• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.1103-1109
• /
• 2023

Today, as the number of audio files submitted as legal evidence increases with the proliferation of smartphones, the integrity of audio files has become an important issue. Accordingly, the purpose of this study is to explore whether the metadata and file structure of audio files recorded on Samsung smartphones can be manipulated to be identical to the original. This study was based on Samsung smartphones, the most widely used in Korea, and conducted experiments on the built-in voice recording app and the 'Easy Voice Recorder' app, which is the most popular recording app. Through the experiments of this study, it was proven that the metadata and file structure of audio files can be manipulated. Therefore, this study reveals that metadata and file structure analysis have limitations in proving the integrity when audio files are analyzed for adoption as legal evidence. They also argue for the need to develop new voice file forgery technology that does not rely on metadata and file structure analysis.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.1
• /
• pp.29-40
• /
• 2012

A challenging research issue that has been one of growing importance to those working in human-computer interaction are to endow a machine with an emotional intelligence. Thus, emotion recognition technology plays an important role in the research area of human-computer interaction, and it allows a more natural and more human-like communication between human and computer. In this paper, we propose the multimodal emotion recognition system using face and speech to improve recognition performance. The distance measurement of the face-based emotion recognition is calculated by 2D-PCA of MCS-LBP image and nearest neighbor classifier, and also the likelihood measurement is obtained by Gaussian mixture model algorithm based on pitch and mel-frequency cepstral coefficient features in speech-based emotion recognition. The individual matching scores obtained from face and speech are combined using a weighted-summation operation, and the fused-score is utilized to classify the human emotion. Through experimental results, the proposed method exhibits improved recognition accuracy of about 11.25% to 19.75% when compared to the most uni-modal approach. From these results, we confirmed that the proposed approach achieved a significant performance improvement and the proposed method was very effective.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.589-591
• /
• 2022

시니어를 위한 메디컬 가상현실 서비스 개발을 목표로 하고 있으며, 시니어가 쉽고 안전하게 체험할 수 있는 가상현실 콘텐츠를 제작하는 것이 주된 목표이다. 본 연구의 최종 목표로는 체험에 집중하기 위한 환경을 조성하기 위해 안전시스템 구축 및 가족/친구와의 연결을 통한 소통 서비스를 개발한다. 시니어를 대상으로 가상현실 체험을 제공할 때 컨트롤러를 쥐고 상호작용을 해야하는 부분을 핸드트래킹 기술을 연구하여 컨트롤러 없이 물리적으로 양손을 자유롭게 하면서 피로감을 줄이는 것은 물론, 주변의 물건을 내려치거나 컨트롤러를 놓쳐 사고로 이어질 소지도 없애 체험에 집중하게 할 수 있는 환경을 제공하고 체험 중 신체에 이상현상이 나타날 경우 즉시 이를 알릴 수 있도록 콘텐츠 내에서 특정 제스쳐나 긴급 버튼을 통하여 체험시 발생할 돌발상황에 대한 대비를 위해 별도의 앱을 개발하고 체험과 상시 연결하여 체험중인 상황을 관제할 수 있도록 시스템을 구축하고, 알림을 통해 조기에 즉각 대처할 수 있도록 한다. 또한, 몸이 불편하거나 요양원 거주등으로 인해 사회적 단절의 해소를 위해 별도의 앱을 통해 체험중인 콘텐츠와 연결이 가능하도록 설계하고 상호간에 아바타를 통한 감정 표현 및 음성 채팅을 할 수 있게 하여 소통을 할 수 있는 서비스 개발하고자 한다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.449-453
• /
• 2019

미디어방송이 다양해지고, 웹에서 소비되는 콘텐츠들 또한 멀티미디어 중심으로 재편되는 경향에 힘입어 인공지능 연구에 멀티미디어 콘텐츠를 적극적으로 활용하고자 하는 시도들이 시작되고 있다. 본 논문은 다양한 형태의 멀티모달 정보를 하나의 동영상 콘텐츠에 연계하여 분석하여, 통합된 형태의 융합정보 데이터셋을 구축한 연구를 소개하고자 한다. 구축한 인공지능 학습용 데이터셋은 영상/음성/언어 정보가 함께 있는 멀티모달 콘텐츠에 상황/의도/감정 정보 추론에 필요한 다양한 의미정보를 부착하여 활용도가 높은 인공지능 영상 데이터셋을 구축하여 공개하였다. 본 연구의 결과물은 한국어 대화처리 연구에 부족한 공개 데이터 문제를 해소하는데 기여하였고, 한국어를 중심으로 다양한 상황 정보가 함께 구축된 데이터셋을 통하여 다양한 상황 분석 기반 대화 서비스 응용 기술 연구에 활용될 것으로 기대할 수 있다.

• Advanced Industrial SCIence
• /
• v.3 no.2
• /
• pp.1-7
• /
• 2024

This paper deals with the topic of quantification of soft power through emotional analysis. Sentiment analysis refers to the process of detecting and analyzing emotions or emotions in various data such as text, voice, and images. Therefore, in this paper, we explored the methodology and significance of how soft power can be quantified through emotional analysis. Soft power refers to the ability of a country or organization to influence the behavior of another country or organization in a desired direction. It is built by soft factors such as culture, values, and political system rather than military or economic means. Additionally, sentiment analysis is being used as a useful tool to measure and understand these soft areas.

• Journal of Software Assessment and Valuation
• /
• v.17 no.1
• /
• pp.101-113
• /
• 2021

In this paper, we introduce a speaker overlap system and look at the process of converting the existed system on the specific framework of artificial intelligence. Speaker overlap is when two or more speakers speak at the same time during a conversation, and can lead to performance degradation in the fields of speech recognition or speaker recognition, and a lot of research is being conducted because it can prevent performance degradation. Recently, as application of artificial intelligence is increasing, there is a demand for switching between artificial intelligence frameworks. However, when switching frameworks, performance degradation is observed due to the unique characteristics of each framework, making it difficult to switch frameworks. In this paper, the process of converting the speaker overlap detection system based on the Keras framework to the pytorch-based system is explained and considers components. As a result of the framework switching, the pytorch-based system showed better performance than the existing Keras-based speaker overlap detection system, so it can be said that it is valuable as a fundamental study on systematic framework conversion.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.211-227
• /
• 2023

Personal service robots, a type of social robot that has emerged with the aging population and technological advancements, are undergoing a transformation centered around technologies that can extend independent living for older adults in their homes. For older adults to accept and use social robot innovations in their daily lives on a long-term basis, it is crucial to have a deeper understanding of user perspectives, contexts, and emotions. This research aims to comprehensively understand older adults by utilizing a mixed-method approach that integrates quantitative and qualitative data. Specifically, we employ the Van Kaam phenomenological methodology to group conversations into nine categories based on emotional cues and conversation participants as key variables, using voice conversation records between older adults and social robots. We then personalize the conversations based on frequency and weight, allowing for user segmentation. Additionally, we conduct profiling analysis using demographic data and health indicators obtained from pre-survey questionnaires. Furthermore, based on the analysis of conversations, we perform K-means cluster analysis to classify older adults into three groups and examine their respective characteristics. The proposed model in this study is expected to contribute to the growth of businesses related to understanding users and deriving insights by providing a methodology for segmenting older adult s, which is essential for the future provision of social robots with caregiving functions in everyday life.

• Science of Emotion and Sensibility
• /
• v.6 no.3
• /
• pp.55-62
• /
• 2003

Patients with schizophrenia have thinking disorders such as delusion or hallucination, because they have a deficit in the ability which to systematize and integrate information. therefore, they cannot integrate or systematize visual, auditory and tactile stimuli. In this study, we suggest a virtual reality system for the assessment of cognitive ability of schizophrenia patients, based on the brain multimodal integration model. The virtual reality system provides multimodal stimuli, such as visual and auditory stimuli, to the patient, and can evaluate the patient's multimodal integration and working memory integration abilities by making the patient interpret and react to multimodal stimuli, which must be remembered for a given period of time. the clinical study showed that the virtual reality program developed is comparable to those of the WCST and the SPM.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.179-185
• /
• 2014

In this paper, a quadruped walking pet robot for human-robot interaction, a robot-controller using a smart phone application program, and a home smart control system using sensor informations providing from the robot are described. The robot has 20 degree of freedom and consists of various sensors such as Kinect sensor, infrared sensor, 3 axis motion sensor, temperature/humidity sensor, gas sensor and graphic LCD module. We propose algorithms for the robot entertainment: walking algorithm of the robot, motion and voice recognition algorithm using Kinect sensor. emotional expression algorithm, smart phone application algorithm for a remote control of the robot, and home smart control algorithm for controlling home appliances. The experiments of this paper show that the proposed algorithms applied to the pet robot, smart phone, and computer are well operated.

• Journal of Oral Medicine and Pain
• /
• v.26 no.1
• /
• pp.87-93
• /
• 2001

SOX9과 SRY 유전자는 척추동물에서 남성고환의 형성을 유도하는 요소로 알려졌다. SOX9 유전자는 SRY related HMG box gene중 하나로 유전질환의 XY성전환 및 성을 결정하는 데에 관여하며 성결정시기에 그 양에 따른 성전환 발생등 연구가 진행되고 있다. 그러나 이 유전자가 성별판정에 유용할 지는 확실치 않다. 반면 SRY 유전자는 포유동물에서의 배형성시기 고환형성을 결정하는 Y염색체 유전자로 남성에만 존재하고 여성에는 존재 않는다. 현재까지 이을 이용하여 법의학적 검체에서 남성판별에 유용하게 사용되고 있다. 본 실험에서는 X, Y와 같은 성염색체가 아닌 상동염색체상에 있으면서 SRY 유전자와 더불어 남성고환을 결정하는 또다른 요소로서의 기능을 가진 SOX9 유전자를 치아에서 검출하여 법의학적 성별판정에 유용할 수 있는지 알아보고자 본 연구를 수행하였다. 남녀각각 5개의 치아에서 치수와 상아질을 분리한 후 DNA를 추출하여 SOX9과 SRY 유전자의 특이적인 시발체를 제작하고 중합효소연쇄반응을 시행하여 증폭하고 전기영동을 시행하였다. 그 결과 SOX9 유전자는 남녀모두에서 유전자가 검출되었고, SOX9 유전자산물과 SRY 유전자를 혼합하여 사용시 남자에서만 유전자가 검출되었다. 이는 법의치과학적 성별판정에 있어 SOX9 유전자는 사람의 치아에서는 남녀 모두 존재하며 남녀 구별을 위한 성별판정에는 이용할 수 없으며 SRY 유전자와 함께 적용시 남성 특이적 SRY 유전자 검사중 발생할 수 있는 가성 음성 반응여부를 확인하는 데 유용할 것으로 사료된다.