Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing

Nanchang, China

Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing

Nanchang, China
SEARCH FILTERS
Time filter
Source Type

Deng C.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | Li Y.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | Ding G.,Nanjing Southeast University | Wang J.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | And 2 more authors.
ICALIP 2016 - 2016 International Conference on Audio, Language and Image Processing - Proceedings | Year: 2016

Sparse unmixing is based on the assumption that each mixed pixel in the hyperspectral image can be expressed in the form of linear combination of a number of pure spectral signatures that are known in advance. Despite the success of sparse unmixing based on the L0 or L1 regularizer, the limitation of these approach focuses on analyzing the hyperspectral data without incorporating spatial structure information of hyperspectral data. In this paper, considering the correlation between the abundance coefficients of neighboring pixels we proposed a weighted abundance vector sparse unmixing model for the hyperspectral unmixing, named Wav-SU model. Based on this model, we use L1 norm and L1/2 norm as the regularizer and adapt the variable splitting and augmented Lagrangian algorithm to solve them. Our experimental results with both simulated and real hyperspectral data sets demonstrate that the proposed Wav-SU method is an effective and simple spectral unmixing algorithm for hyperspectral unmixing. © 2016 IEEE.


Tan D.,Nanchang Institute of Technology | Tan D.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | Fu X.,Nanchang Institute of Technology | Fu X.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | And 2 more authors.
Chinese Journal of Sensors and Actuators | Year: 2017

Aiming at the deficiency of traditional data aggregation methods, a new aggregation method based on abnormal data-driven is proposed by introducing the mechanism of data-driven. In the phase of data acquisition, the sensor nodes only send the abnormal data to cluster head when exceptional event occurs randomly, this can effectively reduce the network traffic. In the phase of data aggregation for cluster head, the support matrix is constructed between sensors, those monitoring data which has lower support values will be eliminated, only the higher support value data is aggregated by cluster head with the method of optimal weight, thus ensuring the accuracy and validity of aggregation results. The simulation experiments show that, compared with the mean value method and the self-adaptive weighted aggregation method, the proposed method can effectively remove redundant information in the period of data transmission, which has obvious advantages in aggregation precision and energy consumption. © 2017, The Editorial Office of Chinese Journal of Sensors and Actuators. All right reserved.


Wang H.,Nanchang Institute of Technology | Wang H.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | Cui Z.,Taiyuan University of Science and Technology | Sun H.,Nanchang Institute of Technology | And 3 more authors.
Soft Computing | Year: 2016

Firefly algorithm (FA) is a new swarm intelligence optimization algorithm, which has shown an effective performance on many optimization problems. However, it may suffer from premature convergence when solving complex optimization problems. In this paper, we propose a new FA variant, called NSRaFA, which employs a random attraction model and three neighborhood search strategies to obtain a trade-off between exploration and exploitation abilities. Moreover, a dynamic parameter adjustment mechanism is used to automatically adjust the control parameters. Experiments are conducted on a set of well-known benchmark functions. Results show that our approach achieves much better solutions than the standard FA and five other recently proposed FA variants. © 2016 Springer-Verlag Berlin Heidelberg


Lv L.,Nanchang Institute of Technology | Lv L.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | Han L.,Nanchang Institute of Technology | Han L.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | And 4 more authors.
International Journal of Wireless and Mobile Computing | Year: 2016

To overcome the drawbacks of Artificial Bee Colony (ABC) algorithm, which converges slowly in the process of searching and easily suffers from premature, this paper presents an effective approach, called ABC with accelerating convergence (AC-ABC). In the process of evolution, first, the employed bee's position is regarded as the general centre position, the bees choose a location greedily as the new global optimal position in the original and general centre position; then we put the advantage of global optimal bee into evolution rule; we add the ability of best bee's learning into the standard ABC and reduce the value of convergence factor linearly according to the iteration times, which can improve the convergence of the new algorithm effectively. Experiments are conducted on 12 test functions to verify the performance of AC-ABC; the results demonstrate promising performance of our method AC-ABC on convergence velocity, precision, and stability of solution. © Copyright 2016 Inderscience Enterprises Ltd.


Wang H.,Nanchang Institute of Technology | Wang H.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | Wang W.,Nanchang Institute of Technology | Sun H.,Nanchang Institute of Technology | And 7 more authors.
Communications in Computer and Information Science | Year: 2016

Firefly algorithm (FA) is a recently proposed swarm intelligence optimization technique, which has shown good performance on many optimization problems. In the standard FA and its most variants, a firefly moves to other brighter fireflies. If the current firefly is brighter than another one, the current one will not be conducted any search. In this paper, we propose a new firefly algorithm (called NFA) to address this issue. In NFA, brighter fireflies can move to other positions based on local search. To verify the performance of NFA, thirteen classical benchmark functions are tested. Experimental results show that our NFA outperforms the standard FA and two other modified FAs. © Springer Science+Business Media Singapore 2016.


Sun H.,Nanchang Institute of Technology | Sun H.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | Li B.,Nanchang Institute of Technology | Li B.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | And 2 more authors.
International Journal of Wireless and Mobile Computing | Year: 2015

In order to overcome the drawbacks of standard artificial bee colony (ABC) algorithm, such as slow convergence and low solution accuracy, a hybrid ABC algorithm based on different search mechanisms is proposed in this paper. According to the type of position information in ABC, three basic search mechanisms are summarised which include searching around the individual, the random neighbour, and the global best solution. Then, the basic search mechanisms are improved to obtain three search strategies. All of these strategies can make a good balance between exploration and exploitation. At every iteration, each bee randomly selects a search strategy to produce a candidate solution under the same probability. The experiment is conducted on 12 classical functions and 28 CEC2013 functions. Results show that the new algorithm performs significantly better than several recently proposed similar algorithms in terms of the convergence speed and solution accuracy. © Copyright 2015 Inderscience Enterprises Ltd.


Wang H.,Nanchang Institute of Technology | Wang H.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | Wang W.,Nanchang Institute of Technology | Sun H.,Nanchang Institute of Technology | Sun H.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing
International Journal of Wireless and Mobile Computing | Year: 2015

Firefly Algorithm (FA) is a new optimisation algorithm based on swarm intelligence, which has shown good performance on many optimisation problems. However, the standard FA easily falls into local minima because of too many attraction operations. To enhance the performance of the standard FA, a new FA is proposed in this paper. The new approach employs Generalised Opposition-Based Learning (GOBL) for population initialisation and generation jumping. To verify the performance of our approach, a set of benchmark functions tested in the experiments. Computational results show that the proposed approach obtains better performance than the standard FA and some recently proposed FA variants. © Copyright 2015 Inderscience Enterprises Ltd.


Sun L.,Wuhan University | Sun L.,Zhengzhou Institute of Surveying and Mapping | Liu Z.,Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing | Liu Z.,Nanchang Institute of Technology | And 8 more authors.
Atmospheric Science Letters | Year: 2016

To analyze the dynamics of air pollution, a homogenous partition of the coarse graining process is employed to transform the daily air pollution index series in Lanzhou into a character series consisting of five characters (R, r, e, d and D). The nodes of the pollution fluctuation network are 125 three-symbol strings (i.e. 125 fluctuation patterns in a duration of 3 days) linked in the network's topology by a time sequence. The network contains integrated information about the interconnections and interactions among the fluctuation patterns of pollution in the network topology. After calculating the dynamical statistics of degree and degree distribution, we find that the distribution follows a three-stage power-law distribution characterized by a scale-free property with hierarchy structure and small-world effect. Therefore, the pollution fluctuation network is not only a scale-free network with hierarchy but also a small-world network. The higher the degree of the node is, the greater the probability that the pollution fluctuation modes will occur. The main nodes of pollution fluctuation networks generally contain the symbols R and r, which demonstrates that the feature of pollution fluctuation is mainly ascending. © 2016 Royal Meteorological Society.

Loading Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing collaborators
Loading Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing collaborators