• 대한의용생체공학회:의공학회지
• /
• 제41권5호
• /
• pp.185-194
• /
• 2020

Arrhythmia is basically diagnosed with the electrocardiogram (ECG) signal, however, ECG is difficult to measure and it requires expert help in analyzing the signal. On the other hand, the radial pulse can be measured with easy and uncomplicated way in daily life, and could be suitable bio-signal for the recent untact paradigm and extensible signal for diagnosis of Korean medicine based on pulse pattern. In this study, we developed an irregular radial pulse detection algorithm based on a learning model and considered its applicability as arrhythmia screening. A total of 1432 pulse waves including irregular pulse data were used in the experiment. Three data sets were prepared with minimal preprocessing to avoid the heuristic feature extraction. As classification algorithms, elastic net logistic regression, random forest, and extreme gradient boosting were applied to each data set and the irregular pulse detection performances were estimated using area under the receiver operating characteristic curve based on a 10-fold cross-validation. The extreme gradient boosting method showed the superior performance than others and found that the classification accuracy reached 99.7%. The results confirmed that the proposed algorithm could be used for arrhythmia screening. To make a fusion technology integrating western and Korean medicine, arrhythmia subtype classification from the perspective of Korean medicine will be needed for future research.

• 융합신호처리학회논문지
• /
• 제11권3호
• /
• pp.250-254
• /
• 2010

As the number of input and fuzzy set of a fuzzy system increase, the size of the rule base increases exponentially and becomes unmanageable (curse of dimensionality). In this paper, tree architectures of fuzzy controller (TAFC) is proposed to overcome the curse of dimensionality problem occurring in the design of fuzzy controller. TAFC is constructed with the aid of AND and OR fuzzy neurons. TAFC can guarantee reduced size of rule base with reasonable performance. For the development of TAFC, genetic algorithm constructs the binary tree structure by optimally selecting the nodes and leaves, and then random signal-based learning further refines the binary connections (two-step optimization). An inverted pendulum system is considered to verify the effectiveness of the proposed method by simulation.

• 전자공학회논문지
• /
• 제52권3호
• /
• pp.89-95
• /
• 2015

무선 헬스케어 서비스에서 생체신호 모니터링 시스템의 전력소모를 효과적으로 감소시킬 수 있는 압축센싱 기법을 다양한 생체신호에 적용하여 압축률을 비교하였다. 압축센싱 기법을 이용하여 일반적인 심전도, 근전도, 뇌전도 신호의 압축과 복원을 수행하였고, 이를 통해 복원된 신호와 원신호를 비교함으로써, 압축센싱의 유효성을 판단하였다. 유사랜덤 행렬을 사용하여 실제 생체신호를 압축하였으며, 압축된 신호는 Block Sparse Bayesian Learning(BSBL) 알고리즘을 사용하여 복원하였다. 가장 산제된 특성을 가지는 근전도 신호의 최대 압축률이 10배로 확인되어 가장 높았으며, 심전도 신호의 최대 압축률은 5배였다. 가장 산제된 특성이 작은 뇌전도 신호의 최대 압축률은 4배였다. 연구된 심전도, 근전도, 뇌전도 신호의 압축률은 향후 압축센싱을 적용한 무선 생체신호 모니터링 회로 및 시스템 개발시 유용한 기초자료로 활용될 수 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.516-516
• /
• 2000

We propose a neuron model that is possible to learn three-dimensional movement. The neuron model by imitating structure of a neuron, has the system resemble a neuron. We considered a neuron system based on the arguments, and wished to examine whether the system had reasonable function. Koch, Poggio and Torre believed that inhibition signal would shunt excitation signal on the dendrites. They believed that excitation signal operated input-signals and inhibition did as delayed ones. Thus, they were sure that function for directional selectivity was arisen by the shunting. Koch's concept is so important; therefore, we construct the neuron system with their concept. The neuron system makes the shunting function; thus, the model may have a function for directional selectivity. We initialized the connections and the dendrites by random data, and trained them by the back-propagation algorithm for three-dimensional movement. We made sure the defection of three-dimensional movement in the system.

• 전기학회논문지P
• /
• 제58권2호
• /
• pp.164-171
• /
• 2009

This paper presents new learning algorithm of dynamic Bayesian networks (DBN) by means of constrained least square (LS) estimation algorithm and gradient descent method. First, we propose constrained LS based parameter estimation for a Markov chain (MC) model given observation data sets. Next, a gradient descent optimization is utilized for online estimation of a hidden Markov model (HMM), which is bi-linearly constructed by adding an observation variable to a MC model. We achieve numerical simulations to prove its reliability and superiority in which a series of non stationary random signal is applied for the DBN models respectively.

• 방송공학회논문지
• /
• 제23권1호
• /
• pp.154-161
• /
• 2018

최근 스마트폰 사용자가 늘어남에 따라 실내 위치인식 서비스에 대한 연구의 중요성이 증가하고 있다. 실내 위치인식에는 주로 WiFi, Bluetooth 등이 연구되고 있으나, 본 연구에서는 대부분의 실내 공간에 설치되어 있고 스마트폰에 WiFi 기능이 탑재되어 있어 접근성이 좋은 WiFi를 사용한다. 본 연구에서는 수집된 WiFi의 수신신호세기를 이용하는 핑거프린트 기술과 다변량 분류법 중 Ensemble learning method인 랜덤포레스트 알고리즘을 사용한다. 핑거프린트의 데이터로는 수신신호세기와 더불어 Mac주소를 사용해 총 4개의 라디오 맵을 만들어 사용하였다. 실험은 제한된 실내공간에서 진행하였고 실험분석을 위해 본 연구에서 제안하는 방법과 유사한 기존의 랜덤포레스트를 사용하는 실내 위치인식 시스템과 비교 분석하였다. 실험 결과 기존의 랜덤포레스트를 사용하는 실내 위치인식 시스템보다 본 연구에서 제안하는 시스템의 위치인식 정확도가 약 5.8% 높고 학습 데이터 개수에 상관없이 위치인식 속도가 일정하게 유지 되며 기존 방식 보다 더 빠름을 입증하였다.

• International Journal of Control, Automation, and Systems
• /
• 제6권1호
• /
• pp.109-118
• /
• 2008

We present two estimators for discrete non-Gaussian and nonstationary probability density estimation based on a dynamic Bayesian network (DBN). The first estimator is for off line computation and consists of a DBN whose transition distribution is represented in terms of kernel functions. The estimator parameters are the weights and shifts of the kernel functions. The parameters are determined through a recursive learning algorithm using maximum likelihood (ML) estimation. The second estimator is a DBN whose parameters form the transition probabilities. We use an asymptotically convergent, recursive, on-line algorithm to update the parameters using observation data. The DBN calculates the state probabilities using the estimated parameters. We provide examples that demonstrate the usefulness and simplicity of the two proposed estimators.

• 한국산학기술학회논문지
• /
• 제13권1호
• /
• pp.343-347
• /
• 2012

결정 궤환 구조를 사용한 비선형 등화기법은 열악한 채널환경에서 발생하는 심각한 심볼간 간섭을 제거하는데 크게 요구되고 있다. 이 논문에서는 정보 이론적 학습방법과 랜덤 심볼에 기본을 두고 개발된 선형 자력 등화 알고리듬에 이 결정 궤환 구조를 적용한다. 제안된 결정 궤환 자력 등화기는 송신 심볼이 가지는 확률밀도함수와 동일한 모양을 갖도록 랜덤 심볼이 생성된다. 이 랜덤 심볼의 확률밀도함수와 등화기 출력이 가지는 확률밀도함수의 차이를 최소화함으로써 제안된 자력 등화 알고리듬은 등화된 출력 신호를 만들어낸다. 시뮬레이션 결과로부터 선형 알고리듬에 비해 향상된 수렴성능 및 오차 성능을 나타냈다.

• 대한원격탐사학회지
• /
• 제39권5_3호
• /
• pp.1061-1067
• /
• 2023

이 단보에서는 차세대 중형위성 4호(농림위성)의 활용에 앞서, 농림위성과 분광밴드가 유사한 Sentinel-2 위성영상에 대하여 대기보정을 모의하였다. second simulation of the satellite signal in the solar spectrum - vector(6SV)2.1 복사전달모델과 기계학습의 일종인 랜덤 포레스트(random forest, RF)를 활용하여 6SV2.1을 모사한 RF 기반의 대기보정 모델을 개발한 결과, 6SV2.1로 산출된 반사도와 RF 모델로 예측된 반사도 간의 유사도가 매우 높게 나타났다.

• Journal of Information Processing Systems
• /
• 제16권3호
• /
• pp.541-556
• /
• 2020

Wireless networks have become integral to society as they provide mobility and scalability advantages. However, their disadvantage is that they cannot control the media, which makes them vulnerable to various types of attacks. One example of such attacks is the evil twin access point (AP) attack, in which an authorized AP is impersonated by mimicking its service set identifier (SSID) and media access control (MAC) address. Evil twin APs are a major source of deception in wireless networks, facilitating message forgery and eavesdropping. Hence, it is necessary to detect them rapidly. To this end, numerous methods using clock skew have been proposed for evil twin AP detection. However, clock skew is difficult to calculate precisely because wireless networks are vulnerable to noise. This paper proposes an evil twin AP detection method that uses a multiple-feature-based machine learning classification algorithm. The features used in the proposed method are clock skew, channel, received signal strength, and duration. The results of experiments conducted indicate that the proposed method has an evil twin AP detection accuracy of 100% using the random forest algorithm.