• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.9
• /
• pp.3510-3516
• /
• 2010

In this paper to make young children to learn habits of the animals, crying, features, and English and Korean language, The system was developed to target the zoo various animals exist. If young child places a doll on the front of interesting animal, then young child can learn to look through the display connected to the model. The zoo is reducing the current appearance of the zoo, sensors that can recognize animals are attached to each cage. Attached to each sensor has a unique ID, If this approach recognizes a doll baby and will transmit a unique ID to the handler. Transmitted ID search the matched value sent from the database to retrieve the content and then the content is to be output through the output device. Also if the doll near the animal's room, young children find out animal sound and basic learning by multimedia effects. At the same time Korean, English, Mathematics are learned.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.1
• /
• pp.60-65
• /
• 2018

In this paper, a covariance matrix and modulogram are proposed for realizing amphibian sound classification using CNN (Convolutional Neural Network). First of all, a database is established by collecting amphibians sounds including endangered species in natural environment. In order to apply the database to CNN, it is necessary to standardize acoustic signals with different lengths. To standardize the acoustic signals, covariance matrix that gives distribution information and modulogram that contains the information about change over time are extracted and used as input to CNN. The experiment is conducted by varying the number of a convolutional layer and a fully-connected layer. For performance assessment, several conventional methods are considered representing various feature extraction and classification approaches. From the results, it is confirmed that convolutional layer has a greater impact on performance than the fully-connected layer. Also, the performance based on CNN shows attaining the highest recognition rate with 99.07 % among the considered methods.

• 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.

• 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.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.219-220
• /
• 2018

본 논문에서는 안드로이드 센서를 활용하여 청각장애인을 위한 소리감지 어플리케이션을 설계하고 구현한다. 이 어플리케이션 메뉴는 백그라운드 실행 유지와 특정 데시벨 이상의 음성인식 동작으로 구성한다. 백그라운드 유지 실행 유지는 스마트폰의 어플리케이션 작동 시 다른 어플리케이션을 활용할 수 있도록 편의성을 증진하며, 특정 데시벨 이상의 음성인식을 통하여 일상적인 소리가 아닌 화재나 재난 상황 시 발생하는 경보기소리나 아이 울음소리, 초인종 소리 등 사운드를 통한 인식이 중요시 되는 상황에서 청각장애인들을 위한 진동과 빛 센서를 활용하여 사용자들이 주변 상황을 감지하도록 구현한다.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.39 no.3
• /
• pp.267-272
• /
• 2012

Dental professionals are exposed to various occupational risks, among which the problem of hearing damage has been newly revealed. There have been some researches reporting that noise occurring in a dental office exceeds the Occupational Safety and Health Act (OSHA) Standards. Especially, the pediatric dentists are repeatedly exposed to an additional noise source called the crying sound of children in addition to all kinds of noises from dental instruments. Accordingly, this study intended to investigate the noise environment likely to affect pediatric dentists and to examine the possibility of resultant hearing damages. The level of noise was measured respectively, when various dental instruments (ultrasonic scaler, high-speed handpiece, low-speed handpiece) are operated, when children are crying, and when both occasions take place simultaneously (from the distance of 30 cm) with a portable noise meter. And the daily duration of pediatric dentists exposed to the noise environment was surveyed. The results were compared with the standard value of noise threshold of NIOSH, OSHA, and that of hearing damage of CRA News letter respectively. Considering the intensity and exposure time, the noise environment of pediatric dentists exceeds the allowable noise threshold values. Even only one exposure to crying child was likely to lead to permanent hearing damage. Comparatively, pediatric dentists have a higher risk for occupational hearing damages, and some active measures are thought highly desirable to minimize it.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.6
• /
• pp.401-406
• /
• 2017

This paper presents the performance assessment of several key algorithms conducted for amphibian species sound classification. Firstly, 9 target species including endangered species are defined and a database of their sounds is built. For performance assessment, three feature vectors such as MFCC (Mel Frequency Cepstral Coefficient), RCGCC (Robust Compressive Gammachirp filterbank Cepstral Coefficient), and SPCC (Subspace Projection Cepstral Coefficient), and three classifiers such as GMM(Gaussian Mixture Model), SVM(Support Vector Machine), DBN-DNN(Deep Belief Network - Deep Neural Network) are considered. In addition, i-vector based classification system which is widely used for speaker recognition, is used to assess for this task. Experimental results indicate that, SPCC-SVM achieved the best performance with 98.81 % while other methods also attained good performance with above 90 %.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.585-590
• /
• 2007

최근 IT기술의 비약적인 발전과 더불어 사용자의 편의성을 극대화 시키는 웨어러블 컴퓨팅 기술이 주목을 받고 있다. 이러한 기술은 일반인뿐만 아니라 장애인들의 일상생활의 보조 도구에 활용되어 큰 도움이 될 것으로 예상된다. 본 논문에서는 시각 및 청각장애인을 위해 개발된 착용형 단말기들을 소개하고자 한다. 시각 장애인용 단말기인 SmartWand는 시각장애인용 지팡이에 부착하거나 손에 휴대할 수 있는 장치로, 시작장애인을 위한 보행 보조 및 색상과 명암 정보 인식 보조 기능을 갖춘 장치이다. SmarWand는 시각장애인이 보행 시 이용하는 기존의 지팡이로는 감지할 수 없는 전방의 장애물을 초음파 센서를 통해 탐지하여 촉각이나 음성으로 경고해주고, 물체의 색깔이나 주변의 밝기 정도를 측정하여 시각장애인에게 알려준다. 청각 장애인용 단말기인 SmarWatch는 손목에 착용하는 장치로서 아기 울음소리, 노크나 초인종 소리, 물 끓는 소리, 화재 경보 등 가정에서 발생하는 일상적인 소리를 인식할 수 있도록 해준다. SmartWatch는 입력 모듈의 마이크로 입력된 소리를 문선통신을 통해 컴퓨터로 전송한 후에 소리의 종류를 인식하고 적절한 제어신호를 다시 무선통신을 통해 전송받아 감지된 소리의 종류를 해당하는 진동과 시각정보로 표시해준다. 이런 착용형 단말기들을 통해 시각 및 청각 장애인의 일상 생활의 안정성과 편의성이 증대 되기를 기대한다.