• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.556-558
• /
• 2022

This paper proposes a CanSat system with a vehicle tracking function based on Jetson Nano, a high-performance small computer capable of operating artificial intelligence algorithms. The CanSat system consists of a CanSat and a ground station. The CanSat falls in the atmosphere and transmits the data obtained through the installed sensors to the ground station using wireless communication. The existing CanSat is limited to the mission of simply transmitting the collected information to the ground station, and there is a limit to efficiently performing the mission due to the limited fall time and bandwidth limitation of wireless communication. The Jetson Nano based CanSat proposed in this paper uses a pre-trained neural network model to detect the location of a vehicle in each image taken from the air in real time, and then uses a 2-axis motor to move the camera to track the vehicle.

• Journal of Biomedical Engineering Research
• /
• v.45 no.2
• /
• pp.90-94
• /
• 2024

Diagnosing wounds presents a significant challenge in clinical settings due to its complexity and the subjective assessments by clinicians. Wound deep learning algorithms quantitatively assess wounds, overcoming these challenges. However, a limitation in existing research is reliance on specific datasets. To address this limitation, we created a comprehensive dataset by combining open dataset with self-produced dataset to enhance clinical applicability. In the annotation process, machine learning based on Gradient Vector Flow (GVF) was utilized to improve objectivity and efficiency over time. Furthermore, the deep learning model was equipped U-net with residual blocks. Significant improvements were observed using the input dataset with images cropped to contain only the wound region of interest (ROI), as opposed to original sized dataset. As a result, the Dice score remarkably increased from 0.80 using the original dataset to 0.89 using the wound ROI crop dataset. This study highlights the need for diverse research using comprehensive datasets. In future study, we aim to further enhance and diversify our dataset to encompass different environments and ethnicities.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.151-161
• /
• 2024

In this paper, we develop 'the Danger Map' of a workplace to identify risk and harmful factors by analyzing images of each process within the manufacturing plant site using artificial intelligence (AI). We proposed a system that automatically derives 'the risk and safety levels' based on the frequency and intensity derived from this Danger Map in accordance with actual field conditions and applies them to similar manufacturing industries. In particular, in the traditional evaluation method of manually evaluating the risk of a workplace using Excel, the risk level for each risk and harmful factor acquired from the video is automatically calculated and evaluated to ensure safety through the system and calculate the safety level, so that the company can take appropriate actions accordingly. and measures were prepared. To automate safety calculation and evaluation, 'Heinrich's law' was used as a model, and a 5X4 point evaluation scale was calculated for risky behavior patterns. To demonstrate this system, we applied it to a casting factory and were able to save 2 people the time and labor required to calculate safety each month.

• Human Ecology Research
• /
• v.62 no.2
• /
• pp.369-383
• /
• 2024

The aim of this study was to develop and implement a program based on Cognitive Behavior Therapy (CBT) for female college students experiencing body dissatisfaction. To systematize the program development process, we adopted the service design method. First, we conducted In-Depth Interviews (IDIs) to identify the difficulties faced by six female college students who experience body dissatisfaction, and to determine what kind of help they needed. Second, content analysis of the findings revealed that female college students were experiencing emotional-behavior problems which derived from the discrepancy between their ideal body image and the reality. Third, a prototype of a cognitive reconstruction program was developed to help transform their perceived 'body distortion' to a rational cognitive concept and thus reduce maladaptive consequences of 'body dissatisfaction'. The overall program consisted of three therapeutic components and seven steps. Fourth, to assess the effectiveness of the program, survey and IDIs were conducted. The results revealed that it is appropriate to use a cognitive model to solve problems caused by body dissatisfaction, and that understanding and reconstructing one's own cognitive processes can be effective in reducing body dissatisfaction. However, based on feedback from participants, a number of revisions were proposed, such as including sufficient induction regarding the behavioral change.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.25-37
• /
• 2024

This study proposes a novel automation system that integrates Optical Character Recognition (OCR) and Retrieval-Augmented Generation (RAG) technologies to enhance the efficiency of the ESG (Environmental, Social, and Governance) document review process. The proposed system improves text recognition accuracy by applying an ensemble model-based image preprocessing algorithm and hybrid information extraction models in the OCR process. Additionally, the RAG pipeline optimizes information retrieval and answer generation reliability through the implementation of layout analysis algorithms, re-ranking algorithms, and ensemble retrievers. The system's performance was evaluated using certificate images from online portals and corporate internal regulations obtained from various sources, such as the company's websites. The results demonstrated an accuracy of 93.8% for certification reviews and 92.2% for company regulations reviews, indicating that the proposed system effectively supports human evaluators in the ESG assessment process.

• Nuclear Medicine and Molecular Imaging
• /
• v.40 no.3
• /
• pp.177-185
• /
• 2006

Purpose: Purpose of this study is to synthesize $^{99m}Tc$-labeled transferrin for injection imaging and to compare it with $^{67}Ga$-titrate for the detection of infectious foci. Materials and methods: Succinimidyl 6-hydrazino-nicotinate hydrochloride-chitosan-transferrin (Transferrin) was synthesized and radiolabeled with $^{99m}Tc$. Labeling efficiencies of $^{99m}Tc$-Transferrin were determined at 10 min, 30 min, 1 hr, 2 hr, 4 hr and 8 hr. Biodistribution and imaging studies with $^{99m}Tc$-Transferrin and $^{67}Ga$-citrate were performed in a rat abscess model induced with approximately $2{\times}10^8$ colony forming unit of Staphylococcus aureus ATCC 25923. Results: Successful synthesis of Transferrin was confirmed by mass spectrometry. Labeling efficiency of $^{99m}Tc$-Transferrin was $96.2{\pm}0.7%,\;96.4{\pm}0.5%,\;96.6{\pm}1.0%,\;96.9{\pm}0.5%,\;97.0{\pm}0.7%\;and\;95.5{\pm}0.7%$ at 10 min, 30 min, 1 hr, 2 hr, 4 hr and 8 hr, respectively. The injected dose per tissue gram of $^{99m}Tc$-Transferrin was $0.18{\pm}0.01\;and\;0.18{\pm}0.01$ in the lesion and $0.05{\pm}0.01\;and\;0.04{\pm}0.01$ in the normal muscle, and lesion-to-normal muscle uptake ratio was $3.7{\pm}0.6\;and\;4.7{\pm}0.4$ at 30 min and 3 hr, respectively. On image, lesion-to-background ratio of $^{99m}Tc$-Transferrin was $2.18{\pm}0.03,\;2.56{\pm}0.11,\;3.08{\pm}0.18,\;3.77{\pm}0.17,\;4.70{\pm}0.45\;and\;5.59{\pm}0.40$ at 10 min, 30 min, 1 hr, 2 hr, 4 hr and 10 hr and those of $^{67}Ga$-citrate was $3.06{\pm}0.84,\;4.12{\pm}0.54\;and\;4.55{\pm}0.74 $ at 2 hr, 24 hr and 48 hr, respectively. Conclusion: Transferrin is successfully labeled with $^{99m}Tc$, and its labeling efficiency was higher than 95% and stable for 8 hours. $^{99m}Tc$-Transferrin scintigraphy showed higher image quality in shorter time compared to $^{67}Ga$-citrate image. $^{99m}Tc$-transferrin is supposed to be useful in the detection of the infectious foci.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.10 no.6
• /
• pp.69-80
• /
• 2015

This can be promoted collaboration environment for the system and the system is very important for competitiveness, it is equipped. If so, could work in collaboration with members of the organization to promote collaboration what factors? Organizational collaboration and cooperation of many people working, or worth pursuing common goals by sharing information and processes to improve labor productivity, defined as collaboration. Factors that promote collaboration are shared visions, the organization's principles and rules that reflect the visions, on-line system developments, and communication methods. First, it embodies the vision shared by the more sympathetic members are active and voluntary participation in the activities of the organization can be achieved. Second, the members are aware of all the rules and principles of a united whole is accepted and leads to good performance. In addition, the ability to share sensitive business activities for self-development and also lead to work to make this a regular activity to create a team that can collaborate to help the environment and the atmosphere. Third, a systematic construction of the online collaboration system is made efficient and rapid task. According to Student team and A corporation we knew that Cloud services and social media, low-cost, high-efficiency services could achieve. The introduction of the latest information technology changes, the members of the organization's systems and active participation can take advantage of continuing education must be made. Fourth, the company to inform people both inside and outside of the organization to communicate actively to change the image of the company activities, the creation of corporate performance is very important to figure. Reflects the latest trend to actively use social media to communicate the effort is needed. For development of systematic collaboration promoting model steps to meet the organizational role. First, the Chief Executive Officer to make a firm and clear vision of the organization members to propagate the faith, empathy gives a sense of belonging should be able to have. Second, middle managers, CEO's vision is to systematically propagate the organizers rules and principles to establish a system would create. Third, general operatives internalize the vision of the company stating that the role of outside companies must adhere. The purpose of this study was well done in collaboration organizations promoting factors for strategic alignment model based on the golden circle and collaboration to understand and reflect the latest trends in information technology tools to take advantage of smart work and business know how student teams through case analysis will derive the success factors. This is the foundation for future empirical studies are expected to be present.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.295-304
• /
• 2022

The purpose of this study is to detect the sorghum panicle using YOLOv5 based on RGB images acquired by a unmanned aerial vehicle (UAV) system. The high-resolution images acquired using the RGB camera mounted in the UAV on September 2, 2022 were split into 512×512 size for YOLOv5 analysis. Sorghum panicles were labeled as bounding boxes in the split image. 2,000images of 512×512 size were divided at a ratio of 6:2:2 and used to train, validate, and test the YOLOv5 model, respectively. When learning with YOLOv5s, which has the fewest parameters among YOLOv5 models, sorghum panicles were detected with mAP@50=0.845. In YOLOv5m with more parameters, sorghum panicles could be detected with mAP@50=0.844. Although the performance of the two models is similar, YOLOv5s ( 4 hours 35 minutes) has a faster training time than YOLOv5m (5 hours 15 minutes). Therefore, in terms of time cost, developing the YOLOv5s model was considered more efficient for detecting sorghum panicles. As an important step in predicting sorghum yield, a technique for detecting sorghum panicles using high-resolution RGB images and the YOLOv5 model was presented.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.95-107
• /
• 2017

In this study, a preliminary study was undertaken for development of a tunnel incident automatic detection system based on a machine learning algorithm which is to detect a number of incidents taking place in tunnel in real time and also to be able to identify the type of incident. Two road sites where CCTVs are operating have been selected and a part of CCTV images are treated to produce sets of training data. The data sets are composed of position and time information of moving objects on CCTV screen which are extracted by initially detecting and tracking of incoming objects into CCTV screen by using a conventional image processing technique available in this study. And the data sets are matched with 6 categories of events such as lane change, stoping, etc which are also involved in the training data sets. The training data are learnt by a resilience neural network where two hidden layers are applied and 9 architectural models are set up for parametric studies, from which the architectural model, 300(first hidden layer)-150(second hidden layer) is found to be optimum in highest accuracy with respect to training data as well as testing data not used for training. From this study, it was shown that the highly variable and complex traffic and incident features could be well identified without any definition of feature regulation by using a concept of machine learning. In addition, detection capability and accuracy of the machine learning based system will be automatically enhanced as much as big data of CCTV images in tunnel becomes rich.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.193-205
• /
• 2023

A large amount of floating debris from land-based sources during heavy rainfall has negative social, economic, and environmental impacts, but there is a lack of monitoring systems for floating debris accumulation areas and amounts. With the recent development of artificial intelligence technology, there is a need to quickly and efficiently study large areas of water systems using drone imagery and deep learning-based object detection models. In this study, we acquired various images as well as drone images and trained with You Only Look Once (YOLO)v5s and the recently developed YOLO7 and YOLOv8s to compare the performance of each model to propose an efficient detection technique for land-based floating debris. The qualitative performance evaluation of each model showed that all three models are good at detecting floating debris under normal circumstances, but the YOLOv8s model missed or duplicated objects when the image was overexposed or the water surface was highly reflective of sunlight. The quantitative performance evaluation showed that YOLOv7 had the best performance with a mean Average Precision (intersection over union, IoU 0.5) of 0.940, which was better than YOLOv5s (0.922) and YOLOv8s (0.922). As a result of generating distortion in the color and high-frequency components to compare the performance of models according to data quality, the performance degradation of the YOLOv8s model was the most obvious, and the YOLOv7 model showed the lowest performance degradation. This study confirms that the YOLOv7 model is more robust than the YOLOv5s and YOLOv8s models in detecting land-based floating debris. The deep learning-based floating debris detection technique proposed in this study can identify the spatial distribution of floating debris by category, which can contribute to the planning of future cleanup work.