This paper introduces a newly developed test system for structure inspection and evaluation of cement-based products by applying ultrasonic test with support vector machine (SVM) classifier. In other words, this paper...
详细信息
ISBN:
(纸本)9781467327435;9781467327428
This paper introduces a newly developed test system for structure inspection and evaluation of cement-based products by applying ultrasonic test with support vector machine (SVM) classifier. In other words, this paper represents a novel method based on SVM for defect detection, classification of number of defects, and identification of defect materials. With the system, pattern of ultrasonic waves for each case of specimen can be obtained from direct and indirect measurements. Machine learning algorithm called support vector machine and artificial neural network (ANN) are employed for classification and verification of the wave patterns obtained from different samples. By applying the system, the presence or absence of a defect in mortar can be identified. Moreover, the system can also classify the number of defects and identify the defect materials being inside the mortar. For classification, input features are extracted in different ways and the numbers of training sets are varied. Base on the results from SVM, the signals extracted in frequency domain gives better performance than time domain. Using a larger training set can give more satisfactory results. In this article, the methodology is explained and the classification results are discussed. The effectiveness of the developed test system is evaluated. Comparison of the classification results that obtained by between SVM and ANN classifiers is also demonstrated. This study shows that this technique based on patternrecognition has a high potential for practical inspection of concrete structure.
The dimensionality and the amount of data that need to be processed when intensive data streams are classified may occur prohibitively large. The aim of this paper is to analyze Johnson-Linden-strauss type random proj...
详细信息
ISBN:
(纸本)9783642132070
The dimensionality and the amount of data that need to be processed when intensive data streams are classified may occur prohibitively large. The aim of this paper is to analyze Johnson-Linden-strauss type random projections as an approach to dimensionality reduction in pattern classification based on K-nearest neighbors search. We show that in-class data clustering allows us to retain accuracy recognition rates obtained in the original high-dimensional space also after transformation to a lower dimension.
Intuitionistic fuzzy set is a significance softcomputing tool for curbing fuzziness embedded in decision-making processes. To enhance the applicability of intuitionistic fuzzy sets in modelling practical real-life pr...
详细信息
Intuitionistic fuzzy set is a significance softcomputing tool for curbing fuzziness embedded in decision-making processes. To enhance the applicability of intuitionistic fuzzy sets in modelling practical real-life problems, various computing methods have been proposed like distance measures, similarity measures and correlation measures. This paper proposes an intuitionistic fuzzy statistical correlation algorithm with applications to patternrecognition and diagnostic processes. This novel method assesses the magnitude of relationship and indicates whether the intuitionistic fuzzy sets under consideration are correlated in either positive or negative sense. We substantiate the proposed technique with some theoretical results and numerically validate it to be superior in terms of accuracy and reliability in contrast to some hitherto techniques. Finally, we determine decision-making processes involving patternrecognition and diagnostic processes by using JAVA programming language to code the intuitionistic fuzzy statistical correlation measure.
This paper attempts to describe the important characteristics of a distributed computing environment for patternrecognition. A multiprocessor-based system that has some of these characteristics is then proposed for t...
详细信息
This paper attempts to describe the important characteristics of a distributed computing environment for patternrecognition. A multiprocessor-based system that has some of these characteristics is then proposed for the analysis and possible implementation of various image transforms. Algorithms have been developed to allow the direct computation of 2-d Fourier, Walsh and Hadamard transforms in a ″distributed″ manner.
The ink drop spread (IDS) method is a modeling technique developed by algorithmically mimicking the information-handling processes of the human brain. This method has been proposed as a new approach to softcomputing....
详细信息
The ink drop spread (IDS) method is a modeling technique developed by algorithmically mimicking the information-handling processes of the human brain. This method has been proposed as a new approach to softcomputing. IDS modeling is characterized by processing that uses intuitive pattern information instead of complex formulas, and it is capable of stable and fast convergences. This paper investigates the modeling ability of the IDS method based on three typical benchmarks. Experimental results demonstrated that the IDS method can handle various modeling targets, ranging from logic operations to complex nonlinear systems, and that its modeling performance is satisfactory in comparison with that of feedforward neural networks. (c) 2006 Elsevier Inc. All rights reserved.
A generalized algorithm is introduced to mitigate difficulties encountered in practical implementations of the conventional projections-onto-constraint-sets algorithm. The theory and framework of this new procedure ar...
详细信息
In order to improve recognition performance, fusion has become a key technique in the recent years. Compared with single-mode biometrics, the recognition rate of multi-modal biometric systems is improved and the final...
详细信息
ISBN:
(纸本)9781538637883
In order to improve recognition performance, fusion has become a key technique in the recent years. Compared with single-mode biometrics, the recognition rate of multi-modal biometric systems is improved and the final decision is more confident. This paper introduces a novel joint density distribution based rank-score fusion strategy that combines rank and score information. recognition at a distance has only recently been of interest in soft biometrics. We create a new soft biometric database containing the human face, body and clothing attributes at three different distances to investigate the influence by distance on soft biometric fusion. A comparative study about our method and other state of the art rank level and score level fusion methods are also conducted in this paper. The experiments are performed using a soft biometric database we created. The results demonstrate the recognition performance is significantly improved by our proposed method.
The present Special Issue "Advances in Neural Networks Research: IJCNN2009" provides a state-of-art overview of the field of neural networks. It includes 39 papers from selected areas of the 2009 Internation...
详细信息
The present Special Issue "Advances in Neural Networks Research: IJCNN2009" provides a state-of-art overview of the field of neural networks. It includes 39 papers from selected areas of the 2009 international joint conference on Neural Networks (IJCNN2009). IJCNN2009 took place on June 14-19, 2009 in Atlanta, Georgia, USA, and it represents an exemplary collaboration between the international Neural Networks Society and the IEEE Computational Intelligence Society. Topics in this issue include neuroscience and cognitive science, computational intelligence and machine learning, hybrid techniques, nonlinear dynamics and chaos, various softcomputing technologies, intelligent signal processing and patternrecognition, bioinformatics and biomedicine, and engineering applications. (C) 2009 Elsevier Ltd. All rights reserved.
Financial information extraction from big financial reports is a tedious task. This paper speaks about page-wise feature generation and applying learning algorithms for identifying financial information (balance sheet...
详细信息
ISBN:
(纸本)9781509036967
Financial information extraction from big financial reports is a tedious task. This paper speaks about page-wise feature generation and applying learning algorithms for identifying financial information (balance sheets, cash flows, and income statements) in Form 10-K or annual reports of companies. Balance sheets, cash flows, and income statements have some structure in them and are semi-structured information. This approach employs selection of unigrams and bigrams based on frequency of occurrence and expert advice, generation of page wise features, and applying learning models for identifying patterns of specific financial information. Different supervised learning models are applied yielding results with very high accuracy (greater than 99%).
Reservoir computing (RC), a framework for recurrent neural networks, is adept at learning the dynamics of time series data. RC, requiring less computational cost for training than traditional recurrent neural networks...
详细信息
ISBN:
(纸本)9798350359329;9798350359312
Reservoir computing (RC), a framework for recurrent neural networks, is adept at learning the dynamics of time series data. RC, requiring less computational cost for training than traditional recurrent neural networks, is versatile in applications such as time series generation, prediction, patternrecognition, and robot control. Recently, the integration of physical system dynamics, particularly oscillatory phenomena, into RC has been explored. This study presents an RC model incorporating oscillators with hysteresis as network elements, focusing on their ubiquitous nature. In speech patternrecognition, the audio waveform, a complex vibration pattern of air, is typically preprocessed into a frequency component time series. This study, however, attempts patternrecognition by using the raw speech waveform as the direct input to the oscillator-based reservoir. The application of this model in recognizing and classifying time series vocal data is investigated, including an assessment of the oscillator elements' bifurcation parameter on RC performance.
暂无评论