• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.1-7
• /
• 2020

Deep neural networks(DNN), which are used as approximation functions in reinforcement learning (RN), theoretically can be attributed to realistic results. In empirical benchmark works, time difference learning (TD) shows better results than Monte-Carlo learning (MC). However, among some previous works show that MC is better than TD when the reward is very rare or delayed. Also, another recent research shows when the information observed by the agent from the environment is partial on complex control works, it indicates that the MC prediction is superior to the TD-based methods. Most of these environments can be regarded as 5-step Q-learning or 20-step Q-learning, where the experiment continues without long roll-outs for alleviating reduce performance degradation. In other words, for networks with a noise, a representative network that is regardless of the controlled roll-outs, it is better to learn MC, which is robust to noisy rewards than TD, or almost identical to MC. These studies provide a break with that TD is better than MC. These recent research results show that the way combining MC and TD is better than the theoretical one. Therefore, in this study, based on the results shown in previous studies, we attempt to exploit a random balance with a mixture of TD and MC in RL without any complicated formulas by rewards used in those studies do. Compared to the DQN using the MC and TD random mixture and the well-known DQN using only the TD-based learning, we demonstrate that a well-performed TD learning are also granted special favor of the mixture of TD and MC through an experiments in OpenAI Gym.

• Journal of Korean Society of Forest Science
• /
• v.90 no.6
• /
• pp.725-733
• /
• 2001

In this study, the relationship between growth factors for Pinus densiflora stands in Anmyun-Island was analyzed and dynamic growth model was prepared. A total of 96 sample plots was investigated in which dbh and height of individual trees were measured. From these plot data, quadratic mean dbh, mean height, dominant tree height, stem number per ha, basal area per ha and volume per ha were estimated. Several regression equations between growth factors were derived using NLIN and REG procedure of SAS. And dynamic growth model, in which the equations were interactively linked, was prepared for the prediction of stand growth and yield under different management regime. The predictions of dynamic growth model were found to be coincided with general growth principles. The dynamic growth model was considered as adequate for predicting growth and yield of Pinus densiflora stand in Anmyun-Island. In practice, the dynamic growth model can be applied for predicting the growth and development of stand for various forest treatments and for decision-making in forest management.

• Korean Journal of Plant Resources
• /
• v.27 no.4
• /
• pp.286-292
• /
• 2014

Near infrared reflectance spectroscopy (NIRS) is a rapid and accurate analytical method for determining the composition of agricultural products and feeds. This study was conducted to measure baicalin, baicalein, and wogonin contents in Scutellaria baicalensis by using NIRS system. Total 63 samples previously were analyzed by HPLC, which showed baicalin, baicalein, and wogonin contents ranging 4.56 to 13.59%, 0.28 to 5.54%, and 0.50 to 1.63% with an average of 9.66%, 2.09% and 0.52%, respectively. Each sample was scanned by NIRS and calculated for calibration and validation equation. A calibration equation calculated by modified partial least squares(MPLS) regression technique was developed in which the coefficient of determination for baicalin, baicalein, and wogonin content was 0.958, 0.944, and 0.709, respectively. Each calibration equation was applied to validation set that was performed with the remaining samples not included in the calibration set, which showed high positive correlation both in baicalin and baicalein content file. In case of wogonin, the prediction model was needed more accuracy because of low $R^2$ value in validation set. These results demonstrate that the developed NIRS equation can be practically used as a rapid screening method for quantification of baicalin and baicalein contents in Scutellaria baicalensis.

• 한국노년학
• /
• v.29 no.1
• /
• pp.243-258
• /
• 2009

Background: Falls are among the most common and serious health problems of older people. The psychological symptoms of falling have received relatively little attention compared to physical problems. Objective: The purpose of this study is to test a model to explain the factors that influence fear of falling among older adults living in a continuing care retirement community (CCRC) in Baltimore city, United States. Methods: A secondary analysis was conducted using data obtained from a Health Promotion Survey done on 149 older adults living in a CCRC. Data was originally obtained during face to face interviews with each participant. Descriptive statistics and bivariate correlations were used to describe the sample and evaluate simple correlations. A path analysis was done using the AMOS 4.0 statistical program. Results: Of the 49 hypothesized paths, 13 were statistically significant, and the model accounted for 22% of the variance in fear of falling among the elderly. There was support for the fit of the model to the data with a nonsignificant chi square at 0.478 (df=2, p=0.79), and the ratio of chi-square to degrees of freedom was 0.24, a CFI of 0.99 and RMSEA of 0.00. In particular, gender, a history of falling, and exercise were significant predictors of fear of falling. Conclusions/Implications: As anticipated, exercise is an important factor to prevent fear of falling. As a modifiable variable, self-efficacy and outcome expectation indirectly influence fear of falling through exercise.

• Korean Journal of Radiology
• /
• v.20 no.4
• /
• pp.683-692
• /
• 2019

Objective: We aimed to evaluate correlations between computed tomography (CT) parameters and pulmonary function test (PFT) parameters according to disease severity in patients with chronic obstructive pulmonary disease (COPD), and to determine whether CT parameters can be used to predict PFT indices. Materials and Methods: A total of 370 patients with COPD were grouped based on disease severity according to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) I-IV criteria. Emphysema index (EI), air-trapping index, and airway parameters such as the square root of wall area of a hypothetical airway with an internal perimeter of 10 mm (Pi10) were measured using automatic segmentation software. Clinical characteristics including PFT results and quantitative CT parameters according to GOLD criteria were compared using ANOVA. The correlations between CT parameters and PFT indices, including the ratio of forced expiratory volume in one second to forced vital capacity (FEV1/FVC) and FEV₁, were assessed. To evaluate whether CT parameters can be used to predict PFT indices, multiple linear regression analyses were performed for all patients, Group 1 (GOLD I and II), and Group 2 (GOLD III and IV). Results: Pulmonary function deteriorated with increase in disease severity according to the GOLD criteria (p < 0.001). Parenchymal attenuation parameters were significantly worse in patients with higher GOLD stages (P < 0.001), and Pi10 was highest for patients with GOLD III (4.41 ± 0.94 mm). Airway parameters were nonlinearly correlated with PFT results, and Pi10 demonstrated mild correlation with FEV1/FVC in patients with GOLD II and III (r = 0.16, p = 0.06 and r = 0.21, p = 0.04, respectively). Parenchymal attenuation parameters, airway parameters, EI, and Pi10 were identified as predictors of FEV₁/FVC for the entire study sample and for Group 1 (R² = 0.38 and 0.22, respectively; p < 0.001). However, only parenchymal attenuation parameter, EI, was identified as a predictor of FEV₁/FVC for Group 2 (R² = 0.37, p < 0.001). Similar results were obtained for FEV₁. Conclusion: Airway and parenchymal attenuation parameters are independent predictors of pulmonary function in patients with mild COPD, whereas parenchymal attenuation parameters are dominant independent predictors of pulmonary function in patients with severe COPD.

• Journal of the Korean Society for Railway
• /
• v.17 no.3
• /
• pp.193-200
• /
• 2014

In this study, fatigue tests on existing continuous welded rail (CWR) on a concrete track were carried out. Based on the test results, a S-N curve expressing the remaining life of the CWR at a fracture probability of 50% was obtained using weighted probit analysis suitable for small-sample fatigue data sets. As rails had different histories in terms of accumulated passing tonnage, the test data were corrected to average out the accumulated passing tonnage. The remaining service life for the CWR on the concrete track in an urban railway was estimated using the prediction equation for the bending stress of rail developed in the past to estimate rail base bending stress and taking the surface irregularities into consideration. Estimating the remaining service life of the CWR in an urban railway showed that the rail replacement period could be extended over 200MGT. In addition, comparing the concrete track to the ballast track, the fatigue life of rail was analyzed as approximately 300MGT higher than. Therefore, the rail replacement criteria needs to distinguish between the ballast track and the concrete track, and not the criteria needs to be changed as a target for the maintenance, although it is necessary to remove longitudinal rail surface irregularities at welds by grinding.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.12
• /
• pp.3866-3873
• /
• 2000

In this paper, we investigates the long-term memory and the Correct answer rate of the foreign exchange data (Yen/Dollar) that is one of economic time series, There are many cases where two kinds of fractal dimensions exist in time series generated from dynamical systems such as AR models that are typical models having a short terrr memory, The sample interval separating from these two dimensions are denoted by kcrossover. Let the fractal dimension be $D_1$ in K < $k^{crossover}$,and $D_2$ in K > $k^{crossover}$ from the statistics mode. In usual, Statistic models have dimensions D1 and D2 such that $D_1$ < $D_2$ and $D_2\cong2$ But it showed a result contrary to this in the real time series such as NIKKEL The exchange data that is one of real time series have relation of $D_1$ > $D_2$ When the interval between data increases, the correlation between data increases, which is quite a peculiar phenomenon, We predict exchange data by neural networks, We confirm that $\beta$ obrained from prediction errors and D calculated from time series data precisely satisfy the relationship $\beta$ = 2-2D which is provided from a non-linear model having fractal dimension, And We identified that the difference of fractal dimension appeaed in the Correct answer rate.

• Journal of muscle and joint health
• /
• v.8 no.1
• /
• pp.27-50
• /
• 2001

Rheumatoid arthritis is a chronic systemic autoimmune disease. Although the joints are the major loci of the disease activity, fatigue is a common extraarticular symptom that exists in all gradations of rheumatoid arthritis. Fatigue is defined as a subjective sense of generalized tiredness or exhaustion and has multiple dimensions. Therefore fatigue is a common and frequent problem for those with rheumatoid arthritis. In fact, 88-100% of individuals with rheumatoid arthritis experience fatigue. Especially the degree of fatigue is higher in women than men with rheumatoid arthritis. Despite the importance of fatigue among the patients with rheumatoid arthritis, the mechanism that leads to fatigue in rheumatoid arthritis is not completely understood. This study was intended to test and validate a model to predict fatigue in women with rheumatoid arthritis. Especially it was intended to identify the direct and indirect effects of the variables of pain, disability, depression, sleep disturbance, morning stiffness, and symptom duration to fatigue. Data were collected by questionnaires including Multidimensional Assesment of Fatigue(Tack, 1991), numeric scale of pain, graphic scale of joints, Ritchie Articular Index, Korean Health Assessment Questionnaire(Bae, et al., 1998), Inventory of Function Status(Tulman, et al., 1991), Center for Epidemiologic Studies-Depression, and Korean Sleep Scale(Oh, et al 1998). The sample consisted of 345 women with a mean duration of rheumatoid arthritis for 10.06 years and a mean age of 49.64 years. SPSS win and Win LISREL were used for the data analysis. Structural equation modeling revealed the overall fit of the model. Pain predicted fatigue directly and indirectly through disability, depression, and sleep disturbance. Disability, sleep disturbance predicted fatigue only directly, while depression only indirectly through disability and sleep disturbance. Also morning stiffness and symptom duration predicted fatigue through disability and depression. All predictors accounted for 65% of the variance of fatigue. Depression, pain, and disability predicted sleep disturbance. Depression had reciprocal relationship with disability and they both were predicted by pain directly and indirectly. In summary, pain, depression, disability, sleep disturbance, morning stiffness, and symptom duration contributed to the fatigue of patients with rheumatoid arthritis. The best predictor of fatigue was pain. This finding indicates that the modification of pain, depression, disability, sleep disturbance, morning stiffness could be nursing intervention for relief or prevention of fatigue.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.4
• /
• pp.1861-1864
• /
• 2016

Although early diagnosis of thyroid nodule type is very important, the diagnostic accuracy of standard tests is a challenging issue. We here aimed to find an optimal combination of factors to improve diagnostic accuracy for distinguishing malignant from benign thyroid nodules before surgery. In a prospective study from 2008 to 2012, 345 patients referred for thyroidectomy were enrolled. The sample size was split into a training set and testing set as a ratio of 7:3. The former was used for estimation and variable selection and obtaining a linear combination of factors. We utilized smoothly clipped absolute deviation (SCAD) logistic regression to achieve the sparse optimal combination of factors. To evaluate the performance of the estimated model in the testing set, a receiver operating characteristic (ROC) curve was utilized. The mean age of the examined patients (66 male and 279 female) was $40.9{\pm}13.4years$ (range 15- 90 years). Some 54.8% of the patients (24.3% male and 75.7% female) had benign and 45.2% (14% male and 86% female) malignant thyroid nodules. In addition to maximum diameters of nodules and lobes, their volumes were considered as related factors for malignancy prediction (a total of 16 factors). However, the SCAD method estimated the coefficients of 8 factors to be zero and eliminated them from the model. Hence a sparse model which combined the effects of 8 factors to distinguish malignant from benign thyroid nodules was generated. An optimal cut off point of the ROC curve for our estimated model was obtained (p=0.44) and the area under the curve (AUC) was equal to 77% (95% CI: 68%-85%). Sensitivity, specificity, positive predictive value and negative predictive values for this model were 70%, 72%, 71% and 76%, respectively. An increase of 10 percent and a greater accuracy rate in early diagnosis of thyroid nodule type by statistical methods (SCAD and ANN methods) compared with the results of FNA testing revealed that the statistical modeling methods are helpful in disease diagnosis. In addition, the factor ranking offered by these methods is valuable in the clinical context.

• Journal of Plant Biotechnology
• /
• v.48 no.3
• /
• pp.165-172
• /
• 2021

The solubilization of isolated proteins into the adequate buffer containing of surfactants is primary step for proteomic analysis. Particularly, sodium dodecyl sulfate (SDS) is the most widely used surfactant, however, it is not compatible with mass spectrometry (MS). Therefore, it must be removed prior to MS analysis through rigorous washing, which eventually results in inevitable protein loss. Recently, photocleavable surfactant, 4-hexylphenylazosulfonate (Azo), was reported which can be easily degraded by UV irradiation and is compatible with MS during proteomic approach using animal tissues. In this study, we employed comparative label-free proteomic analysis for evaluating the solubilization efficacies of the Azo and SDS surfactants using rice leave proteins. This approach led to identification of 3,365 proteins of which 682 proteins were determined as significantly modulated. Further, according to the subcellular localization prediction in SDS and Azo, proteins localized in the chloroplast were the major organelle accounting for 64% of the total organelle in the SDS sample, while only 37.5% of organelle proteins solubilized in the Azo were predicted to be localized in chloroplast. Taken together, this study validates the efficient solubilization of total protein isolated from plant material for bottom-up proteomics. Azo surfactant is suitable as substitute of SDS and promising for bottom-up proteomics as it facilitates robust protein extraction, rapid washing step during enzymatic digestion, and MS analysis.