• Korean Institute of Interior Design Journal
• /
• v.13 no.3
• /
• pp.35-42
• /
• 2004

This study dealt with approaches in architecture and music in the contemporary situation characterized by accidence and uncertainty through Pierre Boulez and Rem Koolhaas' works. First of all, we examined basic positions with starting from zero degree breaking from fixed ideas and with relative neutrality. Then, from a methodological aspect, we inquired into 1) anti-hierarchical objective approach, 2) accidental approach to form. 3) diagram of structure and event, and 4) the use of selective routes. Lastly, from a receptive aspect, we dealt with the space of pluralistic perspective and works in progress. The two persons used chaosmos approach that enables adjustment and control through structure defining the relationship with accidence or chaos. With the approach, they created works in progress or open works that have a pluralistic viewpoint working in the field of specific relation and the concept of endless regeneration.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.2
• /
• pp.8-18
• /
• 1993

A multi-font, multi-size and high speed character recognition system is designed. The design principles are simpilcity of algorithm, adaptibility, learnability, hierachical data processing and attention by feed back. For the multi-size character recognition, the extracted character images are normalized. A hierachical classifier classifies the feature vectors. Feature is extracted by applying the directional receptive field after the directional dege filter processing. The hierachical classifier is consist of two pre-classifiers and one decision making classifier. The effect of two pre-classifiers is prediction to the final decision making classifier. With the pre-classifiers, the time to compute the distance of the final classifier is reduced. Recognition rate is 95% for the three documents printed in three kinds of fonts, total 1,700 characters. For high speed implemention, a multiprocessor system with the ring structure of four transputers is implemented, and the recognition speed of 30 characters per second is aquired.

• International journal of advanced smart convergence
• /
• v.7 no.2
• /
• pp.95-100
• /
• 2018

In this paper, we propose a binarized multi-scale module to accelerate the speed of the pose estimating deep neural network. Recently, deep learning is also used for fine-tuned tasks such as pose estimation. One of the best performing pose estimation methods is based on the usage of two neural networks where one computes the heat maps of the body parts and the other computes the part affinity fields between the body parts. However, the convolution filtering with a large kernel filter takes much time in this model. To accelerate the speed in this model, we propose to change the large kernel filters with binarized multi-scale modules. The large receptive field is captured by the multi-scale structure which also prevents the dropdown of the accuracy in the binarized module. The computation cost and number of parameters becomes small which results in increased speed performance.

• Computers and Concrete
• /
• v.26 no.5
• /
• pp.411-420
• /
• 2020

Deep Convolution neural network (DCNN) has been widely used in the healthy maintenance of civil infrastructure. Using DCNN to improve crack detection performance has attracted many researchers' attention. In this paper, a light-weight spatial attention network module is proposed to strengthen the representation capability of ResNet and improve the crack detection performance. It utilizes attention mechanism to strengthen the interested objects in global receptive field of ResNet convolution layers. Global average spatial information over all channels are used to construct an attention scalar. The scalar is combined with adaptive weighted sigmoid function to activate the output of each channel's feature maps. Salient objects in feature maps are refined by the attention scalar. The proposed spatial attention module is stacked in ResNet50 to detect crack. Experiments results show that the proposed module can got significant performance improvement in crack detection.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.4
• /
• pp.314-322
• /
• 2021

Skeleton-based action recognition has attracted considerable attention in human action recognition. Recent methods for skeleton-based action recognition employ spatiotemporal graph convolutional networks (GCNs) and have remarkable performance. However, most of them have heavy computational complexity for robust action recognition. To solve this problem, we propose a shuffle graph convolutional network (SGCN) which is a lightweight graph convolutional network using pointwise group convolution rather than pointwise convolution to reduce computational cost. Our SGCN is composed of spatial and temporal GCN. The spatial shuffle GCN contains pointwise group convolution and part shuffle module which enhances local and global information between correlated joints. In addition, the temporal shuffle GCN contains depthwise convolution to maintain a large receptive field. Our model achieves comparable performance with lowest computational cost and exceeds the performance of baseline at 0.3% and 1.2% on NTU RGB+D and NTU RGB+D 120 datasets, respectively.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.348-351
• /
• 2021

최근 자동화의 필요성이 증가함에 따라 얼굴 표정 인식 분야(face expression recognition)가 인공지능과 이미지 처리 분야에서 활발히 연구되고 있다. 본 논문에서는 기존 인공신경망에서 요구되었던 고성능 GPU 환경과 높은 연산량을 극복하고자 모델 경량화(Light weighted Model) 기법을 적용하여 드론 및 모바일 기기에서 적용될 수 있는 얼굴 표정 인식 신경망을 제안한다. 제안하는 방법은 미세한 얼굴의 표정 인식을 위한 방법으로, 입력 이미지의 receptive field 를 늘려 특징 맵의 표현력을 높이는 방법을 제안한다. 또한 효과적인 신경망의 경량화를 위하여, 파라미터의 연산량을 줄일 때 발생하는 문제점을 극복하기 위한 방법을 제시한다. 따라서 제안하는 네트워크를 적용하면 많은 연산량과 느린 연산속도로 인해 제한되었던 네트워크 환경을 극복할 수 있을 뿐만 아니라, UAV(Unmanned Aerial Vehicle, 무인항공기) 및 모바일 기기에서 신경망을 이용한 실시간 얼굴 표정 인식을 할 수 있다.

• International Journal of Advanced Culture Technology
• /
• v.11 no.2
• /
• pp.132-141
• /
• 2023

The purpose of this study was to understand the vivid realities of important technical and relational aspects of visual art that were emphasised during training by art therapy supervisors and educators. Max van Manen's hermeneutic phenomenological methodology was incorporated into the study. Summarising their main experiences, art therapy supervisors enabled experiences of reproducibility and immediacy in their supervision, and allowed visual art to be used as a tool to foster inner contact with their supervisees. To enable this experience, art therapy supervisors provided a creative foundation and a receptive environment that promoted creativity for supervisees to use and experience art beyond the role of passive viewers. The results of this research clarified how the participating supervisors interpreted the value of art therapy as a method to nurture the professional growth of trainees. Their contributions suggest experiences and methods that may effectuate future advancements in the field of art therapy supervision.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.203-211
• /
• 2021

Image tampering detection and localization have become an active area of research in the field of digital image forensics in recent times. This is due to the widespread of malicious image tampering. This study presents a new method for image tampering detection and localization that combines the advantages of dilated convolution, residual network, and UNET Architecture. Using the UNET architecture as a backbone, we built the proposed network from two kinds of residual units, one for the encoder path and the other for the decoder path. The residual units help to speed up the training process and facilitate information propagation between the lower layers and the higher layers which are often difficult to train. To capture global image tampering artifacts and reduce the computational burden of the proposed method, we enlarge the receptive field size of the convolutional kernels by adopting dilated convolutions in the residual units used in building the proposed network. In contrast to existing deep learning methods, having a large number of layers, many network parameters, and often difficult to train, the proposed method can achieve excellent performance with a fewer number of parameters and less computational cost. To test the performance of the proposed method, we evaluate its performance in the context of four benchmark image forensics datasets. Experimental results show that the proposed method outperforms existing methods and could be potentially used to enhance image tampering detection and localization.

• Journal of Veterinary Clinics
• /
• v.40 no.4
• /
• pp.243-259
• /
• 2023

Machine learning and deep learning (ML/DL) algorithms have been successfully applied in medical practice. However, their application in veterinary medicine is relatively limited, possibly due to a lack in the quantity and quality of relevant research. Because the potential demands for ML/DL applications in veterinary clinics are significant, it is important to note the current gaps in the literature and explore the possible directions for advancement in this field. Thus, a scoping review was conducted as a situation analysis. We developed a search strategy following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. PubMed and Embase databases were used in the initial search. The identified items were screened based on predefined inclusion and exclusion criteria. Information regarding model development, quality of validation, and model performance was extracted from the included studies. The current review found 55 studies that passed the criteria. In terms of target animals, the number of studies on industrial animals was similar to that on companion animals. Quantitative scarcity of prediction studies (n = 11, including duplications) was revealed in both industrial and non-industrial animal studies compared to diagnostic studies (n = 45, including duplications). Qualitative limitations were also identified, especially regarding validation methodologies. Considering these gaps in the literature, future studies examining the prediction and validation processes, which employ a prospective and multi-center approach, are highly recommended. Veterinary practitioners should acknowledge the current limitations in this field and adopt a receptive and critical attitude towards these new technologies to avoid their abuse.

• The Korean Journal of Physiology
• /
• v.23 no.1
• /
• pp.151-167
• /
• 1989

The present study was undertaken to investigate modification in electrophysiological characteristics of cat dorsal horn cells resulting from carrageenin-induced inflammation. The followings were studied; 1) the time-course of changes in responses of the WDR (wide dynamic range) cell 1-3h after subcutaneous injection of carrageenin in its receptive field; 2) the responses of the same dorsal hern cells before and after induction of inflammation; 3) the effect of inflammation on the responsiveness of dorsal horn neurons to algogens (bradykinin & potassium); and 4) the effect of inflammation on the activity of WDR cell following administration of indomethacin and clonidine. Though responses of WDR neuron were increased dramatically during first 1h, the maximal enhancement was observed 3h after induction of inflammation especially by repetitive light tactile stimulus. Following carrageenin injection the majority of WDR neurons (10/15 units) showed enhanced responses to all the mechanical stimuli while in 3 cases responsiveness were intensified during activation by one tactile stimulus (brush or pressure). One cell was unaffected by inflammation and in another case the response was enhanced only to noxious stimulus. Five of 9 cells that could initially be driven by noxious stimulus were activated more strongly by same stimulus and even by tactile stimulus (pressure) following inflammation. In 2 cases neurons were sensitized only to noxious stimulus whereas in another 2 cells that did not show enhanced responses to noxious stimulus responses to light tactile stimulus (pressure) appeared after inflammation. Of 16 LT cells tested 6 responded to squeeze while 4 showed the characteristics of WDR cell following inflammation. No modification in responsiveness was recognized in 3 cells whereas response to only brush was enhanced in another 3 neurons. Following carrageenin injection responses of LT cell to bradykinin or $K^{+}$ were not altered whereas those of WOR neurons to bradykinin or $K^{+}$ were suppressed in 22.2% and 33.3% of cases, respectively. In two of 8 activity of HT cells were inhibited by bradykinin while in five of 8 responsiveness to $K^{+}$ were rather enhanced by inflammation. In the rest inflammation was ineffective. In inflammation-induced animal the receptive field of LT cell was not changed whereas those of WDR cell and HT cell were tremendously expanded. The enhanced responses of WDR neurons to mechanical stimuli resulted from inflammation were suppressed by intravenously injected indomethacin and clonidine suggesting that postaglandin is involved in inflammation-induced sensitization of these cells. The involvement of peripheral and central mechanisms in the modification in responsiveness of dorsal horn cells in the carrageenin-induced inflammation was discussed.