|
Identification of strategy parameters for particle swarm optimizer through Taguchi method
KHOSLA Arun, KUMAR Shakti, AGGARWAL K.K.
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2006, 7(12): 6-.
https://doi.org/10.1631/jzus.2006.A1989
Particle swarm optimization (PSO), like other evolutionary algorithms is a population-based stochastic algorithm inspired from the metaphor of social interaction in birds, insects, wasps, etc. It has been used for finding promising solutions in complex search space through the interaction of particles in a swarm. It is a well recognized fact that the performance of evolutionary algorithms to a great extent depends on the choice of appropriate strategy/operating parameters like population size, crossover rate, mutation rate, crossover operator, etc. Generally, these parameters are selected through hit and trial process, which is very unsystematic and requires rigorous experimentation. This paper proposes a systematic based on Taguchi method reasoning scheme for rapidly identifying the strategy parameters for the PSO algorithm. The Taguchi method is a robust design approach using fractional factorial design to study a large number of parameters with small number of experiments. Computer simulations have been performed on two benchmark functions—Rosenbrock function and Griewank function—to validate the approach.
|
|
GIS-based logistic regression method for landslide susceptibility mapping in regional scale
ZHU Lei, HUANG Jing-feng
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2006, 7(12): 9-.
https://doi.org/10.1631/jzus.2006.A2007
Landslide susceptibility map is one of the study fields portraying the spatial distribution of future slope failure susceptibility. This paper deals with past methods for producing landslide susceptibility map and divides these methods into 3 types. The logistic linear regression approach is further elaborated on by crosstabs method, which is used to analyze the relationship between the categorical or binary response variable and one or more continuous or categorical or binary explanatory variables derived from samples. It is an objective assignment of coefficients serving as weights of various factors under considerations while expert opinions make great difference in heuristic approaches. Different from deterministic approach, it is very applicable to regional scale. In this study, double logistic regression is applied in the study area. The entire study area is first analyzed. The logistic regression equation showed that elevation, proximity to road, river and residential area are main factors triggering landslide occurrence in this area. The prediction accuracy of the first landslide susceptibility map was showed to be 80%. Along the road and residential area, almost all areas are in high landslide susceptibility zone. Some non-landslide areas are incorrectly divided into high and medium landslide susceptibility zone. In order to improve the status, a second logistic regression was done in high landslide susceptibility zone using landslide cells and non-landslide sample cells in this area. In the second logistic regression analysis, only engineering and geological conditions are important in these areas and are entered in the new logistic regression equation indicating that only areas with unstable engineering and geological conditions are prone to landslide during large scale engineering activity. Taking these two logistic regression results into account yields a new landslide susceptibility map. Double logistic regression analysis improved the non-landslide prediction accuracy. During calculation of parameters for logistic regression, landslide density is used to transform nominal variable to numeric variable and this avoids the creation of an excessively high number of dummy variables.
|
|
A three-level mobility management scheme for hierarchical mobile IPv6 networks
WAN Zheng, PAN Xue-zeng, CHEN Jian, CUI Yu-zeng
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2006, 7(12): 25-.
https://doi.org/10.1631/jzus.2006.A2118
Performance evaluation shows that Hierarchical Mobile IPv6 (HMIPv6) cannot outperform standard Mobile IPv6 (MIPv6) in all scenarios. Thus, adaptive protocol selection under certain circumstances is desired. Moreover, it is necessary to balance the load among different Mobility Anchor Points (MAPs). This paper proposes an efficient three-level hierarchical architecture for mobility management in HMIPv6 networks, in which a mobile node (MN) may register with either a higher/lower MAP or its home agent according to its speed and the number of connecting correspondent nodes (CNs). An admission control algorithm and a replacement algorithm are introduced to achieve load balancing between two MAP levels and among different MAPs within the same MAP level. Admission control is based on the number of CNs but not MNs that an MAP serves. In case there is no capacity for an MN, the MAP chooses an existing MN to be replaced. The replaced MN uses the MAP selection algorithm again to choose another mobility agent. Simulation results showed that the proposed scheme achieves better performance not only in reducing the signaling overhead, but also in load balancing among different MAPs.
|
|
Ensemble learning HMM for motion recognition and retrieval by Isomap dimension reduction
XIANG Jian, WENG Jian-guang, ZHUANG Yue-ting, WU Fei
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2006, 7(12): 2063-2072.
https://doi.org/10.1631/jzus.2006.A2063
Along with the development of motion capture technique, more and more 3D motion databases become available. In this paper, a novel approach is presented for motion recognition and retrieval based on ensemble HMM (hidden Markov model) learning. Due to the high dimensionality of motion’s features, Isomap nonlinear dimension reduction is used for training data of ensemble HMM learning. For handling new motion data, Isomap is generalized based on the estimation of underlying eigenfunctions. Then each action class is learned with one HMM. Since ensemble learning can effectively enhance supervised learning, ensembles of weak HMM learners are built. Experiment results showed that the approaches are effective for motion data recognition and retrieval.
|
25 articles
|