• Journal of the Korea Society for Simulation
• /
• v.30 no.1
• /
• pp.75-85
• /
• 2021

In this paper, we present a deep neural network-based prediction model that processes and analyzes the corporate credit and personal credit information of individual business owners as a new method to predict the default rate of individual business more accurately. In modeling research in various fields, feature selection techniques have been actively studied as a method for improving performance, especially in predictive models including many features. In this paper, after statistical verification of macroeconomic indicators (macro variables) and credit information (micro variables), which are input variables used in the default rate prediction model, additionally, through the credit information feature selection method, the final feature set that improves prediction performance was identified. The proposed credit information feature selection method as an iterative & hybrid method that combines the filter-based and wrapper-based method builds submodels, constructs subsets by extracting important variables of the maximum performance submodels, and determines the final feature set through prediction performance analysis of the subset and the subset combined set.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.193-202
• /
• 2022

The classification of hyperspectral imagery (HSI) is essential in the surface of earth observation. Due to the continuous large number of bands, HSI data provide rich information about the object of study; however, it suffers from the curse of dimensionality. Dimensionality reduction is an essential aspect of Machine learning classification. The algorithms based on feature extraction can overcome the data dimensionality issue, thereby allowing the classifiers to utilize comprehensive models to reduce computational costs. This paper assesses and compares two HSI classification techniques. The first is based on the Joint Spatial-Spectral Stacked Autoencoder (JSSSA) method, the second is based on a shallow Artificial Neural Network (SNN), and the third is used the SVM model. The performance of the JSSSA technique is better than the SNN classification technique based on the overall accuracy and Kappa coefficient values. We observed that the JSSSA based method surpasses the SNN technique with an overall accuracy of 96.13% and Kappa coefficient value of 0.95. SNN also achieved a good accuracy of 92.40% and a Kappa coefficient value of 0.90, and SVM achieved an accuracy of 82.87%. The current study suggests that both JSSSA and SNN based techniques prove to be efficient methods for hyperspectral classification of snow features. This work classified the labeled/ground-truth datasets of snow in multiple classes. The labeled/ground-truth data can be valuable for applying deep neural networks such as CNN, hybrid CNN, RNN for glaciology, and snow-related hazard applications.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1603-1611
• /
• 2021

As IMO environmental regulations are tightened, the need to establish a system that can reduce emissions is increasing, and for this purpose, various power control management systems have been studied and implemented as a new energy management system for ships. In this study, we design a control process through modeling for Bi-Directional Converter (BDC) application with bi-directional power flow to link batteries, which are energy storage devices, to conventional generator power systems, and propose mechanisms for batteries optimized for varying loads. This work models MATLAB/Simulink as a BDC and simulates current control and state of charge (SOC) optimization at the time of charging and discharging batteries according to load scenarios. Through this, the battery, power, and load were interlocked so that the generator operated on board could be operated in the optimal operation range, and power control management was performed to enable the generator to operate in the high fuel efficiency range.

• Journal of Korean Association for Spatial Structures
• /
• v.22 no.3
• /
• pp.25-32
• /
• 2022

In this paper, the instability of the domed spatial truss structure using wood and the characteristics of the buckling critical load were studied. Hexagonal space truss was adopted as the model to be analyzed, and two boundary conditions were considered. In the first case, the deformation of the inclined member is only considered, and in the second case, the deformation of the horizontal member is also considered. The materials of the model adopted in this paper are steel and timbers, and the considered timbers are spruce, pine, and larch. Here, the inelastic properties of the material are not considered. The instability of the target structure was observed through non-linear incremental analysis, and the buckling critical load was calculated through the singularities and eigenvalues of the tangential stiffness matrix at each incremental step. From the analysis results, in the example of the boundary condition considering only the inclined member, the critical buckling load was lower when using timber than when using steel, and the critical buckling load was determined according to the modulus of elasticity of timber. In the case of boundary conditions considering the effect of the horizontal member, using a mixture of steel and timber case had a lower buckling critical load than the steel case. But, the result showed that it was more effective in structural stability than only timber was used.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.3991-4010
• /
• 2021

The Question Similarity Measurement of Chinese Crop Diseases and Insect Pests (QSM-CCD&IP) aims to judge the user's tendency to ask questions regarding input problems. The measurement is the basis of the Agricultural Knowledge Question and Answering (Q & A) system, information retrieval, and other tasks. However, the corpus and measurement methods available in this field have some deficiencies. In addition, error propagation may occur when the word boundary features and local context information are ignored when the general method embeds sentences. Hence, these factors make the task challenging. To solve the above problems and tackle the Question Similarity Measurement task in this work, a corpus on Chinese crop diseases and insect pests(CCDIP), which contains 13 categories, was established. Then, taking the CCDIP as the research object, this study proposes a Chinese agricultural text similarity matching model, namely, the AgrCQS. This model is based on mixed information extraction. Specifically, the hybrid embedding layer can enrich character information and improve the recognition ability of the model on the word boundary. The multi-scale local information can be extracted by multi-core convolutional neural network based on multi-weight (MM-CNN). The self-attention mechanism can enhance the fusion ability of the model on global information. In this research, the performance of the AgrCQS on the CCDIP is verified, and three benchmark datasets, namely, AFQMC, LCQMC, and BQ, are used. The accuracy rates are 93.92%, 74.42%, 86.35%, and 83.05%, respectively, which are higher than that of baseline systems without using any external knowledge. Additionally, the proposed method module can be extracted separately and applied to other models, thus providing reference for related research.

• Journal of Korean Academy of Nursing
• /
• v.52 no.1
• /
• pp.52-65
• /
• 2022

Purpose: This study was conducted to develop a scale to measure spiritual distress in cancer patients. Methods: A total of 69 preliminary items for the spiritaul distress assessment tool (SDAT) were compiled, based on a literature review, selection of empirically relevant items through concept analysis of hybrid models, confirmation of content validity by experts, cognitive interviews, and a pretest. Self-administered questionnaires were collected between April 1 and July 31, 2018, from 225 cancer patients at four medical institutions and one nursing home. The data were analyzed using item analysis, exploratory factor analysis, convergent and discriminant validity, and Pearson correlation for criterion validity. Reliability was tested by Cronbash's α coefficient. Results: The final version of the SDAT consisted of 20 items. Five-factors, loss of peace, burden of family, avoidance of confronting death, guilt and remorse, regret for not being able to apololgize and forgive were extracted, and showed 62.8% of total variance. The factors were confirmed through convergent and discriminant validity. Criterion validity was confirmed by functional assessment chronic illness therapy spiritual well-being scale 12 (FACIT-Sp12). The overall Cronbach's α was .91, and the coefficients of each subscale ranged from .78~.83. Conclusion: The SDAT for cancer patients is valid and reliable. It is suggested that the tool can be used to measure spiritual distress in cancer patients.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1477-1485
• /
• 2021

Recently, super-resolution has been intensively studied only on upscaling models with integer magnification. However, the need to expand arbitrary magnification is emerging in representative application fields of actual super-resolution, such as object recognition and display image quality improvement. In this paper, we propose a model that can support arbitrary magnification by using the weights of the existing integer magnification model. This model converts super-resolution results into the DCT spectral domain to expand the space for arbitrary magnification. To reduce the loss of high-frequency information in the image caused by the expansion by the DCT spectral domain, we propose a high-frequency attention network for arbitrary magnification so that this model can properly restore high-frequency spectral information. To recover high-frequency information properly, the proposed network utilizes channel attention layers. This layer can learn correlations between RGB channels, and it can deepen the model through residual structures.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.96-96
• /
• 2023

지구온난화는 집중호우 및 태풍의 빈도와 규모를 증가시키는 원인이 되었으며, 전 세계적으로 홍수로 인한 피해가 발생하고 있다. 한국에서는 2020년 홍수로 인하여 1조 이상의 피해가 발생하였으며, 2021년에는 호우로 인한 피해가 60%이상을 차지하였다. 과거에는 구조적인 대책을 수립하기 위하여 경제성 높은 치수사업을 결정하는 연구들이 수행되었다. 하지만 치수 사업은 지구온난화를 가속시키게 되며 그로 인해 집중호우의 빈도와 규모가 증가하는 악순환이 발생하게 된다. 따라서 최근에는 비구조적 대책인 홍수 예경보를 수행하여 홍수에 대응하고자 홍수 예경보 지점을 확대하고 있다. 홍수 예경보는 강우-유출 모형을 이용하여 유출량을 산정하고, 일정 수위를 초과하면 홍수 경보가 발령된다. 하지만 강우-유출 모형의 경우 많은 매개변수 값을 요구하며, 강우 사상에 따라 다른 매개변수를 산정하는데 많은 시간을 필요로 한다. 따라서 특정 강우 사상에 따라 매개변수 값을 고정하여 유출량을 산정하고 있으나, 이는 실제 유출량과 예측 유출량과의 오차가 발생할 수 있다. 따라서 본 연구에서는 강우-유출 모형의 오차를 AI로 예측하여 유출량을 보정하는 연구를 수행하고자 하였다. 강우-유출 모형에서는 유출량을 산정하고 그에 따른 오차를 생성하게 된다. 그리고 산정된 오차들을 이용하여 오차를 예측할 수 있는 AI 모형을 개발하게 된다. 최종적으로 강우-유출 모형의 유출량과 AI 모형의 오차가 결합되어 보정된 유출량을 산정하게 된다. 강우-유출 모형과 AI 모형이 결합된 Hybrid model은 기존의 단일로 사용했을 때의 발생할 수 있는 강우-유출 모형의 문제를 개선할 수 있을 것으로 판단된다.

• Mycobiology
• /
• v.50 no.4
• /
• pp.254-257
• /
• 2022

Wolfiporia cocos is a wood-decay brown rot fungus belonging to the family Polyporaceae. While the fungus grows, the sclerotium body of the strain, dubbed Bokryeong in Korean, is formed around the roots of conifer trees. The dried sclerotium has been widely used as a key component of many medicinal recipes in East Asia. Wolfiporia cocos strain KMCC03342 is the reference strain registered and maintained by the Korea Seed and Variety Service for commercial uses. Here, we present the first draft genome sequence of W. cocos KMCC03342 using a hybrid assembly technique combining both short- and long-read sequences. The genome has a total length of 55.5 Mb comprised of 343 contigs with N50 of 332 kb and 95.8% BUSCO completeness. The GC ratio was 52.2%. We predicted 14,296 protein-coding gene models based on ab initio gene prediction and evidence-based annotation procedure using RNAseq data. The annotated genome was predicted to have 19 terpene biosynthesis gene clusters, which was the same number as the previously sequenced W. cocos strain MD-104 genome but higher than Chinese W. cocos strains. The genome sequence and the predicted gene clusters allow us to study biosynthetic pathways for the active ingredients of W. cocos.