• 대한임베디드공학회논문지
• /
• 제18권4호
• /
• pp.159-164
• /
• 2023

Solar energy harvesting IoT devices prioritize maximizing the utilization of collected energy due to the periodic recharging nature of solar energy, rather than minimizing energy consumption. Meanwhile, research on edge AI, which performs machine learning near the data source instead of the cloud, is actively conducted for reasons such as data confidentiality and privacy, response time, and cost. One such research area involves performing various audio AI applications using audio data collected from multiple IoT devices in an IoT edge computing environment. However, in most studies, IoT devices only perform sensing data transmission to the edge server, and all processes, including data preprocessing, are performed on the edge server. In this case, it not only leads to overload issues on the edge server but also causes network congestion by transmitting unnecessary data for learning. On the other way, if data preprocessing is delegated to each IoT device to address this issue, it leads to another problem of increased blackout time due to energy shortages in the devices. In this paper, we aim to alleviate the problem of increased blackout time in devices while mitigating issues in server-centric edge AI environments by determining where the data preprocessed based on the energy state of each IoT device. In the proposed method, IoT devices only perform the preprocessing process, which includes sound discrimination and noise removal, and transmit to the server if there is more energy available than the energy threshold required for the basic operation of the device.

• 융합신호처리학회논문지
• /
• 제16권2호
• /
• pp.35-39
• /
• 2015

Auditory and visual stimuli presented in the peripheral visual field were perceived as spatially coincident when the auditory stimulus was presented five to seven degrees outwards from the direction of the visual stimulus. Furthermore, judgments of the perceived distance between auditory and visual stimuli presented in the periphery did not increase when an auditory stimulus was presented in the peripheral side of the visual stimulus. As to the origin of this phenomenon, there would seem to be two possibilities. One is that the participants could not perceptually distinguish the distance on the peripheral side because of the limitation of accuracy perception. The other is that the participants could distinguish the distances, but could not evaluate them because of the insufficient experimental setup of auditory stimuli. In order to confirm which of these two alternative explanations is valid, we conducted an experiment similar to that of our previous study using a sufficient number of loudspeakers for the presentation of auditory stimuli. Results revealed that judgments of perceived distance increased on the peripheral side. This indicates that we can perceive discrimination between audio and visual stimuli on the peripheral side.

• 대한한의학회지
• /
• 제30권4호
• /
• pp.118-128
• /
• 2009

Objects: This study was conducted to investigate the current educational environment of herbology and to develop a future-oriented curriculum for oriental medicine. The questionnaire used in this research was drawn up based on the current curriculum referring to the current curriculum of herbology and pharmacognosy. Methods: The survey was carried out presenting the questionnaires to a total 12,754 of the students and doctors of oriental medicine through e-mailing five times; of these, 2,074 replied. Results: 1. Among the respondents, about 97% agreed that it was necessary to revise and complement the current curriculum of herbology. 2. The respondents felt that the assigned lecture time of subject was "sufficient" (19%), "insufficient" (39%) and "average" (39%), respectively, and the level of lecture was "insufficient" (37%) or "average" (43%) respectively. According to priority, it showed that the contents which needed complement in lecture were discrimination of medicinal herbs (24%), practical use of action and indications (23%), and correlation with modern disease (21%). In theoretical lectures, 69% of the respondents agreed on the introduction of natural scientific methods 3. In practice, 51% of the respondents replied that the lecture time for practice was insufficient. The contents which needed to be complemented in practice were as follows: audio-visual materials for discrimination of medicinal herbs (22%), concrete exercise for the processing of medicinal herbs (21%), and attempts for the objective discrimination of medicinal herbs using instruments (microscope, analytical instrument, residual pesticide, heavy metal, genetic analysis) (16%). 70% replied that the discrimination of medicinal herbs of high price and rarity was "none or insufficient". 4. 56% replied that it was necessary to introduce and practice physicochemical analysis, and they showed higher requests according to the increase of their educational level. However, 86% replied that they had never experienced concrete attempts for objective discrimination of medicinal herbs, which seemed to indicate that, excepting some schools, practice exercise was rarely performed. Conclusions: According to results, it seems that an urgent review on the current course of herbology and a workshop on the process of experimental practice for professors is needed.

• 음성과학
• /
• 제8권2호
• /
• pp.61-71
• /
• 2001

Speech material, which is collected from ARS(Automatic Response System), was analyzed and classified into disease and non-disease state. The material include 11 different kinds of diseases. Along with ARS speech, DAT(Digital Audio Tape) speech is collected in parallel to give the bench mark. To analyze speech material, analysis tools, which is developed local laboratory, are used to provide an improved and robust performance to the obtained parameters. To classify speech into disease and non-disease class, multi-layered neural network was used. Three different combinations of 3, 6, 12 parameters are tested to obtain the proper network size and to find the best performance. From the experiment, the classification rate of 92.5% was obtained.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 1996년도 The Korean Institute of Navigation 1996년도 한·중 국제학술 심포지움 및 추계학술발표회 논문집
• /
• pp.117-124
• /
• 1996

When navigating in or near an area of restricted visibility it is necessary to be heard the whistle bell and/or the siren of lighthouses or ships at times. Even though we can get the brief informations about the property of sound the direction and range of a sound radiator it is not easy to get the accurate informations for decision making. generally the audio frequency is known as 16-20,000Hz but the earshot is shorten and discrimination of sound is more difficult when there is some noise. The sound pressure is 60dB at the moment when human speaks 1 meter away. Usually the noise pressure in a silent room is 40dB and 60dB on the quiet street. In this study we suggest the basic algorithm to trace the direction and range of the source radiator using the signal received through not a physical sense but the microphone sensors and a series of signal of signal processing.

• 한국항해학회지
• /
• 제20권4호
• /
• pp.71-79
• /
• 1996

When navigating in or near an area of restricted visibility, it is necessary to be heard the whistle, bell and/or the siren of lighthouses or ships at times. Even though we can get the brief informations about the property of sound, the direction and range of a sound radiator, it is not enough to get the accurate informations for decision making. Generally the audio frequency is known as 16~20, 000Hz, but the earshot is shorten and discrimination of sound is more difficult when there is some noise. The sound pressure is 60dB at the moment when human speaks 1 meter away. Usually the noise pressures are 40dB in a silent room and 60dB on the quiet street, respectively. It this study, the basic algorithm and a method of signal processing are suggested to trace the direction and range of the source radiator using the signals received through not a physical sense but the microphone sensors.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 춘계학술발표대회
• /
• pp.204-207
• /
• 2013

Music genre classification is an essential component for music information retrieval system. There are two important components to be considered for better genre classification, which are audio feature extraction and classifier. This paper incorporates two different kinds of features for genre classification, timbral texture and rhythmic content features. Timbral texture contains several spectral and Mel-frequency Cepstral Coefficient (MFCC) features. Before choosing a timbral feature we explore which feature contributes less significant role on genre discrimination. This facilitates the reduction of feature dimension. For the timbral features up to the 4-th order central moments and the covariance components of mutual features are considered to improve the overall classification result. For the rhythmic content the features extracted from beat histogram are selected. In the paper Extreme Learning Machine (ELM) with bagging is used as classifier for classifying the genres. Based on the proposed feature sets and classifier, experiment is performed with well-known datasets: GTZAN databases with ten different music genres, respectively. The proposed method acquires the better classification accuracy than the existing approaches.

• 한국지구과학회지
• /
• 제23권2호
• /
• pp.147-153
• /
• 2002

Reasonable and reliable assessment method is one of the most important issues in science education, Partial credits method is an effective tool for assessing students' science inquiry problem solving. The purposes of this study were to classify the Problem solving types based on the analysis of the thinking Process, and how much the related science concept and the science process skills were used in solving science inquiry problems, and to describe the possibility and rationality of the assessment method that gives partial credit 128 high school seniors were selected and their answers were analyzed to identify science concepts they used to solve each problem, and the result was used as the criterion in the scientific concept test development. Also, to study the science inquiry problem solving type, 152 high school seniors were selected, and protocols were made from audio-taped data of their problem solving process through a think-aloud method and retrospective interviews. In order to get a raw data needed in statistical comparison of reliability, discrimination and the difficulty of the test and the production of the regression equation that determines the ratio of partial credit, 640 students were selected and they were given a science inquiry problem test, a science process skills test, and a scientific concept test. Research result suggested it is more reasonable and reliable to switch to the assessment method that applies partial credit to different problem solving types based on the analysis of the thinking process in problem solving process, instead of the dichotomous credit method.

• Journal of Information Processing Systems
• /
• 제13권3호
• /
• pp.448-463
• /
• 2017

Multimedia is a ubiquitous and indispensable part of our daily life and learning such as audio, image, and video. Objective and subjective quality evaluations play an important role in various multimedia applications. Blind image quality assessment (BIQA) is used to indicate the perceptual quality of a distorted image, while its reference image is not considered and used. Blur is one of the common image distortions. In this paper, we propose a novel BIQA index for Gaussian blur distortion based on the fact that images with different blur degree will have different changes through the same blur. We describe this discrimination from three aspects: color, edge, and structure. For color, we adopt color histogram; for edge, we use edge intensity map, and saliency map is used as the weighting function to be consistent with human visual system (HVS); for structure, we use structure tensor and structural similarity (SSIM) index. Numerous experiments based on four benchmark databases show that our proposed index is highly consistent with the subjective quality assessment.

• 융합정보논문지
• /
• 제9권10호
• /
• pp.101-107
• /
• 2019

본 논문은 화력 발전소 및 시멘트 산업에서 필요한 원자재의 운송 수단에 사용되는 컨베이어 시스템에서의 고장을 검출하는 방법을 제안하였다. 산업현장에서 사람이 접근하기가 힘들고 넓은 공간에 시스템이 동작 하는 점을 고려하여 소형 드론을 설계하였고 컨베이어의 이상을 감지하기 위하여 컨베이어에 내장된 모터의 이상 소음을 감지하는 방법을 임베디드 환경으로 설계하여 드론에 장착하는 구조로 제안하였다. 시스템을 임베디드 마이크로프로세서에 적용하기 위하여 제한된 메모리와 수행 시간을 고려한 하드웨어 및 알고리즘을 제안하였으며 주파수 분석을 통해 고장의 경향을 파악하여 알고리즘 화 하였다. 이때 고장 판별 방식은 측정을 통하여 피크주파수를 측정하고 고주파수의 연속성을 감지하는 방식으로 고장에 의한 소음의 높은 주파수를 분석하여 고장진단을 시행할 수 있었다. 제안된 시스템은 실제 화력 발전소에서 취득한 데이터를 바탕으로 실험 환경을 구성하였으며 드론에 설계된 시스템을 탑재하여 가상 환경 실험을 하여 제안된 시스템의 유용성을 확인하였다. 향후에는 드론의 비행 안정성 향상과 고장 주파수에 대한 좀 더 정밀한 방법을 사용하여 판별성능을 향상 시키는 연구가 요구된다.