• 한국측량학회지
• /
• 제38권5호
• /
• pp.415-423
• /
• 2020

GNSS (Global Navigation Satellite System) is mostly used for high-precise surveys due to its accuracy and efficiency. But this technique does not always fulfill the demanding accuracy in harsh operational environments such as urban canyon and forest. One of the remedies for overcoming this barrier is to compose a heterogeneous surveying network by adopting terrestrial measurements (i.e., distances and angles). Hence, this study dealt with the adjustment of heterogeneous surveying networks consisted of GNSS baseline vectors, distances, horizontal and vertical angles with a view to enhancing their accuracy and so as to derive an appropriate scheme of the measurement combination. Reviewing some technical issues of the network adjustments, the simulation, and experimental studies have been carried out, showing that the inclusion of the terrestrial measurements in the GNSS standalone overall increased the accuracy of the adjusted coordinates. Especially, if the distances, the horizontal angles, or both of them were simultaneously adjusted with GNSS baselines, the accuracy of the GNSS horizontal component was improved. Comparing the inclusion of the horizontal angles with those of the distances, the former has been more influential on accuracy than the latter even though the same number of measurements were employed in the network. On the other hand, results of the GNSS network adjustment together with the vertical angles demonstrated the enhancement of the vertical accuracy. As conclusion, this paper proposes a simultaneous adjustment of GNSS baselines and the terrestrial measurements for an effective scheme that overcomes the limitation of GNSS control surveys.

• International Journal of Computer Science & Network Security
• /
• 제24권5호
• /
• pp.53-63
• /
• 2024

Alzheimer's disease is a brain disorder that worsens over time and affects millions of people around the world. It leads to a gradual deterioration in memory, thinking ability, and behavioral and social skills until the person loses his ability to adapt to society. Technological progress in medical imaging and the use of artificial intelligence, has provided the possibility of detecting Alzheimer's disease through medical images such as magnetic resonance imaging (MRI). However, Deep learning algorithms, especially convolutional neural networks (CNNs), have shown great success in analyzing medical images for disease diagnosis and classification. Where CNNs can recognize patterns and objects from images, which makes them ideally suited for this study. In this paper, we proposed to compare the performances of Alzheimer's disease detection by using two deep learning methods: You Only Look Once (YOLO), a CNN-enabled object recognition algorithm, and Visual Geometry Group (VGG16) which is a type of deep convolutional neural network primarily used for image classification. We will compare our results using these modern models Instead of using CNN only like the previous research. In addition, the results showed different levels of accuracy for the various versions of YOLO and the VGG16 model. YOLO v5 reached 56.4% accuracy at 50 epochs and 61.5% accuracy at 100 epochs. YOLO v8, which is for classification, reached 84% accuracy overall at 100 epochs. YOLO v9, which is for object detection overall accuracy of 84.6%. The VGG16 model reached 99% accuracy for training after 25 epochs but only 78% accuracy for testing. Hence, the best model overall is YOLO v9, with the highest overall accuracy of 86.1%.

• 한국측량학회지
• /
• 제21권1호
• /
• pp.27-36
• /
• 2003

일반적으로 도심지역의 지형공간정보 취득은 대축척 항공사진영상을 이용하여 수치사진측량방법에 의해 수치 표고모형(DEM) 및 정사투영영상을 제작함으로써 수행되어지고 있다. 그러나 수치사진측량방법을 이용하여 도심지역의 지형공간정보를 취득할 때 가장 큰 문제점으로는 자동으로 추출되는 DEM의 정확도가 크게 저하되어 정사투영영상 및 수치지도의 정확도 역시 저하되는 문제점이 있다. 따라서 본 연구에서는 수치사진측량방법을 이용하여 도심지역의 DEM 정확도 향상방안에 대하여 연구함으로써 보다 정확한 도심지역의 지형공간정보 추출에 기여하는데 목적이 있다. 본 논문의 수행결과, 지형분류를 통하여 DEM을 각 지형별로 제작함으로써 일반적으로 사용하는 자동추출된 DEM에 비하여 DEM의 정확도를 크게 향상시켰으며 또한, 경계선추출방법을 적용함으로써 3차원 수치지도의 제작 가능성을 확인할 수 있었다.

• 한국산업보건학회지
• /
• 제6권1호
• /
• pp.109-124
• /
• 1996

This study was performed to evaluate the performance of three passive samplers made in U.S.A. Three passive samplers selected for this study included products made by 3M, Gilian, and SKC in U.S.A. Three organic solvents, such as toluene, trichloroethylene, and n-hexane which are used frequently in Korean industry were selected for the study. Conclusions obtained from this study are summarized as follows. 1. For toluene and trichloroethylene, the overall accuracy of the results from all of three products was within 25 %, which is the criteria recommended by the U.S. National Institute for Occupational Safety and Health (NIOSH). For n-hexane, the overall accuracy of the results from two products except 3M was exceeding 25 %. Thus 3M product showed the best accuracy among three products. 2. When passive samplers collected organic vapors were exposed to clean air for two hours, there were 12 - 16 % loss of organic vapors due to reverse diffusion in Gilian products. There was no significant loss in results from other two products. 3. Air velocity affected greatly on the performance of passive samplers which did not have permeation membrane. At high velocity, 100 cm/sec, accuracies of results from Gilian and SKC were 57 - 108 and 128 - 164 %, respectively. However, the results from 3M samplers, which contain permeation membrane, indicated accuracy below 25 %. 4. When passive samplers collected organic vapors for eight hours, the accuracy was reduced. Thus, it is recommended that passive samplers be used for less than four hours.

• Nutrition Research and Practice
• /
• 제15권5호
• /
• pp.613-627
• /
• 2021

BACKGROUND/OBJECTIVES: Despite the widespread use of dietary assessment tools, the validity of food records has not been evaluated in Koreans. We assessed the accuracy of estimated food records and the effect of a short education session in young Korean women. SUBJECTS/METHODS: Thirty women (aged 18-23 yrs) each completed 3 food records during a controlled-feeding study. One educational session was provided on day 2 of the study. Food records were analyzed for the accuracy of food items and portion size estimation according to food group (grains; meat, fish, eggs, and beans; vegetables; fruit; dairy; and oils and sugars) and type of dish (rice, kimchi, soup, side dishes, spreads, beverages, and snacks). Reported food items were categorized as exact, close, or far matches, exclusions, or intrusions. Portion sizes were evaluated as accurate, similar, or inaccurate estimates, or missing. The means of days 2 and 3 were used to assess post-education results. Paired t-tests were performed to assess the effects of the education session. RESULTS: The mean percentages of exact matches, close matches, far matches, and exclusions on day 1 were 80.9%, 10.9%, 2.0%, and 6.2%, respectively, and mean intrusions observed were 0.1. The education session slightly increased the accuracy of recorded food items. The percentages of accurate, similar, and inaccurate estimates, and missing portion sizes were 11.7%, 19.8%, 12.2%, and 56.3%, respectively, at baseline. The percentage of missing portion size estimates decreased to 14.0% after the education session, resulting in an increase in the percentages of all other estimates. An increase was observed in the accuracy of reported portion sizes of vegetables, rice, and kimchi. CONCLUSIONS: In young Korean women, estimated food records are highly accurate for food items but not for portion size estimates without prior education. A short education session can improve the accuracy of portion size estimation.

• 농업과학연구
• /
• 제49권3호
• /
• pp.431-440
• /
• 2022

Hanwoo cattle are a unique and historical breed in Korea that have been genetically improved and maintained by the national evaluation and selection system. The aim of this study was to provide information that can help improve the accuracy of the estimated breeding values in Hanwoo cattle by showing the difference between the imputation reference chip platforms of genomic data and the scaling factor of the genetic relationship matrix (GRM). In this study, nine sets of data were compared that consisted of 3 reference platforms each with 3 different scaling factors (-0.5, 0 and 0.5). The evaluation was performed using MTG2.0 with nine different GRMs for the same number of genotyped animals, pedigree, and phenotype data. A five multi-trait model was used for the evaluation in this study which is the same model used in the national evaluation system. Our results show that the Hanwoo custom v1 platform is the best option for all traits, providing a mean accuracy improvement by 0.1 - 0.3%. In the case of the scaling factor, regardless of the imputation chip platform, a setting of -1 resulted in a better accuracy increased by 0.5 to 1.6% compared to the other scaling factors. In conclusion, this study revealed that Hanwoo custom v1 used as the imputation reference chip platform and a scaling factor of -0.5 can improve the accuracy of the estimated breeding value in the Hanwoo population. This information could help to improve the current evaluation system.

• Journal of Animal Science and Technology
• /
• 제65권4호
• /
• pp.720-734
• /
• 2023

In Korea, Korea Proven Bulls (KPN) program has been well-developed. Breeding and evaluation of cows are also an essential factor to increase earnings and genetic gain. This study aimed to evaluate the accuracy of cow breeding value by using three methods (pedigree index [PI], pedigree-based best linear unbiased prediction [PBLUP], and genomic-BLUP [GBLUP]). The reference population (n = 16,971) was used to estimate breeding values for 481 females as a test population. The accuracy of GBLUP was 0.63, 0.66, 0.62 and 0.63 for carcass weight (CWT), eye muscle area (EMA), back-fat thickness (BFT), and marbling score (MS), respectively. As for the PBLUP method, accuracy of prediction was 0.43 for CWT, 0.45 for EMA, 0.43 for MS, and 0.44 for BFT. Accuracy of PI method was the lowest (0.28 to 0.29 for carcass traits). The increase by approximate 20% in accuracy of GBLUP method than other methods could be because genomic information may explain Mendelian sampling error that pedigree information cannot detect. Bias can cause reducing accuracy of estimated breeding value (EBV) for selected animals. Regression coefficient between true breeding value (TBV) and GBLUP EBV, PBLUP EBV, and PI EBV were 0.78, 0.625, and 0.35, respectively for CWT. This showed that genomic EBV (GEBV) is less biased than PBLUP and PI EBV in this study. In addition, number of effective chromosome segments (M_e) statistic that indicates the independent loci is one of the important factors affecting the accuracy of BLUP. The correlation between M_e and the accuracy of GBLUP is related to the genetic relationship between reference and test population. The correlations between M_e and accuracy were -0.74 in CWT, -0.75 in EMA, -0.73 in MS, and -0.75 in BF, which were strongly negative. These results proved that the estimation of genetic ability using genomic data is the most effective, and the smaller the M_e, the higher the accuracy of EBV.

• 한국인공지능학회지
• /
• 제10권1호
• /
• pp.1-7
• /
• 2022

In this paper, a study was conducted to predict natural disasters in Afghanistan based on machine learning. Natural disasters need to be prepared not only in Korea but also in other vulnerable countries. Every year in Afghanistan, natural disasters(snow, earthquake, drought, flood) cause property and casualties. We decided to conduct research on this phenomenon because we thought that the damage would be small if we were to prepare for it. The Azure Machine Learning Studio used in the study has the advantage of being more visible and easier to use than other Machine Learning tools. Decision Forest is a model for classifying into decision tree types. Decision forest enables intuitive analysis as a model that is easy to analyze results and presents key variables and separation criteria. Also, since it is a nonparametric model, it is free to assume (normality, independence, equal dispersion) required by the statistical model. Finally, linear/non-linear relationships can be searched considering interactions between variables. Therefore, the study used decision forest. The study found that overall accuracy was 89 percent and average accuracy was 97 percent. Although the results of the experiment showed a little high accuracy, items with low natural disaster frequency were less accurate due to lack of learning. By learning and complementing more data, overall accuracy can be improved, and damage can be reduced by predicting natural disasters.

• 대한기계학회논문집A
• /
• 제31권10호
• /
• pp.993-998
• /
• 2007

To verify the 2D or 3D positioning accuracy of a multi-axes stage is not easy, particularly, in the case the moving path of the stage is not linear. This paper is a study on a measuring method for the curved path accurately. A machine vision technique is used to trace the moving path of two-axes stage. To improve the accuracy of machine vision, a zoom lens is used for the 2D micro moving path. The accuracy of this method depends of the CCD resolution and array align accuracy with the zoom lens system. Also, a further study for software algorithm is required to increase the tracing speed. This technique will be useful to trace a small object in the 2D micro path in real-time accurately.

• 한국해양공학회지
• /
• 제11권2호
• /
• pp.113-121
• /
• 1997

With the increase use of electromagnrtic distance measuring equiment, is is required that we need to study the higher dimensional applications and detail technical methods. The purpose of this paper is to improve the accuracy of ocean construction surveying and computer programming for determining of horizontal position of a quadrilateral by measuring line on traverse surveyng, trigulation and trilateration. Aa long distance measurements with high accuracy became possible by the apperance of EDM distance measuring instruments, we induced correct adjustment equation through angle condition and area conditionequation. After that we compared and experimental model. From its a result of the practical applicationto quadrilateral, it has been found that its triangulation and traverse surveying algorithms provide better accuracy than trilateration.