• Sleep Medicine and Psychophysiology
• /
• v.5 no.2
• /
• pp.177-184
• /
• 1998

Objectives : Disturbance of sleep with or without sleep apnea may impair the memory function. Sleep deficiency, sleepiness, sleep apnea and emotional problem in sleep disorders can induce an impairment of memory function. Methods : In this study, the polysomnographies were administered to 58 sleep apnea patients and 38 sleep disorder patients without sleep apnea. Their clinical symptoms were quantitatively evaluated. Short term and long term memory were evaluated before and after polysom no graphy with Digit symbol test and Rey-Osterrieth complex figure test. And correlations among various sleep, repiratory and clinical variables were statistically studied in order to explore which variables may influence on memory function. Results and Conclusions : Results are as follows. Depth of sleep cis positively correlated with memory function. As sleep apnea increases and average saturation of blood oxygen decreases, memory function is more impaired. Emotional depression, high blood pressure, obesity or alcohol impaired memory function. However, daytime sleepiness was not significantly correlated with memory function. The possible mechanisms how above factors influence on the memory function were discussed.

• Science of Emotion and Sensibility
• /
• v.15 no.4
• /
• pp.527-540
• /
• 2012

We examined the effect of delayed and immediate rewards on short- and long-term memory performance depending on the level of stress. It has been demonstrated that delaying feedback during memory tasks could lead to better retention than presenting it immediately (a.k.a., feedback delay benefit or delay-retention effect). In this study, we manipulated stress level(high-stress or low-stress), reward-timing(delayed or immediate reward), reward-existence(500 or 0 won) and retrieval-timing(delayed or immediate memory test). On the high-stress learning condition, one week later, the number of correct answers with delayed-rewards were significantly more than that of delayed-no-rewards but there was not any difference between immediate-rewards and immediate-no-rewards. On the other hand, in the high-stressful immediate memory test, immediate-rewards only had a positive effect on memory performance. The results indicated that delayed rewards improved long-term memory performance by promoting memory consolidation and the sensitivity to rewards was higher under the high-stress condition.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.377-396
• /
• 2023

As the cryptocurrency market continues to grow, it has developed into a new financial market. The need for investment strategy research on the cryptocurrency market is also emerging. This study aims to conduct an empirical analysis on an investment methodology of cryptocurrency that combines short-term trading strategy and deep learning. Daily price data of the Ethereum was collected through the API of Upbit, the Korean cryptocurrency exchange. The investment performance of the experimental model was analyzed by finding the optimal parameters based on past data. The experimental model is a volatility breakout strategy(VBS), a Long Short Term Memory(LSTM) model, moving average cross strategy and a combined model. VBS is a short-term trading strategy that buys when volatility rises significantly on a daily basis and sells at the closing price of the day. LSTM is suitable for time series data among deep learning models, and the predicted closing price obtained through the prediction model was applied to the simple trading rule. The moving average cross strategy determines whether to buy or sell when the moving average crosses. The combined model is a trading rule made by using derived variables of the VBS and LSTM model using AND/OR for the buy conditions. The result shows that combined model is better investment performance than the single model. This study has academic significance in that it goes beyond simple deep learning-based cryptocurrency price prediction and improves investment performance by combining deep learning and short-term trading strategies, and has practical significance in that it shows the applicability in actual investment.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.144-150
• /
• 2020

Reinforcement learning is a technology that can present successful and creative solutions in many areas. This reinforcement learning technology was used to deploy containers from cloud servers to fog servers to help them learn the maximization of rewards due to reduced traffic. Leveraging reinforcement learning is aimed at predicting traffic in the network and optimizing traffic-based fog computing network environment for cloud, fog and clients. The reinforcement learning system collects network traffic data from the fog server and IoT. Reinforcement learning neural networks, which use collected traffic data as input values, can consist of Long Short-Term Memory (LSTM) neural networks in network environments that support fog computing, to learn time series data and to predict optimized traffic. Description of the input and output values of the traffic-based reinforcement learning LSTM neural network, the composition of the node, the activation function and error function of the hidden layer, the overfitting method, and the optimization algorithm.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1125-1129
• /
• 2017

LSTM(Long Short-term Memory) is a kind of RNN(Recurrent Neural Network) in which a next-state is updated by remembering the previous states. The information of calling a sequence in a malware can be defined as system call function that is called at each time. In this paper, we use calling sequences of system calls in malware codes as input for malware classification to utilize the feature remembering previous states via LSTM. We run an experiment to show that our method can classify malware and measure accuracy by changing the length of system call sequences.

• International Journal of Contents
• /
• v.15 no.4
• /
• pp.8-15
• /
• 2019

This paper presents a solution of the 'Quick, Draw! Doodle Recognition Challenge' hosted by Google. Doodles are drawings comprised of concrete representational meaning or abstract lines creatively expressed by individuals. In this challenge, a doodle is presented as a sequence of sketches. From the view of at the sketch level, to learn the pattern of strokes representing a doodle, we propose a sequential model stacked with multiple convolution layers and Long Short-Term Memory (LSTM) cells following the attention mechanism [15]. From the view at the image level, we use multiple models pre-trained on ImageNet to recognize the doodle. Finally, an ensemble and a post-processing method using the minimum cost flow algorithm are introduced to combine multiple models in achieving better results. In this challenge, our solutions garnered 11th place among 1,316 teams. Our performance was 0.95037 MAP@3, only 0.4% lower than the winner. It demonstrates that our method is very competitive. The source code for this competition is published at: https://github.com/ngxbac/Kaggle-QuickDraw.

• ETRI Journal
• /
• v.42 no.5
• /
• 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.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.320-320
• /
• 2019

유역의 수문 자료를 정확하게 분석하는 것은 수리 구조물을 효율적으로 운영하기 위한 중요한 요소이다. 인공신경망(Artificial Neural Networks, ANNs) 모형은 입 출력 자료의 비선형적인 관계를 해석할 수 있는 모형으로 강우-유출 해석 등 수문 분야에 다양하게 적용되어 왔다. 이후 기존의 인공신경망 모형을 연속적인(sequential) 자료의 분석에 더 적합하도록 개선한 회귀신경망(Recurrent Neural Networks, RNNs) 모형과 회귀신경망 모형의 '장기 의존성 문제'를 개선한 장단기메모리(Long Short-Term Memory Networks, 이하 LSTM)가 차례로 제안되었다. LSTM은 최근에 주목받는 딥 러닝(Deep learning) 기법의 하나로 수문 자료와 같은 시계열 자료의 분석에 뛰어난 성능을 보일 것으로 예상되며, 수문 분야에서 이에 대한 적용성 평가가 요구되고 있다. 본 연구에서는 인공신경망 모형과 LSTM 모형으로 유출량을 모의하여 두 모형의 성능을 비교하고 향후 LSTM 모형의 활용 가능성을 검토하고자 하였다. 나주 수위관측소의 수위 자료와 인접한 기상관측소의 강우량 자료로 모형의 입 출력 자료를 구성하여 강우 사상에 대한 시간별 유출량을 모의하였다. 연구 결과, 1시간 후의 유출량에 대해서는 두 모형 모두 뛰어난 모의 능력을 보였으나, 선행 시간이 길어질수록 LSTM의 정확성은 유지되는 반면 인공신경망 모형의 정확성은 점차 떨어지는 것으로 나타났다. 앞으로의 연구에서 유역 내 다양한 수리 구조물에 의한 유 출입량을 추가로 고려한다면 LSTM 모형의 활용성을 보다 더 확장할 수 있을 것이다.

• Journal of Information Processing Systems
• /
• v.17 no.5
• /
• pp.867-878
• /
• 2021

In context awareness and user intention tasks, dataset construction is expensive because specific domain data are required. Although pretraining with a large corpus can effectively resolve the issue of lack of data, it ignores domain knowledge. Herein, we concentrate on data domain knowledge while addressing data scarcity and accordingly propose a multi-channel long short-term memory (LSTM). Because multi-channel LSTM integrates pretrained vectors such as task and general knowledge, it effectively prevents catastrophic forgetting between vectors of task and general knowledge to represent the context as a set of features. To evaluate the proposed model with reference to the baseline model, which is a single-channel LSTM, we performed two tasks: voice phishing with context awareness and movie review sentiment classification. The results verified that multi-channel LSTM outperforms single-channel LSTM in both tasks. We further experimented on different multi-channel LSTMs depending on the domain and data size of general knowledge in the model and confirmed that the effect of multi-channel LSTM integrating the two types of knowledge from downstream task data and raw data to overcome the lack of data.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.707-720
• /
• 2021

To improve the accuracy of the recommendation system, multi-criteria recommendation systems have been widely researched. However, it is highly complicated to extract the preferred features of users and items from the data. To this end, subjective indicators, which indicate a user's priorities for personalized recommendations, should be derived. In this study, we propose a method for generating recommendation candidates by predicting multi-criteria ratings from reviews and using them to derive user priorities. Using a deep learning model based on convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), multi-criteria prediction ratings were derived from reviews. These ratings were then aggregated to form a linear regression model to predict the overall rating. This model not only predicts the overall rating but also uses the training weights from the layers of the model as the user's priority. Based on this, a new score matrix for recommendation is derived by calculating the similarity between the user and the item according to the criteria, and an item suitable for the user is proposed. The experiment was conducted by collecting the actual "TripAdvisor" dataset. For performance evaluation, the proposed method was compared with a general recommendation system based on singular value decomposition. The results of the experiments demonstrate the high performance of the proposed method.