• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.51-58
• /
• 2023

In this paper, we propose an organ segmentation technique for the automatic extraction of medical diagnostic indicators from X-ray images. In order to calculate diagnostic indicators of heart disease and spinal disease such as VHS(vertebral heart scale) and Cobb angle, it is necessary to accurately segment the thoracic spine, carina, and heart in a chest X-ray image. A deep neural network model in which the high-resolution representation of the image for each layer and the structure converted into a low-resolution feature map are connected in parallel was adopted. This structure enables the relative position information in the image to be effectively reflected in the segmentation process. It is shown that learning performance can be improved by combining the OCR module, in which pixel information and object information are mutually interacted in a multi-step process, and the channel attention module, which allows each channel of the network to be reflected as different weight values. In addition, a method of augmenting learning data is presented in order to provide robust performance against changes in the position, shape, and size of the subject in the X-ray image. The effectiveness of the proposed theory was evaluated through an experiment using 145 human chest X-ray images and 118 animal X-ray images.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.228-239
• /
• 2022

In this paper, we propose an unmanned vehicle scratch detection deep learning model for car sharing services. Conventional scratch detection models consist of two steps: 1) a deep learning module for scratch detection of images before and after rental, 2) a manual matching process for finding newly generated scratches. In order to build a fully automatic scratch detection model, we propose a one-step unmanned scratch detection deep learning model. The proposed model is implemented by applying transfer learning and fine-tuning to the deep learning model that detects changes in satellite images. In the proposed car sharing service, specular reflection greatly affects the scratch detection performance since the brightness of the gloss-treated automobile surface is anisotropic and a non-expert user takes a picture with a general camera. In order to reduce detection errors caused by specular reflected light, we propose a preprocessing process for removing specular reflection components. For data taken by mobile phone cameras, the proposed system can provide high matching performance subjectively and objectively. The scores for change detection metrics such as precision, recall, F1, and kappa are 67.90%, 74.56%, 71.08%, and 70.18%, respectively.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.183-192
• /
• 2023

The remotely sensed data, such as satellite imagery and aerial photos, can be used to extract and detect some objects in the image through image interpretation and processing techniques. Significantly, the possibility for utilizing digital map updating and land monitoring has been increased through automatic object detection since spatial resolution of remotely sensed data has improved and technologies about deep learning have been developed. In this paper, we tried to extract plastic greenhouses into aerial orthophotos by using fully convolutional densely connected convolutional network (FC-DenseNet), one of the representative deep learning models for semantic segmentation. Then, a quantitative analysis of extraction results had performed. Using the farm map of the Ministry of Agriculture, Food and Rural Affairsin Korea, training data was generated by labeling plastic greenhouses into Damyang and Miryang areas. And then, FC-DenseNet was trained through a training dataset. To apply the deep learning model in the remotely sensed imagery, instance norm, which can maintain the spectral characteristics of bands, was used as normalization. In addition, optimal weights for each band were determined by adding attention modules in the deep learning model. In the experiments, it was found that a deep learning model can extract plastic greenhouses. These results can be applied to digital map updating of Farm-map and landcover maps.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.743-744
• /
• 2012

LED digital control convergence technology is receiving attention. It enables to analyze lighting and living environments by recognizing user information and situations through a signal process system composed of a multi-functional composite sensor's module. LED lighting is higly efficient, long-lived, environmentally, and is possible to converge with communication, and receiving as a next-generation general lighting that will replace a florescent light including the light bulb. The proposed system is an intelligent LED control system that uses solar light. This study is about a lighting control technology associated with user-estimated information/situation and related low-cost technology. Also, this study aims to embody emotional lighting by appropriately lighting 10% of the discharge current with supplementary colored LED according to the surrounding environment.

• Journal of Korean Academy of Nursing
• /
• v.45 no.4
• /
• pp.604-612
• /
• 2015

Purpose: The purpose of this study was to investigate the levels of physical symptoms, anxiety, depression, and quality of life (QOL) during chemotherapy for colorectal cancer patients in South Korea and to identify factors influencing their QOL. Methods: Data were collected from 144 colorectal cancer patients receiving chemotherapy during 2012 at one general hospital located in Seoul. Physical symptoms were measured by the M. D. Anderson Symptom Inventory-Gastrointestinal Cancer Module, and anxiety and depression were measured by the Hospital Anxiety Depression Scale. QOL was measured by the Functional Assessment of Cancer Therapy-Colorectal. Data were analyzed using descriptive statistics, t-test, one-way ANOVA, $Scheff{\acute{e}}$ post hoc test, Pearson correlation and stepwise multiple regression. Results: Mean age of the participants was 56.6 and most of them were not employed. In terms of cancer stage, 38.2% were in stage 3, followed by stage 4 (34.7%). The most frequent symptom was lack of appetite, followed by sleep disturbance and fatigue. The mean score for anxiety was 5.40 with a prevalence of 23% and that of depression 8.85 with a prevalence of 64.6%. The mean score for quality of life was 81.93 out of 136 and 75.3% of the variance in QOL was explained by depression, symptoms, anxiety, treatment place, and occupational status. Depression was the strongest predictive factor. Conclusion: Oncology professionals need to pay special attention to relieving depression as well as physical symptoms to improve QOL during chemotherapy for colorectal cancer patients.

• Journal of Satellite, Information and Communications
• /
• v.11 no.4
• /
• pp.81-88
• /
• 2016

In this paper, we propose an adaptive multi-target estimation algorithm using the characteristics of signals in the IR-UWB(Impulse-Radio Ultra Wideband) radar system, which is attracting attention because it has good transparency, robustness to the indoor environment, and high precision positioning of tens of centimeters. We proposed an algorithm that estimates multiple peaks with the characteristic that the signal reflected by the target has a peak. To verify the performance of these algorithms, multiple targets were placed in front of the radar and the existing technique and the multi - target estimation algorithm were compared. The location of the targets is estimated in real time with one transmitting antenna and one receiving antenna. The number of estimates can be increased compared with the existing peak signal derivation method, and multiple targets can be derived. The conventional technique estimates only one target, which results in a mean square error of 1 while a multi - target estimation algorithm yields a result of about 0.05. The proposed method is expected to be able to apply multiple targets to the estimation and application in one IR-UWB module environment.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.4
• /
• pp.39-49
• /
• 2001

Application of information system to hospital would bring innovative improvement on efficiency of business management and provide high quality services toward patients as well as the retrenchment of operating funds. PACS(Picture Archiving and Communication System) including X-ray film that manages the medical image information effectively, has drawn considerable attention to essential structural elements to the sophisticated information system for hospital. PACS system should be connected to the network after making a form of standard medical image file from different style of image information obtained from various medical instruments. In this paper, to solve this problem, we construct Mini-PACS that converts the form of Non-DICOM file to the form of standard file by designing the DICOM converter. This system is designed to be managed under Web environment. Comparing with the existed Mini-PACSs, consisting of the client and server module, our system is designed and implemented with integration of these functions in order to be strongly combine strongly between system.

• Journal of Digital Contents Society
• /
• v.9 no.4
• /
• pp.601-606
• /
• 2008

U-Healthcare is one of the major applications in ubiquitous sensor network. U-Healthcare has potential to become a critical service for the people who immediately require emergency ambulatory attention. This paper describes about the real time pulse monitoring and reporting system, consisting of two components: thus, the one is a reliable bio-sensor that continuously monitors the pulse information of the subject, and the other is the automatic transfer system that transmits pulse information to both his/her family and hospital care system through the Base Station. In the hospital, this bio-information can be used to treat the patient accordingly. I designed the pulse information monitored by a bio-sensor module that transfers the pulse information to both the Base Station and the central monitoring system through transmitting protocols such as Zigbee and TCP/IP, as well as designed the architecture of information packets for the corresponding protocols. Furthermore, the central monitoring system automatically parses the pulse information of the subject into the web database server, which can continuously provides the real time information and status of the subject via an internet browser to the clients who are family members of the subject and the authenticated medical care personnel as well.

• Journal of Korean Society of Water and Wastewater
• /
• v.32 no.4
• /
• pp.317-324
• /
• 2018

SWRO-PRO hybrid desalination technology is recently getting more attention especially in large desalination markets such as USA, Middle East, Japan, Singapore, etc. because of its promising potential to recover a considerable amount of osmotic energy from brine (a high-concentration solution of salt, 60,000 - 80,000 mg/L) and also to minimize the impact of the discharged brine into a marine ecosystem. By the research and development of the core technologies of the SWRO-PRO desalination system in a national desalination research project (Global MVP) supported by Ministry of Land, Infrastructure, and Transport (MOLIT) and Korea Agency for Infrastructure Technology Advancement (KAIA), it is anticipated that around 25% of total energy consumption rate (generally 3 to $4kWh/m^3$) of the SWRO desalination can be reduced by recovering the brine's osmotic energy utilizing wastewater treatment effluent as a PRO feed solution and an isobaric pressure exchanger (PX, ERI) as a PRO energy converter. However, there are still several challenges needed to be overcome in order to ultimately commercialize the novel SWRO-PRO process. They include system optimization and integration, development of efficient PRO membrane and module, development of PRO membrane fouling control technology, development of design and operation technology for the system scaling-up, development of diverse business models, and so on. In this paper, the current status and progress of the pilot study of the newly developed SWRO-PRO hybrid desalination technology is discussed.