• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.467-470
• /
• 2010

최근 음성인식에 관한 연구가 활발히 진행되고 있지만, 음성으로 기기를 작동시키기거나 신원을 파악하는 등과 관련된 성인 음성 인식에 관한 연구들이 대부분이고 아기의 울음소리를 감지하기 위한 학술적인 연구는 미비한 실정이다. 아기들은 통상 울음으로서 자신의 상태를 표현한다는 점을 고려해 볼 때 기존의 성인을 대상으로 한 연구 결과를 그대로 적용시키기에는 무리가 따른다. 아기의 울음소리를 정확히 감지할 수 있다면 아기 및 유아를 위한 다양한 헬스(케어)기기에 적용될 수 있을 것이다. 따라서 대부분의 헬스(케어)기기들이 가지는 제한적인 자원과 컴퓨팅 능력을 고려하여 간단하면서도 정확도가 높은 방법이 필요하다. 이에 본 논문에서는 아기 울음소리의 진동수 패턴을 통계적으로 분석하여 아기 울음소리를 감지하는 방법을 제안한다. 다양한 주변 소리 샘플들을 통해 본 논문의 방법을 검증해본 결과 오감지율이 8.1%로 우수한 결과를 얻을 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.401-404
• /
• 2007

최근 들어 환경 오염과 식습관의 변화로 인해 알레르기성 질환이 널리 유발되고 있다. 특히 평생 건강의 시초라 할 수 있는 소아 시기에 알레르기로 인한 천식, 비염 및 아토피 등의 증세는 소아 뿐만 아니라 부모까지도 위험 요소로 크게 자리잡고 있는 실정이다. 따라서 본 논문은 소아기에 가장 흔하게 발생되는 질환인 소아 천식을 예방하려는 목적으로 연구를 행하였다. 의사 표현 능력이 부족한 소아에게서 울음소리는 소아의 유일한 자기 표현 방법이다. 본 논문에서는 천식을 앓고 있는 소아의 울음소리를 분석하였으며 정상 소아의 울음소리를 동일한 환경 설정으로 분석하여 이를 비교, 분석하여 천식 질환 소아와 정상 소아간의 상관성을 입증하고자 한다.

• The KIPS Transactions:PartB
• /
• v.14B no.7
• /
• pp.503-512
• /
• 2007

An infant of a baby child who haven't communication skills through a language expresses their intention or baby condition as generally crying. Among these things, it is important to show a baby condition because their disease miss diagnosis time or remain to decide an exact diagnosis result too hard. For this, in this paper, we are going to develop system which decides where to be not good body point by analysing their face color and crying sound. Specifically, in this paper, we are going to act for baby heart diseases by doing feature extraction for their face region color and crying sound. To embody, we are going to present diagnosis method and compare analyze their crying sound a stand child, a different diseases child and a baby heart diseases child through each analyzed element. And also, we are going to extract matters to be attended to baby heart diseases through experiment and prepare objective index and an accuracy of baby heart diseases diagnosis result.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.10
• /
• pp.2708-2714
• /
• 2009

Due to poor linguistic communication skills of sucklings and infants, crying mostly is only means of communication to express their body conditions and desires. We, therefore, developed an infant auscultation system which detects which part of the body has a pathological problem, by analysing infant's crying sound patterns. Specifically, in this paper, we accomplished an auscultation system for congenital heart diseases detection by performing pitch, intensity and spectrum analysis of the crying sounds between the normal infants group and the congenital heart diseases group. With this system, we can diagnose congenital heart diseases of infants with poor communication capacity, and, in the near future, can build a home care diagnosis system based on crying sound analysis technologies through additional experiments on medical data.

• Korean Journal of Environmental Biology
• /
• v.25 no.2
• /
• pp.94-99
• /
• 2007

To investigate the spatial distribution and daily calling pattern of the Gold-spotted pond frog, Rana chosenica, in Chungju city and Chungwon gun, Chungbuk province, Korea, we divided the study area into 226 plots with a $2{\times}2km^2$ plot on the map, of which we assigned 32 plots for monitoring populations. Call monitoring on whether the species are present or not were conducted for 5 minutes in between sunset and the midnight from at the end of May to July in 2006. Gold-spotted pond frogs were detected at least once four out of 32 plots. Using program Presence, we obtained site occupancy rate as 0.170 which was quite low compared with other species, while detection probability was 0.66 that propose at least three times to visit the monitoring site to confirm the absence of the frogs. The frogs were actively calling from 21:00 to 02:00, and the number of calling male was significantly and highly correlated with water temperature and humidity. This study shows the present status of the Gold-spotted pond frogs in Chungju city and Chungwon gun and we suggests various effective monitoring methods based on the this study.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.12B
• /
• pp.1123-1130
• /
• 2008

Baby's diseases diagnosis has inconvenient for received direct coming to help that order expression ability was insufficiency which consciousness situation concern about the infant health because of birth rate and decrease the marriage rate and divorce rate. So in this paper through the infant crying sound about home a foundation which infant diseases develop the system comparison normal infant with take a infant that analysis the extract the voice analytics component. Especially this paper propose about the methodology for development system that infant cold, infant pneumonia, infant asthma among extract the crying sound feature part for infant respiratory diseases discussion the most easy has involved the infant. So infant respiratory put case stimulus diseases about all voice organs and experiment the analysis method through the bandwidth about phonetics analysis component that comparison normal infant with take a respiratory infant. Through these method, we were extracted to results that infant's frequency bandwidth suffering from respiratory diseases than a normal infant is short.

• Korean Journal of Environment and Ecology
• /
• v.28 no.3
• /
• pp.273-280
• /
• 2014

This study examined whether Dybowski's brown frogs(Rana dybowskii) in noisy highway roadsides had different mating calls from those in natural sites. We selected four study sites: two rice paddy sites in Youngdong Highway roadside and two nearby natural counterparts. Frog calls were recorded between 18:30 and 20:00 on February 24, February 27, and March 14, 2014. Frog calls in the natural sites had fundamental frequency approximately at 700 Hz with two to four apparent harmonics, while frog calls in the highway sites had higher fundamental frequency with up to seven apparent harmonics. Analysis of variance (ANOVA) shows that a roadside site that are directly exposed to highway noise had statistically higher frog calling frequency than other study sites. However, the higher calling frequency was not found in another roadside site that differed in elevation from the highway and was buffered by forests. These results indicate that male frogs in a noisy highway roadside called females with a higher pitch and more apparent harmonics to avoid being masked by highway noise. These results also suggest that there is a threshold noise level that interrupts frog's mating behavior and it is needed to maintain highway roadside noise to this threshold level.

• The KIPS Transactions:PartB
• /
• v.15B no.4
• /
• pp.301-306
• /
• 2008

Recently, various health care methods for infants have been suggested in the impending era of low birth rate society. We propose, in this context, an early diagnosis method for common infant respiratory diseases. Particularly, the method is regarding infant cold and infant pneumonia. Firstly, sounds of infant crying, only expressing means of infants, among the infant cold group and the infant pneumonia group are compared and examined to find the differences from those among the healthy infant group. For this, the link between infected organs and articulatory organs is investigated. Also, resulting wave forms and frequency bandwidths among each group are compared and analyzed, by using the spectrum for a component voice, to diagnose the infant cold and pneumonia. Finally, the effectiveness of this method is verified through the experiments.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.97-104
• /
• 2006

There is no method to control for the child efficiently when disease happens who cannot be able to express his symptoms. Therefore, doctor's diagnosis depends on inquiring from child's patients, that leads to wrong diagnosis result. For this, in this paper, we would like to develop child ocular inspection, auscultation diagnosis instruments, using Oriental medicine principle that living body signal of five organs and six hallow organs which reflects patients face and voice We would like to get more accurate diagnosis result for child's symptoms from doctor's intuition on the basis of diagnostic sight visualization, objectification, quantization itself. This paper develops color revision, YCbCr application, and face color selection and five sensory organs and nose or apex extraction method etc, in child ocular inspection by first work achievement sequence among the whole development systems. Also, in occasion of child auscultation, crying characteristics of colics through pitch, intensity and formant analysis is numerized and objectifies doctor's intuition through this. Finally, experiments are performed to verify the effectiveness of the proposed methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.839-841
• /
• 2018

인공지능 기술을 활용하여 동물 소리를 분석하고 그 종을 구별하는 기술은 지역의 야생동물 현황 파악이나 생태계 조사 등에 효과적으로 사용될 수 있다. 인공지능 기술을 활용하기 위해서는 많은 동물 소리 샘플이 필요하지만, 현재 그러한 데이터는 녹음 환경이 고도화되어 있는 상용 DB나 전문가 DB 형태로 존재한다. 이러한 데이터만을 학습한 인공지능의 경우 실제 환경에서 녹음된 동물 소리를 식별하는 데 많은 어려움이 예상된다. 따라서 본 논문에서는 다양한 동물 소리를 수집하기 위해 동물 관련 전문가나 일반 사용자 모두 자유롭게 사용할 수 있는 동물 울음소리 수집과 분류를 위한 오픈 플랫폼을 제안한다. 플랫폼에 업로드된 소리 파일은 인공지능의 학습 데이터로 사용하며, 이 인공지능은 사용자에게 소리 파일을 분석한 결과로 해당 동물종과 그에 대한 다양한 생태정보를 제공하고 부가적으로 지역별 동물 통계 및 소리 파일에서의 소리 구간 추출, 소리 파일 공유 등 다양한 기능을 제공한다.