http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Wound-State Monitoring for Burn Patients Using E-Nose/SPME System
변형기,Krishna C. Persaud 한국전자통신연구원 2010 ETRI Journal Vol.32 No.3
Array-based gas sensors now offer the potential of a robust analytical approach to odor measurement for medical use. We are developing a fast reliable method for detection of microbial infection by monitoring the headspace from the infected wound. In this paper, we present initial results obtained from wound-state monitoring for burn patients using an electronic nose incorporating an automated solid-phase microextraction (SPME) desorption system to enable the system to be used for clinical validation. SPME preconcentration is used for sampling of the headspace air and the response of the sensor module to variable concentrations of volatiles emitted from SPME fiber is evaluated. Gas chromatography-mass spectrometry studies prove that living bacteria, the typical infectious agents in clinical practice, can be distinguished from each other by means of a limited set of key volatile products. Principal component analysis results give the first indication that infected patients may be distinguished from uninfected patients. Microbial laboratory analysis using clinical samples verifies the performance of the system.
냄새인식을 위한 강력한 Back-propagation 알고리즘의 제안
변형기 三陟大學校 1998 論文集 Vol.31 No.1
Artificial neural networks are increasingly being used to enhance the classification and recognition powers of data collected from sensor array. This paper reports the effectiveness of multilayer perceptron network based on back-propagation algorithm combined with the output patterns from an artificial sensing system using eletrically conducting polymers as sensor materials. The proposed three layer architecture of a multilayer perceptron network, which has newly proposed pre-processing method and optimal rates of learning and momentum, produced robust performance and classification results throughout the experimental trails.
Exhaled Breath Analysis System based on Electronic Nose Techniques Applicable to Lung Diseases
변형기,유준부,Jeung-SooHuh,임정옥 한양대학교 의과대학 2014 Hanyang Medical Reviews Vol.34 No.3
Smell used to be a common diagnostic tool in medicine, and physicians were trained to use their sense of smell during their medical training. Latterly, odor disgnostics have been relegated to secondary status as a diagnostic method. Array-based gas sensors (“Electronic Nose”) now offer the potential of a robust analytical approach to exhaled breath analysis for medical use. Many diseases are accompanied by characteristic odor, and their recognition can provide diagonostic clues, guide the laboratory evaluation, and affect the choice of immediate therapy. We are developing an intelligent sensor system for non-invasive health care monitoring combined laboratory based sensor module, pattern recognition subsystem and non-invasive sampling of volatile emitted from a patient into a highly intelligent sensor system that allows the rapid processing of these samples. It is capable to assist early and rapid disgnosis of changes in state of patient, and aid decision making by medical personnel in the treatment of such patients. In this paper, we introduce exhaled breath analysis for potential primary lung disease screening using electronic nose system incorporating an automated solid-phase microextraction (SPME) desorption to enable the system to be used. Aiming to increase the sensitivity, SPME preconcentration is used for sampling of headspace air and the response of sensor module to variable concentration of volatile emitted from SPME fiber is evaluated. The initial result shows the distinguished difference between the lung cancer patients and healthy normal individuals according to the analysis of the respective expiratory gases.
전자코 시스템을 사용한 휘발성 화학물질 분류를 위한 퍼지LVQ(Fuzzy Learning Vector Quantization)알고리즘의 응용
변형기 三陟大學校 1997 論文集 Vol.30 No.1
A pattern recognition technique based on fuzzy set theory is applied to gas and odour classification; fuzzy learning vector quantization(FLVQ). This is an algorithm which is derived from Kohonen's learning vector quantization(LVQ), and is modified and extended by fuzzy set theory. The training procedure of FLVQ is more to the position of the reference patterns and modified the fuzziness. The self-organization of FLVQ has been realized using this training method. The performance of FLVQ confirmed the classification of volatile chemicals. Moreover, it is possible to distinguish an unknown pattern from a known one utilizing the FLVQ; the experimental work confirmed this capability.
변형기 ( Byeon Hyeong Gi ),이준섭 ( Lee Jun Seob ),김정도 ( Kim Jeong Do ) 한국센서학회 2004 센서학회지 Vol.13 No.1
N/A There is currently much interest in the development of instruments that emulate the senses of humans. Increasingly,there is demand for mimicking the human sense of smell, which is a sophisticated chemosensory system. An electronicnose system is applicable to a large area of industries including environmental monitoring. We have designed a protableelectronic nose system using an array of commercial chemical gas sensors for recognizing and analyzing the variousodours. In this paper, we have implemented a portable electronic nose system using an array of gas sensors for recognizingand analyzing VOCs (Y31a1i1e Organic Compounds) in the field. The accuracy of a portable electronic nose system maybe lower than an instrument such as GCMS (Gas ChromatographyMass Spectrometer). However, a portable electronicnose system could be used on the field and showed fast response to pollutants in the field. Several different algorithmsfor odours recognition were used such as BP (Back-Propagation) or LM-BP (Levenberq-Marquardt Back-Propagation). Weapplied RBF (Radial Basis Function) Network for recognition and quantifying of odours, which has simpler and fastercompared to the previously used algorithms such as BP and LM-BP.
냄새 센서 Array 패턴들의 실시간 투영을 위한 Sammon 인공지능망의 적용
변형기,Krishna C. Persaud,이수욱 三陟大學校 1999 論文集 Vol.32 No.1
A simple means of data inspection from the responses of multi-element odour sensor arrays based on Sammon's nonlinear mapping algorithm, utilised a Sammon artificial neural network (SAMANN) unsupervised algorithm, with the weights initialised through pretraining to the principal components of the input data set. This produced a robust network that could project previously unseen patterns in real time, allowing the human observer to rapidly make judgements on multidimensional data, previously very difficult to visualise.