• 한국태양에너지학회 논문집
• /
• 제37권1호
• /
• pp.25-38
• /
• 2017

Climate change and environmental pollution are becoming serious due to the use of fossil energy. For this reason, renewable energy systems are increasing, especially photovoltaic systems being more popular. The photovoltaic system has characteristics that are affected by ambient weather conditions such as insolation, outside temperature, wind speed. Particularly, it has been confirmed that the performance of the photovoltaic system decreases as the module temperature increases. In order to grasp the influence of the module temperature in advance, several researchers have proposed the prediction models on the module temperature. In this paper, we predicted the module temperature using the aforementioned prediction model on the basis of the weather conditions in Incheon, South Korea during July and August. The influence of weather conditions (i.e. insolation, outside temperature, and wind speed) on the accuracy of the prediction models was also evaluated using the standard statistical metrics such as RMSE, MAD, and MAPE. The results show that the prediction accuracy is reduced by 3.9 times and 1.9 times as the insolation and outside temperature increased respectively. On the other hand, the accuracy increased by 6.3 times as the wind speed increased.

• 한국멀티미디어학회논문지
• /
• 제14권11호
• /
• pp.1467-1477
• /
• 2011

본 논문에서는 고객 맞춤 서비스의 선호도를 정확하게 예측하기 위하여 사용자 프로파일 분석, 사용자간 유사도 분석을 이용한 HPPS(Hybrid Preference Prediction System) 설계를 제안한다. 기존의 NBCFA(Neighborhood Based Collaborative Filtering Algorithm)과 달리, 본 논문은 첫째, 선호도 예측식에서 이웃의 상품 평가가 없을 경우 상품에 대한 평균값을 이용하도록 하였고, 둘째, 선호도 예측식에서 사용자의 특성을 분석한 가중치를 반영하도록 하였고, 끝으로, 인접 이웃을 선정할 때 유사도, 상품 평가 여부, 평가 횟수를 반영하여 HPPS에 선호도의 정확도를 향상시켰다. 따라서 첫째와 둘째의 선호도 예측식을 이용하면 HPPS의 정확도는 기존의 NBCFA에 비해 97.24% 향상되었고, 인접이웃 선정방식에서도 HPPS 시스템의 정확도가 75% 향상되었다.

• 산업경영시스템학회지
• /
• 제27권2호
• /
• pp.10-16
• /
• 2004

Data mining technique is the exploration and analysis, by automatic or semiautomatic means, of large quantities of data in order to discover meaningful patterns and rules. This paper uses a data mining technique for the prediction of defect types in manufacturing Process. The Purpose of this Paper is to model the recognition of defect type Patterns and Prediction of each defect type before it occurs in manufacturing process. The proposed model consists of data handling, defect type analysis, and defect type prediction stages. The performance measurement shows that it is higher in prediction accuracy than logistic regression model.

• Earthquakes and Structures
• /
• 제18권1호
• /
• pp.73-82
• /
• 2020

With the coal mining depth increasing, both stress and gas pressure rapidly enhance, causing coal and gas outburst risk to become more complex and severe. The conventional method for prediction of coal and gas outburst adopts one prediction index and corresponding critical value to forecast and cannot reflect all the factors impacting coal and gas outburst, thus it is characteristic of false and missing forecasts and poor accuracy. For the reason, based on analyses of both the prediction indicators and the factors impacting coal and gas outburst at the test site, this work carefully selected 6 prediction indicators such as the index of gas desorption from drill cuttings Δh₂, the amount of drill cuttings S, gas content W, the gas initial diffusion velocity index ΔP, the intensity of electromagnetic radiation E and its number of pulse N, constructed the Bayes discriminant analysis (BDA) index system, studied the BDA-based multi-index comprehensive model for forecast of coal and gas outburst risk, and used the established discriminant model to conduct coal and gas outburst prediction. Results showed that the BDA - based multi-index comprehensive model for prediction of coal and gas outburst has an 100% of prediction accuracy, without wrong and omitted predictions, can also accurately forecast the outburst risk even for the low indicators outburst. The prediction method set up by this study has a broad application prospect in the prediction of coal and gas outburst risk.

• International journal of advanced smart convergence
• /
• 제7권4호
• /
• pp.27-39
• /
• 2018

Since the global positioning system (GPS) has been included in mobile devices (e.g., for car navigation, in smartphones, and in smart watches), the impact of personal GPS log data on daily life has been unprecedented. For example, such log data have been used to solve public problems, such as mass transit traffic patterns, finding optimum travelers' routes, and determining prospective business zones. However, a real-time analysis technique for GPS log data has been unattainable due to theoretical limitations. We introduced a machine learning model in order to resolve the limitation. In this paper presents a new, three-stage real-time prediction model for a person's daily route activity. In the first stage, a machine learning-based clustering algorithm is adopted for place detection. The training data set was a personal GPS tracking history. In the second stage, prediction of a new person's transient mode is studied. In the third stage, to represent the person's activity on those daily routes, inference rules are applied.

• 한국철도학회논문집
• /
• 제9권6호
• /
• pp.732-738
• /
• 2006

This research provides a scheme for Highly Accelerated Stress Test that is necessary to demonstrate reliability prediction of Korean Rapid Transit Railway Train Control System sub-equipment, which is calculated by a relevant standard for failure rate prediction of electronic products. Although determining failure information generated in the process of trial running by statistic analysis is widely accepted as a measure of confirmation for reliability prediction, this research suggests the modeling for System Life Test determined by accelerating stress factors as a measure of confirmation for reliability prediction of sub-equipment unit that is generated ahead of a trial running in System Life Cycle. Consequently, the research demonstrates sub-equipment unit reliability test, which is based on the model derived from Accelerated Stress Test, according to accuracy level and the number of samples, and conducts an official experiment by making out a reliability test procedure sheet based on test time as well.

• 한국인터넷방송통신학회논문지
• /
• 제19권2호
• /
• pp.151-159
• /
• 2019

4차 산업의 근간이 되는 빅데이터 시대가 도래하면서 대부분의 관련 업계에서는 데이터에 대한 저장, 통계분석 및 시각화 기술 중심으로 관련 솔루션들이 개발되고 있다. 하지만 빅데이터 기술의 근본적인 발전을 위해서는 인공지능을 이용한 예측 분석기술의 발전이 필요하다. 하지만 이러한 고급기술은 현재 데이터과학자라고 불리는 일부 전문가에 의해서만 가능한 수준이다. 이를 극복하기 위해서는 데이터에 대한 통찰력을 지닌 비전문가(시민 데이터과학자)가 빅데이터 분석 과정을 저비용으로 쉽게 접근할 수 있는 기반이 마련되어야한다. 본 논문에서는 고수준의 데이터과학 지식 없이 사용하기 쉬운 빅데이터 도구 및 기술의 도움으로 데이터를 분석하기 위한 서비스 과정을 제안한다. 이를 위해 필요한 예측 분석 시스템에 필요한 구성 요소와 환경을 정의하고 전반적인 서비스 설계 방안을 제시한다.

• Current Optics and Photonics
• /
• 제5권6호
• /
• pp.641-651
• /
• 2021

To handle the servo delay in a real-time adaptive optics system, a linear subspace system identification algorithm was employed to model the system, and the accuracy of the system identification was verified by numerical calculation. Experimental verification was conducted in a real test bed system. Through analysis and comparison of the experimental results, the convergence can be achieved only 200 times with prediction and 300 times without prediction. After the wavefront peak-to-valley value converges, its mean values are 0.27, 4.27, and 10.14 ㎛ when the communication distances are 1.2, 4.5, and 10.2 km, respectively. The prediction algorithm can effectively improve the convergence speed of the peak-to-valley value and improve the free-space optical communication performance.

• 전기학회논문지
• /
• 제62권7호
• /
• pp.913-917
• /
• 2013

During the restoration process of primary restorative transmission system, some over voltages may happen due to nonlinear interaction between unloaded transformers and transmission systems. These over voltages caused by harmonic resonance can be suppressed by inserting damping loads before energizing transformers. But it is very difficult to predict the occurrence possibility of harmonic resonance and complex simulation must be repeated to estimate the sufficient damping loads. This paper presents a damping loads prediction system to prevent harmonic resonance. Detailed analysis of the relationship between harmonic resonance and the amount of damping loads is discussed. The prediction system is developed using a curve fitting and a neural network based on this relationship. A curve fitting used a Gaussian function based on non-linear least square method and multi-layer back-propagation neural network is applied. The system is applied to primary restorative transmission lines in korean power system and the result showed satisfactory performance.

• 소성∙가공
• /
• 제16권6호
• /
• pp.479-487
• /
• 2007

Die life is generally estimated taking failure life and wear amount into consideration. In this study, the forging die life was investigated considering both of these two factors. The fatigue life prediction for the die was performed using the stress-life method, i.e. Goodman's and Gerber's equations. The Archard's wear model was used in the wear life simulation. These die life prediction techniques were applied to the die used in the forging process of the socket ball joint of a transportation system. A rigid-plastic finite element analysis for the die forging process of the socket ball was carried out and also the elastic stress analysis for the die set was performed in order to get basic data for the die fatigue life prediction. The wear volume of the die was measured using a 3-dimensional measurement apparatus. The simulation results were relatively in good agreement with the experimental measurements.