The task of faults localization is discussed in a model-free setting. As a tool for its solution we consider a multiclass patternrecognition problem with a metric in the label space. Then, this problem is approximate...
详细信息
ISBN:
(纸本)3540357483
The task of faults localization is discussed in a model-free setting. As a tool for its solution we consider a multiclass patternrecognition problem with a metric in the label space. Then, this problem is approximately solved, providing hints on selecting appropriate RBF nets. It was shown that the approximate solution is the exact one in several important cases. Finally, we propose the algorithm for learning the proposed RBF net. The results of its testing are briefly reported.
In the field of mobile communications new robust Voiced/Unvoiced (V/UV) classification algorithms are required in that correct voicing detection is a crucial point in the perceived quality and naturalness of a very lo...
详细信息
In the field of mobile communications new robust Voiced/Unvoiced (V/UV) classification algorithms are required in that correct voicing detection is a crucial point in the perceived quality and naturalness of a very low bit-fate speech coding system. The paper shows that a valid and more convenient alternative to deal with the problem of voicing decision is to use methodologies like fuzzy logic which are suitable for problems requiring approximate rather than exact solutions, and which can be represented through descriptive or qualitative expressions. The Fuzzy Voicing Detector proposed is based on a patternrecognition approach in which the matching phase is performed using three fuzzy rules. The rules have been obtained using FuGeNeSys, a new hybrid learning tool based on Genetic Algorithm and Neural Networks. The fuzzy classifier is computationally very simple and more efficient than traditional methods, which are affected by misclassification errors, above all in the presence of background noise.
Breast cancer continues to be a significant health problem in the world. The most familiar breast anomalies types are mass and microcalcification. However Automatic methods for detecting these abnormalities can identi...
详细信息
ISBN:
(纸本)9781479959341
Breast cancer continues to be a significant health problem in the world. The most familiar breast anomalies types are mass and microcalcification. However Automatic methods for detecting these abnormalities can identify breast cancer at an early stage. In this paper, we propose a marker-controlled watershed algorithm to locate breast masses. The preprocessing step has been introduced to remove all undesirable areas from mammogram. Foreground and background markers are then selected in order to apply a watershed segmentation algorithm that identifies the location of tumor region in mammogram. The proposed method was successful to segment mass anomalies. It has been tested on publicly available Mammographic Image Analysis Society (MIAS) database and it has achieved an overall mass detection rate of 90.83% and an area Az of 0.913 under the receiver operating characteristic curve ROC for mass segmentation.
The first step for computer-aided diagnosis for liver of CT scans is the identification of liver region. To deal with multislice CT scans, automatic liver segmentation is required. In this paper, we propose a liver se...
详细信息
ISBN:
(纸本)9781424453306
The first step for computer-aided diagnosis for liver of CT scans is the identification of liver region. To deal with multislice CT scans, automatic liver segmentation is required. In this paper, we propose a liver segmentation algorithm using hybrid techniques by combining morphological-based, region-based and histogram-based techniques to segment volumetric CT data. A morphological-based technique is used to find the initial liver tissue from the first slice which is set as a starting slice and region-based is used for further processing for the rest slices, which incorporates seed point generation from Euclidean distance transform (EDT) image on the previous slice for region growing on the current slice. In order to remove neighboring abdominal organs of the liver which connect to the liver organ, the histogram-based technique is used by finding the left and right histogram tail threshold (HTT) and we repeat the use of morphology filtering and large contour detecting for liver smoothing.
In this paper, we introduce the application of transformation patternrecognition based on a complex artificial immune system. The key feature of the complex artificial immune system is the introduction of complex dat...
详细信息
In this paper, we introduce the application of transformation patternrecognition based on a complex artificial immune system. The key feature of the complex artificial immune system is the introduction of complex data representation. We use complex numbers as the data representation instead of binary numbers used before, besides the weight between different layers. The complex partial autocorrelation coefficients of input antigen which are considered as the antigen presentation are calculated in major histocompatibility complex (MHC) layer of the complex artificial immune system. In the simulations, the transformation of patterns, such as translation, scale or rotation, are recognized in much higher accuracy, and it has obviously higher noise tolerance ability than traditional real artificial immune system and even the complex PARCOR model.
Non Parametric Bayes models, so called family of Latent Dirichlet Allocation (LDA) Topic Models have found application in various aspects of patternrecognition like sentiment analysis, information retrieval, question...
详细信息
ISBN:
(纸本)9781479934003
Non Parametric Bayes models, so called family of Latent Dirichlet Allocation (LDA) Topic Models have found application in various aspects of patternrecognition like sentiment analysis, information retrieval, question answering etc. The topics induced by LDA are used for later tasks such as classification, regression(movie ratings), ranking and recommendation. Recently various approaches are suggested to improve the utility of topics induced by LDA using various side-information such as labeled examples and labeled features. Pair-Wise feature constraints such as cannot-link and must-link, represent weak-supervision and are prevalent in domains such as sentiment analysis. Though must-link constraints are relatively easier to incorporate by using dirichlet tree, the cannot-link constraints are harder to incorporate using the dirichlet forest. In this paper we proposed an approach to address this problem using posterior constraints. We introduced additional latent variables for capturing the constraints, and modified the gibbs sampling algorithm to incorporate these constraints. Our method of Posterior Regularization has enabled us to deal with both types of constraints seamlessly in the same optimization framework. We have demonstrated our approach on a product sentiment review data set which is typically used in text analysis.
This paper presents a method to hide information in audio based on CPT scheme. The proposed method is done by modifying CPT scheme used for hiding data in binary image. We do not use two matrices as key for embedding ...
详细信息
Reservoir characterization plays a crucial role in modern reservoir management. It helps to make sound reservoir decisions and improves the asset value of the oil and gas companies. It maximizes integration of multi-d...
详细信息
ISBN:
(纸本)0780390172
Reservoir characterization plays a crucial role in modern reservoir management. It helps to make sound reservoir decisions and improves the asset value of the oil and gas companies. It maximizes integration of multi-disciplinary data and knowledge and improves the reliability of the reservoir predictions. The ultimate product is a reservoir model with realistic tolerance for imprecision and uncertainty. softcomputing aims to exploit such a tolerance for solving practical problems. In reservoir characterization, these intelligent techniques can be used for uncertainty analysis, risk assessment, data fusion and data mining which are applicable to feature extraction from seismic attributes, well logging, reservoir mapping and engineering. The main goal is to integrate soft data such as geological data with hard data such as 3D seismic and production data to build a reservoir and stratigraphic model. While some individual methodologies (esp. neurocomputing) have gained much popularity during the past few years, the true benefit of softcomputing ties on the integration of its constituent methodologies rather than use in isolation.
Self-supervised learning has recently achieved great success in representation learning without human annotations. The dominant method - that is contrastive learning, is generally based on instance discrimination task...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
Self-supervised learning has recently achieved great success in representation learning without human annotations. The dominant method - that is contrastive learning, is generally based on instance discrimination tasks, i.e., individual samples are treated as independent categories. However, presuming all the samples are different contradicts the natural grouping of similar samples in common visual datasets, e.g., multiple views of the same dog. To bridge the gap, this paper proposes an adaptive method that introduces soft inter-sample relations, namely Adaptive soft Contrastive Learning (ASCL). More specifically, ASCL transforms the original instance discrimination task into a multi-instance soft discrimination task, and adaptively introduces inter-sample relations. As an effective and concise plug-in module for existing self-supervised learning frameworks, ASCL achieves the best performance on several benchmarks in terms of both performance and efficiency. Code is available at https://***/MrChenFeng/ASCL_ICPR2022.
Semi-supervised classification methods try to improve a supervised learned classifier with the help of unlabeled data. In many cases one assumes a certain structure on the data, as for example the manifold assumption,...
详细信息
ISBN:
(纸本)9781509048472
Semi-supervised classification methods try to improve a supervised learned classifier with the help of unlabeled data. In many cases one assumes a certain structure on the data, as for example the manifold assumption, the smoothness assumption or the cluster assumption. Self-training is a method that does not need any assumptions on the data itself. The idea is to use the supervised trained classifier to label the unlabeled points and to enlarge this way the training data. This paper aims to show that a self-training approach with soft-labeling is preferable in many cases in terms of expected loss (risk) minimization. The main idea is to use a soft-labeling to minimize the risk on labeled and unlabeled data together, in which the hard-labeled self-training is an extreme case.
暂无评论