• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.754-771
• /
• 2021

In the task of continuous dimension emotion recognition, the parts that highlight the emotional expression are not the same in each mode, and the influences of different modes on the emotional state is also different. Therefore, this paper studies the fusion of the two most important modes in emotional recognition (voice and visual expression), and proposes a two-mode dual-modal emotion recognition method combined with the attention mechanism of the improved AlexNet network. After a simple preprocessing of the audio signal and the video signal, respectively, the first step is to use the prior knowledge to realize the extraction of audio characteristics. Then, facial expression features are extracted by the improved AlexNet network. Finally, the multimodal attention mechanism is used to fuse facial expression features and audio features, and the improved loss function is used to optimize the modal missing problem, so as to improve the robustness of the model and the performance of emotion recognition. The experimental results show that the concordance coefficient of the proposed model in the two dimensions of arousal and valence (concordance correlation coefficient) were 0.729 and 0.718, respectively, which are superior to several comparative algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권9호
• /
• pp.2458-2482
• /
• 2023

Medical image segmentation techniques based on convolution neural networks indulge in feature extraction triggering redundancy of parameters and unsatisfactory target localization, which outcomes in less accurate segmentation results to assist doctors in diagnosis. In this paper, we propose a multi-level semantic-rich encoding-decoding network, which consists of a Pooling-Conv-Former (PCFormer) module and a Cbam-Dilated-Transformer (CDT) module. In the PCFormer module, it is used to tackle the issue of parameter explosion in the conservative transformer and to compensate for the feature loss in the down-sampling process. In the CDT module, the Cbam attention module is adopted to highlight the feature regions by blending the intersection of attention mechanisms implicitly, and the Dilated convolution-Concat (DCC) module is designed as a parallel concatenation of multiple atrous convolution blocks to display the expanded perceptual field explicitly. In addition, MultiHead Attention-DwConv-Transformer (MDTransformer) module is utilized to evidently distinguish the target region from the background region. Extensive experiments on medical image segmentation from Glas, SIIM-ACR, ISIC and LGG demonstrated that our proposed network outperforms existing advanced methods in terms of both objective evaluation and subjective visual performance.

• 생물정신의학
• /
• 제6권2호
• /
• pp.259-263
• /
• 1999

Nefazodone, a newer antidepressant is a phenylpiperazine derivative that inhibits the reuptake of both norepinephrine and serotonin, and antagonizes $5-HT_{2A}$ and ${\alpha}_1$ adrenergic receptors. Compared with SSRIs, nefazodone caused the fewer activating symptoms, adverse gastrointestinal effects(nausea, diarrhea, anorexia) and adverse effects of sexual function, but is associated with the more dizziness, dry mouth, constipation, visual disturbances and confusion. We report on 4 cases of visual disturbances and hallucinations in patients taking nefazodone. It is not certain what mechanisms mediated these side effects, but three mechanisms are possible. 1) Nefazodone, as a 5-HT2 antagonist, might induce visual disturbances. 2) mCPP, metabolite of nefazodone might contribute to the hallucination through action on 5-HT receptor. 3) Dopaminergic enhancing activity of nefazodone might cause hallucination. These case report raises the possibility that dose-related perceptual disturbances may exist with nefazodone. The fact emphasizes the need to pay close attention to all possible drug interactions, particularly in patients treated with multiple psychoactive agents, older patients, and patients with decreased hepatic function.

• 대한인간공학회지
• /
• 제30권4호
• /
• pp.563-569
• /
• 2011

Objective: This study focuses on the effects of pre-cues informing the location of upcoming visual stimulus on finger movement response in the context of control-on-display interfaces. Background: Previous research on pre-cues focus on attention allocation and motion studies were limited to indirect control conditions. The design of this study aimed to collect data on the exact landing point for finger-tap responses to a given visual stimulus. Method: Controlled visual stimuli and tasks were presented on a UI evaluation system built using mobile web standards; response accuracy and response time were measured and collected as appropriate. Among the 16 recruited participants, 11 completed the experiment. Results: Providing pre-cue on the location of stimulus affected response time and response accuracy. The response bias, which is a distance from the center of stimulus to the finger-tap location, was larger when the pre-cue was given during a one-handed operation. Conclusion: Given a pre-cue, response time decreases, but with accuracy penalized. Application: In designing touch-screen UI's - more strictly, visual components also acting as controllers - designers would do well to balance human perceptual and cognitive characteristics strategically.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2011년도 춘계학술대회
• /
• pp.365-368
• /
• 2011

영상은 현대인의 욕구에 부응 가능한 가장 적합한 매체로 떠오르고 있으며 영상의 방향 중 모션 그래픽은 관객의 시각과 청각을 동시에 자극하는 뉴미디어이며 사운드와 비주얼로 메시지를 전달할 수 있는 감성커뮤니케이션의 주요한 수단으로 주목받고 있다. 본 연구는 무대 배경에 쓰인 모션그래픽이 관객에게 어떤 느낌을 주며 그 효과와 효율은 어떠한지에 대해 알아보고 무대 배경에 모션그래픽을 적용하는 것이 일반화 되어있지 않아 그 조사범위가 한정되어 있었지만 최근 2~3년간 모션그래픽 사용빈도가 증가하고 있음을 알 수 있게 되어 앞으로 더욱 많은 분야에서 모션그래픽이 활용될 수 있을 것이란 사실에 의의를 두고 있다.

• 한국의상디자인학회지
• /
• 제6권3호
• /
• pp.19-29
• /
• 2004

The current fashion market is experiencing a lot of difficulties in fashion forecasting due to consumers' fast-changing lifestyle on fashion, changes in consumer behavior, and the segmentation of the fashion market. To cope with this harsh reality, many fashion enterprises have paid much attention to the SPA (Specialty Retailer's Store of Private Label Apparel) brand as a promising fashion marketing strategy in terms of which they can survive in the extremely competing fashion market. The SPA brand is in the stage of inception in Korea, but the SPA brands such as MUJI and UNIQLO are already dominating the fashion business in Japan. Korea has just started developing the SPA brand, but its technological development, which was triggered by the success of 'BASIC HOUSE', is rapidly evolving. Under these circumstances, the SPA brand is getting vital for the fashion market in efficiently realizing consumers' requirements, revolutionizing the method for providing product information and the process of Marketing Mix Program, and expressing the value of shop. This paper studies the nature of the SPA brand and fashion merchandising system, and in turn examine the differences between the visual merchandising of the existing fashion brands and the Japanese SPA brands that are used as the fashion marketing strategy which is driven by the up-to-date technological system. Centering around these issues, we propose a visual merchandising system for fashion enterprises which serves to develop Korean-style SPA brands.

• 복식
• /
• 제51권6호
• /
• pp.67-83
• /
• 2001

The purpose of this study is to define the aesthetic consciousness in the late Modernism fashion which generated a sudden style change and craze, and to identify the essential meaning of the style. In order to achieve this the aesthetic approach was applied. Visual commonalities were sought between fashion and contemporary architecture, furniture, ceramic and metalware, to lead to a deeper insight into the aesthetic consciousness. Common visual characteristics are curvedness of the line, obliqueness of the line, asymmetry of the form, exaggeration of the form and symbolic nature of the form. The content which can be analogized from the visual characteristics are the beauty of the nature, the beauty of the glamourous feminity, the beauty of the ideal and the beauty of the creative personality. In the creating process, the existential aspect of human being became a focus of attention, and human being's subjectivity operated as a principal force. In the late Modernism fashion, the appreciator's aesthetic experience became more important, and the appreciator's psychological satisfaction and pleasure were considered in the creative process. Fashion, architecture and crafts, which fulfill functional duties in everyday life, facilitated the appreciator's aesthetic experience through empathy. This study inquires into the relationship between aesthetic consciousness and visual form. This study offers meaning because to uncover the connoted aesthetic consciousness in the late Modernism fashion is to pursue the roots of current aesthetic consciousness and it is hoped that in doing so this study will provide a basis for interpreting and understanding today's fashion style.

• 한국응급구조학회지
• /
• 제24권2호
• /
• pp.111-121
• /
• 2020

Purpose: The purpose of this study was to compare visual blood loss estimation and subjective emergency according to clothing color. Methods: This is a quasi-experimental study which involved the use of mock bleeding patients wearing different colors tops. Results: Differences in visual estimates according to clothing color were significant in both paramedic students (F=6.69, p=.002) and the general department students (F=20.92, p=.000). When looking specifically at the accuracy of visual estimates, the paramedic students group tended to underestimate (50% white, 62.5% black, 32.5% yellow) the actual blood volume in all experimental conditions. On the other hand, the general department group tended to overestimation (45% white, 40% black, 67.5% yellow). The subjective emergency was also found to differ between paramedic students (F=13.58, p=.000) and general department students (F=9.67, p=.000). Conclusion: Paramedics treating bleeding patients at pre-hospital stages need to pay attention to blood loss estimations depending on clothing color, a factor not to be neglected or underestimated.

• 한국조경학회지
• /
• 제31권6호
• /
• pp.120-128
• /
• 2004

This paper was aimed to review the research trends on the subject of ′landscape′ that were published in the Journal of the Korean Institute of Landscape Architecture (KILA) over the 30 years from 1973 to 2003. The total number of articles with the "landscape" subject is 132(12.1%) out of 1,089(the total number of articles). The ratio of the ′landscape′ articles to the total number of the two decades between 1980 and 1999 increased at 8.7% and 1.1% respectively, and decreased at 5.3% since 2000. It was found that each decade showed its own trend of research subject. The first trend during the 1980′s focused on the methodology of analyzing the characteristics of landscape. The second trend during 1990′s converged to the positivistic research method, which relies on computer technology. A new and very important trend began during the same decade. It was "visual landscape planning", which attracted much attention since the operation of local autonomy in Korea. This trend focuses on ′visual landscape planning′, and it is expected to grow drastically in the near future. Therefore, it is recommended that we promote the more elaborate methodology of ′visual landscape planning′, which also includes the ecological and cultural aspects of the environment.

• 한국컴퓨터정보학회논문지
• /
• 제23권11호
• /
• pp.129-135
• /
• 2018

In this study, we designed a model that can measure the level of user's concentration by measuring and analyzing EEG data of the subjects who are performing Continuous Performance Test based on visual stimulus. This study focused on alpha and beta waves, which are closely related to concentration in various brain waves. There are a lot of research and services to enhance not only concentration but also brain activity. However, there are formidable barriers to ordinary people for using routinely because of high cost and complex procedures. Therefore, this study designed the model using the portable EEG measurement device with reasonable cost and Visual Continuous Performance Test which we developed as a simplified version of the existing CPT. This study aims to measure the concentration level of the subject objectively through simple and affordable way, EEG analysis. Concentration is also closely related to various brain diseases such as dementia, depression, and ADHD. Therefore, we believe that our proposed model can be useful not only for improving concentration but also brain disease prediction and monitoring research. In addition, the combination of this model and the Brain Computer Interface technology can create greater synergy in various fields.