A revised support vector regression (SVR) ensemble model based on boosting algorithm (SVR-boosting) is presented in this paper for electricity price forecasting in electric power market. In the light of characteristic...
详细信息
A revised support vector regression (SVR) ensemble model based on boosting algorithm (SVR-boosting) is presented in this paper for electricity price forecasting in electric power market. In the light of characteristics of electricity price sequence, a new triangular-shaped 为oss function is constructed in the training of the forecasting model to inhibit the learning from abnormal data in electricity price sequence. The results from actual data indicate that, compared with the single support vector regression model, the proposed SVR-boosting ensemble model is able to enhance the stability of the model output remarkably, acquire higher predicting accuracy, and possess comparatively satisfactory generalization capability.
This paper presents a new behavior analysis system for analyzing human movements via a boosted string representation. First of all, we propose a triangulation-based method to transform each action sequence into a set ...
详细信息
This paper presents a new behavior analysis system for analyzing human movements via a boosted string representation. First of all, we propose a triangulation-based method to transform each action sequence into a set of symbols. Then, an action sequence can be interpreted and analyzed using this string representation. To analyze action sequences with this string representation, three practical problems should be tackled. Usually, an action sequence has different temporal scaling changes, different initial states, and symbol converting errors. Traditional methods (like hidden Markov models and finite state machines) have limited abilities to deal with the above problems since many unknown states should be constructed and initialized. To tackle the problems, a novel string hypothesis generator is then proposed for generating a bank of string features from which different invariant features can be learned for classifying behaviors more accurately. To learn the invariant features, the Adaboost algorithm is used and modified to train a strong classifier from the set of string hypotheses so that multiple human action events can be well classified. In addition, a forward classification scheme is proposed to classify all input action sequences more accurately even though they have various scaling changes and coding errors. Experimental results prove that the proposed method is a robust, accurate, and powerful tool for human movement analysis. (C) 2008 Elsevier Ltd. All rights reserved.
Support vector machine (SVM) is based on the VC theory and the principle of structural risk minimization. For some learning domains that need more accurate learning performance, SVM can be improved for this objective....
详细信息
ISBN:
(纸本)9780769533049
Support vector machine (SVM) is based on the VC theory and the principle of structural risk minimization. For some learning domains that need more accurate learning performance, SVM can be improved for this objective. This paper describes an algorithm-Boost-SVM, which puts SVM into AdaBoost framework to improve the learning accuracy of the SVM algorithm. By changing the weights of the training examples in the re-sampling process of AdaBoost, SVM appears to be more accurate. The experimental results show that the proposed method has a competitive learning ability and acquires better accuracy than SVM.
boosting is effective in improving the accuracy of a learner. In this paper, we present our research in developing a Multi-Class SLIPPER (MC-SLIPPER) system for intrusion detection from a boosting-based learning algor...
详细信息
boosting is effective in improving the accuracy of a learner. In this paper, we present our research in developing a Multi-Class SLIPPER (MC-SLIPPER) system for intrusion detection from a boosting-based learning algorithm. Our system is built from multiple available binary SLIPPER modules. Multiple prediction-confidence based strategies are proposed and applied to arbitrate the final prediction among predictions from all binary SLIPPER modules. Our MC-SLIPPER system is evaluated on the KDDCUP'99 intrusion detection dataset. The experimental results show that the system achieves the best performance using the BP neural network. And the system using other prediction strategies gets better performance than the winner of the KDDCUP'99 contest does in term of misclassification cost.
The paper describes a method for vehicle recognition using a generic shape model and boosting neural network classifiers. The generic shape model, which is able to represent different vehicle classes, is derived by pr...
详细信息
ISBN:
(纸本)1424403316
The paper describes a method for vehicle recognition using a generic shape model and boosting neural network classifiers. The generic shape model, which is able to represent different vehicle classes, is derived by principal component analysis on a set of training shapes recovered automatically from 2D image sequences. The pose parameters and the shape parameters of the model are estimated by fitting the model to the vehicle in each image using Genetic algorithm, which are used to classify the vehicle. In order to improve the recognition accuracy and speed, we develop adaptive boosting neural network classifiers for vehicle recognition, it is shown that our approach is more accuracy and faster than existing methods.
Modeling contaminant and water flow through soil requires accurate estimates of soil hydraulic properties in field scale. Although artificial neural networks (ANNs) based pedotransfer functions (PTFs) have been succes...
详细信息
Modeling contaminant and water flow through soil requires accurate estimates of soil hydraulic properties in field scale. Although artificial neural networks (ANNs) based pedotransfer functions (PTFs) have been successfully adopted in modeling soil hydraulic properties at larger scales (national, continental, and intercontinental), the utility of ANNs in modeling saturated hydraulic conductivity (K-s) at a smaller (field) scale has rarely been reported. Hence, the objectives of this study are (i) to investigate the applicability of neural networks in estimating K-s at field scales, (ii) to compare the performance of the field-scale PTFs with the published neural networks program Rosetta, and (iii) to compare the performance of two different ensemble methods, namely Bagging and boosting in estimating K-s. Datasets from two distinct sites are considered in the study. The performances of the models were evaluated when only sand, silt, and clay content (SSC) were used as inputs, and when SSC and bulk density rho(b) (SSC+ rho(b)) were used as inputs. For both datasets, the field scale models performed better than Rosetta. The comparison of field-scale ANN models employing bagging and boosting algorithms indicates that the neural network model employing the boosting algorithm results in better generalization by reducing both the bias and variance of the neural network models.
Image classification is of great importance for digital photograph management. In this paper we propose a general statistical learning method based on boosting algorithm to perform image classification for photograph ...
详细信息
Image classification is of great importance for digital photograph management. In this paper we propose a general statistical learning method based on boosting algorithm to perform image classification for photograph annotation and management. The proposed method employs both features extracted from image content (i.e., color moment and edge direction histogram) and features from the EXIT metadata recorded by digital cameras. To fully utilize potential feature correlations and improve the classification accuracy, feature combination is needed. We incorporate linear discriminant analysis (LDA) algorithm to implement linear combinations between selected features and generate new combined features. The combined features are used along with the original features in boosting algorithm for improving classification performance. To make the proposed learning algorithm more efficient, we present two heuristics for selective feature combinations, which can significantly reduce training computation without losing performance. The proposed image classification method has several advantages: small model size, computational efficiency and improved classification performance based on LDA feature combination. (c) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
As a hot research topic over the last 25 years, face recognition still seems to be a difficult and largely problem. Distortions caused by variations in illumination, expression and pose are the main challenges to be d...
详细信息
As a hot research topic over the last 25 years, face recognition still seems to be a difficult and largely problem. Distortions caused by variations in illumination, expression and pose are the main challenges to be dealt with by researchers in this field. Efficient recognition algorithms, robust against such distortions, are the main motivations of this research. Based on a detailed review on the background and wide applications of Gabor wavelet, this powerful and biologically driven mathematical tool is adopted to extract features for face recognition. The features contain important local frequency information and have been proven to be robust against commonly encountered distortions. To reduce the computation and memory cost caused by the large feature dimension, a novel boosting based algorithm is proposed and successfully applied to eliminate redundant features. The selected features are further enhanced by kernel subspace methods to handle the nonlinear face variations. The efficiency and robustness of the proposed algorithm is extensively tested using the ORL, FERET and BANCA databases. To normalize the scale and orientation of face images, a generalized symmetry measure based algorithm is proposed for automatic eye location. Without the requirement of a training process, the method is simple, fast and fully tested using thousands of images from the BioID and BANCA databases. An automatic user identification system, consisting of detection, recognition and user management modules, has been developed. The system can effectively detect faces from real video streams, identify them and retrieve corresponding user information from the application database. Different detection and recognition algorithms can also be easily integrated into the framework.
We describe a new boosting algorithm that is the first such algorithm to be both smooth and adaptive. These two features make possible performance improvements for many learning tasks whose solutions use a boosting te...
详细信息
We describe a new boosting algorithm that is the first such algorithm to be both smooth and adaptive. These two features make possible performance improvements for many learning tasks whose solutions use a boosting technique. The boosting approach was originally suggested for the standard PAC model;we analyze possible applications of boosting in the context of agnostic learning, which is more realistic than the PAC model. We derive a lower bound for the final error achievable by boosting in the agnostic model and show that our algorithm actually achieves that accuracy (within a constant factor). We note that the idea of applying boosting in the agnostic model was first suggested by Ben-David, Long and Mansour (2001) and the solution they give is improved in the present paper. The accuracy we achieve is exponentially better with respect to the standard agnostic accuracy parameter beta. We also describe the construction of a boosting "tandem" whose asymptotic number of iterations is the lowest possible (in both gamma and epsilon) and whose smoothness is optimal in terms of O((.)). This allows adaptively solving problems whose solution is based on smooth boosting (like noise tolerant boosting and DNF membership learning), while preserving the original (non-adaptive) solution's complexity.
In this paper, we present a strategy to implement multi-pose face detection in compressed domain. The strategy extracts firstly feature vectors from DCT domain, and then uses a boosting algorithm to build classificrs ...
详细信息
In this paper, we present a strategy to implement multi-pose face detection in compressed domain. The strategy extracts firstly feature vectors from DCT domain, and then uses a boosting algorithm to build classificrs to distinguish faces and non-faces. Moreover, to get more accurate results of the face detection, we present a kernel function and a linear combination to build incrementally the strong classifiers based on the weak classifiers. Through comparing and analyzing results of some experiments on the synthetic data and the natural data, we can get more satisfied results by the strong classifiers than by the weak classifies.
Key words weak classifier - boosting algorithm - face detection - compressed domain
CLC number TP 391. 41
Foundation item: Supported by the National 863 Program (2002 AA11101) and Open Fund of State Technology Center of Multimedia Software Engineering (621-273128)
Biography: CHEN Lei(1978-), male, Master, research direction: image process, image recognition and AI.
暂无评论