• Journal of KIISE:Software and Applications
• /
• v.32 no.12
• /
• pp.1229-1237
• /
• 2005

Combining multiple classifiers has been actively exploited to improve classification performance. It is required to construct a pool of accurate and diverse base classifier for obtaining a good ensemble classifier. Conventionally ensemble learning techniques such as bagging and boosting have been used and the diversify of base classifiers for the training set has been estimated, but there are some limitations in classifying gene expression profiles since only a few training samples are available. This paper proposes an ensemble technique that analyzes the diversity of classification rules obtained by genetic programming. Genetic programming generates interpretable rules, and a sample is classified by combining the most diverse set of rules. We have applied the proposed method to cancer classification with gene expression profiles. Experiments on lymphoma cancer dataset, prostate cancer dataset and ovarian cancer dataset have illustrated the usefulness of the proposed method. h higher classification accuracy has been obtained with the proposed method than without considering diversity. It has been also confirmed that the diversity increases classification performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.702-723
• /
• 2020

The application of machine learning (ML) in intrusion detection has attracted much attention with the rapid growth of information security threat. As an efficient multi-label classifier, kernel extreme learning machine (KELM) has been gradually used in intrusion detection system. However, the performance of KELM heavily relies on the kernel selection. In this paper, a novel multiple kernel extreme learning machine (MKELM) model combining the ReliefF with nature-inspired methods is proposed for intrusion detection. The MKELM is designed to estimate whether the attack is carried out and the ReliefF is used as a preprocessor of MKELM to select appropriate features. In addition, the nature-inspired methods whose fitness functions are defined based on the kernel alignment are employed to build the optimal composite kernel in the MKELM. The KDD99, NSL and Kyoto datasets are used to evaluate the performance of the model. The experimental results indicate that the optimal composite kernel function can be determined by using any heuristic optimization method, including PSO, GA, GWO, BA and DE. Since the filter-based feature selection method is combined with the multiple kernel learning approach independent of the classifier, the proposed model can have a good performance while saving a lot of training time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2720-2736
• /
• 2013

Multi-view face detection has become an active area for research in the last few years. In this paper, a novel multi-view human face detection algorithm based on improved real Adaboost is presented. Real Adaboost algorithm is improved by weighted combination of weak classifiers and the approximately best combination coefficients are obtained. After that, we proved that the function of sample weight adjusting method and weak classifier training method is to guarantee the independence of weak classifiers. A coarse-to-fine hierarchical face detector combining the high efficiency of Haar feature with pose estimation phase based on our real Adaboost algorithm is proposed. This algorithm reduces training time cost greatly compared with classical real Adaboost algorithm. In addition, it speeds up strong classifier converging and reduces the number of weak classifiers. For frontal face detection, the experiments on MIT+CMU frontal face test set result a 96.4% correct rate with 528 false alarms; for multi-view face in real time test set result a 94.7 % correct rate. The experimental results verified the effectiveness of the proposed approach.

• Korean Journal of Cognitive Science
• /
• v.6 no.2
• /
• pp.27-45
• /
• 1995

In this paper, we suggest the "Fuzzy Behavior Knowledge Space(FBKS)" and explain how to utilize the FBKS when aggregating decisions of individual classifiers. The concept of "Behavior Knowledge Space(BKS)" is known to be the best method in the context that each classifier offers only one class label as its decision. However. the BKS does not considers measurement value of class label. Furthermore, it does not allow the heuristic knowledge of human experts to be embedded when combining multiple decisions. The FBKS eliminates such drawbacks of the BKS by adapting the fwzy concepts. Our method applies to the classification results that contain both class labels and associated measurement values. Experimental results confirm that the FBKS could be a very promising tool in pattern recognition areas.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.200-207
• /
• 2001

In this paper, we propose an HMM(Hidden Markov modeJ)-MLP(Multi-layer perceptron) hybrid model for recognizing legal words on the English bank check. We adopt an explicit segmentation-based word level architecture to implement an HMM engine with nonscaled and non-normalized symbol vectors. We also introduce an MLP for implicit segmentation-based word recognition. The final recognition model consists of a hybrid combination of the HMM and MLP with a new hybrid probability measure. The main contributions of this model are a novel design of the segmentation-based variable length HMMs and an efficient method of combining two heterogeneous recognition engines. ExperimenLs have been conducted using the legal word database of CENPARMI with encouraging results.

• International journal of advanced smart convergence
• /
• v.8 no.1
• /
• pp.141-146
• /
• 2019

These days, there are many applications using neural networks as parts of their system. On the other hand, adversarial examples have become an important issue concerining the security of neural networks. A classifier in neural networks can be fooled and make it miss-classified by adversarial examples. There are many research to encounter adversarial examples by using denoising methods. Some of them using GAN (Generative Adversarial Network) in order to remove adversarial noise from input images. By producing an image from generator network that is close enough to the original clean image, the adversarial examples effects can be reduced. However, there is a chance when adversarial noise can survive the approximation process because it is not like a normal noise. In this chance, we propose a research that utilizes high-level representation in the classifier by combining GAN network with a trained U-Net network. This approach focuses on minimizing the loss function on high representation terms, in order to minimize the difference between the high representation level of the clean data and the approximated output of the noisy data in the training dataset. Furthermore, the generated output is checked whether it shows minimum error compared to true label or not. U-Net network is trained with true label to make sure the generated output gives minimum error in the end. At last, the remaining adversarial noise that still exist after low-level approximation can be removed with the U-Net, because of the minimization on high representation terms.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.20 no.5
• /
• pp.133-138
• /
• 2010

We present a new multimodal biometric authentication method, which performs both feature-level fusion and decision-level fusion. After generating support vector machines for new features made by integrating face and voice features, the final decision for authentication is made by integrating decisions of face SVM classifier, voice SVM classifier and integrated features SVM clssifier. We justify our proposal by comparing our method with traditional one by experiments with XM2VTS multimodal database. The experiments show that our multilevel fusion algorithm gives higher recognition rate than the existing schemes.

• Korean Journal of Remote Sensing
• /
• v.31 no.3
• /
• pp.205-214
• /
• 2015

In this study, a novel land-cover classification framework for multi-temporal SAR data is presented that can combine multiple features extracted through data transforms and multiple classifiers. At first, data transforms using principle component analysis (PCA) and 3D wavelet transform are applied to multi-temporal SAR dataset for extracting new features which were different from original dataset. Then, three different classifiers including maximum likelihood classifier (MLC), neural network (NN) and support vector machine (SVM) are applied to three different dataset including data transform based features and original backscattering coefficients, and as a result, the diverse preliminary classification results are generated. These results are combined via a majority voting rule to generate a final classification result. From an experiment with a multi-temporal ENVISAT ASAR dataset, every preliminary classification result showed very different classification accuracy according to the used feature and classifier. The final classification result combining nine preliminary classification results showed the best classification accuracy because each preliminary classification result provided complementary information on land-covers. The improvement of classification accuracy in this study was mainly attributed to the diversity from combining not only different features based on data transforms, but also different classifiers. Therefore, the land-cover classification framework presented in this study would be effectively applied to the classification of multi-temporal SAR data and also be extended to multi-sensor remote sensing data fusion.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.4
• /
• pp.60-68
• /
• 1994

In this paper we propose a new Hybrid learning rule applied to multilayer feedforward neural networks, which is constructed by combining Hebbian learning rule that is a good feature extractor and Back-Propagation(BP) learning rule that is an excellent classifier. Unlike the BP rule used in multi-layer perceptron(MLP), the proposed Hybrid learning rule is used for uptate of all connection weights except for output connection weigths becase the Hebbian learning in output layer does not guarantee learning convergence. To evaluate the performance, the proposed hybrid rule is applied to classifier problems in two dimensional space and shows better performance than the one applied only by the BP rule. In terms of learning speed the proposed rule converges faster than the conventional BP. For example, the learning of the proposed Hybrid can be done in 2/10 of the iterations that are required for BP, while the recognition rate of the proposed Hybrid is improved by about $0.778\%$ at the peak.

• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.938-949
• /
• 2015

In this paper, we propose a robust speed-limit sign recognition system which is durable to any sign changes caused by exterior damage or color contrast due to light direction. For recognition of speed-limit sign, we apply CNN which is showing an outstanding performance in pattern recognition field. However, original CNN uses multiple hidden layers to extract features and uses fully-connected method with MLP(Multi-layer perceptron) on the result. Therefore, the major demerit of conventional CNN is to require a long time for training and testing. In this paper, we apply randomly-connected classifier instead of fully-connected classifier by combining random forest with output of 2 layers of CNN. We prove that the recognition results of CNN with random forest show best performance than recognition results of CNN with SVM (Support Vector Machine) or MLP classifier when we use eight speed-limit signs of GTSRB (German Traffic Sign Recognition Benchmark).