• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.50-56
• /
• 2020

With the rapid development of deep neural network theory and application research, the effect of face detection has been improved. However, due to the complexity of deep neural network calculation and the high complexity of the detection environment, how to detect face quickly and accurately becomes the main problem. This paper is based on the relatively simple model of the MTCNN model, using FDDB (Face Detection Dataset and Benchmark Homepage), LFW (Field Label Face) and FaceScrub public datasets as training samples. At the same time of sorting out and introducing MTCNN(Multi-Task Cascaded Convolutional Neural Network) model, it explores how to improve training speed and Increase performance at the same time. In this paper, the dynamic image pyramid technology is used to replace the traditional image pyramid technology to segment samples, and OHEM (the online hard example mine) function in MTCNN model is deleted in training, so as to improve the training speed.

• Journal of Information Science Theory and Practice
• /
• v.10 no.spc
• /
• pp.143-153
• /
• 2022

With the development of networks and the increase in the number of network devices, the number of cyber attacks targeting them is also increasing. Since these cyber-attacks aim to steal important information and destroy systems, it is necessary to minimize social and economic damage through early detection and rapid response. Many studies using machine learning (ML) and artificial intelligence (AI) have been conducted, among which payload learning is one of the most intuitive and effective methods to detect malicious behavior. In this study, we propose a preprocessing method to maximize the performance of the model when learning the payload in term units. The proposed method constructs a high-quality learning data set by eliminating unnecessary noise (stopwords) and preserving important features in consideration of the machine language and natural language characteristics of the packet payload. Our method consists of three steps: Preserving significant special characters, Generating a stopword list, and Class label refinement. By processing packets of various and complex structures based on these three processes, it is possible to make high-quality training data that can be helpful to build high-performance ML/AI models for security monitoring. We prove the effectiveness of the proposed method by comparing the performance of the AI model to which the proposed method is applied and not. Forthermore, by evaluating the performance of the AI model applied proposed method in the real-world Security Operating Center (SOC) environment with live network traffic, we demonstrate the applicability of the our method to the real environment.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.175-186
• /
• 1999

Detecting the features of significant patterns from their own historical data is so much crucial to good performance specially in time-series forecasting. Recently, a new data filtering method (or multi-scale decomposition) such as wavelet analysis is considered more useful for handling the time-series that contain strong quasi-cyclical components than other methods. The reason is that wavelet analysis theoretically makes much better local information according to different time intervals from the filtered data. Wavelets can process information effectively at different scales. This implies inherent support fer multiresolution analysis, which correlates with time series that exhibit self-similar behavior across different time scales. The specific local properties of wavelets can for example be particularly useful to describe signals with sharp spiky, discontinuous or fractal structure in financial markets based on chaos theory and also allows the removal of noise-dependent high frequencies, while conserving the signal bearing high frequency terms of the signal. To date, the existing studies related to wavelet analysis are increasingly being applied to many different fields. In this study, we focus on several wavelet thresholding criteria or techniques to support multi-signal decomposition methods for financial time series forecasting and apply to forecast Korean Won / U.S. Dollar currency market as a case study. One of the most important problems that has to be solved with the application of the filtering is the correct choice of the filter types and the filter parameters. If the threshold is too small or too large then the wavelet shrinkage estimator will tend to overfit or underfit the data. It is often selected arbitrarily or by adopting a certain theoretical or statistical criteria. Recently, new and versatile techniques have been introduced related to that problem. Our study is to analyze thresholding or filtering methods based on wavelet analysis that use multi-signal decomposition algorithms within the neural network architectures specially in complex financial markets. Secondly, through the comparison with different filtering techniques' results we introduce the present different filtering criteria of wavelet analysis to support the neural network learning optimization and analyze the critical issues related to the optimal filter design problems in wavelet analysis. That is, those issues include finding the optimal filter parameter to extract significant input features for the forecasting model. Finally, from existing theory or experimental viewpoint concerning the criteria of wavelets thresholding parameters we propose the design of the optimal wavelet for representing a given signal useful in forecasting models, specially a well known neural network models.

• Korean Institute of Interior Design Journal
• /
• v.19 no.6
• /
• pp.100-111
• /
• 2010

'Pattern' is the term that is frequently used in the aspects of history, society, and science. It always appears in the remains or relics of the age of civilization when recording was started, and its evaluation and value differ by time. Patterns in the ancient civilization were symbolic, social, and spatially crucial. However, after the modernization, they were considered to be immoral and unnecessary, so the range of their significance came to reduce. Due to the development of science, ornament patterns lost the limitation of its range of use along with new interpretation of them. Especially with the advent of new scientific theories such as the evolution theory from the biological aspect, quantum mechanics, and super string theory, morphological possibilities more than the human scale perceived by men came to be discovered. Living organisms maintain their lives through patterns, structures, and processes in order to produce a system alive. Among them, patterns are the organization of relations determining the characteristics of the system. The present patterns may correspond to this meaning. The pattern in a space is the matter of how to relate the components after all. In a space, however, there are numerous components mingled with one another. If these tasks are conducted as analogue work, it will take a lot of time and effort. However, if digital media are utilized to perform the tasks like analysis, generation, or fabrication, it will produce a result with higher precision and efficiency. In this sense, parametric modeling is quite useful media. Opening morphological variation, it realizes more possibilities, connects conveniently the relations between complex components composing a space, and helps produce creative patterns.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.4
• /
• pp.41-55
• /
• 1995

In this paper, an optimal idenfication method using fuzzy-neural networks is proposed for modeling of nonlinear complex systems. The proposed fuzzy-neural modeling implements system structure and parameter identification using the intelligent schemes together wlth optimization theory, linguistic fuzzy implication rules, and neural networks(NNs) from input and output data of processes. Inference type for this fuzzy-neural modeling is presented as simplified inference. To obtain optimal model, the learning rates and momentum coefficients of fuzzy-neural networks(FNNs) are tuned automatically using improved modified complex method and modified learning algorithm. For the purpose of its application to nonlinear processes, data for route choice of traffic problems and those for activateti sluge process of sewage treatment system are used for the purpose of evaluating the performance of the proposed fuzzy-neural network modeling. The results show that the proposed method can produce the intelligence model with higher accuracy than other works achieved previously.

• Smart Structures and Systems
• /
• v.15 no.4
• /
• pp.1139-1158
• /
• 2015

This paper proposes an efficient system identification method for modeling nonlinear behavior of civil structures. This method is developed by integrating three different methodologies: principal component analysis (PCA), artificial neural networks, and fuzzy logic theory, hence named PANFIS (PCA-based adaptive neuro-fuzzy inference system). To evaluate this model, a 3-story building equipped with a magnetorheological (MR) damper subjected to a variety of earthquakes is investigated. To train the input-output function of the PANFIS model, an artificial earthquake is generated that contains a variety of characteristics of recorded earthquakes. The trained model is also validated using the1940 El-Centro, Kobe, Northridge, and Hachinohe earthquakes. The adaptive neuro-fuzzy inference system (ANFIS) is used as a baseline. It is demonstrated from the training and validation processes that the proposed PANFIS model is effective in modeling complex behavior of the smart building. It is also shown that the proposed PANFIS produces similar performance with the benchmark ANFIS model with significant reduction of computational loads.

• Journal of Communications and Networks
• /
• v.7 no.4
• /
• pp.438-449
• /
• 2005

In this paper, we describes the information-theoretic approaches to sensor selection and sensor placement in sensor net­works for target localization and tracking. We have developed a sensor selection heuristic to activate the most informative candidate sensor for collaborative target localization and tracking. The fusion of the observation by the selected sensor with the prior target location distribution yields nearly the greatest reduction of the entropy of the expected posterior target location distribution. Our sensor selection heuristic is computationally less complex and thus more suitable to sensor networks with moderate computing power than the mutual information sensor selection criteria. We have also developed a method to compute the posterior target location distribution with the minimum entropy that could be achieved by the fusion of observations of the sensor network with a given deployment geometry. We have found that the covariance matrix of the posterior target location distribution with the minimum entropy is consistent with the Cramer-Rao lower bound (CRB) of the target location estimate. Using the minimum entropy of the posterior target location distribution, we have characterized the effect of the sensor placement geometry on the localization accuracy.

• KIEE International Transactions on Power Engineering
• /
• v.5A no.1
• /
• pp.79-84
• /
• 2005

In many countries, the electric power industry is undergoing significant changes known as deregulation and restructuring. These alterations introduce competition in generation and retail and require open access to the transmission network. The competition of the electric power industry causes many issues to surface. Among them, unbundling of the transmission service is probably the most complicated as it is a single and integrated sector and the transmission revenue requirement must be allocated to market participants in a fair way. In these situations, it is valuable to research the methodologies to allocate transmission usage. The power tracing method offers useful information such as which generators supply a particular load or how much each generator (load) uses a particular transmission line. With this information, we can allocate required transmission revenue to market participants. Recently, several algorithms were proposed for tracing power flow but there is no dominant power tracing method. This paper proposes a power tracing method based on graph theory and complex-current distribution. For practicability, the proposed method for transmission usage allocation is applied to IEEE 30 buses and compared with the method proposed by Felix F.Wu.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.253-259
• /
• 2019

The wedding seating problem(WSP) is to finding a minimum loss of guest relations(sit together preference) with restricted seats of a table for complex guest relation network. The WSP is NP-hard because of the algorithm that can be find the optimal solution within polynomial-time is unknown yet. Therefore we can't solve the WSP not computer-assisted programming but by hand. This paper suggests min-cut rule theory that the two guests with maximum preference can't separate in other two tables because this is not obtains minimum loss of preference. As a result of various experimental, this algorithm obtains proper seating chart meet to the seats of a table constraints.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.5
• /
• pp.2286-2309
• /
• 2016

Overlay networks have been widely deployed upon the Internet by Service Providers (SPs) to provide improved network services. However, the interaction between each overlay and traffic engineering (TE) as well as the interaction among co-existing overlays may occur. In this paper, we adopt both non-cooperative and cooperative game theory to analyze these interactions, which are collectively called hybrid interaction. Firstly, we model a situation of the hybrid interaction as an n+1-player non-cooperative game, in which overlays and TE are of equal status, and prove the existence of Nash equilibrium (NE) for this game. Secondly, we model another situation of the hybrid interaction as a 1-leader-n-follower Stackelberg-Nash game, in which TE is the leader and co-existing overlays are followers, and prove that the cost at Stackelberg-Nash equilibrium (SNE) is at least as good as that at NE for TE. Thirdly, we propose a cooperative coalition mechanism based on Shapley value to overcome the inherent inefficiency of NE and SNE, in which players can improve their performance and form stable coalitions. Finally, we apply distinct genetic algorithms (GA) to calculate the values for NE, SNE and the assigned cost for each player in each coalition, respectively. Analytical results are confirmed by the simulation on complex network topologies.