• Journal of The Korean Society of Grassland and Forage Science
• /
• v.36 no.3
• /
• pp.205-214
• /
• 2016

The objective of this study was to construct a forage rye (FR) dry matter yield (DMY) estimation model based on climate data by locations in South Korea. The data set (n = 549) during 29 years were used. Six optimal climatic variables were selected through stepwise multiple regression analysis with DMY as the response variable. Subsequently, via general linear model, the final model including the six climatic variables and cultivated locations as dummy variables was constructed as follows: DMY = 104.166SGD + 1.454AAT + 147.863MTJ + 59.183PAT150 - 4.693SRF + 45.106SRD - 5230.001 + Location, where SGD was spring growing days, AAT was autumnal accumulated temperature, MTJ was mean temperature in January, PAT150 was period to accumulated temperature 150, SRF was spring rainfall, and SRD was spring rainfall days. The model constructed in this research could explain 24.4 % of the variations in DMY of FR. The homoscedasticity and the assumption that the mean of the residuals were equal to zero was satisfied. The goodness-of-fit of the model was proper based on most scatters of the predicted DMY values fell within the 95% confidence interval.

• The Journal of the Korea Contents Association
• /
• v.9 no.5
• /
• pp.332-336
• /
• 2009

Functional prediction of unannotated proteins is one of the most important tasks in yeast genomics. Analysis of a protein-protein interaction network leads to a better understanding of the functions of unannotated proteins. A number of researches have been performed for the functional prediction of unannotated proteins from a protein-protein interaction network. A chi-square method is one of the existing methods for the functional prediction of unannotated proteins from a protein-protein interaction network. But, the method does not consider the topology of network. In this paper, we propose a novel method that is able to predict specific molecular functions for unannotated proteins from a protein-protein interaction network. To do this, we investigated all protein interaction DBs of yeast in the public sites such as MIPS, DIP, and SGD. For the prediction of unannotated proteins, we employed a modified chi-square measure based on neighborhood counting and we assess the prediction accuracy of protein function from a protein-protein interaction network.

• Journal of IKEEE
• /
• v.24 no.3
• /
• pp.766-776
• /
• 2020

Recently, as interest in machine learning (ML) has increased and research using ML has become active, it is becoming more important to find an optimal hyperparameter combination for various ML models. In this paper, among various hyperparameters, we focused on ML optimizers, and measured and compared the performance of major optimizers using various datasets. In particular, we compared the performance of nine optimizers ranging from SGD, which is the most basic, to Momentum, NAG, AdaGrad, RMSProp, AdaDelta, Adam, AdaMax, and Nadam, using the MNIST, CIFAR-10, IRIS, TITANIC, and Boston Housing Price datasets. Experimental results showed that when Adam or Nadam was used, the loss of various ML models decreased most rapidly and their F1 score was also increased. Meanwhile, AdaMax showed a lot of instability during training and AdaDelta showed slower convergence speed and lower performance than other optimizers.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.29-36
• /
• 2021

In this paper, we classify ECG signal data for mobile devices using deep learning models. To classify abnormal heartbeats with high accuracy, three factors of the deep learning model are selected, and the classification accuracy is compared according to the changes in the conditions of the factors. We apply a CNN model that can self-extract features of ECG data and compare the performance of a total of 48 combinations by combining conditions of the depth of model, optimization method, and activation functions that compose the model. Deriving the combination of conditions with the highest accuracy, we obtained the highest classification accuracy of 97.88% when we applied 19 convolutional layers, an optimization method SGD, and an activation function Mish. In this experiment, we confirmed the suitability of feature extraction and abnormal beat detection of 1-channel ECG signals using CNN.

• Journal of the Korean Society for information Management
• /
• v.38 no.2
• /
• pp.113-127
• /
• 2021

The purpose of this study is to propose a personalized book recommendation system to promote the use of university libraries. In particular, unlike many recommended services that are based on existing users' preferences, this study proposes a method that derive evaluation metrics using individual users' book rental history and tendencies, which can be an effective alternative when users' preferences are not available. This study suggests models using two matrix decomposition methods: Singular Value Decomposition(SVD) and Stochastic Gradient Descent(SGD) that recommend books to users in a way that yields an expected preference score for books that have not yet been read by them. In addition, the model was implemented using a user-based collaborative filtering algorithm by referring to book rental history of other users that have high similarities with the target user. Finally, user evaluation was conducted for the three models using the derived evaluation metrics. Each of the three models recommended five books to users who can either accept or reject the recommendations as the way to evaluate the models.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.4
• /
• pp.11-19
• /
• 2023

The paper proposes a smart mirror system that recommends fragrances based on user emotion analysis. This paper combines natural language processing techniques such as embedding techniques (CounterVectorizer and TF-IDF) and machine learning classification models (DecisionTree, SVM, RandomForest, SGD Classifier) to build a model and compares the results. After the comparison, the paper constructs a personal emotion-based fragrance recommendation mirror model based on the SVM and word embedding pipeline-based emotion classifier model with the highest performance. The proposed system implements a personalized fragrance recommendation mirror based on emotion analysis, providing web services using the Flask web framework. This paper uses the Google Speech Cloud API to recognize users' voices and use speech-to-text (STT) to convert voice-transcribed text data. The proposed system provides users with information about weather, humidity, location, quotes, time, and schedule management.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.101-112
• /
• 2024

Telugu language is considered as fourth most used language in India especially in the regions of Andhra Pradesh, Telangana, Karnataka etc. In international recognized countries also, Telugu is widely growing spoken language. This language comprises of different dependent and independent vowels, consonants and digits. In this aspect, the enhancement of Telugu Handwritten Character Recognition (HCR) has not been propagated. HCR is a neural network technique of converting a documented image to edited text one which can be used for many other applications. This reduces time and effort without starting over from the beginning every time. In this work, a Unicode based Handwritten Character Recognition(U-HCR) is developed for translating the handwritten Telugu characters into English language. With the use of Centre of Gravity (CG) in our model we can easily divide a compound character into individual character with the help of Unicode values. For training this model, we have used both online and offline Telugu character datasets. To extract the features in the scanned image we used convolutional neural network along with Machine Learning classifiers like Random Forest and Support Vector Machine. Stochastic Gradient Descent (SGD), Root Mean Square Propagation (RMS-P) and Adaptative Moment Estimation (ADAM)optimizers are used in this work to enhance the performance of U-HCR and to reduce the loss function value. This loss value reduction can be possible with optimizers by using CNN. In both online and offline datasets, proposed model showed promising results by maintaining the accuracies with 90.28% for SGD, 96.97% for RMS-P and 93.57% for ADAM respectively.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.37 no.2
• /
• pp.145-153
• /
• 2017

This study was aimed to find yield prediction model of Italian ryegrass using climate big data and geographic information. After that, mapping the predicted yield results using Geographic Information System (GIS) as follows; First, forage data were collected; second, the climate information, which was matched with forage data according to year and location, was gathered from the Korean Metrology Administration (KMA) as big data; third, the climate layers used for GIS were constructed; fourth, the yield prediction equation was estimated for the climate layers. Finally, the prediction model was evaluated in aspect of fitness and accuracy. As a result, the fitness of the model ($R^2$) was between 27% to 95% in relation to cultivated locations. In Suwon (n=321), the model was; DMY = 158.63AGD -8.82AAT +169.09SGD - 8.03SAT +184.59SRD -13,352.24 (DMY: Dry Matter Yield, AGD: Autumnal Growing Days, SGD: Spring Growing Days, SAT: Spring Accumulated Temperature, SRD: Spring Rainfall Days). Furthermore, DMY was predicted as $9,790{\pm}120$ (kg/ha) for the mean DMY(9,790 kg/ha). During mapping, the yield of inland areas were relatively greater than that of coastal areas except of Jeju Island, furthermore, northeastern areas, which was mountainous, had lain no cultivations due to weak cold tolerance. In this study, even though the yield prediction modeling and mapping were only performed in several particular locations limited to the data situation as a startup research in the Republic of Korea.

• Journal of Korea Multimedia Society
• /
• v.21 no.4
• /
• pp.441-449
• /
• 2018

Deep learning has been used for various processing centered on image recognition. One core algorithms of the deep learning, convolutional neural network is an deep neural network that specialized in image recognition. In this paper, we use a convolutional neural network to classify forest insects and propose an optimization method. Experiments were carried out by combining two weight initialization and six parameter update methods. As a result, the Xavier-SGD method showed the highest performance with an accuracy of 82.53% in the 12 different combinations of experiments. Through this, the latest learning algorithms, which complement the disadvantages of the previous parameter update method, we conclude that it can not lead to higher performance than existing methods in all application environments.