• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.2
• /
• pp.343-348
• /
• 2001

In this paper we propose a noise reduction algorithm which based on cellular automata with the local median rule. It is supposed that there is no information about the features of the image that must be improved. The proposed method behavior is to locally increase or decrease the gray level differences of the image without loss of the main characteristics of the image. The dynamical behavior of these automata is completely determined by Lyapunov operators for sequential and parallel update. We have found that the automata present very fast convergence to fixed points, stability in front of random noisy images. Based on the experimental results we discuss the advantage and efficiency.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.3
• /
• pp.493-499
• /
• 2008

Cellular Automata(CA) has been used as modeling and computing paradigm for a long time. And CA has been used to model many physical systems. While studying the models of such systems, it is seen that as the complexity of the physical system increase, the CA based model becomes very complex and becomes to difficult to track analytically. Also such models fail to recognize the presence of inherent hierarchical nature of a physical system. In this paper we give the characterization of Hierarchical Cellular Automata(HCA). Especially we analyze transition rules, characteristic polynomials and cyclic structures of HCA.

• Geophysics and Geophysical Exploration
• /
• v.1 no.1
• /
• pp.64-70
• /
• 1998

Diffraction tomography (DT) is a quantitative technique for high resolution subsurface imaging. In general DT algorithm is used for crosswell imaging. In this study high resolution GPR DT algorithm which is able to reconstruct high resolution image of subsurface structures in multi-monostatic geometry is developed. Developed algorithm is applied to finite difference data and its criteria of application and its limit are studied. Inversion parameters (number of imaging frequency, regularization factor, frequency range) are deduced from isolated weak scattering model. And the usuability of the algorithm is proved by applying to models which break the weak scattering approximation.

• Journal of KIISE:Software and Applications
• /
• v.37 no.9
• /
• pp.712-721
• /
• 2010

This paper proposes a new fire-flame detection method using probabilistic membership function of visual features and Fuzzy Finite Automata (FFA). First, moving regions are detected by analyzing the background subtraction and candidate flame regions then identified by applying flame color models. Since flame regions generally have continuous and an irregular pattern continuously, membership functions of variance of intensity, wavelet energy and motion orientation are generated and applied to FFA. Since FFA combines the capabilities of automata with fuzzy logic, it not only provides a systemic approach to handle uncertainty in computational systems, but also can handle continuous spaces. The proposed algorithm is successfully applied to various fire videos and shows a better detection performance when compared with other methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.5 s.305
• /
• pp.103-114
• /
• 2005

This paper presents a content-based image retrieval (CBIR) method using the combination of color and texture features. As a color feature, a color autocorrelogram is chosen which is extracted from the hue and saturation components of a color image. As a texture feature, BDIP(block difference of inverse probabilities) and BVLC(block variation of local correlation coefficients) are chosen which are extracted from the value component. When the features are extracted, the color autocorrelogram and the BVLC are simplified in consideration of their calculation complexity. After the feature extraction, vector components of these features are efficiently quantized in consideration of their storage space. Experiments for Corel and VisTex DBs show that the proposed retrieval method yields 9.5% maximum precision gain over the method using only the color autucorrelogram and 4.0% over the BDIP-BVLC. Also, the proposed method yields 12.6%, 14.6%, and 27.9% maximum precision gains over the methods using wavelet moments, CSD, and color histogram, respectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.1108-1111
• /
• 2009

Auto Pilot is the system which move automatically the vessel through locating operation mode to automatic after entering operating course using a electronic chart or plotter. And water jet is the a propulsion system that make a power to push the vessel through spouting the accelerated water which is absorbed by the hole in the bottom of vessel. The water jet receive the effect of the depth of water lowly, it's acceleration efficiency is higher under high speed and have an advantage on vibrating and floating sound, so it's demand is increasing as new propulsion system. However, the signal systems of auto pilot and water jet are different, we need the system to interface between each system. We designed the interface that efficiently digital feed back control embedded module between auto pilot and water jet system in this paper.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.127-140
• /
• 2021

Recently, sequence data containing time information, such as sensor measurement data and purchase history, has been generated in various applications. So far, many methods for finding sequences that are significantly different from other sequences among given sequences have been proposed. However, most of them have a limitation that they consider only the order of elements in the sequences. Therefore, in this paper, we propose a new anomalous sequence detection method that considers both the order of elements and the time interval between elements. The proposed method uses an extended LSTM autoencoder model, which has an additional layer that converts a sequence into a form that can help effectively learn both the order of elements and the time interval between elements. The proposed method learns the features of the given sequences with the extended LSTM autoencoder model, and then detects sequences that the model does not reconstruct well as anomalous sequences. Using experiments on synthetic data that contains both normal and anomalous sequences, we show that the proposed method achieves an accuracy close to 100% compared to the method that uses only the traditional LSTM autoencoder.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.4
• /
• pp.105-112
• /
• 2022

Recently, many studies using reinforcement learning-based autoscaling have been performed to make autoscaling policies that are adaptive to changes in the environment and meet specific purposes. However, training the reinforcement learning-based Horizontal Pod Autoscaler(HPA) policy in a real environment requires a lot of money and time. And it is not practical to retrain the reinforcement learning-based HPA policy from scratch every time in a real environment. In this paper, we implement a reinforcement learning-based HPA in Kubernetes, and propose a transfer leanring technique using a queuing model-based simulation to accelerate the training of a reinforcement learning-based HPA policy. Pre-training using simulation enabled training the policy through simulation experience without consuming time and resources in the real environment, and by using the transfer learning technique, the cost was reduced by about 42.6% compared to the case without transfer learning technique.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.4
• /
• pp.687-697
• /
• 2023

Botnets, whose attack patterns are becoming more sophisticated and diverse, are recognized as one of the most serious cybersecurity threats today. This paper revisits the experimental results of botnet detection using autoencoder, a semi-supervised deep learning model, for UGR and CTU-13 data sets. To prepare the input vectors of autoencoder, we create data points by grouping the NetFlow records into sliding windows based on source IP address and aggregating them to form features. In particular, we discover a simple power-law; that is the number of data points that have some flow-degree is proportional to the number of NetFlow records aggregated in them. Moreover, we show that our power-law fits the real data very well resulting in correlation coefficients of 97% or higher. We also show that this power-law has an impact on the learning of autoencoder and, as a result, influences the performance of botnet detection. Furthermore, we evaluate the performance of autoencoder using the area under the Receiver Operating Characteristic (ROC) curve.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.500-510
• /
• 2023

Passive sonar signals mainly contain both normal and abnormal signals. The abnormal signals mixed with normal signals are primarily detected using an AutoEncoder (AE) that learns only normal signals. However, existing AEs may perform inaccurate detection by reconstructing distorted normal signals from mixed signal. To address these limitations, we propose an abnormal signal detection model based on a Recurrent Neural Network (RNN) and vector quantization. The proposed model generates a codebook representing the learned latent vectors and detects abnormal signals more accurately through the proposed search process of code vectors. In experiments using publicly available underwater acoustic data, the AE and Variational AutoEncoder (VAE) using the proposed method showed at least a 2.4 % improvement in the detection performance and at least a 9.2 % improvement in the extraction performance for abnormal signals than the existing models.