• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.4
• /
• pp.350-357
• /
• 1991

A speech recognition system based on a neural network, which can be used for telephon number services was tested. Because in Korea two different cardinal number systems, a koreanic one and a sinokoreanic one, are in use, it is necessary that the used systems is able to recognize 22 discret words. The structure of the neural network used had two layers, also a structure with 3 layers, one hidden layreformed of each 11, 22 and 44 hidden units was tested. During the learning phase of the system the so called BP-algorithm (back propagation) was applied. The process of learning can e influenced by using a different learning factor and also by the method of learning(for instance random or cycle). The optimal rate of speaker independent recognition by using a 2 layer neural network was 96%. A drop of recognition was observed by overtraining. This phenomen appeared more clearly if a 3 layer neural network was used. These phenomens are described in this paper in more detail. Especially the influence of the construction of the neural network and the several states during the learning phase are examined.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.3
• /
• pp.69-79
• /
• 2017

In this paper, we propose our four-phase life cycle of P2P botnet with corresponding detection methods and the future direction for more effective P2P botnet detection. Our proposals are based on the intensive analysis that compares existing P2P botnet detection schemes in different points of view such as life cycle of P2P botnet, machine learning methods for data mining based detection, composition of data sets, and performance matrix. Our proposed life cycle model composed of linear sequence stages suggests to utilize features in the vulnerable phase rather than the entire life cycle. In addition, we suggest the hybrid detection scheme with data mining based method and our proposed life cycle, and present the improved composition of experimental data sets through analysing the limitations of previous works.

• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.177-188
• /
• 2022

Recently, the application of distributed acoustic sensors (DAS), which can replace geophones and seismometers, has significantly increased along with interest in micro-seismic monitoring technique, which is one of the CO₂ storage monitoring techniques. A significant amount of temporally and spatially continuous data is recorded in a DAS monitoring system, thereby necessitating fast and accurate data processing techniques. Because event detection and seismic phase picking are the most basic data processing techniques, they should be performed on all data. In this study, a machine learning-based P, S wave phase picking algorithm was developed to compensate for the limitations of conventional phase picking algorithms, and it was modified using a transfer learning technique for the application of DAS data consisting of a single component with a low signal-to-noise ratio. Our model was constructed by modifying the convolution-based EQTransformer, which performs well in phase picking, to the ResUNet structure. Not only the global earthquake dataset, STEAD but also the augmented dataset was used as training datasets to enhance the prediction performance on the unseen characteristics of the target dataset. The performance of the developed algorithm was verified using K-net and KiK-net data with characteristics different from the training data. Additionally, after modifying the trained model to suit DAS data using the transfer learning technique, the performance was verified by applying it to the DAS field data measured in the Pohang Janggi basin.

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.8-17
• /
• 2019

The main purpose of this study isto explore the potential of affective computing (AC) platforms in education through two phases ofresearch: Phase I - platform analysis and Phase II - classification of academic emotions. In Phase I, the results indicate that the existing affective analysis platforms can be largely classified into four types according to the emotion detecting methods: (a) facial expression-based platforms, (b) biometric-based platforms, (c) text/verbal tone-based platforms, and (c) mixed methods platforms. In Phase II, we conducted an in-depth analysis of the emotional experience that a learner encounters in online video-based learning in order to establish the basis for a new classification system of online learner's emotions. Overall, positive emotions were shown more frequently and longer than negative emotions. We categorized positive emotions into three groups based on the facial expression data: (a) confidence; (b) excitement, enjoyment, and pleasure; and (c) aspiration, enthusiasm, and expectation. The same method was used to categorize negative emotions into four groups: (a) fear and anxiety, (b) embarrassment and shame, (c) frustration and alienation, and (d) boredom. Drawn from the results, we proposed a new classification scheme that can be used to measure and analyze how learners in online learning environments experience various positive and negative emotions with the indicators of facial expressions.

• Knowledge Management Research
• /
• v.5 no.2
• /
• pp.25-51
• /
• 2004

The purpose of this study is to investigate the knowledge creating pattern of technology catching-up and pioneering phase in the new product development process. This paper first reviews the knowledge conversion, absorptive capability, learning orientation and the trigger of learning. The paper then presents the integrative model of knowledge creating. Based on the integrative model, in-depth case analysis was conducted on the new product development process in Phicom. As a result, the paper discuss that the pattern of absorptive capability building, knowledge conversion and knowledge transfer is different from technology catching-up and pioneering phase. Finally, the implications and limitations of the study are discussed.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.2
• /
• pp.23-27
• /
• 2024

Underwater images are typically degraded due to color distortion, light absorption, scattering, and noise from artificial light sources. Restoration of these images is an essential task in many underwater applications. In this paper, we propose a two-phase deep learning-based method, Underwater Deep Curve Estimation (UWDCE), designed to effectively enhance the quality of underwater images. The first phase involves a white balancing and color correction technique to compensate for color imbalances. The second phase introduces a novel deep learning model, UWDCE, to learn the mapping between the color-corrected image and its best-fitting curve parameter maps. The model operates iteratively, applying light-enhancement curves to achieve better contrast and maintain pixel values within a normalized range. The results demonstrate the effectiveness of our method, producing higher-quality images compared to state-of-the-art methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.6
• /
• pp.571-576
• /
• 1999

We consider a class of auto-associative memories namely N-Cubes (Neural-network Cubes) in which 2-D gray-level images and hidden sinusoidal 1-D wavelets are stored in cubical memories. First we develop a learning procedure based upon the least-squares algorithm, Therefore each 2-D training image is mapped into the associated 1-D waveform in the training phase. Second we show how the recall procedure minimizes errors among the orthogonal basis functions in the hidden layer. As a 2-D images ould be retrieved in the recall phase. Simulation results confirm the efficiency and the noise-free properties of N-Cubes.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.4
• /
• pp.78-89
• /
• 2012

The generated torque of a switched reluctance(SR) motor is highly nonlinear, which makes it difficult to determine the reference current commands for minimum torque ripples. In this paper, we present a computationally simple and efficient method to minimize torque ripples of SR motors based on iterative learning control. The reference current command of each phase minimizing torque ripples is identified in 2-dimensional look-up table form. Our learning control algorithm does not require the torque model, so our method is not affected by model errors and hence is very accurate. In order to justify our work, we present some computer simulation results.

• The Journal of Korea Robotics Society
• /
• v.15 no.2
• /
• pp.197-204
• /
• 2020

In this paper, we present a learning platform for robotic grasping in real world, in which actor-critic deep reinforcement learning is employed to directly learn the grasping skill from raw image pixels and rarely observed rewards. This is a challenging task because existing algorithms based on deep reinforcement learning require an extensive number of training data or massive computational cost so that they cannot be affordable in real world settings. To address this problems, the proposed learning platform basically consists of two training phases; a learning phase in simulator and subsequent learning in real world. Here, main processing blocks in the platform are extraction of latent vector based on state representation learning and disentanglement of a raw image, generation of adapted synthetic image using generative adversarial networks, and object detection and arm segmentation for the disentanglement. We demonstrate the effectiveness of this approach in a real environment.

• Journal of Digital Convergence
• /
• v.3 no.2
• /
• pp.143-157
• /
• 2005

Many papers point out that the e-Learning is one of the most important industries, and the effect on other industries can be more powerful than any other business. Therefore, we think about social, cultural, industrial and technological effect of the e-Learning in order to enlarge industry scale as well as educational performances. In many cases of developed countries, various kinds of study have been performed for the e-Learning quality assurance because quality of the e-learning should operate on effective and efficient learning and continuous market development of education industries. The e-Learning quality assurance has import function not only for learning contents reusability like a SCORM and metadata but also for learning system, solution and service operation, so activities for the quality assurance should consider of cultural and tactical approach when it is applied in the e-learning business. In this paper, we present the concept, domain and purpose of the e-Learning quality assurance. Furthermore, this paper proposes the process and methodology in order to make the quality assurance standard model which is consist of 6 phase such as Environment Research, Needs Analysis, Framework, Metrics, Development and Implementation, Evaluation and Feedback through the analysis and comparison of pre-studied worldwide quality control, management and assurance documents.