• The Journal of the Acoustical Society of Korea
• /
• v.43 no.1
• /
• pp.9-18
• /
• 2024

The importance of active sonar systems is emerging due to the quietness of underwater targets and the increase in ambient noise due to the increase in maritime traffic. However, the low signal-to-noise ratio of the echo signal due to multipath propagation of the signal, various clutter, ambient noise and reverberation makes it difficult to identify underwater targets using active sonar. Attempts have been made to apply data-based methods such as machine learning or deep learning to improve the performance of underwater target recognition systems, but it is difficult to collect enough data for training due to the nature of sonar datasets. Methods based on mathematical modeling have been mainly used to compensate for insufficient active sonar data. However, methodologies based on mathematical modeling have limitations in accurately simulating complex underwater phenomena. Therefore, in this paper, we propose a sonar signal synthesis method based on a deep neural network. In order to apply the neural network model to the field of sonar signal synthesis, the proposed method appropriately corrects the attention-based encoder and decoder to the sonar signal, which is the main module of the Tacotron model mainly used in the field of speech synthesis. It is possible to synthesize a signal more similar to the actual signal by training the proposed model using the dataset collected by arranging a simulated target in an actual marine environment. In order to verify the performance of the proposed method, Perceptual evaluation of audio quality test was conducted and within score difference -2.3 was shown compared to actual signal in a total of four different environments. These results prove that the active sonar signal generated by the proposed method approximates the actual signal.

• Trans-
• /
• v.16
• /
• pp.1-31
• /
• 2024

The advent of digital media has facilitated easy access for adolescents to environments conducive to the purchase of narcotics. In particular, there's an increasing trend in the purchase and consumption of narcotics mediated through Social Network Services (SNS) and messenger services. Adolescents, sensitive to such environments, are at risk of experiencing neurological and mental health issues due to narcotic addiction, increasing their exposure to criminal activities, hence necessitating national-level management and support. Consequently, the quest for sustainable treatment methods for adolescents exposed to narcotics emerges as a critical challenge. In the context of high relapse rates in narcotic addiction, the necessity for cost-effective and user-friendly treatment programs is emphasized. This study conducts a literature review aimed at utilizing digital platforms to create an environment where adolescents can voluntarily participate, focusing on the development of therapeutic content through art. Specifically, it reviews societal perceptions and treatment statuses of adolescent drug addiction, analyzes the impact of narcotic addiction on adolescent brain activity and cognitive function degradation, and explores approaches for developing digital therapeutics to promote the rehabilitation of the addicted brain through analysis of precedential case studies. Moreover, the study investigates the benefits that the integration of digital therapeutic approaches and art therapy can provide in the treatment process and proposes the possibility of enhancing therapeutic effects through various treatment programs such as drama therapy, music therapy, and art therapy. The application of art therapy methods is anticipated to offer positive effects in terms of tool expansion, diversification of expression, data acquisition, and motivation. Through such approaches, an enhancement in the effectiveness of treatments for adolescent narcotic addiction is anticipated. Overall, this study undertakes foundational research for the development of digital therapeutics and related applications, offering economically viable and sustainable treatment options in consideration of the societal context of adolescent narcotic addiction.

• Journal of Korea Water Resources Association
• /
• v.57 no.3
• /
• pp.151-164
• /
• 2024

In water treatment plants supplying potable water, the management of chlorine concentration in water treatment processes involving pre-chlorination or intermediate chlorination requires process control. To address this, research has been conducted on water quality prediction techniques utilizing AI technology. This study developed an AI-based predictive model for automating the process control of chlorine disinfection, targeting the prediction of residual chlorine concentration downstream of sedimentation basins in water treatment processes. The AI-based model, which learns from past water quality observation data to predict future water quality, offers a simpler and more efficient approach compared to complex physicochemical and biological water quality models. The model was tested by predicting the residual chlorine concentration downstream of the sedimentation basins at Plant, using multiple regression models and AI-based models like Random Forest and LSTM, and the results were compared. For optimal prediction of residual chlorine concentration, the input-output structure of the AI model included the residual chlorine concentration upstream of the sedimentation basin, turbidity, pH, water temperature, electrical conductivity, inflow of raw water, alkalinity, NH₃, etc. as independent variables, and the desired residual chlorine concentration of the effluent from the sedimentation basin as the dependent variable. The independent variables were selected from observable data at the water treatment plant, which are influential on the residual chlorine concentration downstream of the sedimentation basin. The analysis showed that, for Plant, the model based on Random Forest had the lowest error compared to multiple regression models, neural network models, model trees, and other Random Forest models. The optimal predicted residual chlorine concentration downstream of the sedimentation basin presented in this study is expected to enable real-time control of chlorine dosing in previous treatment stages, thereby enhancing water treatment efficiency and reducing chemical costs.

• Journal of the Korean Society of Radiology
• /
• v.84 no.5
• /
• pp.1066-1079
• /
• 2023

Purpose Distinguishing intradural extramedullary (IDEM) spinal ependymoma from myxopapillary ependymoma is challenging due to the location of IDEM spinal ependymoma. This study aimed to investigate the utility of clinical and MR imaging features for differentiating between IDEM spinal and myxopapillary ependymomas. Materials and Methods We compared tumor size, longitudinal/axial location, enhancement degree/pattern, tumor margin, signal intensity (SI) of the tumor on T2-weighted images and T1-weighted image (T1WI), increased cerebrospinal fluid (CSF) SI caudal to the tumor on T1WI, and CSF dissemination of pathologically confirmed 12 IDEM spinal and 10 myxopapillary ependymomas. Furthermore, classification and regression tree (CART) was performed to identify the clinical and MR features for differentiating between IDEM spinal and myxopapillary ependymomas. Results Patients with IDEM spinal ependymomas were older than those with myxopapillary ependymomas (48 years vs. 29.5 years, p < 0.05). A high SI of the tumor on T1W1 was more frequently observed in IDEM spinal ependymomas than in myxopapillary ependymomas (p = 0.02). Conversely, myxopapillary ependymomas show CSF dissemination. Increased CSF SI caudal to the tumor on T1WI was observed more frequently in myxopapillary ependymomas than in IDEM spinal ependymomas (p < 0.05). Dissemination to the CSF space and increased CSF SI caudal to the tumor on T1WI were the most important variables in CART analysis. Conclusion Clinical and radiological variables may help differentiate between IDEM spinal and myxopapillary ependymomas.

• Journal of Wetlands Research
• /
• v.26 no.2
• /
• pp.147-159
• /
• 2024

Lack of streamflow observations makes model calibration difficult and limits model performance improvement. Satellite-based remote sensing products offer a new alternative as they can be actively utilized to obtain hydrological data. Recently, several studies have shown that artificial intelligence-based solutions are more appropriate than traditional conceptual and physical models. In this study, a data-driven approach combining various recurrent neural networks and decision tree-based algorithms is proposed, and the utilization of satellite remote sensing information for AI training is investigated. The satellite imagery used in this study is from MODIS and SMAP. The proposed approach is validated using publicly available data from 25 watersheds. Inspired by the traditional regionalization approach, a strategy is adopted to learn one data-driven model by integrating data from all basins, and the potential of the proposed approach is evaluated by using a leave-one-out cross-validation regionalization setting to predict streamflow from different basins with one model. The GRU + Light GBM model was found to be a suitable model combination for target basins and showed good streamflow prediction performance in ungauged basins (The average model efficiency coefficient for predicting daily streamflow in 25 ungauged basins is 0.7187) except for the period when streamflow is very small. The influence of satellite remote sensing information was found to be up to 10%, with the additional application of satellite information having a greater impact on streamflow prediction during low or dry seasons than during wet or normal seasons.

• Korean Journal of Heritage: History & Science
• /
• v.57 no.3
• /
• pp.24-35
• /
• 2024

Recently, research using deep learning technologies such as artificial intelligence, convolutional neural networks, etc. has been actively conducted in various fields including healthcare, manufacturing, autonomous driving, and security, and is having a significant influence on society. In line with this trend, the present study attempted to apply deep learning to the classification of archaeological artifacts, specifically ancient Korean roof-end tiles. Using 100 images of roof-end tiles from each of the Goguryeo, Baekje, and Silla dynasties, for a total of 300 base images, a dataset was formed and expanded to 1,200 images using data augmentation techniques. After building a model using transfer learning from the pre-trained EfficientNetB0 model and conducting five-fold cross-validation, an average training accuracy of 98.06% and validation accuracy of 97.08% were achieved. Furthermore, when model performance was evaluated with a test dataset of 240 images, it could classify the roof-end tile images from the three dynasties with a minimum accuracy of 91%. In particular, with a learning rate of 0.0001, the model exhibited the highest performance, with accuracy of 92.92%, precision of 92.96%, recall of 92.92%, and F1 score of 92.93%. This optimal result was obtained by preventing overfitting and underfitting issues using various learning rate settings and finding the optimal hyperparameters. The study's findings confirm the potential for applying deep learning technologies to the classification of Korean archaeological materials, which is significant. Additionally, it was confirmed that the existing ImageNet dataset and parameters could be positively applied to the analysis of archaeological data. This approach could lead to the creation of various models for future archaeological database accumulation, the use of artifacts in museums, and classification and organization of artifacts.

• The Korean Journal of Medicine
• /
• v.99 no.1
• /
• pp.37-49
• /
• 2024

Background/Aims: In Korea, the incidence of primary diffuse large B-cell lymphoma of the central nervous system (PCNSL) is increasing and autologous stem cell transplantation (ASCT) has improved the survival of younger patients. We explored our real-world experience with PCNSL at Asan Medical Center (AMC). Methods: We used the AMC lymphoma registry to collect patient data prospectively. We analyzed 279 patients diagnosed from 2002 until August 2019. Results: The PCNSL incidence at AMC increased progressively and comprised 7.4-8.9% of new non-Hodgkin lymphoma patients annually during the most recent 4 years. The median age was 60 years (range, 17-85) and males comprised 55%. Patients under 65 years of age (n = 183) had no significant differences in characteristics compared to those aged 65 years or over, with the exception of less occipital lobe involvement and lower beta-2 microglobulin levels. Rituximab, methotrexate, procarbazine, and vincristine (R-MPV) combination induction had the best overall response, of 95%. The median overall survival was 3.8 years with 5- and 10-year survival rates of 41.5% and 30.2%, respectively. Survival was better in younger patients and those treated with ASCT. Thiotepa, busulfan, and cytoxan (TBC) conditioning chemotherapy had better survival than other combinations. The International Extranodal Lymphoma Study Group and Memorial Sloan Kettering Cancer Center prognostic score systems were valid in this cohort. Age and performance status were independent prognostic factors. Exclusive extra-central nervous system failure occurred in six patients (5.6%) among 107 failures. Conclusions: The incidence of PCNSL is rising. R-MPV induction therapy followed by ASCT with TBC has improved the survival of young, fit PCNSL patients.

• Journal of The Korean Society of Inherited Metabolic disease
• /
• v.24 no.1
• /
• pp.26-36
• /
• 2024

Lesch-Nyhan syndrome (LNS) is an Clinical symptoms can range from mild to severe depending on residual enzyme activity and genetic mutations. In Korea, 27 cases of LNS have been reported. We report the results of an 11-year comparative follow-up of two cases of children who visited because of pink diapers, one who died from LNS with no residual enzymes and one case with partial residual enzymes. Case 1: During follow-up, seizures, developmental delay, and regression were observed. The boy experienced insomnia and severe constipation. He exhibited self-mutilating behavior, a grand mal seizure, scoliosis with severe spasticity, truncal hypotonia, choreoathetoid movement, and ataxia. After prolonged emaciation, staghorn calculi, and recurrent pneumonia, the patient died suddenly at the age of 11 years. Genetic testing revealed a hemizygous HPRT1 variant (c.151C>T (p.Arg51Ter)). Uric acid level was 10.5 mg/dL (normal range: ~3.5-7.9) and HPRT activity 0.02 nmol/hr/spot (10-23.8 nmol/hr/spot). Case 2: During follow-up, the patient remained underweight. He has normal intelligence attending primary school. Self-mutilation symptoms were not observed. Regular renal ultrasonography did not reveal urolithiasis. The patient had a hemizygous HPRT1 variant (c.35A>C (p.Asp12Ala)). Uric acid level and HPRT activity were 11 mg/dL and 0.56 nmol/hr/spot. Pink diapers after the neonatal period and severe protein aversion, neurological problems, and kidney stones, differentiation for LNS is necessary. When suspected, serum uric acid levels, HPRT enzyme activity, and molecular biological tests may be helpful in predicting the prognosis of LNS.

• Journal of Bio-Environment Control
• /
• v.32 no.4
• /
• pp.434-441
• /
• 2023

Determining the size or area of a plant's leaves is an important factor in predicting plant growth and improving the productivity of indoor farms. In this study, we developed a convolutional neural network (CNN)-based model to accurately predict the length and width of lettuce leaves using photographs of the leaves. A callback function was applied to overcome data limitations and overfitting problems, and K-fold cross-validation was used to improve the generalization ability of the model. In addition, ImageDataGenerator function was used to increase the diversity of training data through data augmentation. To compare model performance, we evaluated pre-trained models such as VGG16, Resnet152, and NASNetMobile. As a result, NASNetMobile showed the highest performance, especially in width prediction, with an R_squared value of 0.9436, and RMSE of 0.5659. In length prediction, the R_squared value was 0.9537, and RMSE of 0.8713. The optimized model adopted the NASNetMobile architecture, the RMSprop optimization tool, the MSE loss functions, and the ELU activation functions. The training time of the model averaged 73 minutes per Epoch, and it took the model an average of 0.29 seconds to process a single lettuce leaf photo. In this study, we developed a CNN-based model to predict the leaf length and leaf width of plants in indoor farms, which is expected to enable rapid and accurate assessment of plant growth status by simply taking images. It is also expected to contribute to increasing the productivity and resource efficiency of farms by taking appropriate agricultural measures such as adjusting nutrient solution in real time.

• Journal of Nutrition and Health
• /
• v.24 no.3
• /
• pp.230-242
• /
• 1991

This research was conducted on the 10 take-out boxed-lunches commercially prepared in the department stores. chain stores. and the public railroad trains in Korea. Sampling was conducted from February 1990 to March 1990. Nutritive values and sodium contents of the 10 boxed-lunch samples are summarized as follows : 1) The average weight(percentage) of the cooked rice and the side dishes were 304.6g(49.4) and 312.4(506%), respectively. The weight of these samples were significantly heavier than that of Japanese style boxed-lunches. 2) The average number of the side dishes was 12. The average numbers of food items classified by the five food groups were 6.1 in protein food group, 0.3 in calcium food group. 6.0 in vitamin and mineral food group. 1.5 in carbohydrate food group, and 1.5 in oil and fat food group. 3) They contained on the average 840.7kcal of energy, 38.9g of protein, 22.7g of fat, 120.4g of carbohydrate. 300.8mg of calcium. 410.8mg of phosphours, 6.61 mg of iron. 219.8 R.E. of vitamin A, 0.46mg of thiamin, 0.67mg of riboflavin, 10.5mg of niacin, 27.5mg of ascorbic acid. Thus. except vitamin t the content of all the nutrients were higher than the value of 1/3 of the RDA for adults. 4) The high priced group(group 2) had more protein, calcuim. iron and niacin contents than the cheaper group(group 1). Probably, it's because the group 2 had more animal foods than the group 1. 5) The average energy content per unit price(100 won) was 37.3kcal and the average protein content per unit price(100 won) was 1.64g. Korena style boxed-lunches had higher energy and protein contents per unit price than Japanese style, and the group 1 higher than the group 2. 6) The average energy Proportions of Protein, carbohydrate. and fat were 18.3%, 57.4%, and 24.3%, respectively. These proportions are good enough. 7) Frequency of cooking methods for the side dishes were found in the decreasing order : pan-frying, frying, braising, seasoning, kimchi, grilling, pickling, stir-frying, steaming and fermenting. Generally simple cooking methods were used, thus the menus were lack or varieties. 8) Frequency of colors for the side dishes were found in the decreasing order : red, brown. yellow, green, black, white. Too much red pepper was used. 9) The average capacity of the containers for the staples and the side dishes were 468.1ml and 590.6ml, respectively. And the containers could not keep the food items well seperated. 10) The average contensts of sodium and salt were 2.287mg and 5.76g, in the range of 1, 398mg to 3, 489mg and 3.53g to 8.80g, respectively. These are much higher values than the recommended amount of salt.