• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.313-319
• /
• 2023

In this paper, a time series machine learning model, Long Short Term Memory (LSTM), is applied into the bubble flow noise data and the underwater projectile launch noise data to predict missing values of time-series underwater noise data. The former is mixed with bubble noise, flow noise, and fluid-induced interaction noise measured in a pipe and can be classified into three types. The latter is the noise generated when an underwater projectile is ejected from a launch tube and has a characteristic of instantaenous noise. For such types of noise, a data-driven model can be more useful than an analytical model. We constructed an LSTM model with given data and evaluated the model's performance based on the number of hidden units, the number of input sequences, and the decimation factor of signal. It is shown that the optimal LSTM model works well for new data of the same type.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.142-148
• /
• 2023

In this paper, we identify performance issues in executing compute kernels from PolyBench, which includes compute kernels that are the core computational units of various data-intensive workloads, such as deep learning and data-intensive applications, on Processing-in-Memory (PIM) devices. Therefore, using our in-house simulator, we measured and compared the various performance metrics of workloads based on traditional out-of-order and in-order processors with Processing-in-Memory-based systems. As a result, the PIM-based system improves performance compared to other computing models due to the short-term data reuse characteristic of computational kernels from PolyBench. However, some kernels perform poorly in PIM-based systems without a multi-layer cache hierarchy due to some kernel's long-term data reuse characteristics. Hence, our evaluation and analysis results suggest that further research should consider dynamic and workload pattern adaptive approaches to overcome performance degradation from computational kernels with long-term data reuse characteristics and hidden data locality.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.70-73
• /
• 1992

This paper describes the modeling of human memory using a nerve field model which is proposed for modeling the mechanism of brain mathematically. In our model, two phases of memory, retention and recollection, are focused on. The former consists of two stages, short-term memory (STM) and long-term memory (LTM). The proposed model consists of three parts, the STM Layer, LTM Layer and the Intermediate Layer between them. Each of these is constructed by a nerve field. In the STM Layer, memorized information is retained dynamically in the form of the reverberating states of units within the layer, while in the LTM Layer, it is stored statically in the form of structures of the weight on the links between units. the Intermediate Layer is introduced to translate this dynamic representation in the STM Layer to the LTNI Layer, and also to extract the static information from the STM Layer. In addition to this, we consider the recollection of information stored in the LTM. Finally, the behavior of this model is demonstrated by computer simulation.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.56 no.2
• /
• pp.243-252
• /
• 2023

Fluctuations in the price of aquaculture products have recently intensified. In particular, wholesale price fluctuations are adversely affecting consumers. Therefore, there is an emerging need for a study on forecasting the wholesale price of aquaculture products. The present study forecasted the wholesale price of olive flounder Paralichthys olivaceus, a representative farmed fish species in Korea, by constructing multivariate long-short term memory (LSTM) and gated recurrent unit (GRU) models. These deep learning models have recently been proven to be effective for forecasting in various fields. A total of 191 monthly data obtained for 17 variables were used to train and test the models. The results showed that the mean average percent error of LSTM and GRU models were 2.19% and 2.68%, respectively.

• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.268-273
• /
• 2017

Recently, deep learning encoder-based approach has been actively applied in the field of sentiment classification. However, Long Short-Term Memory network deep learning encoder, the commonly used architecture, lacks the quality of vector representation when the length of the documents is prolonged. In this study, for effective classification of the sentiment documents, we suggest the use of attention method-based deep learning encoder that generates document vector representation by weighted sum of the outputs of Long Short-Term Memory network based on importance. In addition, we propose methods to modify the attention method-based deep learning encoder to suit the sentiment classification field, which consist of a part that is to applied to window attention method and an attention weight adjustment part. In the window attention method part, the weights are obtained in the window units to effectively recognize feeling features that consist of more than one word. In the attention weight adjustment part, the learned weights are smoothened. Experimental results revealed that the performance of the proposed method outperformed Long Short-Term Memory network encoder, showing 89.67% in accuracy criteria.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.322-323
• /
• 2022

The most necessary thing for the optimal operation of a water purification plant is to accurately predict the pattern and amount of tap water used by consumers. The required amount of tap water should be delivered to the drain using a pump and stored, and the required flow rate should be supplied in a timely manner using the minimum amount of electrical energy. The short-term demand forecasting required from the point of view of energy optimization operation among water purification plant volume predictions has been made in consideration of seasons, major periods, and regional characteristics using time series analysis, regression analysis, and neural network algorithms. In this paper, we analyzed energy management methods through AI-based complex sensor applicability analysis such as LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Units), which are types of cyclic neural networks.

• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.37-47
• /
• 2024

This study presents the results of designing a system that determines the location of a person in an indoor environment based on a single IMU sensor attached to the tip of a person's shoe in an area where GPS signals are inaccessible. By adjusting for human footfall, it is possible to accurately determine human location and trajectory by correcting errors originating from the Inertial Measurement Unit (IMU) combined with advanced machine learning algorithms. Although there are various techniques to identify stepping, our study successfully recognized stepping with 98.7% accuracy using an artificial intelligence model known as Long Short-Term Memory (LSTM). Drawing upon the enhancements in our methodology, this article demonstrates a novel technique for generating a 200-meter trajectory, achieving a level of precision marked by a 2.1% error margin. Indoor pedestrian navigation systems, relying on inertial measurement units attached to the feet, have shown encouraging outcomes.

• Journal of Korean Society of Disaster and Security
• /
• v.13 no.4
• /
• pp.75-92
• /
• 2020

In most cases of the water balance analysis, the return flow ratio for each water supply was uniformly determined and applied, so it has been contained a problem that the volume of available water would be incorrectly calculated. Therefore, sewage and wastewater among the return water were focused in this study and the data-driven model was developed to forecast the outflow from the sewage treatment plant. The forecasting results of LSTM (Long Short-Term Memory), GRU (Gated Recurrent Units), and SVR (Support Vector Regression) models, which are mainly used for forecasting the time series data in most fields, were compared with the observed data to determine the optimal model parameters for forecasting outflow. As a result of applying the model, the root mean square error (RMSE) of the GRU model was smaller than those of the LSTM and SVR models, and the Nash-Sutcliffe coefficient (NSE) was higher than those of others. Thus, it was judged that the GRU model could be the optimal model for forecasting the outflow in sewage treatment plants. However, the forecasting outflow tends to be underestimated and overestimated in extreme sections. Therefore, the additional data for extreme events and reducing the minimum time unit of input data were necessary to enhance the accuracy of forecasting. If the water use of the target site was reviewed and the additional parameters that could reflect seasonal effects were considered, more accurate outflow could be forecasted to be ready for climate variability in near future. And it is expected to use as fundamental resources for establishing a reasonable river water management system based on the forecasting results.

• Journal of Korean Society on Water Environment
• /
• v.39 no.1
• /
• pp.46-60
• /
• 2023

Climate change causes fluctuations in water quality in the aquatic environment, which can cause changes in water circulation patterns and severe adverse effects on aquatic ecosystems in the future. Therefore, research is needed to predict and respond to water quality changes caused by climate change in advance. In this study, we tried to predict the dissolved oxygen (DO), chlorophyll-a, and turbidity of the Paldang reservoir for about two weeks using long short-term memory (LSTM) and gated recurrent units (GRU), which are deep learning algorithms based on recurrent neural networks. The model was built based on real-time water quality data and meteorological data. The observation period was set from July to September in the summer of 2021 (Period 1) and from March to May in the spring of 2022 (Period 2). We tried to select an algorithm with optimal predictive power for each water quality parameter. In addition, to improve the predictive power of the model, an important variable extraction technique using random forest was used to select only the important variables as input variables. In both Periods 1 and 2, the predictive power after extracting important variables was further improved. Except for DO in Period 2, GRU was selected as the best model in all water quality parameters. This methodology can be useful for preventive water quality management by identifying the variability of water quality in advance and predicting water quality in a short period.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.5
• /
• pp.574-583
• /
• 2021

Predicting shipping markets is an important issue. Such predictions form the basis for decisions on investment methods, fleet formation methods, freight rates, etc., which greatly affect the profits and survival of a company. To this end, in this study, we propose a shipping freight rate prediction model for container ships using gated recurrent units (GRUs) and long short-term memory structure. The target of our freight rate prediction is the China Container Freight Index (CCFI), and CCFI data from March 2003 to May 2020 were used for training. The CCFI after June 2020 was first predicted according to each model and then compared and analyzed with the actual CCFI. For the experimental model, a total of six models were designed according to the hyperparameter settings. Additionally, the ARIMA model was included in the experiment for performance comparison with the traditional analysis method. The optimal model was selected based on two evaluation methods. The first evaluation method selects the model with the smallest average value of the root mean square error (RMSE) obtained by repeating each model 10 times. The second method selects the model with the lowest RMSE in all experiments. The experimental results revealed not only the improved accuracy of the deep learning model compared to the traditional time series prediction model, ARIMA, but also the contribution in enhancing the risk management ability of freight fluctuations through deep learning models. On the contrary, in the event of sudden changes in freight owing to the effects of external factors such as the Covid-19 pandemic, the accuracy of the forecasting model reduced. The GRU1 model recorded the lowest RMSE (69.55, 49.35) in both evaluation methods, and it was selected as the optimal model.