• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.21-33
• /
• 2022

Recently, the recommender system has been widely used in various fields such as movies, music, online shopping, and social media, and in the meantime, the recommender model has been developed from correlation analysis through the Apriori model, which can be said to be the first-generation model in the recommender system field. In 2005, many models have been proposed, including deep learning-based models, which are receiving a lot of attention within the recommender model. The recommender model can be classified into a collaborative filtering method, a content-based method, and a hybrid method that uses these two methods integrally. However, these basic methods are gradually losing their status as methodologies in the field as they fail to adapt to internal and external changing factors such as the rapidly changing user-item interaction and the development of big data. On the other hand, the importance of deep learning methodologies in recommender systems is increasing because of its advantages such as nonlinear transformation, representation learning, sequence modeling, and flexibility. In this paper, among deep learning methodologies, RNN, CNN, and GAN-based models suitable for sequential modeling that can accurately and flexibly analyze user-item interactions are classified, compared, and analyzed.

• Journal of Digital Contents Society
• /
• v.19 no.3
• /
• pp.435-443
• /
• 2018

Recently, with the explosive development of computing power, various methods such as RNN and CNN have been proposed under the name of Deep Learning, which solve many problems of Computer Vision have. The Generative Adversarial Network, released in 2014, showed that the problem of computer vision can be sufficiently solved in unsupervised learning, and the generation domain can also be studied using learned generators. GAN is being developed in various forms in combination with various models. Machine learning has difficulty in collecting data. If it is too large, it is difficult to refine the effective data set by removing the noise. If it is too small, the small difference becomes too big noise, and learning is not easy. In this paper, we apply a deep CNN model for extracting facial region in image frame to GAN model as a preprocessing filter, and propose a method to produce composite images of various facial expressions by stably learning with limited collection data of two persons.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.1
• /
• pp.44-52
• /
• 2001

This paper describes an off-line method for recognizing totally unconstrained handwritten digits using modified chaotic neural networks(MCNN). The chaotic neural networks(CNN) is modified to be a useful network for solving complex pattern problems by enforcing dynamic characteristics and learning process. Since the MCNN has the characteristics of highly nonlinear dynamics in structure and neuron itself, it can be an appropriate network for the robust classification of complex handwritten digits. Digit identification starts with extraction of features from the raw digit images and then recognizes digits using the MCNN based classifier. The performance of the MCNN classifier is evaluated on the numeral database of Concordia University, Montreal, Canada. For the relative comparison of recognition performance, the MCNN classifier is compared with the recurrent neural networks(RNN) classifier. Experimental results show that the classification rate is 98.0%. It indicates that the MCNN classifier outperforms the RNN classifier as well as other classifiers that have been reported on the same database.

• Communications for Statistical Applications and Methods
• /
• v.31 no.1
• /
• pp.105-127
• /
• 2024

We propose recurrent neural network (RNN) methods for forecasting realized volatility (RV). The data are RVs of ten major stock price indices, four from the US, and six from the EU. Forecasts are made for relative ratio of adjacent RVs instead of the RV itself in order to avoid the out-of-scale issue. Forecasts of RV ratios distribution are first constructed from which those of RVs are computed which are shown to be better than forecasts constructed directly from RV. The apparent asymmetry of RV ratio is addressed by the Piecewise Min-max (PM) normalization. The serial dependence of the ratio data renders us to consider two architectures, long short-term memory (LSTM) and gated recurrent unit (GRU). The hyperparameters of LSTM and GRU are tuned by the nested cross validation. The RNN forecast with the PM normalization and ratio transformation is shown to outperform other forecasts by other RNN models and by benchmarking models of the AR model, the support vector machine (SVM), the deep neural network (DNN), and the convolutional neural network (CNN).

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.90-101
• /
• 2022

Buses are a popular means of transportation. As such, thorough preparation is needed for passenger safety management. However, the safety system is insufficient because there are accidents such as a death accident occurred when the bus departed without recognizing the elderly approaching to get on in 2018. There is a safety system that prevents pinching accidents through sensors on the back door stairs, but such a system does not prevent accidents that occur in the process of getting on and off like the above accident. If it is possible to predict the intention of bus passengers to get on and off, it will help to develop a safety system to prevent such accidents. However, studies predicting the intention of passengers to get on and off are insufficient. Therefore, in this paper, we propose a 1×1 CNN3D-based getting on and off intention prediction model using skeleton keypoints of passengers extracted from the camera image attached to the bus through UDP-Pose. The proposed model shows approximately 1~2% higher accuracy than the RNN and LSTM models in predicting passenger's getting on and off intentions.

• Journal of the Society of Disaster Information
• /
• v.18 no.3
• /
• pp.433-443
• /
• 2022

Purpose: In this paper, we propose a study of deep learning algorithms that estimate and predict sarcopenia by exploiting the high penetration rate of smart devices. Method: To utilize deep learning techniques, experimental data were collected by using the inertial sensor embedded in the smart device. We implemented a smart device application for data collection. The data are collected by labeling normal and abnormal gait and five states of running, falling and squat posture. Result: The accuracy was analyzed by comparative analysis of LSTM, CNN, and RNN models, and binary classification accuracy of 99.87% and multiple classification accuracy of 92.30% were obtained using the CNN-LSTM fusion algorithm. Conclusion: A study was conducted using a smart sensoring device, focusing on the fact that gait abnormalities occur for people with sarcopenia. It is expected that this study can contribute to strengthening the safety issues caused by sarcopenia.

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.495-505
• /
• 2019

Typical algorithms of deep learning include CNN(Convolutional Neural Networks), which are mainly used for image recognition, and RNN(Recurrent Neural Networks), which are used mainly for speech recognition and natural language processing. Among them, CNN is able to learn from filters that generate feature maps with algorithms that automatically learn features from data, making it mainstream with excellent performance in image recognition. Since then, various algorithms such as R-CNN and others have appeared in object detection to improve performance of CNN, and algorithms such as YOLO(You Only Look Once) and SSD(Single Shot Multi-box Detector) have been proposed recently. However, since these deep learning-based detection algorithms determine the success of the detection in the still images, stable object tracking and detection in the video requires separate tracking capabilities. Therefore, this paper proposes a method of combining Kalman filters into deep learning-based detection networks for improved object tracking and detection performance in the video. The detection network used YOLO v2, which is capable of real-time processing, and the proposed method resulted in 7.7% IoU performance improvement over the existing YOLO v2 network and 20 fps processing speed in FHD images.

• Communications for Statistical Applications and Methods
• /
• v.27 no.3
• /
• pp.313-326
• /
• 2020

Deep Learning is the most important key to the development of Artificial Intelligence (AI). There are several distinguishable architectures of neural networks such as MLP, CNN, and RNN. Among them, we try to understand one of the main architectures called Recurrent Neural Network (RNN) that differs from other networks in handling sequential data, including time series and texts. As one of the main tasks recently in Natural Language Processing (NLP), we consider Neural Machine Translation (NMT) using RNNs. We also summarize fundamental structures of the recurrent networks, and some topics of representing natural words to reasonable numeric vectors. We organize topics to understand estimation procedures from representing input source sequences to predict target translated sequences. In addition, we apply multiple translation models with Gated Recurrent Unites (GRUs) in Keras on English-Korean sentences that contain about 26,000 pairwise sequences in total from two different corpora, colloquialism and news. We verified some crucial factors that influence the quality of training. We found that loss decreases with more recurrent dimensions and using bidirectional RNN in the encoder when dealing with short sequences. We also computed BLEU scores which are the main measures of the translation performance, and compared them with the score from Google Translate using the same test sentences. We sum up some difficulties when training a proper translation model as well as dealing with Korean language. The use of Keras in Python for overall tasks from processing raw texts to evaluating the translation model also allows us to include some useful functions and vocabulary libraries as well.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.1023-1025
• /
• 2019

Coal and Natural gas are two biggest contributors to a generation of energy throughout the world. Most of these resources create environmental pollution while making energy affecting the natural habitat. Many approaches have been proposed as alternatives to these sources. One of the leading alternatives is Solar Energy which is usually harnessed using solar farms. In artificial intelligence, the most researched area in recent times is machine learning. With machine learning, many tasks which were previously thought to be only humanly doable are done by machine. Neural networks have two major subtypes i.e. Convolutional neural networks (CNN) which are used primarily for classification and Recurrent neural networks which are utilized for time-series predictions. In this paper, we predict energy generated by solar fields and optimal angles for solar panels in these farms for the upcoming seven days using environmental and historical data. We experiment with multiple configurations of RNN using Vanilla and LSTM (Long Short-Term Memory) RNN. We are able to achieve RSME of 0.20739 using LSTMs.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.253-254
• /
• 2018

본 논문은 비디오기반 행동인식을 연구하였으며, 기존의 구조를 참조하여 더 높은 인식률을 위한 새로운 구조를 제안한다. 딥러닝의 기본인 CNN과 RNN을 베이스로 한 구조이며 UCF-101 이라는 Data Set를 사용하였다.