• 의료ㆍ복지 건축 : 한국의료복지건축학회 논문집
• /
• 제27권1호
• /
• pp.17-34
• /
• 2021

Purpose: The purpose of this study was to find out the difference in the priority level of recognition for universal design application in public spaces by gender. Method: ANOVA(analysis of variance) and post-hoc test were conducted to determine the priority level of recognition and pattern for the disabled, non-disabled, and experts classified into males and females. Results: There was no gender difference in the comparison by sector for all males and females. However, in comparing of domains and facilities, women showed a higher level of recognition than men in the building sector and cross domain. When comparing space consumers and producers by dividing them into male and female groups, women showed a higher level of recognition than men in producers, but there was no gender difference between consumers. In comparison by sector, domain and facility, women producers also showed a higher level of recognition in the road sector, park and recreation sector, sidewalk domain, four-spaces in the park and recreation sector, and six-spaces in the building sector than men producers. Also, in the building sector, women producers and consumers showed a higher recognition level than men. Comparing the disabled, non-disabled people and experts by dividing them into male and female groups, in the case of non-disabled people and experts, women showed a higher level of recognition than men, while men showed a higher level of recognition than women in the disabled. In addition, there were differences in recognition patterns in many spaces and facilities by gender. Implications: This study is meaningful in comparing the differences in the priority level of recognition and patterns between men and women to apply universal design for people of all ages and both sexes.

• 대한치매학회지
• /
• 제23권3호
• /
• pp.146-160
• /
• 2024

Background and Purpose: The emotions of people at various stages of dementia need to be effectively utilized for prevention, early intervention, and care planning. With technology available for understanding and addressing the emotional needs of people, this study aims to develop speech emotion recognition (SER) technology to classify emotions for people at high risk of dementia. Methods: Speech samples from people at high risk of dementia were categorized into distinct emotions via human auditory assessment, the outcomes of which were annotated for guided deep-learning method. The architecture incorporated convolutional neural network, long short-term memory, attention layers, and Wav2Vec2, a novel feature extractor to develop automated speech-emotion recognition. Results: Twenty-seven kinds of Emotions were found in the speech of the participants. These emotions were grouped into 6 detailed emotions: happiness, interest, sadness, frustration, anger, and neutrality, and further into 3 basic emotions: positive, negative, and neutral. To improve algorithmic performance, multiple learning approaches were applied using different data sources-voice and text-and varying the number of emotions. Ultimately, a 2-stage algorithm-initial text-based classification followed by voice-based analysis-achieved the highest accuracy, reaching 70%. Conclusions: The diverse emotions identified in this study were attributed to the characteristics of the participants and the method of data collection. The speech of people at high risk of dementia to companion robots also explains the relatively low performance of the SER algorithm. Accordingly, this study suggests the systematic and comprehensive construction of a dataset from people with dementia.

• 동아시아식생활학회지
• /
• 제17권6호
• /
• pp.765-779
• /
• 2007

The objective of this study was to examine Jeonju residents' recognition towards their native local foods. The results indicate that their degree of interest in the native foods was above average. As age and education increased, the degree of interest was also increased. Also, married people showed greater interest as compared to single people (p<$0.05{\sim}0.001$). There were more people who said they preferred native foods than people who said they didn't, where 213 people (41.3%) answered that they preferred the native foods. Of the people who said they like native foods, their main reason was because the native foods taste good. The main reason for the people who said they disliked native foods was that they didn't have many opportunities to try native foods. TV and radio were the first means, among others, from which people learned about native foods. The place where people ate native foods most often was native food restaurants (242 people, 46.95%). A frequency of a native food intake (including home and dining-out) of $1{\sim}2$ times/year was most prominent, with 137 people (26.6%). Also, a cooking frequency of "hardly ever cooks" was most prominent with 163 people (31.6%). The most prominent reason for the low cooking frequency at home was because they didn't know the recipes. Among 5 basic recipe characteristics for native foods (easy preparation of ingredients, simple recipe procedures, quick preparation, reasonable recipe procedures, sanitation), "sanitation" had the highest average score of 3.54, and "simple recipe procedure" had the lowest score of 2.44. To summarize, in order to develop Jeonju native local foods, it is necessary to implement various strategies such as frequently holding events where people can experience their native foods, running a native food training center, advertising through TV and radio, developing easy home recipes, and simplifying recipes.

• 한국지능시스템학회논문지
• /
• 제16권6호
• /
• pp.772-776
• /
• 2006

얼굴 표정인식에 관한 연구는 대부분 얼굴의 정면 화상을 가지고 연구를 한다. 얼굴 표정인식에 큰 영향을 미치는 대표적인 부위는 눈과 입이다. 그래서 표정 인식 연구자들은 눈, 눈썹, 입을 중심으로 표정 인식이나 표현 연구를 해왔다. 그러나 일상생활에서 카메라 앞에서는 대부분의 사람들은 눈동자의 빠른 변화의 인지가 어렵다. 또한 많은 사람들이 안경을 쓰고 있다. 그래서 본 연구에서는 눈이 가려진 경우의 표정 인식을 Principal Component Analysis (PCA)를 이용하여 시도하였다.

• 전기전자학회논문지
• /
• 제13권4호
• /
• pp.43-46
• /
• 2009

음성신호는 화자에 대한 고유한 정보와 주변의 음향환경에 대한 정보는 물론 감정과 피로도 등 다양한 정보가 포함되어 있다. 이에 음성신호를 이용한 연구분야에서 감정 상태를 파악하기 위한 연구가 지속되어 왔다. 이에 본 논문에서는 화자의 감정을 인식하기 위해 ETSI의 3GPP2 표준코덱인 Selectable Mode Vocoder(SMV)를 분석한다. 이를 기반으로 감정 인식에 효과적인 특징들을 제안한다. 이후 선정된 특징 벡터를 이용하여 Gaussian Mixture Model(GMM) 기반의 감정 인식 알고리즘을 개발하고 Mixture component 개수를 변화시키면서 성능을 검증한다.

• 한국융합학회논문지
• /
• 제12권6호
• /
• pp.241-248
• /
• 2021

본 연구의 목적은 정신요양시설 종사자의 정신장애인에 대한 권리보장에 영향을 미치는 요인을 확인하고자 함이다. 연구대상은 정신요양시설 종사자 132명이었고, 연구도구는 권리 및 보호관련 특성, 권리인식 및 권리보장이었다. 자료분석은 SPSS/WIN 24.0 프로그램을 이용하여 기술통계, t-test, one-way ANOVA, Pearson's correlation coefficients 및 다중회귀분석으로 하였다. 연구결과로, 일반적 특성에 따른 권리보장의 차이에서는 종교에서 통계적으로 유의미한 차이를 보였다. 권리인식과 권리보장 간에는 유의미한 양의 상관관계가 있었고, 권리보장에 영향을 미치는 요인은 권리인식, 권리옹호 필요성 인식 및 종교였다. 연구결과를 바탕으로, 정신장애인 권리보장을 강화하기 위해 지속적인 교육을 통한 인식 개선과 적극적인 권리옹호활동이 필요하다. 권리보장 강화는 정신장애인 회복에 도움을 줄 것이다.

• 재활복지공학회논문지
• /
• 제10권4호
• /
• pp.329-336
• /
• 2016

수화를 사용하는 농아인은 의사소통의 제약에 의해 사회적인 불평등과 금전적 손실을 겪고 있다. 이러한 이유로 본 연구에서는 농아인의 원활한 의사소통을 위해 8개의 근전도와 1개의 관성센서로 구성된 암밴드 센서를 이용하여 실시간으로 미국 수화를 인식하는 알고리즘을 개발하였다. 개발된 알고리즘의 성능 검증은 11명의 피험자를 통해 진행하였으며, 패턴 분류기 학습은 훈련 데이터베이스 크기를 증가시키면서 진행하였다. 실험 결과, 개발된 패턴 인식 알고리즘은 동작 별 20개의 훈련 데이터베이스에서 97%이상의 정확도를 가졌으며, 30개의 훈련 데이터베이스에서 99%이상의 정확도를 보였다. 이를 통해 본 연구에서 제안하는 암밴드 센서를 이용한 수화 인식 알고리즘의 실용성과 우수성을 확인하였다.

• 대한임베디드공학회논문지
• /
• 제12권1호
• /
• pp.35-41
• /
• 2017

We propose a face recognition and notification system that can transform visual face information into tactile signals in order to help visually impaired people. The proposed system consists of a glasses type camera, a mobile computer and an electronic cane. The glasses type camera captures the frontal view of the user, and sends this image to mobile computer. The mobile computer starts to search for human's face in the image when obstacles are detected by ultrasonic sensors. In a case that human's face is detected, the mobile computer identifies detected face. At this time, Adaboost and compressive sensing are used as a detector and a classifier, respectively. After the identification procedures of the detected face, the identified face information is sent to controller attached to a cane using a Bluetooth communication. The controller generates motor control signals using Pulse Width Modulation (PWM) according to the recognized face labels. The vibration motor generates vibration patterns to inform the visually impaired person of the face recognition result. The experimental results of face recognition and notification system show that proposed system is helpful for visually impaired people by providing person identification results in front of him/her.

• 대한물리치료과학회지
• /
• 제10권2호
• /
• pp.86-95
• /
• 2003

This study randomly chose 10 humanity high schools, which are located in Busan and KyoungNam province. We then examined the recognition rate of physical therapy among 378 teachers who were and still are working in the schools. 1. The recognition grade of physical therapeutics between men and women was significantly different with results of 80.7% of men and 69.7% of women(p<0.05). In the case of experiencing physical therapy, 83.6% of people said they knew the physical therapeutics and in the case of the opposite side, the result was also significantly different with a result of 67.8%(p<0.05). 2. We ranked the people on how much they knew about the physical therapeutics among men and women. With men, the actual experience of physical therapeutic came before what they heard from other people. In the case of women, what they heard from other people came first and the actual experience of physical therapeutic came after. According to the public information from Inje University, the recognition grade is recorded in the 3rd grade department as 21.5% while in the case of experiencing treatment from a physical therapist, the result was 39.1%. In the other department (the 1st grade department), what men and women heard from mass media was recorded at 17.5% and what they heard from other people, it was recorded at 33.8%(p<0.05). 3. The research about the recognition of academic ability of being a physical therapist was that 55.6% of teachers thought that 3-year-college was the best, which made the results different from the recognition grade of the experience of education(p<0.05). 4. In the recognition grade of physical therapeutics, there were significantly differences from 50.2% of men and 45.2% of women were expecting about 1mil ion won to 1.99million won. In case of 25.2% of people who have experience less than 15years at work, they expected about 2million to 2.99million won. The figures were higher than 10.1% of people who have experiences over 15years. About the recognition grade of physical therapists social level in the future is 48.8% of people who had experienced of physical therapy and 63.8% of people who never had experienced of it said it would be better in the future. From these results, the recognition about physical therapeutics and the view of its social status are optimistic and they know well about the level of academic ability of physical therapists. On the other hand, most teachers don't know exactly about physical therapists work. So we have to inform them aggressively for enhancing the recognition of physical therapy because high school students are well affected by their teachers when they face their future or major in university.

• 한국컴퓨터정보학회논문지
• /
• 제24권2호
• /
• pp.193-200
• /
• 2019

Hearing impaired people are living in a voice culture area, but due to the difficulty of communicating with normal people using sign language, many people experience discomfort in daily life and social life and various disadvantages unlike their desires. Therefore, in this paper, we study a sign language translation system for communication between a normal person and a hearing impaired person using sign language and implement a prototype system for this. Previous studies on sign language translation systems for communication between normal people and hearing impaired people using sign language are classified into two types using video image system and shape input device. However, existing sign language translation systems have some problems that they do not recognize various sign language expressions of sign language users and require special devices. In this paper, we use machine learning method of artificial neural network to recognize various sign language expressions of sign language users. By using generalized smart phone and various video equipment for sign language image recognition, we intend to improve the usability of sign language translation system.