• 한국항공운항학회지
• /
• 제18권1호
• /
• pp.51-57
• /
• 2010

This study was to analyze the difference in pilot error by using the Signal Detection Theory. The task was to detect the targeted aircraft(signal) which is different shape from many other aircraft(noise). From the two experiments, we differentiated the task difficulty followed by change in noise stimuli. Experiment 1 was to search the signal stimuli(fighter plane) while the noise stimuli(cargo plane) were increasing. The results from the Experiment 1 showed the tendency to decrease the hit rate by increasing the number of noise stimuli. However, the false alarm rate was not increased. The sensitivity(d') showed quite high. In Experiment 2, a disturbance stimulus(helicopter) was added to noise stimuli. The result was generally similar to those of Experiment 1. However, the hit rate was lower than that of Experiment 1.

• 한국자동차공학회논문집
• /
• 제11권2호
• /
• pp.1-7
• /
• 2003

This paper proposes a method to detect misfired cylinders by the exhaust pressure ascent rate. The misfire is generated by faults of electric system or faults of fuel delivery system. It is one of the abnormal combustions. Therefore, it increases the unburned hydrocarbon and the carbon monoxide and affects a bad influence to the 3-way catalyst. The misfire causes to decrease the power of the engine and increase the consumption of the fuel. Early detection and correction of the misfired cylinders can prevent these unusual phenomena. The misfired cylinders can be detected by the comparison of exhaust pressure ascent rate during each cycle. The exhaust pressure ascent rate is defined as pressure rise per time. Our experimental results showed that the proposed method is effective in the detection of the misfired cylinders on a gasoline engine regardless loads and revolutions of the engine.

• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.745-755
• /
• 2023

The wire rope is an indispensable production machinery in coal mines. It is the main force-bearing equipment of the underground traction system. Accurate detection of wire rope defects and positions exerts an exceedingly crucial role in safe production. The existing defect detection solutions exhibit some deficiencies pertaining to the flexibility, accuracy and real-time performance of wire rope defect detection. To solve the aforementioned problems, this study utilizes the camera to sample the wire rope before the well entry, and proposes an object based on YOLOv5. The surface small-defect detection model realizes the accurate detection of small defects outside the wire rope. The transfer learning method is also introduced to enhance the model accuracy of small sample training. Herein, the enhanced YOLOv5 algorithm effectively enhances the accuracy of target detection and solves the defect detection problem of wire rope utilized in mine, and somewhat avoids accidents occasioned by wire rope damage. After a large number of experiments, it is revealed that in the task of wire rope defect detection, the average correctness rate and the average accuracy rate of the model are significantly enhanced with those before the modification, and that the detection speed can be maintained at a real-time level.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2651-2673
• /
• 2019

In order to detect Denial of Service (DoS) attacks, victim-side detection methods are used popularly such as static threshold-based method and machine learning-based method. However, as DoS attacking methods become more sophisticated, these methods reveal some natural disadvantages such as the late detection and the difficulty of tracing back attackers. Recently, in order to mitigate these drawbacks, source-side DoS detection methods have been researched. But, the source-side DoS detection methods have limitations if the volume of attack traffic is relatively very small and it is blended into legitimate traffic. Especially, with the subtle attack traffic, DoS detection methods may suffer from high false positive, considering legitimate traffic as attack traffic. In this paper, we propose an effective source-side DoS detection method with traffic seasonality aware adaptive threshold. The threshold of detecting DoS attack is adjusted adaptively to the fluctuated legitimate traffic in order to detect subtle attack traffic. Moreover, by understanding the seasonality of legitimate traffic, the threshold can be updated more carefully even though subtle attack happens and it helps to achieve low false positive. The extensive evaluation with the real traffic logs presents that the proposed method achieves very high detection rate over 90% with low false positive rate down to 5%.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.40-44
• /
• 2023

The defect detection based on deep learning requires minimal loss and high accuracy to pinpoint product defects. In this paper, we confirm the loss rate of deep learning training based on disc-shaped artificial scaffold images. It is intended to compare the performance of Cross-Entropy functions used in object detection algorithms. The model was constructed using normal, defective artificial scaffold images and category cross entropy and sparse category cross entropy. The data was repeatedly learned five times using each loss function. The average loss rate, average accuracy, final loss rate, and final accuracy according to the loss function were confirmed.

• 센서학회지
• /
• 제33권3호
• /
• pp.119-124
• /
• 2024

Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensing method for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step, fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256 values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with different parameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increased the recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. This is a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In our experiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.

• 융합신호처리학회논문지
• /
• 제17권1호
• /
• pp.18-25
• /
• 2016

자동차 보유량이 늘어남에 따라 남녀노소 모두 교통사고에 위협이 가해지고 있으며 교통사고가 자주 일어나는 점을 미연에 방지하기 위해 ADAS가 중요하다. 이러한 교통사고의 주범을 인지하고 방지하는 한 방법이 차선 검출을 이용하는 것이다. 따라서 본 논문에서는 영상처리를 통해 차선검출 기법을 연구하였고 영상처리에 의한 많은 에지 검출기법들 중 대표적인 소벨 에지 검출 기법과 캐니 에지 검출 기법을 사용하여, 두 가지 에지 검출기법을 통해 곡선과 직선의 차선 검출에서 가장 검출율이 좋은 기법을 찾아 직선의 차선을 검출하는 기법에 적용한다. 실험은 총 4,000프레임(주간영상 2,900프레임, 야간영상 1,100프레임)으로 실험을 수행하고, 실험 결과는 주간 영상에서 소벨 에지 검출 기법의 임계치는 2차미분차수로 검출하는 것이 가장 높은 후보 차선 검출율을 보였으며 검출율이 86.1%이고, 캐니 에지 검출 기법의 임계치는 Low=50, High=300에서 가장 높은 88.0%의 검출율을 보였다.

• Journal of applied mathematics & informatics
• /
• 제9권2호
• /
• pp.761-769
• /
• 2002

Due to the large scale application of software systems, software reliability plays an important role in software developments. In this paper, a software reliability growth model (SRGM) is proposed. The testing time on the right is truncated in this model. The instantaneous failure rate, mean-value function, error detection rate, reliability of the software, estimation of parameters and the simple applications of this model are discussed .

• 한국정보통신학회논문지
• /
• 제2권4호
• /
• pp.553-558
• /
• 1998

We present in this paper the ture union bound of the performance of chip level detection for coded DS/CDMA system operating in Rician fading channels such as LEO satellite mobile radio where the maximum doppler frequency is very high. The main objective of this paper is to calculate the exact doe union bound of BER performance of different performance of different quadrature detectors and to find a optimum spreading factor as a function of fade rate. The rationale of using multiple chip detection is to reduce the effective fade rate or variation. We considered chip level differential detection, chip level maximum likelihood sequence estimation, noncoherent detection and coherent detection with perfect channel state information as a reference.

• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.888-896
• /
• 2018

In this paper, we report detection and recognition of vehicle logo from images captured from street CCTV. Image data includes both the front and rear view of the vehicles. The proposed method is a two-step process which combines image preprocessing and faster region-based convolutional neural network (R-CNN) for logo recognition. Without preprocessing, faster R-CNN accuracy is high only if the image quality is good. The proposed system is focusing on street CCTV camera where image quality is different from a front facing camera. Using perspective transformation the top view images are transformed into front view images. In this system, the detection and accuracy are much higher as compared to the existing algorithm. As a result of the experiment, on day data the detection and recognition rate is improved by 2% and night data, detection rate improved by 14%.