• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.1
• /
• pp.103-116
• /
• 2021

Analysis of runoff is substantial for effective water management in the watershed. Runoff occurs by reaction of a watershed to the rainfall and has non-linearity and uncertainty due to the complex relation of weather and watershed factors. ANN (Artificial Neural Network), which learns from the data, is one of the machine learning technique known as a proper model to interpret non-linear data. The performance of ANN is affected by the ANN's structure, the number of hidden layer nodes, learning rate, and activation function. Especially, the activation function has a role to deliver the information entered and decides the way of making output. Therefore, It is important to apply appropriate activation functions according to the problem to solve. In this paper, ANN models were constructed to estimate runoff with different activation functions and each model was compared and evaluated. Sigmoid, Hyperbolic tangent, ReLU (Rectified Linear Unit), ELU (Exponential Linear Unit) functions were applied to the hidden layer, and Identity, ReLU, Softplus functions applied to the output layer. The statistical parameters including coefficient of determination, NSE (Nash and Sutcliffe Efficiency), NSEln (modified NSE), and PBIAS (Percent BIAS) were utilized to evaluate the ANN models. From the result, applications of Hyperbolic tangent function and ELU function to the hidden layer and Identity function to the output layer show competent performance rather than other functions which demonstrated the function selection in the ANN structure can affect the performance of ANN.

• The Mathematical Education
• /
• v.60 no.3
• /
• pp.321-340
• /
• 2021

As many changes in the future society represented by the age of artificial intelligence(AI) are expected to come, efforts are being made to draw the shape of the future education and various research methods are being employed to support the attempts. While many research studies use methods for deriving generalized results such as expert survey and trend analysis in along with a review of literature, there are attempts to apply the scenario methodology to explore ideas and information needed within a changing context. A scenario method, one of the experiential learning strategies, aims to seek various and alternative approaches by establishing a plan from the present conditions considering future changes. In this study, in-service teachers' perceptions and expectations of the interactivity between human and AI teachers were visualized by applying the role-play presentation technique that grafted the concept of role-play game to the scenario method. In addition, the mandal-art method was introduced to support in conducting productive discussion during the teachers' collaboration. This method appeared to help to depict teachers' perceptions of AI teachers in the detailed and concrete form, which may flow in the abstract otherwise. Through analyses of the teachers' role-play presentations with the implementation of the madal-art method it was suggested that most teachers would want to collaborate with an AI teacher for improved instruction and individualized student learning while they would take the instructional authority over the AI teacher in the classroom.

• Journal of the Korean Society of Radiology
• /
• v.17 no.1
• /
• pp.17-23
• /
• 2023

In this study, the thermoluminescence kinetics of electron trap in Li₆Y_0.5Gd_0.5(BO₃)₃ (LY_0.5G_0.5BO) scintillator for neutron detection composed of Li, Gd, and B with a high neutron response cross-section were investigated. The thermoluminescence glow curve of the LY_0.5G_0.5BO scintillation single crystal was measured and analyzed using the peak shape method, the initial rise method, and the machine learning algorithm to evaluate the physical parameters of the electron trap. The glow curve of the LY_0.5G_0.5BO scintillation single crystal consisted of a single peak. As a result of analyzing this peak, the activation energy, emission order, and frequency factor of the electron trap were 0.61 eV, 1.1, and 1.7×10⁷ s^-1, respectively. In addition, the possibility of thermoluminescence analysis of scintillators using machine learning was confirmed.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.7
• /
• pp.11-18
• /
• 2023

In this paper, we evaluate deep learning time series forecasting models. Recent studies show that those models perform better than the traditional prediction model such as ARIMA. Among them, recurrent neural networks to store previous information in the hidden layer are one of the prediction models. In order to solve the gradient vanishing problem in the network, LSTM is used with small memory inside the recurrent neural network along with BI-LSTM in which the hidden layer is added in the reverse direction of the data flow. In this paper, we compared the performance of Informer by comparing with other models (LSTM, BI-LSTM, and Transformer) for real Nitrogen dioxide (NO2) data. In order to evaluate the accuracy of each method, mean square root error and mean absolute error between the real value and the predicted value were obtained. Consequently, Informer has improved prediction accuracy compared with other methods.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.155-160
• /
• 2023

This paper presents a method for predicting blood pressure using the photoplethysmography signals. First, after measuring the optical blood flow signal, artifacts are removed through a preprocessing process, and a signal for learning is obtained. In addition, weight and height, which affect blood pressure, are measured as additional information. Next, a system is built to estimate systolic and diastolic blood pressure by learning the photoplethysmography signals, height, and weight as input variables through an artificial intelligence algorithm. The constructed system predicts the systolic and diastolic blood pressures using the inputs. The proposed method can continuously predict blood pressure in real time by receiving photoplethysmography signals that reflect the state of the heart and blood vessels, and the height and weight of the subject in an unconstrained method. In order to confirm the usefulness of the artificial intelligence-based blood pressure prediction system presented in this study, the usefulness of the results is verified by comparing the measured blood pressure with the predicted blood pressure.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.99-107
• /
• 2024

While the demand for extrapolating video content horizontally or vertically is increasing, even the most advanced techniques cannot successfully extrapolate all videos. Therefore, it is important to determine if a given video can be well extrapolated before attempting the actual extrapolation. This can help avoid wasting computing resources. This paper proposes a video classifier that can identify if a video is suitable for horizontal extrapolation. The classifier utilizes optical flow and an adaptive Gaussian blur network, which can be applied to flow-based video extrapolation methods. The labeling for training was rigorously conducted through user tests and quantitative evaluations. As a result of learning from this labeled dataset, a network was developed to determine the extrapolation capability of a given video. The proposed classifier achieved much more accurate classification performance than methods that simply use the original video or fixed blur alone by effectively capturing the characteristics of the video through optical flow and adaptive Gaussian blur network. This classifier can be utilized in various fields in conjunction with automatic video extrapolation techniques for immersive viewing experiences.

• Knowledge Management Research
• /
• v.10 no.3
• /
• pp.51-80
• /
• 2009

The purpose of this study is to empirically analyze the impact that occurs when Korean organizations make practical use of various information technology tools and systems in the knowledge management process, such as sharing, learning and creating knowledge. Such a process is usually made through online and offline knowledge management activities. This paper also verifies how the externalization of tacit knowledge, and the internalization of explicit knowledge via the Internet and offline socialization activities have altered the mechanisms of knowledge transfers inside organizations. For the research, a survey was conducted on the satisfaction and usability levels of information technology, and the impact of IT usage on the results of knowledge management activities and knowledge transfers. 622 Korean organizations were surveyed, including major listed firms and public organizations. The results were examined as an online/offline integration process using SECI's Model proposed by Nonaka (1994, 1995). The analysis shows that information technology satisfaction and the usage of information technology help accelerate the pace of the knowledge flow and amplify the volume of the knowledge transfer by boosting the externalization and internalization processes-also known as knowledge management activities. However. there is no distinct correlation between information technology and socialization, an offline knowledge transferal activity. In particular, the quality of knowledge-an end result of knowledge transfer-does not improve merely by the externalization of online knowledge and instead requires the internalization of knowledge processes. Above all, the research reveals that offline socialization processes vastly contribute to the improvement of knowledge quality. This paper suggests that in order to ensure a transfer of quality knowledge, an organization or a company should focus on the use of information technology rather than the satisfaction level of information technology, and that knowledge transfers via the Internet has limitations in creating high quality of knowledge. For an organization to ensure the transfer of high-quality knowledge, the organization should not entirely hinge the transfer of knowledge online, as it is essential to have an offline method-a form of socialization such as a 'community of practice.'

• Journal of Korean Society of Transportation
• /
• v.18 no.4
• /
• pp.75-85
• /
• 2000

The Purpose of this study is to analyze wether the composition of training sample have a relation with the Predictive ability and the learning results of ANNs(Artificial Neural Networks) fur predicting one cycle ahead of the queue length(veh.) in a signalized intersection. In this study, ANNs\` training sample is classified into the assumption of two cases. The first is to utilize time-series(Per cycle) data of queue length which would be detected by one detector (loop or video) The second is to use time-space correlated data(such as: a upstream feed-in flow, a link travel time, a approach maximum stationary queue length, a departure volume) which would be detected by a integrative vehicle detection systems (loop detector, video detector, RFIDs) which would be installed between the upstream node(intersection) and downstream node. The major findings from this paper is In Daechi Intersection(GangNamGu, Seoul), in the case of ANNs\` training sample constructed by time-space correlated data between the upstream node(intersection) and downstream node, the pattern recognition ability of an interrupted traffic flow is better.

• Korean Journal of Oriental Medicine
• /
• v.10 no.1
• /
• pp.49-61
• /
• 2004

The Standardization of terms in The Pulse studies(脈學) is a need for development of learning. This study, for the correction of existing misused terms in The Pulse studies, we study on modernly and objectively the terms in The Pulse studies. By a focus of ${\ulcorner}$The Pulse Studies of Bin-Ho(瀕湖脈學)${\lrcorner}$, we studies on the new classification of pulse condition. The error of a existing technical books on Pulse studies begin that the classification of pulse condition is not establish a Standardization. For the correction of existing misused terms in The Pulse studies, we study on the pulse condition is expressed objectively a blood vessel that it is a subject of pulse condition. The expression of blood vessel contain a depth of blood vessel, a speed of pulsation, a curve of blood vessel, thickness of blood vessel, a diameter of blood vessel in expand and contract of blood vessel, a interval in expand and contract of blood vessel, a distinctness on a boundary of blood vessel, a speed of blood flow in blood vessel, a volume of blood flow in blood vessel, a condition of blood in blood vessel, a propelling power of blood vessel. These is standard of the new classification of pulse condition.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.232-237
• /
• 2013

A newly developed fall detection algorithm using the HMM (Hidden Markov Model) extracted from the video is introduced. To distinguish between the fall from personal difference fall pattern or the normal activities of daily living (ADL), HMM machine learning algorithm is used. For getting fall feature vector of video, the motion vector from the optical flow is applied to the PCA (Principal Component Analysis). The combination of the angle, ratio of long-short axis, velocity from results of PCA make the new fall feature parameters. These parameters were applied to the HMM and the results were compared and analyzed. Among the newly proposed various kinds of fall parameters, the angle of movement showed the best results. The results show that this parameter can distinguish various types of fall from ADLs with 91.5% sensitivity and 88.01% specificity.