• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.887-889
• /
• 2016

본 연구는 전도성 섬유를 양말에 부착하여 발바닥에서 심전도(ECG, Electrocardiogram) 신호를 검출하였다. 발바닥에서 측정한 심전도 신호와 손목에서 측정한 심전도 신호에 Pan-Tompkins algorithm을 적용하였고 R-R interval을 검출하였다. 이후 발바닥과 손목에서 측정된 심전도의 유의성을 검출하기 위해 비모수 검정법인 Spearman검정을 사용하여 상관분석을 수행하였다. 상관분석 결과, 유의확률 p=0.00에서 correlation coefficient=0.901로 두 데이터는 강한 양의 선형 관계에 있는 것으로 나타났다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.10A
• /
• pp.949-955
• /
• 2008

In this paper, we propose the improved energy detector using adaptive thresholds in cognitive radio system, in order to compensate the weak points of the existing energy detector in the distorted communication environment. In addition, by investigating the several parameters we analyze its performance. The numerical results show the proposed method may get the performance gain, when the mobile speed is slow (3 km/h) as well as the false alarm probability is low ($P_f=10^{-1}$).

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.11a
• /
• pp.160-163
• /
• 2014

본 논문에서는 프레임 내 전체 배경 모델을 도입하여 기존 배경 분리 알고리즘에서의 오검출을 줄여 정확도를 개선하고자 한다. 기존의 알고리즘은 프레임 간의 정보만을 이용하여 배경 확률 모델을 만들고 배경을 제외한 전경만을 검출한다. 제안하는 알고리즘에서는 먼저 기존의 알고리즘을 통해 프레임 간의 정보를 이용하여 간단하게 배경과 전경을 분리한다. 그 후 프레임 내 정보를 통해 전체 배경 모델을 만들고, 앞의 결과에서 한번 더 배경을 제외함으로써 검출 정확도를 개선하고자 한다. 실험결과에서 Change Detection Workshop dataset에 대해 실험을 한 후 결과 영상 비교 및 F-measure 를 통해 개선된 결과를 확인할 수 있다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.1
• /
• pp.83-85
• /
• 2016

The OFDM with LS signal detection performs worse in fast time varying channels as the channel matrix has higher chance of becoming ill-conditioned. Various regularization methods are applied to avoid performance degradation in LS signal detection. In this paper, we proposed a CGLS method with the stopping criteria imposed by the characteristics of the modulation method, which shows performance comparable to that of the optimal LMMSE.

• Smart Media Journal
• /
• v.7 no.3
• /
• pp.16-21
• /
• 2018

This paper presents the design and implementation of a deep learning-based automated weed detector on onion fields. The system is based on a Convolutional Neural Network that specifically selects proposed regions. The detector initiates training with a dataset taken from agricultural onion fields, after which candidate regions with very high probability of suspicion are considered weeds. Non-maximum suppression helps preserving the less overlapped bounding boxes. The dataset collected from different onion farms is evaluated with the proposed classifier. Classification accuracy is about 99% for the dataset, indicating the proposed method's superior performance with regard to weed detection on the onion fields.

• Nuclear Engineering and Technology
• /
• v.26 no.4
• /
• pp.548-554
• /
• 1994

The full-energy peak efficiency for a collimated geometry of a Si (Li) detector has been experimentally determined using the electro-deposition sources. The radioactive sources of $^{51}$ Cr, $^{54}$ Mn, $^{57}$ Co and $^{65}$ Zn nuclides are prepared by the electro-deposition method. The measured efficiency values are corrected for the escape losses due to the K X-rays of silicon and the absorptions in materials related to source-to-detector geometry. The corrected efficiency values have turned out to be nearly constant regardless of photon energy.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.71-72
• /
• 2020

본 논문에서는 자동차 블랙박스를 사용하여 촬영된 비디오에서 자동차 사고 발생 여부를 판단하는 방법을 제안한다. 제안한 방법은 우선 객체 추적 과정에서 구한 조감도 좌표를 사용하여 각 차량 사이의 거리에 기반을 두고 교통사고 여부를 판단한다. 그런데 거리만을 사용하여 사고 여부를 판단하는 경우 자동차가 밀집된 주·정차 환경에서는 오검출의 확률이 높아질 수 있다. 이를 위해 각 차량에 대한 움직임 벡터를 계산하고 벡터 간의 정보(사잇각과 크기 등)를 사용하여 차량의 주·정차 여부를 판단한 후 사고 검출 대상에서 배제할 수 있도록 한다. 주·정차 판단 여부를 통해 사고 검출의 정확도를 향상할 수 있는 것을 실험적으로 확인하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.1
• /
• pp.12-21
• /
• 2012

IEEE 802.11 MAC protocol standard, DCF(CSMA/CA), is originally designed to ensure the fair channel access between mobile nodes sharing the local wireless channel. It has been, however, revealed that some misbehavior nodes transmit more data than other nodes through artificial means in hot spot area spreaded rapidly. The misbehavior nodes may modify the internal process of their MAC protocol or interrupt the MAC procedure of normal nodes to achieve more data transmission. This problem has been referred to as a selfish node problem and almost literatures has proposed methods of analyzing the MAC procedures of all mobile nodes to detect the selfish nodes. However, these kinds of protocol analysis methods is not effective at detecting all kinds of selfish nodes enough. This paper address this problem of detecting selfish node using Tsallis-Entropy which is a kind of statistical method. Tsallis-Entropy is a criteria which can show how much is the density or deviation of a probability distribution. The proposed algorithm which operates at a AP node of wireless LAN extracts the probability distribution of data interval time for each node, then compares the one with a threshold value to detect the selfish nodes. To evaluate the performance of proposed algorithm, simulation experiments are performed in various wireless LAN environments (congestion level, how selfish node behaviors, threshold level) using ns2. The simulation results show that the proposed algorithm achieves higher successful detection rate.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.5
• /
• pp.116-124
• /
• 2016

This paper proposes a medium access control protocol for collision detection and resolution when a large number of sensor nodes transmits data in vehicle. The proposed protocol selects a random collision detection (CD) slot after data transmission, suspends its transmission and senses the channel to check whether a collision occurs by the detection of both energy level and jam signal. The proposed scheme uses multiple CD phases and in each CD phase, colliding stations are filtered and only surviving stations compete again in the next CD phase; thus, the collision resolution probability significantly increases. Simulation results show that the proposed protocol using the multiple CD phases has significantly better throughput than the conventional protocol. In addition, according to the number of CD phases and the number of CD slots per phase, the throughput aspect of the proposed scheme is investigated and the optimal parameters are derived.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.147-153
• /
• 2020

Conventional lane detection algorithms have problems in that the detection rate is lowered in road environments having a large change in curvature and illumination. The probabilistic Hough transform method has low lane detection rate since it exploits edges and restrictive angles. On the other hand, the method using a sliding window can detect a curved lane as the lane is detected by dividing the image into windows. However, the detection rate of this method is affected by road slopes because it uses affine transformation. In order to detect lanes robustly and avoid obstacles, we propose driving assist system using semantic segmentation based on deep learning. The architecture for segmentation is SegNet based on VGG-16. The semantic image segmentation feature can be used to calculate safety space and predict collisions so that we control a vehicle using adaptive-MPC to avoid objects and keep lanes. Simulation results with CARLA show that the proposed algorithm detects lanes robustly and avoids unknown obstacles in front of vehicle.