Von-neumann bare bones particle swarm optimization algorithm and chaotic mutation bare bones particle swarm optimization algorithm, the algorithm DBBPSO used a communication method to cooperate evolution. This approach could keep balance between global exploration and local exploration, and a machine selection method was proposed based on the tenet of minimizing makespan. The proposed algorithm was compared with other algorithms on four benchmark problems and a scheduling optimization example. Simulation results indicate that the improved algorithm has …

Go to article

Model Uncertainty Quantification For Dependent Variables Based On Random Set Theory, Zhao Liang, Zhanping Yang Jun 2020

Model Uncertainty Quantification For Dependent Variables Based On Random Set Theory, Zhao Liang, Zhanping Yang

Journal of System Simulation

Abstract: Random set theory provides a uniform mechanism for model uncertainty quantification in system analysis. An improved method was proposed based on random set theory for uncertainty quantification considering the dependence among system variables. The Nataf transformation was used to generate dependent random samples to be consistent with correlation coefficients information, and then the joint basic probability assignments for the multidimensional focal elements were calculated to construct the random set. The result of uncertainty quantification based on the random set can reflect the real system response under dependent variables. Simulation results show the presented method rationality.

Go to article

State Feedback Control Of Hybrid Active Power Filter, Yunjian Wang, Xiaoyun Liu, Rongzhi Zhang, Nana Xue Jun 2020

State Feedback Control Of Hybrid Active Power Filter, Yunjian Wang, Xiaoyun Liu, Rongzhi Zhang, Nana Xue

Journal of System Simulation

Abstract: According to the current tracking of active power filter, a state feedback control strategy was applied to three-phase shunt hybrid active power filter system, replacing popular PID controller, to overcome the drawbacks of the PID controller, such as big overshoot, error compensation etc.. The mathematical model was established and the feedback control law was derived based on the topological structure of hybrid active power filter selected. Moreover, the current detection used ip-iq detection algorithm while the stability of capacitor voltage in DC side used PI control. MATLAB/Simulink was applied to simulate the HAPF system, comparing with …

Go to article

Design And Simulation Of Cut Flat Boring Bar By Both Materials' Composite Structure, Xie Feng, Wenxuan Wang, Xiaobao Lei Jun 2020

Design And Simulation Of Cut Flat Boring Bar By Both Materials' Composite Structure, Xie Feng, Wenxuan Wang, Xiaobao Lei

Journal of System Simulation

Abstract: Because the stressed structure of the boring bar in machine tool is a cantilever beam, and it is very easy to produce vibration. To study the vibration problem of boring bar, the general structure of boring bar was improved into the built-in damping core boring bar structure composed of two materials, according to the principle of self-excited vibration's coupling flutter and forced vibration's dynamic damping. At the same time, according to the principle that reasonable arrangement of small stiffness of the boring bar could reduce vibration, the composite structure boring bar was cut flat expecting to reach optimal damping …

Go to article

Design Of Real-Time Communication On Bus Using Dspace System, Yan Cheng, Decong Huo, Xie Song Jun 2020

Design Of Real-Time Communication On Bus Using Dspace System, Yan Cheng, Decong Huo, Xie Song

Journal of System Simulation

Abstract: The analysis of the problem of real-time communication on CAN bus was proposed using dSPACE simulator, and the solution was proposed. The CAN communication model based on dSPACE was designed using the methods of Interrupt or Enable to trigger the action. The spacecraft subsystem simulation model was built on the dSPACE, and the real-time communication was performed following the spacecraft CAN bus communication protocol, to implement the communication with large amount of data between subsystem simulation model and data handling subsystem. The simulation result verifies the validity of the communication method.

Go to article

Motion Object Feature Extraction Method Based On Multi-Feature Fusion, Xidao Luan, Yuxiang Xie, Zhang Xin, Niu Xiao Jun 2020

Motion Object Feature Extraction Method Based On Multi-Feature Fusion, Xidao Luan, Yuxiang Xie, Zhang Xin, Niu Xiao

Journal of System Simulation

Abstract: Motion object feature extraction is the basis of motion object classification. Traditionally motion object classification mainly depends on single feature extraction which is sensitive to the aspects like motion object detection area, angle, scale and noise disturbance, thus decreases the classification efficiency. To solve these problems and improve the robustness of the algorithms, a motion object feature extraction method based on multi-feature fusion was proposed. In this method, width height ratio feature, rotation invariant uniform local binary pattern feature and SIFT feature were considered, and by fusing them into the SVM and KNN classifier, motion object classification was carried …

Go to article

Numerical Simulation Of Aluminum Foam Cushion Performance Analysis On Set-Forward Overload Of Fuze, Kuahai Yu, Xuhui Zhang, Hongyu Xu, Li Rong, Xingguo Kang Jun 2020

Numerical Simulation Of Aluminum Foam Cushion Performance Analysis On Set-Forward Overload Of Fuze, Kuahai Yu, Xuhui Zhang, Hongyu Xu, Li Rong, Xingguo Kang

Journal of System Simulation

Abstract: Buffering protect of fuze under high-speed impact was realized using aluminum foam gasket with special pore structure, and numerical simulation method to achieve the buffer validity analysis. Numerical model of three-layered concrete target projectile penetration was established, and the numerical model was validated to be accurate by comparing the fuze acceleration curves of simulation and experiment results. Numerical simulations were completed to predict the cushioning effect for different foamed aluminum structures. The result reveals that foamed aluminum cushioning can reduce the load of the fuze, and the foam's void ratio and thickness will significantly affect the cushioning performance, and …

Go to article

Modeling And Realization Of Radar Signal Environment Based On Systemvue, Limin Liu, Cheng Cheng, Zhuangzhi Han Jun 2020

Modeling And Realization Of Radar Signal Environment Based On Systemvue, Limin Liu, Cheng Cheng, Zhuangzhi Han

Journal of System Simulation

Abstract: Aiming at the practical requirements of electronic reconnaissance subsystem in an electronic countermeasure simulation system, according to electronic reconnaissance forms and the distribution of two parties, a modeling method of radar signal environment was proposed. It provided the mixed signals source for electronic reconnaissance subsystem. The signal modeling principle was proposed, which defined the position information of radar platform and target platform in trajectory layer. The angle information was defined in antenna layer, which realized radar signal modeling in signal layer. The radar signal environment simulation system of electronic countermeasure was established based on SystemVue at last. It is …

Go to article

Location Method Of Insulators In Power Grid Patrol Aerial Images, Haiyan Cheng, Han Pu, Wang Di, Yongjie Zhai Jun 2020

Location Method Of Insulators In Power Grid Patrol Aerial Images, Haiyan Cheng, Han Pu, Wang Di, Yongjie Zhai

Journal of System Simulation

Abstract: A method to locate the insulators in the power grid patrol aerial images was proposed. OTSU algorithm improved by genetic algorithm was applied to segment insulators from backgrounds. The segmented images were filtered and reconstructed based on morphology algorithm. SketchUp software was used to build insulator samples, namely positive samples. The moment invariants of these samples and negative samples(background) were calculated respectively to train a classifier based on AdaBoost algorithm. By using the trained classifier, segmented insulators were classified and located coarsely. The Order Cut method (OC) was used to cut the original minimum circumscribed rectangle consisting of all …

Go to article

Simulation Study On Price Control Model With Multiplicative Reference Effect, Yang Hui, Zhang Chen Jun 2020

Simulation Study On Price Control Model With Multiplicative Reference Effect, Yang Hui, Zhang Chen

Journal of System Simulation

Abstract: Considering customers' reference-dependent behavior, modeling and simulation study of the revenue management pricing problem with multiplicative reference effect was focused on, which defined the concept of multiplicative reference effect, described the characteristics of the reference effect function and the demand function with multiplicative reference effect, constructed the optimal control model with continuous time and continuous prices, proposed the Hamilton-Jacobi equation, provided simulation algorithm and designed simulation experiments to compare the pricing strategies under different demand circumstances. The simulation study shows that the reference effect has substantial impact on pricing paths and total revenues. The results provide management …

Go to article

Simulation Of Coal Flow Movement Process In Coal And Gas Outburst Of Roadway Network, Zongxiang Li, Yadi Wang, Chunhua Zhang, Tianming Wang Jun 2020

Simulation Of Coal Flow Movement Process In Coal And Gas Outburst Of Roadway Network, Zongxiang Li, Yadi Wang, Chunhua Zhang, Tianming Wang

Journal of System Simulation

Abstract: In order to improve the simulation accuracy of the process in coal and gas outburst disaster period, time step method was put forward to describing the movement and accumulation of coal flow in roadway network when coal and gas outburst happened. Downward dip angles of tunnel were taken as the independent variables, model for distribution weight of coal output was built based on “Downward Priority” principle, and the model could adapt to downward roadway, nearly horizontal roadway and upward roadway. Strength change of outburst coal was established based on the collapse model. Combining with the coal and gas outburst …

Go to article

Research And Application Of Cloud Manufacturing Service Platform For Crane, Yang Chen, Zhongjie Wang, Zhaohui Liu, Nana Yu Jun 2020

Research And Application Of Cloud Manufacturing Service Platform For Crane, Yang Chen, Zhongjie Wang, Zhaohui Liu, Nana Yu

Journal of System Simulation

Abstract: Based on the research fruits of cloud manufacturing, the cloud manufacturing platform for crane was focused on. Based on the connotation analysis of the crane manufacturing, the key technologies of manufacturing resource access and cloud service modeling were discussed. A multi-level dynamic matching model and a comprehensive matching algorithm were proposed. The construction and testing of the cloud manufacturing platform was carried out, and the future works were given.

Go to article

Modeling And Numerical Simulation Of Micro-Tube Scale Effects In 3dp Process, Congping Chen, Xiaoyun Wang, Jieguang Huang, Li Bo Jun 2020

Modeling And Numerical Simulation Of Micro-Tube Scale Effects In 3dp Process, Congping Chen, Xiaoyun Wang, Jieguang Huang, Li Bo

Journal of System Simulation

Abstract: Wall slip and viscous dissipation are two main scale effects in 3DP (Three dimensional printing) process, which has influences on the material's flow properties and thermophysical properties and the printing quality. According to the two phenomena above, theoretic models of wall slip and viscous dissipation were established, respectively, and the software Polyflow was used to study the two scale effects and their interactions with molten ABS in micro-tubes of different radius. Simulation results show that wall slip level increases with the slip coefficient decreasing, and material's velocity decreases with the increase of tube radius; Viscous dissipation level decreases …

Go to article

Simulation And Improvement Of Automobile Front Cover Assembly Work Based On Delmia, Lizhen Zhang, Shao Qi, Jiaqing Yang, Mengmeng Yang, Song Zheng, Dai Peng Jun 2020

Simulation And Improvement Of Automobile Front Cover Assembly Work Based On Delmia, Lizhen Zhang, Shao Qi, Jiaqing Yang, Mengmeng Yang, Song Zheng, Dai Peng

Journal of System Simulation

Abstract: In order to prevent potential occupational disease in automobile front cover assembly location caused by manual handling, a comprehensive evaluation and improvement method of ergonomics was proposed aiming at front cover assembly work ergonomics based on DELMIA. The ergonomics problems in automobile front cover assembly were evaluated quantitatively and comprehensively by using the methods of rapid upper limb assessment (RULA) and lifting equation analysis (NIOSH), and the process or tools were judged whether they should be improved according to the evaluation results. By simulation, analysis and improvement of front cover assembly work, the improvement plans which aimed at the …

Go to article

Impact Of ‘Small World' Social Network Of Consumers On Pricing Decision In Duopoly Market, Li Feng, Wei Ying Jun 2020

Impact Of ‘Small World' Social Network Of Consumers On Pricing Decision In Duopoly Market, Li Feng, Wei Ying

Journal of System Simulation

Abstract: Noticing the influences of friends on consumers purchasing decisions, the impact of ‘small world' social network on price competition in a duopoly hotelling model was studied. A multi-agent based modeling approach was proposed to represent the consumers' decisions, which related to their connected friends in a social network, as well as the firms' pricing decisions. Simulation results reveal that the ‘small world' social network has a significant impact on the competing firms' pricing decisions. In specific, with the increasing number of consumers who are impacted by their friends, or the increasing likelihood of following friends' decisions, consumers then …

Go to article

Terminal Guidance Radar Modeling Research Based On Feature Parameter Stream, Anmin Zhang, Lianhu Cui Jun 2020

Terminal Guidance Radar Modeling Research Based On Feature Parameter Stream, Anmin Zhang, Lianhu Cui

Journal of System Simulation

Abstract: Aiming at the contradiction between computation and fidelity of terminal guidance radar model, the essential need of simulation was analyzed. Comparing the advantages and disadvantages of the existing radar electronic warfare modeling and simulation method, a modeling method was proposed based on feature parameter stream, building terminal guidance radar model for behavior description, giving the model parameter correction method based on historical test data, and combining the modeling and historical test information together. The comparison of the simulation and test results shows that, it can accurately describe the behavior of terminal guidance radar using the least amount of …

Go to article

Maneuver Models Tracking Filter Of Nonballistic Near Space Targets, Qin Lei, Junlong Li Jun 2020

Maneuver Models Tracking Filter Of Nonballistic Near Space Targets, Qin Lei, Junlong Li

Journal of System Simulation

Abstract: Because hypersonic vehicles in the near space often adopt the way of nonballistic maneuver flight with characteristics of high speed and lift-to-drag ratio, flying in atmosphere for a long time, whose motion trajectories are sometimes characterized by “hopping”, their flight altitudes, flight velocities and flight accelerations change. Targets maneuver are characterized by long period maneuver, which has brought great difficulties with ground defense system for maneuvering target localization and tracking. Traditional filtering algorithms obviously cannot give accurate target state estimation, tracking performance has declined. The overview of tracking filter ways was given, introducing four typical nonballistic maneuver models of …

Go to article

Platica: Personalized Language Acquisition Training & Instruction Chatbot Assistant, Nam Tran, Philip Cori, Andres Morales, Evan Johnson Jun 2020

Platica: Personalized Language Acquisition Training & Instruction Chatbot Assistant, Nam Tran, Philip Cori, Andres Morales, Evan Johnson

Computer Science and Engineering Senior Theses

English is immensely important and useful in our society, however there are many people across the world who are learning English as a second language and have limited options to practice. Casual English conversations with native speakers is one of the most proven and immersive ways to practice a language. However, not everyone has those opportunities or the resources to attend ESL classes. We aim to solve this issue with our project PLATICA, a robust, low-cost mobile application that anyone can use to build experience conversing in English. PLATICA takes advantage of state-of-the-art deep learning and natural language processing techniques …

Go to article

Evaluation And Analysis Of Land Intensive Utilization Based On Parameters Optimization Of Svm, Chen Li, Jiaojiao Li, Shulu Xiao Jun 2020

Evaluation And Analysis Of Land Intensive Utilization Based On Parameters Optimization Of Svm, Chen Li, Jiaojiao Li, Shulu Xiao

Journal of System Simulation

Abstract: Based on relevant literature research of evaluation on intensive land-use both at home and abroad, the theory of Support Vector Machine (SVM) and Ant Colony Algorithm (ACO) was discussed. A new method of Correlation Coefficient, the Ant Colony Algorithm and Support Vector Machine (cACO-SVM) was proposed, which analyzed the relevant indicators to determine index set, using ACO, optimization of SVM parameters to draw a good penalty factor C and kernel function sigma and epsilon insensitive coefficient and training SVM, the method improved the training accuracy. Optimization of the land intensive utilization evaluation based on cACO-SVM was put forward, comparing …

Go to article

Study Machine Tool Spindle Performance Reliability Based On Bayes Method, Yulun Chi, Haolin Li Jun 2020

Study Machine Tool Spindle Performance Reliability Based On Bayes Method, Yulun Chi, Haolin Li

Journal of System Simulation

Abstract: With the development of high precision machine tool, the reliability requirement is higher and higher for machine tool spindle. Reliability evaluation of spindle based on accelerated life testing is becoming a hot spot of research, and how to improve the precision of evaluation is one of the most important issues. According to the Weibulldistribution characteristic of machine tool spindle reliability, the spindle accelerated life reliability was studied by using the Bayes method. Due to the environment difference between the accelerated test load and the actual working load. The Bayes theory which used the environment difference factor, was introduced to …

Go to article

Numerical Simulation And Aerodynamic Effect Research For Multi-Warhead Projection, Yuan Wu Jun 2020

Numerical Simulation And Aerodynamic Effect Research For Multi-Warhead Projection, Yuan Wu

Journal of System Simulation

Abstract: In order to study the complex aerodynamic problem in multi-warhead projection, and also establish the practical analysis method for nonlinear aerodynamic characteristics, the separation process was simulated by using CFD technology as well as Monte Carlo method for a statistical research, while effects of the projection condition, multi-body intervene and unsteady characteristic during the separation process were discussed. The present research shows that the main forms of the submunition movement are radial separation and pitching movement; the direction of mass center motion and attitude motion is determined by the projection condition, however the attitude motion is also sensitive to …

Go to article

Research On Reactor Modeling Simulation Based On Neutron Equivalence Homogeneous Theory, Ma Jin, Zhibin Liu, Bingshu Wang, Xinhui Duan Jun 2020

Research On Reactor Modeling Simulation Based On Neutron Equivalence Homogeneous Theory, Ma Jin, Zhibin Liu, Bingshu Wang, Xinhui Duan

Journal of System Simulation

Abstract: A mathematical nuclear CANada Deuterium Uranium (CANDU) reactor steady and transient modelling simulation is built to get the axial thermal power distribution. With a relatively small number of nodes (100-500 nodes) to present the core, based upon two energy group Neutron Diffusion Formulation and a typical spatial discretization, according to equivalence theory and homogeneous method, this is accomplished by properly defining the nuclear properties (absorption and fission cross sections, diffusion coefficient, etc.) characterizing each of the nodes finished. The 390 channels thermal power distribution is calculated under Linux language environment. The thermal power difference is within 5% error with …

Go to article

Gaussian-Awareness Deep Learning For Block-Level Compressive Video Sensing, Yifei Pei Jun 2020

Gaussian-Awareness Deep Learning For Block-Level Compressive Video Sensing, Yifei Pei

Computer Science and Engineering Master's Theses

Compressive sensing (CS) is a signal processing framework that effectively recovers a signal from a small number of samples. Traditional compressed sensing algorithms, such as basis pursuit (BP) and orthogonal matching pursuit (OMP) have several drawbacks, such as low reconstruction performance at small compressed sensing rates and high time complexity. Recently, researchers focus on deep learning to get compressive sensing matrix and reconstruction operations collectively. However, they failed to consider sparsity in their neural networks to compressive sensing recovery; thus, the reconstruction performances are still unsatisfied. In this thesis, we use 2D-discrete cosine transform and 2D-discrete wavelet transform to impose …

Go to article

First Prev Next Last