• 한국지능시스템학회논문지
• /
• 제13권6호
• /
• pp.722-728
• /
• 2003

In this paper, we propose a fuzzy traffic controller of Sugeno`s fuzzy model so as to model the nonlinear characteristics of controlling the traffic light. It use a degree of the traffic congestion of the preceding roads as an input so that it can cope with traffic congestion appropriately, which causes the loss of fuel and our discomfort. First, in order to construct fuzzy traffic controller of Sugeno`s fuzzy model, we model the control process of the traffic light by using Mamdani`s fuzzy model, which has the uniform membership functions of the same size and shape. Second, we make Mamdani`s fuzzy model with the non-uniform membership functions so that it can exactly reflect the knowledge of experts and operators. Last, we construct the fuzzy traffic controller of Sugeno`s fuzzy model by learning from the input/output data, which is retrieved from Mamdani`s fuzzy model with the non-uniform membership functions. We compared and analyzed the fixed traffic light controller, the fuzzy traffic controller of Mamdani`s fuzzy model and the fuzzy traffic controller of Sugeno`s fuzzy model by using the delay time and the proportion of the entered vehicles to the occurred vehicles. As a result of comparison, the fuzzy traffic controller of Sugeno`s fuzzy model showed the best performance.

• 대한산업공학회지
• /
• 제42권4호
• /
• pp.263-269
• /
• 2016

The purpose of this study is to challenge a computational regression-type problem, that is handling large-size data, in which conventional metamodeling techniques often fail in a practical sense. To solve such problems, regression-type boosting, one of ensemble model techniques, together with bootstrapping-based re-sampling is a reasonable choice. This study suggests weight updates by the amount of the residual itself and a new error decision criterion which constructs an ensemble model of models selectively chosen by rejection limits. Through these ideas, we propose AdaBoost.RMU.R as a metamodeling technique suitable for handling large-size data. To assess the performance of the proposed method in comparison to some existing methods, we used 6 mathematical problems. For each problem, we computed the average and the standard deviation of residuals between real response values and predicted response values. Results revealed that the average and the standard deviation of AdaBoost.RMU.R were improved than those of other algorithms.

• 한국차세대컴퓨팅학회논문지
• /
• 제15권3호
• /
• pp.16-24
• /
• 2019

최근 뇌파를 기반으로 한 인간의 감정을 인식하는 연구가 인간-로봇 상호작용 분야에서 활발히 진행되고 있다. 본 논문에서는 MAHNOB-HCI에서 사용된 자기평가와 주석 레이블링 방법과는 다른, 이미지 기반의 뇌파 Topography를 이용한 레이블링을 통해 감정을 평가하는 방법을 제안한다. 제안한 방법은 뇌파 신호를 Topography의 이미지로 변환하여 기계학습 모델을 학습하고 이를 기반으로 Valence 기반의 감정을 평가한다. 제안한 방법은 레이블링 과정을 자동화하여 지연 시간을 없애고 객관적인 레이블링을 제공할 수 있다. MAHNOB-HCI 데이터베이스를 적용한 실험에서 SVM, kNN의 기계학습 모델을 학습하여 주석 레이블링과 성능 비교를 하였으며, 제안 방법의 감정인식 정확도를 SVM에서 54.2%, kNN에서 57.7%로 확인하였다.

• 방송공학회논문지
• /
• 제24권3호
• /
• pp.420-429
• /
• 2019

최근 CNN (Convolutional Neural Network) 기반의 화질 개선 기술이 H.265/HEVC와 같은 블록 기반 영상 압축 표준을 사용하여 압축된 영상의 화질을 향상시키는 데 적극적으로 사용되어 왔다. 이 논문은 이러한 영상 압축 기술을 위한 화질 개선 연구의 추세를 요약하고 분석하는 것을 목표로 한다. 먼저, 화질 개선을 위한 CNN의 구성 요소를 살펴보고 이미지 도메인에서의 사전 연구를 요약한다. 다음으로 네트워크 구조, 데이터셋 및 학습 방법의 세 가지 측면에서 관련 연구들을 정리하고 성능 비교를 위한 구현 및 실험결과를 제시하고자 한다.

• 반도체디스플레이기술학회지
• /
• 제20권3호
• /
• pp.113-116
• /
• 2021

As artificial intelligence technologies, including deep learning, develop, these technologies are being introduced to code similarity analysis. In the traditional analysis method of calculating the graph edit distance (GED) after converting the source code into a control flow graph (CFG), there are studies that calculate the GED through a trained graph neural network (GNN) with the converted CFG, Methods for analyzing code similarity through CNN by imaging CFG are also being studied. In this paper, to determine which approach will be effective and efficient in researching code similarity analysis methods using artificial intelligence in the future, code similarity is measured through funcGNN, which measures code similarity using GNN, and Siamese Network, which is an image similarity analysis model. The accuracy was compared and analyzed. As a result of the analysis, the error rate (0.0458) of the Siamese network was bigger than that of the funcGNN (0.0362).

• 한국재료학회지
• /
• 제31권12호
• /
• pp.719-726
• /
• 2021

Through the process of chemical vapor deposition, Tungsten Hexafluoride (WF₆) is widely used by the semiconductor industry to form tungsten films. Tungsten Hexafluoride (WF₆) is produced through manufacturing processes such as pulverization, wet smelting, calcination and reduction of tungsten ores. The manufacturing process of Tungsten Hexafluoride (WF₆) is required thorough quality control to improve productivity. In this paper, a real-time detection system for oxidation defects that occur in the manufacturing process of Tungsten Hexafluoride (WF₆) is proposed. The proposed system is implemented by applying YOLOv5 based on Convolutional Neural Network (CNN); it is expected to enable more stable management than existing management, which relies on skilled workers. The implementation method of the proposed system and the results of performance comparison are presented to prove the feasibility of the method for improving the efficiency of the WF₆ manufacturing process in this paper. The proposed system applying YOLOv5s, which is the most suitable material in the actual production environment, demonstrates high accuracy (mAP@0.5 99.4 %) and real-time detection speed (FPS 46).

• Advances in materials Research
• /
• 제11권1호
• /
• pp.75-90
• /
• 2022

In this paper, functionality of soft computing algorithms such as Group method of data handling (GMDH), Random forest (RF), Random tree (RT), Linear regression (LR), M5P, and artificial neural network (ANN) have been looked out to predict the compressive strength of concrete mixed with marble powder. Assessment of result suggests that, the overall performance of ANN based model gives preferable results over the different applied algorithms for the estimate of compressive strength of concrete. The results of coefficient of correlation were maximum in ANN model (0.9139) accompanied through RT with coefficient of correlation (CC) value 0.8241 and minimum root mean square error (RMSE) value of ANN (4.5611) followed by RT with RMSE (5.4246). Similarly, other evaluating parameters like, Willmott's index and Nash-sutcliffe coefficient value of ANN was 0.9458 and 0.7502 followed by RT model (0.8763 and 0.6628). The end result showed that, for both subsets i.e., training and testing subset, ANN has the potential to estimate the compressive strength of concrete. Also, the results of sensitivity suggest that the water-cement ratio has a massive impact in estimating the compressive strength of concrete with marble powder with ANN based model in evaluation with the different parameters for this data set.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3889-3903
• /
• 2022

To address the problem of low detection accuracy due to training noise caused by mislabeling when Tri-training for network intrusion detection (NID), we propose a Tri-training algorithm based on cross entropy and K-nearest neighbors (TCK) for network intrusion detection. The proposed algorithm uses cross-entropy to replace the classification error rate to better identify the difference between the practical and predicted distributions of the model and reduce the prediction bias of mislabeled data to unlabeled data; K-nearest neighbors are used to remove the mislabeled data and reduce the number of mislabeled data. In order to verify the effectiveness of the algorithm proposed in this paper, experiments were conducted on 12 UCI datasets and NSL-KDD network intrusion datasets, and four indexes including accuracy, recall, F-measure and precision were used for comparison. The experimental results revealed that the TCK has superior performance than the conventional Tri-training algorithms and the Tri-training algorithms using only cross-entropy or K-nearest neighbor strategy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권8호
• /
• pp.2552-2570
• /
• 2022

Underwater images usually have various problems, such as the color cast of underwater images due to the attenuation of different lights in water, the darkness of image caused by the lack of light underwater, and the haze effect of underwater images because of the scattering of light. To address the above problems, the channel attention mechanism, strengthen-operate-subtract (SOS) boosting mechanism and gated fusion module are introduced in our paper, based on which, an underwater image recovery network is proposed. First, for the color cast problem of underwater images, the channel attention mechanism is incorporated in our model, which can well alleviate the color cast of underwater images. Second, as for the darkness of underwater images, the similarity between the target underwater image after dehazing and color correcting, and the image output by our model is used as the loss function, so as to increase the brightness of the underwater image. Finally, we employ the SOS boosting module to eliminate the haze effect of underwater images. Moreover, experiments were carried out to evaluate the performance of our model. The qualitative analysis results show that our method can be applied to effectively recover the underwater images, which outperformed most methods for comparison according to various criteria in the quantitative analysis.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.393-396
• /
• 2022

본 연구는 국방과학기술 분야의 특허 및 논문 실적을 이용하여 통계기반 기계학습 모델 4 종을 학습하고, 실제 분석 대상기관의 데이터 입력결과를 분석하여 실용성에 대한 한계점 분석을 목적으로 한다. 기존 연구에서는 특허분류코드를 기준으로 분류하여 특수 목적으로 활용하거나 세부 연구 범위 내 연구 주제탐색 및 특징연구 등 미시적인 관점에서의 상세연구 활용 목적인 반면, 본 연구는 거시적인 관점에서 연구의 전체적인 흐름과 경향성 파악을 목적으로 한다. 이에 ICT 기술 138 종의 특허 및 논문 30,965 건과 국방과학기술 192 종의 특허 및 논문 23,406 건을 학습데이터로 각 모델을 학습하였다. 비교한 통계기반 학습모델은 Support Vector Machines, Decision Tree, Naive Bayes, XGBoost 모델이다. 학습데이터에 대한 학습검증 단계에서는 최대 99.4%의 성능을 보였다. 다만, 실제 분석대상기관의 특허 및 논문 12,824 건으로 입력분석한 결과, 모델별 편향성 문제, 데이터 전처리 이슈, 다중클래스 및 다중레이블 문제를 확인, 도출한 문제에 대한 해결방안을 제시하고 추가 연구의 방향성을 제시한다.