• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.167-183
• /
• 2023

In the recent field of recommendation systems, various studies have been conducted to model sparse data effectively. Among these, GLocal-K(Global and Local Kernels for Recommender Systems) is a research endeavor combining global and local kernels to provide personalized recommendations by considering global data patterns and individual user characteristics. However, due to its utilization of kernel tricks, GLocal-K exhibits diminished performance on highly sparse data and struggles to offer recommendations for new users or items due to the absence of side information. In this paper, to address these limitations of GLocal-K, we propose the GEase-K (Global and EASE kernels for Recommender Systems) model, incorporating the EASE(Embarrassingly Shallow Autoencoders for Sparse Data) model and leveraging side information. Initially, we substitute EASE for the local kernel in GLocal-K to enhance recommendation performance on highly sparse data. EASE, functioning as a simple linear operational structure, is an autoencoder that performs highly on extremely sparse data through regularization and learning item similarity. Additionally, we utilize side information to alleviate the cold-start problem. We enhance the understanding of user-item similarities by employing a conditional autoencoder structure during the training process to incorporate side information. In conclusion, GEase-K demonstrates resilience in highly sparse data and cold-start situations by combining linear and nonlinear structures and utilizing side information. Experimental results show that GEase-K outperforms GLocal-K based on the RMSE and MAE metrics on the highly sparse GoodReads and ModCloth datasets. Furthermore, in cold-start experiments divided into four groups using the GoodReads and ModCloth datasets, GEase-K denotes superior performance compared to GLocal-K.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.207-221
• /
• 2023

This study suggests deep neural network models for estimating air temperature with Level 1B (L1B) datasets of GEO-KOMPSAT-2A (GK-2A). The temperature at 1.5 m above the ground impact not only daily life but also weather warnings such as cold and heat waves. There are many studies to assume the air temperature from the land surface temperature (LST) retrieved from satellites because the air temperature has a strong relationship with the LST. However, an algorithm of the LST, Level 2 output of GK-2A, works only clear sky pixels. To overcome the cloud effects, we apply a deep neural network (DNN) model to assume the air temperature with L1B calibrated for radiometric and geometrics from raw satellite data and compare the model with a linear regression model between LST and air temperature. The root mean square errors (RMSE) of the air temperature for model outputs are used to evaluate the model. The number of 95 in-situ air temperature data was 2,496,634 and the ratio of datasets paired with LST and L1B show 42.1% and 98.4%. The training years are 2020 and 2021 and 2022 is used to validate. The DNN model is designed with an input layer taking 16 channels and four hidden fully connected layers to assume an air temperature. As a result of the model using 16 bands of L1B, the DNN with RMSE 2.22℃ showed great performance than the baseline model with RMSE 3.55℃ on clear sky conditions and the total RMSE including overcast samples was 3.33℃. It is suggested that the DNN is able to overcome cloud effects. However, it showed different characteristics in seasonal and hourly analysis and needed to append solar information as inputs to make a general DNN model because the summer and winter seasons showed a low coefficient of determinations with high standard deviations.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.949-965
• /
• 2023

In this study, we propose a method to monitor the surface area of agricultural reservoirs in South Korea using Sentinel-1 synthetic aperture radar images and the deep learning model, Swin Transformer. Utilizing the Google Earth Engine platform, datasets from 2017 to 2021 were constructed for seven agricultural reservoirs, categorized into 700 K-ton, 900 K-ton, and 1.5 M-ton capacities. For four of the reservoirs, a total of 1,283 images were used for model training through shuffling and 5-fold cross-validation techniques. Upon evaluation, the Swin Transformer Large model, configured with a window size of 12, demonstrated superior semantic segmentation performance, showing an average accuracy of 99.54% and a mean intersection over union (mIoU) of 95.15% for all folds. When the best-performing model was applied to the datasets of the remaining three reservoirsfor validation, it achieved an accuracy of over 99% and mIoU of over 94% for all reservoirs. These results indicate that the Swin Transformer model can effectively monitor the surface area of agricultural reservoirs in South Korea.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.6
• /
• pp.110-121
• /
• 2016

The primary aim of the color constancy algorithm is to estimate illuminant chromaticity. There are various statistical-based, learning-based and combinational-based color constancy algorithms already exist. However, the statistical-based algorithms can only perform well on images that satisfy certain assumptions, learning-based methods are complex methods that require proper preprocessing and training data, and combinational-based methods depend on either pre-determined or dynamically varying weights, which are difficult to determine and prone to error. Therefore, this paper presents a new optimization based illuminant estimation method which is free from complex preprocessing and can estimate the illuminant under different environmental conditions. A strong color cast always has an odd standard deviation value in one of the RGB channels. Based on this observation, a cost function called the degree of illuminant tinge(DIT) is proposed to determine the quality of illuminant color-calibrated images. This DIT is formulated in such a way that the image scene under standard illuminant (d65) has lower DIT value compared to the same scene under different illuminant. Here, a swarm intelligence based particle swarm optimizer(PSO) is used to find the optimum illuminant of the given image that minimizes the degree of illuminant tinge. The proposed method is evaluated using real-world datasets and the experimental results validate the effectiveness of the proposed method.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.60 no.6
• /
• pp.43-54
• /
• 2018

The accurate estimation of reference crop evapotranspiration ($ET_o$) is essential in irrigation water management to assess the time-dependent status of crop water use and irrigation scheduling. The importance of $ET_o$ has resulted in many direct and indirect methods to approximate its value and include pan evaporation, meteorological-based estimations, lysimetry, soil moisture depletion, and soil water balance equations. Artificial neural networks (ANNs) have been intensively implemented for process-based hydrologic modeling due to their superior performance using nonlinear modeling, pattern recognition, and classification. This study adapted two well-known ANN algorithms, Backpropagation neural network (BPNN) and Generalized regression neural network (GRNN), to evaluate their capability to accurately predict $ET_o$ using daily meteorological data. All data were obtained from two automated weather stations (Chupungryeong and Jangsu) located in the Yeongdong-gun (2002-2017) and Jangsu-gun (1988-2017), respectively. Daily $ET_o$ was calculated using the Penman-Monteith equation as the benchmark method. These calculated values of $ET_o$ and corresponding meteorological data were separated into training, validation and test datasets. The performance of each ANN algorithm was evaluated against $ET_o$ calculated from the benchmark method and multiple linear regression (MLR) model. The overall results showed that the BPNN algorithm performed best followed by the MLR and GRNN in a statistical sense and this could contribute to provide valuable information to farmers, water managers and policy makers for effective agricultural water governance.

• Journal of Korean Society of Forest Science
• /
• v.110 no.4
• /
• pp.610-621
• /
• 2021

The soil creep, primarily caused by earthquakes and torrential rainfall events, has widely occurred across the country. The Korea Forest Service attempted to quantify the soil creep susceptible areas using a discriminant value table to prevent or mitigate casualties and/or property damages in advance. With the advent of advanced computer technologies, machine learning-based classification models have been employed for managing mountainous disasters, such as landslides and debris flows. This study aims to quantify the soil creep susceptibility using several classifiers, namely the k-Nearest Neighbor (k-NN), Naive Bayes (NB), Random Forest (RF), and Support Vector Machine (SVM) models. To develop the classification models, we downscaled 292 data from 4,618 field survey data. About 70% of the selected data were used for training, with the remaining 30% used for model testing. The developed models have the classification accuracy of 0.727 for k-NN, 0.750 for NB, 0.807 for RF, and 0.750 for SVM against test datasets representing 30% of the total data. Furthermore, we estimated Cohen's Kappa index as 0.534, 0.580, 0.673, and 0.585, with AUC values of 0.872, 0.912, 0.943, and 0.834, respectively. The machine learning-based classifications for soil creep susceptibility were RF, NB, SVM, and k-NN in that order. Our findings indicate that the machine learning classifiers can provide valuable information in establishing and implementing natural disaster management plans in mountainous areas.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.299-316
• /
• 2019

The purpose of this study was to analyze landslide susceptibility in the Pyeongchang area using Weight of Evidence (WOE) and Evidential Belief Function (EBF) as probability models and Artificial Neural Networks (ANN) as a machine learning model in a geographic information system (GIS). This study examined the widespread shallow landslides triggered by heavy rainfall during Typhoon Ewiniar in 2006, which caused serious property damage and significant loss of life. For the landslide susceptibility mapping, 3,955 landslide occurrences were detected using aerial photographs, and environmental spatial data such as terrain, geology, soil, forest, and land use were collected and constructed in a spatial database. Seventeen factors that could affect landsliding were extracted from the spatial database. All landslides were randomly separated into two datasets, a training set (50%) and validation set (50%), to establish and validate the EBF, WOE, and ANN models. According to the validation results of the area under the curve (AUC) method, the accuracy was 74.73%, 75.03%, and 70.87% for WOE, EBF, and ANN, respectively. The EBF model had the highest accuracy. However, all models had predictive accuracy exceeding 70%, the level that is effective for landslide susceptibility mapping. These models can be applied to predict landslide susceptibility in an area where landslides have not occurred previously based on the relationships between landslide and environmental factors. This susceptibility map can help reduce landslide risk, provide guidance for policy and land use development, and save time and expense for landslide hazard prevention. In the future, more generalized models should be developed by applying landslide susceptibility mapping in various areas.

• Knowledge Management Research
• /
• v.22 no.2
• /
• pp.1-17
• /
• 2021

In this study, we predicted the bitcoin prices of Bithum and Coinbase, a leading exchange in Korea and USA, using ARIMA and Recurrent Neural Networks(RNNs). And we used news articles from each country to suggest a separated RNN model. The suggested model identifies the datasets based on the changing trend of prices in the training data, and then applies time series prediction technique(RNNs) to create multiple models. Then we used daily news data to create a term-based dictionary for each trend change point. We explored trend change points in the test data using the daily news keyword data of testset and term-based dictionary, and apply a matching model to produce prediction results. With this approach we obtained higher accuracy than the model which predicted price by applying just time series prediction technique. This study presents that the limitations of the time series prediction techniques could be overcome by exploring trend change points using news data and various time series prediction techniques with text mining techniques could be applied to improve the performance of the model in the further research.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.99-108
• /
• 2021

There are unrestricted conditions on the driver's face inside the vehicle, such as changes in lighting, partial occlusion and various changes in the driver's condition. In this paper, we propose a face identification system in an unrestricted vehicle environment. The proposed method uses a near-infrared (NIR) camera to minimize the changes in facial images that occur according to the illumination changes inside and outside the vehicle. In order to process a face exposed to extreme light, the normal face image is changed to a simulated overexposed image using mean and variance for training. Thus, facial classifiers are simultaneously generated under both normal and extreme illumination conditions. Our method identifies a face by detecting facial landmarks and aggregating the confidence score of each landmark for the final decision. In particular, the performance improvement is the highest in the class where the driver wears glasses or sunglasses, owing to the robustness to partial occlusions by recognizing each landmark. We can recognize the driver by using the scores of remaining visible landmarks. We also propose a novel robust rejection and a new evaluation method, which considers the relations between registered and unregistered drivers. The experimental results on our dataset, PolyU and ORL datasets demonstrate the effectiveness of the proposed method.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.