• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.746-748
• /
• 2018

전 세계적으로 인플루엔자에 의해 매년 29~64만의 사망자가 발생하며 사회, 경제적 피해를 일으키고 있다. 기침에 의해 생성된 비말은 인플루엔자의 주요 전파 방법으로, 기침 감지 기술을 통해 확산 방지가 가능하다. 이전의 기침 감지에 대한 연구는 기침 소리와 전통적인 기계학습기법을 사용하였다. 본 논문은 기침 소리와 더불어 기침 시 발생하는 신체의 움직임 정보를 동시에 학습하는 멀티모달 딥러닝 기반의 기침 감지 모델을 제안한다. 도출된 모델과 기존의 모델과의 성능 비교를 통해 제안한 모델이 이전의 기침 감지 모델보다 정확한 기침 인식이 가능함을 보였다. 본 논문이 제안하는 모델은 스마트 워치와 같은 웨어러블 기기에 적용되면 인플루엔자의 확산 방지에 크게 기여할 수 있을 것이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.592-595
• /
• 2010

본 논문에서는 감시카메라 환경에서 취득한 오디오 데이터를 입력으로 하여, 비정상 상황을 인식하는 시스템을 제안한다. 제안된 시스템은 단일클래스 SVM의 대표적인 모델인 SVDD와 최근 얼굴 인식 분야에서 성공적인 업적을 보여주고 있는 신호 처리 분야의 SRC를 계층적으로 결합한 구조로써, 첫 번째 계층에서는 SVDD로 비정상 소리를 신속하게 탐지하여 관리자에게 알람 경고하고, 두 번째 계층의 SRC는 탐지된 비정상 소리를 유형별로 세분화 식별하여 관리자에게 비상 상황을 보고함으로써 관리자의 위기 상황 대처를 돕는다. 제안된 시스템은 실시간 처리가 가능하며, 점증적 갱신의 학습 능력으로 인하여 비정상 오디오 데이터베이스의 변화에도 능동적으로 적응할 수 있다. 실험을 통하여 제안된 시스템의 성능을 검증한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1162-1165
• /
• 2012

어미로부터 생후 21일령(또는 28일령)에 젖을 때는 어린 자돈들은 면역력이 약하여 통상 폐사율이 30~40%까지 치솟는 등 자돈 관리가 국내 양돈 농가의 가장 큰 문제 중 하나로 인식되고 있다. 본 논문에서는 이러한 양돈 농가의 문제를 해결하기 위하여 자돈사(새끼돼지 축사)에 카메라와 마이크를 설치하고 획득된 영상과 소리 정보를 이용하여 자돈들을 모니터링하는 시스템을 제안한다. 제안된 시스템은 실시간으로 유입되는 영상과 소리 스트림 데이터로부터 각각 움직임 벡터와 평균 피치 값을 추출하여 이미 설정된 정상 상황의 임계치 값을 넘는 순간부터를 불특정 이상 상황이라 판단한다. 실제, 경상남도 함양군의 한 돼지 농장에 A/V 센서 기반의 실험 환경을 구축하고 2012년 6월 한 달간의 이유자돈 돈사의 모니터링 데이터 셋을 취득하였고 전반기 15일간의 데이터 셋을 이용하여 자돈사 모니터링 시스템의 프로토타입을 설계 구현하였으며 후반기 15일간의 A/V 스트림 데이터로는 검증 실험을 수행하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.12
• /
• pp.1639-1644
• /
• 2018

Unlike internal combustion engines, electric cars have little engine sound and very quiet, causing the following problems to occur. First of all, pedestrians are a threat to safety because they can't feel the car approaching. The driver is also unable to recognize how fast his car is driving at a certain speed. To solve these problems, electric cars should be artificially created and reused. This paper examines the problems of the Sampling engine sound currently being used and uses the engine sound to produce a sound engine sound for the solution. The sampling engine sound has some limitations in making natural engine sounds. To overcome this problem, we studied two methods of using software synthesizers. They found subtractive synthsizing and wavetable synthsizing, which compared wavetabe synthsizing with actual engine, sampling and subtractive methods to find the most similar to real engine sound. We found that data usage and production cost are more advantageous than sampling method and subtractive syndication method.

• Journal of Animal Environmental Science
• /
• v.6 no.2
• /
• pp.121-130
• /
• 2000

Pure voice characteristics of sow were analyzed to predict parturition time. These were analyzed by using oscilloscope and Sound Forge and the results showed that the voice frequency and amplitude of sow were in the range of 30∼2,500Hz and -35∼-75dB. According to the sound analysis results, the frequencies of sound appearance from farrowing sow in the farrowing pen for three days prior to delivery day and eight hours of prior to delivery day and eight hours of prior to time were around 85% and 46%, respectively of the total appearance during eight days to delivery. Forecasting of delivery time of farrowing sow using the number of sound occurrences showed a promising result such that those have been increased whenever the delivery time was approached. The forecasting success rates were 100% for both of one day and six hours prior to the actual delivery.

• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.105-114
• /
• 2022

This paper is presents an intelligent control system that visualizes the direction of arrival for hearing impaired using personal mobility, and aims to recognize and prevent dangerous situations caused by sound such as alarm sounds and crack sounds on roads. The position estimation method of sound source uses a machine learning classification model characterized by generalized correlated phase transformation based on time difference of arrival. In the experimental environment reproducing the road situations, four classification models learned after extracting learning data according to wind speeds 0km/h, 5.8km/h, 14.2km/h, and 26.4km/h were compared with grid search cross validation, and the Muti-Layer Perceptron(MLP) model with the best performance was applied as the optimal algorithm. When wind occurred, the proposed algorithm showed an average performance improvement of 7.6-11.5% compared to the previous studies.

• Korean Journal of Agricultural Science
• /
• v.27 no.2
• /
• pp.107-116
• /
• 2000

Pure voice characteristics of sow were analyzed to predict parturition time. These were analyzed by using oscilloscope and Sound Forge and the results showed that the voice frequency and amplitude of sow were in the range of 30~2,500Hz and -35~-75dB. According to the sound analysis results, the frequencies of sound appearance from farrowing sow in the farrowing pen for three days prior to delivery day and eight hours of prior to time were around 85% and 46%, respectively of the total appearance during eight days to delivery. Forecasting of delivery time of farrowing sow using the number of sound occurrences showed a promising result such that those have been increased whenever the delivery time was approached. The forecasting success rates were 100% for both of one day and six hours prior to the actual delivery.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.57-78
• /
• 2023

COVID-19, which started in Wuhan, China in November 2019, spread beyond China in 2020 and spread worldwide in March 2020. It is important to prevent a highly contagious virus like COVID-19 in advance and to actively treat it when confirmed, but it is more important to identify the confirmed fact quickly and prevent its spread since it is a virus that spreads quickly. However, PCR test to check for infection is costly and time consuming, and self-kit test is also easy to access, but the cost of the kit is not easy to receive every time. Therefore, if it is possible to determine whether or not a person is positive for COVID-19 based on the sound of a cough so that anyone can use it easily, anyone can easily check whether or not they are confirmed at anytime, anywhere, and it can have great economic advantages. In this study, an experiment was conducted on a method to identify whether or not COVID-19 was confirmed based on a cough sound. Cough sound features were extracted through MFCC, Mel-Spectrogram, and spectral contrast. For the quality of cough sound, noisy data was deleted through SNR, and only the cough sound was extracted from the voice file through chunk. Since the objective is COVID-19 positive and negative classification, learning was performed through XGBoost, LightGBM, and FCNN algorithms, which are often used for classification, and the results were compared. Additionally, we conducted a comparative experiment on the performance of the model using multidimensional vectors obtained by converting cough sounds into both images and vectors. The experimental results showed that the LightGBM model utilizing features obtained by converting basic information about health status and cough sounds into multidimensional vectors through MFCC, Mel-Spectogram, Spectral contrast, and Spectrogram achieved the highest accuracy of 0.74.

• Proceedings of the Korea Database Society Conference
• /
• 2001.11a
• /
• pp.134-149
• /
• 2001

CMS(Contents Management Solution)는 컨텐츠를 관리하는 시스템을 의미. 시장조사기관 Ovum은 CMS에 대하여 'e-Business에 포함되는 모든 컨텐츠를 생성, 보관, 관리하는 일련의 작업(Task)과 과정(Process)'이라고 정의. 일반적으로는 '기업 내에 존재하는 다양한 포맷의 컨텐츠인 문서, 이미지, 동영상, 소리 등을 제작, 출판, 관리하는 솔루션으로 보통 컨텐츠 생성, 출판, 배포, 보관 등으로 정리되는 컨텐츠 라이프스타일 전체를 관리하는 것'으로 규정. (중략)

• The Science & Technology
• /
• v.32 no.12 s.367
• /
• pp.67-71
• /
• 1999

휴대폰은 2~3년 내에 종래의 음성장비의 테두리를 벗어나 소리만 아니라 비디오ㆍ정지영상ㆍ데이터 및 문장까지 주고받을 수 있는 다기능 통신장비로 탈바꿈하여 21세기의 핵심기술의 하나로 떠오르면서 우리 생활을 크게 바꿀 전망이다.