• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.6
• /
• pp.367-374
• /
• 2022

This papter presents the use of the automatic differential method based on the backpropagation method to obtain the design sensitivity and its application to topology optimization considering the stress constraints. Solving topology optimization problems with stress constraints is difficult owing to singularities, the local nature of stress constraints, and nonlinearity with respect to design variables. To solve the singularity problem, the stress relaxation technique is used, and p-norm for stress constraints is applied instead of local stresses for global stress measures. To overcome the nonlinearity of the design variables in stress constraint problems, it is important to analytically obtain the exact design sensitivity. In conventional topology optimization, design sensitivity is obtained efficiently and accurately using the adjoint variable method; however, obtaining the design sensitivity analytically and additionally solving the adjoint equation is difficult. To address this problem, the design sensitivity is obtained using a backpropagation technique that is used to determine optimal weights and biases in the artificial neural network, and it is applied to the topology optimization with the stress constraints. The backpropagation technique is used in automatic differentiation and can simplify the calculation of the design sensitivity for the objectives or constraint functions without complicated analytical derivations. In addition, the backpropagation process is more computationally efficient than solving adjoint equations in sensitivity calculations.

• Journal of Science Education
• /
• v.47 no.2
• /
• pp.211-224
• /
• 2023

The purpose of this study is to suggest how to investigate the reliability of the assessment, which consists of items generated by automatic item generation using empirical example data. To achieve this, we analyzed the illustrative assessment data by applying the multivariate generalizability theory, which can reflect the design of responding to different items for each student and multiple error sources in the assessment score. The result of the G-study showed that, in most designs, the student effect corresponding to the true score of the classical test theory was relatively large after residual effects. In addition, in the design where the content domain was fixed, the ranking of students did not change depending on the item types or items. Similarly, in the design where the item format was fixed, the difficulty showed little variation depending on the content domains. The result of the D-study indicated that the original assessment data achieved a sufficient level of reliability. It was also found that higher reliability than the original assessment data could be obtained by reducing the number of items in the content domains of operation, geometry, and probability and statistics, or by assigning higher weights to the domains of letters and formulas, and function. The efficient measurement conditions presented in this study are limited to the illustrative assessment data. However, the method applied in this study can be utilized to determine the reliability and to find efficient measurement conditions for the various assessment situations using automatic item generation based on measurement traits.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.1-12
• /
• 2009

Mobbing is going the rounds through a society rapidly and Military is not exception. Because mobbing of military is expressed not only psychology exclusion that is mobbing pattern of adult society but also sometimes psychologic and physical mobbing, is possible to join serious military discipline like a suicide and outrageous behavior. Specially military try to protect occurrence of victims that is public service through various rules and management plan but victims is going on happen. It means importance of grasp not only current mobbing victims but also potential mobbing victims better than preparation of various rules and management plans. Therefore this paper extracts seven factors and fifty attributes that are related to this matter mobbing. Next, by using Gunwoo's Social Network Service that is made for oneself and expressing extracting factors as '1' if they are related me or not '0'. And apply similarity function(Dice's coefficient) to attributes summation included in factors to calculate similarity between the users. Third, calculate optimizing weight choosing factors included attributes by applying neural network algorithm of SPSS Clementine and propose Mobbing Value(MV) Algorithm through this total summation. Finally through this algorithm which will contribute to efficient personnel management, we can grasp mobbing victims and tentative mobbing victims.

• Journal of Digital Convergence
• /
• v.20 no.3
• /
• pp.325-331
• /
• 2022

As IoT devices are used in various ways in an edge network environment, multiple studies are being conducted that utilizes the information collected from IoT devices in various applications. However, it is not easy to apply accurate IoT data immediately as IoT data collected according to network environment (interference, interference, etc.) are frequently missed or error occurs. In order to minimize mistakes in IoT data collected in an edge network environment, this paper proposes a management technique that ensures the reliability of IoT data by randomly generating signature values of IoT data and allocating only Security Information (SI) values to IoT data in bit form. The proposed technique binds IoT data into a blockchain by applying multiple hash chains to asymmetrically link and process data collected from IoT devices. In this case, the blockchainized IoT data uses a probability function to which a weight is applied according to a correlation index based on deep learning. In addition, the proposed technique can expand and operate grouped IoT data into an n-layer structure to lower the integrity and processing cost of IoT data.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.12 no.1
• /
• pp.1-14
• /
• 2010

Until now, the evaluation method of spalling depth using Martin et al. (1999)'s linear regression relations has long been known applicable. However, it is not likely that the proposed equation is applicable to the openings other than circular type and mostly overpredict the spalling depth in comparison with actual spalling cases. Moreover, the evaluation method to estimate the spalling width has not been presented yet; it is essential to evaluate the spalling width in addition to the spalling depth, because the shape of the spalled region influences the choice of suitable rock reinforcement. In this study, linear regression equations, in which normalized spalling depth ($d_f/W_D$) and normalized spalling width ($w_f/W_D$) are functions of three spalling evaluation indices, ${\sigma}_1/{\sigma}_c,\;D_{is}(={\sigma}_{max}/{\sigma}_c)$ and ${\sigma}_{dev}/{\sigma}_{cm}$, are established based on in-situ spalling observations and CWFS simulation results. Confidence intervals of 95% using the statistical inference theory are used in verifying the reliability of linear regression equations. Spalling depth ($d_f$) and spalling width ($w_f$) predicted from the proposed linear regression relations, which take three spalling evaluation indices into account, showed reasonable match with in-situ observations by adopting weighting factors considering the degree of variance of linear regression relations.

• Journal of Biomedical Engineering Research
• /
• v.19 no.5
• /
• pp.455-468
• /
• 1998

For the objective interpretation of cerebral metabolic patterns in epilepsy patients, we developed computer-aided classifier using artificial neural network. We studied interictal brain FDG PET scans of 257 epilepsy patients who were diagnosed as normal(n=64), L TLE (n=112), or R TLE (n=81) by visual interpretation. Automatically segmented volume of interest (VOI) was used to reliably extract the features representing patterns of cerebral metabolism. All images were spatially normalized to MNI standard PET template and smoothed with 16mm FWHM Gaussian kernel using SPM96. Mean count in cerebral region was normalized. The VOls for 34 cerebral regions were previously defined on the standard template and 17 different counts of mirrored regions to hemispheric midline were extracted from spatially normalized images. A three-layer feed-forward error back-propagation neural network classifier with 7 input nodes and 3 output nodes was used. The network was trained to interpret metabolic patterns and produce identical diagnoses with those of expert viewers. The performance of the neural network was optimized by testing with 5~40 nodes in hidden layer. Randomly selected 40 images from each group were used to train the network and the remainders were used to test the learned network. The optimized neural network gave a maximum agreement rate of 80.3% with expert viewers. It used 20 hidden nodes and was trained for 1508 epochs. Also, neural network gave agreement rates of 75~80% with 10 or 30 nodes in hidden layer. We conclude that artificial neural network performed as well as human experts and could be potentially useful as clinical decision support tool for the localization of epileptogenic zones.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.1
• /
• pp.1-12
• /
• 2008

In this paper, we present a real-time algorithm for recognizing the vehicle color from the indoor and outdoor vehicle images based on GPU (Graphics Processing Unit) acceleration. In the preprocessing step, we construct feature victors from the sample vehicle images with different colors. Then, we combine the feature vectors for each color and store them as a reference texture that would be used in the GPU. Given an input vehicle image, the CPU constructs its feature Hector, and then the GPU compares it with the sample feature vectors in the reference texture. The similarities between the input feature vector and the sample feature vectors for each color are measured, and then the result is transferred to the CPU to recognize the vehicle color. The output colors are categorized into seven colors that include three achromatic colors: black, silver, and white and four chromatic colors: red, yellow, blue, and green. We construct feature vectors by using the histograms which consist of hue-saturation pairs and hue-intensity pairs. The weight factor is given to the saturation values. Our algorithm shows 94.67% of successful color recognition rate, by using a large number of sample images captured in various environments, by generating feature vectors that distinguish different colors, and by utilizing an appropriate likelihood function. We also accelerate the speed of color recognition by utilizing the parallel computation functionality in the GPU. In the experiments, we constructed a reference texture from 7,168 sample images, where 1,024 images were used for each color. The average time for generating a feature vector is 0.509ms for the $150{\times}113$ resolution image. After the feature vector is constructed, the execution time for GPU-based color recognition is 2.316ms in average, and this is 5.47 times faster than the case when the algorithm is executed in the CPU. Our experiments were limited to the vehicle images only, but our algorithm can be extended to the input images of the general objects.

• Progress in Medical Physics
• /
• v.23 no.4
• /
• pp.317-325
• /
• 2012

The Varian PORTALVISION (Varian Medical Systems, US) shows significant overresponses as the off-center distance increases compared to the predicted dose. In order to correct the dose discrepancy, the off-axis correction is applied to VARIAN iX linear accelerators. The portal dose for $38{\times}28cm^2$ open field is acquired for 6 MV, 15 MV photon beams and also are predicted by PDIP algorithm under the same condition of the portal dose acquisition. The off-axis correction is applied by modifying the $40{\times}40cm^2$ diagonal beam profile data which is used for the beam profile calibration. The ratios between predicted dose and measured dose is modeled as a function of off-axis distance with the $4^{th}$ polynomial and is applied to the $40{\times}40cm^2$ diagonal beam profile data as the weight to correct measured dose by EPID detector. The discrepancy between measured dose and predicted dose is reduced from $4.17{\pm}2.76$ CU to $0.18{\pm}0.8$ CU for 6 MV photon beam and from $3.23{\pm}2.59$ CU to $0.04{\pm}0.85$ CU for 15 MV photon beam. The passing rate of gamma analysis for the pyramid fluence patten with the 4%, 4 mm criteria is improved from 98.7% to 99.1% for 6 MV photon beam, from 99.8% to 99.9% for 15 MV photon beam. IMRT QA is also performed for randomly selected Head and Neck and Prostate IMRT plans after applying the off-axis correction. The gamma passing rare is improved by 3% on average, for Head and Neck cases: $94.7{\pm}3.2%$ to $98.2{\pm}1.4%$, for Prostate cases: $95.5{\pm}2.6%$, $98.4{\pm}1.8%$. The gamma analysis criteria is 3%, 3 mm with 10% threshold. It is considered that the off-axis correction might be an effective and easily adaptable means for correcting the discrepancy between measured dose and predicted dose for IMRT QA using EPID in clinic.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.493-500
• /
• 2021

In this paper, we propose the development of deep learning structure to improve quality of polygonal containers. The deep learning structure consists of a convolution layer, a bottleneck layer, a fully connect layer, and a softmax layer. The convolution layer is a layer that obtains a feature image by performing a convolution 3x3 operation on the input image or the feature image of the previous layer with several feature filters. The bottleneck layer selects only the optimal features among the features on the feature image extracted through the convolution layer, reduces the channel to a convolution 1x1 ReLU, and performs a convolution 3x3 ReLU. The global average pooling operation performed after going through the bottleneck layer reduces the size of the feature image by selecting only the optimal features among the features of the feature image extracted through the convolution layer. The fully connect layer outputs the output data through 6 fully connect layers. The softmax layer multiplies and multiplies the value between the value of the input layer node and the target node to be calculated, and converts it into a value between 0 and 1 through an activation function. After the learning is completed, the recognition process classifies non-circular glass bottles by performing image acquisition using a camera, measuring position detection, and non-circular glass bottle classification using deep learning as in the learning process. In order to evaluate the performance of the deep learning structure to improve quality of polygonal containers, as a result of an experiment at an authorized testing institute, it was calculated to be at the same level as the world's highest level with 99% good/defective discrimination accuracy. Inspection time averaged 1.7 seconds, which was calculated within the operating time standards of production processes using non-circular machine vision systems. Therefore, the effectiveness of the performance of the deep learning structure to improve quality of polygonal containers proposed in this paper was proven.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.49 no.2
• /
• pp.89-100
• /
• 2021

This study evaluated the degree of interaction between the people and the environment using perceived naturalness measure. The seventh-grade index of Hemeroby was divided into subclasses of land cover according to degrees of human influence. The grade was standardized for each indicator to evaluate the current state of urban parks in Seoul by applying probability density function and weight. User evaluation was conducted on six distinctive parks selected. In the results, three implications were found between spatial evaluation according to the perceived naturalness. First, park users evaluated highly for the spaces such as broad-leaved forest, coniferous forest and mixed forest evaluated highly in the Hemeroby grade index. Park users generally recognized that various types of trees in the area had high naturalness. The density of trees is one of the factors in perceived naturalness. Second, water spaces were highly evaluated for naturalness in the Hemeroby grade index. However, the perceived naturalness of water spaces such as inland wetlands, pond and reservoir evaluated in various ways depending on environmental conditions around the park. Third, perceived naturalness is easily evaluated through vertical landscape elements such as trees rather than horizontal landscapes such as grassland. The perceived naturalness is similar to the naturalness evaluation using land cover. However the study found the perceived naturalness for a specific space was different from the Hemeroby index. Perceived naturalness by the user includes the content that the individual sees, hears, and experiences. Park users are usually structuring naturalness through evaluating the value of urban green spaces based on personal perception. Therefore there is no absolute standard criterion for evaluating the naturalness of urban green spaces. A deeper study is needed that considers user bundles or user groups with conflicting interests on the perceived naturalness in urban parks. These studies will be essential data on the direction of naturalness urban park service should provide.