An effective evolutionary algorithm for the multiple container packing problem

This paper focuses on a new optimization problem, which is called ＂The Multiple Container Packing Problem （MCPP）＂ and proposes a new evolutionary approach for it. The proposed evolutionary approach uses ＂Adaptive Link Adjustment Evolutionary Algorithm （ALA-EA）＂ as a basic framework and it incorporates a heuristic local improvement approach into ALA-EA. The first step of the local search algorithm is to raise empty space through the exchange among the packed items and then to improve the fitness value through packing unpacked items into the raised empty space. The second step is to exchange the packed items and the unpacked items one another toward improving the fitness value. The proposed algorithm is compared to the previous evolutionary approaches at the bench-mark instances （with the same container capacity） and the modified benchmark instances （with different container capacity） and that the algorithm is proved to be superior to the previous evolutionary approaches in the solution quality.     

Parameter Optimization of Linear Quadratic Controller Based on Genetic Algorithm

The selection of weighting matrix in design of the linear quadratic optimal controller is an important topic in the control theory. In this paper, an approach based on genetic algorithm is presented for selecting the weighting matrix for the optimal controller. Genetic algorithm is adaptive heuristic search algorithm premised on the evolutionary ideas of natural selection and genetic. In this algorithm, the fitness function is used to evaluate individuals and reproductive success varies with fitness. In the design of the linear quadratic optimal controller, the fitness function has relation to the anticipated step response of the system. Not only can the controller designed by this approach meet the demand of the performance indexes of linear quadratic controller, but also satisfy the anticipated step response of close-loop system. The method possesses a higher calculating efficiency and provides technical support for the optimal controller in engineering application. The simulation of a three-order single-input single-output (SISO) system has demonstrated the feasibility and validity of the approach.     

Adaptive interactive genetic algorithms with individual interval fitness

It is necessary to enhance the performance of interactive genetic algorithms in order to apply them to complicated optimization problems successfully. An adaptive interactive genetic algorithm with individual interval fitness is proposed in this paper in which an indi-vidual fitness is expressed by an interval. Through analyzing the fitness, information reflecting the distribution of an evolutionary population is picked up, namely, the difference of evaluating superior individuals and the difference of evaluating a population. Based on these, the adaptive probabilities of crossover and mutation operators of an individual are presented. The algorithm proposed in this paper is applied to a fashion evolutionary design system, and the results show that it can find many satisfactory solutions per generation. The achievement of the paper provides a new approach to enhance the t~erformance of interactive genetic algorithms.     

Personification algorithm for protein folding problem：Improvements in PERM

PERM is the most efficient approach for solving protein folding problem based on simple lattice model. In this article a personification explanation of PERM is proposed. A new version of PERM, population control algorithm with two main improvements is presented: one is that it is able to redefine the weight and its predicted value in PERM,and the other is that it is able to unify the calculation of weight when choosing possible branches. The improved PERM is more efficient than the previous version; specifically it can find the known lowest energy states for the four well-known difficult instances and is generally several to hundreds times faster than PERM. It is noteworthy that with the improved PERM we found new lowest energy configurations of three of the four difficult problems missed in previous papers.     

Personalized Recommendation Algorithm Based on Preference Features

A hybrid collaborative filtering algorithm based on the user preferences and item features is proposed.A thorough investigation of Collaborative Filtering （CF） techniques preceded the development of this algorithm.The proposed algorithm improved the user-item similarity approach by extracting the item feature and applying various item features＇ weight to the item to confirm different item features.User preferences for different item features were obtained by employing user evaluations of the items.It is expected that providing better recommendations according to preferences and features would improve the accuracy and efficiency of recommendations and also make it easier to deal with the data sparsity.In addition,it is expected that the potential semantics of the user evaluation model would be revealed.This would explain the recommendation results and increase accuracy.A portion of the MovieLens database was used to conduct a comparative experiment among the proposed algorithms,i.e.,the collaborative filtering algorithm based on the item and the collaborative filtering algorithm based on the item feature.The Mean Absolute Error （MAE） was utilized to conduct performance testing.The experimental results show that employing the proposed personalized recommendation algorithm based on the preference-feature would significantly improve the accuracy of evaluation predictions compared to two previous approaches.     

Analog Module Placement Design Using Genetic Algorithm

This paper presents a novel genetic algorithm for analog module placement based on a generalization of the two-dimensional bin packing problem. The genetic encoding and operators assure that all problem constraints are always satisfied. Thus the potential problems of adding penalty terms to the cost function are eliminated so that the search configuration space is drastically decreased. The dedicated cost function is based on the special requirements of analog integrated circuits. A fractional factorial experiment was conducted using an orthogonal array to study the algorithm parameters. A meta-GA was applied to determine the optimal parameter values. The algorithm was tested with several local benchmark circuits. The experimental results show that the algorithm has better performance than the simulated annealing approach with satisfactory results comparable to manual placement. This study demonstrates the effectiveness of the genetic algorithm in the analog module placement problem. The algorithm has b     

Algorithm of capacity expansion on networks optimization

The paper points out the relationship between the bottleneck and the minimum cutset of the network, and presents a capacity expansion algorithm of network optimization to solve the network bottleneck problem. The complexity of the algorithm is also analyzed. As required by the algorithm, some virtual sources are imported through the whole positive direction subsection in the network, in which a certain capacity value is given. Simultaneously, a corresponding capacity-expanded network is constructed to search all minimum cutsets. For a given maximum flow value of the network, the authors found an adjustment value of each minimum cutset are‘s group with gradually reverse calculation and marked out the feasible flow on the capacity-extended networks again with the adjustment value increasing. All this has been done repeatedly until the original topology structure is resumed. So the algorithm can increase the capacity of networks effectively and solve the bottleneck problem of networks.     

Robust SLAM using square-root cubature Kalman filter and Huber’ s GM-estimator

Mobile robot systems performing simultaneous localization and mapping ( SLAM) are generally plagued by non-Gaussian noise.To improve both accuracy and robustness under non-Gaussian meas-urement noise, a robust SLAM algorithm is proposed.It is based on the square-root cubature Kal-man filter equipped with a Huber’ s generalized maximum likelihood estimator ( GM-estimator) .In particular, the square-root cubature rule is applied to propagate the robot state vector and covariance matrix in the time update, the measurement update and the new landmark initialization stages of the SLAM.Moreover, gain weight matrices with respect to the measurement residuals are calculated by utilizing Huber’ s technique in the measurement update step.The measurement outliers are sup-pressed by lower Kalman gains as merging into the system.The proposed algorithm can achieve bet-ter performance under the condition of non-Gaussian measurement noise in comparison with benchmark algorithms.The simulation results demonstrate the advantages of the proposed SLAM algorithm.     

A new non-monotone fitness scaling for genetic algorithm

The properties of selection operators in the genetic algorithm (GA) are studied in detail. It is indicated that the selection of operations is significant for both improving the general fitness of a population and leading to the schema deceptiveness. The stochastic searching characteristics of GA are compared with those of heuristic methods. The influence of selection operators on the GA' s exploration and exploitation is discussed, and the performance of selection operators is evaluated with the premature convergence of the GA taken as an example based on One-Max function. In order to overcome the schema deceptiveness of the GA, a new type of fitness scaling, non monotone scaling, is advanced to enhance the evolutionary ability of a population. The effectiveness of the new scaling method is tested by a trap function and a needle-in-haystack (NiH) function.     

Content-based retrieval based on binary vectors for 2-D medical images

In medical research and clinical diagnosis, automated or computer-assisted classification and retrieval methods are highly desirable to offset the high cost of manual classification and manipulation by medical experts. To facilitate the decision-making in the health-care and the related areas, in this paper, a two-step content-based medical image retrieval algorithm is proposed. Firstly, in the preprocessing step, the image segmentation is performed to distinguish image objects, and on the basis of the segmentation results, the boundary of each object is extracted to simplify each object feature space; and then in the second step, the binary vector for each object is generated to record their spatial information; and based on these local binary vectors, the global image vector is obtained. The proposed algorithm provides potential method for large image database retrieval and browsing.     

Air Filter Simulation by Geodict

IntroductionThe previous approach for modeling the particlefiltration process has been to represent the complicatedfilter structure by a single element and then compute thefluid flow and particle transport around the one element[1,2]. The particletransport was computed byseparately addingthe contributions due to diffusion and inertia to the integratedtrajectory. The problem withthese previous approaches is thatonly general trends can be obtained from the computations ,and considerable amount o…     

Broadcast Scheduling Strategy Based on the Priority of Real-Time Data in a Mobile Environment

Data broadcast is an important data dissemination approach in mobile environment. On broadcast channel, scalability and efficiency of data transmission are satisfied. In a mobile environment, there exists a kind of real-time database application in which both the transactions and data can have their timing constraints and priorities of different levels. In order to meet the requirement of real-time data disseminating and retrieving, a broadcast scheduling strategy HPF-ED F (Highest Priority First with Earlier Deadline and Frequency) is proposed under the BoD (Broadcast on Demand) model. Using the strategy, data items are scheduled according to their priority the transaction imposed on them or system set for them. The strategy also considers other characteristics of data items such as deadline and popularity of data. The extensive simulation experiments have been conducted to evaluate the performance of the proposed algorithm. Results show that it can achieve excellent performance compared with existing     

Nonlinear Spline Kernel-based Partial Least Squares Regression Method and Its Application

Inspired by the traditional Wold＇s nonlinear PLS algorithm comprises of NIPALS approach and a spline inner function model, a novel nonlinear partial least squares algorithm based on spline kernel （named SK-PLS ） is proposed for nonlinear modeling in the presence of multicollinearity. Based on the inner-product kernel spanned by the spline basis functions with infinite number of nodes, this method firstly maps the input data into a highdimensional feature space, and then calculates a linear PLS model with reformed NIPALS procedure in the feature space and gives a unified framework of traditional PLS ＂kernel＂ algorithms in consequence. The linear PLS in the feature Space corresponds to a nonlinear PLS in the original input （primal） space. The good approximating property of spline kernel function enhances the generalization ability of the novel model, and two numerical experiments are given to illustrate the feasibility of the proposed method.     

Genetic Tabu Search for the Multi-Objective Knapsack Problem

We introduce a hybrid algorithm for the 0 - 1 multidimensional multi-objective knapsack problem.This algorithm, called GTS^MOKP, combines a genetic procedure and a tabu search operator. The algorithm is evaluated on 9 well-known benchmark instances and shows highly competitive results compared with two state-of-the-art algorithms.     

A novel evolutionary algorithm for global numerical optimization with continuous variables

Evolutionary algorithms （EAs） are a class of general optimization algorithms which are applicable to functions that are multimodal, non-differentiable, or even discontinuous. In this paper, a novel evolutionary algorithm is proposed to solve global numerical optimiza- tion with continuous variables. In order to make the algorithm more robust, the initial population is generated by combining determinate factors with random ones, and a decent scale function is designed to tailor the crossover operator so that it can not only find the decent direction quickly but also keep scanning evenly in the whole feasible space. In addition, to improve the performance of the algorithm, a mutation operator which increases the convergence-rate and ensures the convergence of the proposed algorithm is designed. Then, the global convergence of the presented algorithm is proved in detail. Finally, the presented algorithm is executed to solve 24 benchmark problems, and the results show that the convergence-rate of the proposed algorithm is much faster than that of the compared algorithms.     

Community-Based User Domain Model Collaborative Recommendation Algorithm

Collaborative Filtering (CF) is a commonly used technique in recommendation systems. It can promote items of interest to a target user from a large selection of available items. It is divided into two broad classes: memory-based algorithms and model-based algorithms. The latter requires some time to build a model but recommends online items quickly, while the former is time-consuming but does not require pre-building time. Considering the shortcomings of the two types of algorithms, we propose a novel Community-based User domain Collaborative Recommendation Algorithm (CUCRA). The idea comes from the fact that recommendations are usually made by users with similar preferences. The first step is to build a user-user social network based on users’ preference data. The second step is to find communities with similar user preferences using a community detective algorithm. Finally, items are recommended to users by applying collaborative filtering on communities. Because we recommend items to users in communities instead of to an entire social network, the method has perfect online performance. Applying this method to a collaborative tagging system, experimental results show that the recommendation accuracy of CUCRA is relatively good, and the online time-complexity reduces to O.n/.     

Automatic Web services composition based on SLM

Motivated by the problem of simplifying the manual operation of the composition process, we propose an approach to automatically compose available Web services to fulfill user＇s goal based on the assumption that there are a set of alternative Web services with similar functionality and different QoS properties. A formal model （i.e. semantic links matrix, SLM for short ） is proposed to store semantic links values for the Web services with semantic relationship and QoS of Web services. The SLM provides a search place for a backward-search planning algorithm, at the same time; the QoS criteria make a rational and effective decision among a number of similar Web services. The function and some properties of the algorithm are analyzed. The approach can improve the correctness and flexibility for Web services composition and satisfy the local QoS attribute.     

Design Pattern Mining Using Graph Matching

The identification of design pattern instances is important for program understanding and software maintenance. Aiming at the mining of design patterns in existing systems, this paper proposes a subgraph isomorphism approach to discover several design patterns in a legacy system at a time. The attributed relational graph is used to describe design patterns and legacy systems. The sub-graph isomorphism approach consists of decomposition and composition process. During the decomposition process, graphs corresponding to the design patterns are decom-posed into subgraphs, some of which are graphs corresponding to the elemental design patterns. The composition process tries to get sub-graph isomorphism of the matched graph if sub-graph isomorphism of each subgraph is obtained. Due to the common structures between design patterns, the proposed approach can reduce the matching times of entities and relations. Compared with the existing methods, the proposed algorithm is not linearly dependent on the number of design pattern graphs.     

MICkNN: Multi-Instance Covering kNN Algorithm

Mining from ambiguous data is very important in data mining. This paper discusses one of the tasks for mining from ambiguous data known as multi-instance problem. In multi-instance problem, each pattern is a labeled bag that consists of a number of unlabeled instances. A bag is negative if all instances in it are negative. A bag is positive if it has at least one positive instance. Because the instances in the positive bag are not labeled, each positive bag is an ambiguous. The mining aim is to classify unseen bags. The main idea of existing multi-instance algorithms is to find true positive instances in positive bags and convert the multi-instance problem to the supervised problem, and get the labels of test bags according to predict the labels of unknown instances. In this paper, we aim at mining the multi-instance data from another point of view, i.e., excluding the false positive instances in positive bags and predicting the label of an entire unknown bag. We propose an algorithm called Multi-Instance Covering kNN (MICkNN) for mining from multi-instance data. Briefly, constructive covering algorithm is utilized to restructure the structure of the original multi-instance data at first. Then, the kNN algorithm is applied to discriminate the false positive instances. In the test stage, we label the tested bag directly according to the similarity between the unseen bag and sphere neighbors obtained from last two steps. Experimental results demonstrate the proposed algorithm is competitive with most of the state-of-the-art multi-instance methods both in classification accuracy and running time.     

An efficient algorithm for mining closed itemsets

This paper presents a new efficient algorithm for mining frequent closed itemsets. It enumerates the closed set of frequent itemsets by using a novel compound frequent itemset tree that facilitates fast growth and efficient pruning of search space. It also employs a hybrid approach that adapts search strategies, representations of projected transaction subsets, and projecting methods to the characteristics of the dataset. Efficient local pruning, global subsumption checking, and fast hashing methods are detailed in this paper. The principle that balances the overheads of search space growth and pruning is also discussed. Extensive experimental evaluations on real world and artificial datasets showed that our algorithm outperforms CHARM by a factor of five and is one to three orders of magnitude more efficient than CLOSET and MAFIA.