• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.471-476
• /
• 2024

With the spread of various smart devices and computing devices, big data generation is occurring widely. Machine learning is an algorithm that performs reasoning by learning data patterns. Among the various machine learning algorithms, the algorithm that attracts attention is deep learning based on neural networks. Deep learning is achieving rapid performance improvement with the release of various applications. Recently, among deep learning algorithms, attempts to analyze data using graph structures are increasing. In this study, we present a graph generation method for transferring to a deep learning network. This paper proposes a method of generalizing node properties and edge weights in the graph generation process and converting them into a structure for deep learning input by presenting a matricization We present a method of applying a linear transformation matrix that can preserve attribute and weight information in the graph generation process. Finally, we present a deep learning input structure of a general graph and present an approach for performance analysis.

• Bulletin of the Korean Chemical Society
• /
• v.19 no.6
• /
• pp.628-634
• /
• 1998

The properties of the n-type impurities nitrogen and phosphorus in diamond have been investigated by means of electronic band structure calculations within the framework of the semiempirical extended Huckel tight-binding method. For diamond with the nitrogen and phosphorus substitutional impurities, calculated density of states shows the impurity level deep in the band gap. This property can be derived from the substantial <111> relaxation of the impurity and nearest-neighbor carbon atoms, which is associated with the population of an antibonding orbital between them. The passivated donor property of the P-vacancy complex which lies deep in the gap is also discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.1100-1118
• /
• 2021

In a wide range of ML applications, the training data contains privacy-sensitive information that should be kept secure. Training the ML systems by privacy-sensitive data makes the ML model inherent to the data. As the structure of the model has been fine-tuned by training data, the model can be abused for accessing the data by the estimation in a reverse process called model inversion attack (MIA). Although, MIA has been applied to shallow neural network models of recognizers in literature and its threat in privacy violation has been approved, in the case of a deep learning (DL) model, its efficiency was under question. It was due to the complexity of a DL model structure, big number of DL model parameters, the huge size of training data, big number of registered users to a DL model and thereof big number of class labels. This research work first analyses the possibility of MIA on a deep learning model of a recognition system, namely a face recognizer. Second, despite the conventional MIA under the white box scenario of having partial access to the users' non-sensitive information in addition to the model structure, the MIA is implemented on a deep face recognition system by just having the model structure and parameters but not any user information. In this aspect, it is under a semi-white box scenario or in other words a gray-box scenario. The experimental results in targeting five registered users of a CNN-based face recognition system approve the possibility of regeneration of users' face images even for a deep model by MIA under a gray box scenario. Although, for some images the evaluation recognition score is low and the generated images are not easily recognizable, but for some other images the score is high and facial features of the targeted identities are observable. The objective and subjective evaluations demonstrate that privacy cyber-attack by MIA on a deep recognition system not only is feasible but also is a serious threat with increasing alert state in the future as there is considerable potential for integration more advanced ML techniques to MIA.

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.147-154
• /
• 2019

In this paper, we conducted a study that utilizes deep learning to calculate appropriate physical exercise information when basic human factors such as sex, age, height, and weight of users come in. To apply deep learning, a method was applied to calculate the amount of fat needed to calculate the amount of one repetition maximum by utilizing the structure of the basic Deep Neural Network. By applying Accuracy improvement methods such as Relu, Weight initialization, and Dropout to existing deep learning structures, we have improved Accuracy to derive a lean body weight that is closer to actual results. In addition, the results were derived by applying a formula for calculating the one repetition maximum load on upper and lower body movements for use in actual physical exercise. If studies continue, such as the way they are applied in this paper, they will be able to suggest effective physical exercise options for different conditions as well as conditions for users.

• Korean Journal of Optics and Photonics
• /
• v.15 no.1
• /
• pp.12-16
• /
• 2004

We show that the extinction ratio is improved using slight asymmetry in two core refractive indices of polarization independent very short vertical directional couplers with the double-sided deep-ridge (DSDR) waveguide structure. The optimum asymmetry with the maximum extinction ratio and the tolerance of the refractive index of core with the extinction ratio larger 1ha]1 30 ㏈ increase as the thickness of inner cladding layer and the two cores decrease due to the increase of the coupling strength between the two cores. Also, the device length and the tolerance of the device length with the extinction ratio larger than 30 ㏈ decrease as the thickness of the inner cladding layer and the two cores decrease due to the increase of the coupling strength between the two cores. We show that polarization independent vertical directional couplers with the DSDR waveguide structure with the device length less than 100 ${\mu}{\textrm}{m}$ and the extinction ratio larger than 30 ㏈ could be implemented.

• Geomechanics and Engineering
• /
• v.36 no.2
• /
• pp.167-181
• /
• 2024

The soil-structure relative stiffness is a key factor affecting the seismic response of underground structures. It is of great significance to study the soil-structure relative stiffness for the soil-structure interaction and the seismic disaster reduction of subway stations. In this paper, the dynamic shear modulus ratio and damping ratio of an inhomogeneous soft soil site under different buried depths which were obtained by a one-dimensional equivalent linearization site response analysis were used as the input parameters in a 2D finite element model. A visco-elasto-plastic constitutive model based on the Mohr-Coulomb shear failure criterion combined with stiffness degradation was used to describe the plastic behavior of soil. The damage plasticity model was used to simulate the plastic behavior of concrete. The horizontal and vertical relative stiffness ratios of soil and structure were defined to study the influence of relative stiffness on the seismic response of subway stations in inhomogeneous soft soil. It is found that the compression damage to the middle columns of a subway station with a higher relative stiffness ratio is more serious while the tensile damage is slighter under the same earthquake motion. The relative stiffness has a significant influence on ground surface deformation, ground acceleration, and station structure deformation. However, the effect of the relative stiffness on the deformation of the bottom slab of the subway station is small. The research results can provide a reference for seismic fortification of subway stations in the soft soil area.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.425-430
• /
• 2015

This paper is a study to improve the classification efficiency of rotating objects by using deep neural networks to which a deep learning algorithm was applied. For the classification experiment of rotating objects, COIL-20 is used as data and total 3 types of classifiers are compared and analyzed. 3 types of classifiers used in the study include PCA classifier to derive a feature value while reducing the dimension of data by using Principal Component Analysis and classify by using euclidean distance, MLP classifier of the way of reducing the error energy by using error back-propagation algorithm and finally, deep learning applied DBN classifier of the way of increasing the probability of observing learning data through pre-training and reducing the error energy through fine-tuning. In order to identify the structure-specific error rate of the deep neural networks, the experiment is carried out while changing the number of hidden layers and number of hidden neurons. The classifier using DBN showed the lowest error rate. Its structure of deep neural networks with 2 hidden layers showed a high recognition rate by moving parameters to a location helpful for recognition.

• Geomechanics and Engineering
• /
• v.25 no.3
• /
• pp.179-194
• /
• 2021

In this paper, to study the stability of surrounding rock during roadway excavation in different rock mass structures, the physical model test for roadway excavation process in three types of intact rock mass, layered rock mass and massive rock mass were carried out by using the self-developed two-dimensional simulation testing system of complex underground engineering. Firstly, based on the engineering background of a deep mine in eastern China, the similar materials of the most appropriate ratio in line with the similarity theory were tested, compared and determined. Then, the physical models of four different schemes with 1000 mm (height) × 1000 mm (length) × 250 mm (width) were constructed. Finally, the roadway excavation was carried out after applying boundary conditions to the physical model by the simulation testing system. The results indicate that the supporting effect of rockbolts has a great influence on the shallow surrounding rock, and the rock mass structure can affect the overall stability of the surrounding rock. Furthermore, the failure mechanism and bearing capacity of surrounding rock were further discussed from the comparison of stress evolution characteristics, distribution of stress arch, and failure modes in different schemes.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.11
• /
• pp.1283-1290
• /
• 2014

Recently, a wide variety of simulation techniques such as structure analysis and structure-fluid interaction analysis are being employed in the field of forensic engineering for resolving the problem of legal liability for accidents and disasters. In this study, we performed a forensic engineering investigation of a sinking accident of a DCM (deep cement mixing) vessel. The accident vessel was built as a dedicated SCP (sand compaction pile) vessel at the time of vessel building, and the DCM vessel was structurally modified, e.g., by increasing the leader height and constructing for leader expansion, without a stability review. To determine the effects of expansion and modification of structures in this sinking accident, structural stability evaluation was performed using commercial software for structural analysis, ADINA software. Through an analysis and comparison of simulation results obtained using ADINA software with the results of the structural modification and expansion, we could determine the exact cause of the sinking accident of the DCM vessel.

• Steel and Composite Structures
• /
• v.27 no.4
• /
• pp.417-426
• /
• 2018

This paper presents the seismic behaviors and restoring force model of ring beam joints of steel tube-reinforced concrete column structure under cyclic loading. First, the main failure mode, ultimate bearing capacity, stiffness degradation and energy dissipation capacity are studied. Then, the effects of concrete grade, steel grade, reinforcement ratio and radius-to-width ratios are discussed. Finally, the restoring force model is proposed. Results show that the ring beam joints of steel tube-reinforced concrete column structure performs good seismic performances. With concrete grade increasing, the ultimate bearing capacity and energy dissipation capacity increase, while the stiffness degradation rates increases slightly. When the radius-width ratio is 2, with reinforcement ratio increasing, the ultimate bearing capacity decreases. However, when the radius-to-width ratios are 3, with reinforcement ratio increasing, the ultimate bearing capacity increases. With radius-to-width ratios increasing, the ultimate bearing capacity decreases slightly and the stiffness degradation rate increases, but the energy dissipation capacity increases slightly.