Zhejiang Business College
Zhejiang Business College
Ji X.,Zhejiang Business College
International Journal Bioautomation | Year: 2017
Medical imaging is becoming increasingly important in clinical diagnosis. Ultrasound imaging, computed tomography, magnetic resonance imaging (MRI) and other new medical imaging technology greatly broadens the imaging diagnostic methods. Animal Computer Tomography (CT) imaging, as an animal model, is of great significance to guide the experimental research of clinical diagnosis, and the treatment of pet disease also has a pioneering significance. Image segmentation, as the basis of medical image processing and analysis, has played a vital role in clinical diagnosis and treatment from doctors. In this paper, the existing segmentation algorithm is improved based on the characteristics of CT images of animals. In this paper, we use the global optimization of the genetic algorithm to improve the traditional support vector machine classification algorithm. At the same time, the kernel function of the support vector machine algorithm is improved to promote the segmentation results. The experiments show that the algorithm in this paper has a better segmentation effect in the processing of CT images of animals. © 2017 by the authors.
Wang B.,Zhejiang University of Technology |
Ji X.,Zhejiang Business College
RISTI - Revista Iberica de Sistemas e Tecnologias de Informacao | Year: 2016
While enjoying the great convenience brought by Internet, the Internet has created the problem of information overload. In recent years, personalized recommendation system has become a powerful tool to solve the information overload problem. However, the standalone recommendation system still can't provide highly efficient and quick personalized service. Therefore, it is necessary to combining the Spark platform which can process large-scale data efficiently with the personalized recommendation system to provide satisfying personalized recommendation service in mass data environment. This paper uses Spark platform as the core, combines with other Apache open source software to build a distributed employment recommendation system, sorts out and analyzes the employment information that search on the third-party employment information service website, then according to college student's resume recommends the recruitment information that suit for their professional level and personal preferences, so as to offer help for college students to obtain high-quality employment.
Li K.,Xiamen University |
Ding C.,Xiamen University |
Wang F.,Jimei University |
Hu J.,Zhejiang Business College
Journal of Dynamical and Control Systems | Year: 2014
In this paper, we discuss the semicontinuities of orbital and limit set maps in an impulsive semidynamical system and investigate their relationships with the stabilities of orbits. Actually, we only deal with infinite impulsive trajectories under the hypotheses that each prolongational set is compact in the phase space. We prove that if the limit set is stable (eventually stable or eventually weakly stable), then the corresponding limit set map is upper semicontinuous or lower semicontinuous, respectively. And if the limit set map is upper semicontinuous (lower semicontinuous), then the corresponding limit set is stable (eventually stable or eventually weakly stable, respectively). Furthermore, we give several sufficient conditions to guarantee that limit sets are minimal. © 2013 Springer Science+Business Media New York.
Youming Z.,Zhejiang Business College
International Journal of Smart Home | Year: 2016
Supported by the spatial information technologies (SIT), this paper builds a database by integrating multi-source data like RS, spatial survey, economic statistics, etc., accomplishes the planning of ecological pattern of industrial technology innovation strategic alliance in gulf of Hangzhou area, and presents the strategies of constructing the operation mechanism of the industrial technology innovation strategic alliance in a bid to provide basis for the decision making of enhancing the innovation abilities of Chinese enterprises in this area. © 2016 SERSC.
Zhang G.,Zhejiang Business College |
Liang W.,Shanxi Coke Group Company
Huagong Xuebao/CIESC Journal | Year: 2013
A particle packing method was developed to prepare porous silica ceramics aggregated by sintering silica powder with methyl cellulose as binding agent at 1300°C for 1 h. The result of electromagnetic wave absorption showed obvious electromagnetic wave absorption properties with a bandwidth of 9 GHz and -3 dB reflectivity. The electromagnetic wave absorption properties changed after graphene oxide (GO)layers were incorporated into the samples. When the mass fraction of graphene oxide impregnated samples was 0.004%, an increase of 75% in absorption was observed with the greatest reflectivity of -5 dB. The eddy current damping caused by these GO layers was responsible for the enhanced absorption efficiency. While excess GO made the porous sample to be a reflector for incident waves. © All Rights Reserved.
Fan R.,Zhejiang Business College |
Zhou M.,Zhejiang Business College
Journal of Computational Information Systems | Year: 2013
According to the increasing frequency of current network attack s, the existing network security situational awareness model is unable to meet the network security detection and early warning needs in confrontational environment. The research mainly in establishing unequal time interval sequence model, unequal interval gray model and gray theory-based inverse function model, by the three models, coming out a network security situation awareness model based on gray-theory, and the amendment on the precision of the model based on the multi-stage residuals. The experiments show that the perception of the model to the network security situation is able to achieve a satisfactory fitting accuracy, which is full of practical value. Copyright © 2013 Binary Information Press.
Yang M.,Zhejiang Business College
Advance Journal of Food Science and Technology | Year: 2015
With the advance of China's urbanization, industrialization accelerated and extensions of agricultural, our grain demand changes, then it has a important sense for the forecast of total food demanded during 2014 to 2030 involves China's food security, social stability and rapid development. In this study, we use time series model to forecast the rural and urban residents' per capita food consumption in China during 2020 to 2030, then we combines it with population growth and urbanization-related data of the total food demanded to forecast Chinese total demands in 2030. The results showed that the total demand of food has an increasing trend, as it in 2030, the total grain demands was 627.5 million t, food consumption will be reduced and fodder grain consumption will continue to increase. According to this study, we have analyzed the factors affecting changes in demand for food and it came the result that the food demand is influenced interaction with China's economic structure. © Maxwell Scientific Organization, 2015.
Zhihui F.,Zhejiang Business College
International Journal of Multimedia and Ubiquitous Engineering | Year: 2014
Through analysis of mechanism and characteristics of Session initiation protocol (short for SIP), it is found that SIP possesses prominent flexibility and expansibility, which meet the requirement of Internet infrastructure and media flow transmission. To some extent, tight-coupling model based on SIP reflects the fundamentals of distance education and session initiation. Furthermore, while key control and media mixer are functionally separated. A Web server is added to improve mutual communication. The model SIP-based distance education system with three centralized servers are constructed and the corresponding topology structure is proposed. The mechanism and education function of the model are embodied and realized through several aspects, such as distance class creation, participation and termination, state information notification and education resource control. © 2014 SERSC.
Fu Z.,Zhejiang Business College
BioTechnology: An Indian Journal | Year: 2014
This paper firstly introduces the mode of transmission in free space. List the expression of transmission loss in the vacuum environment. The SON optimization modelings are introduced, and introduces the concrete optimization goal is the capacity and energy saving as well as their mutual self optimization. Then through the communication theory of electromagnetic wave in the private space, analyzed the influence factors of the network capacity, according them to establish the model of the network capacity. And analyze energy consumption when the transmission power of the base station is allocated to each user. Therefore, establish energy-saving model. Finally, we introduced the real-time traffic control variable; to analysis select target optimization under different scenarios, which established the final self-optimization model. © 2014 Trade Science Inc. - INDIA.
Zhang J.,Zhejiang Business College
Journal of Networks | Year: 2014
In complex manufacturing, the system parameters have dynamic and nonlinear characters. Existing parameters setting methods show low efficiency and accuracy, and some setting experience accumulated in engineering practice can not be fully used. Therefore, an online parameter setting method with improved adaptive neuro-based fuzzy inference model is proposed in this paper. The advantages of ANFIS in self-learning and fuzzy inference method of fuzzy mathematics are combined effectively to determine the fuzzy rules and fuzzy membership. Then the neural network predictor is introduced to enhance the adaptive ability and nonlinear approximation ability of fuzzy neural network. The parameters and the structure of fuzzy rules are regulated and updated by the nearest neighbor clustering algorithm, which improves the accuracy of fuzzy inference and enhances the fault-tolerance and robustness of system. In our experiments, by the simulations of transformer fault diagnosis and soldering technology, we find improved ANFIS model can better reflect the actual operating state of transformer and it can make modeling and control for nonlinear I/O system in the manufacturing process like soldering. The improved system is also proved by experiments to have better performance in robustness and convergence. © 2014 ACADEMY PUBLISHER.