• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.23-24
• /
• 2016

본 논문에서는 온라인 오디오 장르 분류의 성능을 비교 분석한다. 온라인 동작을 위해 1초 단위의 오디오 신호를 입력하여 music, speech, effect 중 하나의 장르로 판단한다. 학습 방법은 GMM과 심층 신경망을 사용하며, 특성은 MFCC와 스펙트로그램을 포함하는 네 가지 종류의 벡터를 사용한다. 각 성능을 비교 분석하여 장르 분류에 적합한 학습 방법과 특성 벡터를 확인한다.

• Journal of Korean Society of Transportation
• /
• v.18 no.1
• /
• pp.47-59
• /
• 2000

The purpose of this study is to develop travel-time estimation model using neural networks and prediction model using neural networks and kalman-filtering technique. The data used in this study are travel speed collected from inductive loop vehicle detection systems(VDS) and travel time collected from the toll collection system (TCS) between Seoul and Osan toll Plaza on the Seoul-Pusan Expressway. Two models, one for travel-time estimation and the other for travel-time Prediction were developed. Application cases of each model were divided into two cases, so-called, a single-region and a multiple-region. because of the different characteristics of travel behavior shown on each region. For the evaluation of the travel time estimation and Prediction models, two Parameters. i.e. mode and mean were compared using five-minute interval data sets. The test results show that mode was superior to mean in representing the relationship between speed and travel time. It is, however shown that mean value gives better results in case of insufficient data. It should be noted that the estimation and the Prediction of travel times based on the VDS data have been improved by using neural networks, because the waiting time at exit toll gates can be included for the estimation of travel time based on the VDS data by considering differences between VDS and TCS travel time Patterns in the models. In conclusion, the results show that the developed models decrease estimation and prediction errors. As a result of comparing the developed model with the existing model using the observed data, the equality coefficients of the developed model was average 88% and the existing model was average 68%. Thus, the developed model was improved minimum 17% and maximum 23% rather then existing model .

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.276-284
• /
• 2020

This paper proposes a new convolutional neural network (CNN) based spectrum sensing technique for cognitive radio communications. The proposed technique determines the existence of the primary user (PU) by using energy detection without any prior knowledge of the PU's signal. In the proposed method, the received signal is high-rate sampled to sense the entire spectrum bands of interest. After that, fast Fourier transform (FFT) of the signal converts the time domain signal to frequency domain spectrum and by stacking those consecutive spectrums, a 2 dimensional signal is made. The 2 dimensional signal is cut by the sensing channel bandwidth and inputted to the CNN. The CNN determines the existence of the primary user. Since there are only two states (existence or non-existence), binary classification CNN is used. The performance of the proposed method is examined through computer simulation and indoor experiment. According to the results, the proposed method outperforms the conventional threshold-based method by over 2 dB.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.10
• /
• pp.3195-3200
• /
• 2000

this paper is a stucy onthe preductionof multi-media traffic flow for the realizationof optimum ATM congestion control. In ATM network it is expected that the characteristic of multi-media traffic flow is varied slowly with a time. Fjor the simulation, time-variable multi-media traffic is penerated using possion distribution(connect calls per process time).\, gamma distribution(transmission rate per a call) and exponential distribution(holding time per a call). And using back-propagation neural netwok and proposed tripple neural network, the simulation to predict generaed traffic is executed. From the result,it's capability is shown that the proposed neural network model can be used in the predictionof ATM traffic flow.

• Journal of the Korean Institute of Gas
• /
• v.7 no.3 s.20
• /
• pp.24-31
• /
• 2003

To operate process plant safely and economically, process monitoring is very important. There are a great number of data acquired through distributed control system and process information system. Fault monitoring is the task with difficulties owing to not only the huge amount of data, but also nonlinearity of chemical processes. In this research, the program, REFA, based on PCA and functional link associative neural network has developed. REFA has better learning capabilities, generalization abilities, and shorter learning time than existing neural network programs. In this work its usefulness has proven by application to Tennessee Eastman process.

• Journal of Korea Multimedia Society
• /
• v.12 no.2
• /
• pp.272-280
• /
• 2009

The recent mobile industry is providing of a lot of image on/off-line contents are being converted into the mobile contents for architectural design. However, it is difficult to provide users with the existing on/off-line contents without any considerations due to the small size of the mobile screen. In existing methods to overcome the problem, the comic contents on mobile devices are manually produced by computer software such as Photoshop. In this paper, I describe the Automatic Comics Conversion(ACC) system that provides the variedly form of offline comic contents into mobile device of the small screen using Multi-Layer Perceptorn(MLP). ACC produces an experience together with the comic contents fitting for the small screen, which introduces a clustering method that is useful for variety types of comic images and characters as a prerequisite as a stage for preserving semantic meaning. An application is to use the frame form of pictures, website and images in order into mobile device the availability and can bounce back the freeze images contents into dynamic images content.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.3
• /
• pp.117-127
• /
• 1995

In this paper, we suggest a motion analysis method using ART-I1 competitive learning neural network and fuzzy reasoning by matching the same objects through the consecutive image sequence. we use the size and mean intensity of the region obtained from image segmentation for the region matching by the region and use a ART-I1 competitive learning neural network wh~ch has a learning ability to reflect the topology of the input patterns in order to select characteristic points to describe the shape of a region. Motion vectors for each regions are obtained by matching selected characteristic points. However, the two dimensional image, the projection of the the three dimensional real world, produces fuzziness in motion analysis due to its incompleteness by nature and the error from image segmentation used for extracting information about objects. Therefore, the belief degrees for each regions are calculated using fuzzy reasoning to l-nanipulate uncertainty in motion estimation.

• Smart Media Journal
• /
• v.9 no.2
• /
• pp.9-15
• /
• 2020

In this paper, we propose a network model composed of Multi path Encoder-Decoder branches that can recognize each instance from the image. The network has two branches, Dot branch and Segmentation branch for finding the center point of each instance and for recognizing area of the instance, respectively. In the experiment, the CVPPP dataset was studied to distinguish leaves from each other, and the center point detection branch(Dot branch) found the center points of each leaf, and the object segmentation branch(Segmentation branch) finally predicted the pixel area of each leaf corresponding to each center point. In the existing segmentation methods, there were problems of finding various sizes and positions of anchor boxes (N > 1k) for checking objects. Also, there were difficulties of estimating the number of undefined instances per image. In the proposed network, an effective method finding instances based on their center points is proposed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.7
• /
• pp.1243-1248
• /
• 2008

As development in technology of bioinformatics recently mates it possible to operate micro-level experiments, we can observe the expression pattern of total genome through on chip and analyze the interactions of thousands of genes at the same time. In this thesis, we used CDNA microarrays of 3840 genes obtained from neuronal differentiation experiment of cortical stem cells on white mouse with cancer. It analyzed and compared performance of each of the experiment result using existing DT, NB, SVM and multi-perceptron neural network classifier combined the similar scale combination method after constructing class classification model by extracting significant gene list with a similar scale combination method proposed in this paper through normalization. Result classifying in Multi-Perceptron neural network classifier for selected 200 genes using combination of PC(Pearson correlation coefficient) and ED(Euclidean distance coefficient) represented the accuracy of 98.84%, which show that it improve classification performance than case to experiment using other classifier.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.271-282
• /
• 2021

This study was conducted to develop a model for predicting the length of stay for premature infants through machine learning. For the development of this model, 6,149 cases of premature infants discharged from the hospital from 2011 to 2016 of the discharge injury in-depth survey data collected by the Korea Centers for Disease Control and Prevention were used. The neural network model of the initial hospitalization was superior to other models with an explanatory power (R²) of 0.75. In the model added by converting the clinical diagnosis to CCS(Clinical class ification software), the explanatory power (R²) of the cubist model was 0.81, which was superior to the random forest, gradient boost, neural network, and penalty regression models. In this study, using national data, a model for predicting the length of stay for premature infants was presented through machine learning and its applicability was confirmed. However, due to the lack of clinical information and parental information, additional research is needed to improve future performance.