• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10c
• /
• pp.466-468
• /
• 1999

현재 인터넷 프로토콜인 IPv4의 주소 부족 등의 문제를 해결하기 위해 차세대 인터넷 프로토콜 IPv6에 대한 연구가 활발히 진행되고 있다. 그러나 새로운 프로토콜 IPv6 상에서 기존의 다른 상위 프로토콜 및 응용이 어떠한 영향을 받게 될지는 의문이다. 한편, IPv6 상에서 새로운 프로토콜 및 응용을 개발할 때에 많은 시험이 요구된다. 이와 같은 이유로 인해 새로운 통신 프로토콜에 있어서 모니터링은 필수적이다. 그러나 지금까지의 많은 모니터링 라이브러리들은 텍스트에 기반하고 있으며, 그래픽 데이터를 제공하는 도구들도 대부분 통계정보의 제공에 초점을 두고 있다. 이를 두고 프로토콜이 그 표준에 따라 정확한 원리에 맞게 동작하는 지를 파악하는 데는 큰 도움이 되지 않고 있다. 이에 본 연구에서는 대상 프로토콜의 실제적인 동작 과정이나 원리를 알 수 있도록 그래픽 기반의 사용자 친화적 모니터링 도구를 제작한다. 이를 위해, 먼저 IPv6가 다른 프로토콜에 영향을 미칠 수 있는 사항들을 분석한다. 다음으로 본 교에 구축되어 있는 IPv6 호스트에 모니터링에 필요한 환경을 구축하고, Java Applet을 이용한 모니터 프로그램을 제작한다. 현재 개발하는 모니터 프로그램은 TCP의 슬라이딩 윈도우(Sliding Window) 기법에 관련된 사항을 모니터링 해주는 것으로 그 범위를 한정한다. 개발된 도구를 이용하여 IPv6 상에서 FTP가 TCP를 이용하여 파일을 전송하는 경우의 모니터링을 실시하고, 그 결과를 분석 제시한다. 이로써, 개발된사용자 친화적 모니터링 도구가 얼마나 쉽게 슬라이딩 윈도우 기법을 이해시켜 주고, 내포된 의미를 파악할 수 있게 해주는지를 알 수 있다.한 것으로 연구되었다. 정상조 직에 비해 산소가 부족하여 염기성대사(anaerobic metabolism)를 많이 함으로 그 부산물인 유산 (lactic acid)이 많이 생성됨으로 정상조직보다 pH가 낮아 암 조직이 정상조직에 비해 고온온열치료에 더 잘 듣는 원인이 된다. 3) 영양이 부족한 상태의 세포는 고온온열치료에 훨씬 예민하다. 4) 암조직은 혈관상태가 정상조직에 비해 좋지 않음으로 정상조직보다 쉽게 가온이 되며, 일단 가온된 온도는 잘 식지 않음으로 정상조직에 비해 훨씬 효율적이다. 5)고 온온열치료는 4$0^{\circ}C$~43.5 $^{\circ}C$정도에서만 이 작용이 일어남으로 정상인체에서 43$^{\circ}C$이상의 가온 은 쉽지 않음으로 이 효과는 암조직에서 주고 일어나게 된다. 6)고온온열치료는 방사선치료 후에 생기는 손상의 재생을 억제함으로 방사선의 치료효과를 높인다. 7)38.5$^{\circ}C$~41.5$^{\circ}C$의 낮 은 온도에서도 암조직의 산소 상태를 호전시켜 방사선 치료효과를 증대시키는 역할을 한다.alization)가 나타난다. 그러나 무의식에 대칭화만 있는 것은 아니며, 의식의 사고양식인 비대칭도 어느 정도 나타나며, 대칭화의 정도에 따라, 대상들이 잘 구분되어 있는 단계, 의식수준의 감정단계, 집단 내에서의 대칭화 단계, 집단간에서의 대칭화 단계, 구분이 없어지는 단계로 구분하였다.systems. We believe that this taxonomy is a significant contribution because it ad

• Journal of KIISE:Databases
• /
• v.34 no.5
• /
• pp.409-419
• /
• 2007

Database community focuses on the similar music retrieval systems for music database when a humming query is given. One of the approaches is converting the midi data to time series, building their indices and performing the similarity search on them. Queries based on humming can be transformed to time series by using the known pitch detection algorithms. The recently suggested algorithm, scaled and warped matching, is based on dynamic time warping and uniform scaling. This paper proposes Humming BIRD(Humming Based sImilaR mini music retrieval system) using sliding window and center-aligned scaled and warped matching. Center-aligned scaled and warped matching is a mixed distance measure of center-aligned uniform scaling and time warping. The newly proposed measure gives tighter lower bound than previous ones which results in reduced search space. The empirical results show the superiority of this algorithm comparing the pruning power while it returns the same results.

• Management & Information Systems Review
• /
• v.33 no.1
• /
• pp.45-63
• /
• 2014

A trading system is a computer trading program that automatically submits trades to an exchange. Mechanical a trading system to execute trade is spreading in the stock market. However, a trading system to trade a single asset might occur instability of the profit because payoff of this system is determined a asset movement. Therefore, it is necessary to develop a trading system that is trade two assets such as a pair trading that is to sell overvalued assets and buy the undervalued ones. The aim of this study is to propose a relative value based trading system designed to yield stable and profitable profits regardless of market conditions. In fact, we propose a procedure for building a trading system that is based on the rough set analysis of indicators derived from a price ratio between two assets. KOSPI 200 index futures and S&P 500 index futures are used as a data for evaluation of the proposed trading system. We intend to examine the usefulness of this model through an empirical study.

• Journal of Digital Contents Society
• /
• v.4 no.2
• /
• pp.211-221
• /
• 2003

The objective of this paper is performance analysis of the digital document image decimation algorithm which generates a value of decimated element by an average of a target pixel value and a value of neighbor intelligible element to adaptively reflect the merits of ZOD method and FOD method on the decimated image. First, a target pixel located at the center of sliding window is selected, then the gradient amplitudes of its right neighbor pixel and its lower neighbor pixel are calculated using first order derivative operator respectively. Secondly, each gradient amplitude is divided by the summation result of two gradient amplitudes to generate each local intelligible weight. Next, a value of neighbor intelligible element is obtained by adding a value of the right neighbor pixel times its local intelligible weight to a value of the lower neighbor pixel times its intelligible weight. The decimated image can be acquired by applying the process repetitively to all pixels in input image which generates the value of decimated element by calculating the average of the target pixel value and the value of neighbor intelligible element. In this paper, the performance comparison of proposed method and conventional methods in terms of subjective performance and hardware complexity is analyzed and the preferable approach for developing the decimation algorithm of the digital document image on the basis of this analysis result has been reviewed.

• Journal of KIISE:Databases
• /
• v.37 no.4
• /
• pp.177-184
• /
• 2010

In these day, many data including sensor, delivery, credit and stock data are generated continuously in massive quantity. It is difficult to learn from these data because they are large in volume and changing fast in their concepts. To handle these problems, learning methods based in sliding window methods over time have been used. But these approaches have a problem of rebuilding models every time new data arrive, which requires a lot of time and cost. Therefore we need very simple incremental learning methods. Bayesian method is an example of these methods but it has a disadvantage which it requries the prior knowledge(probabiltiy) of data. In this study, we propose a learning method based on attribute values. In the proposed method, even though we don't know the prior knowledge(probability) of data, we can apply our new method to data. The main concept of this method is that each attribute value is regarded as an expert learner, summing up the expert learners lead to better results. Experimental results show our learning method learns from data very fast and performs well when compared to current learning methods(decision tree and bayesian).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.310-318
• /
• 2018

Recently, the importance of big data analysis is increasing as a large amount of data is generated by various devices connected to the Internet with the advent of Internet of Things (IoT). Especially, it is necessary to analyze various large-scale IoT streaming sensor data generated in real time and provide various services through new meaningful prediction. This paper proposes a real-time indoor PM10 concentration prediction LSTM model based on streaming data generated from IoT sensor using AWS. We also construct a real-time indoor PM10 concentration prediction service based on the proposed model. Data used in the paper is streaming data collected from the PM10 IoT sensor for 24 hours. This time series data is converted into sequence data consisting of 30 consecutive values from time series data for use as input data of LSTM. The LSTM model is learned through a sliding window process of moving to the immediately adjacent dataset. In order to improve the performance of the model, incremental learning method is applied to the streaming data collected every 24 hours. The linear regression and recurrent neural networks (RNN) models are compared to evaluate the performance of LSTM model. Experimental results show that the proposed LSTM prediction model has 700% improvement over linear regression and 140% improvement over RNN model for its performance level.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.367-374
• /
• 2022

The purpose of this study was to propose a deep learning algorithm that applies to the fault diagnosis of fuel pumps and purifiers of autonomous ships. A deep learning algorithm reflecting the time dependence of the measured signal was configured, and the failure pattern was trained using the vibration signal, measured in the equipment's regular operation and failure state. Considering the sequential time-dependence of deterioration implied in the vibration signal, this study adopts Conv1D with sliding window computation for fault detection. The time dependence was also reflected, by transferring the measured signal from two-dimensional to three-dimensional. Additionally, the optimal values of the hyper-parameters of the Conv1D model were determined, using the grid search technique. Finally, the results show that the proposed data preprocessing method as well as the Conv1D model, can reflect the sequential dependency between the fault and its effect on the measured signal, and appropriately perform anomaly as well as failure detection, of the equipment chosen for application.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• Journal of KIISE:Databases
• /
• v.31 no.5
• /
• pp.468-478
• /
• 2004

It is essential in various application areas of data mining and bioinformatics to effectively retrieve the occurrences of interesting patterns from sequence databases. For example, let's consider a network event management system that records the types and timestamp values of events occurred in a specific network component(ex. router). The typical query to find out the temporal casual relationships among the network events is as fellows: 'Find all occurrences of CiscoDCDLinkUp that are fellowed by MLMStatusUP that are subsequently followed by TCPConnectionClose, under the constraint that the interval between the first two events is not larger than 20 seconds, and the interval between the first and third events is not larger than 40 secondsTCPConnectionClose. This paper proposes an indexing method that enables to efficiently answer such a query. Unlike the previous methods that rely on inefficient sequential scan methods or data structures not easily supported by DBMSs, the proposed method uses a multi-dimensional spatial index, which is proven to be efficient both in storage and search, to find the answers quickly without false dismissals. Given a sliding window W, the input to a multi-dimensional spatial index is a n-dimensional vector whose i-th element is the interval between the first event of W and the first occurrence of the event type Ei in W. Here, n is the number of event types that can be occurred in the system of interest. The problem of‘dimensionality curse’may happen when n is large. Therefore, we use the dimension selection or event type grouping to avoid this problem. The experimental results reveal that our proposed technique can be a few orders of magnitude faster than the sequential scan and ISO-Depth index methods.hods.