• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1140-1146
• /
• 2018

Recently, a methodology for analyzing complex bio-signals using a deep learning model has emerged among studies that recognize human emotions. At this time, the accuracy of emotion classification may be changed depending on the evaluation method and reliability depending on the kind of data to be learned. In the case of biological signals, the reliability of data is determined according to the noise ratio, so that the noise detection method is as important as that. Also, according to the methodology for defining emotions, appropriate emotional evaluation methods will be needed. In this paper, we propose a wavelet -based noise threshold setting algorithm for verifying the reliability of data for multimodal bio-signal data labeled Valence and Arousal and a method for improving the emotion recognition rate by weighting the evaluation data. After extracting the wavelet component of the signal using the wavelet transform, the distortion and kurtosis of the component are obtained, the noise is detected at the threshold calculated by the hampel identifier, and the training data is selected considering the noise ratio of the original signal. In addition, weighting is applied to the overall evaluation of the emotion recognition rate using the euclidean distance from the median value of the Valence-Arousal plane when classifying emotional data. To verify the proposed algorithm, we use ASCERTAIN data set to observe the degree of emotion recognition rate improvement.

• Korean Journal of Remote Sensing
• /
• v.32 no.5
• /
• pp.471-482
• /
• 2016

This paper presents an extraction method for water body which uses block-based image partitioning and extension of water body boundaries to improve the performance of supervised classification for water body extraction. The Mahalanobis distance image is created by computing the spectral information of Normalized Difference Water Index (NDWI) and Near Infrared (NIR) band images over a training site within the water body in order to extract an initial water body area. To reduce the effect of noise contained in the Mahalanobis distance image, we apply mean curvature diffusion to the image, which controls diffusion coefficients based on connectivity strength between adjacent pixels and then extract the initial water body area. After partitioning the extracted water body image into the non-overlapping blocks of same size, we update the water body area using the information of water body belonging to water body boundaries. The update is performed repeatedly under the condition that the statistical distance between water body area belonging to water body boundaries and the training site is not greater than a threshold value. The accuracy assessment of the proposed algorithm was tested using KOMPSAT-2 images for the various block sizes between $11{\times}11$ and $19{\times}19$. The overall accuracy and Kappa coefficient of the algorithm varied from 99.47% to 99.53% and from 95.07% to 95.80%, respectively.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.463-470
• /
• 2006

It is difficult to track and extract the movement of an object through a camera exactly because of noises and changes of the light. The fast searching algorithm is necessary to extract the object and to track the movement for realtime image. In this paper, we propose the correct and fast algorithm using the variable searching area and the background image change method to robustic for the change of background image. In case the threshold value is smaller than reference value on an experimental basis, change the background image. When it is bigger, we decide it is the point of the time of the object input and then extract boundary point of it through the pixel check. The extracted boundary points detect precise movement of the object by creating area block of it and searching block that maintaining distance. The designed and embodied system shows more than 95% accuracy in the experimental results.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.2
• /
• pp.1-7
• /
• 2020

In modern society, as technology has advanced and human life area has expanded, there has been an increasing demand for high-quality voice and video communications services without restrictions on time and place. In response to this demand, satellite communications systems that provide a wide range of communications and that offer multiple access are evolving day by day. In satellite communications systems such as Digital Video Broadcasting - Return Channel Via Satellite (DVB-RCS) and Warfighter Information Network-Tactical (WIN-T), the multi-frequency time division multiple access (MF-TDMA) demand assigned multiple access (DAMA) scheme is used for efficient resource allocation. In this scheme, since the satellite terminals periodically request resources from the network controller, and the network controller dynamically allocates resources, it is necessary to arrange resource allocation information from time to time. Shortening of the alignment time is a more important factor in a satellite communications system in which a long transmission delay occurs due to long-distance transmission and reception. In this paper, we propose a sorting algorithm variable-selection scheme that shortens the sorting time by cross-selecting the sorting algorithm based on a threshold value, while setting the number of frames in the MF-TDMA DAMA satellite communications system as the threshold value.

• Journal of KIISE:Software and Applications
• /
• v.31 no.3
• /
• pp.379-386
• /
• 2004

Video segmentation is a fundamental task in video indexing and it includes two kinds of shot change detections such as the abrupt transition and the gradual transition. The abrupt shot boundaries are detected by computing the image-based distance between adjacent frames and comparing this distance with a pre-determined threshold value. However, the gradual shot boundaries are difficult to detect with this approach. To overcome this difficulty, we propose the method that detects gradual transition in the MPEG compressed video using the HMM (Hidden Markov Model). We take two different HMMs such as a discrete HMM and a continuous HMM with a Gaussian mixture model. As image features for HMM's observations, we use two distinct features such as the difference of histogram of DC images between two adjacent frames and the difference of each individual macroblock's deviations at the corresponding macroblock's between two adjacent frames, where deviation means an arithmetic difference of each macroblock's DC value from the mean of DC values in the given frame. Furthermore, we obtain the DC sequences of P and B frame by the first order approximation for a fast and effective computation. Experiment results show that we obtain the best detection and classification performance of gradual transitions when a continuous HMM with one Gaussian model is taken and two image features are used together.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.2
• /
• pp.69-76
• /
• 2010

This paper proposed a new fast multi-reference frame motion estimation algorithm. The proposed algorithm reduces search areas of motion estimation using a linear relation of motion vector with distance of each reference frame. New algorithm executes full search area motion estimation in reference frame 0 and reference frame 1. After that, search areas in reference frame 2, reference frame 3 and reference frame 4 are minimized by distance of each reference frame and results of motion estimation in reference frame 0 and reference frame 1. The proposed algorithm does not use a threshold value which is obstacle of hardware implementation and processing time schedule. Also, it reduced computation quantity of multi-reference motion estimation. Hardware implementation of multi-reference frame motion estimation is possible by these features. Simulation results show that PSNR drop and bitrate increase of proposed algorithm are lower than those of previous fast multi-reference frame motion estimation algorithm The number of computation of new algorithm is reduced 52.5% and quality of result is negligible when compared with full search area motion estimation which has 5 reference frames.

• Journal of the East Asian Society of Dietary Life
• /
• v.9 no.2
• /
• pp.177-187
• /
• 1999

This study was designed to investigate the effects of sports drink including the extract from Prunus mume on the changes of oxygen uptake, minute ventilaton, heart rate, and blood lactate concentration during 1 hour treadmill running exercise corresponding to 75%VO$_2$max. Subjects were 16 male athletes(long distance runners and tennis players). The changing patterns of oxygen uptake and minute ventilation showed no significnat difference among all types of sports drink, but the minute vetilation of the placebo group showed a higher value than type I group during submaximal exercise. Although the changing patterns of heart rate and blood lactate concentration showed no significnat difference among all types of sports drink, but type E group showed a lower heart rate compared to Placebo group. And blood lactate concentration of placebo group showed a higher value compared to the value corresponding to lactate threshold during submaimal exercise. but the other types of sports drink showed a lower value of blood lactate concentration. Especially blood lactate threshold of type D and E groups showed a lower value (range from 1.44 to 2.00mM) during submaximal exercise. In these results, the sports drink including the extract from Prunus mume showed no significant effects to the changes of oxygen uptake, minute ventilaton, heart rate, and blood lactate concentration during 1 hour treadmill runnuing exercise corresponding to 75%VO$_2$max. But it could be suggested the positive effects of the intake of sports drink including the extract from Prunus mume on the inhibition of exercise-induced fatigue during submaximal exercise, because of the lower changing Patterns of heart rate, blood lactate concentration, and ventilation efficiency in this results.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.209-219
• /
• 2004

In order to implement a real time hardware for keyword spotting, we propose a Single-End-Point DTW(SEP-DTW) algorithm which is simple and less complex for computation. The SEP-DTW algorithm only needs a single end point which enables efficient applications, and it has a small wont of computations because the global search area is divided into successive local search areas. Also, we adopt new local constraints and a new distance measure for a better performance of the SEP-DTW algorithm. Besides, we make a normalization of feature same vectors so that they have the same variance in each frequency bin, and each frame has the same energy levels. To construct several reference patterns for each keyword, we use a clustering algorithm for all training patterns, and mean vectors in every cluster are taken as reference patterns. In order to detect a key word for input streams of speech, we measure the distances between reference patterns and input pattern, and we make a decision whether the distances are smaller than a pre-defined threshold value. With isolated speech recognition and keyword spotting experiments, we verify that the proposed algorithm has a better performance than other methods.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.36 no.4
• /
• pp.95-102
• /
• 1994

The series of the papers consist of three parts to describe the development, calibration, and applications of the flood forecasting models for the Youngsan Estuarine Dam located at the mouth of the Youngsan river. And this paper discusses the hydrologic model for inflow simulation at Naju station, which constitutes 64 percent of the drainage basin of 3521 .6km$^2$ in area. A simplified TANK model was formulated to simulate hourly runoff from rainfall And the model parameters were optirnized using historical storm data, and validated with the records. The results of this paper were summarized as follows. 1. The simplified TANK model was formulated to conceptualize the hourly rainfall-run-off relationships at a watershed with four tanks in series having five runoff outlets. The runoff from each outlet was assumed to be proportional to the storage exceeding a threshold value. And each tank was linked with a drainage hole from the upper one. 2. Fifteen storm events from four year records from 1984 to 1987 were selected for this study. They varied from 81 to 289rn'm The watershed averaged, hourly rainfall data were determined from those at fifteen raingaging stations using a Thiessen method. Some missing and unrealistic records at a few stations were estimated or replaced with the values determined using a reciprocal distance square method from abjacent ones. 3. An univariate scheme was adopted to calibrate the model parameters using historical records. Some of the calibrated parameters were statistically related to antecedent precipitation. And the model simulated the streamflow close to the observed, with the mean coefficient of determination of 0.94 for all storm events. 4. The simulated streamflow were in good agreement with the historical records for ungaged condition simulation runs. The mean coefficient of determination for the runs was 0.93, nearly the same as calibration runs. This may indicates that the model performs very well in flood forecasting situations for the watershed.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.7 no.4
• /
• pp.163-172
• /
• 2012

A driver assistance system is critical to improve a convenience and stability of vehicle driving. Several systems have been already commercialized such as adaptive cruise control system and forward collision warning system. Efficient vehicle detection is very important to improve such driver assistance systems. Most existing vehicle detection systems are based on a radar system, which measures distance between a host and leading (or oncoming) vehicles under various weather conditions. However, it requires high deployment cost and complexity overload when there are many vehicles. A camera based vehicle detection technique is also good alternative method because of low cost and simple implementation. In general, night time vehicle detection is more complicated than day time vehicle detection, because it is much more difficult to distinguish the vehicle's features such as outline and color under the dim environment. This paper proposes a method to detect vehicles at night time using analysis of a captured color space with reduction of reflection and other light sources in images. Four colors spaces, namely RGB, YCbCr, normalized RGB and Ruta-RGB, are compared each other and evaluated. A suboptimal threshold value is determined by Otsu algorithm and applied to extract candidates of taillights of leading vehicles. Statistical features such as mean, variance, skewness, kurtosis, and entropy are extracted from the candidate regions and used as feature vector for SVM(Support Vector Machine) classifier. According to our simulation results, the proposed statistical feature based SVM provides relatively high performances of leading vehicle detection with various distances in variable nighttime environments.