• Proceedings of the IEEK Conference
• /
• 2003.07c
• /
• pp.2883-2886
• /
• 2003

좋은 발성을 위하여 음성이 만들어지려면, 뇌의 언어중추의 명령에 의하여 신경망을 통하여 ‘호흡기관(폐와 흉곽. 호흡관련 근육들)’과 ‘발성기관(주로 후두 즉 성대)’ 그리고 ‘조음, 공명기관(인두, 구강 및 비강)’의 근육들이 유기적으로 작용하여야 한다. 이런 협력 체제에 문제가 생기면, 다양한 종류의 질환이 유발될 수 있다[1,2]. 현재 임상에서 음성 분석을 위해 사용되는 시스템은 대부분 성대의 진동을 측정하기 위해 stroboscopy, 전기성문파형검법 (EGG, electroglottography), 후두근전도 중의 한 방법과 음성 분석을 위한 분석 프로그램으로 구성되어 있다. 그러나, 발성은 호흡과 매우 밀접한 관계가 있어 음성, 성대의 진동, 호흡 관계를 종합적으로 관찰할 필요가 있다. 본 연구에서는 발성 시 성대 점막의 접촉 양상은 ECG 로 측정하며, 발성의 주 에너지원이 되는 호흡의 변화를 2 channel 인덕턴스 호흡감시 장치(RIP: repiratory inductive plethymography)를 이용하여 흉곽의 움직임과 상 복강의 움직임에 대하여 측정하며, 발성되는 음성은 마이크로폰을 통하여 측정하는 ‘EGG, 음성, 호흡 통합검사 장치’를 개발하였다.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.4
• /
• pp.60-67
• /
• 2005

Compared with conventional welding, laser spot welding offers a unique combination of high speed, precision and low heat distortion. This combination of advantages is attractive for manufacturing industries including automotive and electronics companies. In this paper, a real time monitoring scheme fur a pulsed Nd:YAG laser spot welding was suggested. Acoustic emission (AE) signals were collected during welding and analyzed for given process conditions such as laser power and pulse duration. A back propagation artificial neural network, with AE frequency content inputs, was used to predict the weldability of stainless steel sheets.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.15 no.6
• /
• pp.35-42
• /
• 2001

Since daily peak load forecasted data are essential to economic operation and power monitor, the technique of accurate forecasting is needled. The chief advantage of forecasting technique using neural network and fuzzy theory is high accuracy and operative implicity but the loaming time is long, and it makes large forecasting error when the load changes rapidly. This paper has resented a new forecasting technique to improve those faults and the forecasting technique prove to be valid by forcasted results.

• Annals of Clinical Neurophysiology
• /
• v.1 no.1
• /
• pp.70-75
• /
• 1999

Trancranial Doppler(TCD) monitoring is a new application of ultrasonography which allows the nonivasive detection of blood flow velocity in the horizontal (M1) segment of the middle cerebral artery (MCA) and detects microembolic phenomena in the cerebral circulation. Recent studies emphasized the potential of using this technique in vascular surgery (carotid endarterectomy, cardiopulmonary bypass), interventional and intensive care setting. Although the disparity between CBF and blood flow velocity and number of microemboli could be used to prevent cerebral ischemic and embolism based on clinical studies. A reduction of more than 60% of MCA can reflex hemodynamic ischemic state and acoustic feedback of high intensity transient signals(HITS) from the TCD monitoring unit has a direct influence on surgical technique. TCD monitoring can immediately provide information about thromboembolism and hemodynamic changes, which may be a useful tool in the study and prevention of stroke.

• Journal of Power System Engineering
• /
• v.4 no.2
• /
• pp.25-30
• /
• 2000

The grinding process is very complex and relates many parameters to control the process. As this reason, a theoretical analysis and a quantitative estimation of the grinding process has not been well established. In this study, the in-process monitoring system was suggested by applying the neural network for monitoring and shooting the malfunction of cylindrical plunge grinding process. This system used the power signals from the electric power meter. This neural network was composed of processing elements [4-(5-5)-3] with 4 identified power parameters. Because sensitivity is blunted some minute vibration components, the simulation result of this system has appeared about 10% erroneous recognition in the uncertain pattern and the average success rate of the trouble recognition was about 90%. Consequently, the developed system, which applied to the power signals, can be recognize enough to monitor the grinding process as in-process.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1993.10a
• /
• pp.70-75
• /
• 1993

Chatter vibration is an unwanted phenomenon in metal cutting and it always affects surface finish, tool life machine life and the productivity of machining process. The In-process monitoring & control of chatter vibration is necessarily required to automation system. In this study, we constructed the multi-sensing system using Tool Dynamometer,Accelerometer and AE(Acoustic Emission) sensor for the credible detection of chatter vibration. And a new approach using a neural network to process the features of multi-sensor for the recognition of chatter vibration in turning operation is proposed. With the back propagation training process, the neural network memorize and classify the feature difference of multi-sensor signals.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.11 no.2
• /
• pp.103-111
• /
• 2002

Out of all metal-cutting process, the hole-making process is the most widely used. It is estimated to be more than 30% of the total metal-cutting process. It is therefore desirable to monitor and detect drill wear during the hole-drilling process. One important aspect in controlling the drilling process is monitoring drill wear status. There are two systems, Basic system and Online system, to detect the drill wear. Basic system comprised of spindle rotational speed, feed rates, thrust torque and flank wear measured by tool microscope. Outline system comprised of spindle rotational speed feed rates, AE signal, flank wear area measured by computer vision, On-line monitoring system does not need to stop the process to inspect drill wear. Backpropagation neural networks (BPNs) were used for on-line detection of drill wear. The output was the drill wear state which was either usable or failure. This paper deals with an on-line drill wear monitoring system to fit the detection of the abnormal tool state.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1993.04b
• /
• pp.235-241
• /
• 1993

생산시스템의 요소기술은 단계별로 설계, 가공, 검사에 관한것이 있으며 FMS, CIM과같은 생산시스템에서는 통가공 Cell의 효율을 극대화시키기 위한 기술로 지능화한 지능화기술은 전문가시스템(Expert System), 퍼지 이론 (Fuzzy logic)및 신경회로망(Neural Network)의 도입에 의해 활발히 이루어지고있다. 시스템의 지능화 를 위해서 가장 근간이 되는 기술은 그림 1.에 나타낸 바와 같이 지식(Knowledge) 기술과 센서(Sensor) 응용 기술이 며, 현재의 가공상태에 대한 정보는 전적으로 센서를 통해 얻어지며 상태판단은 축적된 지식을 바탕으 로 행해진다. 센서를 통해 얻어진 외부정보를 외부정보를 처리하는 인식(Recognition)이란 대상물의 존재를 아는 인지(Cognition)의 과정에서 한걸음 더 나아가 구체적인의미나 정보내용을 판정하는 것을 의미한다. 당 연구실에서는 이러한 기법들을 이용한 지능화된 공구마모/파손 감지에대한 연구를 수행중이다. 1차적으로 머시님센타의 엔드밀공정을 중심으로한 연구가 진행중이며 본 논문에서는 현재 연구실 차원에서 사용되고 있는 고가의 센서를 대체 할 수 있는 저가의 신뢰성 있는 센서의 이용에 촛점을 맞추어 패턴인식을 위한 절삭신호특성 분석 및 패턴 특성에대한 연구 결과를 소개하고자 한다.

• Annals of Clinical Neurophysiology
• /
• v.10 no.1
• /
• pp.1-12
• /
• 2008

Intraoperative neuromonitoring (INM) is well known to be useful method to reduce intraoperative complications during the surgery of nervous system lesions. Evoked potentials are most commonly used among the electrophysiological tests. Brainstem auditory evoked potentials are for detecting the problems along the auditory pathways including the eighth cranial nerve and brainstem. Somatosensory evoked potentials are applied for preventing the spinal cord lesions. The INM is affected by many factors. In order to perform an optimal INM, the confounding factors including technical, anesthetical, and individual factors should be kept well under control. INM has frequent electrophysiologic changes during the surgery and it might be helpful to keep one's eyes on which monitoring modalities are reluctant to change during each operation. The skillful monitoring and timely interpretation of electrophysiologic changes can drive the patient to be undergone surgery, even in high surgical risk group.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.47-51
• /
• 1997

The high speed machining which can improve the production and quality in machining has been adopted remarkably in dietmold industry. As the speed of machine tool spindle increases, the machinability evaluation and monitoring of high speed machining is necessary. In this study, the machinability of 30, 000rpm class spindle was evaluated by using the developed tool dynamometer and the machining properties of high hardened and toughness materials in high speed were examined. Finally, the in-process monitoring technologies of tool wear were presented through the prediction by the experimental formula and pattern recognition by the neural network.