• Korean Journal of Cognitive Science
• /
• v.25 no.1
• /
• pp.1-24
• /
• 2014

Growing boy of studies focus on the letter transposition effect since it gives the information on how letters are coded and what variables are involved in the processes of word recognition. This review investigated various models on letter transposition effect. While most proposed models rely mainly on the bottom-up processes, evidences from various studies suggested the necessity of the top-down variables based on the cognitive processing mechanism. Especially, empirical evidences suggested that Hangul model should include a position specific processing mechanism based on onset, vowel, and coda of the Korean character.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1881-1892
• /
• 1997

This paper proposes the method for recognition of printed chinese characters by probabilistic VQ networks and multi-stage recognizer has hierarchical structure. We use modular neural networks, because it is difficult to construct a large-scale neural network. Problems in this procedure are replaced by probabilistic neural network model. And, Confused Characters which have significant ratio of miss-classification are reclassified using the entropy theory. The experimental object consists of 4,619 chinese characters within the KSC5601 code except the same shape but different code. We have 99.33% recognition rate to the training data, and 92.83% to the test data. And, the recognition speed of system is 4-5 characters per second. Then, these results demonstrate the usefulness of our work.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.439-448
• /
• 2021

Driver negligence accounts for the largest proportion of the causes of traffic accidents, and research to detect them is continuously being conducted. This paper proposes a method to accurately detect a distracted driver and localize the most characteristic parts of the driver. The proposed method hierarchically constructs a CNN basic model that classifies 10 classes based on CAM in order to detect driver distration and 4 subclass models for detailed classification of classes having a confusing or common feature area in this model. The classification result output from each model can be considered as a new feature indicating the degree of matching with the CNN feature maps, and the accuracy of classification is improved by horizontally combining and learning them. In addition, by combining the heat map results reflecting the classification results of the basic and detailed classification models, the characteristic areas of attention in the image are found. The proposed method obtained an accuracy of 95.14% in an experiment using the State Farm data set, which is 2.94% higher than the 92.2%, which is the highest accuracy among the results using this data set. Also, it was confirmed by the experiment that more meaningful and accurate attention areas were found than the results of the attention area found when only the basic model was used.

• Advanced Industrial SCIence
• /
• v.3 no.2
• /
• pp.8-16
• /
• 2024

This paper shows the system of drug classification, the goal of this is to foretell the apt drug for the patients based on their demographic and physiological traits. The dataset consists of various attributes like Age, Sex, BP (Blood Pressure), Cholesterol Level, and Na_to_K (Sodium to Potassium ratio), with the objective to determine the kind of drug being given. The models used in this paper are K-Nearest Neighbors (KNN), Logistic Regression and Random Forest. Further to fine-tune hyper parameters using 5-fold cross-validation, GridSearchCV was used and each model was trained and tested on the dataset. To assess the performance of each model both with and without hyper parameter tuning evaluation metrics like accuracy, confusion matrices, and classification reports were used and the accuracy of the models without GridSearchCV was 0.7, 0.875, 0.975 and with GridSearchCV was 0.75, 1.0, 0.975. According to GridSearchCV Logistic Regression is the most suitable model for drug classification among the three-model used followed by the K-Nearest Neighbors. Also, Na_to_K is an essential feature in predicting the outcome.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.2
• /
• pp.139-148
• /
• 2020

The most important factor affecting the berthing energy generated when a ship berths is the berthing velocity. Thus, an accident may occur if the berthing velocity is extremely high. Several ship features influence the determination of the berthing velocity. However, previous studies have mostly focused on the size of the vessel. Therefore, the aim of this study is to analyze various features that influence berthing velocity and determine their respective importance. The data used in the analysis was based on the berthing velocity of a ship on a jetty in Korea. Using the collected data, machine learning classification algorithms were compared and analyzed, such as decision tree, random forest, logistic regression, and perceptron. As an algorithm evaluation method, indexes according to the confusion matrix were used. Consequently, perceptron demonstrated the best performance, and the feature importance was in the following order: DWT, jetty number, and state. Hence, when berthing a ship, the berthing velocity should be determined in consideration of various features, such as the size of the ship, position of the jetty, and loading condition of the cargo.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.19-23
• /
• 2024

Patients with amputations of both hands need prosthetic hands that serve both cosmetic and functional purposes, and research on prosthetic hands using electromyography of remaining muscles is active, but there is still the problem of high cost. In this study, an artificial prosthetic hand was manufactured and its performance was evaluated using low-cost parts and software such as a surface electromyography sensor, machine learning software Edge Impulse, Arduino Nano 33 BLE, and 3D printing. Using signals acquired with surface electromyography sensors and subjected to digital signal processing through Edge Impulse, the flexing movement signals of each finger were transmitted to the fingers of the prosthetic hand model through training to determine the type of finger movement using machine learning. When the digital signal processing conditions were set to a notch filter of 60 Hz, a bandpass filter of 10-300 Hz, and a sampling frequency of 1,000 Hz, the accuracy of machine learning was the highest at 82.1%. The possibility of being confused between each finger flexion movement was highest for the ring finger, with a 44.7% chance of being confused with the movement of the index finger. More research is needed to successfully develop a low-cost prosthetic hand.

• Journal of Navigation and Port Research
• /
• v.27 no.4
• /
• pp.367-373
• /
• 2003

The marine accident investigation of Korean Marine Safety Tribunal does not keep up with the international rule and guideline. Also there is no manual for a proper investigation into the marine accident. This study analyzed the investigation system and manual of Korea. USA and Japan etc., and proposed the new investigation system and manual of KMST including the inquiry guideline according to the type of marine accident.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.102-102
• /
• 2019

토양수분은 수문 및 기상 현상의 주요 요인으로 가뭄, 홍수 및 범람과 같은 자연 재해와 관련이 깊은 인자이다. 이러한 토양수분의 관측 기술 중 위성 데이터를 활용한 원격탐사 기술은 광범위한 지역의 관측이 용이하고 지점이 아닌 공간 데이터를 제공하는 장점을 지니고 있어 토양수분의 관측에 유리하다. 특히 높은 해상도의 위성기반 토양수분 데이터는 토양수분의 변동성이 큰 지역의 수문, 기상학적 현상을 보다 자세히 분석할 수 있게 해주며 가뭄 및 범람과 같은 수자원 관련 재해를 정확하게 분석하는데 요구된다. 이로 인해 최근 Sentinel-1 위성에서 운용중인 Synthetic Aperture Radar(SAR) 데이터를 이용한 매우 높은 공간해상도(10m~1km)를 지니고 있는 토양수분데이터 생산에 관한 연구가 세계적으로 활발히 진행되고 있다. 그러나 국내에서는 Sentinel-1 위성을 이용한 토양수분 데이터 복원에 관한 연구가 미비한 실정이다. 따라서 본 연구에서는 파주 감악산 설마천 유역에서의 Sentinel-1 위성의 SAR 데이터를 이용한 고해상도 토양수분 데이터를 복원하고자 한다. 파주 설마천 유역은 감악산 일대로 경사가 심하고 식생이 두터운 산악지형이다. SAR를 이용하여 산지에서 신뢰성 있는 토양수분 자료를 복원하기 위해서는 가장 큰 오차의 원인으로 작용하는 경사와 식생을 고려하여야 한다. 먼저 표면 경사의 영향의 경우 SAR 센서의 레이더 입사각과 수치 표고 모델을 이용하여 고려하고자 한다. 다음 과정으로 표면 경사가 고려된 Sentinel-1 데이터의 후방산란계수와 Landsat-8 데이터 및 지점 토양수분 데이터를 이용하여 식생에 따른 후방산란계수의 거동을 Water Cloud Model을 이용하여 분석하였다. Water Cloud Model은 토양위의 식생의 수분이 후방산란계수에 혼동을 주는 구름과 같이 작용한다고 가정하고 식생수분을 후방산란계수와 레이더 입사각 및 식생지수를 통해 계산하는 모델이며 이를 이용하여 토양수분 복원에 있어 식생의 영향을 제거하고자 하였다. 이를 통해 식생과 표면 경사를 고려하여 복원된 토양수분 데이터를 설마천 유역의 지점 데이터와 비교 분석하고 다른 위성기반 토양수분 데이터 및 강우 데이터를 이용하여 평가하였다. 본 연구결과를 통해 한반도 산지에서의 SAR 데이터를 이용한 토양수분 복원 기술의 기초가 마련될 것이며 이를 통해 산지가 대부분인 한반도의 토양수분 거동을 이해하는데 유용한 자료를 제공할 수 있을 것으로 기대된다. 본 연구 이후에는 연구결과분석을 통한 산지에서의 고해상도 토양수분 복원 알고리즘을 분석, 보완하고 한반도에서의 SAR 기반 토양수분 데이터의 정확도를 높이는 연구가 진행되어야 할 것이다.

• The Mathematical Education
• /
• v.61 no.1
• /
• pp.157-178
• /
• 2022

Mathematics teachers' content knowledge is an important asset for effective teaching. To enhance this asset, teacher's knowledge is required to be diagnosed and developed. In this study, we employed problem-posing and problem-solving tasks to diagnose preservice teachers' understanding of fraction multiplication. We recruited 41 elementary preservice teachers who were taking elementary mathematics methods courses in Korea and the United States and gave the tasks in their final exam. The collected data was analyzed in terms of interpreting, understanding, model, and representing of fraction multiplication. The results of the study show that preservice teachers tended to interpret (fraction)×(fraction) more correctly than (whole number)×(fraction). Especially, all US preservice teachers reversed the meanings of the fraction multiplier as well as the whole number multiplicand. In addition, preservice teachers frequently used 'part of part' for posing problems and solving posed problems for (fraction)×(fraction) problems. While preservice teachers preferred to a area model to solve (fraction)×(fraction) problems, many Korean preservice teachers selected a length model for (whole number)×(fraction). Lastly, preservice teachers showed their ability to make a conceptual connection between their models and the process of fraction multiplication. This study provided specific implications for preservice teacher education in relation to the meaning of fraction multiplication, visual representations, and the purposes of using representations.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.23-35
• /
• 2021

In the era of the 4th industrial revolution, smart factories have received great attention, where production and manufacturing technology and ICT converge. With the development of IoT technology and big data, automation of production systems has become possible. In the advanced manufacturing industry, production systems are subject to unscheduled performance degradation and downtime, and there is a demand to reduce safety risks by detecting and reparing potential errors as soon as possible. This study designs a model based on supervised and unsupervised learning for detecting anomalies. The accuracy of XGBoost, LightGBM, and CNN models was compared as a supervised learning analysis method. Through the evaluation index based on the confusion matrix, it was confirmed that LightGBM is most predictive (97%). In addition, as an unsupervised learning analysis method, MD, AE, and LSTM-AE models were constructed. Comparing three unsupervised learning analysis methods, the LSTM-AE model detected 75% of anomalies and showed the best performance. This study aims to contribute to the advancement of the smart factory by combining supervised and unsupervised learning techniques to accurately diagnose equipment failures and predict when abnormal situations occur, thereby laying the foundation for preemptive responses to abnormal situations. do.