• Journal of Internet Computing and Services
• /
• v.22 no.1
• /
• pp.23-30
• /
• 2021

This paper proposes a noise-tolerant image classification system using multiple autoencoders. The development of deep learning technology has dramatically improved the performance of image classifiers. However, if the images are contaminated by noise, the performance degrades rapidly. Noise added to the image is inevitably generated in the process of obtaining and transmitting the image. Therefore, in order to use the classifier in a real environment, we have to deal with the noise. On the other hand, the autoencoder is an artificial neural network model that is trained to have similar input and output values. If the input data is similar to the training data, the error between the input data and output data of the autoencoder will be small. However, if the input data is not similar to the training data, the error will be large. The proposed system uses the relationship between the input data and the output data of the autoencoder, and it has two phases to classify the images. In the first phase, the classes with the highest likelihood of classification are selected and subject to the procedure again in the second phase. For the performance analysis of the proposed system, classification accuracy was tested on a Gaussian noise-contaminated MNIST dataset. As a result of the experiment, it was confirmed that the proposed system in the noisy environment has higher accuracy than the CNN-based classification technique.

• 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 the Korea Institute of Building Construction
• /
• v.22 no.6
• /
• pp.619-630
• /
• 2022

The concrete mix design and compressive strength evaluation are used as basic data for the durability of sustainable structures. However, the recent diversification of mixing factors has created difficulties in calculating the correct mixing factor or setting the reference value concrete mixing design. The purpose of this study is to design a predictive model of bidirectional analysis that calculates the mixing elements of ternary concrete using deep learning, one of the artificial intelligence techniques. For the DNN-based predictive model for calculating the concrete mixing factor, performance evaluation and comparison were performed using a total of 8 models with the number of layers and the number of hidden neurons as variables. The combination calculation result was output. As a result of the model's performance evaluation, an average error rate of about 1.423% for the concrete compressive strength factor was achieved. and an average MAPE error of 8.22% for the prediction of the ternary concrete mixing factor was satisfied. Through comparing the performance evaluation for each structure of the DNN model, the DNN5L-2048 model showed the highest performance for all compounding factors. Using the learned DNN model, the prediction of the ternary concrete formulation table with the required compressive strength of 30 and 50 MPa was carried out. The verification process through the expansion of the data set for learning and a comparison between the actual concrete mix table and the DNN model output concrete mix table is necessary.

• International journal of advanced smart convergence
• /
• v.11 no.1
• /
• pp.19-27
• /
• 2022

Across the world, 'housing' comprises a significant portion of wealth and assets. For this reason, fluctuations in real estate prices are highly sensitive issues to individual households. In Korea, housing prices have steadily increased over the years, and thus many Koreans view the real estate market as an effective channel for their investments. However, if one purchases a real estate property for the purpose of investing, then there are several risks involved when prices begin to fluctuate. The purpose of this study is to design a real estate price 'return rate' prediction model to help mitigate the risks involved with real estate investments and promote reasonable real estate purchases. Various approaches are explored to develop a model capable of predicting real estate prices based on an understanding of the immovability of the real estate market. This study employs the LSTM method, which is based on artificial intelligence and deep learning, to predict real estate prices and validate the model. LSTM networks are based on recurrent neural networks (RNN) but add cell states (which act as a type of conveyer belt) to the hidden states. LSTM networks are able to obtain cell states and hidden states in a recursive manner. Data on the actual trading prices of apartments in autonomous districts between January 2006 and December 2019 are collected from the Actual Trading Price Disclosure System of the Ministry of Land, Infrastructure and Transport (MOLIT). Additionally, basic data on apartments and commercial buildings are collected from the Public Data Portal and Seoul Metropolitan Government's data portal. The collected actual trading price data are scaled to monthly average trading amounts, and each data entry is pre-processed according to address to produce 168 data entries. An LSTM model for return rate prediction is prepared based on a time series dataset where the training period is set as April 2015~August 2017 (29 months), the validation period is set as September 2017~September 2018 (13 months), and the test period is set as December 2018~December 2019 (13 months). The results of the return rate prediction study are as follows. First, the model achieved a prediction similarity level of almost 76%. After collecting time series data and preparing the final prediction model, it was confirmed that 76% of models could be achieved. All in all, the results demonstrate the reliability of the LSTM-based model for return rate prediction.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.29-41
• /
• 2022

Recently, with the development of deep learning technology, a variety of huge models with excellent performance have been devised by pre-training massive amounts of text data. However, in order for such a model to be applied to real-life services, the inference speed must be fast and the amount of computation must be low, so the technology for model compression is attracting attention. Knowledge distillation, a representative model compression, is attracting attention as it can be used in a variety of ways as a method of transferring the knowledge already learned by the teacher model to a relatively small-sized student model. However, knowledge distillation has a limitation in that it is difficult to solve problems with low similarity to previously learned data because only knowledge necessary for solving a given problem is learned in a teacher model and knowledge distillation to a student model is performed from the same point of view. Therefore, we propose a heterogeneous knowledge distillation method in which the teacher model learns a higher-level concept rather than the knowledge required for the task that the student model needs to solve, and the teacher model distills this knowledge to the student model. In addition, through classification experiments on about 18,000 documents, we confirmed that the heterogeneous knowledge distillation method showed superior performance in all aspects of learning efficiency and accuracy compared to the traditional knowledge distillation.

• Journal of Internet Computing and Services
• /
• v.25 no.3
• /
• pp.43-54
• /
• 2024

This study employs text mining techniques to compare user responses across various Over-The-Top (OTT) service platforms. The primary objective of the research is to understand user satisfaction with OTT service platforms and contribute to the formulation of more effective review strategies. The key questions addressed in this study involve identifying prominent topics and keywords in user reviews of different OTT services and comprehending platform-specific user reactions. TF-IDF is utilized to extract significant words from positive and negative reviews, while BERTopic, an advanced topic modeling technique, is employed for a more nuanced and comprehensive analysis of intricate user reviews. The results from TF-IDF analysis reveal that positive app reviews exhibit a high frequency of content-related words, whereas negative reviews display a high frequency of words associated with potential issues during app usage. Through the utilization of BERTopic, we were able to extract keywords related to content diversity, app performance components, payment, and compatibility, by associating them with content attributes. This enabled us to verify that the distinguishing attributes of the platforms vary among themselves. The findings of this study offer significant insights into user behavior and preferences, which OTT service providers can leverage to improve user experience and satisfaction. We also anticipate that researchers exploring deep learning models will find our study results valuable for conducting analyses on user review text data.

• The Korean Journal of Applied Statistics
• /
• v.37 no.4
• /
• pp.525-539
• /
• 2024

Massive multiplayer online role playing game (MMORPG) is a common type of game these days. Predicting user churn in MMORPG is a crucial task. The retention rate of users is deeply associated with the lifespan and revenue of the service. If the churn of a specific user can be predicted in advance, targeted promotions can be used to encourage their stay. Therefore, not only the accuracy of churn prediction but also the speed at which signs of churn can be detected is important. In this paper, we propose methods to identify early signs of churn by utilizing the daily predicted user retention probabilities. We train various deep learning and machine learning models using log data and estimate user retention probabilities. By analyzing the change patterns in these probabilities, we provide empirical rules for early identification of users at high risk of churn. Performance evaluations confirm that our methodology is more effective at detecting high risk users than existing methods based on login days. Finally, we suggest novel methods for customized marketing strategies. For this purpose, we provide guidelines of the percentage of accessed users who are at risk of churn.

• Therapeutic Science for Rehabilitation
• /
• v.11 no.4
• /
• pp.23-39
• /
• 2022

Objective : To summarize clinical and demographic variables and machine learning uses for predicting functional outcomes of patients with stroke. Methods : We searched PubMed, CINAHL and Web of Science to identify published articles from 2010 to 2021. The search terms were "machine learning OR data mining AND stroke AND function OR prediction OR/AND rehabilitation". Articles exclusively using brain imaging techniques, deep learning method and articles without available full text were excluded in this study. Results : Nine articles were selected for this study. Support vector machines (19.05%) and random forests (19.05%) were two most frequently used machine learning models. Five articles (55.56%) demonstrated that the impact of patient initial and/or discharge assessment scores such as modified ranking scale (mRS) or functional independence measure (FIM) on stroke patients' functional outcomes was higher than their clinical characteristics. Conclusions : This study showed that patient initial and/or discharge assessment scores such as mRS or FIM could influence their functional outcomes more than their clinical characteristics. Evaluating and reviewing initial and or discharge functional outcomes of patients with stroke might be required to develop the optimal therapeutic interventions to enhance functional outcomes of patients with stroke.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.961-973
• /
• 2020

In this manuscript, a new pansharpening model based on Convolutional Neural Network (CNN) was developed. Dilated convolution, which is one of the representative convolution technologies in CNN, was applied to the model by making it deep and complex to improve the performance of the deep learning architecture. Based on the dilated convolution, the residual network is used to enhance the efficiency of training process. In addition, we consider the spatial correlation coefficient in the loss function with traditional L1 norm. We experimented with Dilated Residual Networks (DRNet), which is applied to the structure using only a panchromatic (PAN) image and using both a PAN and multispectral (MS) image. In the experiments using KOMPSAT-3A, DRNet using both a PAN and MS image tended to overfit the spectral characteristics, and DRNet using only a PAN image showed a spatial resolution improvement over existing CNN-based models.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.569-575
• /
• 2020

The serial arc is one of factors causing electrical fires. Over past decades, various researches have been carried out to detect arc occurrences. Even though frequency analysis, wavelet, and statistical features have been used, additional steps such as transformation and feature extraction are required. On the contrary, deep learning models directly use the raw data without any feature extraction processes. Therefore, the usage of time-domain data is preferred, but the performance is not satisfactory. To solve this problem, subsequent 1-D signals are transformed into 2-D data that can feed into a convolutional neural network (CNN). Experiments validated that CNN model outperforms deep neural network (DNN) by the classification accuracy of 8.6%. In addition, data augmentation is utilized, resulting in the accuracy improvement by 14%.