• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1271-1279
• /
• 2020

Text region detection is a technology that detects text area in handwriting or printed documents. The detected text areas are digitized through a recognition step, which is used in various fields depending on the purpose of use. However, the detection result of the small text unit is not suitable for the industrial field. In addition, the border of tables in the document that it causes miss-detected results, which has an adverse effect on the recognition step. To solve the issues, we propose a method for detecting text region using the border information of the table. In order to utilize the border information of the table, the proposed method adjusts the flow of two decoders. Experimentally, we show improved performance using the table border pseudo label based on weak supervised learning.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.1
• /
• pp.103-111
• /
• 2021

Naju Seokdanggan, Treasure No. 49, was dismantled and reconstructed due to poor performance. During construction, the crack area was reinforced and the inclination was improved. It is necessary to analyze the stiffness changes before and after the reconstruction of these cultural properties, and to establish a database of related information. In addition, there is a need for research on a scientific non-destructive testing method capable of predicting or evaluating the reinforcing effect. In this study, a simple equation for estimating the overall stiffness of the structural system was derived from information on the elasticity coefficient and the natural frequency measured by vibration tests before and after reconstruction work, and the applicability of the equation was examined. If the stiffness of important cultural properties is regularly investigated by the suggested method, it is judged that it can be used as data to estimate the time when structural safety diagnosis is necessary or when repair or reinforcement is necessary.

• Membrane Journal
• /
• v.31 no.6
• /
• pp.456-470
• /
• 2021

In this study, polyetherimide-based hollow fiber membranes were manufactured using the NIPS (nonsolvent induced phase separation) method. THF, Ethanol, and LiNO₃ were used as additives to control the morphology of the PEI-hollow fiber membranes. Furthermore, for the development of a high hydrogen separation membrane, the spinning conditions were optimized through the characterization of SEM and gas permeance. As a result, as the content of THF increased, the hydrogen/carbon dioxide selectivity increased. However, the permeance decreased due to the trade-off relationship. When ethanol was added, a finger-like structure was shown, and when LiNO₃ was added, a sponge structure was shown. In particular, in the case of a hollow fiber membrane with an optimized PDMS coating layer, the permeance was 40 GPU and the hydrogen/carbon dioxide selectivity was 5.6.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.2
• /
• pp.71-76
• /
• 2022

Round-robin is widely used for the scheduling of large-scale parallel workloads in the computing units of GPGPU. Round-robin is easy to implement by sequentially allocating tasks to each computing unit, but the load balance between computing units is not well achieved in multi-workload environments like cloud. In this paper, we propose a new thread block scheduling policy to resolve this situation. The proposed policy manages thread blocks generated by various GPGPU workloads with multiple queues based on their computation loads and tries to maximize the resource utilization of each computing unit by selecting a thread block from the queue that can maximally utilize the remaining resources, thereby inducing load balance between computing units. Through simulation experiments under various load environments, we show that the proposed policy improves the GPGPU performance by 24.8% on average compared to Round-robin.

• Korean Journal of Plant Resources
• /
• v.35 no.2
• /
• pp.192-200
• /
• 2022

Nitrogen is the most essential macronutrient for the growth of fruit trees and is important factor determining the fruit yield. In order to produce high-quality fruits, it is necessary to supply the appropriate nitrogen fertilizer at the right time. For this, it is a prerequisite to accurately diagnose the nitrogen status of fruit trees. The fastest and most accurate way to determine the nitrogen deficiency of fruit trees is to measure the nitrogen concentration in leaves. However, it is not easy for citrus growers to measure nitrogen concentration through leaf analysis. In this study, several machine learning models were developed to classify the nitrogen deficiency based on the concentration measurement of mineral nutrients in the leaves of tangor Shiranuhi (Citrus unshiu × C. sinensis). The data analyzed from the leaves were increased to about 1,000 training dataset through the bootstrapping method and used to train the models. As a result of testing each model, gradient boosting model showed the best classification performance with an accuracy of 0.971.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.57 no.4
• /
• pp.271-282
• /
• 2021

This study aims to understand the opening efficiency of the finless porpoise escape guide net by the type of extension net that is the part to which the escape guide net is attached in stow net. To this end, extension nets were manufactured in full size and the net mouth area and towing tension were investigated according to the towing speed (0.2, 0.4, 0.6 and 0.8 m/s) and the type of extension net (25 mm net and raschel net) in the water tank. As a result, the net mouth area of the guide net was larger when the raschel net was used for the extension net than when the 25 mm net was used under all towing speeds. In addition, regardless of the type of extension net, the net mouth area reached about 80% of the maximum value at a towing speed of 0.4 m/s. In the field, fishing operation of stow net is performed only when the current speed is above 0.4 m/s. Therefore, the speed of 0.4 m/s was confirmed as a meaningful value to determine whether it is possible to operate. As a result of analyzing the relationship between the net mouth area of the guide net and the towing tension, it was confirmed that the difference in the net mouth area of the guide net according to the type of the extension net was due to the difference in the solidity ratio.

• Journal of Advanced Navigation Technology
• /
• v.26 no.1
• /
• pp.9-14
• /
• 2022

In this paper we investigate the advantages when the GPS Antenna is installed on the rear missile body. In conventional design the GPS antenna locates on the front part of missile. However it causes degraded GPS positioning performance since the missile body blocks the GPS signals. This paper proposes the GPS array antenna design which locates on the rear part of missile body and has the tilted antenna patches to achieve the maximum area of receiving GPS signals. We simulate LOS region of receiving signals and conducted anechoic chamber test to define the effective signal receiving region. And we conduct field test and flight test to check out the enhancement of signal receiving area.

• Journal of the Korea Society for Simulation
• /
• v.31 no.2
• /
• pp.11-20
• /
• 2022

There is a critical need for AI assistance in guard operations of Army base perimeters, which is exacerbated by changes in the national defense and security environment such as force reduction. In addition, the possibility for human error inherent to perimeter guard operations attests to the need for an innovative revamp of current systems. The purpose of this study is to propose a real-time object detection AI tailored to military CCTV surveillance with three unique characteristics. First, training data suitable for situations in which relatively small objects must be recognized is used due to the characteristics of military CCTV. Second, we utilize a data augmentation algorithm suited for military context applied in the data preparation step. Third, a noise reduction algorithm is applied to account for military-specific situations, such as camouflaged targets and unfavorable weather conditions. The proposed system has been field-tested in a real-world setting, and its performance has been verified.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.4
• /
• pp.40-47
• /
• 2022

The present study aimed to examine the effectiveness of different techniques for controlling the diagonal cracks at the corners of openings on the strength, deformation, and crack propagation in reinforced concrete walls. The crack control strip proposed in this study, the conventional diagonal steel reinforcing bars, and stress-dispersion curved plates were investigated for controlling the diagonal cracks at the opening corners. An additional crack self-healing function was also considered for the crack control strip. To evaluate the volume change ratio and crack width propagation around the opening, downsized wall specimens with a opening were tested under the diagonal shear force at the opening corner. Test result showed that the proposed crack control strip was more effective in reducing the volume change and controlling the crack width around the opening when compared to the conventional previous methods. The crack control strip with crack healing feature displayed the superior performance in improving the strength of the wall and reducing the crack width while healing cracks occurred in the previous tests.

• Journal of Aerospace System Engineering
• /
• v.16 no.4
• /
• pp.77-87
• /
• 2022

The Precision Aerial Delivery System is an instrument designed to improve the poor landing accuracy of aerial delivery system with conventional circular parachutes, and is equipped with an Airborne Guidance Unit to safely transport supplies to the desired destination. Currently, the landing accuracy of the PADS product is reported as CEP₅₀ 100m and also differs significantly, depending on the actual topography and weather environment. In this study, HILS was constructed based on the 6DOF nonlinear modeling of PADS to analyze the maneuver characteristics of Ram Air Parachute under wind environments. By using the new algorithm a precision soft landing algorithm including Energy Management and Final Approach is designed. HILS results show that it is possible to achieve a precise soft landing within CEP₅₀ 40m, and it can be exploited to develop an actual PADS drop test.