Current Issue : October - December Volume : 2019 Issue Number : 4 Articles : 5 Articles
Feature selection is a task of choosing the best combination of potential features that\nbest describes the target concept during a classification process. However, selecting such relevant\nfeatures becomes a difficult matter when large number of features are involved. Therefore, this\nstudy aims to solve the feature selection problem using binary particle swarm optimization (BPSO).\nNevertheless, BPSO has limitations of premature convergence and the setting of inertia weight.\nHence, a new co-evolution binary particle swarm optimization with a multiple inertia weight strategy\n(CBPSO-MIWS) is proposed in this work. The proposed method is validated with ten benchmark\ndatasets from UCI machine learning repository. To examine the effectiveness of proposed method,\nfour recent and popular feature selection methods namely BPSO, genetic algorithm (GA), binary\ngravitational search algorithm (BGSA) and competitive binary grey wolf optimizer (CBGWO) are\nused in a performance comparison. Our results show that CBPSO-MIWS can achieve competitive\nperformance in feature selection, which is appropriate for application in engineering, rehabilitation\nand clinical areas....
This paper presents GM (1, N) models with linear cross effect and nonlinear cross effect,\nand discusses the difference of driving factors between these two types of models to solve the cross\neffects of GM (1, N) model. The model with a linear cross effect in this paper preserves the solution\nof whitenization in the GM (1, 1) model. While the model with nonlinear cross effect integrates the\nsequences of systemic features, driving factors, and the cross effect of these driving factors. While\napplying support vector machine (SVM) regression, it transfers the nonlinear relationship among\nthese sequences to a linear relationship. To test the GM (1, N) model that is based on support vector\nmachine (SVM) with nonlinear effect, the study applies it to forecast the total output of the\npharmaceutical industry. The range of the data is selected from 2005-2017, which the data from\n2005-2013 are used to fit into the model. The GM (1, N) model based on SVM with nonlinear cross\neffect achieves 0.6566 and 0.2956 in its fitted total of relative error and the forecast total of relative\nerror, respectively. The new model presents a more accurate analysis on fitting and forecast\nprecision than the classic GM (1, N) model and GM (1, N) with the linear cross effect model....
In this work, we compare the performance of convolutional neural networks and support\nvector machines for classifying image stacks of specular silicon wafer back surfaces. In these image\nstacks, we can identify structures typically originating from replicas of chip structures or from\ngrinding artifacts such as comets or grinding grooves. However, defects like star cracks are also visible\nin those images. To classify these image stacks, we test and compare three different approaches. In the\nfirst approach, we train a convolutional neural net performing feature extraction and classification.\nIn the second approach, we manually extract features of the images and use these features to train\nsupport vector machines. In the third approach, we skip the classification layers of the convolutional\nneural networks and use features extracted from different network layers to train support vector\nmachines. Comparing these three approaches shows that all yield an accuracy value above 90%.\nWith a quadratic support vector machine trained on features extracted from a convolutional network\nlayer we achieve the best compromise between precision and recall rate of the class star crack with\n99.3% and 98.6%, respectively....
State monitoring and fault diagnosis of an internal combustion engine are critical for complex machinery safety. In the present\nstudy, a high-frequency vibration system was proposed based on Fiber Bragg Grating (FBG) cantilever sensor and intelligent\nalgorithm. Structural vibration signal containing fault information of engine valves and oil nozzle was identified by FBG sensors\nand preprocessed using wavelet decomposition and reconstruction. Moreover, vibration energy was taken as fault characteristics.........
In this paper, a new probability mechanism based particle swarm optimization (PMPSO) algorithm is proposed to solve\ncombinatorial optimization problems. Based on the idea of traditional PSO, the algorithm generates new particles based on\nthe optimal particles in the population and the historical optimal particles in the individual changes. In our algorithm, new\nparticles are generated by a specially designed probability selection mechanism. We adjust the probability of each child element\nin the new particle generation based on the difference between the best particles and the elements of each particle. To this\nend, we redefine the speed, position, and arithmetic symbols in the PMPSO algorithm. To test the performance of PMPSO,\nwe used PMPSO to solve resource-constrained project scheduling problems. Experimental results validated the efficacy of the\nalgorithm....
Loading....