• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2005.10a
• /
• pp.247-252
• /
• 2005

The wedge type rail clamp has the operating mechanism: First, the jaw pad clamps a rail with small clamping force Next as the wind speed increases, the clamping force of the jaw pad is increased by the wedge. In order to design the wedge type rail clamp, we need to determine the proper wedge angle to minimize the sliding distance of a roller and the proper clamping angle of a locker to generate the initial clamping force of a jaw pad. The researches for the proper wedge angle have conducted, and in this study we conducted the investigation to determine the proper clamping angle of a locker in the rail clamp with wedge angle of $10^{\circ}$. Because the initial damping force of the jaw pad was determined by the clamping angle of the locker, in order to carry out the clamping force of a jaw pad, we measured the locking force applied to a locker with respect to the clamping angle of a locker, such as $3^{\circ},\;4^{\circ},\;5^{\circ},\;6^{\circ},\;$ using a pressure gauge, and compared the results with the FEA results.

• 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.

• The Journal of Korean Academy of Prosthodontics
• /
• v.33 no.3
• /
• pp.467-491
• /
• 1995

In order to analyze the occlusin of intercuspation with maximun bite force, fifteen healthy adult subjects with the ages 23 to 27 were studied(Group1 ; 5-normal occlusion with Angle's Class1, Group2 ; 5-Angle's Class2 malocclusion, Group3 ; 5-Angle’s Class3 malocclusion). Head Position was fixed with occlusal plane paralleling to horizontal line and occlusal registration r cord was made with polyether rubber impression material(Ramitec, ESPECo. West Germany). After all subject were trained for maximum intercuspation at least 5 times, occlusal registration procedure was repeated for this study. Lower posterior rubber occlusal registration records were sliced with 1mm thickness using precision metal sliding channel(Hitachi Ind. Co., Japan). Gross sectional drawings were traced from occluding view of upper and lower posterior teeth on the rubber slices using digitizer, and superimposed for the determination of each drawing distance(Superimposed Rubber Pattern Method). Based on superimposed rubber pattern drawings, total area of occlusal view, sum of each area of the 5 divided occlusal contact provinces and its ratio, total area and number of occlusal contact area were determined to elucidate occlusal stability in the normal and abnormal occlusion groups. The data were analysed by t-test(p=0.05) to determine statistical significance. The obtained results were as follows : 1. Group1 showed the largest standard area with occlusal view of the lower posterior teeth and Group3 showed the smallest area. There was a significant difference between Group2 and Group3(p=0.025), and Gropu1 was not statistically different for both Group2 and Group3. 2. Means and ratio of the under 2.0mm area(D) and ratio showed $197.49mm^2$, 59.76% in Group1, $188,69mm^2$, 56.10% in Group2, and $174.23mm^2$, 55.76% in Group3. The results that Group1 has the most area/ratio and Group3 has the least area/ratio can be considered Group1 is the most advantageous for masticatory effective area, and Group3 is the least adnantageous. 3. Means and ratio of the under 1.0mm area(C) were $198.96mm^2$, 42.65% in Group1, 123.06$mm^2$, 46.58% in Group2, and $92.24mm^2$, 29.52% in Group3. These data means that Group1 is the most advantageous in terms of masticatory effective area and Group3 is the least. 4. Means and ratio of the under 0.5mm area(B) were $86.68mm^2$, 26.68% in Group1, $62.98mm^2$, 18.71% in Group2, and $36.44mm^2$, 11.66% in Group3. These can also be considered Group1 is the most advantageous for masticatory effective area and occlusal stability. 5. Means and ratio of the under 0.05mm area(A) were $30.92mm^2$, 9.21% in Group1, $14.31mm^2$, 4.25% in Group2, and $7.59mm^2$, 2.43% in Group3. The area ratio of the each subject group was(4.1) : (1.9) : (1)and the data of the under 0.05mm area has the intimate relationship with inter-group and intra-group data/ratio. 6. First molar showed the most occlusal contact points in all subject group and Group1 showed somewhat uniformly distributed occlusal contact point except first premolar. In Group2, all contact point in posterior teeth showed significantly reduced distribution except first molar. Group3 showed evenly distributed contace points in first and second molars.

• Journal of Korean Society of Forest Science
• /
• v.66 no.1
• /
• pp.16-36
• /
• 1984

It is very important in forestry to study the shear strength of weathered granitic soil, because the soil covers 66% of our country, and because the majority of land slides have been occured in the soil. In general, the causes of land slide can be classified both the external and internal factors. The external factors are known as vegetations, geography and climate, but internal factors are known as engineering properties originated from parent rocks and weathering. Soil engineering properties are controlled by the skeleton structure, texture, consistency, cohesion, permeability, water content, mineral components, porosity and density etc. of soils. And the effects of these internal factors on sliding down summarize as resistance, shear strength, against silding of soil mass. Shear strength basically depends upon effective stress, kinds of soils, density (void ratio), water content, the structure and arrangement of soil particles, among the properties. But these elements of shear strength work not all alone, but together. The purpose of this thesis is to clarify the characteristics of shear strength and the related elements, such as water content ($w_o$), void ratio($e_o$), dry density (${\gamma}_d$) and specific gravity ($G_s$), and the interrelationship among related elements in order to decide the dominant element chiefly influencing on shear strength in natural/undisturbed state of weathered granitic soil, in addition to the characteristics of soil hardness of weathered granitic soil and root distribution of Pinus rigida Mill and Pinus rigida ${\times}$ taeda planted in erosion-controlled lands. For the characteristics of shear strength of weathered granitic soil and the related elements of shear strength, three sites were selected from Kwangju district. The outlines of sampling sites in the district were: average specific gravity, 2.63 ~ 2.79; average natural water content, 24.3 ~ 28.3%; average dry density, $1.31{\sim}1.43g/cm^3$, average void ratio, 0.93 ~ 1.001 ; cohesion, $ 0.2{\sim}0.75kg/cm^2$ ; angle of internal friction, $29^{\circ}{\sim}45^{\circ}$ ; soil texture, SL. The shear strength of the soil in different sites was measured by a direct shear apparatus (type B; shear box size, $62.5{\times}20mm$; ${\sigma}$, $1.434kg/cm^2$; speed, 1/100mm/min.). For the related element analyses, water content was moderated through a series of drainage experiments with 4 levels of drainage period, specific gravity was measured by KS F 308, analysis of particle size distribution, by KS F 2302 and soil samples were dried at $110{\pm}5^{\circ}C$ for more than 12 hours in dry oven. Soil hardness represents physical properties, such as particle size distribution, porosity, bulk density and water content of soil, and test of the hardness by soil hardness tester is the simplest approach and totally indicative method to grasp the mechanical properties of soil. It is important to understand the mechanical properties of soil as well as the chemical in order to realize the fundamental phenomena in the growth and the distribution of tree roots. The writer intended to study the correlation between the soil hardness and the distribution of tree roots of Pinus rigida Mill. planted in 1966 and Pinus rigida ${\times}$ taeda in 199 to 1960 in the denuded forest lands with and after several erosion control works. The soil texture of the sites investigated was SL originated from weathered granitic soil. The former is situated at Py$\ddot{o}$ngchangri, Ky$\ddot{o}$m-my$\ddot{o}$n, Kogs$\ddot{o}$ng-gun, Ch$\ddot{o}$llanam-do (3.63 ha; slope, $17^{\circ}{\sim}41^{\circ}$ soil depth, thin or medium; humidity, dry or optimum; height, 5.66/3.73 ~ 7.63 m; D.B.H., 9.7/8.00 ~ 12.00 cm) and the Latter at changun-long Kwangju-shi (3.50 ha; slope, $12^{\circ}{\sim}23^{\circ}$; soil depth, thin; humidity, dry; height, 10.47/7.3 ~ 12.79 m; D.B.H., 16.94/14.3 ~ 19.4 cm).The sampling areas were 24quadrats ($10m{\times}10m$) in the former area and 12 in the latter expanding from summit to foot. Each sampling trees for hardness test and investigation of root distribution were selected by purposive selection and soil profiles of these trees were made at the downward distance of 50 cm from the trees, at each quadrat. Soil layers of the profile were separated by the distance of 10 cm from the surface (layer I, II, ... ...). Soil hardness was measured with Yamanaka soil hardness tester and indicated as indicated soil hardness at the different soil layers. The distribution of tree root number per unit area in different soil depth was investigated, and the relationship between the soil hardness and the number of tree roots was discussed. The results obtained from the experiments are summarized as follows. 1. Analyses of simple relationship between shear strength and elements of shear strength, water content ($w_o$), void ratio ($e_o$), dry density (${\gamma}_d$) and specific gravity ($G_s$). 1) Negative correlation coefficients were recognized between shear strength and water content. and shear strength and void ratio. 2) Positive correlation coefficients were recognized between shear strength and dry density. 3) The correlation coefficients between shear strength and specific gravity were not significant. 2. Analyses of partial and multiple correlation coefficients between shear strength and the related elements: 1) From the analyses of the partial correlation coefficients among water content ($x_1$), void ratio ($x_2$), and dry density ($x_3$), the direct effect of the water content on shear strength was the highest, and effect on shear strength was in order of void ratio and dry density. Similar trend was recognized from the results of multiple correlation coefficient analyses. 2) Multiple linear regression equations derived from two independent variables, water content ($x_1$ and dry density ($x_2$) were found to be ineffective in estimating shear strength ($\hat{Y}$). However, the simple linear regression equations with an independent variable, water content (x) were highly efficient to estimate shear strength ($\hat{Y}$) with relatively high fitness. 3. A relationship between soil hardness and the distribution of root number: 1) The soil hardness increased proportionally to the soil depth. Negative correlation coefficients were recognized between indicated soil hardness and the number of tree roots in both plantations. 2) The majority of tree roots of Pinus rigida Mill and Pinus rigida ${\times}$ taeda planted in erosion-controlled lands distributed at 20 cm deep from the surface. 3) Simple linear regression equations were derived from indicated hardness (x) and the number of tree roots (Y) to estimate root numbers in both plantations.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.