• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.12
• /
• pp.85-91
• /
• 2021

In our daily life, artificial intelligence performs simple and complicated tasks like us, including operating mobile phones and working at homes and workplaces. Artificial intelligence is used in industrial technology for diagnosing various types of equipment using the machine learning technology. This study presents a fault mode effect analysis (FMEA) of start motors using machine learning and big data. Through multiple data collection, we observed that the primary failure of the start motor was caused by the melting of the magnetic switch inside the start motor causing it to fail. Long-short-term memory (LSTM) was used to diagnose the condition of the magnetic locations, and synthetic data were generated using the synthetic minority oversampling technique (SMOTE). This technique has the advantage of increasing the data accuracy. LSTM can also predict a start motor failure.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.41 no.5
• /
• pp.61-70
• /
• 2004

The operation mode of neural network is divided into learning and recognition process. Learning is updating process of weight until neural network archives target result from input pattern. Recognition is arithmetic process of input pattern and weight. Traditional inner product process is focused to improve processing speed and hardware complexity. There is no hardware architecture to distinguish between loaming and recognition mode of neural network. In this paper we propose the new architecture of low power inner product processor for reconfigurable neural network. The proposed architecture is similar with bit-serial inner product processor on learning mode. It have several advantages which are fast processing base on bit-level, suitability of hardware implementation and pipeline architecture to compute data. And proposed architecture minimizes active units and reduces consumption power on recognition mode. Result of simulation shows that active units is depend on bit representation of weight, but we can reduce active units about 50 precent.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.13 no.1
• /
• pp.13-22
• /
• 2007

Purpose: The purpose of this study was to determine learning styles and preferred learning methods of undergraduate nursing students in Korea. Method: Data was collected from 724 nursing students at five universities in Seoul, Busan, Daegu, Daejeon, and Gwangju. Kolb's Learning Style Inventory, a self-report questionnaire was completed. Result: Learning styles of nursing students were diverger 43.5%, accommodator 36.7%, assimilator 10.8%, or converger 9.0% Learning styles were significantly different related to preferred future clinical practice area and grade. Furthermore, active experimentation(AE) learning mode was significantly different by grade. Concrete experience(CE), conceptualization(AC), and active experimentation(AE) learning modes were significantly different preferred future clinical practice area. preferred learning methods were lecture 40.7%, clinical practice 37.2%, self-directed learning 8.7%, laboratory practice 8.0%, and group discussion 5.4%. Preferred learning methods were significantly different by learning styles and grade. Lecture was preferred in diverger and assimilator. Clinical practice was preferred in accommodator and converger. Styles Conclusion: This study suggested that nursing education should be applied to nursing students after examining learning styles and preferred learning methods. In conclusion, nursing educators should help to develop various learning modes for student's balanced learning capabilities.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.179-179
• /
• 2023

This study suggests a new approach of water level forecasting for extended lead times using original data preprocessing with variational mode decomposition (VMD). Here, two machine learning algorithms including light gradient boosting machine (LGBM) and random forest (RF) were considered to incorporate extended lead times (i.e., 5, 10, 15, 20, 25, 30, 40, and 50 days) forecasting of water levels. At first, the original data at two water level stations (i.e., SW173 and SW269 in Bangladesh) and their decomposed data from VMD were prepared on antecedent lag times to analyze in the datasets of different lead times. Mean absolute error (MAE), root mean squared error (RMSE), and mean squared error (MSE) were used to evaluate the performance of the machine learning models in water level forecasting. As results, it represents that the errors were minimized when the decomposed datasets were considered to predict water levels, rather than the use of original data standalone. It was also noted that LGBM produced lower MAE, RMSE, and MSE values than RF, indicating better performance. For instance, at the SW173 station, LGBM outperformed RF in both decomposed and original data with MAE values of 0.511 and 1.566, compared to RF's MAE values of 0.719 and 1.644, respectively, in a 30-day lead time. The models' performance decreased with increasing lead time, as per the study findings. In summary, preprocessing original data and utilizing machine learning models with decomposed techniques have shown promising results for water level forecasting in higher lead times. It is expected that the approach of this study can assist water management authorities in taking precautionary measures based on forecasted water levels, which is crucial for sustainable water resource utilization.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.495-497
• /
• 2012

클래스라벨에 대한 정보를 가진 데이터가 매우 적을 때 클래스라벨 정보가 없는 데이터로부터의 정보를 학습에 활용하는 반감독학습(semi-supervised learning) 방법들 중에서 데이터 샘플들 간의 유사도를 나타내는 그래프를 이용하는 방법이 잘 알려져 있다. 본 논문에서는 그래프 기반 반감독 학습에서 배치 모드 능동적 학습을 위한 방법을 제안하고 실제 데이터를 이용한 실험결과를 통해 제안된 방법의 성능을 입증한다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.3
• /
• pp.256-262
• /
• 2000

This paper proposes a new sliding mode controller combined with a multi-layer neural network using the error back propagation learning algorithm,, The network acts as a compensator of the conventional sliding mode controller to improve the control performance when initial assumptions of uncertainty bounds of system parameters are violated. The proposed controller can reduce th steady state error of conventional sliding mode controller with the boundary layer technique Computer simulation results show that the proposed method is effective to control dynamic systems with unexpectably large uncertainties.

• Journal of the Korean Society for Precision Engineering
• /
• v.33 no.12
• /
• pp.985-992
• /
• 2016

Bearings have various uses in industrial equipment. The lifetime of bearings is often lesser than anticipated at the time of purchase, due to environmental wear, processing, and machining errors. Bearing conditions are important, since defects and damage can lead to significant issues in production processes. In this study, we developed a method to diagnose faults in the bearing conditions. The faults were determined using kurtosis, average, and standard deviation. An intrinsic mode function for the data from the selected axis was extracted using empirical mode decomposition. The intrinsic mode function was obtained based on the frequency, and the learning data of ANN (Artificial Neural Network) was concluded, following which the normal and fault conditions of the bearing were classified.

• Journal of Fisheries and Marine Sciences Education
• /
• v.28 no.3
• /
• pp.872-880
• /
• 2016

The purpose of this study is to find the research trends relating to flipped learning through keyword network analysis. For investigating this topic, final 100 papers (removed due to overlap in all 205 papers) were selected as subjects from the result of research databases such as RISS, DBPIA, and KISS. After keyword extraction, coding, and data cleaning, we made a 2-mode network with final 202 keywords. In order to find out the research trends, frequency analysis, social network structural property analysis based on co-keyword network modeling, and social network centrality analysis were used. Followings were the results of the research: (a) Achievement, writing, blended learning, teaching and learning model, learner centered education, cooperative leaning, and learning motivation, and self-regulated learning were found to be the most common keywords except flipped learning. (b) Density was .088, and geodesic distance was 3.150 based on keyword network type 2. (c) Teaching and learning model, blended learning, and satisfaction were centrally located and closed related to other keywords. Satisfaction, teaching and learning model blended learning, motivation, writing, communication, and achievement were playing an intermediary role among other keywords.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.115-120
• /
• 2022

The main purpose of the study is to identify the key aspects of the use of innovative distance learning technologies in the training of biology students. Currently, there is a modernization, the evolution of the education system from a classical university to a virtual one, from lecture material teaching to computer educational programs, from a book library to a computer one, from multi-volume paper encyclopedias to modern search databases. During studies in higher education, distance learning ensures the delivery of information in an interactive mode through the use of information and communication technologies. The main disadvantage of distance learning is the emotional interaction of the teacher with students. It is necessary to increase the level of methodological developments for independent studies of students. The methodology includes a number of theoretical methods. Based on the results of the study, the main elements of the use of innovative distance learning technologies in the training of biology students were identified.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.8
• /
• pp.64-70
• /
• 2018

The development of weapon systems (or components) is hindered by the number of tests due to the limited development period and cost, which reduces the scale of accumulated data related to failures. Nevertheless, because a large amount of failure data and maintenance details during the operational period are managed by computerized data, the cause of failure of weapon systems (or components) can be analyzed using the data. On the other hand, analyzing the failure and maintenance details of various weapon systems is difficult because of the variation among groups and companies, and details of the cause of failure are described as unstructured text data. Fortunately, the recent developments of big data processing technology, machine learning algorithm, and improved HW computation ability have supported major research into various methods for processing the above unstructured data. In this paper, unstructured data related to the failure / maintenance of defense weapon systems (or components) is presented by applying doc2vec, a machine learning technique, to analyze the failure cases.