• Title/Summary/Keyword: Parameters Optimization

Search Result 3,253, Processing Time 0.026 seconds

R-Trader: An Automatic Stock Trading System based on Reinforcement learning (R-Trader: 강화 학습에 기반한 자동 주식 거래 시스템)

  • 이재원;김성동;이종우;채진석
    • Journal of KIISE:Software and Applications
    • /
    • v.29 no.11
    • /
    • pp.785-794
    • /
    • 2002
  • Automatic stock trading systems should be able to solve various kinds of optimization problems such as market trend prediction, stock selection, and trading strategies, in a unified framework. But most of the previous trading systems based on supervised learning have a limit in the ultimate performance, because they are not mainly concerned in the integration of those subproblems. This paper proposes a stock trading system, called R-Trader, based on reinforcement teaming, regarding the process of stock price changes as Markov decision process (MDP). Reinforcement learning is suitable for Joint optimization of predictions and trading strategies. R-Trader adopts two popular reinforcement learning algorithms, temporal-difference (TD) and Q, for selecting stocks and optimizing other trading parameters respectively. Technical analysis is also adopted to devise the input features of the system and value functions are approximated by feedforward neural networks. Experimental results on the Korea stock market show that the proposed system outperforms the market average and also a simple trading system trained by supervised learning both in profit and risk management.

Comparison of response surface methods for the optimization of an upflow anaerobic sludge blanket for the treatment of slaughterhouse wastewater

  • Chollom, Martha Noro;Rathilal, Sudesh;Swalaha, Feroz Mohammed;Bakare, Babatunde Femi;Tetteh, Emmanuel Kweinor
    • Environmental Engineering Research
    • /
    • v.25 no.1
    • /
    • pp.114-122
    • /
    • 2020
  • This study was aimed at using the Central Composite Design (CCD) and Box-Behnken Design (BBD) to compare the efficiency and to elucidate the main interacting parameters in the upflow anaerobic sludge blanket (UASB) reactor, namely: Organic Loading Rate (OLR), Hydraulic Retention Times (HRT) and pH at a constant temperature of 35℃. Optimum HRT (15 h), OLR (3.5 kg.m-3.d-1) and pH (7) resulted in biogas production of 5,800 mL/d and COD removal of 80.8%. BBD produced a higher desirability efficiency of 94% as compared to the CCD which was 92%. The regression quadratic models developed with high R2 values of 0.961 and 0.978 for both CCD and BBD, respectively, demonstrated that the interaction models could be used to pilot the design space. BBD model developed was more reliable with a higher prediction of biogas production (5,955.4 ± 225.3 mL/d) and COD removal (81.5 ± 1.014%), much close to the experimental results at a 95% confidence level. CCD model predictions was greater in terms of COD removal (82.6 ± 1.06% > 80.8%) and biogas production (4,636.31 mL/d ± 439.81 < 5,800 mL/d) which was less than the experimental results. Therefore, RSM can be adapted for optimizing various wastewater treatment processes.

Modeling and Optimization of High Strength Wastewater Treatment Using the Electro Oxidation Process (전기산화공법을 이용한 고농도폐수 처리공정의 모델링 및 최적화)

  • Lee, Hongmin;Lee, Sangsun;Hwang, Sungwon;Jin, Dongbok
    • Korean Chemical Engineering Research
    • /
    • v.54 no.3
    • /
    • pp.340-349
    • /
    • 2016
  • Electro oxidation system was designed in this study for the reduction of COD (Chemical Oxygen Demand) from high-strength wastewater, produced during refinery turnaround period. First, BDD (Boron Doped Diamond) electrode was synthesized and electro oxidation system of actual industrial wastewater was developed by adopting the synthesized BDD electrode. The experiments were carried out under various operating conditions under certain range of current density, pH, electrolyte concentration and reaction time. Secondly, reaction kinetics were identified based on the experimental results, and the kinetics were embedded into a genetic mathematical model of the electro oxidation system. Lastly, design and operating parameters of the process were optimized to maximize the efficiency of the pretreatment system. The coefficient of determination ($R^2$) of the model was found to be 0.982, and it proved high accuracy of the model compared with experimental results.

Optimization of Adsorbent Treatment Process for the Purification of Paclitaxel from Plant Cell Cultures of Taxus chinensis (주목 식물세포(Taxus chinensis)배양으로부터 파클리탁셀 정제를 위한 흡착제 처리 공정 최적화)

  • Lee, Chung-Gi;Kim, Jin-Hyun
    • Korean Chemical Engineering Research
    • /
    • v.52 no.4
    • /
    • pp.497-502
    • /
    • 2014
  • Biomass-derived tar and waxy compounds have a highly negative effect on the separation and purification of paclitaxel and should be removed prior to final purification. Adsorbent treatment is a simple, efficient method for removal of tar and waxy compounds from plant cell cultures. In this study, we optimized the important process parameters (adsorption temperature, time, solvent type and adsorbent amount) of adsorbent treatment with Sylopute to remove the tar and waxy compounds in a pre-purification step. The optimal adsorption temperature, adsorption time, solvent type, and crude extract/Sylopute ratio were $30^{\circ}C$, 15 min, methylene chloride, and 1:1(w/w), respectively. This result could be confirmed by HPLC analysis of the absorbent after treatment and TGA of the organic substances that were bound to the adsorbent. In adsorbent treatment step, the purity seemed to show a small improvement but this treatment had a significant effect on convenience and feasibility of following steps by the removal of tar and waxy compounds.

Optimization of powder compaction parameters for the pressureless sintered ZTA (상압소결 ZTA의 분말 성형 공정 최적화)

  • 신동우;김경도;박삼식;임창성;이수완
    • Journal of the Korean Crystal Growth and Crystal Technology
    • /
    • v.8 no.2
    • /
    • pp.356-364
    • /
    • 1998
  • The dependence of green and sintered densities of Zirconia-Toughened Alumina ($ZTA:\;Al_2O_3/\;15\;vol{%}\;ZrO_2$) on the properties of spray-dried granules was studied thoroughly to establish the optimum compaction condition leading to high reproducibility in the light of sintered density. The sphericity, mean size, degree of hollow occurrence and moisture content of spray-dried granules were largely different in between the granule containing binder and the ones with no binder. The effect of these differences in the characteristic of granules on the compaction behavior was examined in terms of the compaction pressure from 80 MPa to 120 MPa 10 MPa increment and the compaction method, i.e., uniaxial and cold isostatic pressing. This work confirmed that the reproducibility of sintered density caused by the variation of granule property could be improved by the optimization of compaction process. The variation of sintered density was controlled within 1 % deviation by compacting the granules under a relatively low pressure of 80 MPa in an uniaxial forming and subsequent cold isostatic pressing at high pressure of 500 MPa.

  • PDF

Dual Band Design of Aperture-Coupled Cavity-Fed Microstrip Antenna (이중 대역 개구면 결합 공진기 급전 마이크로스트립 안테나 설계)

  • Jang, Guk-Hyun;Nam, Kyung-Min;Lee, Jang-Hwan;Nam, Sang-Ho;Kim, Chul-Un;Kim, Jeong-Phill
    • Journal of the Institute of Electronics Engineers of Korea TC
    • /
    • v.44 no.3 s.357
    • /
    • pp.26-32
    • /
    • 2007
  • A simple but accurate equivalent circuit of an aperture-coupled cavity-fed microstrip patch antenna is developed. It consists of ideal transformers, admittance elements, and transmission lines, and the related circuit element values are computed by applying the reciprocity theorem and complex power concept with the spectral-domain immittance approach. After validating by the published design example, a dual-band antenna was designed with the help of a hybrid optimization method. For this purpose, the Genetic Algorithm is applied with the Nelder-Mead simplex method. The obtained good results show that this approach turned out to be a very efficient tool for the design of aperture-coupled cavity-fed microstrip patch antenna having various structural design parameters.

Opitmal Design Technique of Nielsen Arch Bridges by Using Genetic Algorithm (유전자 알고리즘을 이용한 닐센아치교의 최적설계기법)

  • Lee, Kwang Su;Chung, Young Soo
    • Journal of Korean Society of Steel Construction
    • /
    • v.21 no.4
    • /
    • pp.361-373
    • /
    • 2009
  • Using the genetic algorithm, the optimal-design technique of the Nielsen arch bridge was proposed in this paper. The design parameters were the arch-rise ratio and the steel weight ratio of the Nielsen arch bridge, and optimal-design techniques were utilized to analyze the behavior of the bridge. The optimal parameter values were determined for the estimated optimal level. The parameter determination requires the standardization of the safety, utility, and economic concepts as the critical factors of a structure. For this, a genetic algorithm was used, whose global-optimal-solution search ability is superior to the optimization technique, and whose object function in the optimal design is the total weight of the structure. The constraints for the optimization were displacement, internal stress, and time and space. The structural analysis was a combination of the small displacement theory and the genetic algorithm, and the runtime was reduced for parallel processing. The optimal-design technique that was developed in this study was employed and deduced using the optimal arch-rise ratio, steel weight ratio, and optimal-design domain. The optimal-design technique was presented so it could be applied in the industry.

Optimization Techniques for Soil Parameters used in Axisymmetric Nonlinear Consolidation Analysis (축대칭 비선형 압밀해석을 위한 지반정수값의 최적화기법)

  • 김윤태;이승래
    • Geotechnical Engineering
    • /
    • v.12 no.4
    • /
    • pp.131-144
    • /
    • 1996
  • In order to accelerate the rate of consolidation settlement and to gain a required shear strength for a given soft clay deposit, the preloadina technique combined with a vertical drainage system has been widely applied. Even if a sophisticated numerical analysis technique is applied to solve the consolidation behavior of drainage-installed soft deposits, the actual field behavior is often different from the behavior predicted in the design state due to several uncertainties involved in soil properties, numerical modelling, and measuring system. In this paper, two back-analysis schemes such hs simplex and BFGS methods have been implemented in an a Bisymmetric consolidation program, AXICON which considers the variation of compressibility and permeability during the consolidation process. Utilizing the program, one might be able to appropriately predict the subsequent consolidation behavior from the measured data in an early stage of consolidation of drainage-installed soft deposits.

  • PDF

Optimization of Hydrogen Production Using the Mixed Microflora Isolated from Sewage Sludge (하수슬러지로부터 분리된 혐기세균에 의한 수소생산 최적화)

  • Oh, You-Kwan;Kim, Mi-Sun
    • Transactions of the Korean hydrogen and new energy society
    • /
    • v.19 no.1
    • /
    • pp.41-48
    • /
    • 2008
  • Fermentative $H_2$ production was studied using microbial consortia isolated from heat-treated ($90{\circ}C$, 20 min) sewage sludge. Important parameters investigated were carbon(C) and nitrogen(N)-sources, C/N ratio, phosphate concentration, pH and temperature during anaerobic cultivation in serum bottles. Starch, ribose, sucrose and glucose were good C-sources for the culture growth and $H_2$ production. Yeast extract was better N-source than $(NH_4)_2SO_4$ or peptone when individually added to the synthetic media, however the combination of above three N-sources exhibited the additional effect for cell growth and $H_2$ evolution. Addition of 100 mM phosphate as a buffering agent prevented the rapid pH drop during the cultivation. The optimum initial pH for the cell growth was at 7.0, whereas $H_2$ production was observed at pH 5.5. Optimum temperature for the cell growth and $H_2$ production was $37{\circ}C$. Initial C/N ratio of 1.22 in the media using glucose and yeast extract as the C- and N-sources, respectively, showed the $H_2$ yield 1.0 mol $H_2$/mol glucose.

Power Estimation and Optimum Design of a Buoy for the Resonant Type Wave Energy Converter Using Approximation Scheme (근사기법을 활용한 공진형 파력발전 부이의 발전량 추정 및 최적설계)

  • Koh, Hyeok-Jun;Ruy, Won-Sun;Cho, Il-Hyoung
    • Journal of Ocean Engineering and Technology
    • /
    • v.27 no.1
    • /
    • pp.85-92
    • /
    • 2013
  • This paper deals with the resonant type of a WEC (wave energy converter) and the determination method of its geometric parameters which were obtained to construct the robust and optimal structure, respectively. In detail, the optimization problem is formulated with the constraints composed of the response surfaces which stand for the resonance period(heave, pitch) and the meta center height of the buoy. Use of a signal-to-noise ratio calculated from normalized multi-objective results with the weight factor can help to select the robust design level. In order to get the sample data set, the motion responses of the power buoy were analyzed using the BEM (boundary element method)-based commercial code. Also, the optimization result is compared with a robust design for a feasibility study. Finally, the power efficiency of the WEC with the optimum design variables is estimated as the captured wave ratio resulting from absorbed power which mainly related to PTO (power take off) damping. It could be said that the resultant of the WEC design is the economical optimal design which satisfy the given constraints.