Current Issue : April - June Volume : 2017 Issue Number : 2 Articles : 5 Articles
For the shortcoming of fuzzy c-means algorithm (FCM) needing to know the number of clusters in advance, this paper proposed\na new self-adaptive method to determine the optimal number of clusters. Firstly, a density-based algorithm was put forward.The\nalgorithm, according to the characteristics of the dataset, automatically determined the possible maximum number of clusters\ninstead of using the empirical rule âË?Å¡...
This study investigated the use of Artificial Neural Network (ANN) and Genetic Algorithm (GA) for prediction of Thailand�s SET50\nindex trend.ANNis a widely accepted machine learning method that uses past data to predict future trend,while GA is an algorithm\nthat can find better subsets of input variables for importing into ANN, hence enabling more accurate prediction by its efficient\nfeature selection. The imported data were chosen technical indicators highly regarded by stock analysts, each represented by 4\ninput variables that were based on past time spans of 4 different lengths: 3-, 5-, 10-, and 15-day spans before the day of prediction.\nThis import undertaking generated a big set of diverse input variables with an exponentially higher number of possible subsets that\nGA culled down to a manageable number of more effective ones. SET50 index data of the past 6 years, from 2009 to 2014, were\nused to evaluate this hybrid intelligence prediction accuracy, and the hybrid�s prediction results were found to be more accurate\nthan those made by a method using only one input variable for one fixed length of past time span....
Locating the assignable causes by use of the abnormal patterns of control chart is a widely used technology for manufacturing quality\ncontrol. If there are uncertainties about the occurrence degree of abnormal patterns, the diagnosis process is impossible to be carried\nout. Considering four common abnormal control chart patterns, this paper proposed a characteristic numbers based recognition\nmethod point by point to quantify the occurrence degree of abnormal patterns under uncertain conditions and a fuzzy inference\nsystem based on fuzzy logic to calculate the contribution degree of assignable causes with fuzzy abnormal patterns. Application case\nresults show that the proposed approach can give a ranked causes list under fuzzy control chart abnormal patterns and support the\nabnormity eliminating....
Robots are developing in much the same way that personal computers did 40 years ago, and robot operating system\nis the critical basis. Current robot software is mainly designed for individual robots. We present in this paper the design\nof micROS, a morphable, intelligent and collective robot operating system for future collective and collaborative\nrobots. We first present the architecture of micROS, including the distributed architecture for collective robot system\nas a whole and the layered architecture for every single node. We then present the design of autonomous behavior\nmanagement based on the observeââ?¬â??orientââ?¬â??decideââ?¬â??act cognitive behavior model and the design of collective intelligence\nincluding collective perception, collective cognition, collective game and collective dynamics. We also give\nthe design of morphable resource management, which first categorizes robot resources into physical, information,\ncognitive and social domains, and then achieve morphability based on self-adaptive software technology. We finally\ndeploy micROS on NuBot football robots and achieve significant improvement in real-time performance....
As one of the key challenges in network virtualization, the problem of virtual network embedding has attracted\nsignificant attention from researchers. In this problem, it needs to embed virtual networks with both node and link\ndemands into a shared physical network. The main goal of this problem is to embed more virtual networks to gain\nmore revenue. However, the prior approaches still suffer from low performance and await to be further optimized in\nterms of this goal. In this paper, we design an artificial bee colony-based virtual network embedding algorithm, called\nVNE-ABC, to solve this problem. The core idea of this algorithm is to leverage the iterations and intelligence of artificial\nbee colony to achieve a more optimal solution for virtual network embedding. Through simulations, we show that our\nproposed algorithm gains about 35.4% more revenue than the existing algorithm....
Loading....