• Bulletin of the Korean Chemical Society
• /
• v.15 no.1
• /
• pp.23-25
• /
• 1994

A simple analytical method that allows direct monitoring of small amount of CO$_2$ in a CO$_2$ discharge tube which utilizes the optoacoustic detection technique is described. The dependence of the optoacoustic signal on the mole fraction of CO$_2$ was shown that the system responded linearly to the amount of CO$_2$ present in the miniature discharge cavity equipped with Cu electrodes. It was also found that fraction of dissociated CO$_2$ varied from 14 to 37% of the initial concentration which depended on the current and the pressure in the tube. This simple and easy detection method has proven to possess the practical advantages over the conventional systems for the study of CO$_2$ laser electrodes.

• Proceedings of the KSR Conference
• /
• 2008.11b
• /
• pp.1312-1320
• /
• 2008

In this paper, we analyzed the error rate performance of convolution coded 16 QAM signal with Optimum Threshold Detection with maximum ratio combining diversity in Rician Fading Environments. The performance of 16-QAM signal with CTD (conventional threshold detection) which employs convolution coding technique was analyzed and the performance improvement of convolution coded 16-QAM signal with OTD (optimum threshold detection) which is varied according to fading parameter "K" and AWGN in Rician Fading channel was simulated. As a result of analysis, it was shown the effect of performance improvement to overcome the environment of mobile radio data communication channel.

• Journal of Sensor Science and Technology
• /
• v.30 no.5
• /
• pp.290-294
• /
• 2021

Experts have designed popular and successful model architectures, which, however, were not the optimal option for different scenarios. Despite the remarkable performances achieved by deep neural networks, manually designed networks for classification tasks are the backbone of object detection. One major challenge is the ImageNet pre-training of the search space representation; moreover, the searched network incurs huge computational cost. Therefore, to overcome the obstacle of the pre-training process, we introduce a network adaptation technique using a pre-trained backbone model tested on ImageNet. The adaptation method can efficiently adapt the manually designed network on ImageNet to the new object-detection task. Neural architecture search (NAS) is adopted to adapt the architecture of the network. The adaptation is conducted on the MobileNetV2 network. The proposed NAS is tested using SSDLite detector. The results demonstrate increased performance compared to existing network architecture in terms of search cost, total number of adder arithmetics (Madds), and mean Average Precision(mAP). The total computational cost of the proposed NAS is much less than that of the State Of The Art (SOTA) NAS method.

• Journal of Korea Multimedia Society
• /
• v.21 no.11
• /
• pp.1244-1253
• /
• 2018

The color of traffic light is sensitive to various illumination conditions. Especially it loses the hue information when oversaturation happens on the lighting area. This paper proposes a traffic light recognition method robust to these illumination variations. The method consists of two steps of traffic light detection and recognition. It just uses the intensity and saturation in the first step of traffic light detection. It delays the use of hue information until it reaches to the second step of recognizing the signal of traffic light. We utilized a deep learning technique in the second step. We designed a deep convolutional neural network(DCNN) which is composed of three convolutional networks and two fully connected networks. 12 video clips were used to evaluate the performance of the proposed method. Experimental results show the performance of traffic light detection reporting the precision of 93.9%, the recall of 91.6%, and the recognition accuracy of 89.4%. Considering that the maximum distance between the camera and traffic lights is 70m, the results shows that the proposed method is effective.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.1017-1028
• /
• 2019

Pedestrian tracking is a particular object tracking problem and an important component in various vision-based applications, such as autonomous cars and surveillance systems. Following several years of development, pedestrian tracking in videos remains challenging, owing to the diversity of object appearances and surrounding environments. In this research, we proposed a tracking-by-detection system for pedestrian tracking, which incorporates a convolutional neural network (CNN) and color information. Pedestrians in video frames are localized using a CNN-based algorithm, and then detected pedestrians are assigned to their corresponding tracklets based on similarities between color distributions. The experimental results show that our system is able to overcome various difficulties to produce highly accurate tracking results.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.425-430
• /
• 2022

As robots are considered one of the mainstream digital transformations, robots with machine vision becomes a main area of study providing the ability to check what robots watch and make decisions based on it. However, it is difficult to find a small object in the image mainly due to the flaw of the most of visual recognition networks. Because visual recognition networks are mostly convolution neural network which usually consider local features. So, we make a model considering not only local feature, but also global feature. In this paper, we propose a detection method of a small marker on the object using deep learning and an algorithm that considers global features by combining Transformer's self-attention technique with a convolutional neural network. We suggest a self-attention model with new definition of Query, Key and Value for model to learn global feature and simplified equation by getting rid of position vector and classification token which cause the model to be heavy and slow. Finally, we show that our model achieves higher mAP than state of the art model YOLOr.

• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.298-301
• /
• 2011

Edge detection is an base research task in the field of image processing. Edge detection can be regarded as a technique for locating pixels of abrupt gray-level change. So with Gradient method, it can be computed easily. But it can't satisfy human naked eye. so in this paper, new algorithm based on the NLM(Non Local Means) is proposed for good performance for human naked eye.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.65-68
• /
• 2021

본 연구에서는 Dilated U-Net 기반의 이미지 복원기법을 통해 콘크리트 균열 추출 성능 개선 방안을 제안한다. 콘크리트 균열은 구조물의 미관상의 문제뿐 아니라 추후 큰 안전사고의 원인이 될 수 있어 초기대응이 중요하다. 현재는 점검자가 직접 육안으로 검사하는 외관 검사법이 주로 사용되고 있지만, 이는 정확성 및 비용, 시간, 그리고 안전성 면에서 한계를 갖고 있다. 이에 콘크리트 구조물 표면에 대해 획득한 영상 처리 기법을 사용한 검사 방식 도입의 관심이 늘어나고 있다. 또한, 딥러닝 기술의 발달로 딥러닝을 적용한 영상처리의 연구 역시 활발하게 진행되고 있다. 본 연구는 콘크리트 균열 추개선출 성능 개선을 위해 Dilated U-Net 기반의 이미지 복원기법을 적용하는 방안을 제안하였고 성능 검증 결과, 기존 U-Net 기반의 정확도가 98.78%, 조화평균 82.67%였던 것에 비해 정확도 99.199%, 조화평균 88.722%로 성능이 되었음을 확인하였다.

• Journal of Advanced Information Technology and Convergence
• /
• v.9 no.1
• /
• pp.1-10
• /
• 2019

In recent years, information collection of attacks through stealth port scanning technology has become more sophisticated. The most commonly used Nmap port scanner supports a variety of stealth scanning technologies along with the existing scanning techniques. Nmap also supports Idle scan that is different from conventional stealth scans. This is a more sophisticated stealth scan technique by applying the SYN scan and ACK scan techniques. In previous studies, the detection of Idle scanning was on zombie system, but was not on victim system. In this paper, we propose an effective detection method of Idle scan on victim system. The Idle scanning is composed of two stages; they are probing the zombie and victim system and scanning the victim system. We analyzed the characteristics of the two stages. The characteristics, we captured, are that SYN and RST packets are different from normal packet. We applied them to detection method, then Idle scanning is detected effectively.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.151-153
• /
• 2023

Federated learning (FL)-based network intrusion detection techniques have enormous potential for securing the Industrial Internet of Things (IIoT) cybersecurity. The openness and connection of systems in smart industrial facilities can be targeted and manipulated by malicious actors, which emphasizes the significance of cybersecurity. The conventional centralized technique's drawbacks, including excessive latency, a congested network, and privacy leaks, are all addressed by the FL method. In addition, the rich data enables the training of models while combining private data from numerous participants. This research aims to create an FL-based architecture to improve cybersecurity and intrusion detection in IoT networks. In order to assess the effectiveness of the suggested approach, we have utilized well-known cybersecurity datasets along with centralized and federated machine learning models.