염색체 핵형 분류를 위한 계층적 인공 신경회로망 분류기 구현

전계록,최욱환,남기곤,엄상희,이권순,장용훈,Jeon, Gye-Rok,Choe, Uk-Hwan,Nam, Gi-Gon,Eom, Sang-Hui,Lee, Gwon-Sun,Jang, Yong-Hun 대한의용생체공학회 1997 의공학회지 Vol.18 No.3

The research on chromosomes is very significant in cytogenetics since genes of the chromosomes control revelation of the inheritance plasma. The human chromosome analysis is widely used to study leukemia, malignancy, radiation hazard, and mutagen dosimetry as well as various congenital anomalies such as Down's, Klinefelter's, Edward's, and Patau's syndrome. The framing and analysis of the chromosome karyogram, which requires specific cytogenetic knowledge is most important in this field. Many researches on automated chromosome karyotype analysis methods have been carried out, some of which produced commercial systems. However, there still remains much room to improve the accuracy of chromosome classification and to reduce the processing time in real clinic environments. In this paper, we proposed a hierarchical artificial neural network(HANN) to classify the chromosome karyotype. We extracted three or four chromosome morphological feature parameters such as centromeric index, relative length ratio, relative area ratio, and chromosome length by preprocessing from ten human chromosome images. The feature parameters of five human chromosome images were used to learn HANN and the rest of them were used to classify the chromosome images. The experiment results show that the chromosome classification error is reduced much more than that of the other researchers using less feature parameters.

하부요로증상 진단을 위한 요속 및 요류음 분석 시스템 구현

전계록,정도운,Jeon, Gye-Rok,Jeong, Do-Un 대한의용생체공학회 2010 의공학회지 Vol.31 No.4

The present study proposed a method of measuring uroflow and urophonography at the same time for more accurate diagnosis in case uroflow looks normal due to compensatory function hypertrophy in the expression of early obstruction. In case of early obstruction, there happens turbulent uroflow by the obstruction even if the uroflow looks normal and thus obstruction can be detected by measuring and analyzing signal caused by turbulent flow. We implemented a system that can measure both uroflow and urophonography, and evaluated its performance. In the experiment, we observed changes in uroflow and urophonography according to artificial pressure and the degree of obstruction, and confirmed that it is possible to determine the effect of compensatory function hypertrophy by analyzing urophonographyic parameter under the same uroflow. The results of our experiment show that the effect of compensatory function hypertrophy in the early-stage obstruction of lower urinary tract, which is not detectible with uroflowmetry alone, can be assessed through urophonographic analysis.

지식 구조화 경정맥 완전 영양공급 시스템의 개발에 관한 연구 (I)

전계록,최삼길,변건식,Jeon, Gye-Rok,Choe, Sam-Gil,Byeon, Geon-Sik 대한의용생체공학회 1990 의공학회지 Vol.11 No.2

In this paper we have implemented and tested TPN which is system to supply sufficent nutrition to nutritionally deficient patient by means of ES (expert system) a kind of A.1 (artificial intelligence) . This system affords to evaluation of nutritional state of patient which is essential to physi- cian. who performs TPN, decision of performing TPN and management of patient-data & calculation of information needing to making TPN fluid. The features were as follolv 1. we input data, take ideal weight of patient and 24hr's creatlnln In urine according to chart in system compare TSF (triceps skin fold), MAC (mid-arm circumference), AMC (arm muscle circumference) to 5th, 15th, 50th percentile and evaluate the nutritional state of patient. 2. Calculation of protein & nonprotein calorie needing to treament of patient can be made exactly by stress factor, activity factor and body temperature. 3. patient's personal recording needing to management of patient date name of chief doc- tor, name of department of admission, chart number, history can by taken very easily. 4. The way of system operating is pull-down Menu one, It can be processing very efficiently. 5. Date processing in system, we can manage memory volume of computer verlr efficiently using of dynamic allocation variables. 6. We can make it very easy to edit & revise the input data, processed data is saved to diskette in 2 files (TDF, THF) , these are semipermanent preservation.

워그너_빌 분포 변환 기법을 이용한 마취단계별 심박변이율 신호 분석

전계록,김명철,유주연,이해림,박성민,손정만,예수영,노정훈,김길중,백승완,Jeon, Gye-Rok,Kim, Myung-Chul,Yoo, Ju-Yeon,Lee, Hae-Lim,Park, Seong-Min,Shon, Jung-Man,Ye, Soo-Young,Ro, Jung-Hoon,Kim, Gil-Jung,Baik, Seung-Wan 한국전기전자재료학회 2010 전기전자재료학회논문지 Vol.23 No.2

In this study, the heart rate variability(HRV) signal of operating patient was acquired according to anesthesia progress and identified to evaluation possibility of depth of anesthesia in each anesthesia stage. The HRV signal was analyzed time-frequency domain applied to Wigner-Ville distribution method, the characteristic parameters were extracted for evaluation of depth of anesthesia in each anesthesia stage. The progress of general anesthesia was divided into the states of pre-operation, induction of anesthesia, operation, awaking and post-operation.

HRV 신호의 웨이브렛 변환에 의한 마취단계별 마취심도 평가 파라미터 개발

전계록(Jeon, Gye-Rok),김명철(Kim, Myung-Chul),한봉효(Han, Bong-Hyo),예수영(Ye, Soo-Young),노정훈(Ro, Jung-Hoon),백승완(Baik, Seong-Wan) 한국산학기술학회 2009 한국산학기술학회논문지 Vol.10 No.9

본 연구에서는 마취 단계에서 마취 심도 평가를 위한 파라미터 추출을 수행하였다. 연구대상은 평균 나이 42 ± 9.13세, 신체등급 분류상 1 또는 2 등급에 속하는 산부인과 수술 환자를 선택하였다. 투약제로는 Enflurane으로 전신 마취를 시행하였다. HRV 신호는 ECG 신호로부터 R 피크치 검출 알고리즘에 의해 획득 되었다. HRV 데이터는 전처리 단계를 거쳤고, 마취 단계별 마취심도 평가 파라미터를 개발하기 위하여 마취단계를 마취 전, 마취유도, 수술 중, 각성, 마취 후 등으로 구분하여 시행하였다. 본 연구에서는 마취단계에서 웨이브렛 변환을 이용한 HRV신호 분석 알고리듬이 제안되었다. 세 종류의 웨이브렛 함수를 적용한 PSD 분석 결과 마취 단계에 따라 모두 비슷한 양상을 나 타내었으나, 이들 중 Daubeches 10의 실험 결과가 보다 양호하게 관측되어 마취 단계별 마취심도를 평가할 수 있는 특징 파라미터로서 가장 적절하다는 판단하였다. In this study, the parameter extraction for evaluation of the anesthesia depth in each anesthesia stages was conducted. An object of the this experiment study has studied 5 adult patients (mean ± SD age:42 ± 9.13), ASA classification I and Ⅱ, undergoing surgery of obstetrics and gynecology. Anaesthesia was maintained with Enflurane. HRV signal was created by R-peak detection algorithm form ECG signal. The HRV data were preprocessing algorithm. It has tried find out the anesthesia parameter which responds the anesthesia events and shows objective anesthesia depth according to anesthesia stage including pre-anesthesia, induction, maintenance, awake and post-anesthesia. In this study, proposed algorithm to analysis the HRV(heart rate variability) signal using wavelet transform in anesthesia stage. Three sorts of wavelet functions applied to PSD. In the result, all of the results were showed similarly. But experiment results of Daubeches 10 is better. Therefore, this parameter is the best parameter in the evaluation of anesthesia stage.

심전도와 맥파 신호 검출을 위한 일체형 센서 시스템의 구현

전계록(Jeon, Gye-Rok),정동근(Jung, Dong-Keun),김기련(Kim, Gi-Ryun),신범주(Shin, Bum-Joo) 한국산학기술학회 2009 한국산학기술학회논문지 Vol.10 No.5

심전도와 맥파를 측정함으로써 구해질 수 있는 맥파전달시간은 심혈관계의 상태를 진단하기 위한 의미있는 지표가 된다. 그러나 맥파를 측정하는 동안 움직이거나, 측정 시에 가해지는 압력이 부정확할 경우, 잘못된 측정 결과를 얻을 수 있다. 이를 해결하기 위하여 본 논문에서는 심전도, 압력맥파 및 광전용적맥파를 동시에 측정할 수 있는 일체형 센서 시스템과 심전도를 지속적으로 측정할 수 있는 금속 전극을 개발하였으며, 실험을 통해 일체형 센서 시스템 및 금속 전극의 유용성을 입증하였다. The pulse transit time(PTT), which is determined by measuring the electrocardiogram(ECG) and pulse wave, gives comprehensive information about the cardiovascular system. However, a little movement of body and/or inaccurate pressure applied to skin during the measurement of pulse wave leads to acquire incorrect results. To overcome such problem, we developed an integrated sensor system which makes it possible to measure ECG, pressure pulse wave(PPW) and photoplethysmograph(PPG) at the same time. Futhermore, we implemented a new metal electrode which enables to continuously measure ECG. We verified that both integrated sensor system and new electrode provide useful effect.

3축 가속도 센서를 이용한 낙상 검출 시스템 구현

전아영(Jeon, Ah-Young),유주연(Yoo, Ju-Yeon),박근철(Park, Geun-Chul),전계록(Jeon, Gye-Rok) 한국산학기술학회 2010 한국산학기술학회논문지 Vol.11 No.5

본 연구에서는 3축 가속도 신호를 이용하여 낙상과 낙상 방향을 검출하는 시스템을 구현하였다. 가속도 신 호는 3축 가속도 센서로부터 획득하였으며, 획득된 신호를 USB 인터페이스를 통하여 PC에 전달하였다. PC에 전송 된 신호를 제안한 알고리즘을 사용하여 낙상을 검출하였으며, 퍼지 분류기를 사용하여 낙상의 방향을 분류하였다. 실 험을 위하여 실험대상군 6명 선정하였으며, 가슴에 가속도계를 부착한 후 실험을 수행하였다. 실험대상자는 5초 동 안 정상 보행을 한 후 4 가지 방향(전․후․좌․우)으로 낙상이 발생하도록 하였으며, 낙상에 소요되는 시간은 최소 2초 로 설정하였다. 본 연구에서 제안된 알고리즘을 이용하여 낙상을 검출하였으며 낙상 발생 후 1초부터 데이터를 분석 하고 퍼지 분류기를 이용하여 낙상방향을 분류하였다. 낙상 검출율은 평균 94.79%이었다. 낙상 방향에 따른 분류율 은 front_fall은 95.83%, back_fall은 100%, left_fall 은 87.5%, right_fall은 95.83%이었다. In this study, the falls detection and direction classification system was implemented using 3-axial acceleration signal. The acceleration signals were acquired from the 3-axial accelerometer(MMA7260Q, Freescale, USA), and then transmitted to the computer through USB interface. The implemented system can detect falls using the newly proposed algorithm, and also classify the direction of falls using fuzzy classifier. The 6 subjects was selected for experiment and the accelerometer was attached on each subject's chest. Each subject walked in normal pace for 5 seconds, and then the fall down according to the four direction(front_fall, back_fall, left_fall and right_fall) during at least 2 second. The falls was easily detect using the newly proposed algorithm in this study. The acquired signals were analyzed after 1 second from generating falls. The fuzzy classifier was used to classify the direction of falls. The mean value of the falls detection rate was 94.79 %. The classifier rate according to falls direction were 95.83% in case of front falls, 100% incase of back falls, 87.5% in case of left falls, and 95.83% in case of right falls.

미세증가감수지수검사와 자기청력검사를 이용한 난청 유형의 감별 진단

김진동,전계록,왕수건,신범주,Kim, Jin-Dong,Jeon, Gye-Rok,Wang, Soo-Geon,Shin, Bum-Joo 한국전기전자재료학회 2009 전기전자재료학회논문지 Vol.22 No.8

As using recruitment phenomenon, SISI test and Bekesy audiometry are employed to differentially diagnose both the cochlear hearing loss and the retrocochlear hearing loss. The main purpose of this study is to find out the sensitivity and specificity of the SISI test within the scope of 1 KHz to 4 KHz in diagnosing various types of hearing losses. In this study, the Bekesy audiometry was conducted for Bekesy audiograms of certain groups according to Jerger's classification, which included persons with normal hearing and patients with hearing impairment. Subject persons of the SISI test were categorized into the several groups with normal hearing, mild hearing loss, moderate hearing loss, moderate-severe hearing loss and severe hearing loss, respectively. The sensitivity and specificity of certain groups were evaluated according to the SISI scores of 20 % below, 25 ${\sim}$ 65 %, and more than 70%. Also, the Bekesy audiometry is conducted on the several subject groups with normal hearing, mixed hearing loss, and sensori-neural hearing loss.

객체 중심 계층적 계획을 이용한 뇌경색 환자의 시기별 MRI 정량적 분석에 관한 연구

하광,전계록,김길중,Ha, Kwang,Jeon, Gye-Rok,Kim, Gil-Joong 대한의용생체공학회 2003 의공학회지 Vol.24 No.2

본 논문에서는 의학적 진단 및 처치 방법의 결정에 중요한 역할을 하는 뇌경색 환자의 각 시기별 특징을 정량화하기 위해 3 가지 MRI 촬영기법을 이용하여 획득한 영상의 특징과 그들의 상관관계들을 객체중심 계층적계획기법을 이용하여 분석하였다. 3 가지 영상의 비교를 위하여 다항워핑 알고리즘과 어파인 변환기법을 수행하여 영상을 정합하였으며, 정합된 영상을 기반으로 뇌경색 시기별 정량화를 수행하였다. 그리고 각 시기별로 색을 설정하여 수 작업으로 얻어진 데이터를 바탕으로 의사 컬러로 나타내었다. 본 연구에서 구한 뇌경색 시기별 정량화 자료를 바탕으로 구분된 결과와 전문의가 판단한 결과를 비교하였다. This paper presents a quantitative analysis method for fall in sick times of the cerebral infarction patients using three types of magnetic resonance image, which play an important role in deciding method of medical treatment. For this object, image characteristics obtained by three radiographic methods of MRI and their relation were analyzed by means of object centered hierarchical Planning method. This methode presents an approach to the knowledge based processes for image interpretation and analysis. To compare three type of MRI. a multiple warping algorithm and affine transform method performed for image matching. Then each fall in sick times level of cerebral infarction was quantified and pseudo-color mapping performed by comparing gray level value one another according to Previously obtained hand maid data. The result of this study was compared to a medical doctors decision.

SSOR을 이요한 강인한 F-행렬의 추정

김효성,남기곤,전계록,이상욱,정두영,Kim, Hyo-Seong,Nam, Gi-Gon,Jeon, Gye-Rok,Lee, Sang-Uk,Jeong, Du-Yeong 대한전자공학회 2002 電子工學會論文誌-SP (Signal processing) Vol.39 No.1

시점을 달리하는 영상으로부터 3차원 장면 복구는 두 영상의 에피폴라 기하구조를 나타내는 F-행렬을 계산함으로서 가능하다. F-행렬을 계산하기 위해 입력으로 주어지는 두 영상의 일치점에는 잘못된 정합점과 같은 잡음을 포함하고 있기 때문에 정확한 F-행렬의 계산은 많은 오류를 가지게 된다. 따라서 본 논문에서는 에피폴라 기하구조에 영향을 미치는 잡음의 종류를 크게 outlier와 미세잡음으로 구분하였다. 상대적으로 에피폴라 기하구조에 영향을 크게 미치는 outlier를 단계적으로 제거시킴으로써 잡음 환경에서도 효과적으로 F-행렬을 계산할 수 있는 SSOR 알고리즘을 제안한다. 제안 알고리즘의 성능 평가를 위해 합성영상과 실 영상에서 실험하였으며 실험결과 제안 알고리즘이 기존의 알고리즘보다 성능이 우수함을 확인하였다. Three-Dimensional scene reconstruction from images acquired with different viewpoints is possible as estimating Fundamental matrix(F-matrix) that indicates the epipolar geometry of two images. Correspondence points required to calculate F-matrix of two images include noise such as miss matches, so generally it is hard to calculate F-matrix accurately. In this paper, we classify noise into two types; outlier and minute noise. we propose SSOR algorithm that estimate F-matrix effectively. SSOR algorithm is rejecting outlier step by step in a noise environment. To evaluate the performance of proposed algorithm we simulated with synthetic images and real images. As a result of simulation we show that proposed algorithm is better than conventional algorithms.