• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.2
• /
• pp.383-388
• /
• 2024

This paper is a study to derive the predicted value of power generation based on the photovoltaic power generation data measured in Jeollanam-do, South Korea. Multivariate variables such as direct current, alternating current, and environmental data were measured in the inverter to measure the amount of power generation, and pre-processing was performed to ensure the stability and reliability of the measured values. Correlation analysis used only data with high correlation with power generation in time series data for prediction using partial autocorrelation function (PACF). Deep learning models were used to measure the amount of power generation to predict the amount of photovoltaic power generation, and the results of correlation analysis of each multivariate variable were used to increase the prediction accuracy. Learning using refined data was more stable than when existing data were used as it was, and the solar power generation prediction algorithm was improved by using only highly correlated variables among multivariate variables by reflecting the correlation analysis results.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.31-40
• /
• 2024

In the realm of domestic online fashion platform industry the manual registration of product information by individual business owners leads to inconvenience and reliability issues, especially when dealing with simultaneous registrations of numerous product groups. Moreover, bias is significantly heightened due to the low quality of product images and an imbalance in data quantity. Therefore, this study proposes a ResNet50 model aimed at minimizing data bias through oversampling techniques and conducting multiple classifications for 13 fashion categories. Transfer learning is employed to optimize resource utilization and reduce prolonged learning times. The results indicate improved discrimination of up to 33.4% for data augmentation in classes with insufficient data compared to the basic convolution neural network (CNN) model. The reliability of all outcomes is underscored by precision and affirmed by the recall curve. This study is suggested to advance the development of the domestic online fashion platform industry to a higher echelon.

• Journal of Internet Computing and Services
• /
• v.25 no.2
• /
• pp.49-55
• /
• 2024

This paper proposes PredFeed Net, a neural network model that mimics the food distribution of fish farming experts. Unlike existing food distribution automation systems, PredFeed Net predicts food distribution by learning the food distribution patterns of experts. This has the advantage of being able to learn using only existing environmental data and food distribution records from food distribution experts, without the need to experiment by changing food distribution variables according to the environment in an actual aquarium. After completing training, PredFeed Net predicts the next food ration based on the current environment or fish condition. Prediction of feed ration is a necessary element for automating feed ration, and feed ration automation contributes to the development of modern fish farming such as smart aquaculture and aquaponics systems.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.39-46
• /
• 2024

Many researchers make efforts to evaluate water quality using various models. Such models require a dataset without missing values, but in real world, most datasets include missing values for various reasons. Simple deletion of samples having missing value(s) could distort distribution of the underlying data and pose a significant risk of biasing the model's inference when the missing mechanism is not MCAR. In this study, to explore the most appropriate technique for handing missing values in water quality data, several imputation techniques were experimented based on existing KNN and MICE imputation with/without the generative neural network model, Autoencoder(AE) and Denoising Autoencoder(DAE). The results shows that KNN and MICE combined imputation without generative networks provides the closest estimated values to the true values. When evaluating binary classification models based on support vector machine and ensemble algorithms after applying the combined imputation technique to the observed water quality dataset with missing values, it shows better performance in terms of Accuracy, F1 score, RoC-AuC score and MCC compared to those evaluated after deleting samples having missing values.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.61-70
• /
• 2023

Clustering is an unsupervised learning method that involves grouping data based on features such as distance metrics, using data without known labels or ground truth values. This method has the advantage of being applicable to various types of data, including images, text, and audio, without the need for labeling. Traditional clustering techniques involve applying dimensionality reduction methods or extracting specific features to perform clustering. However, with the advancement of deep learning models, research on deep clustering techniques using techniques such as autoencoders and generative adversarial networks, which represent input data as latent vectors, has emerged. In this study, we propose a deep clustering technique based on deep learning. In this approach, we use an autoencoder to transform the input data into latent vectors, and then construct a vector space according to the cluster structure and perform k-means clustering. We conducted experiments using the MNIST and Fashion-MNIST datasets in the PyTorch machine learning library as the experimental environment. The model used is a convolutional neural network-based autoencoder model. The experimental results show an accuracy of 89.42% for MNIST and 56.64% for Fashion-MNIST when k is set to 10.

• Korean Journal of Soil Science and Fertilizer
• /
• v.39 no.5
• /
• pp.259-267
• /
• 2006

Hydraulic conductivity is the rate of water flux on hydraulic gradient. The van Genuchten Mualem (VGM) model is frequently used for describing unsaturated state of soils, that is composed with the function of soil water potential and soil water content and requests various parameters. This study is to get the value of VGM parameters used Rosetta computer program based on neural network analysis method and to calculate VGM parameters. VGM parameters included Ko(effective saturated hydraulic conductivity), ${\theta}r$(residual soil water content), ${\theta}s$(saturated soil water content), L, n and m. The unsaturated hydraulic conductivity at 10 kPa was calculated by using Rosetta program. Unsaturated hydraulic conductivities of 17 soil series at 1, 3, 5, 7 kPa were also obtained by applying saturated hydraulic conductivity by disk tension infiltrometer based on Gardner and Wooding's equation. Water flow at the water potential of 3 kPa was very low except Namgye, Hagog, Baegsan, Sangju, Seogcheon, Yesan soil series. Unsaturated hydraulic conductivity at 1 kPa showed the highest value for Samgag soil series and was in order of Yesan, Hwabong, Hagog and Baegsan soil series. Those of Gacheon, Seocheon and Ugog soil series were very low. When the value by VGM was compared with the value by disc tension infiltrometer, there was a tendency with exponential function to soils without gravel but there was no tendency to soils including gravel. Conclusively, it would be limited that VGM model for unsaturated hydraulic conductivity analysis applies to Korean agricultural land including gravel and having steep slope, shallow soil depth.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.189-198
• /
• 2024

Lipreading is one of the important parts of speech recognition, and several studies have been conducted to improve the performance of lipreading in lipreading systems for speech recognition. Recent studies have used method to modify the model architecture of lipreading system to improve recognition performance. Unlike previous research that improve recognition performance by modifying model architecture, we aim to improve recognition performance without any change in model architecture. In order to improve the recognition performance without modifying the model architecture, we refer to the cues used in human lipreading and set other regions such as chin and cheeks as regions of interest along with the lip region, which is the existing region of interest of lipreading systems, and compare the recognition rate of each region of interest to propose the highest performing region of interest In addition, assuming that the difference in normalization results caused by the difference in interpolation method during the process of normalizing the size of the region of interest affects the recognition performance, we interpolate the same region of interest using nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation, and compare the recognition rate of each interpolation method to propose the best performing interpolation method. Each region of interest was detected by training an object detection neural network, and dynamic time warping templates were generated by normalizing each region of interest, extracting and combining features, and mapping the dimensionality reduction of the combined features into a low-dimensional space. The recognition rate was evaluated by comparing the distance between the generated dynamic time warping templates and the data mapped to the low-dimensional space. In the comparison of regions of interest, the result of the region of interest containing only the lip region showed an average recognition rate of 97.36%, which is 3.44% higher than the average recognition rate of 93.92% in the previous study, and in the comparison of interpolation methods, the bilinear interpolation method performed 97.36%, which is 14.65% higher than the nearest neighbor interpolation method and 5.55% higher than the bicubic interpolation method. The code used in this study can be found a https://github.com/haraisi2/Lipreading-Systems.

• Journal of Korea Water Resources Association
• /
• v.51 no.12
• /
• pp.1207-1216
• /
• 2018

Discharge or water level predictions at tidally affected river reaches are currently still a great challenge in hydrological practices. This research aims to predict water level of the tide dominated site, Jamsu bridge in the Han River downstream. Physics-based hydrodynamic approaches are sometimes not applicable for water level prediction in such a tidal river due to uncertainty sources like rainfall forecasting data. In this study, TensorFlow deep learning framework was used to build a deep neural network based LSTM model and its applications. The LSTM model was trained based on 3 data sets having 10-min temporal resolution: Paldang dam release, Jamsu bridge water level, predicted tidal level for 6 years (2011~2016) and then predict the water level time series given the six lead times: 1, 3, 6, 9, 12, 24 hours. The optimal hyper-parameters of LSTM model were set up as follows: 6 hidden layers number, 0.01 learning rate, 3000 iterations. In addition, we changed the key parameter of LSTM model, sequence length, ranging from 1 to 6 hours to test its affect to prediction results. The LSTM model with the 1 hr sequence length led to the best performing prediction results for the all cases. In particular, it resulted in very accurate prediction: RMSE (0.065 cm) and NSE (0.99) for the 1 hr lead time prediction case. However, as the lead time became longer, the RMSE increased from 0.08 m (1 hr lead time) to 0.28 m (24 hrs lead time) and the NSE decreased from 0.99 (1 hr lead time) to 0.74 (24 hrs lead time), respectively.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.1
• /
• pp.1-9
• /
• 2022

Non-small cell lung cancer (NSCLC) accounts for a high proportion of 85% among all lung cancer and has a significantly higher mortality rate (22.7%) compared to other cancers. Therefore, it is very important to predict the prognosis after surgery in patients with non-small cell lung cancer. In this study, the types of preoperative chest CT image patches for non-small cell lung cancer patients with tumor as a region of interest are diversified into five types according to tumor-related information, and performance of single classifier model, ensemble classifier model with soft-voting method, and ensemble classifier model using 3 input channels for combination of three different patches using pre-trained ResNet and EfficientNet CNN networks are analyzed through misclassification cases and Grad-CAM visualization. As a result of the experiment, the ResNet152 single model and the EfficientNet-b7 single model trained on the peritumoral patch showed accuracy of 87.93% and 81.03%, respectively. In addition, ResNet152 ensemble model using the image, peritumoral, and shape-focused intratumoral patches which were placed in each input channels showed stable performance with an accuracy of 87.93%. Also, EfficientNet-b7 ensemble classifier model with soft-voting method using the image and peritumoral patches showed accuracy of 84.48%.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.9-18
• /
• 2023

Predicting the compressive strength of high-performance concrete (HPC) is challenging because of the use of additional cementitious materials; thus, the development of improved predictive models is essential. The purpose of this study was to develop an HPC compressive-strength prediction model using an ensemble machine-learning method of combined bagging and stacking techniques. The result is a new ensemble technique that integrates the existing ensemble methods of bagging and stacking to solve the problems of a single machine-learning model and improve the prediction performance of the model. The nonlinear regression, support vector machine, artificial neural network, and Gaussian process regression approaches were used as single machine-learning methods and bagging and stacking techniques as ensemble machine-learning methods. As a result, the model of the proposed method showed improved accuracy results compared with single machine-learning models, an individual bagging technique model, and a stacking technique model. This was confirmed through a comparison of four representative performance indicators, verifying the effectiveness of the method.