• International Journal of Contents
• /
• v.11 no.2
• /
• pp.50-56
• /
• 2015

The area of discourse analysis has long neglected the value of images as a semiotic resource in communication. This paper suggests that like language, images are rich in meaning potential and are governed by visual grammar structures which can be utilized to decode the meanings of images. Employing a theoretical framework in visual communication, two digital images are examined for their representational and interactive dimensions and the dimensions' relation to the magazine advertisement genre. The results show that the framework identified narrative and conceptual processes, relations between participants and viewers, and symbolic attributes of the images, which all contribute to the sociological interpretations of the images. The identities and relationships between viewers and participants suggested in the images signify desirable qualities that may be associated to the product of the advertiser. The findings support the theory of visual grammar and highlight the potential of images to convey multi-layered meanings.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.2
• /
• pp.76-80
• /
• 2021

Post-concussion syndrome (PCS) following mild traumatic brain injury (mTBI) is a major factor that contributes to the increased socioeconomic burden caused by TBI. Myelin loss has been implicated in the development of PCS following mTBI. Diffusion tensor imaging (DTI), a traditional imaging modality for the evaluation of axonal and myelin integrity in mTBI, has intrinsic limitations, including its lack of specificity and its time-consuming and labor-intensive post-processing analysis. More recently, various fast MR techniques based on multicomponent relaxometry (MCR), including QRAPMASTER, mcDESPOT, and MDME sequences, have been developed. These MCR-based sequences can provide myelin water fraction/myelin volume fraction, a quantitative parameter more specific to myelin, which might serve as a surrogate marker of myelin volume, in a clinically feasible time. In this review, we summarize the clinical application of the MCR-based fast MR techniques in mTBI patients.

• Annual Conference of KIPS
• /
• 2004.05a
• /
• pp.1645-1648
• /
• 2004

해마를 비롯하여, 뇌 기능과 밀접한 관련을 가지는 뇌 하위조직의 분석에 대한 최근 연구로 MR 영상 등의 해부학적 영상으로부터의 볼륨 추출, 형상 복원, 대칭성 비교 등을 들 수 있다. 이러한 연구들은 뇌의 해부학적 정보에만 의존함으로써 관심영역에 대한 신진대사 등의 분석에 한계를 가진다. 본 논문에서는 뇌 해마영역에 대하여 해부학적, 기능적 특성의 동시 분석이 가능한 프로시저를 제안한다. 먼저 해부학적 영상과 기능적 영상의 다중모달리티 영상정합을 수행하고 이를 기반으로 해마 SPECT 볼륨이 추출되며, 나아가 체적 측정 및 강도 분포 등의 정량분석을 수행함으로써 해부학적 영역의 기능정보에 대한 직관적이며 객관적인 분석이 가능하도록 하였다.

• Journal of the Korean Physical Society
• /
• v.73 no.10
• /
• pp.1603-1603
• /
• 2018

• Korean Journal of Otorhinolaryngology-Head and Neck Surgery
• /
• v.56 no.12
• /
• pp.749-753
• /
• 2013

Basically stem cells have characteristics of multi-potency, differentiation into multiple tissue types, and self-renew through proliferation. Recent advances in stem cell biology can make identifying the stem-cell like cells in various mammalian tissues. Stem cells in various tissues can restore damaged tissue. Stem cells from the adult nervous system proliferate to form clonal floating colonies called spheres in vitro, and recent studies have demonstrated sphere formation by cells in the tympanic membrane, vestibular system, spiral ganglion, and partly in the organ of Corti. The presence of stem cells in the ear raises the possibilities for the regeneration of the tympanic membrane & inner ear hair cells & neurons. But the gradual loss of stem cells postnatally in the organ of Corti may correlate with the loss of regenerative capacity and limited hearing restoration. Future strategies using endogenous stem cells in the ear can be the another treatment modality for the patients with intractable inner ear diseases.

• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.636-639
• /
• 2024

Time series forecasting can be enhanced by integrating various data modalities beyond the past observations of the target time series. This paper introduces the Multimodal Block Transformer, a novel architecture that incorporates multivariate time series data alongside multimodal static information, which remains invariant over time, to improve forecasting accuracy. The core feature of this architecture is the Block Attention mechanism, designed to efficiently capture dependencies within multivariate time series by condensing multiple time series variables into a single unified sequence. This unified temporal representation is then fused with other modality embeddings to generate a non-autoregressive multi-horizon forecast. The model was evaluated on a dataset containing daily movie gross revenues and corresponding multimodal information about movies. Experimental results demonstrate that the Multimodal Block Transformer outperforms state-of-the-art models in both multivariate and multimodal time series forecasting.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.65-71
• /
• 2014

This paper present the multi-modal user distance estimation system using mono camera and mono microphone basically equipped with a mobile device. In case of a distance estimation method using an image, we is estimated a distance of the user through the skin color region extraction step, a noise removal step, the face and eyes region detection step. On the other hand, in case of a distance estimation method using speech, we calculates the absolute difference between the value of the sample of speech input. The largest peak value of the calculated difference value is selected and samples before and after the peak are specified as the ROI(Region of Interest). The samples specified perform FFT(Fast Fourier Transform) and calculate the magnitude of the frequency domain. Magnitude obtained is compared with the distance model to calculate the likelihood. We is estimated user distance by adding with weights in the sorted value. The result of an experiment using the multi-modal method shows more improved measurement value than that of single modality.

• Journal of the HCI Society of Korea
• /
• v.13 no.2
• /
• pp.31-44
• /
• 2018

In the IoT environment, various things could be connected. Those connected things learn and operate themselves, by acquiring data. As human being, they have self-learning and self-operating systems. In the field of IoT study, therefore, the key issue is to design communication system connecting both of the two different types of subjects, human being(user) and the things. With the advent of the IoT environment, much research has been done in the field of UI design. It can be seen that research has been conducted to take complex factors into account through keywords such as multi-modality and interusability. However, the existing UI design method has limitations in structuring or testing interaction between things and users of IoT environment. Therefore, this paper suggests a new UI prototyping method. In this paper, the major analysis and studies are as follows: (1) defined what is the behavior process of the things (2) analyzed the existing IoT product (3) built a new framework driving personality types (4) extracted three representative personality models (5) applied the three models to the smart home service and tested UI prototyping. It is meaningful with that this study can confirm user experience (UX) about IoT service in a more comprehensive way. Moreover, the concept of the personality of things will be utilized as a tool for establishing the identity of artificial intelligence (AI) services in the future.

• Smart Media Journal
• /
• v.13 no.10
• /
• pp.19-27
• /
• 2024

Recently, as the demand for non-face-to-face counseling has rapidly increased, the need for emotion recognition technology that combines various aspects such as text, voice, and facial expressions is being emphasized. In this paper, we address issues such as the dominance of non-Korean data and the imbalance of emotion labels in existing datasets like FER-2013, CK+, and AFEW by using Korean video data. We propose methods to enhance multimodal emotion recognition performance in videos by integrating the strengths of image modality with text modality. A pre-trained model is used to overcome the limitations caused by small training data. A GPT-4-based LLM model is applied to text, and a pre-trained model based on VGG-19 architecture is fine-tuned to facial expression images. The method of extracting representative emotions by combining the emotional results of each aspect extracted using a pre-trained model is as follows. Emotion information extracted from text was combined with facial expression changes in a video. If there was a sentiment mismatch between the text and the image, we applied a threshold that prioritized the text-based sentiment if it was deemed trustworthy. Additionally, as a result of adjusting representative emotions using emotion distribution information for each frame, performance was improved by 19% based on F1-Score compared to the existing method that used average emotion values for each frame.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.8
• /
• pp.738-744
• /
• 2013

According to the cognitive science research, the interaction intent of humans can be estimated through an analysis of the representing behaviors. This paper proposes a novel methodology for reliable intention analysis of humans by applying this approach. To identify the intention, 8 behavioral features are extracted from the 4 characteristics in human-human interaction and we outline a set of core components for nonverbal behavior of humans. These nonverbal behaviors are associated with various recognition modules including multimodal sensors which have each modality with localizing sound source of the speaker in the audition part, recognizing frontal face and facial expression in the vision part, and estimating human trajectories, body pose and leaning, and hand gesture in the spatial part. As a post-processing step, temporal confidential reasoning is utilized to improve the recognition performance and integrated human model is utilized to quantitatively classify the intention from multi-dimensional cues by applying the weight factor. Thus, interactive robots can make informed engagement decision to effectively interact with multiple persons. Experimental results show that the proposed scheme works successfully between human users and a robot in human-robot interaction.