Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 290

Year

2023 19

2022 15

2021 24

2020 14

2019 17

2018 20

2017 35

2016 22

2015 4

2014 7

2013 6

2012 5

2011 3

2010 4

2009 6

2008 10

2007 16

2006 16

2005 11

2004 10

open ︾

Keywords

genetic algorithm 12

Genetic algorithm 4

Artificial intelligence 3

Deep learning 3

ANN 2

BP algorithm 2

Convolutional neural network 2

Optimization 2

Reinforcement learning 2

genetic algorithms 2

learning algorithm 2

motion compensation 2

neural network 2

optimization 2

scanning microwave radiometer 2

1) model 1

3D path planning 1

3D printing 1

5G 1

open ︾

Search scope:

排序： Display mode:

High capacity reversible data hiding in encrypted images based on adaptive quadtree partitioning and MSB prediction Research Article

Kaili QI, Minqing ZHANG, Fuqiang DI, Yongjun KONG,1804480181@qq.com

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 8, Pages 1156-1168 doi: 10.1631/FITEE.2200501

Abstract: To improve the embedding capacity of , a new RDH-EI scheme is proposed based on and most significant bit (MSB) prediction. First, according to the smoothness of the image, the image is partitioned into blocks based on , and then blocks of different sizes are encrypted and scrambled at the block level to resist the analysis of the encrypted images. In the data embedding stage, the adaptive MSB prediction method proposed by Wang and He (2022) is improved by taking the upper-left pixel in the block as the target pixel, to predict other pixels to free up more embedding space. To the best of our knowledge, quadtree partitioning is first applied to RDH-EI. Simulation results show that the proposed method is reversible and separable, and that its average embedding capacity is improved. For gray images with a size of 512×512, the average embedding capacity is increased by 25 565 bits. For all smooth images with improved embedding capacity, the average embedding capacity is increased by about 35 530 bits.

Keywords： Adaptive quadtree partitioning Adaptive most significant bit (MSB) prediction Reversible data hiding in encrypted images (RDH-EI) High embedding capacity

HTML PDF Collect

A partition approach for robust gait recognition based on gait template fusion Research Articles

Kejun Wang, Liangliang Liu, Xinnan Ding, Kaiqiang Yu, Gang Hu,heukejun@126.com,liuliangliang@hrbeu.edu.cn,dingxinnan@hrbeu.edu.cn,yukaiqiang@hrbeu.edu.cn,hugang@hrbeu.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5, Pages 615-766 doi: 10.1631/FITEE.2000377

Abstract: has significant potential for remote human identification, but it is easily influenced by identity-unrelated factors such as clothing, carrying conditions, and view angles. Many have been presented that can effectively represent gait features. Each gait template has its advantages and can represent different prominent information. In this paper, gait template fusion is proposed to improve the classical representative gait template (such as a ) which represents incomplete information that is sensitive to changes in contour. We also present a partition method to reflect the different gait habits of different body parts of each pedestrian. The fused template is cropped into three parts (head, trunk, and leg regions) depending on the human body, and the three parts are then sent into the convolutional neural network to learn merged features. We present an extensive empirical evaluation of the CASIA-B dataset and compare the proposed method with existing ones. The results show good accuracy and robustness of the proposed method for .

Keywords：步态识别；分块算法；步态模板；步态分析；步态能量图；深度卷积神经网络；生物特征识别；模式识别

HTML PDF Collect

Optimization and its realization of anneal-genetic algorithm

Wang Ying

Strategic Study of CAE 2008, Volume 10, Issue 7, Pages 57-59

Abstract:

A method that uses annealing algorithm to improve the inefficient local search of genetic algorithm is proposed. That method bases on analysis of the advantages and disadvantages of the annealing and the genetic algorithm. The algorithm optimization is more rapidly in precision after annealing algorithm integration with the genetic algorithm. By examples of cement ratio works, compared with results of the simple algorithm, it is effectively.

Keywords： genetic algorithm simulated annealing algorithm genetic algorithm improvement

HTML PDF Collect

The application of marine meteorological observation in tropical cyclone data assimilation

Wan Qilin,He Jinhai

Strategic Study of CAE 2012, Volume 14, Issue 10, Pages 33-42

Abstract:

Based on the current situation and development plan of marine meteorological observation, it is recognized that there is a need to develop appropriate data assimilation technology for enhancing the efficiency of data utilization. Only in that way, there is a chance to overcome the lack of observation, and to improve numerical weather prediction. In this paper, the multi scale/block batch wise data assimilation is suggested to perform the test of tropical cyclone data assimilation. The results show: the multi scale/block batch wise data assimilation can be appropriate for the data assimilation of tropical cyclone multi scale circulation, satisfy with the flow dependent background error covariance required by tropical cyclone data assimilation, also can use effectively the marine meteorological observation. By means of the multi scale/block batch wise data assimilation, to amplify the utilization of marine meteorological observation, it is an effective approach to obtain high quality tropical cyclone initial circulation.

Keywords： marine meteorological observation the efficiency of data utilization multi scale/block batch wise data assimilation tropical cyclone initial circulation

HTML PDF Collect

Solving Knapsack Problem by Hybrid Particle Swarm Optimization Algorithm

Gao Shang,Yang Jingyu

Strategic Study of CAE 2006, Volume 8, Issue 11, Pages 94-98

Abstract:

The classical particle swarm optimization is a powerful method to find the minimum of a numerical function, on a continuous definition domain. The particle swarm optimization algorithm combining with the idea of the genetic algorithm is recommended to solve knapsack problem. All the 6 hybrid particle swarm optimization algorithms are proved effective. Especially the hybrid particle swarm optimization algorithm derived from across strategy A and mutation strategy C is a simple yet effective algorithm and it has been applied successfully to investment problem. It can easily be modified for any combinatorial problem for which there has been no good specialized algorithm.

Keywords： particle swarm algorithm knapsack problem genetic algorithm mutation

HTML PDF Collect

Quantum coding genetic algorithm based on frog leaping

Xu Bo,Peng Zhiping,Yu Jianping and Ke Wende

Strategic Study of CAE 2014, Volume 16, Issue 3, Pages 108-112

Abstract:

The determinations of the rotation phase of quantum gates and mutation probability are the two main issues that restrict the efficiency of quantum genetic algorithm. This paper presents a quantum real coding genetic algorithm（QRGA）. QRGA used an adaptive means to adjust the direction and the size of the rotation angle of quantum rotation gate. In order to ensure the direction of evolution and population diversity，the mutation probability is guided based on the step of frog leaping algorithm which quantified by fuzzy logic. Comparative experimental results show that the algorithm can avoid falling into part optimal solution and astringe to the global optimum solution quickly，which has achieved good results in the running time and performance of the solution.

Keywords： quantum encoding quantum genetic algorithm frog leaping algorithm swarm intelligence

HTML PDF Collect

The Application of FDTD and Micro Genetic Algorithms to the Planar Spiral Inductors

Wang Hongjian,Li Jing,Liu Heguang,Jiang Jingshan

Strategic Study of CAE 2004, Volume 6, Issue 11, Pages 38-42

Abstract:

High Q inductors are the important elements for RF circuit design. In this paper, the FDTD method is applied to explain the crowding effect of the spiral inductor , which can never be accurately analyzed by analytical solutions. The experimental results verify the FDTD simulation. The micro genetic algorithms and FDTD are combined to design the high Q inductor. The results show the efficiency of this exploration.

Keywords： FDTD genetic algorithms(GA) spiral inductor quality factor

HTML PDF Collect

Improved dynamic grey wolf optimizer Research Articles

Xiaoqing Zhang, Yuye Zhang, Zhengfeng Ming,249140543@qq.com

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 6, Pages 887-890 doi: 10.1631/FITEE.2000191

Abstract: In the standard (GWO), the search wolf must wait to update its current position until the comparison between the other search wolves and the three leader wolves is completed. During this waiting period, the standard GWO is seen as the static GWO. To get rid of this waiting period, two dynamic GWO algorithms are proposed: the first dynamic (DGWO1) and the second dynamic (DGWO2). In the dynamic GWO algorithms, the current search wolf does not need to wait for the comparisons between all other search wolves and the leading wolves, and its position can be updated after completing the comparison between itself or the previous search wolf and the leading wolves. The position of the search wolf is promptly updated in the dynamic GWO algorithms, which increases the iterative convergence rate. Based on the structure of the dynamic GWOs, the performance of the other improved GWOs is examined, verifying that for the same improved algorithm, the one based on dynamic GWO has better performance than that based on static GWO in most instances.

Keywords：群智能；灰狼优化算法；动态灰狼优化算法；优化实验

HTML PDF Collect

A Parallel Evolutionary Algorithm Based on Space Contraction

Wang Tao,LiQiqiang

Strategic Study of CAE 2003, Volume 5, Issue 3, Pages 57-61

Abstract:

A novel algorithm which is based on space contraction for solving MINLP problems is proposed. The algorithm applies fast and effective non-complete evolution to the search for the information of better solutions, by which locates the possible area of optimal solutions, determines next search space by the information of elite individuals. The result shows that it is better than other existing evolutionary algorithms in search efficiency, range of applications, accuracy and robustness of solutions.

Keywords： space contraction evolutionary algorithms MINLP

HTML PDF Collect

Survey of the Algorithms on Association Rule Mining

Bi Jianxin,Zhang Qishan

Strategic Study of CAE 2005, Volume 7, Issue 4, Pages 88-94

Abstract:

In this paper the principle of the algorithms on association rule mining is introduced firstly, and researches of the algorithms on association rule mining are summarized in turn according to variable (dimension), abstract levels data and types of transacted variable (Boolean and Quantitative) in the process of data mining. At the same time some typical algorithms are analyzed and compared. At last, some future directions on association rule generation are viewed.

Keywords： data mining association rule algorithms survey

HTML PDF Collect

TIE algorithm: a layer over clustering-based taxonomy generation for handling evolving data None

Rabia IRFAN, Sharifullah KHAN, Kashif RAJPOOT, Ali Mustafa QAMAR

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 6, Pages 763-782 doi: 10.1631/FITEE.1700517

Abstract: Taxonomy is generated to effectively organize and access large volume of data. A taxonomy is a way of representing concepts that exist in data. It needs to continuously evolve to reflect changes in data. Existing automatic taxonomy generation techniques do not handle the evolution of data; therefore, the generated taxonomies do not truly represent the data. The evolution of data can be handled by either regenerating taxonomy from scratch, or allowing taxonomy to incrementally evolve whenever changes occur in the data. The former approach is not economical in terms of time and resources. A taxonomy incremental evolution (TIE) algorithm, as proposed, is a novel attempt to handle the data that evolve in time. It serves as a layer over an existing clustering-based taxonomy generation technique and allows an existing taxonomy to incrementally evolve. The algorithm was evaluated in research articles selected from the computing domain. It was found that the taxonomy using the algorithm that evolved with data needed considerably shorter time, and had better quality per unit time as compared to the taxonomy regenerated from scratch.

Keywords： Taxonomy Clustering algorithms Information science Knowledge management Machine learning

HTML PDF Collect

United Algorithm for Dynamic Subcarrier, Bit and Power Allocation in OFDM System

Gao Huanqin,Feng Guangzeng,Zhuqi

Strategic Study of CAE 2006, Volume 8, Issue 3, Pages 62-65

Abstract:

A realtime united algorithm for dynamic subbcarrier, bit and power allocation according to the change of channel (UA) is presented in this paper, which can be used into the down-link of multi-user orthogonal frequency division multiplexing (OFDM) system. With the algorithm the total transmission power is the minimum while the data rate of each user and the required BER performance can be achieved. Comparing to the subcarrier allocation algorithm (WSA) , the simulation results show that the algorithm presented in this paper has better performance while both have equal calculating complexity.

Keywords： OFDM Wong's subcarrier allocation (WSA) UA

HTML PDF Collect

Modified Binary Artificial Bee Colony Algorithm forMultidimensional Knapsack Problem

Wang Zhigang,Xia Huiming

Strategic Study of CAE 2014, Volume 16, Issue 8, Pages 106-112

Abstract:

The binary artificial bee colony algorithm has the shortcomings of slower convergence speed and falling into local optimum easily. According to the defects, a modified binary artificial bee colony algorithm is proposed. The algorithm redesign neighborhood search formula in artificial bee colony algorithm, the probability of the food position depends on the Bayes formula. The modified algorithm was used for solving multidimensional knapsack problem, during the evolution process, it uses the greedy algorithm repairs the infeasible solution and rectify knapsack resources with insufficient use. The simulation results show the feasibility and effectiveness of the proposed algorithm.

Keywords： artificial bee colony algorithm multidimensional knapsack problem greedy algorithm combinatorial optimization

HTML PDF Collect

Short-term Load Forecasting Using Neural Network

Luo Mei

Strategic Study of CAE 2007, Volume 9, Issue 5, Pages 77-80

Abstract:

Based on the load data of meritorious power of some area power system, three BP ANN models, namely SDBP, LMBP and BRBP Model, are established to carry out the short-term load forecasting work, and the results are compared. Since the traditional BP algorithm has some unavoidable disadvantages, such as the low training speed and the possibility of being plunged into minimums local minimizing the optimized function, an optimized L-M algorithm, which can accelerate the training of neural network and improve the stability of the convergence, should be applied to forecast to reduce the mean relative error. Bayesian regularization can overcome the over fitting and improve the generalization of ANN.

Keywords： short-term load forecasting(STLF) ANN Levenberg-Marquardt Bayesian regularization optimized algorithms

HTML PDF Collect

Survey on Particle Swarm Optimization Algorithm

Yang Wei,Li Chiqiang

Strategic Study of CAE 2004, Volume 6, Issue 5, Pages 87-94

Abstract:

Particle swarm optimization (PSO) is a new optimization technique originating from artificial life and evolutionary computation. The algorithm completes the optimization through following the personal best solution of each particle and the global best value of the whole swarm. PSO can be implemented with ease and few parameters need to be tuned. It has been successfully applied in many areas. In this paper, the basic principles of PSO are introduced at length, and various improvements and applications of PSO are also presented. Finally, some future research directions about PSO are proposed.

Keywords： swarm intelligence evolutionary algorithm particle swarm optimization

HTML PDF Collect

Title Author Date Type Operation

High capacity reversible data hiding in encrypted images based on adaptive quadtree partitioning and MSB prediction

Kaili QI, Minqing ZHANG, Fuqiang DI, Yongjun KONG,1804480181@qq.com

Journal Article

A partition approach for robust gait recognition based on gait template fusion

Kejun Wang, Liangliang Liu, Xinnan Ding, Kaiqiang Yu, Gang Hu,heukejun@126.com,liuliangliang@hrbeu.edu.cn,dingxinnan@hrbeu.edu.cn,yukaiqiang@hrbeu.edu.cn,hugang@hrbeu.edu.cn

Journal Article

Optimization and its realization of anneal-genetic algorithm

Wang Ying

Journal Article

The application of marine meteorological observation in tropical cyclone data assimilation

Wan Qilin,He Jinhai

Journal Article

Solving Knapsack Problem by Hybrid Particle Swarm Optimization Algorithm

Gao Shang,Yang Jingyu

Journal Article

Quantum coding genetic algorithm based on frog leaping

Xu Bo,Peng Zhiping,Yu Jianping and Ke Wende