• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1224-1232
• /
• 2022

Whole body bone scan is the most frequently performed nuclear medicine imaging to evaluate bone metastasis in cancer patients. We evaluated the performance of a VGG16-based transfer learning classifier for bone scan images in which metastatic bone lesion was present. A total of 1,000 bone scans in 1,000 cancer patients (500 patients with bone metastasis, 500 patients without bone metastasis) were evaluated. Bone scans were labeled with abnormal/normal for bone metastasis using medical reports and image review. Subsequently, gradient-weighted class activation maps (Grad-CAMs) were generated for explainable AI. The proposed model showed AUROC 0.96 and F1-Score 0.90, indicating that it outperforms to VGG16, ResNet50, Xception, DenseNet121 and InceptionV3. Grad-CAM visualized that the proposed model focuses on hot uptakes, which are indicating active bone lesions, for classification of whole body bone scan images with bone metastases.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.150-159
• /
• 2022

This paper presents an implementation of detecting whether a helmet is worn and there is a fall accident through individual image analysis in real-time from extracting the image objects of several workers active in the industrial field. In order to detect image objects of workers, YOLO, a deep learning-based computer vision model, was used, and for whether a helmet is worn or not, the extracted images with 5,000 different helmet learning data images were applied. For whether a fall accident occurred, the position of the head was checked using the Pose real-time body tracking algorithm of Mediapipe, and the movement speed was calculated to determine whether the person fell. In addition, to give reliability to the result of a falling accident, a method to infer the posture of an object by obtaining the size of YOLO's bounding box was proposed and implemented. Finally, Telegram API Bot and Firebase DB server were implemented for notification service to administrators.

• Journal of the Daesoon Academy of Sciences
• /
• v.21
• /
• pp.255-284
• /
• 2013

There are many discourses about 'religion and women,' but it is no exaggeration to say that there is none about 'religion and men.' This is because the existing religions have been male-centric and have produced legions of male-dominated cultures. In Catholic Church, even today, only men can become the Pope, and women are not allowed to enter priesthood. Meanwhile, in the Islamic cultural areas, the reality is that women are being victimized by men who do not recognize the bad habits such as honor killings, or honor crimes. It is certain that gender discrimination in religious and cultural areas cannot be overlooked. This study focuses on the understanding of women in the thought of Daesoonjinrihoe(大巡眞理會), that is, the Daesoon Thought, which claims to advocate world peace. Daesoonjinrihoe is understood as a thought which tries to overcome gender discrimination prevalent in the existing religions and presents the vision of a new religion which aims to realize a new world of peace by drawing a distinction between the Former Heaven and the Latter Heaven. This study examines the understanding of women by looking at the tenet of Daesoonjinrihoe that consists of 'YeumYangHapDeok(陰陽合德), SinInJoHwa(神人調化), HaeWon-SangSaeng(解冤相生), DoTongJinGyeong(道通眞境).' The tenet is thought of as the basis of creed on which the understanding of women by the Daesoon Thought can be grasped as it basically contains the essence of teaching of the order. In the Daesoon Thought, women have the same status as men; women can become holy and dignified beings by engaging in independent, active, and autonomous spiritual exercises, and serve as a driving force for the realization of the ideal world. This understanding of women by the Daesoon Thought contains the idea of peace which can turn 'the culture of discrimination' into 'the culture of equality,' and 'the culture of life destruction' into 'the culture of life care.'

• Asia Marketing Journal
• /
• v.12 no.1
• /
• pp.81-101
• /
• 2010

Lotte Shopping Co. started its business from Lotte Department Store. From the beginning, Lotte Shopping Co. opened the largest department store and, since then, has expanded its business size through the processes of active developments of its own stores and merges and acquisitions of other companies. Currently, it operates a variety of retail shops such as department stores, discount stores, movies theaters, shopping malls, and supermarkets along with a TV home-shopping station and an online shopping mall. Lotte group, a business conglomerate Lotte Shopping belongs to, has an objective of becoming TOP 10 business group in Asia by 2018. Lotte group declared its vision statements in 2009 and has spent its effort to accomplish the goal. Lotte Shopping is implementing the group-level growth strategy through merges and acquisitions and diverse marketing programs. We will briefly investigate the current situation of Lotte Shopping and will then analyze its 1) entertainment shopping center and multi-channel strategy, 2) global market entry, and 3) education system.

• Smart Structures and Systems
• /
• v.33 no.1
• /
• pp.55-64
• /
• 2024

This paper proposes a fusion imaging-based coating-defect classification method for steel structures that uses zero-shot learning. In the proposed method, a halogen lamp generates heat energy on the coating surface of a steel structure, and the resulting heat responses are measured by an infrared (IR) camera, while photos of the coating surface are captured by a charge-coupled device (CCD) camera. The measured heat responses and visual images are then analyzed using zero-shot learning to classify the coating defects, and the estimated coating defects are visualized throughout the inspection surface of the steel structure. In contrast to older approaches to coating-defect classification that relied on visual inspection and were limited to surface defects, and older artificial neural network (ANN)-based methods that required large amounts of data for training and validation, the proposed method accurately classifies both internal and external defects and can classify coating defects for unobserved classes that are not included in the training. Additionally, the proposed model easily learns about additional classifying conditions, making it simple to add classes for problems of interest and field application. Based on the results of validation via field testing, the defect-type classification performance is improved 22.7% of accuracy by fusing visual and thermal imaging compared to using only a visual dataset. Furthermore, the classification accuracy of the proposed method on a test dataset with only trained classes is validated to be 100%. With word-embedding vectors for the labels of untrained classes, the classification accuracy of the proposed method is 86.4%.

• The Journal of Korean Society for Radiation Therapy
• /
• v.16 no.2
• /
• pp.43-61
• /
• 2004

Purpose : For qualify improvement in radiotherapy, it is important to set up and evaluate equipment (linac) accurately. In addition, technicians are needed to be fully aware of the equipment's detailed quality and its manual. Therefore, the result of ATP is evaluated and introduced, in order that the technicians are skilled by participating in quality assurance (QA) and understanding the quality of the equipment before clinical use. Method and Material : QA for LINAC 21EX (Varian, US) was done with suppliers its procedure was divided into radiation survey, mechanical test, radiation isocenter test, bean performance, dosimetry, and enhanced dynamic wedge and using X-omat film (Kodak), multidata, densitometer, and electrometer. QA of MLC (Millennium, 120 leaf) attached to LINAC and EPID (Portal vision) were done separately. Result : The leakage dose by survey meter was below the tolerance. In mechanical test, collimater, gantry, and couch rotation were less than 1mm, and the angles were ${\pm}0.1^{\circ}$ for digital and ${\pm}0.5^{\circ}$ for mechanical. The alignment test of the light field and crosshair were evaluated less than 1mm. The (a)symmetrical jaw field was less than ${\pm}0.5mm$. The radiation isocenter test using X-mat film was less than 1mm. The consistency of light field and radiation field was less than ${\pm}0.1mm$. PDD for photon energy was less than ${\pm}1\%$ and for electron energy of $90\%,\;80\%,\;50\%,\;and\;30\%$ were evaluated within the tolerance. Flatness for photon and electron energy was evaluated $2.3\%$ (tolerance $3\%$) and $3\%$ (tolerance $4.5\%$), respectively, and symmetry was $0.45\%$ (tolerance $2\%$) and $0.3\%$ (tolerance $2\%$), respectively. Dosimetry test for short term, MU setting, rep rate, and dose rate accuracy of photon and electron energy was within the tolerance depending on energy, MU, and gantry angle. Conclusion : Accuracy and safety for clinical use of Clinac 21EX was verified through customer acceptance procedure and the quality of the equipment was found out. These can reduce the difficulties in using the equipment. Furthermore, it is useful for clinically treatment of patients by technicians' active participations.

• Journal of the Daesoon Academy of Sciences
• /
• v.29
• /
• pp.1-36
• /
• 2017

The purpose of this article is to investigate the future prospects for establishing the True Donghak phase of Daesoon Thought. The True Donghak refers to 'the future prospect of having a true life, true thinking, and true living' in which enjoying the world in a state of good fortune became a true reality after the death of Suwun, according to faith in Gucheon Sangje. The correlation between "Attending to the Lord of Heaven" in Donghak, and "The Reordering Works of Heaven and Earth" in Daesoon shows the prospect of achieving the Daesoonist transformation into energy to gain true life and re-creation. The correlation between "Nourishing the Lord of Heaven" in Donghak and "Attending to Study and Attending to Law" in Daesoon show the transformation of Daesoon-reason into true thinking and renewing. The correlation between "Humanity is Divine" in Donghak and "The Salvation of Humanity is the Will of Heaven" in Daesoon show transformation into the practice of Daesoon for the true living and renewing. This investigation utilizes the literature review and the generation theory of life-philosophy to examine revelations regarding the conversation between Spirit and Mind. This is the future prospect for the establishing the True Donghak phase of Daesoon thought. It consists of a threefold connection among life, thinking, and living. The "public-centered spirituality of Daesoon Truth" which connects and mediates among people appears in three aspects. Firstly, it is thought to be the vision of the true life through the 'renewal of active, energetic power' bestowed by Gucheon Sangje. Secondly, it is thought to be the vision of true thinking through the "renewal via freedom from delusion". Thirdly, it is thought to be the vision of true living through the "renewal of true mind". To bring about the creation of true Donghak, Gucheon Sangje incarnated to the Korean peninsula instead of Suwun and the salvation of the world salvation now centers on Korea with regards to the threefold connection future prospect. Gucheon Sangje's revelation addresses and solves the postscript problem of Chosun and further establishes a Utopia. Suwun established Donghak but failed later on due to his lankiness. At last the true Donghak has been opened for the future by Gucheon Sangje and Jeongsan's fifty years of religious accomplishments. In the long run, it has been developed further by Woodang's Daesoon Jinrihoe.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.9-16
• /
• 2020

In the Image processing and computer vision, the problem of reconstructing from one image to another or generating a new image has been steadily drawing attention as hardware advances. However, the problem of computer-generated images also continues to emerge when viewed with human eyes because it is not natural. Due to the recent active research in deep learning, image generating and improvement problem using it are also actively being studied, and among them, the network called Generative Adversarial Network(GAN) is doing well in the image generating. Various models of GAN have been presented since the proposed GAN, allowing for the generation of more natural images compared to the results of research in the image generating. Among them, pix2pix is a conditional GAN model, which is a general-purpose network that shows good performance in various datasets. pix2pix is based on U-Net, but there are many networks that show better performance among U-Net based networks. Therefore, in this study, images are generated by applying various networks to U-Net of pix2pix, and the results are compared and evaluated. The images generated through each network confirm that the pix2pix model with Attention, R2, and Attention-R2 networks shows better performance than the existing pix2pix model using U-Net, and check the limitations of the most powerful network. It is suggested as a future study.

• Cartoon and Animation Studies
• /
• s.29
• /
• pp.151-172
• /
• 2012

Game production education in a university is very important because it is the stage for completing a game education course as well as for determining a future of game industry. In order to perform various experience and creative learning, it should be able to effectively use a computer infrastructure representing the knowledge and information society for the purpose of obtaining and re-processing information necessary for game production through prediction of directions of game industry as well information technology. This research is focused on an effective game engine education for students whom want to become game graphics designers. The purpose of this study is to draw a lesson of game production utilizing game engines and it enables practice-focused class for game production. It also allows the class participant to manufacture prototypes without support from game programmers for their outcomes of works planned during the game production class. The theoretical background of game production compared and analyzed exemplary game engines. Based on the result, the study selected Unity 3D engine and conducted the research on the background where the Unity engine has been selected and its characteristics. In addition, this study provided an example of game production utilizing a game engine, and also described the details of actual realization. This study selected Torque3D with the Unity in order to identify the purpose of this study and efficiency of learning. Thus, the previous situation is that the class remained in making a game plan during the course of game production project and, students whose major is not game programming. Now, it is necessary for students to make many efforts to make a game in an active and positive attitude by utilizing a game engine beyond the previous method of class.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.101-109
• /
• 2014

It is an essential element for the establishment of image processing related systems to find the exact contour from the image of an arbitrary object. In particular, if a vision system is established to inspect the products in the automated production process, it is very important to detect the contours for standardized shapes such lines and curves. In this paper, we propose a prototype adaptive dynamic contour model, p-Snake with improved contour extraction algorithms by adding the prototype energy. The proposed method is to find the initial contour by applying the existing Snake algorithm after Sobel operation is performed for prototype analysis. Next, the final contour of the object is detected by analyzing prototypes such as lines and circles, defining prototype energy and using it as an additional energy item in the existing Snake function on the basis of information on initial contour. We performed experiments on 340 images obtained by using an environment that duplicated the background of an industrial site. It was found that even if objects are not clearly distinguished from the background due to noise and lighting or the edges being insufficiently visible in the images, the contour can be extracted. In addition, in the case of similarity which is the measure representing how much it matches the prototype, the prototype similarity of contour extracted from the proposed p-ACM is superior to that of ACM by 9.85%.