• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.1125-1132
• /
• 2017

In a situation where the severity and frequency of drought events getting stronger and higher, many studies related to drought forecast have been conducted to improve the drought forecast accuracy. However it is difficult to predict drought events using a single model because of nonlinear and complicated characteristics of temporal behavior of drought events. In this study, in order to overcome the shortcomings of the single model approach, we first build various single models capable to explain the relationship between the meteorological drought index, Standardized Precipitation Index (SPI), and other independent variables such as world climate indices. Then, we developed a combined models using Stochastic Gradient Descent method among Ensemble Learnings.

• Korean Journal of Remote Sensing
• /
• v.33 no.4
• /
• pp.423-436
• /
• 2017

This paper presents a deep learning-based road segmentation framework from very high-resolution orthophotos. The proposed method uses Deep Convolutional Autoencoders for end-to-end mapping of orthophotos to road segmentations. In addition, a set of post-processing steps were applied to make the model outputs GIS-ready data that could be useful for various applications. The optimization of the model's parameters is explained which was conducted via grid search method. The model was trained and implemented in Keras, a high-level deep learning framework run on top of Tensorflow. The results show that the proposed model with the best-obtained hyperparameters could segment road objects from orthophotos at an average accuracy of 88.5%. The results of optimization revealed that the best optimization algorithm and activation function for the studied task are Stochastic Gradient Descent (SGD) and Exponential Linear Unit (ELU), respectively. In addition, the best numbers of convolutional filters were found to be 8 for the first and second layers and 128 for the third and fourth layers of the proposed network architecture. Moreover, the analysis on the time complexity of the model showed that the model could be trained in 4 hours and 50 minutes on 1024 high-resolution images of size $106{\times}106pixels$, and segment road objects from similar size and resolution images in around 14 minutes. The results show that the deep learning models such as Convolutional Autoencoders could be a best alternative to traditional machine learning models for road segmentation from aerial photographs.

• Ocean and Polar Research
• /
• v.40 no.2
• /
• pp.77-85
• /
• 2018

We observed the concentrations of Dissolved Organic Carbon (DOC) and Colored Dissolved Organic Matter (CDOM) in coastal seawater and groundwater around a volcanic island, Jeju, Korea. The sampling of surface seawater and coastal groundwater was conducted in Woljeongri, Pyoseon, and Kwakgi beaches, in three sampling campaigns (June, July, and October 2016). The concentrations of DOC in groundwater were relatively higher in June and October than in July. Salinity and DOC concentrations in the coastal groundwater of Woljeongri and Pyoseon beaches did not show a marked relationship, whereas those in Kwakgi beach showed a good positive correlation (July: $R^2=0.64$, P < 0.01; October: $R^2=0.95$, P < 0.01). In addition, the concentrations of CDOM (C and M peaks) in the groundwater of Woljeongri and Pyoseon beaches, where saline groundwater discharge dominates, were relatively higher than those of Kwakgi beach, where fresh groundwater discharge dominates. The relatively higher DOC concentrations in the coastal groundwater of Woljeongri and Pyoseon, with higher CDOM concentrations, seem to be mainly from anthropogenic sources such as local pollution sources (i.e., aquaculture wastewater or domestic sewage). In order to understand the behavior of DOC in the coastal groundwater of a volcanic island, extensive studies are necessary in the future over a larger-area and greater time-scales using various isotopic tracers.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.108-117
• /
• 2024

The selection and recommendation of a suitable job applicant from the pool of thousands of applications are often daunting jobs for an employer. The recommendation and selection process significantly increases the workload of the concerned department of an employer. Thus, Resume Classification System using the Natural Language Processing (NLP) and Machine Learning (ML) techniques could automate this tedious process and ease the job of an employer. Moreover, the automation of this process can significantly expedite and transparent the applicants' selection process with mere human involvement. Nevertheless, various Machine Learning approaches have been proposed to develop Resume Classification Systems. However, this study presents an automated NLP and ML-based system that classifies the Resumes according to job categories with performance guarantees. This study employs various ML algorithms and NLP techniques to measure the accuracy of Resume Classification Systems and proposes a solution with better accuracy and reliability in different settings. To demonstrate the significance of NLP & ML techniques for processing & classification of Resumes, the extracted features were tested on nine machine learning models Support Vector Machine - SVM (Linear, SGD, SVC & NuSVC), Naïve Bayes (Bernoulli, Multinomial & Gaussian), K-Nearest Neighbor (KNN) and Logistic Regression (LR). The Term-Frequency Inverse Document (TF-IDF) feature representation scheme proven suitable for Resume Classification Task. The developed models were evaluated using F-Score_M, Recall_M, Precission_M, and overall Accuracy. The experimental results indicate that using the One-Vs-Rest-Classification strategy for this multi-class Resume Classification task, the SVM class of Machine Learning algorithms performed better on the study dataset with over 96% overall accuracy. The promising results suggest that NLP & ML techniques employed in this study could be used for the Resume Classification task.

• International Journal of Computer Science & Network Security
• /
• v.24 no.10
• /
• pp.1-16
• /
• 2024

Due to its complexity and high diagnosis and treatment costs, heart attack (HA) is the top cause of death globally. Heart failure's widespread effect and high morbidity and death rates make accurate and fast prognosis and diagnosis crucial. Due to the complexity of medical data, early and accurate prediction of HA is difficult. Healthcare providers must evaluate data quickly and accurately to intervene. This novel hybrid approach predicts HA using Long Short-Term Memory (LSTM) networks, Deep belief networks (DBNs) with attention mechanism, and robust data mining to fill this essential gap. HA is predicted using Kaggle, PhysioNet, and UCI datasets. Wearable sensor data, ECG signals, and demographic and clinical data provide a solid analytical base. To maintain consistency, ECG signals are normalized and segmented after thorough cleaning to remove missing values and noise. Feature extraction employs complex approaches like Principal Component Analysis (PCA) and Autoencoders to pick time-domain (MNN, SDNN, RMSSD, PNN50) and frequency-domain (PSD at VLF, LF, HF bands) characteristics. The hybrid model architecture uses LSTM networks for sequence learning and DBNs for feature representation and selection to create a robust and comprehensive prediction model. Accuracy, precision, recall, F1-score, and ROC-AUC are measured after cross-entropy loss and SGD optimization. The LSTM-DBN model outperforms predictive methods in accuracy, sensitivity, and specificity. The findings show that several data sources and powerful algorithms can improve heart attack predictions. The proposed architecture performed well on many datasets, with an accuracy rate of 96.00%, sensitivity of 98%, AUC of 0.98, and F1-score of 0.97. High performance proves this system's dependability. Moreover, the proposed approach is outperformed compared to state-of-the-art systems.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.17 no.4
• /
• pp.306-317
• /
• 2014

This study has been executed to understand the additional and removal processes of nutrients in the Saemangeum Salt-water Lake, and discussed with other monthly-collected environmental parameters such as water temperature, salinity, dissolved oxygen, suspended solids, and Chl-a from 2008 to 2010. $NO_3$-N, TP, $PO_4$-P, and DISi showed the removal processes along with the salinity gradients at the surface water of the lake, whereas $NO_2$-N, $NH_4$-N, and Chl-a showed addition trend. In the bottom water all water quality parameters except $NO_3$-N appeared addition processes indicating evidence of continuous nutrients suppliance into the bottom layer. The mixing modelling approach revealed that the biogeochemical processes in the lake consume $NO_3$-N and consequently added $NH_4$-N and $PO_4$-P to the bottom water during the summer seasons. The $NH_4$-N and $PO_4$-P appeared strong increase at the bottom water of the river-side of the lake and strong concentration gradient difference of dissolved oxygen also appeared in the same time. DISi exhibited continuous seasonal supply from spring to summer. Internal addition of $NH_4$-N and $PO_4$-P in the river-side of the lake were much higher than the dike-side, while the increase of DISi showed similar level both the dike and river sides. The temporal distribution of benthic flux for DISi indicates that addition of nutrients in the bottom water was strongly affected by other sources, for example, submarine ground-water discharge (SGD) through bottom sediment.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.66 no.2
• /
• pp.105-111
• /
• 2021

Rice lodging is an annual occurrence caused by typhoons accompanied by strong winds and strong rainfall, resulting in damage relating to pre-harvest sprouting during the ripening period. Thus, rapid estimations of the area of lodged rice are necessary to enable timely responses to damage. To this end, we obtained images related to rice lodging using a drone in Gimje, Buan, and Gunsan, which were converted to 128 × 128 pixels images. A convolutional neural network (CNN) model, a deep learning model based on these images, was used to predict rice lodging, which was classified into two types (lodging and non-lodging), and the images were divided in a 8:2 ratio into a training set and a validation set. The CNN model was layered and trained using three optimizers (Adam, Rmsprop, and SGD). The area of rice lodging was evaluated for the three fields using the obtained data, with the exception of the training set and validation set. The images were combined to give composites images of the entire fields using Metashape, and these images were divided into 128 × 128 pixels. Lodging in the divided images was predicted using the trained CNN model, and the extent of lodging was calculated by multiplying the ratio of the total number of field images by the number of lodging images by the area of the entire field. The results for the training and validation sets showed that accuracy increased with a progression in learning and eventually reached a level greater than 0.919. The results obtained for each of the three fields showed high accuracy with respect to all optimizers, among which, Adam showed the highest accuracy (normalized root mean square error: 2.73%). On the basis of the findings of this study, it is anticipated that the area of lodged rice can be rapidly predicted using deep learning.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.2 no.2
• /
• pp.138-150
• /
• 1997

The late Quaternary stratigraphy of the tidal deposits in the Hampyung Bay, southwestern coast of Korea comprises 1) Unit III (nonmarine fluvial coarse-grained sediments), 2) Unit II (late Pleistocene tidal deposits), and 3) Unit I (late Holocene fine-grained tidal deposits) in ascending order. The basements of the Hampyung Bay is composed of granitic rocks and basic dyke rocks. These three units are of unconformally bounded sedimentary sequences. The sequence boundary between Unit I and Unit II, in particular, seems to be significant suggesting erosional surface and exposed to the air under the cold climate during the LGM. The uppermost stratigraphic sequence (Unit I) is a common tidal deposit formed under the transgression to highstand sea-level during the middle to late Holocene.

• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.25-34
• /
• 2022

Brain computed tomography (CT) is useful for brain lesion diagnosis, such as brain hemorrhage, due to non-invasive methodology, 3-dimensional image provision, low radiation dose. However, there has been numerous misdiagnosis owing to a lack of radiologist and heavy workload. Recently, object detection technologies based on artificial intelligence have been developed in order to overcome the limitations of traditional diagnosis. In this study, the applicability of a deep learning-based YOLOv5s model was evaluated for brain hemorrhage detection using brain CT images. Also, the effect of hyperparameters in the trained YOLOv5s model was analyzed. The YOLOv5s model consisted of backbone, neck and output modules. The trained model was able to detect a region of brain hemorrhage and provide the information of the region. The YOLOv5s model was trained with various activation functions, optimizer functions, loss functions and epochs, and the performance of the trained model was evaluated in terms of brain hemorrhage detection accuracy and training time. The results showed that the trained YOLOv5s model is able to provide a bounding box for a region of brain hemorrhage and the accuracy of the corresponding box. The performance of the YOLOv5s model was improved by using the mish activation function, the stochastic gradient descent (SGD) optimizer function and the completed intersection over union (CIoU) loss function. Also, the accuracy and training time of the YOLOv5s model increased with the number of epochs. Therefore, the YOLOv5s model is suitable for brain hemorrhage detection using brain CT images, and the performance of the model can be maximized by using appropriate hyperparameters.

• 한국노년학
• /
• v.41 no.1
• /
• pp.107-125
• /
• 2021

The purpose of this study is to verify the effects of gender and exercise participation types on depression and cognitive function in the elderly. The data of 10,059 elderly individuals who participated in survey on the welfare and living conditions of elderly individuals in 2017 were utilized for this study. The SGDS and the MMES-DS were used to measure their level of depression and level of cognitive function. The data were analyzed using the frequency analysis, the reliability analysis, and the two-way ANOVA. The results are as follows: first, the main effects of gender and exercise participation on depression are statistically significant. However, the interaction effect between gender and exercise participation is not significant. Second, the main effect of gender on depression is statistically significant. However, the main effect of exercise frequency on depression and interaction effect between gender and exercise frequency are not significant. Third, the main effects of gender and exercise hours on depression are statistically significant. However, the interaction effect between gender and exercise hours is not significant. Fourth, the main effects of gender and exercise participation on cognitive function are statistically significant. Additionally, the interaction effect between gender and exercise participation is significant. Fifth, the main effects of gender and exercise frequency on cognitive function are statistically significant. However, the interaction effect between gender and exercise frequency is not significant. Lastly, the main effects of gender and exercise hours on cognitive function are statistically significant. Moreover, the interaction effect between gender and exercise hours is significant. In conclusion, participating in exercise has shown to be beneficial for decreasing the level of depression and increasing level of cognitive function in elderly of both genders. An additional discovery made through this research is that women's level of cognitive function improves larger than men's when they participate in exercise.