• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.331-334
• /
• 2021

In the latest eras, there has been a significant amount of development and research is done on the usage of Deep Learning (DL) for speech emotion recognition (SER) based on Convolutional Neural Network (CNN). These techniques are usually focused on utilizing CNN for an application associated with emotion recognition. Moreover, numerous mechanisms are deliberated that is based on deep learning, meanwhile, it's important in the SER-based human-computer interaction (HCI) applications. Associating with other methods, the methods created by DL are presenting quite motivating results in many fields including automatic speech recognition. Hence, it appeals to a lot of studies and investigations. In this article, a review with evaluations is illustrated on the improvements that happened in the SER domain though likewise arguing the existing studies that are existence SER based on DL and CNN methods.

• 제어로봇시스템학회논문지
• /
• 제13권9호
• /
• pp.915-919
• /
• 2007

This paper proposed a transponder detection method to reduce recognition time in RFID system. It's also shown that conventional procedure of communication in the system could cause a waste of time when a reader recognizes a transponder. The reduction of recognition time can be obtained by developing a circuit to detect a transponder actively. Detecting a transponder is achieved by using the voltage variation of reader antenna voltage that happens when a transponder approaches to the vicinity of magnetic field formed by the reader. By adding a comparator to the antenna receiver of a reader, the reader can perceive approach or existence of a transponder. A reader for experiment is made using the MFRC500 by Phillips that supports ISO/IEC 14443 protocol. Comparing the proposed method with the conventional methods by experiment, there are 47.5ms reduction of recognition time maximally and 12ms in average.

• 한국전자통신학회논문지
• /
• 제8권1호
• /
• pp.77-83
• /
• 2013

본 논문에서는 음성 인식률 개선에 관한 방법을 제시하고 연구하였다. 기존의 음성 검출 방법 중 많이 이용되고 있는 HMM(Hidden Markov Model) 알고리즘을 이용하여서 음성을 검출하였다. 실험은 음성 검출과 음성 인식의 두 가지 방법으로 진행하였다. 음성 검출은 음성의 단위로 영교차율을 구하여 데이터의 유무를 판별하였다. 음성 인식은 음성의 형상의 패턴을 분석한 후 학습된 패턴과 비교 하는 형식으로 분석하였다. 실험 결과, 제안된 음성 형상의 패턴인식 이용한 알고리즘은 92%의 음성 인식률을 얻어 80%의 기존 HMM 알고리즘에 비해서 약 12%의 향상된 인식률을 얻을 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제20권12호
• /
• pp.1890-1900
• /
• 2017

Tangram game consists of seven pieces of polygons such as triangle, square, and parallelogram. Typical methods of image processing for object recognition may suffer from the existence of side thickness and shadow of the puzzle pieces that are dependent on the pose of 3D-shaped puzzle pieces and the direction of light sources. In this paper, we propose an image processing method that recognizes simple convex polygon-shaped objects irrespective of thickness and pose of puzzle objects. Our key algorithm to remove the thick side of piece of puzzle objects is based on morphological operations followed by logical operations with edge image and background image. By using the proposed object recognition method, we are able to implement a stable tangram game applications designed for tablet computers with front camera. As the experimental results, recognition rate is about 86 percent and recognition time is about 1ms on average. It shows the proposed algorithm is fast and accurate to recognize tangram blocks.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.1181-1185
• /
• 1991

Unlike printed character, the recognition of Hand written one has various kinds of difficulties due to the existence of the huge pattern associated with the person who writes. Therefore, in general, recognition of Hand written characters requires an algorithm which takes into consideration of the individual differences. Hangul characters are basically made of straight lines and circles. They can be represented in terms of feature parameters such as the end point of the straight line, the length and the angle. Then all Hangul characters can be represented by the number of basic segments(-, /, vertical bar, O) multiplied by the feature parameters respectively. In this study we propose a method for recognizing Hand written Hangul characters in terms of fuzzy inference.

• Journal of the Korean Data and Information Science Society
• /
• 제17권3호
• /
• pp.831-842
• /
• 2006

Today rapidly changing internal and external environment of the universities such as the reduction of freshmen quota forces most universities to be facing a dangerous existence. It is an urgent thing for the universities to secure finance and good students. Because it was thought that to know freshmen's recognition of their choice of colleges would serve to establish the screening system of each university, we studied it through the survey of the freshmen in some universities. We randomly chose some national universities, private universities and educational universities to investigate who are responsible for their choice of colleges. It is shown that the influence of their high school teachers upon their students’ choosing universities is no more than 10%. As a result, the establishment of proper policy of admission to each university on its own that makes use of the characteristics of the region and the university will be effective in choosing good students.

• 한국철학논집
• /
• 제57호
• /
• pp.9-30
• /
• 2018

최한기의 사유에서 존재와 인식 두 측면에 걸친 패러다임이 근대성의 맥락에서 전환된다. 그에게 만사만물의 근원은 리(理)가 아니고 기(氣)이다. 그 리는 기를 미루어 헤아릴 수 있다. 그리고 종래의 존재론 차원에서만 있던 '리'가 최한기의 기철학에서는 인식 국면에도 있다. 존재론에 '유행의 리'가 있다면 인식 국면에는 '추측의 리'가 있다. 또한 그의 사유에서 리는 존재와 인식 모두에 걸쳐 무수히 많다. 이렇다 할 때 리는 메커니즘으로서 이치, 방식, 방법의 의미로 접근해 볼 수 있지 않을까 싶다. 최한기의 생각에서 만물 존재와 인식 모두에 생성, 운동, 변화의 운화기가 내재한다. 최한기의 기학에서는 '경험'이 매우 중시된다. 도덕적으로 행위할 줄 아는 것도, 예를 들어 맹자의 측은지심의 발동도 그의 사유에서는 경험, 교접을 통해 획득되는 것이고 도덕 행위의 인식은 심체, 즉 마음의 본질인 신기에 의한 추측으로 보았다. 이와 같은 면모로 최한기의 철학에서 존재와 인식의 문제가 대두된다. 사물의 존재의 본질뿐만 아니라 그것에 대한 인식 과정 모두에 걸쳐 운동, 변화가 내재한다. 이런 양태로 최한기의 사유는 실학적이며 근대적인 사유로 나아갔다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권2호
• /
• pp.176-181
• /
• 2004

This paper introduces a Web site login system that uses user's native voice to improve the bother of remembering the ID and password in order to login the Web site. The DTW method that applies fuzzy inference is used as the speaker recognition algorithm. We get the ACC(Average Cepstrum Coefficient) membership function by each degree, by using the LPC that models the vocal chords, to block the recorded voice that is problem for the speaker recognition. We infer the existence of the recorded voice by setting on the basis of the number of zeros that is the value of the ACC membership function, and on the basis of the average value of the ACC membership function. We experiment the six Web sites for the six subjects and get the result that protects the recorded voice about 98% that is recorded by the digital recorder.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2002년도 하계학술발표대회 논문집 제21권 1호
• /
• pp.33-36
• /
• 2002

We implemented a robust Korean broadcast news transcription system for out-of-vocabulary (OOV), tested its performance. The occurrence of OOV words in the input speech is inevitable in large vocabulary continuous speech recognition (LVCSR). The known vocabulary will never be complete due to the existence of for instance neologisms, proper names, and compounds in some languages. The fixed vocabulary and language model of LVCSR system directly face with these OOV words. Therefore our Broadcast news recognition system has an offline OOV update module of language model and vocabulary to solve OOV problem and selects morpheme-based recognition unit (so called, pseudo-morpheme) for OOV robustness.

• 한국멀티미디어학회논문지
• /
• 제22권11호
• /
• pp.1233-1241
• /
• 2019

The goal of the sound-based mechanical fault diagnosis technique is to automatically find abnormal signals in the machine using acoustic emission. Conventional methods of using mathematical models have been found to be inaccurate due to the complexity of industrial mechanical systems and the existence of nonlinear factors such as noise. Therefore, any fault diagnosis issue can be treated as a pattern recognition problem. We propose an automatic fault diagnosis method using discrete wavelet transform and power spectrum density using multi pattern recognition. First, we perform DWT-based filtering analysis for noise cancelling and effective feature extraction. Next, the power spectral density(PSD) is performed on each subband of the DWT in order to effectively extract feature vectors of sound. Finally, each PSD data is extracted with the features of the classifier using multi pattern recognition. The results show that the proposed method can not only be used effectively to detect faults as well as apply to various automatic diagnosis system based on sound.