• Journal of Korea Multimedia Society
• /
• v.23 no.3
• /
• pp.468-475
• /
• 2020

In this paper, we proposed a three-dimensional visualization system for medical images in augmented reality based on deep learning. In the proposed system, the artificial neural network model performed fully automatic segmentation of the region of lung and pulmonary nodule from chest CT images. After applying the three-dimensional volume rendering method to the segmented images, it was visualized in augmented reality devices. As a result of the experiment, when nodules were present in the region of lung, it could be easily distinguished with the naked eye. Also, the location and shape of the lesions were intuitively confirmed. The evaluation was accomplished by comparing automated segmentation results of the test dataset to the manual segmented image. Through the evaluation of the segmentation model, we obtained the region of lung DSC (Dice Similarity Coefficient) of 98.77%, precision of 98.45%, recall of 99.10%. And the region of pulmonary nodule DSC of 91.88%, precision of 93.05%, recall of 90.94%. If this proposed system will be applied in medical fields such as medical practice and medical education, it is expected that it can contribute to custom organ modeling, lesion analysis, and surgical education and training of patients.

• Ceramist
• /
• v.22 no.3
• /
• pp.243-255
• /
• 2019

Graphene, a two-dimensional material with a single atomic layer, has recently become a major research focus in various applications such as electronic devices, sensors, energy storage, catalysts, and adsorbents, because of its large theoretical surface area, excellent electrical conductivity, outstanding chemical stability, and good mechanical properties. Recently, 3D nanoporous graphene structures have received tremendous attention to expand the application of 2D graphene. Here, we overview the synthesis of 3D nanoporous graphene network structure with two-dimensional graphite oxide sheets, the control of porous parameters such as specific surface area, pore volume and pore size etc, and the modification of electronic structure by heteroatom doping along with its various applications. The 3D nanoporous graphene shows superior performance in diverse applications as a promising key material. Consequently, 3D nanoporous graphene can lead the future for advanced nanotechnology.

• Journal of the Korean Society of Groundwater Environment
• /
• v.5 no.2
• /
• pp.80-87
• /
• 1998

Since groundwater flow paths have one of the major roles to transport the radioactive nuclides from the radioactive waste repository to the biosphere, the discrete fracture network model is used for the rock block scale flow instead of the porous continuum model. This study aims to construct a three dimensional discrete fracture network to interpret the groundwater flow system in the study site. The modeling work includes the determination of the probabilistic distribution function from the fracture geometric and hydraulic parameters, three dimensional fracture modeling and model calibration. The results of the constant pressure tests performed in a fixed interval length at boreholes indicate that the flow dimension around boreholes shows mainly radial to spherical flow pattern. The fracture transmissivity value calculated by Cubic law is 6.12${\times}$10$\^$-7/ ㎡/sec with lognormal distribution. The conductive fracture intensity estimated by FracMan code is 1.73. Based on this intensity, the total number of conductive fractures are obtained as 3,080 in the rock block of 100 m${\times}$100 m${\times}$100 m.

• Journal of Communications and Networks
• /
• v.11 no.1
• /
• pp.57-71
• /
• 2009

Networking together hundreds or thousands of cheap sensor nodes allows users to accurately monitor a remote environment by intelligently combining the data from the individual nodes. As sensor nodes are typically battery operated, it is important to efficiently use the limited energy of the nodes to extend the lifetime of the wireless sensor network (WSN). One of the fundamental issues in WSNs is the coverage problem. In this paper, the border coverage problem in WSNs is rigorously analyzed. Most existing results related to the coverage problem in wireless sensor networks focused on planar networks; however, three dimensional (3D) modeling of the sensor network would reflect more accurately real-life situations. Unlike previous works in this area, we provide distributed algorithms that allow the selection and activation of an optimal border cover for both 2D and 3D regions of interest. We also provide self-healing algorithms as an optimization to our border coverage algorithms which allow the sensor network to adaptively reconfigure and repair itself in order to improve its own performance. Border coverage is crucial for optimizing sensor placement for intrusion detection and a number of other practical applications.

• ETRI Journal
• /
• v.39 no.2
• /
• pp.234-244
• /
• 2017

Research interest in three-dimensional multiple-input multiple-output (3D-MIMO) beamforming has rapidly increased on account of its potential to support high data rates through an array of strategies, including sector or user-specific elevation beamforming and cell-splitting. To evaluate the full performance benefits of 3D and full-dimensional (FD) MIMO beamforming, the 3D character of the real MIMO channel must be modeled with consideration of both the azimuth and elevation domain. Most existing works on the 2D spatial channel model (2D-SCM) assume a wide range for the distribution of elevation angles of departure (eAoDs), which is not practical according to field measurements. In this paper, an optimal FD-MIMO planar array configuration is presented for different practical channel conditions by restricting the eAoDs to a finite range. Using a dynamic network level simulator that employs a complete 3D SCM, we analyze the relationship between the angular spread and sum throughput. In addition, we present an analysis on the optimal antenna configurations for the channels under consideration.

• Journal of Korean Institute of Industrial Engineers
• /
• v.25 no.3
• /
• pp.382-392
• /
• 1999

Industrial robots have increased in both the number and applications in today's material handling systems. However, traditional approaches to robot controling have had limited success in complicated environment, especially for real time applications. One of the main reasons for this is that most traditional methods use a set of kinematic equations to figure out the physical environment of the robot. In this paper, a neural network model to solve robot manipulator's inverse kinematics problem is suggested. It is composed of two Self-Organizing Feature Maps by which the workspace of robot environment and the joint space of robot manipulator is inter-linked to enable the learning of the inverse kinematic relationship between workspace and joint space. The proposed model has been simulated with two robot manipulators, one, consisting of 2 links in 2-dimensional workspace and the other, consisting of 3 links in 2-dimensional workspace, and the performance has been tested by accuracy of the manipulator's positioning and the response time.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.6
• /
• pp.143-152
• /
• 2000

The comer filling in shaped drawing process is an important characteristic, unlike the round drawing. It has also influence on the dimensional accuracy of the product. In this study, therefore, the shaped drawing process has been simulated by the three dimensional rigid-plastic finite element method in order to investigate the effect of process variables such as reduction in area and semi-die angle to the corner filling. The artificial neural network has also been introduced to reduce the number of simulations. To verify the results of simulations, experiments have been performed on the real industrial products. According to the results, the main process variable on the corner filling is the combination of semi-die angle in the irregular shaped drawing processes, but in the case of regular shaped drawing processes, reduction in area has great influence on the corner filling.

• Journal of information and communication convergence engineering
• /
• v.19 no.3
• /
• pp.148-154
• /
• 2021

With the advent of context-aware computing, many attempts were made to understand emotions. Among these various attempts, Speech Emotion Recognition (SER) is a method of recognizing the speaker's emotions through speech information. The SER is successful in selecting distinctive 'features' and 'classifying' them in an appropriate way. In this paper, the performances of SER using neural network models (e.g., fully connected network (FCN), convolutional neural network (CNN)) with Mel-Frequency Cepstral Coefficients (MFCC) are examined in terms of the accuracy and distribution of emotion recognition. For Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset, by tuning model parameters, a two-dimensional Convolutional Neural Network (2D-CNN) model with MFCC showed the best performance with an average accuracy of 88.54% for 5 emotions, anger, happiness, calm, fear, and sadness, of men and women. In addition, by examining the distribution of emotion recognition accuracies for neural network models, the 2D-CNN with MFCC can expect an overall accuracy of 75% or more.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.2
• /
• pp.111-118
• /
• 2002

These days, surveying instruments are developing rapidly and the precision is improving continuously. The building of three dimensional terrains of high precision are possible and the calculation of the areas or the volumes have high precision due to the development of the technique of the spatial information system using computer. But actually, in construction site they calculate two-dimensional area using the traditional method, plate table surveying, planimeter, and then get three-dimensional area through multiplying two-dimensional area by the slope correction factor. In this study, we show the defect and inefficiency of the calculation of area by the traditional methods and survey the area with Electric Distance Measurement and GPS instrument. With this data, we made the three dimensional terrain model and calculated two-dimensional area, three-dimensional area. After that, we compared areas that calculated by algorithm of triangulated irregular network and analysis of grid method with standard area that calculated by the traditional method. Finally, this paper suggested more effective and precious method in calculating three-dimensional area.

• Journal of the Korean Chemical Society
• /
• v.55 no.2
• /
• pp.199-203
• /
• 2011

The title one-dimensional hydrogen-bonded coordination compound $[Cu^{II}(C_{13}H_{17}N_3OBr)(C_8H_5O_4)]{\cdot}2H_2O.CH_3OH$ has been synthesized and characterized by single crystal X-ray diffraction study. The monomeric unit contains a square-planar $Cu^{II}$ centre. The four coordination sites are occupied by a tridentate anionic Schiff base ligand (4-bromo-2-[(2-piperazin-1-yl-ethylimino)-methyl]-phenol) which furnishes an $N_2O$-donor set, with the fourth position being occupied by the oxygen atom of an adjacent terephthalate unit. Two adjacent neutral molecules are linked through intermolecular N-H---O and O-H---N hydrogen bonds and generate a dimeric pair. Each dimeric pair is connected with each other via discrete water and methanol molecules by hydrogen bonding to form a one-dimensional supramolecular network.