• Title/Summary/Keyword: width control

Search Result 2,405, Processing Time 0.032 seconds

Comparison of Convolutional Neural Network (CNN) Models for Lettuce Leaf Width and Length Prediction (상추잎 너비와 길이 예측을 위한 합성곱 신경망 모델 비교)

  • Ji Su Song;Dong Suk Kim;Hyo Sung Kim;Eun Ji Jung;Hyun Jung Hwang;Jaesung Park
    • 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.

OVERVIEW OF KSTAR INTEGRATED CONTROL SYSTEM

  • Park, Mi-Kyung;Kim, Kuk-Hee;Lee, Tae-Gu;Kim, Myung-Kyu;Hong, Jae-Sic;Baek, Sul-Hee;Lee, Sang-Il;Park, Jin-Seop;Chu, Yong;Kim, Young-Ok;Hahn, Sang-Hee;Oh, Yeong-Kook;Bak, Joo-Shik
    • Nuclear Engineering and Technology
    • /
    • v.40 no.6
    • /
    • pp.451-458
    • /
    • 2008
  • After more than 10 years construction, KSTAR (Korea Superconducting Tokamak Advanced Research) had finally completed its assembly in June 2007, and then achieved the goal of first-plasma in July 2008 through the four month's commissioning. KSTAR was constructed with fully superconducting magnets with material of $Nb_3Sn$ and NbTi, and their operation temperatures are maintained below 4.5K by the help of Helium Refrigerator System. During the first-plasma operation, plasmas of maximum current of 133kA and maximum pulse width of 865ms were obtained. The KSTAR Integrated Control System (KICS) has successfully fulfilled its missions of surveillance, device operation, machine protection interlock, and data acquisition and management. These and more were all KSTAR commissioning requirements. For reliable and safe operation of KSTAR, 17 local control systems were developed. Those systems must be integrated into the logically single control system, and operate regardless of their platforms and location installed. In order to meet these requirements, KICS was developed as a network-based distributed system and adopted a new framework, named as EPICS (Experimental Physics and Industrial Control System). Also, KICS has some features in KSTAR operation. It performs not only 24 hour continuous plant operation, but the shot-based real-time feedback control by exchanging the initiatives of operation between a central controller and a plasma control system in accordance with the operation sequence. For the diagnosis and analysis of plasma, 11 types of diagnostic system were implemented in KSTAR, and the acquired data from them were archived using MDSpius (Model Driven System), which is widely used in data management of fusion control systems. This paper will cover the design and implementation of the KSTAR integrated control system and the data management and visualization systems. Commissioning results will be introduced in brief.

A Study on the Ship Channel Design Method using Variable Bumper Area Model (I) (가변범퍼영역모델을 이용한 항로설계기법(I))

  • Jeong Dae-Deug;Lee Joong-Woo
    • Proceedings of the Korean Institute of Navigation and Port Research Conference
    • /
    • 2004.11a
    • /
    • pp.169-174
    • /
    • 2004
  • To design ship channel is one of important factors for planning and developing a port. In most case, the core factors for designing ship channel are the layout and width of dvnnel provided the net underkeel clearance is assessed as safety. In this study, Variable Bumper Area(VBA) model is applied to design and assess ship channel. This model reflects ship's principle dimension, ship domain theory, ship speed, conning officer's ship handling skill and experience and all external forces which cause leeway, set and drift and the change of ship maneuvering characteristics. Full Mission Ship Handling Simulator is used to analyze ship dynamic data according to conning officer's ship control, external forces, etc. This model uses Domain-index for assessing the efficiency and safety of the channel. The proposed model is applied to Ulsan new port plan which has a channel width of 1.5 times the length if the largest vessel, a radius if 5 times the length of the largest vessel in a curve of 57 degree centerline angle and SBM facility adjacent to the lateral edge if channel. The result of this study shows tint the width and radius of channel curve are suitable for the target ship but the difficulty of ship handling is caused by the large course change and SBM located in the vicinity if channel.

  • PDF

Design of PWM-Based Photo Irradiation System for Acne Treatment (여드름 치료를 위한 PWM 기반 광 조사 시스템 설계)

  • Kim, Chang-Su;Lim, Hyun-Soo
    • Journal of the Korean Society of Radiology
    • /
    • v.6 no.3
    • /
    • pp.207-215
    • /
    • 2012
  • As one of photo dynamic therapies, the existing LED photo irradiation method with 635 nm continuous wave has most frequently been used for acne treatment, it suffered from a low energy efficiency and generation of a large amount of heat in tissues requiring improvement measures. In this thesis, a LED photo irradiation system for acne treatment has been designed using PWM(Pulse Width Modulation) mode to enhance the energy efficiency and prevent thermal destruction in tissues. System configuration consisting largely of timer module, PWM module, and photo transfer device has been designed with the use of 1 W LED at a wavelength of 660 nm for the photo transfer device to increase skin penetration depth for treatment of acne. Frequency and wave form generated by using PWM control was verified along with confirmation of output energy of 660 nm LED and surface temperatures of tissues, followed by evaluation of stable energy outputs and stability of tissues. The results indicated that whereas power loss was high and thermal destruction in tissues was exhibited when C.W mode was used to obtain the optical energy of 1 W LED at a wavelength of 660 nm for acne treatment, realization of PWM mode allowed lowering of power consumption for LED through pulse width modulation, and no occurrence of thermal destruction in tissues, suggesting that PWM mode is safer and more effective for treatment of acne than C.W mode.

A study on the laser surface hardening of SM 45C steel (SM 45C강의 레이저 표면경화처리에 관한 연구)

  • 나석주;김성도;이건이;김태균
    • Transactions of the Korean Society of Mechanical Engineers
    • /
    • v.11 no.1
    • /
    • pp.53-62
    • /
    • 1987
  • High power lasers provide a controllable and precise energy source in surface transformation hardening. A careful control of the process is needed in order that the surface layer of the material reaches the austenizing temperature, but that it does not melt. In order to achieve this the results of theoretical and experimental studies on the laser surface hardening of a medium carbon steel are described. A two-dimensional computer program, which can be used generally for the determination of transient temperature distributions in welding and heat treatment, was established on the basis of the finite element method. For the confirmation of the accuracy of the numerical analysis, a medium carbon steel (SM 45C) of 5mm thickness was heat-treated with a 1kW CW CO$_{2}$ laser machine, while the traverse speed and the distance from the focal point (defocused distance) were varied. Experimental and numerical results showed a similar tendency in correlations between the hardened zone shape and the process parameters. With increasing beam spot diameter the width and depth of the hardened zone increased for relatively small beam spot diameters, but decreased rapidly after reaching the maximum value, while with increasing traverse speed the width and depth of the hardened zone decreased monotonously. Too small beam spot diameters are to be avoided, since the surface melting would lower the surface hardness and produce an uneven surface which may be unacceptable because of the possible requirement for subsequent machining. It could be observed that for a given traverse speed and laser power input there exists a optimal range of the beam spot diameter, which produce a large width of the hardened zone but no melting on the surface.

Characteristics of Fluid Force Reduction for Two Different Square Prisms in a Tandem Arrangement (직렬배열에 놓인 크기가 다른 정방형주의 유체력 저감특성)

  • Ro, Ki Deok;Kang, Chang Whan;Park, Kwon Ho
    • Transactions of the Korean Society of Mechanical Engineers B
    • /
    • v.41 no.7
    • /
    • pp.435-443
    • /
    • 2017
  • The Characteristics of the flowfields of a square prism having a small square prism were investigated by measuring of lift and drag on the square prism and visualizing the flowfield using PIV. The experimental parameters were the width ratios(H/B=0.2~0.6) of small square prisms to the prism width and the gap ratios (G/B=0~3) between the prism and the small square prism. The drag reduction rate of the square prism initially increased and then decreased with the G/B ratio for the same H/B ratio, and increased with the H/B ratio for the same G/B ratio. The maximum drag reduction rate of 98.0% was observed at H/B=0.6 and G/B=1.0. The lift reduction rate of the square prism was not affected by the width and gap ratios; the total average value was approximately 66.5%. In case of a square prism having a small square prism, the stagnation regions were represented in the upstream and downstream sides of the square prism.

A HISTOLOGIC STUDY OF INITIAL CHANCE AND REPAIR OF TOOTH AND PERIODONTAL TISSUE IN EXTRUSION OF YOUNG ADULT DOGS (유성견 소구치 정출시 치아 및 치주 조직의 초기 조직학적 변화 및 재생에 관한 연구)

  • Yoon, Byung-sun;Cha, Kyung-Suk;Lee, Jin-Woo
    • The korean journal of orthodontics
    • /
    • v.28 no.3 s.68
    • /
    • pp.419-429
    • /
    • 1998
  • This study was carried out in order to study early histologic changes and repair reaction appling to extrusive force for 3rd premolar of adult dogs. After 1 week of extrusive force with elastic chain, one of dogs was sacrified and after 3 weeks retention period, another dog was sacrified. The paraffin sections of samples were stained with Hematoxylin - Eosin and Masson's Trichrome and were examed by light microscopy . The obtained results as follows 1. In Hematoxylin - Eosin and Masson Trichrome stain of control group , the periodontal ligament width was constant from apical third to cervical third of the root and periodontal fiber arrangement was horizontal or oblique in cervical third. oblique in middle third, oblique in apical third of root. in alveolar bone, smooth appearance was shown 2. In Group 1, all periodontal fiber arrangement was oblique toward tooth, and the periodontal ligament width increased Partially PDL was ruptured in apex. In MT stain, immature bone formation was seen at alveolar crest area. Active bone formation was observed along the one side of alveolus, and apical portion of pulp was involved with blood vessel rupture , vacuolization of pulp tissue and hyperemia 3. In Group 2, most periodontal ligament arrangement and PDL width was repaired and fiber density increased. In MT stain, mineralization of immature bone on the alveolar crest was progressed. In pulp, vacuole and hyperemia was diminished and fibrotic change was diminished 4. After 3 week periodontal ligament has more repair ability than pulp tissue. pulp was involved with vacuolization and fibrosis, so it takes more time for repair.

  • PDF

A Study on the Ship Channel Design Method using Variable Bumper Area Model (I) (가변범퍼영역모델을 이용한 항로설계기법(I))

  • Jeong Dae-Deug;Lee Joong-Woo
    • Journal of Navigation and Port Research
    • /
    • v.29 no.1 s.97
    • /
    • pp.9-15
    • /
    • 2005
  • To design ship channel is one of important factors for planning and developing a port. In most case, the core factors for designing ship channel are the layout and width of channel provided the net underkeel clearance is secured to be safe enough to pass. In this study, Variable Bumper Area(VBA) model is applied to design and assess ship channel. This model reflects ship's particular, ship domain theory, ship speed and mariner's ship handling skill and experience, especially external forces which cause leeway, set and drift and the change of ship maneuvering characteristics. A real time, full mission shiphandling simulator is used to analyze ship dynamic data according to mariner's ship control, external forces, ete. This model defines Domain degree and Domain-index for assessing the efficiency and safety of the channel. The proposed model is applied to Ulsan new port plan which has a channel width of 1.5 times the length of the largest vessel, a radius of 5 times the length of the largest vessel in a curve of 57 degree centerline angle and SBM facility adjacent to the lateral edge of channel. The result of this study shows that the width of the channel and radius of channel curve are suitable for the target ship but the difficulty of ship handling is caused by the large course change and SBM located in the vicinity of channel.

Change of Weeds Occurrence, Early Growth and Yield of Soybean at Simultaneous Planting with Rye as Living Mulch (초생피복용 호밀과 동시파종 시 잡초발생, 콩의 초기생육 및 수량 변화)

  • Seo, Jong-Ho;Moon, Jung-Kyung;Kwon, Young-Up;Ku, Ja-Hwan;Kim, Si-Ju
    • Weed & Turfgrass Science
    • /
    • v.2 no.3
    • /
    • pp.236-241
    • /
    • 2013
  • Introduction of rye living mulch in soybean production is important for labor-saving and reduction of herbicide usage for weeding by weed suppression and for soil conservation by mulching of rye. Soybean and rye were row-planted and broadcasted simultaneously at different planting times (May 15, May 25, June 5) and row widths (35 and 70 cm) in 2010, different soybean cultivars (Daepoong, Singi) and planting times (May 15 and June 1) in 2011, respectively, and investigated weed occurrence, early growth and yield of soybean. Acalypha australis, which is known to herbicide-resistant weed, could be controlled ecologically by rye living mulch. Occurrence of Acalypha australis was controlled effectively also by mixture of alachlor and linulon at no mulch in 2011. Early growth amount of soybean plant per area was increased by narrow row width (35 cm) at rye living mulch, which was helpful in the control of weeds, but grain yield of soybean with narrow row was decreased compared to conventional row width (70 cm) at the planting in early June. It is concluded that soybean planting as row width 70 cm in early June is proper at simultaneous planting with rye.

Riparian Connectivity Assessment Using Species Distribution Model of Fish Assembly (어류군집의 종분포모형을 이용한 수변지역 연결성 평가)

  • Jeong, Seung Gyu;Lee, Dong Kun;Ryu, Ji Eun
    • Journal of Korean Society for Geospatial Information Science
    • /
    • v.23 no.2
    • /
    • pp.17-26
    • /
    • 2015
  • River corridors facilitate dispersal and movement and prevent local extinction of species. As a result of stream restoration projects, which include installation of waterfront and flood control structures, the number of animals, which rely on river corridor, is decreasing. For the study, factors affecting fish assembly were extracted by a species distribution model with the fish data collected from the Seom River in Hoengseong County and City of Wonju, Ganwon Province, Korea between March to October 2013. The riparian connectivity was assessed using species richness and rarity. According to result of the field survey, there were 38 species and 7,061 individuals for fish. The analysis suggests the following. Firstly, factors affecting fish richness in species distribution model results are shown to be velocity, riffle, riparian width, and water width. The accuracy of the model proves to be suitable with the correlation coefficient of 0.83 and MAPE of 19.2%. Secondly, the low rarity area is shown to be straight streams in Jeon river near to Hongseong County and the high rarity area to be streams with large width, existing alluvial area at channel junction between Jeon river and Seom river. Thirdly, according to connectivity results, areas where weirs are installed or riparian buffer area is removed showed low connectivity. The areas where farmland near riparian and forest areas showed high connectivity. The results of this study can be utilized to improve current facilities and enhance connectivity as a restoration guide.