• Journal of Bio-Environment Control
• /
• v.32 no.4
• /
• pp.434-441
• /
• 2023

Determining the size or area of a plant's leaves is an important factor in predicting plant growth and improving the productivity of indoor farms. In this study, we developed a convolutional neural network (CNN)-based model to accurately predict the length and width of lettuce leaves using photographs of the leaves. A callback function was applied to overcome data limitations and overfitting problems, and K-fold cross-validation was used to improve the generalization ability of the model. In addition, ImageDataGenerator function was used to increase the diversity of training data through data augmentation. To compare model performance, we evaluated pre-trained models such as VGG16, Resnet152, and NASNetMobile. As a result, NASNetMobile showed the highest performance, especially in width prediction, with an R_squared value of 0.9436, and RMSE of 0.5659. In length prediction, the R_squared value was 0.9537, and RMSE of 0.8713. The optimized model adopted the NASNetMobile architecture, the RMSprop optimization tool, the MSE loss functions, and the ELU activation functions. The training time of the model averaged 73 minutes per Epoch, and it took the model an average of 0.29 seconds to process a single lettuce leaf photo. In this study, we developed a CNN-based model to predict the leaf length and leaf width of plants in indoor farms, which is expected to enable rapid and accurate assessment of plant growth status by simply taking images. It is also expected to contribute to increasing the productivity and resource efficiency of farms by taking appropriate agricultural measures such as adjusting nutrient solution in real time.

• Journal of Society of Preventive Korean Medicine
• /
• v.19 no.1
• /
• pp.109-116
• /
• 2015

Objective : Solar ultraviolet (UV) light can cause photoaging of human skin. Many researchers have focused on effective prevention to mitigate the aging process. This study was aimed to investigate anti-wrinkle effects of pomegranate concentration solution (PCS) using photoaged hairless mouse model. Method : To clarify the protective effect of PCS against UVB-induced photo-damage, water capacity was measured with transepidermal water loss (TEWL) in SKH-1 hairless mice. In addition, image of skin replicas was analyzed. Results : Our results showed that the PCS treatment protects skin against UVB-induced photoaging, based on the parameters including moisture capacity and TEWL. According to visual assessment of skin replica, application of 1 ml/kg PCS inhibited UV-induced wrinkle formation in mice skin as compared to the vehicle-applied control mice. Conclusion : Taken together, these results indicated that PCS could improve skin wrinkle formation induced by UVB irradiation in SHK-1 hairless mice. PCS could be applied as an anti-wrinkle agent.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.10
• /
• pp.67-78
• /
• 2003

As optical network technology advances and high bandwidth Internet is demanded for the exponential growth of internet traffic volumes, the Dense-Wavelength Division Multiplexing (DWDM) networks have been widely accepted as a promising approach to the Next Generation Optical Internet (NGOI) backbone networks for nation wide or global coverage. Important issues in the NGOI based on DWDM networks are the Routing and Wavelength Assignment(RWA) problem and survivability. Especially, fault/attack detection, localization and recovery schemes in All Optical Transport Network(AOTN) is one of the most important issues because a short service disruption in DWDM networks carrying extremely high data rates causes loss of vast traffic volumes. In this paper, we suggest a fault/attack management model for NGOI through analyzing fault/attack vulnerability of various optical backbone network devices and propose fault/attack recovery procedure considering Extended-LMP(Link Management Protocol) and RSVP-TE+(Resource Reservation Protocol-Traffic Engineering) as control protocols in IP/GMPLS over DWDM.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.2
• /
• pp.9-14
• /
• 2018

The function of gas springs is based on the compression of a gas. They are used in a wide variety of industries, and demand for them is increasing. Gas springs can be divided into compression and extension springs. Extension springs have not been studied much in relation to control of the piston speed, unlike compression springs. In this study, the magnitude of the piston rebound pressure was theoretically predicted by calculating the pressure loss in a double-cylinder extension gas spring. Numerical simulations of the piston behavior were carried out for small and large amounts of friction between the piston and the cylinder. FLUENT was used for the simulation with a 6-DOF model and UDF to simulate the behavior of the piston. The calculation regions of the front and rear of the piston were separated, and different types of grids were generated in the regions to implement a dynamic mesh using only a layering method. The results show that the piston returns with the target speed in both cases. However, the patterns of the piston behavior reaching the final speed are different.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.9A
• /
• pp.1372-1382
• /
• 1999

The major source of errors in high-speed networks such as Broadband ISDN(B-lSDN) is buffer overflow during congested conditions. These congestion errors are the dominant sources of errors in 1high-speed networks and result in cell losses. Conventional communication protocols use error detection and retransmission to deal with lost packets and transmission errors. However, these conventional ARQ(Automatic Repeat Request) methods are not suitable for the high-speed networks since the transmission delay due to retransmissions becomes significantly large. As an alternative, we have presented a method to recover consecutive cell losses using forward error correction(FEC) in ATM(Asynchronous Transfer Mode)networks to reduce the problem. The performance estimation based on the cell discard process model has showed our method can reduce the cell loss rate substantially. Also, the performance estimations in ATM networks by interleaving and IP multicast service are discussed.

• Journal of Korea Water Resources Association
• /
• v.48 no.8
• /
• pp.647-657
• /
• 2015

This study assessed the water use vulnerability for 12 basins of South Korea. The annual runoff of 12 basins are derived using a Soil and Water Assessment Tool (SWAT) and the calculated runoff per unit area and population are compared with each basin. The 18 indicators are selected in order to assess the vulnerability. Those are classified by aspects of demand, loss and supply of water use. Their weighting values used Entropy method to determine objective weights. To quantitatively assess the water use vulnerability, the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) based on multi-criteria decision making are applied. The results show that the water availability vulnerability of Hyeongsan River has the highest value followed by Sapgyo River; Dongjin River; Seomjin River; Anseong River; Mangyung River; Nakdong River; Tamjin River; Youngsan River, Geum River; Taehwa River; and Han River. The result of this study has a capability to provide references for the index deveopment of climate change vulnerability assessment.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.605-609
• /
• 2010

기상변화와 지구온난화로 인해 국지성 호우의 강도와 빈도가 늘어나고 있으며 이로 인해 소양강, 도암댐, 임하댐 유역의 탁수 문제 등, 토양 유실에 관한 문제가 심각해지고 있다. 정확한 토양 유실 모의를 위하여 지난 수 십 년간 Universal Soil Loss Equation(USLE) 등의 모형이 사용되었지만 이러한 모형들에 관한 연구 중 강한 집중 호우에 의해 발생하는 걸리 침식(Gully Erosion)을 적용한 경우는 많지 않다. 이에 본 연구에서는 걸리 침식을 고려한 토양 유실량 및 유사량 산정을 위하여 입력자료가 간단하고 ArcView GIS를 기반으로 융합이 가능한 Sediment Assessment Tool for Effective Erosion Control (SATEEC) system, nLS, Unit Stream Power-based Erosion/Deposition (USPED) 연계 모형을 개발하여 강원도 양구군 해안면 유역에 적용하였다. 기존 SATEEC system에서는 강우 시 유역에서 발생하는 면상 침식(Sheet Erosion), 세류 침식(Rill Erosion)의 모의만이 가능하였지만, 본 연구에서 개발한 연계모형에서는 nLS 모형을 이용한 걸리 헤드 발생 지역 선정과 USPED 모형을 이용한 걸리 발생 지역에서의 토양 유실량 산정이 가능하기 때문에, 걸리 침식을 고려한 토양 유실량 산정이 가능하다. 연계 모형의 모의 결과 해안면 유역의 최종 유출구에서 발생하는 평균 유사량은 101,933 ton/year 로 산정 되었다. 토양 유실량과 유사량을 모의함에 있어, 면상, 세류, 걸리 침식을 종합적으로 고려해야 실제 지형에서 발생하는 토양 유실량 및 유사량을 좀 더 정확하게 예측할 수 있을 것이며, 본 연구에서 개발된 연계 모형을 이용한다면 실제 유역에서 발생하는 여러 형태의 토양 유실을 모의 할 수 있을 것이라 판단된다.

• Journal of Aerospace System Engineering
• /
• v.18 no.3
• /
• pp.48-55
• /
• 2024

In recent years, as the commercialization of unmanned aerial vehicles (UAVs) has been actively promoted, much attention has been focused on developing a technology to ensure the safety of UAVs. In general, the UAV has the potential to enter an uncontrollable state caused by sudden maneuvers, disturbances, and pilot error. To prevent entering an uncontrolled situation, it is essential to predict the flight state of the UAV. In this paper, we propose a flight state prediction technique based on an improved CNN-LSTM hybrid mode to enhance the flight state prediction performance. Simulation results show that the proposed prediction technique offers better state prediction performance than the existing prediction technique, and can be operated in real-time in an on-board environment.

• Journal of Navigation and Port Research
• /
• v.44 no.4
• /
• pp.305-311
• /
• 2020

Rising sea levels along the coast from global warming causes the increase of wave energy along the coast. This rise in sea levels results in relatively deep water levels, which would incur the loss of sand that had not occurred in the past from erosion in coastal areas. Generally, it has been challenging to protect against coastal erosion, and the slope, cross-sectional shape, and materials are selected for the site conditions depending on the change in external forces. However, the application of counter measures based on insufficient understanding of the phenomenon is causing various damage, indicating the need for technological development and converging technologies to improve credibility. In this study, we developed eco-friendly permeable biopolymer concrete blocks to control the coastal erosion by using the Bio-Coast, an effective porous structure that mitigates the destructive erosion caused by the rising sea levels. The hexagonal design of Bio-Coast was derived from the honeycomb, columnar joints, and clover, which are durable and stable structures in nature, and the design was changed to apply bumps on the Bio-Coast filling in the form of a clover to reduce wave overtopping and run-up. Applying the field condition of beaches on the east coast of Korea, the block weight and size were decided and the prototype blocks were manufactured and are ready for field placement. In particular, it is intended to protect coastal areas from destructive erosion by natural and artificial external forces, and to extend the design to river,s lakes, and natural walking trails, to improve the efficiency of quality control and process control through the use of blocks.

• Molecules and Cells
• /
• v.42 no.6
• /
• pp.480-494
• /
• 2019

Aggregates of disease-causing proteins dysregulate cellular functions, thereby causing neuronal cell loss in diverse neurodegenerative diseases. Although many in vitro or in vivo studies of protein aggregate inhibitors have been performed, a therapeutic strategy to control aggregate toxicity has not been earnestly pursued, partly due to the limitations of available aggregate models. In this study, we established a tetracycline (Tet)-inducible nuclear aggregate (${\beta}23$) expression model to screen potential lead compounds inhibiting ${\beta}23$-induced toxicity. High-throughput screening identified several natural compounds as nuclear ${\beta}23$ inhibitors, including peucedanocoumarin III (PCIII). Interestingly, PCIII accelerates disaggregation and proteasomal clearance of both nuclear and cytosolic ${\beta}23$ aggregates and protects SH-SY5Y cells from toxicity induced by ${\beta}23$ expression. Of translational relevance, PCIII disassembled fibrils and enhanced clearance of cytosolic and nuclear protein aggregates in cellular models of huntingtin and ${\alpha}$-synuclein aggregation. Moreover, cellular toxicity was diminished with PCIII treatment for polyglutamine (PolyQ)-huntingtin expression and ${\alpha}$-synuclein expression in conjunction with 6-hydroxydopamine (6-OHDA) treatment. Importantly, PCIII not only inhibited ${\alpha}$-synuclein aggregation but also disaggregated preformed ${\alpha}$-synuclein fibrils in vitro. Taken together, our results suggest that a Tet-Off ${\beta}23$ cell model could serve as a robust platform for screening effective lead compounds inhibiting nuclear or cytosolic protein aggregates. Brain-permeable PCIII or its derivatives could be beneficial for eliminating established protein aggregates.