• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.76-84
• /
• 2022

Arrhythmia is a condition in which the heart beats abnormally or irregularly, early detection is very important because it can cause dangerous situations such as fainting or sudden cardiac death. However, performance degradation occurs due to personalized differences in ECG signals. In this paper, we propose arrhythmia classification using hybrid combination model of CNN-LSTM. For this purpose, the R wave is detected from noise removed signal and a single bit segment was extracted. It consisted of eight convolutional layers to extract the features of the arrhythmia in detail, used them as the input of the LSTM. The weights were learned through deep learning and the model was evaluated by the verification data. The performance was compared in terms of the accuracy, precision, recall, F1 score through MIT-BIH arrhythmia database. The achieved scores indicate 92.3%, 90.98%, 92.20%, 90.72% in terms of the accuracy, precision, recall, F1 score, respectively.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2004.02a
• /
• pp.199-221
• /
• 2004

본 연구의 목적은 해안 유역의 지하수 함양율을 평가하는 기법을 제시하는 데 그 목적이 있다. 해안 유역에서 이용되는 수자원 중에서 지하수가 차지하는 비중은 내륙에 소재한 유역의 지하수 비중에 비하여 더욱 크다. 해안지역의 급수율은 전국 평균 급수율의 절반에도 미치지 못하는 40%대로 나타났으며, 해안지역 1인당 지하수 이용량은 전국 평균의 4배에 달하는 261㎥로 조사되었다(홍성훈 외, 2003). 또한 94년과 96년에 발생한 10∼15년 재현기간의 가뭄 시대부분의 해안지역이 제한급수지역에 포함된 바 있다(건설교통부, 2001). (중략)

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.630-639
• /
• 2001

This study proposes a new calculation method for generating real nighttime lamp-lit images. In order to improve the color appearance in the prediction of a nighttime lamp-lighted scene, the lamp-lit image is synthesized based on spectral distribution using the estimated local spectral distribution of the headlamps and the surface reflectance of every object. The Principal component analysis method is introduced to estimate the surface color of an object, and the local spectral distribution of the headlamps is calculated based on the illuminance data and spectral distribution of the illuminating headlamps. HID and halogen lamps are utilized to create beam patterns and captured road scenes are used as background images to simulate actual headlamp-lit images on a monitor. As a result, the reproduced images presented a color appearance that was very close to a real nighttime road image illuminated by single and multiple headlamps compared to the conventional graphic-based algorithm.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.7
• /
• pp.80-86
• /
• 2019

As computer performance improves, research using deep learning are being actively carried out in various fields. Recently, deep learning technology has been applying to the safety evaluation for structures. In particular, the internal blades of a turbine structure requires experienced experts and considerable time to detect surface damages because of the difficulty of separation of the blades from the structure and the dark environmental condition. This study proposes a Faster R-CNN deep learning model that can detect surface damages on the internal blades, which is one of the primary elements of the turbine structure. The deep learning model was trained using image data with dent and punch damages. The image data was also expanded using image filtering and image data generator techniques. As a result, the deep learning model showed 96.1% accuracy, 95.3% recall, and 96% precision. The value of the recall means that the proposed deep learning model could not detect the blade damages for 4.7%. The performance of the proposed damage detection system can be further improved by collecting and extending damage images in various environments, and finally it can be applicable for turbine engine maintenance.

• The KIPS Transactions:PartB
• /
• v.14B no.5
• /
• pp.383-390
• /
• 2007

Interactions between proteins and genes are often considered essential in the description of biomolecular phenomena and networks of interactions are considered as an entre for a Systems Biology approach. Recently, many works try to extract information by analyzing biomolecular text using natural language processing technology. Previous researches insist that linguistic information is useful to improve the performance in detecting gene interactions. However, previous systems do not show reasonable performance because of low recall. To improve recall without sacrificing precision, this paper proposes a new method for detection of gene interactions based on syntactic relations. Without biomolecular knowledge, our method shows reasonable performance using only small size of training data. Using the format of LLL05(ICML05 Workshop on Learning Language in Logic) data we detect the agent gene and its target gene that interact with each other. In the 1st phase, we detect encapsulation types for each agent and target candidate. In the 2nd phase, we construct verb lists that indicate the interaction information between two genes. In the last phase, to detect which of two genes is an agent or a target, we learn direction information. In the experimental results using LLL05 data, our proposed method showed F-measure of 88% for training data, and 70.4% for test data. This performance significantly outperformed previous methods. We also describe the contribution rate of each phase to the performance, and demonstrate that the first phase contributes to the improvement of recall and the second and last phases contribute to the improvement of precision.

• Ecology and Resilient Infrastructure
• /
• v.10 no.4
• /
• pp.107-115
• /
• 2023

High turbidity in source water can have adverse effects on water treatment plant operations and aquatic ecosystems, necessitating turbidity management. Consequently, research aimed at predicting river turbidity continues. This study developed a multi-class classification model for prediction of turbidity using LightGBM (Light Gradient Boosting Machine), a representative ensemble machine learning algorithm. The model utilized data that was classified into four classes ranging from 1 to 4 based on turbidity, from low to high. The number of input data points used for analysis varied among classes, with 945, 763, 95, and 25 data points for classes 1 to 4, respectively. The developed model exhibited precisions of 0.85, 0.71, 0.26, and 0.30, as well as recalls of 0.82, 0.76, 0.19, and 0.60 for classes 1 to 4, respectively. The model tended to perform less effectively in the minority classes due to the limited data available for these classes. To address data imbalance, the SMOTE (Synthetic Minority Over-sampling Technique) algorithm was applied, resulting in improved model performance. For classes 1 to 4, the Precision and Recall of the improved model were 0.88, 0.71, 0.26, 0.25 and 0.79, 0.76, 0.38, 0.60, respectively. This demonstrated that alleviating data imbalance led to a significant enhancement in Recall of the model. Furthermore, to analyze the impact of differences in input data composition addressing the input data imbalance, input data was constructed with various ratios for each class, and the model performances were compared. The results indicate that an appropriate composition ratio for model input data improves the performance of the machine learning model.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.382-385
• /
• 2007

본 논문은 "X라는 인물은 누구인가?"와 같은 질의어가 주어질 때, X라는 인물에 대한 나이, 직업, 학력 또는 특정 사건에서 X라는 인물의 역할에 대한 정보를 기술하는 문장을 인식하고 추출함으로써 해당 인물에 대한 신문 기사 내용을 요약하는 방법을 제시한다. 질의어 용어에 대해 가능한 많은 관련 문장을 추출하기 위하여 중심 벡터에 기반한 통계적 방법을 적용하였으며, 정확도와 재현율 성능을 개선하기 위해 위키피디어 같은 외부 지식을 사용한 중심 단어의 개선된 가중치 측도를 적용하였다. 실험 대상인 전자신문 말뭉치 상에서 출현 빈도수가 큰 20 인의 IT 인물에 대해 제안한 방법이 개선된 성능을 보임을 알 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.232-234
• /
• 2004

XML 문서의 요소는 의미적인 정보와 트리기반의 구조적인 정보를 포함하고 있기 때문에 요소의 구조적인 유사성이 곧 XML 문서의 유사성으로 연구되어 왔다. 그러나 구조적이고 순차적인 유사성만을 고려한 순차패턴 유사성 검색 방법은 의미적인(sementic) 유사성을 제대로 반영을 할 수가 없다. 이것은 정보 검색에 있어 재현율(recall)을 낮을 수밖에 없는 원인을 제공한다. 따라서 본 논문에서는 기존에 사용되었던 순차패턴을 기반으로 한 유사성의 계산 방법과 각각의 연구 방법이 의미적인 유사성에 대하여 한계가 있음을 찾아보았다.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1557-1560
• /
• 2003

본 논문에서는 이 문서 클러스터링 방법 중 계층적 방법인 Kmeans 클러스터링 알고리즘을 이용하여 문서를 클러스터링 하고자 한다. 기존의 Kmeans 클러스터링 알고리즘은 문서의 수가 많을 경우 하나의 클러스터링에 너무 많은 문서들이 할당되는 문제점이 있다. 이 치우침을 완화하고자 각 클러스터링에 할당된 문서 수에 따라서 문서에 가중치를 부여한 후 다시 클러스터링을 하는 방법을 제안하였다. 실험 결과는 정확률, 재현율을 결합한 조화 평균(F-measure)을 사용하여 평가하였으며 기존 알고리즘보다 9％이상의 성능 향상을 나타냈다.

• Proceedings of the Korean Society for Information Management Conference
• /
• 1994.12a
• /
• pp.3-6
• /
• 1994

본 연구에서는 전문데이터베이스의 자연어 검색에 있어서 탐색시소러스의 검색효율과 퍼지시소러스 관련어 확장검색의 검색효율을 측정하였다. 한국경제신문사 ECONET의 기사 데이터베이스를 대상으로 질문의 기본 탐색어를 계층어와 관련어로 확장검색한 결과 탐색시소러스를 이용한 관련어 확장검색과 종합검색이 정확률은 저하시키지 앓고 재현율을 향상시켰다.