• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.420-423
• /
• 2022

최근 딥러닝 기술이 모바일 기기에 활발히 적용됨에 따라 다양한 엣지 디바이스에서 신경망 모델의 추론 성능을 측정하는 것이 중요해지고 있다. 하지만 디바이스 별 환경 구성과 런타임별 모델 변환 방식이 다르기 때문에 이를 실제로 수행하는 것은 많은 시간을 필요로 한다. 따라서 본 논문에서는 이기종 환경을 고려하여 추론 성능을 측정할 수 있는 Docker 기반의 프로그램을 구현하였고, 이를 이용하여 다양한 엣지 디바이스에서 최신 모델들의 추론 성능을 측정하였다. 또한, 본 프로그램으로 확보 가능한 추론시간 데이터 기반 추론 성능 예측 연구의 사전 연구로서, 대표적 경량모델인 MobilenetV1 에 대한 연산자별 프로파일링을 수행하여 추론시간의 변화 양상을 관찰하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.39-40
• /
• 2023

본 논문은 딥러닝 기반의 소리 인식 모델을 기반으로 실내에서 발생하는 다양한 소리를 시각적인 정보로 제공하는 시스템을 위해 경량화된 CNN ResNet 구조의 인공지능 모델을 제시한다. 적용하는 경량화 기법은 모델의 크기와 연산량을 최적화하여 자원이 제한된 장치에서도 효율적으로 동작할 수 있도록 한다. 이를 위해 마이크로 컴퓨터나 휴대용 기기와 같은 임베디드 장치에서도 원활한 인공지능 추론을 가능하게 하는 모델을 양자화 기법을 적용한 경량화 방법들을 실험적으로 비교한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1010-1011
• /
• 2023

코로나19 팬데믹 이후 배달 앱 사용량이 증가에 따라 배달 오토바이 수가 급증하면서 이와 관련 사고 또한 급격히 증가하는 추세를 보이고 있다. 특히 청각 장애인들은 도로에서 이러한 종류의 사고 위험에 더욱 노출되어 있으며, 이 문제를 해결하기 위해 구글 앱 인벤터를 사용하여 도로에서 오토바이 소리를 인식하는 인공지능 학습 모델을 개발하였다. 개발된 어플리케이션은 도로에서 오토바이 소리를 감지하고 사용자에게 진동과 사진으로 알림을 보냄으로써 사고를 예방에 기여할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.759-762
• /
• 2023

스마트 인솔은 멀티 센서가 장착된 디바이스로써, 발바닥의 정보를 추출하는 기기의 특성으로 인해 헬스케어 디바이스로 주목받고 있다. 최근에는 스마트 인솔 내 센서 사양의 증가로 인해 획득 가능한 데이터의 품질이 증가하였으나, 취득한 데이터를 모두 사용하는 것은 통신 대역폭 및 컴퓨팅 파워의 문제가 발생할 수 있다. 본 논문에서는 스마트 인솔 내 파라미터에 대한 분석과 연구를 진행하고, 최적의 파라미터를 제시한다.

• The Journal of the Korea Contents Association
• /
• v.10 no.10
• /
• pp.86-93
• /
• 2010

With the introduction of smart phones, the augmented reality became popular and is increasingly drawing attention. The augmented reality in the mobile devices is becoming an individual area to study. Many applications of the augmented reality have been studied, but there are just a few studies on its combination with artificial intelligence in games. In this study, an artificial intelligence algorithm was proposed, which dynamically converts the state of the 3D agent in the augmented reality environment using the 3-Axis acceleration sensor in the smart phone. To control the state of the agent to which the artificial intelligence is applied, users used to directly enter the data or use markers to detect them. The critical values, which were determined via test, were given to the acceleration sensor to ensure accurate state conversion. In this paper, makerless tracking technology was used to implement the augmented reality, and the state of the agent was dynamically converted using the 3-Axis acceleration seonsor.

• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.1-9
• /
• 2021

Artificial intelligence (AI) devices are rapidly emerging as a core platform of next-generation information and communication technology (ICT), this study investigated consumer usage behavior and user experience through AI devices that are widely applied to consumers' daily lives. To this end, data was collected from 600 consumers with experience in using AI devices were derived to recognize the attributes and behavior of AI devices. The analysis results are as follows. First, music listening was the most used among various attributes and it was found that simple functions such as providing weather information were usefully recognized. Second, the main devices used by AI device users were identified as AI speakers, smartphone, PC and laptops. Third, associative images of AI devices appeared in the order of fun, useful, novel, smart, innovative, and friendly. Therefore, practical implications are suggested to contribute to provision of user services using AI devices in the future by analyzing usage behaviors that reflect the characteristics of AI devices.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.159-162
• /
• 2009

캐릭터가 발전하는 이유 중 사람의 감정을 충족시키려는 욕구는 움직이지 않은 캐릭터에게 반영되어 인터랙티브 캐릭터로 발전되었고 현재 인터랙티브 캐릭터는 사람들의 많은 관심을 받고 있다. 그 중 최근에는 기존의 인터랙티브 캐릭터인 타마고치와 포스트 팻의 장점을 가져온 휴대용 게임기기인 NDSL의 게임 '닌텐독스'가 등장했다. '닌텐독스'는 터치스크린, 마이크와 같은 체감형 인터페이스를 사용하고 있다. 또한 사람들에게 친근한 강아지라는 캐릭터를 사용하여 사람들이 캐릭터를 애완동물과 비슷하게 느끼고 감정을 교류하게끔 유도하고 있다. 하지만 인터랙티브 캐릭터들이 감정을 표현하기에는 기존의 인공지능으로는 해결할 수 없기 때문에 인공감정을 사용하여 인터랙티브 캐릭터의 감정을 표현하도록 제안한다.

• Journal of the Korean Society of Radiology
• /
• v.17 no.6
• /
• pp.881-887
• /
• 2023

This study aims to analyze the development and current trends of AI-based medical imaging devices commercialized in South Korea. As of September 30, 2023, there were a total of 186 AI-based medical devices licensed, certified, and reported to the Korean Ministry of Food and Drug Safety, of which 138 were related to imaging. The study comprehensively examined the yearly approval trends, equipment types, application areas, and key functions from 2018 to 2023. The study found that the number of AI medical devices started from four products in 2018 and grew steadily until 2023, with a sharp increase after 2020. This can be attributed to the interaction between the advancement of AI technology and the increasing demand in the medical field. By equipment, AI medical devices were developed in the order of CT, X-ray, and MR, which reflects the characteristics and clinical importance of the images of each equipment. This study found that the development of AI medical devices for specific areas such as the thorax, cranial nerves, and musculoskeletal system is active, and the main functions are medical image analysis, detection and diagnosis assistance, and image transmission. These results suggest that AI's pattern recognition and data analysis capabilities are playing an important role in the medical imaging field. In addition, this study examined the number of Korean products that have received international certifications, particularly the US FDA and European CE. The results show that many products have been certified by both organizations, indicating that Korean AI medical devices are in line with international standards and are competitive in the global market. By analyzing the impact of AI technology on medical imaging and its potential for development, this study provides important implications for future research and development directions. However, challenges such as regulatory aspects, data quality and accessibility, and clinical validity are also pointed out, requiring continued research and improvement on these issues.

• Journal of the Korean Society of Radiology
• /
• v.17 no.3
• /
• pp.411-416
• /
• 2023

The purpose of this study is to investigate the utilization of major learning tools among radiology science students and assess the accuracy of a conversational artificial intelligence service program, specifically a chatbot, in the context of the national radiologic technologist licensing exam. The survey revealed that 84.3% of radiology science students actively utilize electronic devices during their learning process. In addition, 104 out of 140 respondents said they use search engines as a top priority for efficient data collection while studying. When asked about their awareness of chatbots, 80% of participants responded affirmatively, and 22.9% reported having used chatbots for academic purposes at least once. From 2018 to 2022, exam questions from the first and second periods were presented to the chatbot for answers. The results showed that ChatGPT's accuracy in answering first period questions increased from 48.28% to 60%, while for second period questions, it increased from 50% to 62.22%. Bing's accuracy in answering first period questions improved from 55% to 64.55%, and for second period questions, it increased from 48% to 52.22%. The study confirmed the general trend of radiology science students utilizing electronic devices for learning and obtaining information through the internet. However, conversational artificial intelligence service programs in the field of radiation science face challenges related to accuracy and reliability, and providing perfect solutions remains difficult, highlighting the need for continuous development and improvement.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.454-460
• /
• 2020

Artificial intelligence assistants that provide speech recognition operate through cloud-based voice recognition with high accuracy. In cloud-based speech recognition, Wake-Up-Word (WUW) detection plays an important role in activating devices on standby. In this paper, we compare the performance of Convolutional Neural Network (CNN)-based WUW detection models for mobile devices by using Google's speech commands dataset, using the spectrogram and mel-frequency cepstral coefficient features as inputs. The CNN models used in this paper are multi-layer perceptron, general convolutional neural network, VGG16, VGG19, ResNet50, ResNet101, ResNet152, MobileNet. We also propose network that reduces the model size to 1/25 while maintaining the performance of MobileNet is also proposed.