• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.1
• /
• pp.10-21
• /
• 2023

For various target tracking applications, it is well known that the Kalman filter is the optimal estimator(in the minimum mean-square sense) to predict and estimate the state(position and/or velocity) of linear dynamical systems driven by Gaussian stochastic noise. In the case of nonlinear systems, Extended Kalman filter(EKF) and/or Unscented Kalman filter(UKF) are widely used, which can be viewed as approximations of the(linear) Kalman filter in the sense of the conditional expectation. However, to implement EKF and UKF, the exact dynamical model information and the statistical information of noise are still required. In this paper, we propose the recurrent neural-network based Kalman filter, where its Kalman gain is obtained via the proposed GRU-LSTM based neural-network framework that does not need the precise model information as well as the noise covariance information. By the proposed neural-network based Kalman filter, the state estimation performance is enhanced in terms of the tracking error, which is verified through various linear and nonlinear tracking problems with incomplete model and statistical covariance information.

• Geomechanics and Engineering
• /
• v.32 no.6
• /
• pp.583-600
• /
• 2023

The resilient modulus (M_R) of various pavement materials plays a significant role in the pavement design by a mechanistic-empirical method. The M_R determination is done by experimental tests that need time and money, along with special experimental tools. The present paper suggested a novel hybridized extreme gradient boosting (XGB) structure for forecasting the M_R of modified base materials subject to wet-dry cycles. The models were created by various combinations of input variables called deep learning. Input variables consist of the number of W-D cycles (WDC), the ratio of free lime to SAF (CSAFR), the ratio of maximum dry density to the optimum moisture content (DMR), confining pressure (σ₃), and deviatoric stress (σ_d). Two XGB structures were produced for the estimation aims, where determinative variables were optimized by particle swarm optimization (PSO) and black widow optimization algorithm (BWOA). According to the results' description and outputs of Taylor diagram, M1 model with the combination of WDC, CSAFR, DMR, σ₃, and σ_d is recognized as the most suitable model, with R² and RMSE values of BWOA-XGB for model M1 equal to 0.9991 and 55.19 MPa, respectively. Interestingly, the lowest value of RMSE for literature was at 116.94 MPa, while this study could gain the extremely lower RMSE owned by BWOA-XGB model at 55.198 MPa. At last, the explanations indicate the BWO algorithm's capability in determining the optimal value of XGB determinative parameters in M_R prediction procedure.

• Korean Journal of Agricultural Science
• /
• v.48 no.4
• /
• pp.957-963
• /
• 2021

The study aimed to investigate the effects of supplemented sodium butyrate on the in vitro rumen fermentation and growth performance of Hanwoo calves. In total, four treatments were employed according to the sodium butyrate levels: no addition (control), an addition of 0.1% (treatment 1), an addition of 0.3% (treatment 2), and an addition of 0.5% (treatment 3). After 48 hours of fermentation, the ruminal pH was found to be higher in T1 than in C. Total volatile fatty acids were significantly higher in T2 and T3 than in C. The ratio of acetate and propionate was significantly lower in T1 and T3 than in C. In this study, the optimal concentration to promote rumen fermentation was found to be 0.3%, i.e., T2, and an experiment on Hanwoo calves at a farm was conducted. However, there were no significant differences between the treatment groups in terms of the daily weight gain, feed conversion ratio, and final body weight in the feeding experiment. Also, there were no significant differences in the body length, withers height, and height at hip cross between the control and the treatment groups. The addition of 0.3% sodium butyrate was most effective at promoting in vitro rumen fermentation, but it did not significantly affect the growth performance when fed to Hanwoo calves. This indicates that the addition of sodium butyrate improved rumen fermentation but did not have a growth-promoting effect. Future studies need to compare growth and carcass performance outcomes to confirm long-term effects.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.56 no.5
• /
• pp.734-740
• /
• 2023

The effect of feeding frequency on growth performance, body nutrient composition, and hematological parameters of juvenile chum salmon Oncorhynchus keta was investigated. The juveniles (10.9±0.3 g) were fed commercial feed for 30 days with feeding frequencies of 1, 2, 3, 4, or 5 meal (s)/day (n=2 tanks per treatment) in a recirculating aquaculture system (RAS). Fish were fed to satiation at each of the feeding frequencies. At the end of the feeding trial, final body weight, weight gain, and specific growth rate of fish fed 2 meals/day were significantly higher than those of fish fed 1 meal/day(P<0.05); however, no difference was detected among the other feeding frequencies. Daily feed intake significantly increased with increasing feeding frequency, whereas feed and protein utilization efficiencies continuously decreased with increase in the feeding frequency. Among the treatments, fish fed 1 meal/day showed the lowest value in whole-body lipid content and total protein concentration in plasma. Taken together, the optimal feeding frequency for growth performance and feed utilization efficiency in chum salmon juveniles reared in the RAS was determined to be 2 meals/day.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.1-8
• /
• 2023

In recent years, robots have been utilized in various industries to reduce workload and enhance work efficiency. The following mobility offers users convenience by autonomously tracking specific locations and targets without the need for additional equipment such as forklifts or carts. In this paper, deep learning techniques were employed to recognize individuals and assign each of them a unique identifier to enable the recognition of a specific person even among multiple individuals. To achieve this, the distance and angle between the robot and the targeted individual are transmitted to respective controllers. Furthermore, this study explored the control methodology for mobility that tracks a specific person, utilizing Simultaneous Localization and Mapping (SLAM) and Proportional-Integral-Derivative (PID) control techniques. In the PID control method, a genetic algorithm is employed to extract the optimal gain value, subsequently evaluating PID performance through simulation. The SLAM method involves generating a map by synchronizing data from a 2D LiDAR and a depth camera using Real-Time Appearance-Based Mapping (RTAB-MAP). Experiments are conducted to compare and analyze the performance of the two control methods, visualizing the paths of both the human and the following mobility.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.6
• /
• pp.309-318
• /
• 2008

In this paper, we discuss a method for efficiently coding the high-band signal in the split-band coding approach where an input signal is divided into two bands and then each band may be encoded separately. Generally, and especially through the research on the artificial bandwidth extension (BWE), it is well known that there is a correlation between the two bands to some degree. Therefore, some coding gain could be achieved by utilizing the correlation. In the BWE-prediction-based coding approach, using a simple linear BWE function may not yield optimal results because the correlation has a non-linear characteristic. In this paper, we investigate the new coding scheme more in details. A few representative BWE functions including linear and non-linear ones are investigated and compared to find a suitable one for the coding purpose. In addition, it is also discussed whether there are some additional gains in combining the BWE coder with the predictive vector quantizer which exploits the temporal correlation.

• Korean Journal of Agricultural Science
• /
• v.50 no.4
• /
• pp.603-616
• /
• 2023

This study was conducted to investigate the productivity, meat quality, blood variables, stress responses, and litter quality of broilers offered feed with different levels of Glycine (Gly) supplementation under heat stress condition. A total of 760 one-day-old Ross 308 broiler males were randomly assigned to one of the four dietary treatment groups: (1) basal diet (control; CON); (2) basal diet + Gly 0.1% (Gly 0.1%); (3) basal diet + Gly 0.2% (Gly 0.2%); and (4) basal diet + Gly 0.3% (Gly 0.3%). The environments for all the treatments groups were maintained according to broiler rearing guidelines from day 1 to day 21, and heat stress condition (32 ± 1℃, 60 ±5%) was created from day 22 to the end. The addition of Gly increased weight gain and affected feed intake (p < 0.05). Gly 0.1% group had higher pH and ferric reducing antioxidant power (FRAP) in the chicken meat and lower heterophil (HE)/lymphocyte (LY) ratio in the blood (p < 0.05). In particular, Gly 0.2% treatment group had lower serum corticosterone level (p < 0.05) than other groups. For jejunum morphology, the addition of Gly 0.2% significantly reduced the depth of the crypts (p < 0.05). However, the addition of Gly did not significantly affect litter quality (p > 0.05). In conclusion, the addition of glycine improved productivity and meat quality, alleviated heat stress, and improved intestinal function. Further studies are needed to determine the optimal level and mechanism of action of the additive when ingested.

• Journal of The Korean Society of Integrative Medicine
• /
• v.12 no.2
• /
• pp.155-166
• /
• 2024

Purpose : This study aims to identify key factors for predicting dropout risk at the university level and to provide a foundation for policy development aimed at dropout prevention. This study explores the optimal machine learning algorithm by comparing the performance of various algorithms using data on college students' dropout risks. Methods : We collected data on factors influencing dropout risk and propensity were collected from N University. The collected data were applied to several machine learning algorithms, including random forest, decision tree, artificial neural network, logistic regression, support vector machine (SVM), k-nearest neighbor (k-NN) classification, and Naive Bayes. The performance of these models was compared and evaluated, with a focus on predictive validity and the identification of significant dropout factors through the information gain index of machine learning. Results : The binary logistic regression analysis showed that the year of the program, department, grades, and year of entry had a statistically significant effect on the dropout risk. The performance of each machine learning algorithm showed that random forest performed the best. The results showed that the relative importance of the predictor variables was highest for department, age, grade, and residence, in the order of whether or not they matched the school location. Conclusion : Machine learning-based prediction of dropout risk focuses on the early identification of students at risk. The types and causes of dropout crises vary significantly among students. It is important to identify the types and causes of dropout crises so that appropriate actions and support can be taken to remove risk factors and increase protective factors. The relative importance of the factors affecting dropout risk found in this study will help guide educational prescriptions for preventing college student dropout.

• Fisheries and Aquatic Sciences
• /
• v.27 no.3
• /
• pp.171-179
• /
• 2024

A study was conducted to evaluate dietary valine (Val) requirement for Pacific white shrimp (Penaeus vannamei). Five isonitrogenous (353 g/kg) and isocaloric (4.08 kcal/g) semi-purified diets containing graded levels of Val (2.7, 5.1, 8.7, 12.1 or 16.0 g/kg) were formulated. Quadruplicate groups of 12 shrimp (average body weight: 0.46 ± 0.00 g) were fed one of the experimental diets (2%-5% of total body weight) for 8 weeks. Maximum weight gain was observed in 8.7 g/kg Val group. However, the growth performance was reduced when Val concentration in diets were higher than 12.1 g/kg. Feed conversion ratio was significantly increased with 2.7 and 16.0 g/kg Val inclusion. Shrimp fed the diets containing 2.7 g/kg Val showed significantly lower protein efficiency ratio, whole-body crude protein and Val concentrations. Dietary inclusion of Val significantly improved the relative expression of insulin-like growth factor binding protein and immune-related genes (prophenoloxidase, lysozyme and crustin) in the hepatopancreas and 8.7 g/kg Val group showed highest expression among all the groups. The dietary requirement of Val for maximum growth of juvenile P. vannamei, estimated using polynomial regression analysis on growth, was 9.54 g/kg of Val (27.2 g/kg based on protein level) and maximum growth occurred at 9.27 g/kg of Val (26.2 g/kg based on protein level) based on broken-line regression analysis.

• Clinics in Shoulder and Elbow
• /
• v.26 no.4
• /
• pp.390-396
• /
• 2023

Background: The subacromial (SA) space is a commonly used injection site for treatment of impingement syndrome. For shoulder stiffness, glenohumeral (GH) injections are commonly performed. However, in cases of impingement syndrome with mild shoulder stiffness, the optimal site of steroid injection has yet to be identified. Methods: This prospective, randomized study compared the short-term outcomes of ultrasound-guided GH and SA steroid injections in patients who were diagnosed with impingement syndrome and mild stiffness. Each group comprised 24 patients who received either a GH or SA injection of 40 mg of triamcinolone. Range of motion and clinical scores were assessed before and 3, 7, and 13 weeks after the injection. Results: GH and SA injections significantly improved the range of motion and clinical scores after 13 weeks of follow-up. Notably, targeting the GH joint resulted in an earlier gain of forward elevation, external rotation, and internal rotation in 3 weeks (P<0.001, P=0.012, and P=0.002, respectively) and of internal rotation and a Constant-Murley score in 7 weeks (P<0.001 and P=0.046). Subsequent measurements were similar between the groups and showed a steady improvement in all ranges of motion and clinical scores. Conclusions: GH injections may be more favorable than SA injections for treatment of impingement syndrome with mild stiffness, especially in improving the range of motion in the early period. However, the procedures showed similar outcomes after 3 months. Level of evidence: I.