Applied Mechanics and Materials Vols. 644-650

Abstract: Frequency diversity scheduling allocates whole system bandwidth to a user in order to conquer deep fading of the sub-band when user with high-mobility. Though OFDMA technology mitigates interference of users in same cell, it increases interference of cell edge user as base stations use same frequency. Thus, we developed a frequency diversity fairness scheduling algorithm to balance fairness of cell center user and cell edge user. It is demonstrated by computer simulation that the proposed algorithm increases user fairness of the system with same system throughput and fairness between cell edge user and cell center user. It also points out that the algorithm proposed has the same complexity with the frequency diversity scheduling algorithm.

Abstract: In this paper, we present a scheme to improve immune cloning selection algorithm. The improved algorithm, which is referred to as adaptive cloning selection algorithm (ACSA), is proposed and then applied to function optimization. At first, we present adaptive gene mutation which decides mutation probability of each code point (locus) based on the quality of antibodies and the number of evolution iterations. Secondly, we present an iteratively increasing method from one locus to the all ones, which can be used in function optimization. Then, the cloning selection process of evolution is divided into two-stages. The first step is to increase locus of antibodies. In the other one, the Baldwin effect learning operator is employed. And finally, an experiment is carried out to verify the theoretical analyses on several testing functions.

Abstract: Screening candidates is the key step to improve the efficiency of ontology mapping. Minimum spanning tree clustering is one of the important ways of graph clustering algorithm. Defining the related concepts and methods first, according to the characteristics of the ontology file itself, Select graph clustering of minimum spanning tree clustering algorithm, To screening candidates of participate in the concept of mapping, Aiming at the deficiency and improvement of objective function in the algorithm, based on the system information entropy instead of the complicated calculation of similarity to supervise the clustering. To reduce the computational scale and improve the efficiency.

Abstract: High-speed Railway Energy-saving Operation is a NP complete problem and it’s difficult to seek the optimal solution by tradition method. In this paper, considering the influence braking utilization to train operation, we established a high-speed railway minimum energy cost model, in which the optimization objective are maximizing the Interval efficiency and minimizing the total energy consumption. Then the model is solved by heuristic algorithm and the operation strategies are gotten. The simulation experiment result showed that when the braking utilization is equal to 0, the energy will be largely saved if the operation time is increased slightly; with the increasing of braking utilization, the percentage of saved energy will decrease correspondingly. So, the high-speed railway energy-saving operation strategy based on heuristic algorithm performed well.

Abstract: Locally linear embedding algorithm (LLE) , It makes up the shortcomings that the manifold learning algorithm can be only applied to training samples but not be extended to test samples . However, due to the presence of its Low-dimensional feature space redundant information,and its sample category information does not integrate into a low-dimensional embedding. For this shortcoming, here we introduce the two improved algorithms:the local linear maximum dispersion matrix algorithm (FSLLE) and the adaptive algorithm (ALLE), and the combinations of the above two algorithms.With this experience,combined Garbol and locally linear embedding algorithm (LLE) to compare each conclusion. The results proved to be effective elimination of redundant information among basis vectors and improve the recognition rate.

Abstract: Association rules has played a significant role in mining classification clear affairs, but the performance is poor for the continuous time series data . Firstly, this paper presents the trend of time series, including the rise, decline and steady trend, and the time series trend method is proposed; Secondly, define the trend of association rules, including the trend of association rules’ support degree, trend of association rule’s confidence; Finally, gives an application example, show the effectiveness of the method in classification and association analysis of time series.

Abstract: This paper develops an improved novel global harmony search (INGHS) algorithm for solving optimization problems. INGHS employs a novel method for generating new solution vectors that enhances accuracy and convergence rate of novel global harmony search (NGHS) algorithm. Simulations for five benchmark test functions show that INGHS possesses better ability to find the global optimum than that of harmony search (HS) algorithm. Compared with NGHS and HS, INGHS is better in terms of robustness and efficiency.

Abstract: The normal parameter reduction in soft set is difficult to application in data mining because of great calculation quantity. In this paper, the intelligent optimization algorithm, the harmony search algorithm, is applied to solve the problem. The normal parameter reduction model is constructed and the harmony search algorithm is designed. Experience has shown that the method is feasible and fast..

Abstract: Influence of different pre-hem paths on the flange geometry was studied first. According to the results of simulation the vertical pre-hem path was applied. Effects of the process parameters including pre-hem angle, flange length and friction coefficient on Roll-in/out were also investigated in this paper. Results of the simulations show that roll-in values decrease with pre-hem angle increasing and increase with flange length and friction coefficient increasing. And in the case of 6×45° leads least hemming force.

Abstract: Particle swarm algorithm is an efficient evolutionary computation method and wildly used in various disciplines. But as a random global search algorithm, particle swarm algorithm easily falls into the local optimal solution for its rapid propagation in populations and in order to overcome these shortcomings, a novel particle swarm algorithm is presented and used in classifying online trading customers. The corresponding improvements include improving the speed update formula of particles and improving the balance between the development and detection capability of original algorithm and redesigning the calculation flow of the improved algorithm. Finally after designing 21 customer classification indicators, the improved algorithm is realized for customer classification of a certain E-commerce enterprise and experimental results show that the algorithm can improve classification accuracy and decreases the square errors.