• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.14 no.4
• /
• pp.367-384
• /
• 2016

Many countries have developed a safety case suitable to their own countries in order to improve the confidence of disposal safety in deep geological disposal of high-level radioactive waste as well as to develop a disposal program and obtain its license. This study introduces and summarizes the meaning, necessity, and development process of the safety case for radioactive waste disposal. The disposal safety is also discussed in various aspects of the safety case. In addition, the status of safety case development in the foreign countries is briefly introduced for Switzerland, Japan, the United States of America, Sweden, and Finland. The strategy for the safety case development that is being developed by KAERI is also briefly introduced. Based on the safety case, we analyze the efforts necessary to improve confidence in disposal safety for high-level radioactive waste. Considering domestic situations, we propose and discuss some implementing methods for the improvement of disposal safety, such as construction of a reliable information database, understanding of processes related to safety, reduction of uncertainties in safety assessment, communication with stakeholders, and ensuring justice and transparency. This study will contribute to the understanding of the safety case for deep geological disposal and to improving confidence in disposal safety through the development of the safety case in Korea for the disposal of high-level radioactive waste.

• Korean Journal of Materials Research
• /
• v.21 no.12
• /
• pp.639-643
• /
• 2011

Zinc oxide as an optoelectronic device material was studied to utilize its wide band gap of 3.37 eV and high exciton biding energy of 60 meV. Using anti-site nitrogen to generate p-type zinc oxide has shown a deep acceptor level and low solubility. To increase the nitrogen solubility in zinc oxide, group 13 elements (aluminum, gallium, and indium) was co-added to nitrogen. The effect of aluminum on nitrogen solubility in a $3{\times}3{\times}2$ zinc oxide super cell containing 72 atoms was investigated using density functional theory with hybrid functionals of Heyd, Scuseria, and Ernzerhof (HSE). Aluminum and nitrogen were substituted for zinc and oxygen sites in the super cell, respectively. The band gap of the undoped super cell was calculated to be 3.36 eV from the density of states, and was in good agreement with the experimentally obtained value. Formation energies of a nitrogen molecule and nitric oxide in the zinc oxide super cell in zinc-rich conditions were lower than those in oxygen-rich conditions. When the number of nitrogen molecules near the aluminum increased from one to four in the super cell, their formation energies decreased to approach the valence band maximum to some degree. However, the acceptor level of nitrogen in zinc oxide with the co-incorporation of aluminum was still deep.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.2993-3010
• /
• 2021

The job shop scheduling problem (JSSP) plays a critical role in smart manufacturing, an effective JSSP scheduler could save time cost and increase productivity. Conventional methods are very time-consumption and cannot deal with complicated JSSP instances as it uses one optimal algorithm to solve JSSP. This paper proposes an effective scheduler based on deep learning technology named self-supervised long-short term memory (SS-LSTM) to handle complex JSSP accurately. First, using the optimal method to generate sufficient training samples in small-scale JSSP. SS-LSTM is then applied to extract rich feature representations from generated training samples and decide the next action. In the proposed SS-LSTM, two channels are employed to reflect the full production statues. Specifically, the detailed-level channel records 18 detailed product information while the system-level channel reflects the type of whole system states identified by the k-means algorithm. Moreover, adopting a self-supervised mechanism with LSTM autoencoder to keep high feature extraction capacity simultaneously ensuring the reliable feature representative ability. The authors implemented, trained, and compared the proposed method with the other leading learning-based methods on some complicated JSSP instances. The experimental results have confirmed the effectiveness and priority of the proposed method for solving complex JSSP instances in terms of make-span.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.6
• /
• pp.43-52
• /
• 2022

We can sense somebody's feeling fatigue, which means that fatigue can be detected through sensing human biometric signals. Numerous researches for assessing fatigue are mostly focused on diagnosing the edge of disease-level fatigue. In this study, we adapt quantitative analysis approaches for estimating qualitative data, and propose video analysis models for measuring fatigue state. Proposed three deep-learning based classification models selectively include stages of video analysis: object detection, feature extraction and time-series frame analysis algorithms to evaluate each stage's effect toward dividing the state of fatigue. Using frontal face videos collected from various fatigue situations, our CNN model shows 0.67 accuracy, which means that we empirically show the video analysis models can meaningfully detect fatigue state. Also we suggest the way of model adaptation when training and validating video data for classifying fatigue.

• Journal of the Korean Institute of Navigation
• /
• v.19 no.2
• /
• pp.77-97
• /
• 1995

The protection of the marine environment is one of the main international legal problems in recent years. In parallel with the industrial development, a great quantity of chemical materials were used and in consequence, mass transportation of oil and other dangerous materials was required on the one hand, and discharge of industrial wasters drew also the attention on the other hand. Furthermore, oil tankers accidents, mass use of nuclear materials, sea-bed exploration and exploitation stimulated further deep human concern on the marine environment. The expansion of international concern to new and more dangerous sources of marine pollution regarded more strict and legal control on the Oil Tanker(DWT 95, 000tons, Cb=0.805) model. Calculation results are compared to the international, especially regional level. In particular, this study is concerned with the preservation of the Northeast Asian Seas surrounded by Japan, the Russian Far East, South Korea, North Korea, China and Taiwan. These adjacent countries must intensify cooperation regarding the prevention, reduction and control of the contamination of the sea. And this cooperation between the States concerned should, as much as possible, be aimed at maximizing the effectiveness of measures to prevent or abate transboundary environmental pollution. To achieve this purpose, States concerned should be imposed upon duties such as duty to assess the environmental impact, duty to inform, duty to consult and duty to assist on the basis of general principle of international law, international customary law and other various resolutions of international bodies. Depending on the nature and extent of actual or potential transboundary pollution with the use of a natural resource or the environment in general the establishment of some form of institutionalized cooperation between the States concerned may become useful or indispensable. The functions of this Organization are, inter alia, to keep the implementation of the Convention and the protocals under continuous observation, to make recommendations on regional or sub-regional rules and standards to be elaborated and on measures to be taken by the Contracting Parties, to be notified of any grave and imminent danger from pollution or threat of pollution by the Contracting Parties and to promote in close cooperation with appropriate governmental bodies additional measures to protect the marine environment of the Northeast Asian Seas, and so on. Above mentioned countries, first of all, are located within the Northeast Asian Seas geographically and, therefore, take responsibilities of preserving the clean sea against marine interferences regardless of any difference of the social, political and economic systems. They must be followed under the UNCLOS and other marine conventions. Under the present circumstances, Northeast Asian Seas will become dead seas in case that there is no instant and prompt action against pollution. Hence we have an absolute obligation to promote the development of the mandatory international environmental law, which in turn can faciliate more effective implementation of the regional cooperation by the neighbouring states within this area.

• Strategy21
• /
• s.41
• /
• pp.108-152
• /
• 2017

This paper aims to analyze hegemonic competition and the role of naval power. To this end the paper is composed of four chapters titled introduction, the role of naval power in the hegemonic competition, the role of naval power in the East Asia, and the lessons and implications for the Korean Peninsula. Since the modern era, the hegemonic competition in the East Asian region has been the intrusion and struggle process between the world system and the East Asian regional system, and the ocean between these two systems has become the goal and means of supremacy(hegemony). Currently, the hegemonic competition between the US and China consists of systemic competition at the global level and marine competition at the regional level. When South Korea is forced to make strategic choices in the course of the US-China hegemonic competition, naval power will be the first factor to be considered. The ROK is asymmetrically maintaining a deep dependency relationship with the United States in terms of security and China in relation to the economy. And while the ROK's national economic power is acquired from the ocean, the ROK's military power is imbalanced because it is centered on the ground forces. These international relations and asymmetric-unbalanced resources distribution will not be able to effectively cope with the hegemonic competition between the US and China in the future, and will limit Korea's strategic choice. Since naval power and forces are the prerequisites for the hegemonic competition or the maintenance of supremacy we must construct balanced naval forces(naval power) that are not subordinate to the ground forces at the national strategic level for the future of the country.

• Proceedings of the Korean Institute of Surface Engineering Conference
• /
• 2017.05a
• /
• pp.126-126
• /
• 2017

Using first principles calculations we unveil fundamental mechanism of hydrolysis reactions of two hazardous chemicals $PCl_3$ and $POCl_3$ with molecular water clusters nearby. It is found that the water molecules play a key role as a catalyst significantly lowing the activation barriers by transferring its protons to the reaction intermediates. Interestingly, torsional angles of molecular complexes at transition states are identified as a vital descriptor on the reaction rate. Analysis of charge distribution over the complexes further reinforces the finding with atomic level correlation between the torsional angle and variation of the orbital hybridization state of P in the complex. Electronic charge separation (or polarization) enhances thermodynamic stability of the activated complex at transition state and reduces the activation energy through hydrogen bonding network with water molecules nearby. Calculated potential energy surfaces (PES) for the hydrolysis reactions of $PCl_3$ and $POCl_3$ depict their two contrastingly different profiles of double- and triple-deep wells, respectively. It is ascribed to the unique double-bonding O=P in the $POCl_3$. Our results on the activation free energy show well agreements with previous experimental data within $7kcalmol^{-1}$ deviation.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.5
• /
• pp.330-337
• /
• 2022

Research on object detection algorithms using 2D data has already progressed to the level of commercialization and is being applied to various manufacturing industries. Object detection technology using 2D data has an effective advantage, there are technical limitations to accurate data generation and analysis. Since 2D data is two-axis data without a sense of depth, ambiguity arises when approached from a practical point of view. Advanced countries such as the United States are leading 3D data collection and research using 3D laser scanners. Existing processing and detection algorithms such as ICP and RANSAC show high accuracy, but are used as a processing speed problem in the processing of large-scale point cloud data. In this study, PointNet a representative technique for detecting objects using widely used 3D point cloud data is analyzed and described. And RandLA-Net, which overcomes the limitations of PointNet's performance and object prediction accuracy, is described a review of detection technology using point cloud data was conducted.

• Journal of information and communication convergence engineering
• /
• v.9 no.6
• /
• pp.725-728
• /
• 2011

Infrared transmission images from GaAs semi insulating wafers were considered for years as directly related to the quantum absorption by electrons on fundamental states of deep centers, especially EL2. The satisfying correspondence of these images with the dislocations revealed by etching or X ray topography or infrared tomography led to the opinion that a strong concentration of EL2 centers was to be expected in the immediate vicinity of the dislocations. More recent work indicates that contrary to the expected behavior the photoqu$\acute{e}$nching of transmission images at T=80K does not appreciably change the image structure itself but more largely the uniform background level of absorption. Such investigations show that the transmission images of isolated dislocations (Indium doped materials) or cell structures of tangled dislocations (undoped materials) can be partly attributed to scattered light; similar operation at T=10K removes the dark features associated to EL2 but still preserves the skeleton of the pattern which is due to scattering. A result of the measurements is that dislocations must not be considered any longer as inexhaustive EL2 reservoirs. The lifetime of the photoqu$\acute{e}$nching mechanism is shown to vary differently for EL2 centers located close to the dislocations or in the matrix. In this paper we will develop the details of infrared image photoqu$\acute{e}$nching experiments in the vicinity of dislocations; undoped and In doped GaAs materials will be shown. These results will be discussed in the light of surface etching experiments.