• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.1
• /
• pp.269-274
• /
• 2023

In this paper, we proposed a new UNet 3+ model for medical image segmentation. The proposed ensemble(E) UNet 3+ model consists of UNet 3+s of varying depths into one unified architecture. UNet 3+s of varying depths have same encoder, but have their own decoders. They can bridge semantic gap between encoder and decoder nodes of UNet 3+. Deep supervision was used for learning on a total of 8 nodes of the E-UNet 3+ to improve performance. The proposed E-UNet 3+ model shows better segmentation results than those of the UNet 3+. As a result of the simulation, the E-UNet 3+ model using deep supervision was the best with loss function values of 0.8904 and 0.8562 for training and validation data. For the test data, the UNet 3+ model using deep supervision was the best with a value of 0.7406. Qualitative comparison of the simulation results shows the results of the proposed model are better than those of existing UNet 3+.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.36 no.5
• /
• pp.93-103
• /
• 2020

The purpose of this study is to suggest a supervisory way to improve the efficiency of Building Supervision using Deep Learning, especially object detecting technology. Since the establishment of the Building Supervision system in Korea, it has been changed and improved many times systematically, but it is hard to find any improvement in terms of implementing methods. Therefore, the Supervision is until now the area where a lot of money, time and manpower are needed. This might give a room for superficial, formal and documentary supervision that could lead to faulty construction. This study suggests a way of Building Supervision which is more automatic and effective so that it can lead to save the time, effort and money. And the way is to detect the hoop-bars of a column and count the number of it automatically. For this study, we made a hoop-bar detecting network by transfor learnning of YOLOv2 network through MATLAB. Among many training experiments, relatively most accurate network was selected, and this network was able to detect rebar placement in building site pictures with the accuracy of 92.85% for similar images to those used in trainings, and 90% or more for new images at specific distance. It was also able to count the number of hoop-bars. The result showed the possibility of automatic Building Supervision and its efficiency improvement.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.1
• /
• pp.11-17
• /
• 2024

Lung cancer segmentation in chest CT images is challenging due to the varying sizes of tumors and the presence of surrounding structures with similar intensity values. To address these issues, we propose a lung cancer segmentation network that incorporates deep supervision and utilizes UNet3+ as the backbone. Additionally, we propose a hybrid lesion focal loss function comprising three components: pixel-based, region-based, and shape-based, which allows us to focus on the smaller tumor regions relative to the background and consider shape information for handling ambiguous boundaries. We validate our proposed method through comparative experiments with UNet and UNet3+ and demonstrate that our proposed method achieves superior performance in terms of Dice Similarity Coefficient (DSC) for tumors of all sizes.

• Journal of the Korea Construction Safety Engineering Association
• /
• s.37
• /
• pp.74-83
• /
• 2006

As there are more accidents which are more serious in construction site than other industries, it needs the safety management system to be SLIM on the same time, there are still lots of difficulties to prevent those accidents exactly, so it also needs a safety supervision team to prevent the accident, unsafe operation and condition before happening, which is also called as a Man-to Man safety management method. The range of the job site in one personnel's management is very big and large, so it needs the personnel to deep watch the safety operation and prevent any unsafe/fire accidents; the personnel also should find out the unsafe points in the job site, and carefully supervise the dead angle site, then support the totally safety management POINT and realize the ZERO accident.

• Animal Bioscience
• /
• v.34 no.9
• /
• pp.1532-1543
• /
• 2021

Objective: This study was aimed to establish a quantitative detection method for meat contamination based on specific polypeptides. Methods: Thermally stable peptides with good responses were screened by high resolution liquid chromatography tandem mass spectrometry. Standard curves of specific polypeptide were established by triple quadrupole mass spectrometry. Finally, the adulteration of commercial samples was detected according to the standard curve. Results: Fifteen thermally stable peptides with good responses were screened. The selected specific peptides can be detected stably in raw meat and deep processed meat with the detection limit up to 1% and have a good linear relationship with the corresponding muscle composition. Conclusion: This method can be effectively used for quantitative analysis of commercial samples.

• The Journal of Information Systems
• /
• v.30 no.1
• /
• pp.65-84
• /
• 2021

Purpose Based on the development of artificial intelligence and big data technologies, the RegTech has been emerged to reduce regulatory costs and to enable efficient supervision by regulatory bodies. The word RegTech is a combination of regulation and technology, which means using the technological methods to facilitate the implementation of regulations and to make efficient surveillance and supervision of regulations. The purpose of this study is to describe the recent adoption of RegTech and to provide basic examples of applying RegTech to capital market regulations. Design/methodology/approach English-based ontology and deep learning technologies are quite developed in practice, and it will not be difficult to expand it to European or Latin American languages that are grammatically similar to English. However, it is not easy to use it in most Asian languages such as Korean, which have different grammatical rules. In addition, in the early stages of adoption, companies, financial institutions and regulators will not be familiar with this machine-based reporting system. There is a need to establish an ecosystem which facilitates the adoption of RegTech by consulting and supporting the stakeholders. In this paper, we provide a simple example that shows a procedure of applying RegTech to recognize and interpret Korean language-based capital market regulations. Specifically, we present the process of converting sentences in regulations into a meta-language through the morpheme analyses. We next conduct deep learning analyses to determine whether a regulatory sentence exists in each regulatory paragraph. Findings This study illustrates the applicability of RegTech-based ontology and deep learning technologies in Korean-based capital market regulations.

• Korean Institute of Interior Design Journal
• /
• v.25 no.4
• /
• pp.105-112
• /
• 2016

Nurses in a children's hospital have to meet a special condition with their younger patients who need continuous supervision and cares. The planning of the ward where the nurse as well as the patient and his/her caregivers stay all day long should cover all the users need. This study focused on the nurse's need for the ward in children's hospital. The nurse stay longer than any users in hospital and their treatment have to be based on deep understanding of their patients. The survey research followed the literature review on the children's hospital and the nurses' task and behavior. 119 nurses answered the structural questionnaire and their answers were analyzed using the statistical process such as basic descriptive statistics, ANOVA, and actor analysis. Results and conclusions are as follows. (1) The subjects least satisfied with the accessibility for the children and the nature-and child-friendly design features among physical environment design factors of the hospital. (2) The Subject regarded the patients' room to a private place of the patients and their caregivers not to the work places. (3) The design factors of the nursing station were classified into four: the functionality-, the privacy-, the supervision-and the restfulness-factor. The functionality and supervision factor were highly required as a workplace, the privacy factor between the patients, their caregivers and subject were also represented high score, but the restfulness factor were least required.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.38-40
• /
• 2021

Medical domain has a massive number of data records without the response value. Self-supervised learning is a suitable method for medical data since it learns pretext-task and supervision, which the model can understand the semantic representation of data without response values. However, since self-supervised learning performance depends on the expression learned by the pretext-task, it is necessary to define an appropriate Pretext-task with data feature consideration. In this paper, to actively exploit the unlabeled medical data into artificial intelligence research, experimentally find pretext-tasks that suitable for the medical data and analyze the result. We use the x-ray image dataset which is effectively utilizable for the medical domain.

• International Journal of High-Rise Buildings
• /
• v.4 no.4
• /
• pp.261-270
• /
• 2015

Hong Kong is a renowned small city with densely placed skyscrapers. It is no surprise that heavy duty or even mega foundations are built over the years to support these structures. To cope with the fast construction pace, several heavy deep foundation types have been widely adopted with some prescribed design rules. This Paper has selected two commonly adopted but distinctive foundation types, namely large diameter bored piles and percussive steel H-piles to illustrate the special design and construction considerations related to these pile types in related to local context. The supervision requirement in related to foundation works for which again may be unique in Hong Kong will also be highlighted. A case history is also discussed in the later part of the Paper to illustrate the application of one of these foundations and to highlight the importance of considering foundation design and basement excavation method in a holistic manner.

• Smart Structures and Systems
• /
• v.32 no.3
• /
• pp.135-151
• /
• 2023

Using 3D asphalt pavement surface data, a deep and multiscale network named CrackNet-M is proposed in this paper for pixel-level crack detection for improvements in both accuracy and robustness. The CrackNet-M consists of four function-specific architectural modules: a central branch net (CBN), a crack map enhancement (CME) module, three pooling feature pyramids (PFP), and an output layer. The CBN maintains crack boundaries using no pooling reductions throughout all convolutional layers. The CME applies a pooling layer to enhance potential thin cracks for better continuity, consuming no data loss and attenuation when working jointly with CBN. The PFP modules implement direct down-sampling and pyramidal up-sampling with multiscale contexts specifically for the detection of thick cracks and exclusion of non-crack patterns. Finally, the output layer is optimized with a skip layer supervision technique proposed to further improve the network performance. Compared with traditional supervisions, the skip layer supervision brings about not only significant performance gains with respect to both accuracy and robustness but a faster convergence rate. CrackNet-M was trained on a total of 2,500 pixel-wise annotated 3D pavement images and finely scaled with another 200 images with full considerations on accuracy and efficiency. CrackNet-M can potentially achieve crack detection in real-time with a processing speed of 40 ms/image. The experimental results on 500 testing images demonstrate that CrackNet-M can effectively detect both thick and thin cracks from various pavement surfaces with a high level of Precision (94.28%), Recall (93.89%), and F-measure (94.04%). In addition, the proposed CrackNet-M compares favorably to other well-developed networks with respect to the detection of thin cracks as well as the removal of shoulder drop-offs.