• Economic and Environmental Geology
• /
• v.53 no.4
• /
• pp.479-489
• /
• 2020

A fault is a geological structure that can be a migration path or a cap rock of hydrocarbon such as oil and gas, formed from source rock. The fault is one of the main targets of seismic exploration to find reservoirs in which hydrocarbon have accumulated. However, conventional fault detection methods using lateral discontinuity in seismic data such as semblance, coherence, variance, gradient magnitude and fault likelihood, have problem that professional interpreters have to invest lots of time and computational costs. Therefore, many researchers are conducting various studies to save computational costs and time for fault interpretation, and machine learning technologies attracted attention recently. Among various machine learning technologies, many researchers are conducting fault interpretation studies using the support vector machine, multi-layer perceptron, deep neural networks and convolutional neural networks algorithms. Especially, researchers use not only their own convolution networks but also proven networks in image processing to predict fault locations and fault information such as strike and dip. In this paper, by investigating and analyzing these studies, we found that the convolutional neural networks based on the U-Net from image processing is the most effective one for fault detection and interpretation. Further studies can expect better results from fault detection and interpretation using the convolutional neural networks along with transfer learning and data augmentation.

• Ecology and Resilient Infrastructure
• /
• v.6 no.4
• /
• pp.227-235
• /
• 2019

This study monitored Daecheong 1-bo, Daecheong-stream, which carried out the project in 2014, from 2015 to 2016. The technology applied to the stream was evaluated using Periphytic Algae to check contamination indicators and ecological health of the area with an integral river-bed protection using non-toxic materials. The water quality of the monitoring section was confirmed to be above the river environment standard (II), and it was confirmed that the Saproxenic taxa of the river bed protection were higher than the upper and downstream sections. The TDI, which is an index of attachment algae, was shown in the average 51.03 and 52.15 for the pilot project sections in 2015 and 2016, confirming that the index is of the "normal" grade. This is the other sections in the upstream and downstream sections showed higher than "bad", which is thought to have a positive effect on the habitat of the river ecosystem components, especially the microbial population in river bed protection.

• Journal of the Korea Society of Computer and Information
• /
• v.5 no.2
• /
• pp.30-36
• /
• 2000

The hidden node plays a role of the functional units that classifies the features of input pattern in the given question. Therefore, a neural network that consists of the number of a suitable optimum hidden node has be on the rise as a factor that has an important effect upon a result. However there is a problem that decides the number of hidden nodes based on back-propagation learning algorithm. If the number of hidden nodes is designated very small perfect learning is not done because the input pattern given cannot be classified enough. On the other hand, if designated a lot, overfitting occurs due to the unnecessary execution of operation and extravagance of memory point. So, the recognition rate is been law and the generality is fallen. Therefore, this paper suggests a method that decides the number of neural network node with feature information consisted of the parameter of learning algorithm. It excludes a node in the Pruning target, that has a maximum value among the feature value obtained and compares the average of the rest of hidden node feature value with the feature value of each hidden node, and then would like to improve the learning speed of neural network deciding the optimum structure of the multi-layer neural network as pruning the hidden node that has the feature value smaller than the average.

• Korean Journal of Materials Research
• /
• v.11 no.5
• /
• pp.339-344
• /
• 2001

An all solid-state thin film supercapacitor (TFSC) with Co$_3$O$_4$/LiPON/Co$_3$O$_4$ structure was fabricated on Pt/Ti/Si substrate using Co$_3$O$_4$ thin film electrode. Each Co$_3$O$_4$ film was grown by reactive dc reactive magnetron sputtering with increasing $O_2$/[Ar+O$_2$] ratio. Amorphous LiPON electrolyte film was deposited on Co$_3$O$_4$/Pt/Ti/Si in pure nitrogen ambient by using reactive rf magnetron sputtering. The electrochemical behavior of the Co$_3$O$_4$/LiPON/Co$_3$O$_4$ multi-layer structures exhibits a behavior of a bulk-type supercapacitor, even though much lower capacity (from 5 to 25 mF/$\textrm{cm}^2$-$\mu\textrm{m}$) than that of the bulk one. It was found that the TFSC showed a fairly constant discharge capacity with a constant current of 50 $\mu\textrm{A}/\textrm{cm}^2$ at the cut-off voltage 0-2V during 400 cycles. It is shown that the electrochemical behavior of the Co$_3$O$_4$/LiPON/Co$_3$O$_4$ TFSC is dependent upon the sputtering gas ratio. The capacity dependency of electrode films on different gas ratios was explained by different structural, electrical, and surfacical properties.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.361-368
• /
• 2014

The LPR(License plate recognition) system has been developed to efficient control for complex traffic environment and currently be used in many places. However, because of light, noise, background changes, environmental changes, damaged plate, it only works limited environment, so it is difficult to use in real-time. This paper presents a heuristic segmentation algorithm for robust to noise and illumination changes and introduce a real-time license plate recognition system using it. In first step, We detect the plate utilized Haar-like feature and Adaboost. This method is possible to rapid detection used integral image and cascade structure. Second step, we determine the type of license plate with adaptive histogram equalization, bilateral filtering for denoise and segment accurate character based on adaptive threshold, pixel projection and associated with the prior knowledge. The last step is character recognition that used histogram of oriented gradients (HOG) and multi-layer perceptron(MLP) for number recognition and support vector machine(SVM) for number and Korean character classifier respectively. The experimental results show license plate detection rate of 94.29%, license plate false alarm rate of 2.94%. In character segmentation method, character hit rate is 97.23% and character false alarm rate is 1.37%. And in character recognition, the average character recognition rate is 98.38%. Total average running time in our proposed method is 140ms. It is possible to be real-time system with efficiency and robustness.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.11
• /
• pp.1757-1763
• /
• 2010

Flywheel energy storage system (FESS) is defined as a high speed rotating flywheel system that can save surplus electric power. The FESS is proposed as an efficient energy storage system because it can accumulate a large amount of energy when it is operated at a high rotating speed and no mechanical problems are encountered. The FESS consists of a shaft, flywheel, motor/generator, bearings, and case. It is difficult to simulate rotor dynamics using common structure simulation programs because these programs are based on the 3D model and complex input rotating conditions. Therefore, in this paper, a program for the FESS based on the 2D FEM was developed. The 2D FEM can model easier than 3D, and it can present the multi-layer rotor with different material each other. Stiffness changing of the shaft caused by shrink fitting of the hub can be inputted to get clear solving results. The results obtained using the program were compared with those obtained using the common programs to determine any errors.

• Polymer(Korea)
• /
• v.38 no.6
• /
• pp.752-759
• /
• 2014

Crosslinked polyimides (PIs) were synthesized by reacting 4,4'-(hexafluoroisopropylidene)-diphthalic anhydride (6FDA) and 2,2'-bis(trifluoromethyl)benzidine (TFDB) with various ratios of the cross-linkable, end-capping agent cis-1,2,3,6-tetrahydrophthalic anhydride (CDBA) via ring-opening metathesis polymerization. Residual stress behaviors were investigated in-situ during thermal imidization of the crosslinked PI precursors using a thin film stress analyzer (TFSA) by wafer bending method. The thermal properties were investigated via differential scanning calorimetry (DSC), thermomechanical analysis (TMA), and thermogravimetric analysis (TGA). The optical properties were measured by ultraviolet-visible spectrophotometer (UV-vis) and spectrophotometry. All properties were interpreted with respect to their morphology of crosslinked networks. With increasing the amounts of the end-capping agent, the residual stress decreased from 27.9 to -1.3 MPa, exhibited ultra-low stress and high thermal properties. The minimized residual stress and enhanced thermal properties of the crosslinked PI makes them potential candidates for versatile high-density multi-layer structure applications.

• Korean Journal of Optics and Photonics
• /
• v.14 no.6
• /
• pp.669-673
• /
• 2003

We fabricated a buried-ridge waveguide laser diode (B-RWG LD) which has more advantages for obtaining lateral single mode operation on the same ridge width and for the planarization of the device surface, compared to the conventional RWG LD. In this LD, the difference of the lateral effective refractive index can be controlled by the thickness of the InGaAsP layer which is grown on the active and the p-InP layers. The InGaAsP multiple quantum well was grown on a n-InP substrate by the CBE. The buried ridge structure was formed by selective wet etchings, followed by liquid phase epitaxy methods. The fabricated LD with the ridge width of 7 ${\mu}{\textrm}{m}$ showed a linear increase of the optical power up to 20 ㎽ without any kinks and a saturated output power of more than 80 ㎽. By measuring the far field pattern, we demonstrate that LDs with the ridge widths of 5 ${\mu}{\textrm}{m}$ and 7 ${\mu}{\textrm}{m}$ were operated in a lateral single mode up to 2.7I$_{th}$ and 2.4I$_{th}$, respectively.ely.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.29-38
• /
• 2019

With the advancement of information and communication technology, tactical networks are continuously being converted to All-IP future tactical networks that integrate all application services based on Internet protocol. Futuristic tactical mesh network is built with tactical WAN (wide area network) nodes that are inter-connected by a mesh structure. In order to guarantee QoS (quality of service) of application services, tactical service mesh (TSM) is suggested as an intermediate layer between infrastructure and application layers for futuristic tactical mesh network. The tactical service mesh requires dynamic QoS monitoring and control for intelligent QoS coordination. However, legacy networking nodes used for existing tactical networks are difficult to support these functionality due to inflexible monitoring support. In order to resolve such matter, we propose a tactical mesh WAN node as a hardware/software co-designed networking node in this paper. The tactical mesh WAN node is conceptually designed to have multi-access networking interfaces and virtualized networking switches by leveraging the DANOS whitebox server/switch. In addition, we explain how to apply eBPF-based traffic monitoring to the tactical mesh WAN node and verify the traffic monitoring feasibility for supporting QoS coordination of tactical-mesh traffic.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.147-161
• /
• 2022

This study examined changes in the ecological characteristics and design characteristics of Ban's exhibition space in three representative temporary exhibition halls and three permanent exhibition halls designed by Ban Shigeru since 2000. Through the investigation of the concepts and characteristics of ecological architecture, the design characteristics of exhibition space, the analysis framework of the design characteristics of exhibition space and the design elements of ecological architecture is obtained. The analysis results show that there are big changes between the temporary exhibition space and the permanent exhibition space in terms of building scale, space composition, function, materials and technology. On the one hand, the temporary exhibition space used recyclable materials, such as paper tubes, containers to be assembled on site into a single-layer space focused on display. The assembly method was simple and the construction period was short. After the exhibition, the exhibition space were dismantled. The materials were either transported to the next display site or recycled and reused. On the other hand, the permanent exhibition space used reinforced concrete as the main structure, and used a large amount of wood and glass materials to construct a multi-layered composite cultural space that separated the exhibition space and the leisure space. In terms of ecological characteristics, the building materials of the temporary exhibition space were recycled and no industrial wastes were generated after the demolition. The permanent exhibition hall uses eco-friendly wood for the roof and walls, so it is easy to replace and repair. Both types of exhibition halls are changing ecological architecture in a more sustainable direction by saving resources and energy through natural light and ventilation.