• Journal of the Korea Society of Computer and Information
• /
• v.28 no.5
• /
• pp.155-161
• /
• 2023

97.5% of our country's exports and 87.2% of imports are transported by sea, making ports an important component of the Korean economy. To efficiently operate these ports, it is necessary to improve the short-term prediction of port water volume through scientific research methods. Previous research has mainly focused on long-term prediction for large-scale infrastructure investment and has largely concentrated on container port water volume. In this study, short-term predictions for petroleum and liquefied gas cargo water volume were performed for Ulsan Port, one of the representative petroleum ports in Korea, and the prediction performance was confirmed using the deep learning model LSTM (Long Short Term Memory). The results of this study are expected to provide evidence for improving the efficiency of port operations by increasing the accuracy of demand predictions for petroleum and liquefied gas cargo water volume. Additionally, the possibility of using LSTM for predicting not only container port water volume but also petroleum and liquefied gas cargo water volume was confirmed, and it is expected to be applicable to future generalized studies through further research.

• Journal of Korea Trade
• /
• v.25 no.4
• /
• pp.17-36
• /
• 2021

Purpose - This study provides useful information to stakeholders by forecasting the tramp shipping market, which is a completely competitive market and has a huge fluctuation in freight rates due to low barriers to entry. Moreover, this study provides the most effective parameters for Baltic Dry Index (BDI) prediction and an optimal model by analyzing and comparing deep learning models such as the artificial neural network (ANN), recurrent neural network (RNN), and long short-term memory (LSTM). Design/methodology - This study uses various data models based on big data. The deep learning models considered are specialized for time series models. This study includes three perspectives to verify useful models in time series data by comparing prediction accuracy according to the selection of external variables and comparison between models. Findings - The BDI research reflecting the latest trends since 2015, using weekly data from 1995 to 2019 (25 years), is employed in this study. Additionally, we tried finding the best combination of BDI forecasts through the input of external factors such as supply, demand, raw materials, and economic aspects. Moreover, the combination of various unpredictable external variables and the fundamentals of supply and demand have sought to increase BDI prediction accuracy. Originality/value - Unlike previous studies, BDI forecasts reflect the latest stabilizing trends since 2015. Additionally, we look at the variation of the model's predictive accuracy according to the input of statistically validated variables. Moreover, we want to find the optimal model that minimizes the error value according to the parameter adjustment in the ANN model. Thus, this study helps future shipping stakeholders make decisions through BDI forecasts.

• Toxicological Research
• /
• v.31 no.4
• /
• pp.347-354
• /
• 2015

Excess manganese (Mn) is neurotoxic. Increased manganese stores in the brain are associated with a number of behavioral problems, including motor dysfunction, memory loss and psychiatric disorders. We previously showed that the transport and neurotoxicity of manganese after intranasal instillation of the metal are altered in Hfe-deficient mice, a mouse model of the iron overload disorder hereditary hemochromatosis (HH). However, it is not fully understood whether loss of Hfe function modifies Mn neurotoxicity after ingestion. To investigate the role of Hfe in oral Mn toxicity, we exposed Hfe-knockout ($Hfe^{-/-}$) and their control wild-type ($Hfe^{+/+}$) mice to $MnCl_2$ in drinking water (5 mg/mL) for 5 weeks. Motor coordination and spatial memory capacity were determined by the rotarod test and the Barnes maze test, respectively. Brain and liver metal levels were analyzed by inductively coupled plasma mass spectrometry. Compared with the water-drinking group, mice drinking Mn significantly increased Mn concentrations in the liver and brain of both genotypes. Mn exposure decreased iron levels in the liver, but not in the brain. Neither Mn nor Hfe deficiency altered tissue concentrations of copper or zinc. The rotarod test showed that Mn exposure decreased motor skills in $Hfe^{+/+}$ mice, but not in $Hfe^{-/-}$ mice (p = 0.023). In the Barns maze test, latency to find the target hole was not altered in Mn-exposed $Hfe^{+/+}$ compared with water-drinking $Hfe^{+/+}$ mice. However, Mn-exposed $Hfe^{-/-}$ mice spent more time to find the target hole than Mn-drinking $Hfe^{+/+}$ mice (p = 0.028). These data indicate that loss of Hfe function impairs spatial memory upon Mn exposure in drinking water. Our results suggest that individuals with hemochromatosis could be more vulnerable to memory deficits induced by Mn ingestion from our environment. The pathophysiological role of HFE in manganese neurotoxicity should be carefully examined in patients with HFE-associated hemochromatosis and other iron overload disorders.

• Molecules and Cells
• /
• v.39 no.8
• /
• pp.603-610
• /
• 2016

Recently, an increasing number of studies have focused on the effects of CD4+ T cell on cognitive function. However, the changes of Th2 cytokines in restricted CD4+ T cell receptor (TCR) repertoire model and their effects on the adult hippocampal neurogenesis and memory are not fully understood. Here, we investigated whether and how the mice with restricted CD4+ repertoire TCR exhibit learning and memory impairment by using OT-II mice. OT-II mice showed decreased adult neurogenesis in hippocampus and short- and long- term memory impairment. Moreover, Th2 cytokines in OT-II mice are significantly increased in peripheral organs and IL-4 is significantly increased in brain. Finally, IL-4 treatment significantly inhibited the proliferation of cultured adult rat hippocampal neural stem cells. Taken together, abnormal level of Th2 cytokines can lead memory dysfunction via impaired adult neurogenesis in OT-II transgenic.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1328-1336
• /
• 2019

To maintain the safe and optimal performance of batteries, accurate estimation of state of charge (SOC) is critical. In this paper, Long short-term memory network (LSTM) based on the artificial intelligence algorithm is applied to address the problem of the conventional coulomb-counting method. Different discharge cycles are concatenated to form the dataset for training and verification. In oder to improve the quality of input data for learning, preprocessing was performed. In addition, we compared learning ability and SOC estimation performance according to the structure of LSTM model and hyperparameter setup. The trained model was verified with a UDDS profile and achieved estimated accuracy of RMSE 0.82% and MAX 2.54%.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.23-30
• /
• 2022

Deep learning analyzes data to discover a series of rules and anticipates the future, helping us in various ways in our lives. For example, prediction of stock prices and agricultural prices. In this research, the results of solar photovoltaic power generation accompanied by weather are analyzed through deep learning in situations where the importance of solar energy use increases, and the amount of power generation is predicted. In this research, we propose a model using LSTM(Long Short Term Memory network) that stand out in time series data prediction. And we compare LSTM's performance with CNN(Convolutional Neural Network), which is used to analyze various dimensions of data, including images, and CNN-LSTM, which combines the two models. The performance of the three models was compared by calculating the MSE, RMSE, R-Squared with the actual value of the solar photovoltaic power generation performance and the predicted value. As a result, it was found that the performance of the LSTM model was the best. Therefor, this research proposes predicting solar photovoltaic power generation using LSTM.

• Biomolecules & Therapeutics
• /
• v.24 no.3
• /
• pp.328-337
• /
• 2016

We examined whether wogonin (WO) improved hippocampal neuronal activity, behavioral alterations and cognitive impairment, in rats induced by administration of trimethyltin (TMT), an organotin compound that is neurotoxic to these animals. The ability of WO to improve cognitive efficacy in the TMT-induced neurodegenerative rats was investigated using a passive avoidance test, and the Morris water maze test, and using immunohistochemistry to detect components of the acetylcholinergic system, brain-derived neurotrophic factor (BDNF), and cAMP-response element-binding protein (CREB) expression. Rats injected with TMT showed impairments in learning and memory and daily administration of WO improved memory function, and reduced aggressive behavior. Administration of WO significantly alleviated the TMT-induced loss of cholinergic immunoreactivity and restored the hippocampal expression levels of BDNF and CREB proteins and their encoding mRNAs to normal levels. These findings suggest that WO might be useful as a new therapy for treatment of various neurodegenerative diseases.

• Journal of Korea Multimedia Society
• /
• v.13 no.4
• /
• pp.504-511
• /
• 2010

In this paper, we propose the face region recognition system for City-Security CCTV(Closed Circuit Television) using hippocampal neural network which is modelling of human brain's hippocampus. This system is composed of feature extraction, learning and recognition part. The feature extraction part is constructed using PCA(Principal Component Analysis) and LDA(Linear Discriminants Analysis). In the learning part, it can label the features of the image-data which are inputted according to the order of hippocampal neuron structure to reaction-pattern according to the adjustment of a good impression in a dentate gyrus and remove the noise through the auto-associative memory in the CA3 region. In the CA1 region receiving the information of the CA3, it can make long-term memory learned by neuron. Experiments confirm the each recognition rate, that are shape change and light change. The experimental results show that we can compare a feature extraction and learning method proposed in this paper of any other methods, and we can confirm that the proposed method is superior to existing methods.

• 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.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.1
• /
• pp.70-85
• /
• 2021

Deep learning methodology, which has been actively studied in recent years, has improved the performance of artificial intelligence. Accordingly, systems utilizing deep learning have been proposed in various industries. In traffic systems, spatio-temporal graph modeling using GNN was found to be effective in predicting traffic speed. Still, it has a disadvantage that the model is trained inefficiently due to the memory bottleneck. Therefore, in this study, the road network is clustered through the graph clustering algorithm to reduce memory bottlenecks and simultaneously achieve superior performance. In order to verify the proposed method, the similarity of road speed distribution was measured using Jensen-Shannon divergence based on the analysis result of Incheon UTIC data. Then, the road network was clustered by spectrum clustering based on the measured similarity. As a result of the experiments, it was found that when the road network was divided into seven networks, the memory bottleneck was alleviated while recording the best performance compared to the baselines with MAE of 5.52km/h.