• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.713-722
• /
• 2013

This paper proposes a method of using depth information to detect the hand region in real-time based on the cascade method. In order to ensure stable and speedy detection of the hand region even under conditions of lighting changes in the test environment, this study uses only features based on depth information, and proposes a method of detecting the hand region by means of a classifier that uses boosting and cascading methods. First, in order to extract features using only depth information, we calculate the difference between the depth value at the center of the input image and the average of depth value within the segmented block, and to ensure that hand regions of all sizes will be detected, we use the central depth value and the second order linear model to predict the size of the hand region. The cascade method is applied to implement training and recognition by extracting features from the hand region. The classifier proposed in this paper maintains accuracy and enhances speed by composing each stage into a single weak classifier and obtaining the threshold value that satisfies the detection rate while exhibiting the lowest error rate to perform over-fitting training. The trained classifier is used to classify the hand region, and detects the final hand region in the final merger stage. Lastly, to verify performance, we perform quantitative and qualitative comparative analyses with various conventional AdaBoost algorithms to confirm the efficiency of the hand region detection algorithm proposed in this paper.

• Journal of Yeungnam Medical Science
• /
• v.18 no.1
• /
• pp.39-50
• /
• 2001

Background: Power spectrum analysis method is a powerful noninvasive tool for quantifying autonomic nervous system activity. In this paper, we developed a data acquistion system for estimating the activity of the autonomic nervous system by the analysis of heart rate and respiratory rate variability using power spectrum analysis. Materials and methods: For the detection of QRS peak and measurement of respiratory rate from patient's ECG, we used low-pass filter and impedence method respectively. This system adopt an isolated power for patient's safety. In this system, two output signals can be obtained: R-R interval heart rate) and respiration rate time series. Experimental ranges are 30-240 BPM for ECG and 15-80 BPM for respiration. Results: The system can acquire two signals accurately both in the experimental test using simulator and in real clinical setting. Conclusion: The system developed in this paper is efficient for the acquisition of heart rate and respiration signals. This system will play a role in research area for improving our understanding of the pathophysiologic involvement of the autonomic nervous system in various disease states.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.37-41
• /
• 2021

This paper presents a study to implement a touch screen capable of real-time response processing in a low-end embedded system. This was done by introducing an algorithm using an interpolation method to represent real-time response characteristics when a touch input is performed. In this experiment, we applied a linear interpolation algorithm that estimates random data by deriving a first-order polynomial from 2-point data. We also applied a Lagrange interpolation algorithm that estimates random data by deriving a quadratic polynomial from 3-point data. As a result of the experiment, it was found that the Lagrange interpolation method was more complicated than the linear interpolation method, and the processing speed was slow, so the text was not smooth. When using the linear interpolation method, it was confirmed that the speed displayed on a screen is 2.4 times faster than when using the Lagrange interpolation method. For real-time response characteristics, it was confirmed that smaller size of the executable file of the algorithm is more advantageous than the superiority of the algorithm itself. In conclusion, in order to secure real-time response characteristics in a low-end embedded system, it was confirmed that a relatively simple linear interpolation algorithm performs touch operations with better real-time response characteristics than the Lagrange interpolation method.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1214-1217
• /
• 2018

In this paper, we propose the development of a Small $360^{\circ}$ Oral Scanner embedded board. The proposed small $360^{\circ}$ oral scanner embedded board consists of image level and transfer method changing part FPGA part, memory part and FIFO to USB transfer part. The image level and transmission mode change unit divides the MIPI format oral image received through the small $360^{\circ}$ oral cavity image sensor and the image sensor into low power signal mode and high speed signal mode and distributes them to the port and transfers the level shift to the FPGA unit. The FPGA unit performs functions such as $360^{\circ}$ image distortion correction, image correction, image processing, and image compression. In the FIFO to USB transfer section, the RAW data transferred through the FIFO in the FPGA is transferred to the PC using USB 3.0, USB 3.1, etc. using the transceiver chip. In order to evaluate the efficiency of the proposed small $360^{\circ}$ oral scanner embedded board, it has been tested by an authorized testing institute. As a result, the frame rate per second is over 60 fps and the data transfer rate is 4.99 Gb/second

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.193-204
• /
• 2019

The explosion of data due to the improvement of sensor technology and computing performance has become the basis for analyzing the situation in the industrial fields, and various attempts to detect events based on such data are increasing recently. In particular, sound signals collected from sensors are used as important information to classify events in various application fields as an advantage of efficiently collecting field information at a relatively low cost. However, the performance of sound-event classification in the field cannot be guaranteed if noise can not be removed. That is, in order to implement a system that can be practically applied, robust performance should be guaranteed even in various noise conditions. In this study, we propose a system that can classify the sound event after generating the enhanced sound signal based on the deep learning algorithm. Especially, to remove noise from the sound signal itself, the enhanced sound data against the noise is generated using SEGAN applied to the GAN with a VAE technique. Then, an end-to-end based sound-event classification system is designed to classify the sound events using the enhanced sound signal as input data of CNN structure without a data conversion process. The performance of the proposed method was verified experimentally using sound data obtained from the industrial field, and the f1 score of 99.29% (railway industry) and 97.80% (livestock industry) was confirmed.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.6
• /
• pp.25-32
• /
• 2020

The seed, the most basic component, is an important factor in increasing production and efficiency in agriculture. Seeds with superior genes can be expected to improve agricultural productivity, crop survival, and reproduction. Currently, however, screening of superior seeds depends mostly on manual work, which requires a lot of time and manpower. In this paper, we propose a system that can extract the characteristics of seed phenotypes by using computer image processing technology, so that even a small number of people and a short period of time are needed to extract the characteristics of seeds. The proposed system detects individual seeds from images containing large quantities of seeds, and extracts and stores various characteristics such as representative colors, area, perimeter and roundness for each individual seed. Due to the regularity of input images, the accuracy of individual seed extraction in the proposed system is 99.12% for soybean seeds and 99.76% for rice seeds. The extracted data will be used as basic data for various data analyses that reflect the opinions of experts in the future, and will be used as basic data to determine the expressive nature of each seed.

• Journal of Korean Society of Disaster and Security
• /
• v.13 no.4
• /
• pp.75-92
• /
• 2020

In most cases of the water balance analysis, the return flow ratio for each water supply was uniformly determined and applied, so it has been contained a problem that the volume of available water would be incorrectly calculated. Therefore, sewage and wastewater among the return water were focused in this study and the data-driven model was developed to forecast the outflow from the sewage treatment plant. The forecasting results of LSTM (Long Short-Term Memory), GRU (Gated Recurrent Units), and SVR (Support Vector Regression) models, which are mainly used for forecasting the time series data in most fields, were compared with the observed data to determine the optimal model parameters for forecasting outflow. As a result of applying the model, the root mean square error (RMSE) of the GRU model was smaller than those of the LSTM and SVR models, and the Nash-Sutcliffe coefficient (NSE) was higher than those of others. Thus, it was judged that the GRU model could be the optimal model for forecasting the outflow in sewage treatment plants. However, the forecasting outflow tends to be underestimated and overestimated in extreme sections. Therefore, the additional data for extreme events and reducing the minimum time unit of input data were necessary to enhance the accuracy of forecasting. If the water use of the target site was reviewed and the additional parameters that could reflect seasonal effects were considered, more accurate outflow could be forecasted to be ready for climate variability in near future. And it is expected to use as fundamental resources for establishing a reasonable river water management system based on the forecasting results.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.579-586
• /
• 2021

Time series forecasting refers to predicting future time information based on past time information. Accurately predicting future information is crucial because it is used for establishing strategies or making policy decisions in various fields. Recently, a transformer model has been mainly studied for a time series prediction model. However, the existing transformer model has a limitation in that it has an auto-regressive structure in which the output result is input again when the prediction sequence is output. This limitation causes a problem in that accuracy is lowered when predicting a distant time point. This paper proposes a sequential decoding model focusing on the style transformation technique to handle these problems and make more precise time series forecasting. The proposed model has a structure in which the contents of past data are extracted from the transformer-encoder and reflected in the style-based decoder to generate the predictive sequence. Unlike the decoder structure of the conventional auto-regressive transformer, this structure has the advantage of being able to more accurately predict information from a distant view because the prediction sequence is output all at once. As a result of conducting a prediction experiment with various time series datasets with different data characteristics, it was shown that the model presented in this paper has better prediction accuracy than other existing time series prediction models.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.1
• /
• pp.35-42
• /
• 2022

Visible light communication (VLC) is a method of transmitting data through LED blinking and is vulnerable to eavesdropping because the illumination affects the wide range of area. IEEE standard 802.15.7 defines On-Off Keying (OOK), Variable Pulse Position Modulation (VPPM), and Color Shift Keying (CSK) as modulation. In this paper, we propose an encryption method in VPPM for secure communication. The VPPM uses an encoding method called 4B6B where 16 different outputs are represented with 6-bit. This paper extends the number of outputs to 20, to add complexity while not violating the 4B6B generation conditions. Then each entry in the extended 4B6B table is scrambled using vigenère cipher. The probability of decrypting each 6-bit data is $\frac{1}{20}$. Eavesdropper should perform $\sum\limits_{k=1}^{n}20^k$ number of different trials to decrypt the message if the number of keys is n. The proposed method can be applied to OOK of PHY II and CSK of PHY III. We further discuss the secure encoding that can be used in OOK and CSK without performance degradation.