• ETRI Journal
• /
• 제46권3호
• /
• pp.379-391
• /
• 2024

To meet increasing traffic requirements in mobile networks, small base stations (SBSs) are densely deployed, overlapping existing network architecture and increasing system capacity. However, densely deployed SBSs increase energy consumption and interference. Although these problems already exist because of densely deployed SBSs, even more SBSs are needed to meet increasing traffic demands. Hence, base station (BS) switching operations have been used to minimize energy consumption while guaranteeing quality-of-service (QoS) for users. In this study, to optimize energy efficiency, we propose the use of deep reinforcement learning (DRL) to create a BS switching operation strategy with a traffic prediction model. First, a federated long short-term memory (LSTM) model is introduced to predict user traffic demands from user trajectory information. Next, the DRL-based BS switching operation scheme determines the switching operations for the SBSs using the predicted traffic demand. Experimental results confirm that the proposed scheme outperforms existing approaches in terms of energy efficiency, signal-to-interference noise ratio, handover metrics, and prediction performance.

• 산업경영시스템학회지
• /
• 제46권1호
• /
• pp.105-111
• /
• 2023

Recently, research on prediction algorithms using deep learning has been actively conducted. In addition, algorithmic trading (auto-trading) based on predictive power of artificial intelligence is also becoming one of the main investment methods in stock trading field, building its own history. Since the possibility of human error is blocked at source and traded mechanically according to the conditions, it is likely to be more profitable than humans in the long run. In particular, for the virtual currency market at least for now, unlike stocks, it is not possible to evaluate the intrinsic value of each cryptocurrencies. So it is far effective to approach them with technical analysis and cryptocurrency market might be the field that the performance of algorithmic trading can be maximized. Currently, the most commonly used artificial intelligence method for financial time series data analysis and forecasting is Long short-term memory(LSTM). However, even t4he LSTM also has deficiencies which constrain its widespread use. Therefore, many improvements are needed in the design of forecasting and investment algorithms in order to increase its utilization in actual investment situations. Meanwhile, Prophet, an artificial intelligence algorithm developed by Facebook (META) in 2017, is used to predict stock and cryptocurrency prices with high prediction accuracy. In particular, it is evaluated that Prophet predicts the price of virtual currencies better than that of stocks. In this study, we aim to show Prophet's virtual currency price prediction accuracy is higher than existing deep learning-based time series prediction method. In addition, we execute mock investment with Prophet predicted value. Evaluating the final value at the end of the investment, most of tested coins exceeded the initial investment recording a positive profit. In future research, we continue to test other coins to determine whether there is a significant difference in the predictive power by coin and therefore can establish investment strategies.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.411-412
• /
• 2023

Speech emotion recognition(SER) is one of the interesting topics in the machine learning field. By developing SER, we can get numerous benefits. By using a convolutional neural network and Long Short Term Memory (LSTM ) method as a part of Artificial intelligence, the SER system can be built.

• 한국컴퓨터정보학회논문지
• /
• 제26권10호
• /
• pp.179-184
• /
• 2021

본 논문에서는 딥러닝 기반의 순환신경망을 이용하여 선박 연료유 예측을 시도하였다. 해운업에서는 선박 운항비에서 연료유가 차지하는 비중이 가장 크고 가격 변동성도 크기 때문에, 해운 기업은 합리적이고 과학저인 방법으로 연료유를 예측하여 시장경쟁력을 확보할 수 있다. 본 논문에서는 순환신경망 모델 3가지(RNN, LSTM, GRU)를 이용하여 싱가폴의 HSFO 380CST 벙커유 가격을 단기 예측하였다. 예측결과, 첫째, 선박 연료유 단기적 예측을 위해서는 장기 메모리를 사용하는 LSTM, GRU보다는 일반적인 RNN 모델의 성능이 우수한 것으로 분석되어, 장기적 정보의 예측 기여가 낮은 것으로 분석되었다. 둘째, 계량경제학 모델을 사용한 선행연구와 비교하여 순환신경망 모델의 예측성능이 우수한 것으로 분석되어 연료유가의 비선형적 특성을 고려한 순환신경망 모델을 통한 예측 연구의 필요성을 확인하였다. 연구의 결과는 선박 연료유의 단기 예측을 통하여 해운기업의 선박 연료유 수급 결정과 같은 의사결정에 도움이 될 수 있을 것으로 기대된다.

• Structural Monitoring and Maintenance
• /
• 제7권2호
• /
• pp.109-124
• /
• 2020

Benefiting from the massive monitoring data collected by the Structural health monitoring (SHM) system, scholars can grasp the complex environmental effects and structural state during structure operation. However, the monitoring data is often missing due to sensor faults and other reasons. It is necessary to study the recovery method of missing monitoring data. Taking the structural temperature monitoring data of Nanjing Dashengguan Yangtze River Bridge as an example, the long short-term memory (LSTM) network-based recovery method for missing structural temperature data is proposed in this paper. Firstly, the prediction results of temperature data using LSTM network, support vector machine (SVM), and wavelet neural network (WNN) are compared to verify the accuracy advantage of LSTM network in predicting time series data (such as structural temperature). Secondly, the application of LSTM network in the recovery of missing structural temperature data is discussed in detail. The results show that: the LSTM network can effectively recover the missing structural temperature data; incorporating more intact sensor data as input will further improve the recovery effect of missing data; selecting the sensor data which has a higher correlation coefficient with the data we want to recover as the input can achieve higher accuracy.

• 한국군사과학기술학회지
• /
• 제22권2호
• /
• pp.278-286
• /
• 2019

Conventional methods for selecting jamming techniques in electronic warfare are based on libraries in which a list of jamming techniques for radar signals is recorded. However, the choice of jamming techniques by the library is limited when modified signals are received. In this paper, we propose a method to predict the jamming technique for radar signals by using deep learning methods. Long short-term memory(LSTM) is a deep running method which is effective for learning the time dependent relationship in sequential data. In order to determine the optimal LSTM model structure for jamming technique prediction, we test the learning parameter values that should be selected, such as the number of LSTM layers, the number of fully-connected layers, optimization methods, the size of the mini batch, and dropout ratio. Experimental results demonstrate the competent performance of the LSTM model in predicting the jamming technique for radar signals.

• Journal of Information Processing Systems
• /
• 제18권1호
• /
• pp.115-129
• /
• 2022

Adopting Internet of Things (IoT)-based technologies in smart homes helps users analyze home appliances electricity consumption for better overall cost monitoring. The IoT application like smart home system (SHS) could suffer from large missing values gaps due to several factors such as security attacks, sensor faults, or connection errors. In this paper, a novel framework has been proposed to predict large gaps of missing values from the SHS home appliances electricity consumption time-series datasets. The framework follows a series of steps to detect, predict and reconstruct the input time-series datasets of missing values. A hybrid convolutional neural network-long short term memory (CNN-LSTM) neural network used to forecast large missing values gaps. A comparative experiment has been conducted to evaluate the performance of hybrid CNN-LSTM with its single variant CNN and LSTM in forecasting missing values. The experimental results indicate a performance superiority of the CNN-LSTM model over the single CNN and LSTM neural networks.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.415-415
• /
• 2023

홍수는 일반적으로 많은 피해와 인명 손실을 초래하는 자연재해 중 하나로, 홍수위 예측은 이를 방지하고 대처하는 데 중요한 역할을 한다. 최근 기계학습 기술을 이용하여 홍수위 예측 모델을 개발하고자 하는 연구가 많이 진행되고 있다. 특히, LSTM(long short-term memory) 모형은 시계열 예측에 대해 검증된 모형으로 홍수위 예측 연구에도 활발하게 적용되고 있다. 하지만 기계학습 모델의 학습 성능은 하이퍼파라미터의 값에 영향을 크게 받을 수 있으며, 특히 집중호우로 인해 수위가 급변하는 경우에는 과거 시계열 자료에 영향을 받는 LSTM 모형의 예측 성능이 오히려 낮게 나타날 수 있다. 따라서 본 연구에서는 홍수위 예측시 LSTM 모형의 예측 성능을 향상시킬 수 있는 세부 하이퍼파라미터 값을 분석하여 최적의 하이퍼파라미터 조합을 제안하고자 한다. 이를 위해 하이퍼파라미터 조정을 위한 자동화 도구인 W&B(Weights&Bias)의 Sweep 기능을 적용하고자 한다. 본 연구를 통해 LSTM 모형을 적용한 홍수위 예측의 정확도를 향상시키는 데에 기여할 수 있을 것으로 기대된다.

• ETRI Journal
• /
• 제42권5호
• /
• pp.761-772
• /
• 2020

This paper presents an automatic proficiency assessment method for a non-native Korean read utterance using bidirectional long short-term memory (BLSTM)-based acoustic models (AMs) and speech data augmentation techniques. Specifically, the proposed method considers two scenarios, with and without prompted text. The proposed method with the prompted text performs (a) a speech feature extraction step, (b) a forced-alignment step using a native AM and non-native AM, and (c) a linear regression-based proficiency scoring step for the five proficiency scores. Meanwhile, the proposed method without the prompted text additionally performs Korean speech recognition and a subword un-segmentation for the missing text. The experimental results indicate that the proposed method with prompted text improves the performance for all scores when compared to a method employing conventional AMs. In addition, the proposed method without the prompted text has a fluency score performance comparable to that of the method with prompted text.

• 한국IT서비스학회지
• /
• 제17권4호
• /
• pp.75-83
• /
• 2018

Enterprises need to monitor systems for reliable IT service operations to quickly detect and respond to events affecting the service, thereby preventing failures. Events in non-critical systems can be seen as a precursor to critical system incidents. Therefore, event relationship analysis in the operation of IT services can proactively recognize and prevent faults by identifying non-critical events and their relationships with incidents. This study used the Recurrent Neural Network and Long Short Term Memory techniques to create a model to analyze event relationships in a system and to verify which models are suitable for analyzing event relationships. Verification has shown that both models are capable of analyzing event relationships and that RNN models are more suitable than LSTM models. Based on the pattern of events occurring, this model is expected to support the prediction of the next occurrence of events and help identify the root cause of incidents to help prevent failures and improve the quality of IT services.