• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.475-477
• /
• 2022

최근 강화 학습을 적용한 게임 AI 에 대한 연구가 활발히 진행되고 있다. 하지만 대부분 상용게임은 유한 상태 머신(Finite State Machine, FSM)을 이용한 스크립트 기반 AI 를 사용하기 때문에 복잡한 환경의 게임에서 불안정한 상태로 인해 적절한 강화 학습의 수행이 어렵다. 따라서 본 논문에서는 상용 게임 강화 학습 적용을 위하여 상태 정규화 및 Dense 보상 기반 강화 학습 기법을 제안한다. 제안한 기법을 상용 농구 게임에 적용하고 학습된 모델의 성능을 기존 FSM 기반 AI 와 비교를 통해 성능이 약 80% 증가한 결과를 확인하였다.

• Nuclear Engineering and Technology
• /
• v.55 no.11
• /
• pp.4282-4286
• /
• 2023

Nuclear energy is estimated by the machine learning method as the mathematical quantifications where neural networking is the major algorithm of the data propagations from input to output. As the aspect of nuclear energy, the other energy sources of the traditional carbon emission-characterized oil and coal are compared. The artificial intelligence (AI) oriented algorithm like the intelligence of a robot is applied to the modeling in which the mimicking of biological neurons is utilized in the mathematical calculations. There are graphs for nuclear priority weighted by climate factor and for carbon dioxide mitigation weighted by climate factor in which the carbon dioxide quantities are divided by the weighting that produces some results. Nuclear Priority and CO2 Mitigation values give the dimensionless values that are the comparative quantities with the normalization in 2010. The values are 1.0 in 2010 of the graphs which are changed to 24.318 and 0.0657 in 2040, respectively. So, the carbon dioxide emissions could be reduced in this study.

• Radiation Oncology Journal
• /
• v.17 no.2
• /
• pp.136-140
• /
• 1999

Purpose : Prostate specific antigen (PSA) is a useful tumor marker, which is widely used as a diagnostic index and predictor of both treatment and follow-up result in prostate cancer. A prospective analysis was carried out to obtain the period of PSA normalization and the half life of PSA and to analyze the factors influencing the period of PSA normalization. The PSA level was checked before and serially after radical radiotherapy. Materials and Method : Twen쇼 patients with clinically localized prostate cancer who underwent radical external beam radiotherapy were enrolled in this study. Accrual period was from April 1993 to May 1998. Median follow-up period was 20 months. Radiotherapy was given to whole pelvis followed by a boost to prostate. Dose range for the whole pelvis was from 45 Gy to 50 Gy and boost dose to prostate, from 14 Gy to 20 Gy. The post-irradiation PSA normal value was under 3.0 ng/ml. The physical examination and serum PSA level evaluation were performed at 3 month interval in the first one year, and then at every 4 to 6 months. Results : PSA value was normalized in nineteen patients (95%) within 12 months. The mean period of PSA normalization was 5.3 (${\pm}$2.7) months. The half life of PSA Of the nonfailing patients was 2.1 (${\pm}$0.9) month. The nadir PSA level Of the nonfailing Patients waS 0.8 (${\pm}$0.5) ng/ml. The period of PSA normalization had the positive correlation with pretreatment PSA level (R$^{2}$=0.468). The nadir PSA level had no definite positive correlation with the pretreatment PSA level (R$^{2}$=0.075). The half life of serum PSA level also had no definite correlation with pretreatment PSA level (R$^{2}$=0.029). Conclusion :The PSA level was mostly normalized within 8 months (85%). If it has not normalized within 12 months, we should consider the residual disease in prostate or distant metastasis. In 2 patients, the PSA level increased 6 months or 20 months before clinical disease was detected. So the serum PSA level can be used as early diagnostic indicator of treatment failure.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.157-157
• /
• 2017

To minimize the damage by wild birds and acquire the benefits such as protection against weeds and maintenance of water content in soil, the mulching black color vinyl after seeding should be carried out. Non-contact and non-destructive methods that can continuously determine the locations are necessary. In this study, a crop position detection method was studied that uses infrared thermal image sensor to determine the cotyledon position under vinyl mulch. The moving system for acquiring image arrays has been developed for continuously detecting crop locations under plastic mulching on the field. A sliding mechanical device was developed to move the sensor, which were arranged in the form of a linear array, perpendicular to the array using a micro-controller integrated with a stepping motor. The experiments were conducted while moving 4.00 cm/s speed of the IR sensor by the rotational speed of the stepping motor based on a digital pulse width modulation signal from the micro-controller. The acquired images were calibrated with the spatial image correlation. The collected data were processed using moving averaging on interpolation to determine the frame where the variance was the smallest in resolution units of 1.02 cm. Non-linear integral interpolation was one of method for analyzing the frequency using the normalization image and then arbitrarily increasing the limited data value of $16{\times}4pixels$ in one frame. It was a method to relatively reduce the size of overlapping pixels by arbitrarily increasing the limited data value. The splitted frames into 0.1 units instead of 1 pixel can propose more than 10 times more accurate and original method than the existing correction method. The non-integral calibration method was conducted by applying the subdivision method to the pixels to find the optimal correction resolution based on the first reversed frequency. In order to find a correct resolution, the expected location of the first crop was indicated on near pixel 4 in the inversion frequency. For the most optimized resolution, the pixel was divided by 0.4 pixel instead of one pixel to find out where the lowest frequency exists.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.367-369
• /
• 2004

In this paper we propose an effective and reliable hand detection method using neural network with ICA(Independent Component Analysis) Features. Many algorithms of hand detection have been proposed yet. Among them, ICA is the one of the interesting topics in image processing. ICA can not only separate mixed signals but also efficiently extract low-dimensional features in signals. ICA features are able to represent the characteristic of the images well. The object of this paper is to use effectively ICA that has above advantage. That is, by the proper number of Independent component the arithmetic speed is faster and by normalization of ICA feature the performance of detection is more reliable. For this, we adopt the algorithm, the Proportion of variance, which select the ICA feature by comparing the ratio of variance of ICA feature. By this method, we can extract the feature that is good at classifying hand and non-hand. Our experimental results show that by using ICA features, we obtained a better performance in hand detection than by only training NN on the image. And we can use hand detection system effectively and reliably by our proposal.

• Journal of Advanced Marine Engineering and Technology
• /
• v.35 no.6
• /
• pp.802-808
• /
• 2011

One of the important mechanical properties of cryogenic temperature structure material is fracture toughness. Research on normalization of fracture toughness test method is becoming very important issue with development of cryogenic structural elements. Specially, mechanical properties estimation by each micro-structure of welding department is important because it can cause unstable fracture when use under cryogenic environment in case of welding department. In this study, fracture toughness estimation test was carried out to unloading compliance method and sensitization heat-tread minimized test specimen at liquid nitrogen (77K), liquid helium (4K), 293K temperature to STS-316L base metal and weld metal.

• Food Science and Biotechnology
• /
• v.16 no.3
• /
• pp.477-481
• /
• 2007

Fourier transform near-infrared (FT-NIR) spectroscopy and partial least squares (PLS) regression were used to predict the amylose content of polished rice. Spectral reflectance data in a wavelength range of 1,000 to 2,500 nm were obtained with a commercial spectrophotometer for 60 different varieties of Korean rice. For a comparison of this spectroscopic method to a standard chemical analysis, the amylose contents of the tested rice samples were determined by the iodine-blue colorimetric method. The highest correlation for the rice amylose ($R^2=0.94$, standard error of prediction=0.20% amylose content) was obtained when using the FT-NIR spectrum data pre-treated with normalization, the first derivative, smoothing, and scattering correction.

• The Journal of the Korea Contents Association
• /
• v.13 no.3
• /
• pp.1-8
• /
• 2013

This paper proposes a new feature extraction algorithm to improve children's speech recognition in Korean. The proposed feature extraction algorithm combines three methods. The first method is on the vocal tract length normalization to compensate acoustic features because the vocal tract length in children is shorter than in adults. The second method is to use the uniform bandwidth because children's voice is centered on high spectral regions. Finally, the proposed algorithm uses a smoothing filter for a robust speech recognizer in real environments. This paper shows the new feature extraction algorithm improves the children's speech recognition performance.

• The KIPS Transactions:PartD
• /
• v.12D no.3 s.99
• /
• pp.355-364
• /
• 2005

Previous researches on subsequence matching have been focused on how to make indexes in order to speed up the matching time, and do not take into account the effectiveness issues of subsequence matching methods. This paper considers the effectiveness of subsequence matching methods and proposes two metrics for effectiveness evaluations of subsequence matching algorithms. We have applied the proposed metrics to Korean stock data and five known matching algorithms. The analysis on the empirical data shows that two methods (i.e., the method supporting normalization, and the method supporting scaling and shifting) outperform the others in terms of the effectiveness of subsequence matching.

• Journal of KIISE:Software and Applications
• /
• v.36 no.4
• /
• pp.273-282
• /
• 2009

Missing data is one of the common problems in building analysis or prediction models using software project data. Missing imputation methods are known to be more effective missing data handling method than deleting methods in small software project data. While K nearest neighbor imputation is a proper missing imputation method in the software project data, it cannot use non-missing information of incomplete project instances. In this paper, we propose an approach to missing data imputation for numerical software project data by combining K nearest neighbor and maximum likelihood estimation; we also extend the average absolute error measure by normalization for accurate evaluation. Our approach overcomes the limitation of K nearest neighbor imputation and outperforms on our real data sets.