• Journal of KIISE:Software and Applications
• /
• v.33 no.5
• /
• pp.489-498
• /
• 2006

In this paper, we suggested a vehicle classification algorithm using pattern recognition method. At present, Inductive Loop Detector is rarely used for vehicle classification because of its low accuracy. To improve the accuracy, we suggest a new algorithm for Loop Detector using neural networks. In the developed algorithm, the inputs to the neural networks are the variation rate of frequency and occupancy-time. The output is classified vehicles. The developed algorithm was assessed at test sites and the recognition rate was 91.3percent. The results verified that the proposed algorithm improves the vehicle classification accuracy compared to the conventional method based on Loop Detector.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.539-544
• /
• 2003

This paper describes how to reduce the effect of an occupation threshold by that the transform of mixture components of HMM parameters is controlled in hierarchical tree structure to prevent from over-adaptation. To reduce correlations between data elements and to remove elements with less variance, we employ PCA (Principal component analysis) and ICA (independent component analysis) that would give as good a representation as possible, and decline the effect of over-adaptation. When we set lower occupation threshold and increase the number of transformation function, ordinary MLLR adaptation algorithm represents lower recognition rate than SI models, whereas the proposed MLLR adaptation algorithm represents the improvement of over 2% for the word recognition rate as compared to performance of SI models.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.43-49
• /
• 2004

The classification time required by conventional multi-class SVMs(Support Vector Machines) greatly increases as the number of pattern classes increases. This is due to the fact that the needed set of binary class SVMs gets quite large. In this paper, we propose a method to reduce the number of classes by using nearest neighbor rule (NNR) in the principle component analysis and linear discriminant analysis (PCA+LDA) feature subspace. The proposed method reduces the number of face classes by selecting a few classes closest to the test data projected in the PCA+LDA feature subspace. Results of experiment show that our proposed method has a lower error rate than nearest neighbor classification (NNC) method. Though our error rate is comparable to the conventional multi-class SVMs, the classification process of our method is much faster.

• Korean Journal of Health Education and Promotion
• /
• v.20 no.3
• /
• pp.1-18
• /
• 2003

This study was conducted to evaluate factors related to the recogniton and behavioral intention for smoking cessation programs. Five effective smoking cessation programs were considered： acupuncture, nicotine patch, clinic program, mass education, and alliance programs. To explain the health behavior for smoking and smoking cessation programs, a five-stage behavioral intention model was built, and 500 questionnaires were completed through a telephone survey. Stages of the model included recogniton of the programs, past experiences, present smoking status, intention for smoking, and behavioral intention for smoking cessation programs. The results showed that the recogniton rate of the programs were low in general, therefore strategies of education, public relations, and advertisement need to be pursued. Nicotine dependency resulted in the fact that success rates were low although trial rates of smoking cessation were high among smokers. The necessity for smoking cessation programs was suggested. And the significant factors related to the intention for smoking cessation were individual attitude and reluctancy to pay time and money. Others' attitude was insignificant to subjects' smoking cessation. Purchase rates for nicotine patches were 11.3％ for male and 27.3％ for female, those for acupunture were 7.6％ for male and 10.0％ for female. There were very low purchase rates for clinic, mass education, and alliance programs. In conclusion, evidence-based and effective smoking cessation programs need to be promoted by medical doctors. Strategies in education, public relations, and advertisement also need development. In addition, continuing legal and systematic support for smoking cessation would lower the smoking rate and ultimately contribute to the nation's health.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.1
• /
• pp.103-113
• /
• 2003

We must enhance a fingerprint image to improve the performance of a fingerprint recognition. Because of this reason, many researches were achieved about the fingerprint image enhancement. Representative method is to use Gabor-Filter among them. However GF has the weakness which a processing hour takes long. In this paper, we proposed Half Gabor Filter (HGF) to enhance the fingerprint image fast in the on-line. The HGF, however, can make calculation much simpler, as well as both minutiae-extraction rate and recognition rate. On the other hand, the fingerprint image to enhance using HGF has almost same with the case effectiveness to apply GF. In this paper, we confirme it mathematically and experimentally.

• Journal of Broadcast Engineering
• /
• v.18 no.4
• /
• pp.535-542
• /
• 2013

In this paper, we proposed a advanced hardware engine architecture for high speed and high detection rate image recognitions. We adopted the HOG-LBP feature extraction algorithm and more parallelized architecture in order to achieve higher detection rate and high throughput. As a simulation result, the designed engine which can search about 90 frames per second detects 97.7% of pedestrians when false positive per window is $10^{-4}$.

• Journal of Broadcast Engineering
• /
• v.22 no.2
• /
• pp.257-260
• /
• 2017

In this letter, we propose an efficient automatic modulation recognition (AMR) method which classifies digitally modulated signals by estimating the bandwidth. In AMR, feature-based methods are widely used and the accuracy of the features is highly dependent on the number of symbols and the number of samples per symbol (NSPS). In this letter, at first, we coarsely estimate the bandwidth of the oversampled signals, and then decrease the sample rate to yield adequate NSPS. As a result, more symbols are used for AMR and the correct classification rate becomes high under the same number of samples.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.9 no.3
• /
• pp.145-150
• /
• 2014

This paper presents an effective vision based method for LED traffic light detection at the daytime. First, the proposed method calculates horizontal coordinates to set region of interest (ROI) on input sequence images. Second, the proposed uses color segmentation method to extract region of green and red traffic light. Next, to classify traffic light and another noise, shape filter and haar-like feature value are used. Finally, temporal delay filter with weight is applied to remove blinking effect of LED traffic light, and state and weight of traffic light detection are used to classify types of traffic light. For simulations, the proposed method is implemented through Intel Core CPU with 2.80 GHz and 4 GB RAM, and tested on the urban and rural road video. Average detection rate of traffic light is 94.50 % and average recognition rate of traffic type is 90.24 %. Average computing time of the proposed method is 11 ms.

• Phonetics and Speech Sciences
• /
• v.1 no.1
• /
• pp.63-67
• /
• 2009

In this paper, in order to protect music copyrights, we propose a music identification system which is scalable to the number of pieces of registered music and robust to signal-level variations of registered music. For its implementation, we define the new concepts of 'music word' and 'music phoneme' as recognition units to construct 'music acoustic models'. Then, with these concepts, we apply the HMM-based framework used in continuous speech recognition to identify the music. Each music file is transformed to a sequence of 39-dimensional vectors. This sequence of vectors is represented as ordered states with Gaussian mixtures. These ordered states are trained using Baum-Welch re-estimation method. Music files with a suspicious copyright are also transformed to a sequence of vectors. Then, the most probable music file is identified using Viterbi algorithm through the music identification network. We implemented a music identification system for 1,000 MP3 music files and tested this system with variations in terms of MP3 bit rate and music speed rate. Our proposed music identification system demonstrates robust performance to signal variations. In addition, scalability of this system is independent of the number of registered music files, since our system is based on HMM method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.10
• /
• pp.1131-1146
• /
• 1992

In this paper, we suggest a new algorithm applied to the segmentation of published documents to obtain constituent and layout information of document. Firstly, we begin the process of blocking and labeling on a 300dpi scanned document. Secondly, we classify the blocked document by individual sub-regions. Thirdly, we group sub-regions into graphic areas and text areas. Finally, we extract information for layout recognition by using the data. From an experiment on papers of an academic society, we obtain the above 98% of region classification rate and extraction rate of information for the layout recognition.