• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.877-881
• /
• 2008

In this paper, we propose a real-time people tracking system with multiple CCD cameras for security inside the building. The camera is mounted from the ceiling of the laboratory so that the image data of the passing people are fully overlapped. The implemented system recognizes people movement along various directions. To track people even when their images are partially overlapped, the proposed system estimates and tracks a bounding box enclosing each person in the tracking region. The approximated convex hull of each individual in the tracking area is obtained to provide more accurate tracking information. To achieve this goal, we propose a method for 3D walking human tracking based on the IMPRESARIO framework incorporating cascaded classifiers into hypothesis evaluation. The efficiency of adaptive selection of cascaded classifiers have been also presented. We have shown the improvement of reliability for likelihood calculation by using cascaded classifiers. Experimental results show that the proposed method can smoothly and effectively detect and track walking humans through environments such as dense forests.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2E
• /
• pp.17-24
• /
• 2001

In this paper, we propose the bootstrap and aggregating (bagging) vector quantization (VQ) classifier to improve the performance of the text-independent speaker recognition system. This method generates multiple training data sets by resampling the original training data set, constructs the corresponding VQ classifiers, and then integrates the multiple VQ classifiers into a single classifier by voting. The bagging method has been proven to greatly improve the performance of unstable classifiers. Through two different experiments, this paper shows that the VQ classifier is unstable. In one of these experiments, the bias and variance of a VQ classifier are computed with a waveform database. The variance of the VQ classifier is compared with that of the classification and regression tree (CART) classifier[1]. The variance of the VQ classifier is shown to be as large as that of the CART classifier. The other experiment involves speaker recognition. The speaker recognition rates vary significantly by the minor changes in the training data set. The speaker recognition experiments involving a closed set, text-independent and speaker identification are performed with the TIMIT database to compare the performance of the bagging VQ classifier with that of the conventional VQ classifier. The bagging VQ classifier yields improved performance over the conventional VQ classifier. It also outperforms the conventional VQ classifier in small training data set problems.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.6
• /
• pp.88-98
• /
• 1998

Subspace classifier is a popular pattern recognition method based on Karhunen-Loeve transform. This classifier describes a high dimensional pattern by using a reduced dimensional subspace. Because of the loss of information induced by dimensionality reduction, however, a subspace classifier sometimes shows unsatisfactory recognition performance to the patterns having quite similar principal components each other. In this paper, we propose the use of multiple novelty neural network classifiers constructed on novelty vectors to adopt minor components usually ignored and present a method of improving recognition performance through combining those with the subspace classifier. We develop the proposed classifier on handwritten numeral database and analyze its properties. Our proposed classifier shows better recognition performance compared with other classifiers, though it requires more weight links.

• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.99-102
• /
• 2003

In this paper we propose an adaptive learning method for HMM classifiers by using splitting and merging techniques to overcome the problem of the conventional teaming, where one HMM classifier per class has been trained, individually. The experimental results demonstrate a possibility that the proposed mechanism could be applied for applications of having multiple clusters in a class.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.11a
• /
• pp.411-416
• /
• 2006

Fault detection and diagnosis is the most important technology in condition-based maintenance(CBM) system that usually begins from collecting signatures of running machines using multiple sensors for subsequent accurate analysis. With the quick development in industry, there is an increasing requirement of selecting special sensors that are cheap, robust, and easy-installation. This paper experimentally investigated performances of four types of sensors used in induction motors faults diagnosis, which are vibration, current, voltage and flux. In addition, diagnostic effects of five popular classifiers also were evaluated. First, the raw signals from the four types of sensors are collected at the same time. Then the features are calculated from collected signals. Next, these features are classified through five classifiers using artificial intelligence techniques. Finally, conclusions are given based on the experiment results.

• Journal of Information Technology Services
• /
• v.14 no.4
• /
• pp.121-135
• /
• 2015

Ensemble classification is to utilize multiple classifiers instead of using a single classifier. Recently ensemble classifiers have attracted much attention in data mining community. Ensemble learning techniques has been proved to be very useful for improving the prediction accuracy. Bagging, boosting and random subspace are the most popular ensemble methods. In random subspace, each base classifier is trained on a randomly chosen feature subspace of the original feature space. The outputs of different base classifiers are aggregated together usually by a simple majority vote. In this study, we applied the random subspace method to the bankruptcy problem. Moreover, we proposed a method for optimizing the random subspace ensemble. The genetic algorithm was used to optimize classifier subset of random subspace ensemble for bankruptcy prediction. This paper applied the proposed genetic algorithm based random subspace ensemble model to the bankruptcy prediction problem using a real data set and compared it with other models. Experimental results showed the proposed model outperformed the other models.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.3
• /
• pp.163-169
• /
• 2008

In this paper, we propose a real-time people tracking system with multiple CCD cameras for security inside the building. The camera is mounted from the ceiling of the laboratory so that the image data of the passing people are fully overlapped. The implemented system recognizes people movement along various directions. To track people even when their images are partially overlapped, the proposed system estimates and tracks a bounding box enclosing each person in the tracking region. The approximated convex hull of each individual in the tracking area is obtained to provide more accurate tracking information. To achieve this goal, we propose a method for 3D walking human tracking based on the IMPRESARIO framework incorporating cascaded classifiers into hypothesis evaluation. The efficiency of adaptive selection of cascaded classifiers have been also presented. We have shown the improvement of reliability for likelihood calculation by using cascaded classifiers. Experimental results show that the proposed method can smoothly and effectively detect and track walking humans through environments such as dense forests.

• 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.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1175-1186
• /
• 2017

Human emotion recognition is one of the promising applications in the era of artificial super intelligence. Thus far, facial expression traits are considered to be the most widely used information cues for realizing automated emotion recognition. This paper proposes a novel facial expression recognition (FER) method that works well for recognizing emotion from image sequences. To this end, we develop the so-called weighted soft voting classification (WSVC) algorithm. In the proposed WSVC, a number of classifiers are first constructed using different and multiple feature representations. In next, multiple classifiers are used for generating the recognition result (namely, soft voting) of each face image within a face sequence, yielding multiple soft voting outputs. Finally, these soft voting outputs are combined through using a weighted combination to decide the emotion class (e.g., anger) of a given face sequence. The weights for combination are effectively determined by measuring the quality of each face image, namely "peak expression intensity" and "frontal-pose degree". To test the proposed WSVC, CK+ FER database was used to perform extensive and comparative experimentations. The feasibility of our WSVC algorithm has been successfully demonstrated by comparing recently developed FER algorithms.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.2
• /
• pp.21-28
• /
• 2010

This paper reports an experimental result on optimizing dissimilarity-based classification(DBC) by simultaneously using a dynamic time warping(DTW) and a multiple fusion strategy(MFS). DBC is a way of defining classifiers among classes; they are not based on the feature measurements of individual samples, but rather on a suitable dissimilarity measure among the samples. In DTW, the dissimilarity is measured in two steps: first, we adjust the object samples by finding the best warping path with a correlation coefficient-based DTW technique. We then compute the dissimilarity distance between the adjusted objects with conventional measures. In MFS, fusion strategies are repeatedly used in generating dissimilarity matrices as well as in designing classifiers: we first combine the dissimilarity matrices obtained with the DTW technique to a new matrix. After training some base classifiers in the new matrix, we again combine the results of the base classifiers. Our experimental results for well-known benchmark databases demonstrate that the proposed mechanism achieves further improved results in terms of classification accuracy compared with the previous approaches. From this consideration, the method could also be applied to other high-dimensional tasks, such as multimedia information retrieval.