• Journal of Positioning, Navigation, and Timing
• /
• 제13권1호
• /
• pp.111-115
• /
• 2024

This study builds a machine learning model optimized for clocks among various techniques in the field of artificial intelligence and applies it to clock stabilization or synchronization technology based on atomic clock noise characteristics. In addition, the possibility of providing stable source clock data is confirmed through the characteristics of machine learning predicted values during holdover of atomic clocks. The proposed machine learning model is evaluated by comparing its performance with the AutoRegressive Integrated Moving Average (ARIMA) model, an existing statistical clock prediction model. From the results of the analysis, the prediction model proposed in this study (MSE: 9.47476) has a lower MSE value than the ARIMA model (MSE: 221.2622), which means that it provides more accurate predictions. The prediction accuracy is based on understanding the complex nature of data that changes over time and how well the model reflects this. The application of a machine learning prediction model can be seen as a way to overcome the limitations of the statistical-based ARIMA model in time series prediction and achieve improved prediction performance.

• 스마트미디어저널
• /
• 제12권10호
• /
• pp.47-54
• /
• 2023

지구 온난화로 인해 갑작스러운 기후변화와 농업 생산성에 대한 이해가 점점 중요해지면서, 토양 수분 예측은 농업에서 핵심 주제로 떠오르고 있다. 토양 수분은 농작물의 성장과 건강에 큰 영향을 미치며, 적절한 관리와 정확한 예측은 농업 생산성 향상과 자원 관리의 핵심 요소이다. 이러한 이유로 토양 수분 예측은 농업 및 환경 분야에서 큰 주목을 받고 있다. 본 논문에서는 머신러닝 알고리즘인 랜덤 포레스트를 통하여 시범포를 이용하여 노지 환경 데이터를 수집하고 분석하여 데이터 특성들과 토양 수분의 상관관계를 구하고 토양 수분 실제 값과 예측값을 비교하였으며 비교 결과 예측률이 약 92%의 정확성을 갖는다는 것을 확인하였다. 추후 연구를 통해 작물의 생장 데이터 변수들을 추가하여 토양 수분 예측을 진행한다면 토양 수분에 따른 작물의 생장 속도, 적절한 관수 타이밍 등의 주요 정보를 정확하게 제어함으로써 작물의 품질 상승, 물 관리 효율 증가 등 생산성 및 자원 효율성에 좋은 영향을 미칠 것이라고 기대된다.

• 한국항해학회지
• /
• 제16권3호
• /
• pp.33-41
• /
• 1992

Handling performance of a vessel is greatly related with her steering characteristics which consist of two kinds of motion characteristics ; namely course stability and turning ability. The correct prediction of the qualities, especially the steering characteristics is as much important in ship handling as in ship design. It is the purpose of this paper to provide ships handlers better understanding of steering characteristics and then to help them in safe controlling and maneuvering of vessels presenting distinct inherent steering characteristic difference that lies between a fine-form vessel and full-form vessel. The authors calculated dynamic course stabilities of two kinds of ideal models, one of which represents a fine-form ship and the other a full-form ship, based on hydrodynamic data of forces and moments obtained by model tests in maneuvering tanks. The result of calculations indicated that a ship of full-form configuration has inhernet course instability. Though significant nonlinearties affect ship montions in maneuvers, application of linear theory is sufficient for prediction of the maneuvering characteristics of vessels on calm waters for handling reference.

• 연구논문집
• /
• 통권23호
• /
• pp.45-56
• /
• 1993

In order to acquire more comprehensive understanding of textile composites, the processing-microstructure-performance relationships for a variety of material systems, reinforcing schemes and processing technologies should be established. In this paper, emphasis is placed on the integrated analysis of three-dimensional (3-D) 2-step braided composites. The analysis includes the geometric model of unit cells, identification of key process parameters and processing windows due to limiting geometries of yarn jamming, and prediction of elastic constants of the composite. The coordinate transformation and averaging of stiffness and compliance constants are utilized in the prediction of elastic constants. Since there are several types of unit cells in the thickness and width directions of the composites, characterization of mechanical properties is based upon the macro-cell, which occupies the entire cross-section and the unit pitch length of the sample. The performance map demonstrates that a wide range of elastic properties can be achieved by varying the geometric and process parameters.

• Nuclear Medicine and Molecular Imaging
• /
• 제41권2호
• /
• pp.85-90
• /
• 2007

Acute event in cerebrovascular disease is the second most common cause of death in Korea following cancer, and it can also cause serious neurologic deficits. Understanding of perfusion status is important for clinical applications in management of patients with cerebrovascular diseases, and then the attacks of ischemic neurologic symptoms and the risk of acute events can be reduced. Therefore, the normal vascular anatomy of brain, various clinical applications of acetazolamide-enhanced brain perfusion SPECT, including meaning and role of assessment of vascular reserve in carotid stenosis before procedure, in pediatric Moyamoya disease before and after operation, in prediction of development of hyperperfusion syndrome before procedure, and in prediction of vasospasm and of prognosis in subarachnoid hemorrahge were reviewed in this paper.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.280-282
• /
• 2005

A ribonucleic acid (RNA) is one of the two types of nucleic acids found in living organisms. An RNA molecule represents a long chain of monomers called nucleotides. The sequence of nucleotides of an RNA molecule constitutes its primary structure, and the pattern of pairing between nucleotides determines the secondary structure of an RNA. Non-coding RNA genes produce transcripts that exert their function without ever producing proteins. Predicting the secondary structure of non-coding RNAs is very important for understanding their functions. We focus on Nussinov's algorithm as useful techniques for predicting RNA secondary structures. We introduce a new traceback matrix and scoring table to improve above algorithm. And the improved algorithm provides better levels of performance than the originals.

• 한국환경과학회지
• /
• 제6권4호
• /
• pp.351-357
• /
• 1997

In the Atmosphere under the various physical and chemical condition different chemical reactions occur and there are a number of air pollutants which are generated by photochemical reaction by absorbing solar energy. Therefor various testing simulation was done as foundation work to develop the numerical model for the prediction of concentration of air pollutants. It was shown change of msjor air pollutants concentration In according to variation of photodissociation speed constant, Kl and Initial condition of air pollutants concentration which plays major role In photochemical reaction. The photochemical reaction model which was used In this study Is found to be useful for understanding relationship among the concentration of reacting air pollutants and the prediction of concentration of air pollutants in urban atmosphere.

• 한국정밀공학회지
• /
• 제11권5호
• /
• pp.189-198
• /
• 1994

The achievable machining accuracy depends upon the level of the micro-engineering, and the today's accuracy targets are dimensional tolerances in the order of 10nm and surface roughness in the order of 1nm. Such requirements cannot be satisfied by the conventional machining processes. Single point diamond turning is the one of new techniques which can produce the parts with such accuracy limits. The aims of this thesis are to get a better understanding of the complex cutting process with a diamond tool and, consequently, to develope a predicting model of a turned surface profile. In order to predict the turned surface profile, a numerical model has been developed. By means of this model, the influence of the operational settings-the material properties of the workpiece, the geometry of the cutting tool and the dynamic behaviour of the lathe-and their influences via the cutting forces upon the surface roughness have been estimated.

• 한국정밀공학회지
• /
• 제28권2호
• /
• pp.251-256
• /
• 2011

The radial overcut in micro electrochemical machining was investigated. The prediction of overcut is important not only for the machining accuracy but also for the shape control of micro structures. In micro ECM, machining gap or overcut depends on electrolyte, pulse voltage, pulse duration and dissolution time etc. Understanding of electrochemical dissolution rate is necessary for the overcut prediction. In this paper, the radial overcut of micro electrochemical machining according to pulse duration and dissolution time was simulated using electrochemical principles and also experimentally estimated.

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 1999년도 제30회 추계학술대회
• /
• pp.19-24
• /
• 1999

Understanding of wear mode and prediction of wear rate of parts in sliding contact are very important in field of meterial design relating with wear resistant. This paper has been undertaken to analyze the possibility of elucidation of wear mode and prediction of wear rate for annealed steel in sliding contact using the X-ray diffraction. The sliding wear test with various velocities using pin-on-disc machine and the X-ray diffraction test on the worn surface have been carried out. The results have been shown that the magnitude of residual stress and half-value breadth on the worn surface have a good correlation with wear mode. The difference between before and after test of half-value breadth on worn surface has been shown to be exponential relation with wear rate in the same wear mode.