• Journal of Internet Computing and Services
• /
• v.23 no.2
• /
• pp.53-59
• /
• 2022

After the 3rd level autonomous driving vehicle, the 4th and 5th level of autonomous driving technology is trying to maintain the optimal condition of the passengers as well as the perfect driving of the vehicle. However current autonomous driving technology is too dependent on visual information such as LiDAR and front camera, so it is difficult to fully autonomously drive on roads other than designated roads. Therefore this paper proposes a Braking Strength Calculation System (BSCS), in which a vehicle classifies road conditions using data other than visual information and calculates optimal braking strength according to road conditions and driving conditions. The BSCS consists of RCDM (Road Condition Definition Module), which classifies road conditions based on KNN algorithm, and BSCM (Braking Strength Calculation Module), which calculates optimal braking strength while driving based on current driving conditions and road conditions. As a result of the experiment in this paper, it was possible to find the most suitable number of Ks for the KNN algorithm, and it was proved that the RCDM proposed in this paper is more accurate than the unsupervised K-means algorithm. By using not only visual information but also vibration data applied to the suspension, the BSCS of the paper can make the braking of autonomous vehicles smoother in various environments where visual information is limited.

• Journal of Industrial Convergence
• /
• v.20 no.8
• /
• pp.77-84
• /
• 2022

This study aims to present a method for implementing a decision support system that can be used for selecting emerging technologies by applying a machine learning-based automatic classification technique. To conduct the research, the architecture of the entire system was built and detailed research steps were conducted. First, emerging technology candidate items were selected and trend data was automatically generated using a big data system. After defining the conceptual model and pattern classification structure of technological development, an efficient machine learning method was presented through an automatic classification experiment. Finally, the analysis results of the system were interpreted and methods for utilization were derived. In a DTW-kNN-based classification experiment that combines the Dynamic Time Warping(DTW) method and the k-Nearest Neighbors(kNN) classification model proposed in this study, the identification performance was up to 87.7%, and particularly in the 'eventual' section where the trend highly fluctuates, the maximum performance difference was 39.4% points compared to the Euclidean Distance(ED) algorithm. In addition, through the analysis results presented by the system, it was confirmed that this decision support system can be effectively utilized in the process of automatically classifying and filtering by type with a large amount of trend data.

• Journal of Life Science
• /
• v.33 no.3
• /
• pp.227-233
• /
• 2023

The purpose of this paper was to describe a statistical analysis for the spatial distribution of geographical distances of Erythronium japonicum at Mt. Geumjeong in Korea. The spatial pattern of E. japonicum was analyzed according to the nearest neighbor rule, population aggregation under different plot sizes by dispersion indices, and spatial autocorrelation. Most natural plots of E. japonicum were uniformly distributed in the forest community. Disturbed plots were aggregately distributed within 5 m × 5 m of one another. Neighboring patches of E. japonicum were predominantly 7.5~10 m apart on average. If the natural populations of E. japonicum were disturbed by human activities, then the aggregation occurred in a shorter distance than the 7.5~10 m distance scale. The Morisita index (IM) is related to the patchiness index (PAI) that showed the 2.5 m × 5 m plot had an overly steep slope at the west and south areas when the area was smaller than 5 m × 5 m. When the patch size was one 2.5 m × 5 m quadrat at the west distributed area of Mt. Geumjeong, the cluster was determined by both species characteristics and environmental factors. The comparison of Moran's I values to a logistic regression indicated that individuals in E. japonicum populations at Mt. Geumjeong could be explained by isolation by distance.

• Clean Technology
• /
• v.29 no.3
• /
• pp.217-226
• /
• 2023

The amount of hydrogen adsorbed in arrays of single walled carbon nanotubes (SWNTs) was studied as a function of nanotube diameter and distance between the nearest-neighbor nanotubes on square arrangements using a grand canonical Monte Carlo simulation. The influence of the geometry of a triangle array with the same diameters and distances was also studied. Hydrogen-carbon and hydrogen-hydrogen interactions were modeled with Lennard-Jones potentials for short range interactions and electrostatic interactions were added for hydrogen-hydrogen pairs to consider quantum contributions at low temperatures. At 194.5 K, Type I isotherms for large-diameter SWNTs and Type IV isotherms without hysteresis between adsorption and desorption processes for wider tube separations were observed. At 200 bars, the gravimetric hydrogen storage capacity of the SWNTs was reached or exceeded the US Department of Energy (DOE) target, but the volumetric capacity was about 70% of the DOE target. At 77 K, a two-step adsorption was observed, corresponding to a monolayer formation step followed by a condensation step. Hydrogen was adsorbed first to the inner surface of the nanotubes, then to the outer surface, intratubular space and the interstitial channels between the nanotube bundles. The simulation indicated that SWNTs of various diameters and distances in a wide range of configurations exceeded the DOE gravimetric and volumetric targets at under 1 bar.

• Journal of Navigation and Port Research
• /
• v.47 no.4
• /
• pp.231-238
• /
• 2023

The position of a light buoy is always flexible due to the influence of external forces such as tides and wind. The position can be checked through AIS (Automatic Identification System) or RTU (Remote Terminal Unit) for AtoN. As a result of analyzing the position data for the last five years (2017-2021) of a light buoy, the average position error was 15.4%. It is necessary to detect position error data and obtain refined position data to prevent navigation safety accidents and management. This study aimed to detect position error data and obtain refined position data by DBSCAN Clustering position data obtained through AIS or RTU for AtoN. For this purpose, 21 position data of Gunsan Port No. 1 light buoy where RTU was installed among western waters with the most position errors were DBSCAN clustered using Python library. The minPts required for DBSCAN Clustering applied the value commonly used for two-dimensional data. Epsilon was calculated and its value was applied using the k-NN (nearest neighbor) algorithm. As a result of DBSCAN Clustering, position error data that did not satisfy minPts and epsilon were detected and refined position data were acquired. This study can be used as asic data for obtaining reliable position data of a light buoy installed with AIS or RTU for AtoN. It is expected to be of great help in preventing navigation safety accidents.

• Journal of The Geomorphological Association of Korea
• /
• v.17 no.4
• /
• pp.71-83
• /
• 2010

In this study, the volume of shoreline retreat at sea-cliffs in the Taean peninsula(West Coast of Korea) was estimated and their erosion and seasonal landforms characteristics changes were investigated through multi-temporal aerial photographs and field survey. Based on the analysis of aerial photographs through ortho-correction, the results show that the length of shoreline and erosion area increase as erosion at sea-cliffs occurs in Pado-li and Dundu-li. To obtain the seasonal quantitative landforms changes and retreat of sea-cliffs, we marked top, middle, and bottom datum-points, from which the distance to the nearest bedrock was repeatedly measured. In these regions, the retreat of sea-cliffs gradually increases in spring to summer, but gradually decreases in autumn. In particular, the typhoon that has a great influence on the Korean peninsula in July to September in summer would drastically increase the retreat of sea-cliffs in comparison with other seasons. As the outcrop of sea-cliffs repeats freezing and thawing in winter, the retreat of sea-cliffs increases a little due to active mechanical weathering. To know the erosion and seasonal landforms changes of sea-cliffs, we took pictures of them in every month and then analyze their condition. The retreat of sea-cliffs was repeatedly occurred by the circulation of the erosion of sea-cliff base, landslides, the formation of slope sediment debris and their erosion, in that order.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.261-261
• /
• 2020

물관리의 기본이 되는 연속적인 유량 자료 확보를 위해서는 정확도 높은 수위-유량 관계 곡선식 개발이 필수적이다. 수위-유량 관계곡선식은 모든 수문시설 설계의 기초가 되며 홍수, 가뭄 등 물재해 대응을 위해서도 중요한 의미를 가지고 있다. 그러나 일반적으로 유량 측정은 많은 비용과 시간이 들고, 식생성장, 단면변화 등의 통제특성(control)이 변함에 따라 구간분리, 기간분리와 같은 비선형적인 양상이 나타나 자료 해석에 어려움이 존재한다. 특히, 국내 하천의 경우 자연적 및 인위적인 환경 변화가 다양하여 지점 및 기간에 따라 세밀한 분석이 요구된다. 머신러닝(Machine Learning)이란 데이터를 통해 컴퓨터가 스스로 학습하여 모델을 구축하고 성능을 향상시키는 일련의 과정을 뜻한다. 기존의 수위-유량 관계곡선식은 개발자의 판단에 의해 데이터의 종류와 기간 등을 설정하여 회귀식의 파라미터를 산출한다면, 머신러닝은 유효한 전체 데이터를 이용해 스스로 학습하여 자료 간 상관성을 찾아내 모델을 구축하고 성능을 지속적으로 향상 시킬 수 있다. 머신러닝은 충분한 수문자료가 확보되었다는 전제 하에 복잡하고 가변적인 수자원 환경을 반영하여 유량 추정의 정확도를 지속적으로 향상시킬 수 있다는 이점을 가지고 있다. 본 연구는 머신러닝의 대표적인 알고리즘들을 활용하여 유량을 추정하는 모델을 구축하고 성능을 비교·분석하였다. 대상지역은 안정적인 수량을 확보하고 있는 한강수계의 거운교 지점이며, 사용자료는 2010~2018년의 시간, 수위, 유량, 수면폭 등 이다. 프로그램은 파이썬을 기반으로 한 머신러닝 라이브러리인 사이킷런(sklearn)을 사용하였고 알고리즘은 랜덤포레스트 회귀, 의사결정트리, KNN(K-Nearest Neighbor), rgboost을 적용하였다. 학습(train) 데이터는 입력자료 종류별로 조합하여 6개의 세트로 구분하여 모델을 구축하였고, 이를 적용해 검증(test) 데이터를 RMSE(Roog Mean Square Error)로 평가하였다. 그 결과 모델 및 입력 자료의 조합에 따라 3.67~171.46로 다소 넓은 범위의 값이 도출되었다. 그 중 가장 우수한 유형은 수위, 연도, 수면폭 3개의 입력자료를 조합하여 랜덤포레스트 회귀 모델에 적용한 경우이다. 비교를 위해 동일한 검증 데이터를 한국수문조사연보(2018년) 내거운교 지점의 수위별 수위-유량 곡선식을 이용해 유량을 추정한 결과 RMSE가 3.76이 산출되어, 머신러닝이 세분화된 수위-유량 곡선식과 비슷한 수준까지 성능을 내는 것으로 확인되었다. 본 연구는 양질의 유량자료 생산을 위해 기 구축된 수문자료를 기반으로 머신러닝 기법의 적용 가능성을 검토한 기초 연구로써, 국내 효율적인 수문자료 측정 및 수위-유량 곡선 산출에 도움이 될 수 있을 것으로 판단된다. 향후 수자원 환경 및 통제특성에 영향을 미치는 다양한 영향변수를 파악하기 위해 기상자료, 취수량 등의 입력 자료를 적용할 필요가 있으며, 머신러닝 내 비지도학습인 딥러닝과 같은 보다 정교한 모델에 대한 추가적인 연구도 수행되어야 할 것이다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.122-124
• /
• 2022

Handling Passenger Traffic is the main challenge for designing an elevator group-control algorithm. Advanced control systems such as Hyundai's Destination Selection System(DSS) lets passengers select the destination by pressing on a selecting screen, and the systems have shown great efficiency. However, the algorithm cannot be applied to the general elevator control system due to the expensive cost of the technology. Often many elevator systems use Nearest Car(NC) algorithms based on the SCAN algorithm, which results in time efficiency problems. In this paper, we designed an elevator group-control algorithm for specific buildings that have approximate timetable data for most of the passengers in the building. In that way, it is possible to predict the destination and the location of passenger calls. The algorithm consists of two parts; the waiting function and the assignment function. They evaluate elevators' actions with respect to the calls and the overall situation. 10 different timetables are created in reference to a real timetable following midday traffic and interfloor traffic. The specific coefficients in the function are set by going through the genetic algorithm process that represents the best algorithm. As result, the average waiting time has shortened by a noticeable amount and the efficiency was close to the known DSS result. Finally, we analyzed the algorithm by evaluating the meaning of each coefficient result from the genetic algorithm.

• Korean Journal of Culture and Social Issue
• /
• v.17 no.3
• /
• pp.261-285
• /
• 2011

In our studies, We defined the concept of social reputation and aimed to estimate the effect of social reputation on likability, trust, preference of interpersonal relationship. To accomplish these goal, photographs of 12 persons(six young unmarried man, six young unmarried women) volunteered were shown to 60 raters, and the one male and one female pictures of scores of facial attractiveness are nearest to median were selected as experimental figures in preliminary study. After this, We asked 260 raters to assess likability, trust, preference of interpersonal relationship after showing raters the chosen pictures of man and woman and telling scenario of positive, negative reputation about these two persons. The outcomes showed that in both men and women, likability, trust, preference of persons who gained positive reputation were significantly higher than persons gained negative reputation. Facial attractiveness was effect on likability, trust, and preference, but effect size of reputation was much higher on likability, interpersonal preference, especially trust level. Also, in three-way ANCOVA results, Woman has showed higher likability and trust than man under the condition of good reputation in both woman was rater and object to be assessed, but on the contrary, likability, trust, and preference of woman were lower than man in either woman was rater or object to be judged under the bad reputation,. Lastly, this study's implications and limitations were discussed.

• Journal of the Korean Society for information Management
• /
• v.40 no.4
• /
• pp.307-327
• /
• 2023

To analyze the impact of word embedding on book titles, this study utilized word embedding models (Word2vec, GloVe, fastText) to generate embedding vectors from book titles. These vectors were then used as classification features for automatic classification. The classifier utilized the k-nearest neighbors (kNN) algorithm, with the categories for automatic classification based on the DDC (Dewey Decimal Classification) main class 300 assigned by libraries to books. In the automatic classification experiment applying word embeddings to book titles, the Skip-gram architectures of Word2vec and fastText showed better results in the automatic classification performance of the kNN classifier compared to the TF-IDF features. In the optimization of various hyperparameters across the three models, the Skip-gram architecture of the fastText model demonstrated overall good performance. Specifically, better performance was observed when using hierarchical softmax and larger embedding dimensions as hyperparameters in this model. From a performance perspective, fastText can generate embeddings for substrings or subwords using the n-gram method, which has been shown to increase recall. The Skip-gram architecture of the Word2vec model generally showed good performance at low dimensions(size 300) and with small sizes of negative sampling (3 or 5).