• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.2
• /
• pp.33-38
• /
• 2020

Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.273-281
• /
• 2022

In this paper, we propose a robot sound recognition system that detects various sound events. The proposed system is designed to detect various sound events in real-time by using a microphone on a robot. To get real-time performance, we use a VGG11 model which includes several convolutional neural networks with real-time normalization scheme. The VGG11 model is trained on augmented DB through 24 kinds of various environments (12 reverberation times and 2 signal to noise ratios). Additionally, based on random forest algorithm, a decision logic is also designed to generate event signals for robot applications. This logic can be used for specific classes of acoustic events with better performance than just using outputs of network model. With some experimental results, the performance of proposed sound recognition system is shown on real-time device for robots.

• Journal of Digital Contents Society
• /
• v.18 no.3
• /
• pp.499-508
• /
• 2017

With the recent advance of IT technology and the change of education paradigm, vocational training has been also evolved. In the background of mobilization of learning, increase of bite-size contents, and the agility of just-in-time learning, this study surveyed the online learners' motivation, perceptions, and learning behaviour. Total 4,021 learners from 6 distance learning institutions revealed that learners take the e-learning courses due to more for their self-development than the company's supports and policy. Also, they perceived the subject matter in contents are the most important. The results from this study suggest that the development of contents should focus on the subject matter that can be utilized for their jobs immediately. Lastly, the study confirms that learning space and time has been changed in the flexible way to use their spare time between work and life. Irregularity of learning and hasty preparations were one of major characteristics in the aspect of learning behaviour.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.04a
• /
• pp.869-879
• /
• 1995

The new field of learning control develops controllers that learn to improve their performance at executing a given task, based on experience performing this task. The simplest forms of learning control are based on the same concept as integral control, but operating in the domain of the repetitions of the task. In the previous paper, I had studied the use of such controllers in a decentralized system, such as a robot with the controller for each link acting independently. The basic result of the paper is to show that stability of the learning controllers for all subsystems when the coupling between subsystems is turned off, assures stability of the decentralized learning in the coupled system, provided that the sample time in the digital learning controller is sufficiently short. In this paper, we present two examples. The first illustrates the effect of coupling between subsystems in the system dynamics, and the second studies the application of decentralized learning control to robot problems. The latter example illustrates the application of decentralized learning control to nonlinear systems, and also studies the effect of the coupling between subsystems introduced in the input matrix by the discretization of the system equations. The conclusion is that for sufficiently small learning gain, and sufficiently small sample time, the simple learning control law based on integral control applied to each robot axis will produce zero tracking error in spite o the dynamic coupling in the robot equations. Of course, the results of this paper have much more general application than just to the robotics tracking problem. Convergence in decentralized systems is seen to depend only on the input and output matrices, provided the sample time is suffiently small.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.993-996
• /
• 2009

The object of this study is to make leaners have studying environment to study adaptively, any where, any one, any time, and just in time. So, it helps leaners find solutions to questions and problems which they can face in the process of learning. This study tried to find a solution to possibility of ontologied electronic circuit, after consideration of the Semantic web and ontology theory through studying of Sundry records. As the result, I established the ontology frame about the electronic circuit, and I studied on application for e-learning based on the Semantic web ontology.

• Journal of Engineering Education Research
• /
• v.26 no.6
• /
• pp.79-86
• /
• 2023

In our research, we delved into the impact of video length assigned for pre-class assignments on students' level of engagement. What we discovered is that as the length of the video increases, student engagement tends to decrease and the time allocated for homework preparation does not significantly influence engagement, as many students tend to complete their assignments just before the due date. Interestingly, the well-known "6-minute rule" often advocated for online educational videos does not align with the dynamics of real university settings. Whether in traditional lecture-based classes or flipped learning environments, students exhibit a high degree of self-responsibility when it comes to video consumption. Our findings strongly suggest that, in the context of flipped learning, it is advisable to create videos that are shorter than 15 minutes in length.

• Journal of Fisheries and Marine Sciences Education
• /
• v.24 no.2
• /
• pp.180-202
• /
• 2012

The purpose of this study was to extract an u-PBL support system core value and design strategy based upon field experience learning. To accomplish this the study, first of all, analyzed the core values, design strategy which was selected after needs analysis and literature review of theories and cases regarding the PBL, e-PBL, blended-PBL, Field experience learning based on ubiquitous environment, and learning model based on ubiquitous technology. This study identified the three core values as; systemic support for instructional activity, just in time support for instructional activity and support for interaction facilitation. As further research areas, it might be useful to develop u-PBL instructional support system based upon the model designed from this study. Also, research concerning the verification of the model based upon implementation of the program case might be necessary.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.3
• /
• pp.98-105
• /
• 2021

The sensory stimulation of a cosmetic product has been deemed to be an ancillary aspect until a decade ago. That point of view has drastically changed on different levels in just a decade. Nowadays cosmetic formulators should unavoidably meet the needs of consumers who want sensory satisfaction, although they do not have much time for new product development. The selection of new products from candidate products largely depend on the panel of human sensory experts. As new product development cycle time decreases, the formulators wanted to find systematic tools that are required to filter candidate products into a short list. Traditional statistical analysis on most physical property tests for the products including tribology tests and rheology tests, do not give any sound foundation for filtering candidate products. In this paper, we suggest a deep learning-based analysis method to identify hand cream products by raw electric signals from tribological sliding test. We compare the result of the deep learning-based method using raw data as input with the results of several machine learning-based analysis methods using manually extracted features as input. Among them, ResNet that is a deep learning model proved to be the best method to identify hand cream used in the test. According to our search in the scientific reported papers, this is the first attempt for predicting test cosmetic product with only raw time-series friction data without any manual feature extraction. Automatic product identification capability without manually extracted features can be used to narrow down the list of the newly developed candidate products.

• The Journal of the Korea Contents Association
• /
• v.7 no.12
• /
• pp.283-291
• /
• 2007

In the age of ubiquitous computing, computer systems will be seamlessly integrated into our everyday life, providing services and information to us in an anywhere, anytime fashion. This ubiquitous computing can be used for developing a ubiquitous learning (U-learning). In this paper, we present a framework for U-school in which ubiquitous computing technologies are applied to advance the existing ERSS (Korea's Educational Resources Sharing System). Our framework applies mobile, sensor, and context-aware technologies to the existing ERSS. This framework presents a user-centric learning environment, using user-centric scenario. The U-school with context-aware services therefore can lead to the just-in-time learning or learner-led learning based on dynamic contexts acquired from learners, teachers and computing entities.