• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2005년도 춘계학술대회 학술발표 논문집 제15권 제1호
• /
• pp.289-292
• /
• 2005

본 논문에서는 클러스터링과 뉴로-퍼지 모델링을 동시에 실시하는 학습 기법을 제안하였다. 클러스터링을 이용하여 뉴로-퍼지 모델링을 실시하는 일반적인 경우, 클러스터링 학습을 실시한 후 학습된 파라미터를 뉴로-퍼지 모델의 초기 파라미터로 설정하고 모델을 다시 학습하는 방법을 취한다. 즉 클러스터링에서 클러스터의 수를 구하고 파라미터를 최적화함으로써 초기 구조동정과 파라미터 동정을 실시하며 이를 다시 뉴로-퍼지 모델에서 세부적인 파라미터 동정을 실시하는 것이다. 또한 모델에서의 학습은 출력데이터의 오차를 이용한 오차미분기반 학습으로 전제부 소속함수 파라미터를 수정하는 방법을 이용한다. 이 경우 클러스터링의 영향과 모델의 영향이 각각 별개로 고려될 수 있다. 따라서 본 논문에서는 클러스터링을 전제부 소속함수로 부여하고 클러스터링의 학습에 뉴로-퍼지 모델을 이용하면서 또한 모델의 학습에 클러스터링을 직접 적용하는 클러스터링 기반 뉴로-퍼지 모델링을 제안하였으며 이 경우 클러스터링의 학습과 모델의 학습이 동시에 이루어지며 뉴로-퍼지 모델에서 클러스터링의 효과를 직접적으로 확인할 수 있다. 제안된 방법의 유용성을 시뮬레이션을 통하여 보이고자 한다.

• 조명전기설비학회논문지
• /
• 제27권5호
• /
• pp.9-17
• /
• 2013

Preferred combinations of illuminance and color temperature of lighting depend on daily living activities. We investigated whether the illumination stimuli of LED lighting can enhance attention and relaxation level by controlling color temperature and illuminance level according to activities. Illuminations and color temperatures of LED flat panels are controlled in accordance with activities such as office work and resting. The attention and relaxation level under the task specific lightings are compared with those under normal lighting condition. Single channel EEG signals from the NeuroSky's Mindset are used to estimate attention and relaxation level of human subjects under different lighting conditions. Experiment results show that high color temperature with high illuminance of LED lightings (6600K, 800lx) shows improved attention level compared with conventional lighting conditions (4000K, 500lx).

• Journal of Magnetics
• /
• 제16권3호
• /
• pp.246-252
• /
• 2011

A high-voltage power supply has been built for activation of the brain via stimulation using a Full Wave Cockroft-Walton Circuit (FWCW). A resonant half-bridge inverter was applied (with half plus/half minus DC voltage) through a bidirectional power transistor to a magnetic stimulation device with the capability of producing a variety of pulse forms. The energy obtained from the previous stage runs the transformer and FW-CW, and the current pulse coming from the pulse-forming circuit is transmitted to a stimulation coil device. In addition, the residual energy in each circuit will again generate stimulation pulses through the transformer. In particular, the bidirectional device modifies the control mode of the stimulation coil to which the current that exceeds the rated current is applied, consequently controlling the output voltage as a constant current mode. Since a serial resonant half-bridge has less switching loss and is able to reduce parasitic capacitance, a device, which can simultaneously change the charging voltage of the energy-storage condenser and the pulse repetition rate, could be implemented. Image processing of the brain activity was implemented using a graphical user interface (GUI) through a data mining technique (data mining) after measuring the vital signs separated from the frequencies of EEG and ECG spectra obtained from the pulse stimulation using a 90S8535 chip (AMTEL Corporation).

• 한국정보통신학회논문지
• /
• 제2권2호
• /
• pp.223-230
• /
• 1998

본 논문은 뉴랄퍼지를 이용한 디지탈식 제어기를 고주파 유도 가열기의 전력 조절을 위해 IGBT를 사용한 위상 전이(Phase-Shift) 펄스폭 변조(PWM)와 펄스 주파수 변조(PFM)가 조절되는 공진 고주파 인버터를 응용한 유도가열기를 설명한다. 이는 실제로 산업 현장에서 20KHz~500KHz 유도 가열 및 유도 용해 전원 장치용으로 쓰인다. 위상 전이(Phase-Shift) PWM 정전력 조절 기술을 바탕으로 한 적응 주파수 추종 기법은 스위칭 손실을 최소화하고 전력조절을 용이하게 하기 위해 소개되어졌다. IGBT를 사용하여 실험적으로 만들어진 실험장치는 성공적으로 논증과 토의가 되어졌다.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.III
• /
• pp.715-721
• /
• 2000

In this research, rule and neuro net based boundary extraction algorithm was developed. Extracting boundary of the interest, lean tissue, is essential for the quality evaluation of the beef based on color machine vision. Major quality features of the beef are size, marveling state of the lean tissue, color of the fat, and thickness of back fat. To evaluate the beef quality, extracting of loin parts from the sectional image of beef rib is crucial and the first step. Since its boundary is not clear and very difficult to trace, neural network model was developed to isolate loin parts from the entire image input. At the stage of training network, normalized color image data was used. Model reference of boundary was determined by binary feature extraction algorithm using R(red) channel. And 100 sub-images(selected from maximum extended boundary rectangle 11${\times}$11 masks) were used as training data set. Each mask has information on the curvature of boundary. The basic rule in boundary extraction is the adaptation of the known curvature of the boundary. The structured model reference and neural net based boundary extraction algorithm was developed and implemented to the beef image and results were analyzed.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.169-177
• /
• 2024

Interacting Spherical tank has maximum storage capacity is broadly utilized in industries because of its high storage capacity. This two tank level system has the nonlinear characteristics due to its varying surface area of cross section of tank. The challenging tasks in industries is to manage the flow rate of liquid. This proposed work plays a major role in controlling the liquid level in avoidance of time delay and error. Several researchers studied and investigated about reducing the nonlinearity problem and their approaches do not provide better result. Different types of controllers with various techniques are implemented by the proposed system. Intelligent Adaptive Neuro Fuzzy Inference System (ANFIS) based Sliding Mode Controller (SMC) with Fractional order PID controller is a novel technique which is developed for a liquid level control in a interacting spherical tank system to avoid the external disturbances perform better result in terms of rise time, settling time and overshoot reduction. The performance of the proposed system is obtained by analyzing the simulation result obtained from the controller. The simulation results are obtained with the help of FOMCON toolbox with MATLAB 2018. Finally, the performance of the conventional controller (FOPID, PID-SMC) and proposed ANFIS based SMC-FOPID controllers are compared and analyzed the performance indices.

• Advances in nano research
• /
• 제17권2호
• /
• pp.109-124
• /
• 2024

In the era of smart manufacturing, precise prediction of springback-a common issue in ultra-thin sheet metal forming- and forming limits are critical for ensuring high-quality production and minimizing waste. This paper presents a novel approach that leverages the Internet of Things (IoT) and Artificial Neural Networks (ANN) to enhance springback and forming limits prediction accuracy. By integrating IoT-enabled sensors and devices, real-time data on material properties, forming conditions, and environmental factors are collected and transmitted to a central processing unit. This data serves as the input for an ANN model, which is trained with crystal plasticity simulations and experimental data to predict springback with high precision. Our proposed system not only provides continuous monitoring and adaptive learning capabilities but also facilitates real-time decision-making in manufacturing processes. Experimental results demonstrate significant improvements in prediction accuracy compared to traditional methods, highlighting the potential of IoT and ANN integration in advancing smart manufacturing. This approach promises to revolutionize quality control and operational efficiency in the industry, paving the way for more intelligent and responsive manufacturing systems.

• Journal of Preventive Medicine and Public Health
• /
• 제31권4호
• /
• pp.728-739
• /
• 1998

To improve wellness and quality of life by recognizing the health efforts of stress, the author estimated the relationships between stress, subjective symptoms and clinical diagnosis through a questionnaire and a battery of specified laboratory tests; electrocardiography, blood pressure, cholesterol, aspartate aminotransferase(AST), alanine aminotransferase(ALT), gamma glutamyl transferase$(\gamma-GTP)$, fasting blood sugar, gastro-endoscopy or UGI, abdominal sonography, etc. The data was gathered from 337 clients who were undergoing multiphasic screening program at a University Hospital from January to March 1998. The mean age of subjects was $46.5{\pm}11.2$ years and the mean of body mass index was $24.0{\pm}3.7kg/m^2$. The mean vol of stress was $18.5{\pm}6.0$ expressed as the score out of 40. By general characteristics and lift style among male, mean level of stress was significantly higher in case of lower socioeconomic status, habitual drug use, longer daily working time(>10 hours), no regular exercise, drinkers, irregular meal, skip-ping breakfast(p<0.05). In case of female, that was significantly higher in case of lower education, lowe. socioeconomic status, longer daily working time(>10 hours), no regular exercise, drinkers, smokers, irregular meal, skipping breakfast(p<0.05). Significant correlations were observed between stress and subjective symptoms in all kinds of organ system (p<0.01). Correlation coefficients of stress among male were relatively high with neuro-psychiatric symptom$(\gamma=0.476)$ and cardio-vascular symptom$(\gamma=0.361)$ in order, and correlation coefficients of stress among female was highest with neuro-psychiatric symptom$(\gamma=0.371)$. The prevalence of the diagnosis through the battery of laboratory tests was high in upper gastrointestinal disorders and hypercholesterolemia in order in both sex group. Among male the mean score of stress was significantly high in ulcerative peptic disorder of upper gastrointestine and hepatopathy in order (p<0.05) . Among female that was significantly high in diabetes mellitus. In summary, it is likely that there are associations between stress, subjective symptoms and clinical diagnosis. To promote wellness and quality of life it would be of value that periodic stress evaluation program and stress management including apropriate control of smoking and drinking, regular exercise and meal.

• Investigative Magnetic Resonance Imaging
• /
• 제16권2호
• /
• pp.124-135
• /
• 2012

목적: 본 연구에서는 숙달된 택시운전기사들을 대상으로 내비게이션 시스템을 이용하여 운전하는 한국인 대조군에 비교하여 해마의 부피와 모양 그리고 기능적 변화를 알아보고자 하였다. 대상과 방법: 총 8명의 대상군(4명의 숙달된 택시운전기사들과 4명의 같은 나이대 일반인 대조군)에 대해 삼차원 T1강조영상과 혈류산소 수준에 따른 기능성 자기공명영상을 촬영하였다. 해마의 용적과 모양, 기능성 자기공명영상 자료를 분석하여 두 군간에 신경 활성도 차이를 비교하였다. 결과: 해마의 용적은 두 군간에 통계적으로 유의한 차이를 보이지 않았다(p > 0.05). 해마의 모양을 보면, 택시운전기사군의 왼쪽 해마가 대조군에 비해 전체 길이가 약간 길고 머리와 꼬리부분이 약간 더 컸다(p < 0.05, uncorrected). 기능성 자기공명영상에서는 택시운전기사군에서 대조군에 비해 방추상회가 특히 활성화되어 있었다. 결론: 택시운전기사군의 해마가 보이는 이러한 구조적, 기능적 변화는 그들의 직업과 관련하여 공간적 탐색능력을 지속적으로 사용하면서 해마와 관련 뇌영역이 기능적으로 분화했음을 나타내는 소견으로 추측할 수 있겠다.

• IMMUNE NETWORK
• /
• 제6권1호
• /
• pp.27-32
• /
• 2006

Background: Chronic inflammation in the brain has known to be associated with the development of a various neurological diseases including dementia. In general, the characteristic of neuro-inflammation is the activated microglia over the brain where the pathogenesis occurs. Pro-inflammatory repertoires, interleukin-1${\beta}$ (IL-1${\beta}$) and nitric oxide (NO), are the main causes of neuro-degenerative disease, particularly in Alzheimer's disease (AD) which is caused by neuronal destruction. Those pro-inflammatory repertoires may lead the brain to chronic inflammatory status, and thus we hypothesized that chronic inflammation would be inhibited when pro-inflammatory repertoires are to be well controlled by inactivating the signal transduction associated with inflammation. Methods: In the present study, we examined whether biphenyl dimethyl dicarboxylate (DDB), an active compound from Schizandra chinensis Baillon, inhibits the NO production by a direct method using Griess reagent and by RT-PCR in the gene expression of inducible nitric oxide synthase (iNOS) and IL-1${\beta}$. Western blots were also used for the analysis of NF-${\kappa}B$ and I${\kappa}B$. Results: In the study, we found that DDB effectively inhibited IL-1${\beta}$ as well as NO production in BV-2 microglial cell, and the translocation of NF-${\kappa}B$ was comparably inhibited in the presence of DDB comparing those to the positive control, lipopolysaccharide. Conclusion: The data suggested that the DDB from Schizandra chinensis Baillon may play an effective role in inhibiting the pro-inflammatory repertoires which may cause neurodegeneration and the results imply that the compound suppresses a cue signal of the microglial activation which can induce the brain pathogenesis such as Alzheimer's disease.