• Phonetics and Speech Sciences
• /
• v.14 no.4
• /
• pp.35-43
• /
• 2022

This paper studies how to improve the identification rate of laryngeal disability speech data by convolutional neural network (CNN) and machine learning ensemble learning methods. In general, the number of laryngeal dysfunction speech data is small, so even if identifiers are constructed by statistical methods, the phenomenon caused by overfitting depending on the training method can lead to a decrease the identification rate when exposed to external data. In this work, we try to combine results derived from CNN models and machine learning models with various accuracy in a multi-voting manner to ensure improved classification efficiency compared to the original trained models. The Pusan National University Hospital (PNUH) dataset was used to train and validate algorithms. The dataset contains normal voice and voice data of benign and malignant tumors. In the experiment, an attempt was made to distinguish between normal and benign tumors and malignant tumors. As a result of the experiment, the random forest method was found to be the best ensemble method and showed an identification rate of 85%.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.2
• /
• pp.80-98
• /
• 2023

This study explores the effectiveness of various data preprocessing algorithms for improving subseasonal to seasonal (S2S) climate predictions from six climate forecast models and their Multi-Model Ensemble (MME) using a deep learning-based postprocessing model. A pipeline of data transformation algorithms was constructed to convert raw S2S prediction data into the training data processed with several statistical distribution. A dimensionality reduction algorithm for selecting features through rankings of correlation coefficients between the observed and the input data. The training model in the study was designed with TimeDistributed wrapper applied to all convolutional layers of U-Net: The TimeDistributed wrapper allows a U-Net convolutional layer to be directly applied to 5-dimensional time series data while maintaining the time axis of data, but every input should be at least 3D in U-Net. We found that Robust and Standard transformation algorithms are most suitable for improving S2S predictions. The dimensionality reduction based on feature selections did not significantly improve predictions of daily precipitation for six climate models and even worsened predictions of daily maximum and minimum temperatures. While deep learning-based postprocessing was also improved MME S2S precipitation predictions, it did not have a significant effect on temperature predictions, particularly for the lead time of weeks 1 and 2. Further research is needed to develop an optimal deep learning model for improving S2S temperature predictions by testing various models and parameters.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.2
• /
• pp.319-328
• /
• 2021

In this paper, we perform prediction of amount of electric power plant for complex of wind plant using multi-layer perceptron in order to calculate exact calculation of capacity of ESS to maximize profit through generation and to minimize generation cost of wind generation. We acquire wind speed, direction of wind and air density as variables to predict the amount of generation of wind power. Then, we merge and normalize there variables. To train model, we divide merged variables into data as train and test data with ratio of 70% versus 30%. Then we train model by using training data, and we alsouate the prediction performance of model by using test data. Finally, we present the result of prediction in amount of wind power.

• Journal of Korea Water Resources Association
• /
• v.33 no.5
• /
• pp.537-550
• /
• 2000

In this study, Neural Networks models were used to forecast daily streamflow at Jindong station of the Nakdong River basin. Neural Networks models consist of CASE 1(5-5-1) and CASE 2(5-5-5-1). The criteria which separates two models is the number of hidden layers. Each model has Fletcher-Reeves Conjugate Gradient BackPropagation(FR-CGBP) and Scaled Conjugate Gradient BackPropagation(SCGBP) algorithms, which are better than original BackPropagation(BP) in convergence of global error and training tolerance. The data which are available for model training and validation were composed of wet, average, dry, wet+average, wet+dry, average+dry and wet+average+dry year respectively. During model training, the optimal connection weights and biases were determined using each data set and the daily streamflow was calculated at the same time. Except for wet+dry year, the results of training were good conditions by statistical analysis of forecast errors. And, model validation was carried out using the connection weights and biases which were calculated from model training. The results of validation were satisfactory like those of training. Daily streamflow forecasting using Neural Networks models were compared with those forecasted by Multiple Regression Analysis Mode(MRAM). Neural Networks models were displayed slightly better results than MRAM in this study. Thus, Neural Networks models have much advantage to provide a more sysmatic approach, reduce model parameters, and shorten the time spent in the model development.

• Information Systems Review
• /
• v.25 no.3
• /
• pp.27-41
• /
• 2023

Unlike the previous works focusing on the state-of-the-art methodologies to improve the performance of machine learning models, this study improves the 'quality' of training data used in machine learning. We propose a method to enhance the quality of training data through the processing of 'local grammar,' frequently used in corpus analysis. We collected a vast amount of unstructured corporate review text data posted by employees working in the top 100 companies in Korea. After improving the data quality using the local grammar process, we confirmed that the classification model with local grammar outperformed the model without it in terms of classification performance. We defined five factors of work engagement as classification categories, and analyzed how the pattern of reviews changed before and after the COVID-19 pandemic. Through this study, we provide evidence that shows the value of the local grammar-based automatic identification and classification of employee experiences, and offer some clues for significant organizational cultural phenomena.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.10
• /
• pp.503-510
• /
• 2016

FsGr model, which has been proposed recently, is an approach of accelerometer-based gesture recognition by applying DTW algorithm in two steps, which improved recognition success rate. In FsGr model, sets of similar gestures will be produced through training phase, in order to define the notion of a set of similar gestures. At the 1st attempt of gesture recognition, if the result turns out to belong to a set of similar gestures, it makes the 2nd recognition attempt to feature-strengthened parts extracted from the set of similar gestures. However, since a same gesture show drastically different characteristics according to physical traits such as body size, age, and sex, FsGr model may not be good enough to apply to multi-user environments. In this paper, we propose FsGrM model that extends FsGr model for multi-user environment and present a program which controls channel and volume of smart TV using FsGrM model.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.3
• /
• pp.531-539
• /
• 2019

This paper proposes the training features for malware family analysis and analyzes the multi-classification performance of ensemble models. We construct training data by extracting API and DLL information from malware executables and use Random Forest and XGBoost algorithms which are based on decision tree. API, API-DLL, and DLL-CM features for malware detection and family classification are proposed by analyzing frequently used API and DLL information from malware and converting high-dimensional features to low-dimensional features. The proposed feature selection method provides the advantages of data dimension reduction and fast learning. In performance comparison, the malware detection rate is 93.0% for Random Forest, the accuracy of malware family dataset is 92.0% for XGBoost, and the false positive rate of malware family dataset including benign is about 3.5% for Random Forest and XGBoost.

• Journal of the Korean Chemical Society
• /
• v.67 no.1
• /
• pp.42-53
• /
• 2023

The purpose of this study is to obtain basic data for constructing a modeling practice program integrated with meta-modeling knowledge by analyzing the cognition level for each meta-modeling knowledge components through modeling practice in the context of the chemistry discipline content. A chemistry teacher conducted inquiry-based modeling practice including anomalous phenomena for 16 students in the second year of a science gifted school, and in order to analyze the cognition level for each of the three meta-modeling knowledge components such as model variability, model multiplicity, and modeling process, the inquiry notes recorded by the students and observation note recorded by the researcher were used for analysis. The recognition level was classified from 0 to 3 levels. As a result of the analysis, it was found that the cognition level of the modeling process was the highest and the cognition level of the multiplicity of the model was the lowest. The cause of the low recognitive level of model variability is closely related to students' perception of conceptual models as objective facts. The cause of the low cognitive level of model multiplicity has to do with the belief that there can only be one correct model for a given phenomenon. Students elaborated conceptual models using symbolic models such as chemical symbols, but lacked recognition of the importance of data interpretation affecting the entire modeling process. It is necessary to introduce preliminary activities that can explicitly guide the nature of the model, and guide the importance of data interpretation through specific examples. Training to consider and verify the acceptability of the proposed model from a different point of view than mine should be done through a modeling practice program.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.3
• /
• pp.252-262
• /
• 2020

In Remote Sensing, a machine learning based SVM model is typically utilized for land cover classification. And study using neural network models is also being carried out continuously. But study using high-resolution imagery of KOMPSAT is insufficient. Therefore, the purpose of this study is to assess the accuracy of land cover classification by neural network models using high-resolution KOMPSAT-3 satellite imagery. After acquiring satellite imagery of coastal areas near Gyeongju City, training data were produced. And land cover was classified with the SVM, ANN and DNN models for the three items of water, vegetation and land. Then, the accuracy of the classification results was quantitatively assessed through error matrix: the result using DNN model showed the best with 92.0% accuracy. It is necessary to supplement the training data through future multi-temporal satellite imagery, and to carry out classifications for various items.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1061-1070
• /
• 2021

In this manuscript, we tried to improve the performance of the FC-DenseNet by applying an attention gate for the classification of cropping areas. The attention gate module could facilitate the learning of a deep learning model and improve the performance of the model by injecting of spatial/spectral weights to each feature map. Crop classification was performed in the onion and garlic regions using a proposed deep learning model in which an attention gate was added to the skip connection part of FC-DenseNet. Training data was produced using various PlanetScope satellite imagery, and preprocessing was applied to minimize the problem of imbalanced training dataset. As a result of the crop classification, it was verified that the proposed deep learning model can more effectively classify the onion and garlic regions than existing FC-DenseNet algorithm.