• International Journal of Highway Engineering
• /
• v.19 no.2
• /
• pp.35-44
• /
• 2017

PURPOSES: This study suggests a specific methodology for the prediction of road surface temperature using vehicular ambient temperature sensors. In addition, four kind of models is developed based on machine learning algorithms. METHODS : Thermal Mapping System is employed to collect road surface and vehicular ambient temperature data on the defined survey route in 2015 and 2016 year, respectively. For modelling, all types of collected temperature data should be classified into response and predictor before applying a machine learning tool such as MATLAB. In this study, collected road surface temperature are considered as response while vehicular ambient temperatures defied as predictor. Through data learning using machine learning tool, models were developed and finally compared predicted and actual temperature based on average absolute error. RESULTS : According to comparison results, model enables to estimate actual road surface temperature variation pattern along the roads very well. Model III is slightly better than the rest of models in terms of estimation performance. CONCLUSIONS : When correlation between response and predictor is high, when plenty of historical data exists, and when a lot of predictors are available, estimation performance of would be much better.

• The Journal of Information Technology
• /
• v.5 no.2
• /
• pp.55-67
• /
• 2002

This paper presents an adaptive back propagation algorithm that update the learning parameter by the generated error, adaptively and varies the number of hidden layer node. This algorithm is expected to escaping from the local minimum and make the best environment for convergence to be change the number of hidden layer node. On the simulation tested this algorithm on two learning pattern. One was exclusive-OR learning and the other was $7{\times}5$ dot alphabetic font learning. In both examples, the probability of becoming trapped in local minimum was reduce. Furthermore, in alphabetic font learning, the neural network enhanced to learning efficient about 41.56%~58.28% for the conventional back propagation. and HNAD(Hidden Node Adding and Deleting) algorithm.

• Cross-Cultural Studies
• /
• v.19
• /
• pp.411-444
• /
• 2010

This paper explored the academic socialization of a group of Mongolian college students, learning Korean as their L3 (Third Language), by focusing on their uses of an electronic communication channel. From a perspective of the continua of bi-literacy, this case study investigated how Mongolian students who had limited exposure to a Korean learning community overcame academic challenges through the use of a written communication channel as a tool in the socialization process. Data were collected mainly through three methods: written products, interviews, and questionnaires. The results from this study were as follows. Interactional opportunities for these minority students were seriously constrained during the classroom practices in a Korean-speaking classroom. They also described the lack of communicative competence in Korean and the limited roles played by L2 (English) communication as key barriers to classroom practices. However, students' ways of engaging in electronic interactions differed widely in that they were able to broaden interactional circles by communicating their expertise and difficulties with their Korean peers through the electronic channel. More importantly, the communication pattern of "L2-L2/L3-L3" (on a L2-L3 continuum) emerging from data demonstrated how these students used a written channel as a socialization tool to mediate their learning process in a new community of learning. This study argues that a written communication channel should be taken as an essential part of teaching practices especially for foreign students who cannot speak Korean fluently in multi-cultural classes.

• Transactions of Materials Processing
• /
• v.31 no.4
• /
• pp.229-239
• /
• 2022

Convolution Neural Network(CNN) is a class of deep learning algorithms and can be used for image analysis. In particular, it has excellent performance in finding the pattern of images. Therefore, CNN is commonly applied for recognizing, learning and classifying images. In this study, the surface defect classification performance of Al 6061 extruded material using CNN-based algorithms were compared and evaluated. First, the data collection criteria were suggested and a total of 2,024 datasets were prepared. And they were randomly classified into 1,417 learning data and 607 evaluation data. After that, the size and quality of the training data set were improved using data augmentation techniques to increase the performance of deep learning. The CNN-based algorithms used in this study were VGGNet-16, VGGNet-19, ResNet-50 and DenseNet-121. The evaluation of the defect classification performance was made by comparing the accuracy, loss, and learning speed using verification data. The DenseNet-121 algorithm showed better performance than other algorithms with an accuracy of 99.13% and a loss value of 0.037. This was due to the structural characteristics of the DenseNet model, and the information loss was reduced by acquiring information from all previous layers for image identification in this algorithm. Based on the above results, the possibility of machine vision application of CNN-based model for the surface defect classification of Al extruded materials was also discussed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.195-201
• /
• 2022

For a efficient distance education environment, the need for correct problem recommendation guides considering the learner's exact learning pattern is increasing. In this paper, we study block chain based smart contract technology to suggest a method for presenting the optimal problem recommendation path for individual learners based on the data given by situational weights to the problem patterns of learners collected in the distance education environment. For the performance evaluation of this study, the learning satisfaction with the existing similar learning environment, the usefulness of the problem recommendation guide, and the learner data processing speed were analyzed. Through this study, it was confirmed that the learning satisfaction improved by more than 15% and the learning data processing speed was improved by more than 20% compared to the existing learning environment.

• Journal of Korean Society for Quality Management
• /
• v.50 no.3
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• Journal of KIBIM
• /
• v.13 no.3
• /
• pp.12-20
• /
• 2023

Deep learning-based anomaly detection technology is used in various fields such as computer vision, speech recognition, and natural language processing. In particular, this technology is applied in various fields such as monitoring manufacturing equipment abnormalities, detecting financial fraud, detecting network hacking, and detecting anomalies in medical images. However, in the field of construction and architecture, research on deep learning-based data anomaly detection technology is difficult due to the lack of digitization of domain knowledge due to late digital conversion, lack of learning data, and difficulties in collecting and processing field data in real time. This study acquires necessary data through IoT (Internet of Things) from the viewpoint of monitoring for environmental management of architectural spaces, converts them into a database, learns deep learning, and then supports anomaly patterns using AI (Artificial Infelligence) deep learning-based anomaly detection. We propose an implementation process. The results of this study suggest an effective environmental anomaly pattern detection solution architecture for environmental management of architectural spaces, proving its feasibility. The proposed method enables quick response through real-time data processing and analysis collected from IoT. In order to confirm the effectiveness of the proposed method, performance analysis is performed through prototype implementation to derive the results.

• The Journal of the Korea Contents Association
• /
• v.9 no.5
• /
• pp.346-354
• /
• 2009

This paper proposes a new learning recommendation system for learning patterns that educators are applying to learners using item-based method. The proposed method in this paper first collects personal learning methods based on learning information that learners are performing through the internet contents site. Then this system recommends a learning method which is estimated most properly to learners after classifying learning elements based on these information. The students of a middle school took part in the experiment in order to evaluate the proposed system, and the students were divided into three groups according to their grades. We gave inter-attribute and intra-attribute weights to learning elements applying to each group for recommending the most efficient method to improve learning achievement. The experiment showed that the learning achievement of learners in the proposed method is improved considerably compared to the previous grades.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1083-1093
• /
• 2021

It is an essential to predict water usage for establishing an optimal supply operation plan and reducing power consumption. However, the water usage by consumer has a non-linear characteristics due to various factors such as user type, usage pattern, and weather condition. Therefore, in order to predict the water consumption, we proposed the methodology linking various techniques that can consider non-linear characteristics of water use and we called it as KWD framework. Say, K-means (K) cluster analysis was performed to classify similar patterns according to usage of each individual consumer; then Wavelet (W) transform was applied to derive main periodic pattern of the usage by removing noise components; also, Deep (D) learning algorithm was used for trying to do learning of non-linear characteristics of water usage. The performance of a proposed framework or model was analyzed by comparing with the ARMA model, which is a linear time series model. As a result, the proposed model showed the correlation of 92% and ARMA model showed about 39%. Therefore, we had known that the performance of the proposed model was better than a linear time series model and KWD framework could be used for other nonlinear time series which has similar pattern with water usage. Therefore, if the KWD framework is used, it will be possible to accurately predict water usage and establish an optimal supply plan every the various event.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.212-217
• /
• 1993

In this paper, characteristics of the motions of a human arm are investigated experimentally. When the conditions of the target point are restricted, human adjusts its trajectory and velocity pattern of the arm to fit the conditions skillfully. The purpose of this work is to examine the characteristics of the trajectory, velocity pattern, and the size of the duration in the following cases. First, we examine the case of point-to-point motion. The results are consistent with the minimum jerk theory. However, individual differences in the length of the duration can be observed in the experiment. Second, we examine the case which requires accuracy of positioning at the target point. It is found that the velocity pattern differs from the bell shaped pattern explained by the minimum jerk theory, and has its peak in the first half of the duration. When higher accuracy of the positioning is required, learning effects can be observed. Finally, to examine the case which requires constraint of the arm posture at the target point, we conduct experiments of a human trying to grasp a cup. It is considered that this motion consists of two steps : one is the positioning motion of the person in order to start the grasping motion, the other is the grasping motion of the human's hand approaching toward the cup and grasping it. In addition, two representative velocity patterns are observed : one is the similar velocity pattern explained in the above experiment, the other is the velocity pattern which has its relative maximum in the latter half of the duration.