• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.1108-1109
• /
• 2023

본 논문은 선박 내부 소음을 효과적으로 감소시키기 위한 ANC(Active Noise Cancellation)및 인공 지능 (AI) 결합 시스템의 개발과 적용에 관한 연구를 다룬다. 선박 환경에서의 소음은 승원의 스트레스 증가와 불편을 초래하므로, 이를 해결하기 위한 방법을 제안하고자 한다. 외부 소음과 내부 소음 데이터를 수집하고, STFT(Short-Time Fourier Transform)알고리즘을 통해 소음 데이터를 분석 가능한 형태로 전처리한다. 그 후, LSTM(Long Short-Term Memory)알고리즘을 사용하여 선박 외부에서 발생한 소음을 입력으로 받아 내부에서 들리는 외부 소음을 예측하고 제어하는 모델을 훈련시킨다. 이후 최적화 과정을 거쳐 예측 소음의 반대 파형을 생성 및 출력을 통해 ANC 를 구현한다.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.48 no.1
• /
• pp.39-49
• /
• 2011

Turbo code needs long decoding time because of iterative decoding. To communicate with high speed, we have to shorten decoding time and it is possible with parallel process. But memory contention can cause from parallel process, and it reduces performance of decoder. To avoid memory contention, QPP interleaver is proposed in 2006. In this paper, we propose MDF method which is fit to QPP interleaver, and has relatively short decoding time and reduced logic. And introduce the design of MAP decode module using MDF method. Designed decoder is targetted to FPGA of Xilinx, and its throughput is 80Mbps maximum.

• Journal of Korea Water Resources Association
• /
• v.53 no.4
• /
• pp.273-283
• /
• 2020

Quantitative forecasting of groundwater levels for the assessment of groundwater variation and vulnerability is very important. To achieve this purpose, various time series analysis and machine learning techniques have been used. In this study, we developed a prediction model based on LSTM (Long short term memory), one of the artificial neural network (ANN) algorithms, for predicting the daily groundwater level of 11 groundwater wells in Hankyung-myeon, Jeju Island. In general, the groundwater level in Jeju Island is highly autocorrelated with tides and reflected the effects of precipitation. In order to construct an input and output variables based on the characteristics of addressing data, the precipitation data of the corresponding period was added to the groundwater level data. The LSTM neural network was trained using the initial 365-day data showing the four seasons and the remaining data were used for verification to evaluate the fitness of the predictive model. The model was developed using Keras, a Python-based deep learning framework, and the NVIDIA CUDA architecture was implemented to enhance the learning speed. As a result of learning and verifying the groundwater level variation using the LSTM neural network, the coefficient of determination (R²) was 0.98 on average, indicating that the predictive model developed was very accurate.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.6
• /
• pp.34-43
• /
• 2019

The maintenance cost for road pavement is gradually increasing due to the continuous increase in road extension as well as increase in the number of old routes that have passed the public period. As a result, there is a need for a method of minimizing costs through preventative grievance preventive maintenance requires the establishment of a strategic plan through accurate prediction of road pavement. Hence, In this study, the deep neural network(DNN) and the recurrent neural network(RNN) were used in order to develop the expressway pavement damage prediction model. A superior model among these two network models was then suggested by comparing and analyzing their performance. In order to solve the RNN's vanishing gradient problem, the LSTM (Long short-term memory) circuits which are a more complicated form of the RNN structure were used. The learning result showed that the RMSE value of the RNN-LSTM model was 0.102 which was lower than the RMSE value of the DNN model, indicating that the performance of the RNN-LSTM model was superior. In addition, high accuracy of the RNN-LSTM model was verified through the comparison between the estimated average road pavement condition and the actually measured road pavement condition of the target section over time.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.5
• /
• pp.780-790
• /
• 2022

Quantitative risk levels must be presented by analyzing the causes and consequences of accidents and predicting the occurrence patterns of the accidents. For the analysis of marine accidents related to vessel traffic, research on the traffic such as collision risk analysis and navigational path finding has been mainly conducted. The analysis of the occurrence pattern of marine accidents has been presented according to the traditional statistical analysis. This study intends to present a marine accident prediction model using the statistics on marine accidents related to vessel traffic. Statistical data from 1998 to 2021, which can be accumulated by month and hourly data among the Korean domestic marine accidents, were converted into structured time series data. The predictive model was built using a long short-term memory network, which is a representative artificial intelligence model. As a result of verifying the performance of the proposed model through the validation data, the RMSEs were noted to be 52.5471 and 126.5893 in the initial neural network model, and as a result of the updated model with observed datasets, the RMSEs were improved to 31.3680 and 36.3967, respectively. Based on the proposed model, the occurrence pattern of marine accidents could be predicted by learning the features of various marine accidents. In further research, a quantitative presentation of the risk of marine accidents and the development of region-based hazard maps are required.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.8
• /
• pp.11-21
• /
• 2024

This study explores the use of virtual reality (VR) technology to identify and label key segments of the golf swing. To address the limitations of existing VR devices, we developed a platform to collect kinematic data from various VR devices using the OpenVR SDK (Software Development Kit) and SteamVR, and developed a semi-automated labeling technique to identify and label temporal changes in kinematic behavior through LSTM (Long Short-Term Memory)-based time series data analysis. The experiment consisted of 80 participants, 20 from each of the following age groups: teenage, young-adult, middle-aged, and elderly, collecting data from five swings each to build a total of 400 kinematic datasets. The proposed technique achieved consistently high accuracy (≥0.94) and F1 Score (≥0.95) across all age groups for the seven main phases of the golf swing. This work aims to lay the groundwork for segmenting exercise data and precisely assessing athletic performance on a segment-by-segment basis, thereby providing personalized feedback to individual users during future education and training.

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.11
• /
• pp.31-41
• /
• 2018

Text classification has been studied for a long time in the Natural Language Processing field. In this paper, we propose an article- and paragraph-level genre classification system using Word2Vec-based LSTM, GRU, and CNN models for large-scale English corpora. Both article- and paragraph-level classification performed best in accuracy with LSTM, which was followed by GRU and CNN in accuracy performance. Thus, it is to be confirmed that in evaluating the classification performance of LSTM, GRU, and CNN, the word sequential information for articles is better than the word feature extraction for paragraphs when the pre-trained Word2Vec-based word embeddings are used in both deep learning-based article- and paragraph-level classification tasks.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1231-1242
• /
• 2019

This paper presents a two-dimensional attention-based long short-memory (2D-ALSTM) model for stock index prediction, incorporating input attention and temporal attention mechanisms for weighting of important stocks and important time steps, respectively. The proposed model is designed to overcome the long-term dependency, stock selection, and stock volatility delay problems that negatively affect existing models. The 2D-ALSTM model is validated in a comparative experiment involving the two attention-based models multi-input LSTM (MI-LSTM) and dual-stage attention-based recurrent neural network (DARNN), with real stock data being used for training and evaluation. The model achieves superior performance compared to MI-LSTM and DARNN for stock index prediction on a KOSPI100 dataset.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.22 no.3
• /
• pp.37-58
• /
• 1997

An AI approach with tabu search is designed to solve multi-level knapsack problems. The approach performs intelligent actions with memories of historic data and learning effect. These action are developed ont only by observing the attributes of the optimal solution, the solution space, and its corresponding path to the optimal, but also by applying human intelligence, experience, and intuition with respect to the search strategies. The approach intensifies, or diversifies the search process appropriately in time and space. In order to create a good neighborhood structure, this approach uses two powerful choice rules that emphasize the impact of candidate variables on the current solution with respect to their profit contribution. "Pseudo moves", similar to "aspirations", support these choice rules during the evaluation process. For the purpose of visiting as many relevant points as possible, strategic oscillation between feasible and infeasible solutions around the boundary is applied. To avoid redundant moves, short-term (tabu-lists), intemediate-term (cycle-detection), and long-term (recording frequency and significant solutions for diversfication) memories are used. Test results show that among the 45 generated problems (these problems pose significant or insurmountable challenges to exact methods) the approach produces the optimal solutions in 39 cases.lutions in 39 cases.