• Title/Summary/Keyword: pre-prediction

Search Result 622, Processing Time 0.024 seconds

A Quality Prediction Model for Ginseng Sprouts based on CNN (CNN을 활용한 새싹삼의 품질 예측 모델 개발)

  • Lee, Chung-Gu;Jeong, Seok-Bong
    • Journal of the Korea Society for Simulation
    • /
    • v.30 no.2
    • /
    • pp.41-48
    • /
    • 2021
  • As the rural population continues to decline and aging, the improvement of agricultural productivity is becoming more important. Early prediction of crop quality can play an important role in improving agricultural productivity and profitability. Although many researches have been conducted recently to classify diseases and predict crop yield using CNN based deep learning and transfer learning technology, there are few studies which predict postharvest crop quality early in the planting stage. In this study, a early quality prediction model is proposed for sprout ginseng, which is drawing attention as a healthy functional foods. For this end, we took pictures of ginseng seedlings in the planting stage and cultivated them through hydroponic cultivation. After harvest, quality data were labeled by classifying the quality of ginseng sprout. With this data, we build early quality prediction models using several pre-trained CNN models through transfer learning technology. And we compare the prediction performance such as learning period and accuracy between each model. The results show more than 80% prediction accuracy in all proposed models, especially ResNet152V2 based model shows the highest accuracy. Through this study, it is expected that it will be able to contribute to production and profitability by automating the existing seedling screening works, which primarily rely on manpower.

The Difference of Predictor of Bone Mineral Density in Pre and Postmenopausal Women (폐경에 따른 골밀도 예측인자의 차이)

  • Kim, Mi-Young;Kim, Hwa-Sun
    • Journal of radiological science and technology
    • /
    • v.34 no.3
    • /
    • pp.195-201
    • /
    • 2011
  • We studied the relationship between prediction parameters and bone mineral density for pre-and-post menopausal women. We measured BMI%Fat by BIA, blood pressure and lipid profiles for 483 adult women who are in NPO state. SBP, TC, TG, LDL have significant statistical value in the postmenopause women group and postmenopause woman. The value of postmenopause women of these parameters are lower than premenopause woman. BMD has the most strongest relationship with LBM. The BMD and LDL level of postmenopause women have statistically negative relationship. The results show that for the premenopause cases, weight, BF, and HDL level were the major factors which affect the BMD. For postmenopause cases, however, weight, age, and LDL level turned out to be the most significant factors.

Three Dimensional Solidification Analysis in Large Steel Castings by Modified Finite Difference Method (개량차분법에 의한 대형주강품의 3차원 응고해석)

  • Yoo, Seung-Mog;Lee, Doo-Ho;Kim, Jong-Ki;So, Chan-Young;Hong, Chun-Pyo
    • Journal of Korea Foundry Society
    • /
    • v.11 no.1
    • /
    • pp.54-62
    • /
    • 1991
  • A computer program which consists of pre-processor, main solidification simulator and post-processor has been developed for three dimensional solidification analysis of steel castings. The pre-processor is used for mesh generation in a small personal computing system. The modified finite difference method is adopted for the main solidification simulation algorithm. The post -processor graphically presents the simulation results and shows the formation of shrinkage defects. Several experiments on large steel castings in sand mold were carried out. The temperature variations in casting and mold with time are measured experimentally, and the results are compared with calculation results. Several numerical examples for the prediction of shrinkage cavity in large steel casting of SC42 and SCNCrM2 alloys are compared with experimental results. The effect of sleeve and chills on solidification patterns are also studied. Formation of shrinkage defects for the three cases of experimental castings are relatively well predicted by present model.

  • PDF

Analytical Methodology and Design Consideration of Advanced Test Structure for the Micromechanical Characteristics of MEMS device (초소형 박막구조물의 기계적 특성 평가소자 설계 및 분석 기법)

  • Lee, Se-Ho;Park, Byung-Woo;kwon, Dong-Il
    • Proceedings of the KIEE Conference
    • /
    • 1998.11c
    • /
    • pp.1010-1013
    • /
    • 1998
  • In micromechanical system (MEMS) such as microactuators. thin film has been widely used as structural material. MEMS materials have difference with bulk in terms of mechanical properties. So, we design the advanced test structure for micromechanical properties of MEMS. The designed structure includes the newly developed pre-crack and it is driven by electrostatic force. To measure the fracture toughness, the pre-crack formation in the test structure is developed with conventional etching process. The advanced test structure is fabricated by application of semiconductor technology. After this, we propose analytical methodology to evaluate the fracture toughness and fatigue properties through a prediction of crack behavior from the variations of stiffness and frequency. Additionally, life time of a mirror plane used in DVD(Digital Video Disk) is measured as a function of capacitance and applied voltage under the accelerated conditions. Ultimately, we propose the method to evaluate the micromechanical reliabilities of the MEMS materials using the advanced test structure.

  • PDF

Three Dimensional Solidification Analysis in Automotive Cast Piston (자동차용 피스톤 주물의 3차원 응고해석)

  • Kim, Ji-Joon;Kim, Jin-Soo;Ryu, Gwan-Ho;Choi, Jeong-Kil;Lee, Zin-Hyoung;Hong, Chun-Pyo
    • Journal of Korea Foundry Society
    • /
    • v.13 no.3
    • /
    • pp.268-275
    • /
    • 1993
  • In gravity die casting, die cooling systems are frequently employed with water cooling to remove the heat of the solidifying metal. Thermal modeling is an important technique in mold design for improving the productivity of the process. Computer simulation system which consists of pre-processor, main solidification simulator and post-processor has been developed for three dimensional solidification analysis of cyclic gravity die casting. The pre-processor is used for mesh generation in a PC system. The modified finite difference method is adopted for the main solidification simulation algorithm during all the casting cycles. The post-processor graphically presents the simulation results. Several experiments in automotive cast piston were carried out. The temperature variations in casting and mold with time are measured experimentally, and the results are compared with calculation results. The effects of cycle number on solidification pattern are also studied. Several experimental results for the prediction of shrinkage defects are compared with calculated results.

  • PDF

Adaptive Pre-/Post-Filters for NRT-Based Stereoscopic Video Coding

  • Lee, Byung-Tak;Lee, BongHo;Choi, Haechul;Kim, Jin-Soo;Yun, Kugjin;Cheong, Won-Sik;Kim, Jae-Gon
    • ETRI Journal
    • /
    • v.34 no.5
    • /
    • pp.666-673
    • /
    • 2012
  • Non-real-time delivery of stereoscopic video has been considered as a service scenario for 3DTV to overcome the limited bandwidth in the terrestrial digital television system. A hybrid codec combining MPEG-2 and H.264/AVC has been suggested for the compression of stereoscopic video for 3DTV. In this paper, we propose a stereoscopic video coding scheme using adaptive pre-/post-filters (APPF) to improve the quality of 3D video while retaining compatibility with legacy video coding standards. The APPF are applied adaptively to blocks of various sizes determined by the macroblock coding mode and reference frame index. Experiment results show that the proposed method achieves up to 24.86% bit rate savings relative to a hybrid codec of MPEG-2 and H.264/AVC including the inter-view prediction.

Pre-stress Effect of Geosynthetics-reinforced Soil Structure (토목섬유로 보강된 구조물의 프리스트레스효과)

  • Kim Eun-Ra;Kang Ho-Keun
    • Journal of the Korean Geotechnical Society
    • /
    • v.21 no.6
    • /
    • pp.53-65
    • /
    • 2005
  • This paper presented a mechanism of the soil structure reinforced by geosynthetics, in which the reinforcing mechanism is treated as the effect arising from the reinforcement process to prevent the dilative deformation of soil under shearing. A full-scale in-situ model test was carried out by introducing the prestress method to enhance the geosynthetic-reinforcement, and the prestress effect through the FEM is also examined. The elasto-plastic model and the initial parameters needed in the FEM are presented. Moreover, the theoretical prediction is compared with the experimental results, which were obtained by a full-scale in-situ model test.

A Pre-Visualization Method for FDM 3D Printing Based on Perlin Noise (FDM 3D 프린팅을 위한 Perlin 노이즈 기반 사전 시각화 기법)

  • Lim, Jae-Gwang;Jang, Seung-Ho;Hong, Jeong-Mo
    • Korean Journal of Computational Design and Engineering
    • /
    • v.21 no.3
    • /
    • pp.224-233
    • /
    • 2016
  • We propose a new method to visualize 3D models for FDM (Fused Deposition. Modeling) printing that appearance of the printed results can be predicted more realistically as that the efficiency of the modeling-printing process can be improved. The layered nature of horizontal slicing and the vibratory nozzle movements of customer-level FDM 3D printers leaving the characteristic patterns of noisy stripes on the surfaces of printed objects make difficulties in prediction of printed result in company with the thermal contraction of filament material. First, our method analyses the G-codes generated by common slicers to obtain proper outlines and take advantages of a modified version of Perlin noise based texturing method for rendering efficiency and enough number of control parameters on the visual details. The results show improved rendering details of pre-visualization of FDM printing.

Prediction of Laminar Burning Velocity and Flame Thickness in Methane-Air Pre-Mixture (메탄-공기 예혼합기에서의 층류 화염속도 및 화염두께 예측)

  • Kwon, Soon-Ik;Bowen, Philip J.
    • Transactions of the Korean Society of Mechanical Engineers B
    • /
    • v.27 no.9
    • /
    • pp.1201-1208
    • /
    • 2003
  • The thickness of flame and preheat zone from burning velocity which was computed by using Premix code of Chemkin program for methane-air mixture. Also the thickness was evaluated from temperature profile which is also obtained from Premix code for the equivalence ratio of 0.5 to 1.6. The computations were carried out for the laminar flame thickness and burning velocity under the unburned gas temperature 0.5bat-30bar and temperature of 300K-700K at ${\Phi}=l.0$. Comparison of the results showed no difference between these two methods. The flame thickness was decreased by increasing the pressure and temperature, but, the affect of pressure is more significant than the effect of temperature on the flame thickness. The thickness of preheat zone was about 66.5% of the flame thickness, and flame thickness and burning velocity were also predicted by using empirical equation.

Reconstruction Analysis of Vehicle-pedestrian Collision Accidents: Calculations and Uncertainties of Vehicle Speed (차량-보행자 충돌사고 재구성 해석: 차량 속도 계산과 불확실성)

  • Han, In-Hwan
    • Transactions of the Korean Society of Automotive Engineers
    • /
    • v.19 no.5
    • /
    • pp.82-91
    • /
    • 2011
  • In this paper, a planar model for mechanics of a vehicle/pedestrian collision incorporating road gradient is derived to evaluate the pre-collision speed of vehicle. It takes into account a few physical variables and parameters of popular wrap and forward projection collisions, which include horizontal distance traveled between primary and secondary impacts with the vehicle, launch angle, center-of-gravity height at launch, distance from launch to rest, pedestrian-ground drag factor, the pre-collision vehicle speed and road gradient. The model including road gradient is derived analytically for reconstruction of pedestrian collision accidents, and evaluates the vehicle speed from the pedestrian throw distance. The model coefficients have physical interpretations and are determined through direct calculation. This work shows that the road gradient has a significant effect on the evaluation of the vehicle speed and must be considered in accident cases with inclined road. In additions, foreign/domestic empirical cases and multibody dynamic simulation results are used to construct a least-squares fitted model that has the same structure of the analytical one that provides an estimate of the vehicle speed based on the pedestrian throw distance and the band within which the vehicle speed would be expected to be in 95% of cases.