• 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 the Korea Concrete Institute
• /
• v.17 no.2 s.86
• /
• pp.201-212
• /
• 2005

A new strut-tie model using secant stiffness, Direct Inelastic Strut-Tie Model, was developed. Since basically the proposed design method uses linear analysis, it is convenient and stable in numerical analysis. At the same time, the proposed design method can accurately estimate the inelastic strength and ductility demands of struts and ties because it can analyzes the inelastic behavior of structure using iterative calculations for secant stiffness. In the present study, the procedure of the proposed design method was established, and a computer program incorporating the proposed method was developed. Design examples using the proposed method were presented, and its advantages were highlighted by the comparison with the traditional strut-tie model. The Direct Inelastic Strut-Tie Model, as an integrated analysis/design method, can directly address the design strategy intended by the engineer to prevent development of macro-cracks and brittle failure of struts. Since the proposed model can analyze the inelastic deformation, indeterminate strut-tie model can be used. Also, since the proposed model controls the local deformations of struts and ties, it can be used as a performance-based design method for various design criteria.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.620-626
• /
• 2004

For general nonlinear processes, it is difficult to control with a linear model-based control method and nonlinear controls are considered. Among the numerous approaches suggested, the most rigorous approach is to use dynamic optimization. Many general engineering problems like control, scheduling, planning etc. are expressed by functional optimization problem and most of them can be changed into dynamic programming (DP) problems. However the DP problems are used in just few cases because as the size of the problem grows, the dynamic programming approach is suffered from the burden of calculation which is called as 'curse of dimensionality'. In order to avoid this problem, the Neuro-Dynamic Programming (NDP) approach is proposed by Bertsekas and Tsitsiklis (1996). To get the solution of seriously nonlinear process control, the interest in NDP approach is enlarged and NDP algorithm is applied to diverse areas such as retailing, finance, inventory management, communication networks, etc. and it has been extended to chemical engineering parts. In the NDP approach, we select the optimal control input policy to minimize the value of cost which is calculated by the sum of current stage cost and future stages cost starting from the next state. The cost value is related with a weight square sum of error and input movement. During the calculation of optimal input policy, if the approximate cost function by using simulation data is utilized with Bellman iteration, the burden of calculation can be relieved and the curse of dimensionality problem of DP can be overcome. It is very important issue how to construct the cost-to-go function which has a good approximate performance. The neural network is one of the eager learning methods and it works as a global approximator to cost-to-go function. In this algorithm, the training of neural network is important and difficult part, and it gives significant effect on the performance of control. To avoid the difficulty in neural network training, the lazy learning method like k-nearest neighbor method can be exploited. The training is unnecessary for this method but requires more computation time and greater data storage. The pH neutralization process has long been taken as a representative benchmark problem of nonlin ar chemical process control due to its nonlinearity and time-varying nature. In this study, the NDP algorithm was applied to pH neutralization process. At first, the pH neutralization process control to use NDP algorithm was performed through simulations with various approximators. The global and local approximators are used for NDP calculation. After that, the verification of NDP in real system was made by pH neutralization experiment. The control results by NDP algorithm was compared with those by the PI controller which is traditionally used, in both simulations and experiments. From the comparison of results, the control by NDP algorithm showed faster and better control performance than PI controller. In addition to that, the control by NDP algorithm showed the good results when it applied to the cases with disturbances and multiple set point changes.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.104-112
• /
• 2012

Recently, the HDR imaging technique that mimics human eye is incorporated with LCD/LED display devices to deal with mismatch between the real world scene and the displayed image. However, HDR image has a veiling glare limit as well as a scale of the local contrast problem. In order to overcome these problems, several color correction methods, CSR(center/surround Retinex), MSR (Multi-Scale Retinex), tone-mapping method, iCAM06 and so on, are proposed. However, these methods have a dominated color throughout the entire resulting image after performing color correction. Accordingly, this paper presents a new color correction method using dynamic cone response function. The proposed color correction method consists of tone-mapping and dynamic cone response. The tone-mapping is obtained by using a linear interpolation between chromatic and achromatic. Thereafter, the resulting image is processed through the dynamic cone response function, which estimates the dynamic responses of human visual system as well as deals with mismatch between the real scene image and the rendered image. The experiment results show that the proposed method yields better performance of color correction over the conventional methods.

• Geophysics and Geophysical Exploration
• /
• v.11 no.1
• /
• pp.15-25
• /
• 2008

Ocean-bottom seismometer (OBS) positions are one of the key parameters in an OBS-airgun seismic survey for crustal structure study. To improve the quality of these parameters, we have developed a new method of determining OBS positions, using airgun shot data and bathymetric data in addition to available distance measurements by acoustic transponders. The traveltimes of direct water waves emitted by airgun shots and recorded by OBSs are used as important information for determining OBS locations, in cases where there are few acoustic transponder data (<3 sites). The new method consists of two steps. A global search is performed as the first step, to find nodes of the bathymetric grid that are the closest to explaining the observed direct water-wave traveltimes from airgun shots, and acoustic ranging using a transponder system. The use of precise 2D bathymetric data is most important if the bottom topography near the OBS is extremely rough. The locations of the nodes obtained by the first step are used as initial values for the second step, to avoid falling into local convergence minima. In the second step, a non-linear inverse method is executed. If the OBS internal clock shows large drift, a secondary correction for the OBS internal clock is obtained, as well as the OBS location, as final results by this method. We discuss the error and the influence of each measurement used in the determination of OBS location.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.14 no.1
• /
• pp.171-178
• /
• 1994

The skin friction on single piles was investigated by using an analytical study and a numerical analysis. The emphasis was given to the variation of skin friction on piles based on the load transfer mechanism developed for the consolidation of a surrounding soft clay. Local yield or slip at the pile-soil interface was taken into account by specifying a limiting value of shear stress. The response of a single pile was analyzed and compared to the results of field case study. Based on the results obtained, it is shown that the skin friction on a pile increases as the degree of consolidation increases and the ultimate axial forces result from the long term behavior of clay corresponding to the end of the consolidation. It is also found that the analysis using one-dimensional consolidation theory as well as two or three-dimensional non-linear analysis gives relatively reasonable results.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.346-348
• /
• 2004

In this rarer, we introduce a new Fuzzy Polynomial Neural Networks (FPNNs)-like structure whose neuron is based on the Fuzzy Set-based Fuzzy Inference System (FS-FIS) and is different from that of FPNNs based on the Fuzzy relation-based Fuzzy Inference System (FR-FIS) and discuss the ability of the new FPNNs-like structurenamed Fuzzy Set-based Polynomial Neural Networks (FSPNN). The premise parts of their fuzzy rules are not identical, while the consequent parts of the both Networks (such as FPNN and FSPNN) are identical. This difference results from the angle of a viewpoint of partition of input space of system. In other word, from a point of view of FS-FIS, the input variables are mutually independent under input space of system, while from a viewpoint of FR-FIS they are related each other. In considering the structures of FPNN-like networks such as FPNN and FSPNN, they are almost similar. Therefore they have the same shortcomings as well as the same virtues on structural side. The proposed design procedure for networks' architecture involves the selection of appropriate nodes with specific local characteristics such as the number of input variables, the order of the polynomial that is constant, linear, quadratic, or modified quadratic functions being viewed as the consequent part of fuzzy rules, and a collection of the specific subset of input variables. On the parameter optimization phase, we adopt Information Granulation (IG) based on HCM clustering algorithm and a standard least square method-based learning. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized FSPNN (gFSPNN), the model is experimented with using gas furnace process dataset.

• Ecology and Resilient Infrastructure
• /
• v.4 no.2
• /
• pp.83-92
• /
• 2017

Increased investment in environment-friendly transport vehicles has led to rapid transit of railway tracks, double track program, linear improvements in railway lines, and moving railroad routes into the suburbs. They resulted in fast increase of railway yards. However, as the railroad yards being neglected, urban fine sites have been degraded. Local governments kept seeking ways to utilize the railway yards. In addition, Ministry of land, infrastructure and transport enacted "Guidelines for utilization of railway yards". The Guidelines categorized the railway yards into three types; conservation, utilized, and other sites in order to make efficient use of them. The railway yards have been converted and used for parks, rail bike trails, bike paths, and solar projects. It seems that studies are needed on diverse use of the yards and on post evaluation. This study investigated current uses of railway yards, domestic and foreign, and analyzed for the pertinent conditions on natural and cultural landscape, educational value, location and accessibility, potential for recreational area, and development opportunities. In this study, I proposed a quantitative evaluation method, and to find way to diversify the use of railway yards.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.6
• /
• pp.5-14
• /
• 1994

This paper is about an experiment of speaker-independent automatic Korean spoken words recognition using Multi-Layered Perceptron and Error Back-propagation algorithm. The object words are 50 citynames of D.D.D local numbers. 43 of those are 2 syllables and the rest 7 are 3 syllables. The words were not segmented into syllables or phonemes, and some feature components extracted from the words in equal gap were applied to the neural network. That led independent result on the speech duration, and the PARCOR coefficients calculated from the frames using linear predictive analysis were employed as feature components. This paper tried to find out the optimum conditions through 4 differerent experiments which are comparison between total and pre-classified training, dependency of recognition rate on the number of frames and PAROCR order, recognition change due to the number of neurons in the hidden layer, and the comparison of the output pattern composition method of output neurons. As a result, the recognition rate of $89.6\%$ is obtaimed through the research.

• Journal of Power Electronics
• /
• v.14 no.2
• /
• pp.271-281
• /
• 2014

Fluctuating wind conditions necessitate the use of a variable speed wind turbine (VSWT) with a AC/DC/AC converter scheme in order to harvest the maximum power from the wind and to decouple the synchronous generator voltage and frequency from the grid voltage and frequency. In this paper, a combination of a three phase diode bridge rectifier (DBR) and a modified topology of the diode clamped multilevel inverter (DCMLI) has been considered as an AC/DC/AC converter. A control strategy has been proposed for the DCMLI to achieve the objective of grid interface of a wind power system together with local load compensation. A novel fixed frequency current control method is proposed for the DCMLI based on the level shifted multi carrier PWM for achieving the required control objectives with equal and uniform switching frequency operation for better control and thermal management with the modified DCMLI. The condition of the controller gain is derived to ensure the operation of the DCMLI at the fixed frequency of the carrier. The converter current injected into the distribution grid is controlled in accordance with the wind power availability. In addition, load compensation is performed as an added facility in order to free the source currents being fed from the grid of harmonic distortion, unbalance and a low power factor even though the load may be unbalanced, non-linear and of a poor power factor. The results are validated using PSCAD/EMTDC simulation studies.