• Journal of Navigation and Port Research
• /
• v.45 no.6
• /
• pp.284-297
• /
• 2021

A simple kinematic model for the prediction of ship manoeuvres based on trial data is proposed in this study. The model consists of first order differential equations in surge, sway, and yaw directions which simulate the time series of each velocity component. Actually instead of sea trial data, dynamic model simulations are conducted with randomly varied control inputs such as propeller revolution rates and rudder angles. Based on learning of control inputs and velocity outputs of dynamic model simulations in sufficient time, kinematic model coefficients are optimized so that the kinematic model can be approximately reproduce the velocity outputs of dynamic model simulations with arbitrary control inputs. The resultant kinematic model is verified with new dynamic simulation sets.

• Asian-Australasian Journal of Animal Sciences
• /
• v.31 no.12
• /
• pp.1980-1990
• /
• 2018

Objective: The aim of this study was to discover the functional impact of non-synonymous single nucleotide polymorphisms (nsSNPs) that were found in selective sweep regions of the Landrace genome Methods: Whole-genome re-sequencing data were obtained from 40 pigs, including 14 Landrace, 16 Yorkshire, and 10 wild boars, which were generated with the Illumina HiSeq 2000 platform. The nsSNPs in the selective sweep regions of the Landrace genome were identified, and the impacts of these variations on protein function were predicted to reveal their potential association with traits of the Landrace breed, such as reproductive capacity. Results: Total of 53,998 nsSNPs in the mapped regions of pigs were identified, and among them, 345 nsSNPs were found in the selective sweep regions of the Landrace genome which were reported previously. The genes featuring these nsSNPs fell into various functional categories, such as reproductive capacity or growth and development during the perinatal period. The impacts of amino acid sequence changes by nsSNPs on protein function were predicted using two in silico SNP prediction algorithms, i.e., sorting intolerant from tolerant and polymorphism phenotyping v2, to reveal their potential roles in biological processes that might be associated with the reproductive capacity of the Landrace breed. Conclusion: The findings elucidated the domestication history of the Landrace breed and illustrated how Landrace domestication led to patterns of genetic variation related to superior reproductive capacity. Our novel findings will help understand the process of Landrace domestication at the genome level and provide SNPs that are informative for breeding.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.41-47
• /
• 2019

Recently, enhanced methods on the inter merging have been being investigated in Versatile Video Coding (VVC) standardization which will be a next generation video coding standard with capability beyond the High Efficiency Video Coding (HEVC). If there is not enough motion information available in the neighboring blocks in the merge mode, zero motion candidate is inserted into the merge candidate list, which could make the coding efficiency decreased. In this paper, we propose an efficient method of constructing the merge mode candidate list to reduce the case that the zero motion is used as a candidate by generating an alternative merge candidate. Experimental results show that the proposed method gives the average BD-rate gain of 0.2% with the decoding time increase of 3% in the comparison with VTM 1.0.

• Journal of The Geomorphological Association of Korea
• /
• v.24 no.1
• /
• pp.77-91
• /
• 2017

Many debris landforms in the mountains of Korea have formed in the periglacial environment during the last glacial stage when the generation of sediments was active. Because these landforms are generally located on steep slopes and mostly covered by vegetation, however, it is difficult to observe and access them through field investigation. A scientific method is required to reduce the survey range before performing field investigation and to save time and cost. For this purpose, the use of remote sensing and GIS technologies is essential. This study has extracted the potential area of debris landform formation using a fuzzy set model as a mathematical data integration method. The first step was to obtain information about the location of debris landforms and their related factors. This information was verified through field observation and then used to build a database. In the second step, we conducted the fuzzy set modeling to generate a map, which classified the study area based on the possibility of debris formation. We then applied a cross-validation technique in order to evaluate the map. For a quantitative analysis, the calculated potential rate of debris formation was evaluated by plotting SRC(Success Rate Curve) and calculating AUC(Area Under the Curve). The prediction accuracy of the model was found to be 83.1%. We posit that the model is accurate and reliable enough to contribute to efficient field investigation and debris landform management.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.153-166
• /
• 2021

A main goal of pharmacogenomics studies is to predict individual's drug responsiveness based on high dimensional genetic variables. Due to a large number of variables, feature selection is required in order to reduce the number of variables. The selected features are used to construct a predictive model using machine learning algorithms. In the present study, we applied several hybrid feature selection methods such as combinations of logistic regression, ReliefF, TurF, random forest, and LASSO to a next generation sequencing data set of 400 epilepsy patients. We then applied the selected features to machine learning methods including random forest, gradient boosting, and support vector machine as well as a stacking ensemble method. Our results showed that the stacking model with a hybrid feature selection of random forest and ReliefF performs better than with other combinations of approaches. Based on a 5-fold cross validation partition, the mean test accuracy value of the best model was 0.727 and the mean test AUC value of the best model was 0.761. It also appeared that the stacking models outperform than single machine learning predictive models when using the same selected features.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.294-302
• /
• 2022

Detection of fake news is a complex and a challenging task. Generation of fake news is very hard to stop, only steps to control its circulation may help in minimizing its impacts. Humans tend to believe in misleading false information. Researcher started with social media sites to categorize in terms of real or fake news. False information misleads any individual or an organization that may cause of big failure and any financial loss. Automatic system for detection of false information circulating on social media is an emerging area of research. It is gaining attention of both industry and academia since US presidential elections 2016. Fake news has negative and severe effects on individuals and organizations elongating its hostile effects on the society. Prediction of fake news in timely manner is important. This research focuses on detection of fake news spreaders. In this context, overall, 6 models are developed during this research, trained and tested with dataset of PAN 2020. Four approaches N-gram based; user statistics-based models are trained with different values of hyper parameters. Extensive grid search with cross validation is applied in each machine learning model. In N-gram based models, out of numerous machine learning models this research focused on better results yielding algorithms, assessed by deep reading of state-of-the-art related work in the field. For better accuracy, author aimed at developing models using Random Forest, Logistic Regression, SVM, and XGBoost. All four machine learning algorithms were trained with cross validated grid search hyper parameters. Advantages of this research over previous work is user statistics-based model and then ensemble learning model. Which were designed in a way to help classifying Twitter users as fake news spreader or not with highest reliability. User statistical model used 17 features, on the basis of which it categorized a Twitter user as malicious. New dataset based on predictions of machine learning models was constructed. And then Three techniques of simple mean, logistic regression and random forest in combination with ensemble model is applied. Logistic regression combined in ensemble model gave best training and testing results, achieving an accuracy of 72%.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.322-330
• /
• 2021

In modern aquaculture, mass mortality is a very important issue that determines the success of aquaculture business. If a fish disease is not detected at an early stage in the farm, the disease spreads quickly because the farm is a closed environment. Therefore, early detection of diseases is crucial to prevent mass mortality of fish raised in farms. Recently deep learning-based automatic identification of fish diseases has been widely used, but there are many difficulties in identifying objects due to insufficient images of fish diseases. Therefore, this paper suggests a method to generate a large number of fish disease images by synthesizing normal images and disease images using SinGAN deep learning model in order to to solve the lack of fish disease images. We generate images from the three most frequently occurring Paralichthys Olivaceus diseases such as Scuticociliatida, Vibriosis, and Lymphocytosis and compare them with the original image. In this study, a total of 330 sheets of scutica disease, 110 sheets of vibrioemia, and 110 sheets of limphosis were made by synthesizing 10 disease patterns with 11 normal halibut images, and 1,320 images were produced by quadrupling the images.

• Journal of Korean Society on Water Environment
• /
• v.37 no.6
• /
• pp.442-448
• /
• 2021

Seawater desalination is a technology through which salt and other constituents are removed from seawater to produce fresh water. While a significant amount of fresh water is produced, the desalination process is limited by the generation of concentrated brine with a higher salinity than seawater; this imposes environmental and economic problems. In this study, characteristics of seawater from three different locations in South Korea were analyzed to evaluate the feasibility of crystallization to seawater desalination. Organic and inorganic substances participating in crystal formation during concentration were identified. Then, prediction and economic feasibility analysis were conducted on the actual water flux and obtainable salt resources (i.e. Na2SO4) using membrane distillation and energy-saving crystallizer based on multi-stage flash (MSF-Cr). The seawater showed a rather low salinity (29.9~34.4 g/L) and different composition ratios depending on the location. At high concentrations, it was possible to observe the participation of dissolved organic matter and various ionic substances in crystalization. When crystallized, materials capable of forming various crystals are expected. However, it seems that different salt concentrations should be considered for each location. When the model developed using the Aspen Plus modular was applied in Korean seawater conditions, relatively high economic feasibility was confirmed in the MSF-Cr. The results of this study will help solve the environmental and economic problems of concentrated brine from seawater desalination.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.11
• /
• pp.763-770
• /
• 2022

In an environment where multiple drones are operated, collisions can occur when path points overlap, and collision avoidance in preparation for this is essential. When multiple drones perform multiple tasks, it is not appropriate to use a method to generate a collision-avoiding path in the path planning phase because the path of the drone is complex and there are too many collision prediction points. In this paper, we generate a path through a commonly used path generation algorithm and propose a collision avoidance method using speed profile optimization from that path segment. The safe distance between drones was considered at the expected point of collision between paths of drones, and it was designed to assign a speed profile to the path segment. The optimization problem was defined by setting the distance between drones as variables in the flight time equation. We constructed the constraints through linearize and convexification, and compared the computation time of SQP and convex optimization method in multiple drone operating environments. Finally, we confirmed whether the results of performing convex optimization in the 20 drone operating environments were suitable for the multiple drone operating system proposed in this study.

• Journal of Fashion Business
• /
• v.26 no.4
• /
• pp.64-82
• /
• 2022

This study aimed to explore fashion technologies for small-scale designer brands and reveal the priorities of the derived fashion technologies. Interviews were conducted with owners of 15 designer brands to explore fashion technologies needed in the field based on the business operation stage (study 1), and an online survey of owners of 61 designer brands was conducted to verify their priorities (study 2). A total of 12 fashion technologies were derived from study 1, including 2 market analysis stages, 6 season planning stages, and 4 product operation stages. In study 2, importance and satisfaction were measured with 12 fashion techniques derived from study 1, and importance-performance analysis (IPA) was performed. The technologies of product management with image tagging and sales channel matching were considered to be the fashion technologies that should be developed first. Second, in the case of maintenance, demand prediction and price determination were applicable. Third, over-effort avoidance was revealed through market analysis and design generation. Finally, in automatic product detail page creation and digital marketing, development was the lowest priority. The results of this study are expected to provide insight into priority areas for fashion technology developers and policy departments providing emerging brand support.