• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.233-247
• /
• 2023

Recently, research on detecting objects in hidden spaces beyond the direct line-of-sight of observers has received attention. Most studies use optical equipment that utilizes the directional of light, but sound that has both diffraction and directional is also suitable for non-line-of-sight(NLOS) research. In this paper, we propose a novel method of detecting objects in non-line-of-sight (NLOS) areas using acoustic signals in the audible frequency range. We developed a deep learning model that extracts information from the NLOS area by inputting only acoustic signals and predicts the properties and location of hidden objects. Additionally, for the training and evaluation of the deep learning model, we collected data by varying the signal transmission and reception location for a total of 11 objects. We show that the deep learning model demonstrates outstanding performance in detecting objects in the NLOS area using acoustic signals. We observed that the performance decreases as the distance between the signal collection location and the reflecting wall, and the performance improves through the combination of signals collected from multiple locations. Finally, we propose the optimal conditions for detecting objects in the NLOS area using acoustic signals.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.27-40
• /
• 2023

With the increase in the spread of smart devices and the impact of COVID-19, the consumption of media contents through smart devices has significantly increased. Along with this trend, the amount of media contents viewed through OTT platforms is increasing, that makes contents recommendations on these platforms more important. Previous contents-based recommendation researches have mostly utilized metadata that describes the characteristics of the contents, with a shortage of researches that utilize the contents' own descriptive metadata. In this paper, various text data including titles and synopses that describe the contents were used to recommend similar contents. KLUE-RoBERTa-large, a Korean language model with excellent performance, was used to train the model on the text data. A dataset of over 20,000 contents metadata including titles, synopses, composite genres, directors, actors, and hash tags information was used as training data. To enter the various text features into the language model, the features were concatenated using special tokens that indicate each feature. The test set was designed to promote the relative and objective nature of the model's similarity classification ability by using the three contents comparison method and applying multiple inspections to label the test set. Genres classification and hash tag classification prediction tasks were used to fine-tune the embeddings for the contents meta text data. As a result, the hash tag classification model showed an accuracy of over 90% based on the similarity test set, which was more than 9% better than the baseline language model. Through hash tag classification training, it was found that the language model's ability to classify similar contents was improved, which demonstrated the value of using a language model for the contents-based filtering.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.3
• /
• pp.12-19
• /
• 2023

In the case of the construction industry, the relationship between process and cost should be appropriately distributed so that the finished product can be delivered at the minimum fee within the construction period. At that time, it should be considered the size of the bridge, the construction method, the environment and production capacity of the factory, and the transport distance. However, due to various reasons that occur during the construction period, problems such as construction delay, construction cost increase, and quality and reliability degradation occur. Therefore, a systematic and scientific construction technique and process management technology are needed to break away from the conventional method. The prefab(Pre-Fabrication) is a representative OSC (Off-Site Construction) method manufactured in a factory and constructed onsite. This study develops a resource and process plan optimization system for the process management of the Nodular girder, a prefab bridge girder. A simulation algorithm develops to automatically test various variables in the personnel equipment mobilization plan to derive the optimal value. And, the algorithm was applied to the Paju-Pocheon Expressway Construction (Section 3) Dohwa 4 Bridge under construction, and the results compare. Based on construction work standard product calculation, actual input manpower, equipment type, and quantity were applied to the Activity Card, and the amount of work by quantity counting, resource planning, and resource requirements was reflected. In the future, we plan to improve the accuracy of the program by applying forecasting techniques including various field data.

• Journal of the Korean Orthopaedic Association
• /
• v.54 no.6
• /
• pp.509-518
• /
• 2019

Purpose: Lymph node metastasis is a very important prognostic factor for all skin cancers and some sarcomas. A sentinel lymph node (SLN) biopsy is the most useful technique for identifying SLNs. Recently, a new generation of diagnostic tools, such as single photon emission computed tomography/computed tomography (SPECT/CT) and positron emission tomography/CT (PET/CT) enabled the detection of SLNs. This study compared the efficacy of PET/CT for detecting lymph node metastases with a SLN biopsy in a single medical center. Materials and Methods: From 2008 to 2018, 72 skin cancers of sarcoma patients diagnosed with some lymph node involvement in a whole body PET/CT reading were assessed. Patients suspected of lymph node metastasis were sent to biopsy and those suspected to be reactive lesions were observed. The analysis was performed retrospectively using the medical records, clinical information, PET/CT readings, and pathology results. Results: The age of patients ranged from 14 to 88 years and the mean follow-up period was 2.4 years. Twenty-two patients were suspected of a lymph node metastasis and confirmed. The sensitivity, specificity, positive predictive value and negative predictive value of PET/CT images in sarcoma and non-sarcoma tumors were increased significantly when the expert's findings were considered together. Conclusion: PET/CT is effective in detecting lymph node metastases.

• Journal of the Korean Orthopaedic Association
• /
• v.52 no.1
• /
• pp.73-82
• /
• 2017

Purpose: To assess the chronological changes of disease-related kyphosis after chemotherapy alone. Materials and Methods: A total of 101 children aged 2 to 15 years with spinal tuberculosis, accompanied by various stages of disease processes were enrolled for analysis. By utilizing the images in them, the growth plate condition and chronological changes of kyphosis after chemotherapy were analyzed at two points in time; the first assessment was at post-chemotherapy one-year and second at the final discharge. Results: Complete disc destruction in the cervical, dorsal and lumbosacral spines was observed in 2 out of 40 children (5.0%), 8 out of 30 children (26.7%), and 6 out of 31 children (19.4%), respectively. In those cases, the residual kyphosis inevitably developed. In the remaining children, the discs were intact or partially damaged. Among the 101 children kyphotic deformity was maintained without change in 20 children (19.8%). Kyphosis decreased in 14 children (13.9%), while it increased in 67 children (66.3%) with non-recoverably damaged growth plate. Conclusion: Although it is tentatively possible to predict the deformity progress or non-progress and spontaneous correction at the time of the initial treatment, its predictive accuracy is low. Therefore, assessment of the chronological changes should be performed at the end of chemotherapy. In children with progressive curve change, assessment of deformity should be continued until maturity.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.5B
• /
• pp.409-417
• /
• 2009

In this study it was assessed the accuracy of the Chukwooki rainfall data in Seoul by comparing with tree-ring width index data, sunspot numbers, southern oscillation index (SOI) and global temperature anomaly. And it was investigated the correlations of climatic change and change characteristics in past north-east asia by comparisons of tree-ring width index data in near Korea. The results of this study shows that Chukwooki rainfall data has the strong reliance since the trends and depths of change are very well matched with other comparative data. And with the results by compared with tree-ring width index data in six sites of near Korea, climates of north-east asia are changed with strong correlations as being temporal and spatial and longterm periodic possibility of reproducing are exist on those changes. However characteristics of climate change post 1960 A.D. are investigated as represented differently to past although statistical moving characteristics or changing criterion are within the limitations of reproducing phase in the past since they represent the different trends and irregularity and their frequencies are increase. The results of this study are widely used on long-term forecasting for climate change in north-east asia.

• Journal of Korea Water Resources Association
• /
• v.56 no.7
• /
• pp.439-449
• /
• 2023

Recent advancements in data measuring technology have facilitated the installation of various sensors, such as pressure meters and flow meters, to effectively assess the real-time conditions of water distribution systems (WDSs). However, as cities expand extensively, the factors that impact the reliability of measurements have become increasingly diverse. In particular, demand data, one of the most significant hydraulic variable in WDS, is challenging to be measured directly and is prone to missing values, making the development of accurate data generation models more important. Therefore, this paper proposes an adversarially trained autoencoder (ATAE) model based on generative deep learning techniques to accurately estimate demand data in WDSs. The proposed model utilizes two neural networks: a generative network and a discriminative network. The generative network generates demand data using the information provided from the measured pressure data, while the discriminative network evaluates the generated demand outputs and provides feedback to the generator to learn the distinctive features of the data. To validate its performance, the ATAE model is applied to a real distribution system in Austin, Texas, USA. The study analyzes the impact of data uncertainty by calculating the accuracy of ATAE's prediction results for varying levels of uncertainty in the demand and the pressure time series data. Additionally, the model's performance is evaluated by comparing the results for different data collection periods (low, average, and high demand hours) to assess its ability to generate demand data based on water consumption levels.

• Convergence Security Journal
• /
• v.22 no.4
• /
• pp.85-97
• /
• 2022

With the development of big data technology, data is rapidly entering a hyperconnected intelligent society that accelerates innovative growth in all industries. The convergence industry, which holds and utilizes various high-quality data, is becoming a new growth engine, and big data is fused to various traditional industries. In particular, in the medical field, structured data such as electronic medical record data and unstructured medical data such as CT and MRI are used together to increase the accuracy of disease prediction and diagnosis. Currently, the importance and size of unstructured data are increasing day by day in the medical industry, but conventional data security technologies and policies are structured data-oriented, and considerations for the security and utilization of unstructured data are insufficient. In order for medical treatment using big data to be activated in the future, data diversity and security must be internalized and organically linked at the stage of data construction, distribution, and utilization. In this paper, the current status of domestic and foreign data security systems and technologies is analyzed. After that, it is proposed to add unstructured data-centered de-identification technology to the guidelines for unstructured data and technology application cases in the industry so that unstructured data can be actively used in the medical field, and to establish standards for judging personal information for unstructured data. Furthermore, an object feature-based identification ID that can be used for unstructured data without infringing on personal information is proposed.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1679-1692
• /
• 2023

South Korea is a country that emits a large amount of pollutants as a result of population growth and industrial development and is also severely affected by transboundary air pollution due to its geographical location. As pollutants from both domestic and foreign sources contribute to air pollution in Korea, the location of air pollutant emission sources is crucial for understanding the movement and distribution of pollutants in the atmosphere and establishing national-level air pollution management and response strategies. Based on this background, this study aims to effectively acquire spatial information on domestic and international air pollutant emission sources, which is essential for analyzing air pollution status, by utilizing high-resolution optical satellite images and deep learning-based image segmentation models. In particular, industrial parks and quarries, which have been evaluated as contributing significantly to transboundary air pollution, were selected as the main research subjects, and images of these areas from multi-purpose satellites 3 and 3A were collected, preprocessed, and converted into input and label data for model training. As a result of training the U-Net model using this data, the overall accuracy of 0.8484 and mean Intersection over Union (mIoU) of 0.6490 were achieved, and the predicted maps showed significant results in extracting object boundaries more accurately than the label data created by course annotations.

• Journal of Korea Water Resources Association
• /
• v.56 no.10
• /
• pp.641-653
• /
• 2023

As climate change and urbanization are causing unprecedented natural disasters in urban areas, it is crucial to have urban flood predictions with high fidelity and accuracy. However, conventional physically- and deep learning-based urban flood modeling methods have limitations that require a lot of computer resources or data for high-resolution flooding analysis. In this study, we propose and implement a method for improving the spatial resolution of urban flood analysis using a deep learning based super-resolution technique. The proposed approach converts low-resolution flood maps by physically based modeling into the high-resolution using a super-resolution deep learning model trained by high-resolution modeling data. When applied to two cases of retrospective flood analysis at part of City of Portland, Oregon, U.S., the results of the 4-m resolution physical simulation were successfully converted into 1-m resolution flood maps through super-resolution. High structural similarity between the super-solution image and the high-resolution original was found. The results show promising image quality loss within an acceptable limit of 22.80 dB (PSNR) and 0.73 (SSIM). The proposed super-resolution method can provide efficient model training with a limited number of flood scenarios, significantly reducing data acquisition efforts and computational costs.