• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1013-1018
• /
• 2021

Due to the recent accident caused by the automated vehicle, discussions on the ethical aspects of AI have been actively underway. This paper confirms that AI is inevitably connected to ethical components through the concepts and techniques related to robots-AI, and argues that ethical aspects are built-in, not post facto. Furthermore, this devises a solution to the trolley dilemma that can serve as a clue to ethical problems associated with automated vehicles. Preferentially, that process contains writing Bayesian networks. Next, only important and influential data are left after the pre-processing stage, and crowd-sourcing & extrapolation is used to calculate the exact figures of the networks. Through this process, this argues that humans' subjects are certainly included in implementing algorithms and models and discusses the necessity and direction of engineering liberal arts, especially education of ethics that distinguished from major education to prevent distortions and biases abouts AI systems.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.617-628
• /
• 2021

Drought is a major natural disaster that causes serious social and economic losses. Local drought forecasts can provide important information for drought preparedness. In this study, we propose a new machine learning model that predicts drought by using historical drought indices and meteorological data from 10 sites from 1981 to 2020 in the southeastern part of the Korean Peninsula, Busan-Ulsan-Gyeongnam. Using Bayesian optimization techniques, a hyper-parameter-tuned Random Forest, XGBoost, and Light GBM model were constructed to predict the evaporative demand drought index on a 6-month time scale after 1-month. The model performance was compared by constructing a single site model and a regional model, respectively. In addition, the possibility of improving the model performance was examined by constructing a fine-tuned model using data from a individual site based on the regional model.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.1
• /
• pp.79-89
• /
• 2022

Soil moisture is significantly related to crop growth and plays an important role in irrigation management. To predict soil moisture, various process-based model has been developed and used in the world. Various models (Land surface model) may have different performance depending on the model parameters and structures that causes the different model output for the same modeling condition. In this study, the three land surface models (Noah Land Surface Model, Soil Water Atmosphere Plant, Community Land Model) were used to compare the model performance (soil moisture prediction) and develop the multi-model simulation. At first, the genetic algorithm was used to estimate the optimal soil parameters for each model, and the parameters were used to predict soil moisture in the study area. Then, we used the multi-model approach based on Bayesian model averaging (BMA). The results derived from this approach showed a better match to the measurements than the results from the original single land surface model. In addition, identifying the strengths and weaknesses of the single model and utilizing multi-model methods can help to increase the accuracy of soil moisture prediction.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.14-19
• /
• 2021

This paper presents LiDAR static obstacle map based vehicle dynamic state estimation algorithm for urban autonomous driving. In an autonomous driving, state estimation of host vehicle is important for accurate prediction of ego motion and perceived object. Therefore, in a situation in which noise exists in the control input of the vehicle, state estimation using sensor such as LiDAR and vision is required. However, it is difficult to obtain a measurement for the vehicle state because the recognition sensor of autonomous vehicle perceives including a dynamic object. The proposed algorithm consists of two parts. First, a Bayesian rule-based static obstacle map is constructed using continuous LiDAR point cloud input. Second, vehicle odometry during the time interval is calculated by matching the static obstacle map using Normal Distribution Transformation (NDT) method. And the velocity and yaw rate of vehicle are estimated based on the Extended Kalman Filter (EKF) using vehicle odometry as measurement. The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment, and is verified with data obtained from actual driving on urban roads. The test results show a more robust and accurate dynamic state estimation result when there is a bias in the chassis IMU sensor.

• Journal of the Korean Geosynthetics Society
• /
• v.21 no.3
• /
• pp.1-10
• /
• 2022

In this paper, the spatial randomness and probability characteristics of material properties are inversely estimated by using a set of the stochastic fields for the material properties of geotechnical structures. By using the probability distribution and probability characteristics of these estimated material properties, topology optimization is performed on structure shape, and the results are compared with the existing deterministic topology optimization results. A set of stochastic fields for material properties is generated, and the spatial randomness of material properties in each field is simulated. The probability distribution and probability characteristics of actual material properties are estimated using the partial values of material properties in each stochastic field. The probability characteristics of the estimated actual material properties are compared with those of the stochastic field set. Also, response variability of the ground structure having a modulus of elasticity with randomness is compared with response variability of the ground structure having a modulus of elasticity without randomness. Therefore, the quantified stochastic topology optimization result can be obtained with considering the spatial randomness of actual material properties.

• Communications for Statistical Applications and Methods
• /
• v.29 no.4
• /
• pp.421-439
• /
• 2022

Phase I dose-finding trials are essential in drug development. By finding the maximum tolerated dose (MTD) of a new drug or treatment, a Phase I trial establishes the recommended doses for later-phase testing. The primary toxicity endpoint of interest is often a binary variable, which describes an event of a patient who experiences dose-limiting toxicity. However, there is a growing interest in dose-finding studies regarding non-binary outcomes, defined by either the weighted sum of rates of various toxicity grades or a continuous outcome. Although several novel methods have been proposed in the literature, accessible software is still lacking to implement these methods. This study introduces a newly developed R package, UnifiedDoseFinding, which implements three phase I dose-finding methods with non-binary outcomes (Quasi- and Robust Quasi-CRM designs by Yuan et al. (2007) and Pan et al. (2014), gBOIN design by Mu et al. (2019), and by a method by Ivanova and Kim (2009)). For each of the methods, UnifiedDoseFinding provides corresponding functions that begin with next that determines the dose for the next cohort of patients, select, which selects the MTD defined by the non-binary toxicity endpoint when the trial is completed, and get oc, which obtains the operating characteristics. Three real examples are provided to help practitioners use these methods. The R package UnifiedDoseFinding, which is accessible in R CRAN, provides a user-friendly tool to facilitate the implementation of innovative dose-finding studies with nonbinary outcomes.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.55 no.2
• /
• pp.183-188
• /
• 2022

It is a difficult task to estimate parameters in even a simple stock assessment model such as a surplus production model, using only data about temporal catch-per-unit-effort (CPUE) (or survey index) and fishery yields. Such difficulty is exacerbated when time-varying parameters are treated as random effects (aka state variables). To overcome the difficulty, previous studies incorporated somewhat subjective assumptions (e.g., B₁=K) or informative priors of parameters. A key is how to build an objective joint prior of parameters, reducing subjectivity. Given the limited data on temporal CPUEs and fishery yields from 1999-2020 for common squid Todarodes pacificus, we built a joint prior of only two parameters, intrinsic growth rate (r) and carrying capacity (K), based on the resilience level of the population (Froese et al., 2017), and used a Bayesian state-space production assessment model. We used template model builder (TMB), a R package for implementing the assessment model, and estimating all parameters in the model. The predicted annual biomass was in the range of 0.76×10⁶ to 4.06×10⁶ MT, the estimated MSY was 0.13×10⁶ MT, the estimated r was 0.24, and the estimated K was 2.10×10⁶ MT.

• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2334-2340
• /
• 2021

Radioactive particle tracking (RPT) is a minimally invasive nuclear technique that tracks a radioactive particle inside a volume of interest by means of a mathematical location algorithm. During the past decades, many algorithms have been developed including ones based on artificial intelligence techniques. In this study, RPT technique is applied in a simulated test section that employs a simplified mixer filled with concrete, six scintillator detectors and a¹³⁷Cs radioactive particle emitting gamma rays of 662 keV. The test section was developed using MCNPX code, which is a mathematical code based on Monte Carlo simulation, and 3516 different radioactive particle positions (x,y,z) were simulated. Novelty of this paper is the use of a location algorithm based on a deep learning model, more specifically a 6-layers deep rectifier neural network (DRNN), in which hyperparameters were defined using a Bayesian optimization method. DRNN is a type of deep feedforward neural network that substitutes the usual sigmoid based activation functions, traditionally used in vanilla Multilayer Perceptron Networks, for rectified activation functions. Results show the great accuracy of the DRNN in a RPT tracking system. Root mean squared error for x, y and coordinates of the radioactive particle is, respectively, 0.03064, 0.02523 and 0.07653.

• Journal of Veterinary Science
• /
• v.21 no.3
• /
• pp.43.1-43.13
• /
• 2020

Background: Canine parvovirus (CPV) and feline panleukopenia (FPV) cause severe intestinal disease and leukopenia. Objectives: In Korea, there have been a few studies on Korean FPV and CPV-2 strains. We attempted to investigate several genetic properties of FPV and CPV-2. Methods: Several FPV and CPV sequences from around world were analyzed by Bayesian phylo-geographical analysis. Results: The parvoviruses strains were newly classified into FPV, CPV 2-I, CPV 2-II, and CPV 2-III genotypes. In the strains isolated in this study, Gigucheon, Rara and Jun belong to the FPV, while Rachi strain belong to CPV 2-III. With respect to CPV type 2, the new genotypes are inconsistent with the previous genotype classifications (CPV-2a, -2b, and -2c). The root of CPV-I strains were inferred to be originated from a USA strain, while the CPV-II and III were derived from Italy strains that originated in the USA. Based on VP2 protein analysis, CPV 2-I included CPV-2a-like isolates only, as differentiated by the change in residue S297A/N. Almost CPV-2a isolates were classified into CPV 2-III, and a large portion of CPV-2c isolates was classified into CPV 2-II. Two residue substitutions F267Y and Y324I of the VP2 protein were characterized in the isolates of CPV 2-III only. Conclusions: We provided an updated insight on FPV and CPV-2 genotypes by molecular-based and our findings demonstrate the genetic characterization according to the new genotypes.

• The korean journal of orthodontics
• /
• v.52 no.5
• /
• pp.313-323
• /
• 2022

Objective: This study aimed to estimate the clinical effects of different types of bone-anchored maxillary protraction devices by using a network meta-analysis. Methods: We searched seven databases for randomized and controlled clinical trials that compared bone-anchored maxillary protraction with tooth-anchored maxillary protraction interventions or untreated groups up to May 2021. After literature selection, data extraction, and quality assessment, we calculated the mean differences, 95% confidence intervals, and surface under the cumulative ranking scores of eleven indicators. Statistical analysis was performed using R statistical software with the GeMTC package based on the Bayesian framework. Results: Six interventions and 667 patients were involved in 18 studies. In comparison with the tooth-anchored groups, the bone-anchored groups showed significantly more increases in Sella-Nasion-Subspinale (°), Subspinale-Nasion-Supramentale(°) and significantly fewer increases in mandibular plane angle and the labial proclination angle of upper incisors. In comparison with the control group, Sella-Nasion-Supramentale(°) decreased without any statistical significance in all treated groups. IMPA (angle of lower incisors and mandibular plane) decreased in groups with facemasks and increased in other groups. Conclusions: Bone-anchored maxillary protraction can promote greater maxillary forward movement and correct the Class III intermaxillary relationship better, in addition to showing less clockwise rotation of mandible and labial proclination of upper incisors. However, strengthening anchorage could not inhibit mandibular growth better and the lingual inclination of lower incisors caused by the treatment is related to the use of a facemask.