• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.4
• /
• pp.328-337
• /
• 2021

Air pollution, which is a class 1 carcinogen, such as asbestos and benzene, is the cause of various diseases. The spread of ultra-air pollution is one of the important causes of the spread of the corona virus. This paper analyzes and predicts fine dust and ultra-air pollution from 2015 to 2019 based on weather data such as average temperature, precipitation, and average wind speed in Seoul and atmospheric environment data such as SO2, NO2, and O3. Linear regression, SVM, and ensemble models among machine learning models were compared and analyzed to predict fine dust by grasping and analyzing the status of air pollution and ultra-air pollution by season and month. In addition, important features(attributes) that affect the generation of fine dust and ultra-air pollution are identified. The highest ultra-air pollution was found in March, and the lowest ultra-air pollution was observed from August to September. In the case of meteorological data, the data that has the most influence on ultra-air pollution is average temperature, and in the case of meteorological data and atmospheric environment data, NO2 has the greatest effect on ultra-air pollution generation.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.2
• /
• pp.35-40
• /
• 2019

Traditional Malware Detection is susceptible for detecting malware which is modified by polymorphism or obfuscation technology. By learning patterns that are embedded in malware code, machine learning algorithms can detect similar behaviors and replace the current detection methods. Data must collected continuously in order to learn malicious code patterns that change over time. However, the process of storing and processing a large amount of malware files is accompanied by high space and time complexity. In this paper, an HDFS-based distributed processing system is designed to reduce space complexity and accelerate feature extraction time. Using a distributed processing system, we extract two API features based on filtering basis, 2-gram feature and APICFG feature and the generalization performance of ensemble learning models is compared. In experiments, the time complexity of the feature extraction was improved about 3.75 times faster than the processing time of a single computer, and the space complexity was about 5 times more efficient. The 2-gram feature was the best when comparing the classification performance by feature, but the learning time was long due to high dimensionality.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1773-1793
• /
• 2023

Automated machine learning, often referred to as "AutoML," is the process of automating the time-consuming and iterative procedures that are associated with the building of machine learning models. There have been significant contributions in this area across a number of different stages of accomplishing a data-mining task, including model selection, hyper-parameter optimization, and preprocessing method selection. Among them, preprocessing method selection is a relatively new and fast growing research area. The current work is focused on the recommendation of preprocessing methods, i.e., feature subset selection (FSS) algorithms. One limitation in the existing studies regarding FSS algorithm recommendation is the use of a single learner for meta-modeling, which restricts its capabilities in the metamodeling. Moreover, the meta-modeling in the existing studies is typically based on a single group of data characterization measures (DCMs). Nonetheless, there are a number of complementary DCM groups, and their combination will allow them to leverage their diversity, resulting in improved meta-modeling. This study aims to address these limitations by proposing an architecture for preprocess method selection that uses ensemble learning for meta-modeling, namely AutoFE-Sel. To evaluate the proposed method, we performed an extensive experimental evaluation involving 8 FSS algorithms, 3 groups of DCMs, and 125 datasets. Results show that the proposed method achieves better performance compared to three baseline methods. The proposed architecture can also be easily extended to other preprocessing method selections, e.g., noise-filter selection and imbalance handling method selection.

• Geomechanics and Engineering
• /
• v.34 no.6
• /
• pp.697-726
• /
• 2023

Brittleness as an important property of rock plays a crucial role both in the failure process of intact rock and rock mass response to excavation in engineering geological and geotechnical projects. Generally, rock brittleness indices are calculated from the mechanical properties of rocks such as uniaxial compressive strength, tensile strength and modulus of elasticity. These properties are generally determined from complicated, expensive and time-consuming tests in laboratory. For this reason, in the present research, an attempt has been made to predict the rock brittleness indices from simple, inexpensive, and quick laboratory test results namely dry unit weight, porosity, slake-durability index, P-wave velocity, Schmidt rebound hardness, and point load strength index using multiple linear regression, exponential regression, support vector machine (SVM) with various kernels, generating fuzzy inference system, and regression tree ensemble (RTE) with boosting framework. So, this could be considered as an innovation for the present research. For this purpose, the number of 39 rock samples including five igneous, twenty-six sedimentary, and eight metamorphic were collected from different regions of Iran. Mineralogical, physical and mechanical properties as well as five well known rock brittleness indices (i.e., B₁, B₂, B₃, B₄, and B₅) were measured for the selected rock samples before application of the above-mentioned machine learning techniques. The performance of the developed models was evaluated based on several statistical metrics such as mean square error, relative absolute error, root relative absolute error, determination coefficients, variance account for, mean absolute percentage error and standard deviation of the error. The comparison of the obtained results revealed that among the studied methods, SVM is the most suitable one for predicting B₁, B₂ and B₅, while RTE predicts B₃ and B₄ better than other methods.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.21-31
• /
• 2021

As the COVID-19 pandemic rapidly changes healthcare around the globe, the need for smart healthcare that allows for remote diagnosis is increasing. The current classification of respiratory diseases cost high and requires a face-to-face visit with a skilled medical professional, thus the pandemic significantly hinders monitoring and early diagnosis. Therefore, the ability to accurately classify and diagnose respiratory sound using deep learning-based AI models is essential to modern medicine as a remote alternative to the current stethoscope. In this study, we propose a deep learning-based respiratory sound classification model using data collected from medical experts. The sound data were preprocessed with BandPassFilter, and the relevant respiratory audio features were extracted with Log-Mel Spectrogram and Mel Frequency Cepstral Coefficient (MFCC). Subsequently, a Parallel CNN network model was trained on these two inputs using stacking ensemble techniques combined with various machine learning classifiers to efficiently classify and detect abnormal respiratory sounds with high accuracy. The model proposed in this paper classified abnormal respiratory sounds with an accuracy of 96.9%, which is approximately 6.1% higher than the classification accuracy of baseline model.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.139-159
• /
• 2022

As interest in health functional foods has increased since COVID-19, the importance of imported food safety inspections is growing. However, in contrast to the annual increase in imports of health functional foods, the budget and manpower required for inspections for import and export are reaching their limit. Hence, the purpose of this study is to propose a machine learning model that efficiently detects unsuitable food suitable for the characteristics of data possessed by government offices on imported food. First, the components of food import/export inspections data that affect the judgment of nonconformity were examined and derived variables were newly created. Second, in order to select features for the machine learning, class imbalance and nonlinearity were considered when performing exploratory analysis on imported food-related data. Third, we try to compare the performance and interpretability of each model by applying various machine learning techniques. In particular, the ensemble model was the best, and it was confirmed that the derived variables and models proposed in this study can be helpful to the system used in import/export inspections.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.95-101
• /
• 1999

In this paper, a comparison between different methods to combine predictions from neural networks will be given. These methods are bagging, bumping, and balancing. Those are based on the analysis of the ensemble generalization error into an ambiguity term and a term incorporating generalization performances of individual networks. Neural Networks and AI machine learning models are prone to overfitting. A strategy to prevent a neural network from overfitting, is to stop training in early stage of the learning process. The complete data set is spilt up into a training set and a validation set. Training is stopped when the error on the validation set starts increasing. The stability of the networks is highly dependent on the division in training and validation set, and also on the random initial weights and the chosen minimization procedure. This causes early stopped networks to be rather unstable: a small change in the data or different initial conditions can produce large changes in the prediction. Therefore, it is advisable to apply the same procedure several times starting from different initial weights. This technique is often referred to as training ensembles of neural networks. In this paper, we presented a comparison of three statistical methods to prevent overfitting of neural network.

• Smart Media Journal
• /
• v.11 no.2
• /
• pp.9-17
• /
• 2022

The purpose of this study is to implement a predictive model to support decision-making to replace a starting pitcher before a crisis situation in a baseball game. To this end, using the Major League Statcast data provided by Baseball Savant, we implement a predictive model that preemptively replaces starting pitchers before a crisis situation. To this end, first, the crisis situation that the starting pitcher faces in the game was derived through data exploration. Second, if the starting pitcher was replaced before the end of the inning, learning was carried out by composing a label with a replacement in the previous inning. As a result of comparing the trained models, the model based on the ensemble method showed the highest predictive performance with an F1-Score of 65%. The practical significance of this study is that the proposed model can contribute to increasing the team's winning probability by replacing the starting pitcher before a crisis situation, and the coach will be able to receive data-based strategic decision-making support during the game.

• Convergence Security Journal
• /
• v.21 no.2
• /
• pp.57-66
• /
• 2021

Deep neural networks (DNNs) provide excellent performance for image, speech, and pattern recognition. However, DNNs sometimes misrecognize certain adversarial examples. An adversarial example is a sample that adds optimized noise to the original data, which makes the DNN erroneously misclassified, although there is nothing wrong with the human eye. Therefore studies on defense against adversarial example attacks are required. In this paper, we have experimentally analyzed the success rate of detection for adversarial examples by adjusting various parameters. The performance of the ensemble defense method was analyzed using fast gradient sign method, DeepFool method, Carlini & Wanger method, which are adversarial example attack methods. Moreover, we used MNIST as experimental data and Tensorflow as a machine learning library. As an experimental method, we carried out performance analysis based on three adversarial example attack methods, threshold, number of models, and random noise. As a result, when there were 7 models and a threshold of 1, the detection rate for adversarial example is 98.3%, and the accuracy of 99.2% of the original sample is maintained.

• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1085-1093
• /
• 2016

Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.