Time filter

Source Type

Han B.,Hainan University | Han B.,Hainan Software Profession Institute | Li J.,Hainan University
Cybernetics and Information Technologies | Year: 2016

Medical volume data containing patient information is often faced with various attacks in the transmission process. In order to enhance the medical information system security, and effectively solve the problem of medical volume data protection, a new zero-watermarking algorithm is proposed in the paper. The new zero-watermarking algorithm takes advantage of three-dimensional discrete wavelet transform multi-resolution analysis characteristics of space and time, three-dimensional discrete cosine transform properties, and differences hashing robust characteristic. In order to enhance watermarking algorithm security, Legendre chaotic neural network is used for scrambling original watermark image. The medical volume data is made by three-dimensional discrete wavelet transform, three-dimensional discrete cosine transform and three-dimensional discrete inverse cosine transform r to obtain the medical volume data feature matrix (4×5×4), which is converted to 64-bit binary feature sequence through difference hashing algorithm. The 64-bit binary feature sequence is used to construct the zero-watermarking. The experimental results prove that the new zero-watermarking has favorable security and robustness resisting various attacks. Therefore, the new zero-watermarking algorithm is more applicable to protect medical volume data.

Han B.,Hainan Software Profession Institute | Li J.B.,Hainan University
Applied Mechanics and Materials | Year: 2013

Base on improved particle swarm algorithm, this paper proposes a linear decreasing inertia weight particle swarm algorithm and error back propagation algorithm based on hybrid algorithm combining. The linear decreasing inertia weight particle swarm algorithm and momentum-adaptive learning rate BP algorithm interchangeably adjust the network weights, so that the two algorithms are complementary. It gives full play to the PSO's global optimization ability and the BP algorithm local search advantage, to overcome the slow convergence speed and easily falling into local weight problems. Simulation results show that this diagnostic method can be used for tolerance analog circuit fault diagnosis, with a high convergence rate and diagnostic accuracy. © (2013) Trans Tech Publications, Switzerland.

Bao-Tai W.,Hainan Software Profession Institute | Rui Z.,Chongqing University of Posts and Telecommunications
2nd International Conference on Future Networks, ICFN 2010 | Year: 2010

There may exist multi-path between the source node and the destination node in asymmetric wireless networks. By calculating the throughput, this paper proposes a new method which determines whether to use different paths to transmit TCP data segment and ACK segment. This method uses bandwidth as criteria for judging, and selects the path having lager bandwidth to forward ACK. Simulation result shows that the proposed method can improve the throughput effectively and advance TCP performance. © 2010 IEEE.

Qin X.,Hainan Software Profession Institute | Han B.,Hainan Software Profession Institute | Cui L.,Yanshan University
CCIE 2011 - Proceedings: 2011 IEEE 2nd International Conference on Computing, Control and Industrial Engineering | Year: 2011

Combining fuzzy theory and neural network is an effective way to be applied in fault diagnosis of analog circuit. For tolerance analog circuit fault, this paper proposed a kind new based on integrated adaptive fuzzy neural network the diagnosis method. The method first uses wavelet transform to extract the signal from the output sample, and characteristics of fault feature vectors are normalized. Then it uses the principal element analysis to reduce the fault sample dimension, the network architecture can be simplified, the computation complexity can be reduced. Afterward training and testing integrated adaptive fuzzy neural network with the preprocessed fault characteristic data. Experimentation indicates that the method has higher diagnosis nicety rate and effectively solves fault tolerance of ambiguity and problems. © 2011 IEEE.

Meng L.-L.,Yanshan University | Sun C.-D.,Yanshan University | Han B.-R.,Hainan software Profession Institute
Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control | Year: 2012

In this paper, a new algorithm based on least square method and FastICA algorithm is proposed to overcome the difficulty in inter-harmonic detection in power system. The algorithm combines FFT and least-squares method to determine the fundamental and harmonic parameters. And it constructs the appropriate virtual observed signals and separates the fundamental, harmonics and some easy detected inter-harmonics with the help of ICA algorithm. Then according to the estimated parameters it can adjust the observed signal matrix and detect remaining small amplitude inter-harmonic signals. The simulation results show that the algorithm can accurately detect the small amplitude inter-harmonics near fundamental and harmonic without prior knowledge and eliminating fundamental and harmonic components in the case of less real-time demand. And this algorithm has high obvious superiority with ICA algorithm.

Huang G.,Hainan Software Profession Institute | Han B.R.,Hainan Software Profession Institute
Applied Mechanics and Materials | Year: 2014

With the rapid development of electronic technology, the system reliability and economic requirements of the importance of the analog circuit fault diagnosis has become increasingly prominent. Aiming at the shortcomings of traditional diagnosis method, the paper presents an analog circuit fault diagnosis method based on principal component analysis of pretreatment and particle swarm hybrid neural network. The method adopts hybrid algorithm to adjust the network weights and thresholds to avoid falling into the local minimum value, which uses principal component pretreatment effectively reduce the complexity of calculation. Simulation results show that the diagnostic method can be used for tolerance analog circuit fault diagnosis, has better application prospect. © (2014) Trans Tech Publications, Switzerland.

Ou J.,Hainan Software Profession Institute | Bai X.-B.,Hainan Software Profession Institute | Pei Y.,Hainan Software Profession Institute | Ma L.,Hainan Software Profession Institute | Liu W.,Hainan Software Profession Institute
ICCMS 2010 - 2010 International Conference on Computer Modeling and Simulation | Year: 2010

Facial expression extraction is the essential step of facial expression recognition. The paper presents a system that uses 28 facial feature key-points in images detection and Gabor wavelet filter provided with 5 frequencies, 8 orientations. In according to actual demand, It can extract the feature of low quality facial expression image target, and have good robust for automatic facial expression recognition. Experimental results show that the performance of the proposed method achieved excellent average recognition rates, when it is applied to facial expression recognition system. © 2010 IEEE.

Wu H.,Hainan Software Profession Institute | Tang M.,Hainan Software Profession Institute | Huang G.,Hainan Software Profession Institute
ICIMA 2010 - 2010 2nd International Conference on Industrial Mechatronics and Automation | Year: 2010

Presented is a street lights control system based on AT89S52 as control core. It is a combined product of the following technologies: a digital clock, a timer, a Liquid Crystal Display (LCD), a statistics of traffic flowing magnitude, a photosensitive induction, an infrared control and alarm function. This street light system also includes a time cut-out function, and an automatic control pattern for even more electricity conserving, namely when vehicles pass by, the light will turn on automatically, later turn off. This design can save a great amount of electricity compared to streetlamps that keep alight during nights. The design implements traffic flow magnitude statistics without adding any hardware, facilitating transportation condition information coUecting. Furthermore, this system has auto-alarm function which will set off if any light is damaged and will show the serial number of the damaged light, thus it is easy to be found and repaired the damaged light. © 2010 IEEE.

Han B.,Hainan Software Profession Institute | Zhang C.,Hainan Software Profession Institute | Qin X.,Hainan Software Profession Institute
2011 IEEE 3rd International Conference on Communication Software and Networks, ICCSN 2011 | Year: 2011

In view of vocational signals and systems courses teaching shortcomings and combined with the characteristics of the course, this article used the Matlab simulation software and project-driven method to study on course teaching, proposed one kind based on Matlab project-driven teaching method that stimulates the student's interest to study, improves the quality of teaching. In practical teaching, it has better teaching effectiveness. © 2011 IEEE.

Bai X.-B.,Hainan Software Profession Institute | Ou J.,Hainan Software Profession Institute | Jiang C.-X.,Hainan Software Profession Institute
2nd International Conference on Future Networks, ICFN 2010 | Year: 2010

The modeling technology of software reliability is analyzed in detail in the paper. According to practical software development, the evaluation standard of reliability model of practical software will be explored. The methods of constructing reliability model of practical software is discussed from the point of view of practical application. © 2010 IEEE.

Loading Hainan Software Profession Institute collaborators
Loading Hainan Software Profession Institute collaborators