• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.439-441
• /
• 2018

딥 러닝의 높은 성능으로 여러 분야에 사용되며 기침 탐지에서도 수행된다. 이 때 기침과 유사한 재채기, 큰 소리는 단일 데이터만으로는 구분하기에 한계가 있다. 본 논문에서는 기존의 오디오 데이터와 오디오 데이터를 인코딩 한 스펙트로그램 이미지 데이터를 함께 학습하는 멀티 모달 딥 러닝을 적용하는 방법을 사용한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.601-604
• /
• 2023

기술이 발전함에 따라 복합적인 모달리티 정보를 포함하는 멀티미디어 데이터의 수집이 용이해지면서, 사람의 성격 특성을 이해하고 이를 개인화된 에이전트에 적용하고자 하는 연구가 활발히 진행되고 있다. 본 논문에서는 비디오 스트림 구조를 활용하여 사용자 특성을 예측하기 위한 동적 키프레임 추출 방법을 제안한다. 비디오 데이터를 효과적으로 활용하기 위해서는 무작위로 선택한 프레임에서 특징을 추출하던 기존의 방법을 개선하여 영상 내 시간에 따른 정보와 변화량을 기반으로 중요한 프레임을 선택하는 방법이 필요하다. 본 논문에서는 제 3자가 평가한 Big-five 지표 값이 레이블링된 대표적인 데이터셋인 First Impressions V2 데이터셋을 사용하여 외면에서 발현되는 특징들을 기반으로 영상에서 등장하는 인물들의 성격 특성을 예측했다. 결론에서는 선택된 키프레임에서 멀티 모달리티 정보를 조합하여 성격 특성을 예측한 결과와 베이스라인 모델과의 성능을 비교한다.

• The Journal of Society for e-Business Studies
• /
• v.21 no.1
• /
• pp.147-163
• /
• 2016

Gender information of a smart device user is essential to provide personalized services, and multi-modal data obtained from the device is useful for predicting the gender of the user. However, the method for utilizing each of the multi-modal data for gender prediction differs according to the characteristics of the data. Therefore, in this study, an ensemble method for predicting the gender of a smart device user by using three classifiers that have text, application, and acceleration data as inputs, respectively, is proposed. To alleviate privacy issues that occur when text data generated in a smart device are sent outside, a classification method which scans smart device text data only on the device and classifies the gender of the user by matching text data with predefined sets of word. An application based classifier assigns gender labels to executed applications and predicts gender of the user by comparing the label ratio. Acceleration data is used with Support Vector Machine to classify user gender. The proposed method was evaluated by using the actual smart device log data collected from an Android application. The experimental results showed that the proposed method outperformed the compared methods.

• Journal of KIISE
• /
• v.42 no.4
• /
• pp.451-458
• /
• 2015

Previous multimodal learning methods focus on problem-solving aspects, such as image and video search and tagging, rather than on knowledge acquisition via content modeling. In this paper, we propose the Multimodal Concept Hierarchy (MuCH), which is a content modeling method that uses a cartoon video dataset and a character-based subtitle generation method from the learned model. The MuCH model has a multimodal hypernetwork layer, in which the patterns of the words and image patches are represented, and a concept layer, in which each concept variable is represented by a probability distribution of the words and the image patches. The model can learn the characteristics of the characters as concepts from the video subtitles and scene images by using a Bayesian learning method and can also generate character-based subtitles from the learned model if text queries are provided. As an experiment, the MuCH model learned concepts from 'Pororo' cartoon videos with a total of 268 minutes in length and generated character-based subtitles. Finally, we compare the results with those of other multimodal learning models. The Experimental results indicate that given the same text query, our model generates more accurate and more character-specific subtitles than other models.

• Journal of Korea Multimedia Society
• /
• v.7 no.3
• /
• pp.427-437
• /
• 2004

Shape comparison between 3D models is essential for shape recognition, retrieval, classification, etc. In this paper, we propose a method for comparing 3D shapes, which is invariant under translation, rotation and scaling of models and is robust to non-uniformly distributed and incomplete data sets. first, a modal model is constructed from input data using vibration modes and then shape similarity is evaluated with modal strain energy. The proposed method provides global-to-local ordering of shape deformation using vibration modes ordered by frequency Thus, we evaluated similarity in terms of global properties of shape without being affected localised shape features using ordered shape representation and modal strain one energy.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.145-150
• /
• 2020

최근 음성인식 분야에서 신경망 기반의 종단간 모델이 제안되고 있다. 해당 모델들은 음성을 직접 입력받아 전사된 문장을 생성한다. 음성을 직접 입력받는 모델의 특성상 데이터의 품질이 모델의 성능에 많은 영향을 준다. 본 논문에서는 이러한 종단간 모델의 문제점을 해결하고자 음성인식 결과를 후처리하기 위한 멀티모달 기반 모델을 제안한다. 제안 모델은 음성과 전사된 문장을 입력 받는다. 입력된 각각의 데이터는 Encoder를 통해 자질을 추출하고 주의집중 메커니즘을 통해 Decoder로 추출된 정보를 전달한다. Decoder에서는 전달받은 주의집중 메커니즘의 결과를 바탕으로 후처리된 토큰을 생성한다. 본 논문에서는 후처리 모델의 성능을 평가하기 위해 word error rate를 사용했으며, 실험결과 Google cloud speech to text모델에 비해 word error rate가 8% 감소한 것을 확인했다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.589-591
• /
• 2023

현재 수치예보 시스템은 항공기, 위성 등 다양한 센서에서 얻은 다종 관측 데이터를 동화하여 대기 상태를 추정하고 있지만, 관측변수 또는 물리량이 서로 다른 관측들을 처리하기 위한 계산 복잡도가 매우 높다. 본 연구에서 기존 시스템의 계산 효율성을 개선하여 관측을 평가하거나 전처리하는 데에 효율적으로 활용하기 위해, 각 관측의 특성을 고려한 자기 지도학습 방법을 통해 멀티모달 기상관측으로부터 실제 대기 상태를 추정하는 방법론을 제안하고자 한다. 비균질적으로 수집되는 멀티모달 기상관측 데이터를 융합하기 위해, (i) 기상관측의 heterogeneous network를 구축하여 개별 관측의 위상정보를 표현하고, (ii) pretext task 기반의 self-supervised learning을 바탕으로 개별 관측의 특성을 표현한다. (iii) Graph neural network 기반의 예측 모델을 통해 실제에 가까운 대기 상태를 추정한다. 제안하는 모델은 대규모 수치 시뮬레이션 시스템으로 수행되는 기존 기술의 한계점을 개선함으로써, 이상 관측 탐지, 관측의 편차 보정, 관측영향 평가 등 관측 전처리 기술로 활용할 수 있다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.5
• /
• pp.1037-1042
• /
• 2018

The neuromorphic technology has been researched for decades, which learns and processes the information by imitating the human brain. The hardware implementations of neuromorphic systems are configured with highly parallel processing structures and a number of simple computational units. It can achieve high processing speed, low power consumption, and low hardware complexity. Recently, the interests of the neuromorphic technology for low power and small embedded systems have been increasing rapidly. To implement low-complexity hardware, it is necessary to reduce input data dimension without accuracy loss. This paper proposed a low-complexity artificial intelligent engine which consists of parallel neuron engines and a feature extractor. A artificial intelligent engine has a number of neuron engines and its controller to process multimodal sensor data. We verified the performance of the proposed neuron engine including the designed artificial intelligent engines, the feature extractor, and a Micro Controller Unit(MCU).

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.1
• /
• pp.69-80
• /
• 2019

This paper proposes a multimodal sensor platform which supports plug and play (PnP) technology. PnP technology automatically recognizes a connected sensor module and an application program easily controls a sensor. To verify a multimodal platform for PnP technology, we build up a firmware and have the experiment on a sensor system. When a sensor module is connected to the platform, a firmware recognizes the sensor module and reads sensor data. As a result, it provides PnP technology to simply plug sensors without any software configuration. Measured sensor raw data suffer from various distortions such as gain, offset, and non-linearity errors. Therefore, we introduce a polynomial calculation to compensate for sensor distortions. To find the optimal coefficients for sensor calibration, we apply a genetic algorithm which reduces the calibration time. It achieves reasonable performance using only a few data points with reducing 97% error in the worst case. The platform supports various protocols for multimodal sensors, i.e., UART, I2C, I2S, SPI, and GPIO.

• Journal of Korea Game Society
• /
• v.9 no.6
• /
• pp.127-137
• /
• 2009

Web Game provides computer games through a web browser, and have several benefits. First, we can access the game through web browser easily if we are connected to the internet environment. Second, usually we don't need much space of a game data for downloading it into a local disk. Nowadays, an industry area of Web Game has a chance to grow through advancements of mobile computing technologies and an age of Web 2.0. This study proposes a Web Game system that users can apply to manipulate the game with multimodal interfaces and mobile devices for intuitive interactions. In this study, multi modal interfaces are used to efficient control the game, and both ordinary computers and mobile devices are applied to the game scenarios. The proposed system is evaluated in both performance and user acceptability in comparison with previous approaches. The proposed system reduces total clear time and numbers of errors of the experiment in a mobile device. It can also provide good satisfactions of users.