• Title/Summary/Keyword: RL

Search Result 433, Processing Time 0.033 seconds

Reinforcing Reverse Logistics Activities in Closed-loop Supply Chain Model: Hybrid Genetic Algorithm Approach (폐쇄루프공급망모델에서 역물류 활동 강화: 혼합유전알고리즘 접근법)

  • Yun, YoungSu
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.26 no.1
    • /
    • pp.55-65
    • /
    • 2021
  • In this paper, a methodology for reinforcing reverse logistics (RL) activities in a closed-loop supply chain (CLSC) model is proposed. For the methodology, the activities of the recovery center (RC) which can be considered as one of the facilities in the RL are reinforced. By the reinforced activities in the RC, the recovered parts and products after checking and recovering processes of the returned product from customer can be reused in the forward logistics (FL) of the CLSC model. A mathematical formulation is suggested for representing the CLSC model with reinforced RL activities, and implemented using a hybrid genetic algorithm (HGA) approach. In numerical experiment, two different scales of the CLSC model are presented and the performance of the HGA approach is compared with those of some conventional approaches. The experimental results show that the former outperforms the latter in most of performance measures. The robustness of the CLSC model is also proved by regulating various rates of the recovered parts and products in the RC.

Development and Clinical Application of Real-Time Light-Guided Vocal Fold Injection (실시간 광유도 성대주입술의 개발과 임상적 적용)

  • Huh, Gene;Cha, Wonjae
    • Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
    • /
    • v.33 no.1
    • /
    • pp.1-6
    • /
    • 2022
  • Vocal fold injection (VFI) is widely accepted as a first line treatment in treating unilateral vocal fold paralysis and other vocal fold diseases. Although VFI is advantageous for its minimal invasiveness and efficiency, the invisibility of the needle tip remains an essential handicap in precise localization. Real-time light-guided vocal fold injection (RL-VFI) is a novel technique that was developed under the concept of performing simultaneous injection with precise placement of the needle tip under light guidance. RL-VFI has confirmed its possibility of technical implementation and the feasibility in injecting the needle from various directions through ex vivo animal studies. Further in vivo animal study has approved the safety and feasibility of the procedure when various transcutaneous approaches were applied. Currently, RL-VFI device is authorized for clinical use by the Ministry of Food and Drug Safety in South Korea and is clinically applied to patients with safe and favorable outcome. Several clinical studies are currently under process to approve the safety and the efficiency of RL-VFI. RL-VFI is expected to improve the complication rate and the functional outcome of voice. Furthermore, it will support laryngologists in overcoming the steep learning curve by its intuitive guidance.

Development of Optimal Design Technique of RC Beam using Multi-Agent Reinforcement Learning (다중 에이전트 강화학습을 이용한 RC보 최적설계 기술개발)

  • Kang, Joo-Won;Kim, Hyun-Su
    • Journal of Korean Association for Spatial Structures
    • /
    • v.23 no.2
    • /
    • pp.29-36
    • /
    • 2023
  • Reinforcement learning (RL) is widely applied to various engineering fields. Especially, RL has shown successful performance for control problems, such as vehicles, robotics, and active structural control system. However, little research on application of RL to optimal structural design has conducted to date. In this study, the possibility of application of RL to structural design of reinforced concrete (RC) beam was investigated. The example of RC beam structural design problem introduced in previous study was used for comparative study. Deep q-network (DQN) is a famous RL algorithm presenting good performance in the discrete action space and thus it was used in this study. The action of DQN agent is required to represent design variables of RC beam. However, the number of design variables of RC beam is too many to represent by the action of conventional DQN. To solve this problem, multi-agent DQN was used in this study. For more effective reinforcement learning process, DDQN (Double Q-Learning) that is an advanced version of a conventional DQN was employed. The multi-agent of DDQN was trained for optimal structural design of RC beam to satisfy American Concrete Institute (318) without any hand-labeled dataset. Five agents of DDQN provides actions for beam with, beam depth, main rebar size, number of main rebar, and shear stirrup size, respectively. Five agents of DDQN were trained for 10,000 episodes and the performance of the multi-agent of DDQN was evaluated with 100 test design cases. This study shows that the multi-agent DDQN algorithm can provide successfully structural design results of RC beam.

Effects of Acclimatization to Different Light Colors on the Growth of Petunia (Petunia hybrida) in a Greenhouse (조직배양 페튜니아의 순화과정에서 광질에 따른 생장반응 특성)

  • Young-Sun Kim;Geung-Joo Lee
    • Korean Journal of Environmental Agriculture
    • /
    • v.42 no.1
    • /
    • pp.14-20
    • /
    • 2023
  • Light is an important factor that influences the growth and development of flowering plants. The present study investigated the effects of in vitro acclimatization to different light colors (white light (WL; control), blue light (BL; 447 nm), green light (GL; 519 nm), and red light (RL; 667 nm)) on the growth of petunia (Petunia hybrida) and of hardening cultivation of plant transferred form in vitro to a greenhouse under sunlight. Compared to the control, the shoot length and leaf width of Petunia increased by 42% and 11.7%, respectively, after acclimatization to BL and the shoot growth increased by 29.3% after acclimatization to RL. The chlorophyll and carotenoid contents after acclimatization to BL and GL were 16.7% and 11.3% higher, respectively, and 14.4% and 11.9% higher, respectively, than those in the control. During greenhouse cultivation, the shoot length increased by 16.7% and 11.3%, respectively, after acclimatization to BL and RL, respectively, and the leaf length and leaf width increased by 14.4% and 11.9%, respectively, after acclimatization to GL. While dry weight of root of GL and BL was not significant difference in vitro, increased by 59.0% and 22.9% ex vitro than that of WL. Thus, acclimatization to BL increased the shoot growth and leaf chlorophyll contents, and acclimatization to GL and RL enhanced shoot and root growth, in petunia.

Effects of the difference between actual body condition and body image perception on nutrient intake, weight control and mental health in Korean adults: Based on the 5th Korea National Health and Nutrition Examination Survey (한국 성인의 체질량 지수에 따른 비만도와 주관적 체형인식 간의 차이가 영양소 섭취와 체중조절 및 정신건강에 미치는 영향 : 제 5기 국민건강영양조사 자료를 이용하여)

  • Seo, Jihyun;Ma, Hyesun;Kim, Sunghee;Kim, Jiyoung;Shin, Minseo;Yang, Yoon Jung
    • Journal of Nutrition and Health
    • /
    • v.49 no.3
    • /
    • pp.153-164
    • /
    • 2016
  • Purpose: The objective of this study was to examine the effect of the body shape discordance, the difference between true body type based on body mass index (BMI) and self-recognized body image, on nutrient intake, weight control attempt, and mental health in Korean adults. Methods: Subjects were persons aged 19~64 years (4,382 men and 6,226 women) who participated in the 2010~2012 Korea National Health and Nutrition Examination Survey. Subjects were categorized as RL (Group recognized as lighter than BMI criteria), RA (Group with agreement between BMI criteria and self-recognized body image), and RH (Group recognized as heavier than BMI criteria) according to the difference between actual body type based on BMI and self-recognized body image. Results: Means of BMI in RH groups were lower than or equal to that of RA groups in all groups. No significant differences in total energy intake were observed among the three groups in men, but total energy intake was higher in the RL group than in the RH group in 30~49 year old women. Proportion of carbohydrate was the highest in the RL group among 30~49 year old women. RH groups paid more attention to weight control and had less weight gain than other groups. Higher proportions of depressive symptoms were reported in the RH group in 19~29 year old men, while a higher proportion of depressive symptoms were reported in the RL group in 50~64 year old men. Conclusion: The current findings suggest an association of perceiving body shape with energy intake, weight control attempt, or depressed mood in some age groups. Body image perception can influence eating, weight control attempt, and depressed mood, therefore proper body image perception should be established in Korean adults.

A Study on a RL-Photocoupler Circuit for Chaos Oscillation (카오스 발진을 위한 RL-광결합기 회로 연구)

  • 정동호;정설희
    • Proceedings of the IEEK Conference
    • /
    • 2003.07c
    • /
    • pp.2835-2838
    • /
    • 2003
  • We study the characteristics of oscillating in non-autonomous condition and the conducted noise generation in a RL-photocoupler circuit. This circuit may be shown a period-doubling and a chaos dynamics under any specific conditions of input circuit. But, the relationship between input signals and output signals is different according to the amplitude of driving input voltage. Then, the oscillation noise was analyzed with respect to both the frequency and the amplitude of an external ac signal and do values. The results show that the noise-induced oscillations for falling and rising cycles induced by kick-back effect in an inductor, nonlinear capacitance, nonlinear resistance and charge storage time in a diode and an LED. We also compared the simulation with the experimental results.

  • PDF

Cloning and Expression of B. Aphaericus insecticidal toxin gene in E. coli

  • Lim, Pyong-Ok;Lee, Hong-Sup;Lee, Hyung-Hoan
    • Proceedings of the Korean Society for Applied Microbiology Conference
    • /
    • 1986.12a
    • /
    • pp.515.2-515
    • /
    • 1986
  • B. sphaericus 1593 K-5 synthesize a potent entomicidal toxin against mosquito larvae. B. sphaericus EcoRl DNA fragment carrying the biocidal activity was clonied and expression in E. coli JM83. For the construction of a recombinant plasmid bearing the toxin activity the DNA of B. sphaericus was partially digested by the EcoRl. The EcoRl DNA fragments were ligated to plasmid pUC 8-EcoR1 site. The transformants were selected on LB plates containing X-gall and ampicilline. The transformants were bioassayed against mosquito larvae of which two clones showed biocidal activity. The two clones were redigested with Eco R1 and analyzed by 0.7% agarose gel electrophorsis.

  • PDF

On the Spectral Shape of Non-recycled γ-ray Pulsars

  • Hui, Chung-Yue;Lee, Jongsu
    • Journal of Astronomy and Space Sciences
    • /
    • v.33 no.2
    • /
    • pp.101-104
    • /
    • 2016
  • More than 100 γ−ray pulsars have been discovered by the Fermi Gamma-ray Space Telescope. With a significantly enlarged sample size, it is possible to compare the properties of different classes. Radio-quiet (RQ) γ−ray pulsars form a distinct population, and various studies have shown that the properties of the RQ population can be intrinsically different from those of radio-loud (RL) pulsars. Utilizing these differences, it is possible to further classify the pulsar-like unidentified γ−ray sources into sub-groups. In this study, we suggest the possibility of distinguishing RQ/RL pulsars by their spectral shape. We compute the probabilities of a pulsar to be RQ or RL for a given spectral curvature. This can provide a key to the estimation of the intrinsic fraction of radio-quietness in the γ−ray pulsar population, which can place a tight constraint on the emission geometry.

Labeling Q-Learning for Maze Problems with Partially Observable States

  • Lee, Hae-Yeon;Hiroyuki Kamaya;Kenich Abe
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2000.10a
    • /
    • pp.489-489
    • /
    • 2000
  • Recently, Reinforcement Learning(RL) methods have been used far teaming problems in Partially Observable Markov Decision Process(POMDP) environments. Conventional RL-methods, however, have limited applicability to POMDP To overcome the partial observability, several algorithms were proposed [5], [7]. The aim of this paper is to extend our previous algorithm for POMDP, called Labeling Q-learning(LQ-learning), which reinforces incomplete information of perception with labeling. Namely, in the LQ-learning, the agent percepts the current states by pair of observation and its label, and the agent can distinguish states, which look as same, more exactly. Labeling is carried out by a hash-like function, which we call Labeling Function(LF). Numerous labeling functions can be considered, but in this paper, we will introduce several labeling functions based on only 2 or 3 immediate past sequential observations. We introduce the basic idea of LQ-learning briefly, apply it to maze problems, simple POMDP environments, and show its availability with empirical results, look better than conventional RL algorithms.

  • PDF

Cloning of Biosurfactant-Producing Gene from Bacillus subtilis KL-57 (Bacillus subtilis KL-57로부터 생산되는 생체계면활성제 합성 유전자 클로닝)

  • 강상모;이병옥;이철수
    • Microbiology and Biotechnology Letters
    • /
    • v.22 no.6
    • /
    • pp.593-598
    • /
    • 1994
  • A bacterium KL-57 which exhibited biosurfactant activity was isolated. This bacterium was identified as Bacillus subtilis. The biosurfactant-producing gene of B. subtilis KL-57 was cloned into R subtilis MI113 by using plasmid pTB523. The plasmid DNA from the clone was found to carry a 18 kb PstI insert. The biosurfactant-producing gene was cleaved into 4 fragments by SmaI, 3 fragments by PvulI or EcoRl, 4 fragments by PvulI and EcoRI double digestion, 5 fragments by AccI, and 2 fragments by KpnI, HindIII or BamHI. By subcloning the 18 kb Pstl insert, a 2.3 kb EcoRl fragment conferred the biosurfactant producing activity on B. subtilis cells. The 2.3 kb had one HindIII cleave site. But Two fragments, which corresponds HindIII/EcoRl termini, exhibited no biosurfactant activity.

  • PDF