• Journal of the Chungcheong Mathematical Society
• /
• v.34 no.2
• /
• pp.157-168
• /
• 2021

This study uses the benchmark interest rate of the Federal Open Market Committee (FOMC) to predict gold futures prices. For the predictions, we used the support vector machine (SVM) (a machine-learning model) and the long short-term memory (LSTM) deep-learning model. We found that the LSTM method is more accurate than the SVM method. Moreover, we applied the Boruta algorithm to demonstrate that the FOMC benchmark interest rates correlate with gold futures.

• Journal of Positioning, Navigation, and Timing
• /
• v.8 no.4
• /
• pp.209-214
• /
• 2019

Precise point positioning (PPP) requires precise orbit and clock products. International GNSS service (IGS) real-time service (RTS) data can be used in real-time for PPP, but it may not be possible to receive these corrections for a short time due to internet or hardware failure. In addition, the time required for IGS to combine RTS data from each analysis center results in a delay of about 30 seconds for the RTS data. Short-term orbit prediction can be possible because it includes the rate of correction, but the clock correction only provides bias. Thus, a short-term prediction model is needed to preidict RTS clock corrections. In this paper, we used a long short-term memory (LSTM) network to predict RTS clock correction for three minutes. The prediction accuracy of the LSTM was compared with that of the polynomial model. After applying the predicted clock corrections to the broadcast ephemeris, we performed PPP and analyzed the positioning accuracy. The LSTM network predicted the clock correction within 2 cm error, and the PPP accuracy is almost the same as received RTS data.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.4
• /
• pp.261-266
• /
• 2017

In this paper, we propose a vocal and nonvocal separation method which uses a combination of kernel model and LSTM (Long-Short Term Memory) networks. Conventional vocal and nonvocal separation methods estimate the vocal component even in sections where only non-vocal components exist. This causes a problem of the source estimation error. Therefore we combine the existing kernel based separation method with the vocal/nonvocal classification based on LSTM networks in order to overcome the limitation of the existing separation methods. We propose a parallel combined separation algorithm and series combined separation algorithm as combination structures. The experimental results verify that the proposed method achieves better separation performance than the conventional approaches.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.4
• /
• pp.433-441
• /
• 2019

In this paper, a method of estimating speech parameters for ultrasonic Doppler signals reflected from the articulatory muscles using LSTM (Long Short Term Memory) RNN (Recurrent Neural Networks) was introduced and compared with the method using MLP (Multi-Layer Perceptrons). LSTM RNN were used to estimate the Fourier transform coefficients of speech signals from the ultrasonic Doppler signals. The log energy value of the Mel frequency band and the Fourier transform coefficients, which were extracted respectively from the ultrasonic Doppler signal and the speech signal, were used as the input and reference for training LSTM RNN. The performance of LSTM RNN and MLP was evaluated and compared by experiments using test data, and the RMSE (Root Mean Squared Error) was used as a measure. The RMSE of each experiment was 0.5810 and 0.7380, respectively. The difference was about 0.1570, so that it confirmed that the performance of the method using the LSTM RNN was better.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.187-194
• /
• 2021

A person's behavioral recognition is the recognition of what a person does according to joint movements. To this end, we utilize computer vision tasks that are utilized in image processing. Human behavior recognition is a safety accident response service that combines deep learning and CCTV, and can be applied within the safety management site. Existing studies are relatively lacking in behavioral recognition studies through human joint keypoint extraction by utilizing deep learning. There were also problems that were difficult to manage workers continuously and systematically at safety management sites. In this paper, to address these problems, we propose a method to recognize risk behavior using only joint keypoints and joint motion information. AlphaPose, one of the pose estimation methods, was used to extract joint keypoints in the body part. The extracted joint keypoints were sequentially entered into the Long Short-Term Memory (LSTM) model to be learned with continuous data. After checking the behavioral recognition accuracy, it was confirmed that the accuracy of the "Lying Down" behavioral recognition results was high.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.39 no.3
• /
• pp.376-382
• /
• 2010

It has been shown that BF-7 enhances short- and long-term memory and attention in normal person. BF-7 was addressed to clinical study for children if BF-7 is also effective to children, since accumulated verification of safety and effectiveness is needed for young ages, in special. We administered BF-7 and a placebo control to two different groups of children (7-12 years old, 9.78 on averages). Their memory enhancement was tested with Rey-Kim Memory Test for Children before and after the administration of BF-7 and a placebo, in a double blinded way. The results showed that long- and short-term memories were significantly improved by the administration of BF-7. Interestingly, the degree of memory preservation, the ability of memory application and awareness of complex thing were also significantly improved. These results indicate that BF-7 is a promising substance from natural resource improving learning and memory of children as well as cognitive function of adults

• Communications for Statistical Applications and Methods
• /
• v.9 no.3
• /
• pp.577-594
• /
• 2002

For the estimation and test of long memory feature in volatilities of stock indices and individual companies semiparametric approach, Geweke and Porter-Hudak (1983), is employed. Empirical study supports the strong evidence of volatility persistence in Korean stock market. Most of indices and individual companies have the feature of long term dependence of volatility. Hence the short memory models are unable to explain the volatilities in Korean stock market.

• The Research Journal of the Costume Culture
• /
• v.27 no.1
• /
• pp.1-10
• /
• 2019

Firefighters wear Personal Protective Equipment (PPE) for protection from environmental hazards. However, due to the layers of protective functions, the PPE inevitably adds excessive weight, bulkiness, and thermal stress to firefighters. This study investigated the adverse impact of wearing PPE as an occupational stressor on the firefighter's cognitive functioning. Twenty-three firefighters who had been involved in firefighting at least for 1 year were recruited. The overall changing trend in the firefighter's cognitive functioning (short-term memory, long-term memory, and inductive reasoning) was measured by the scores of three standardized cognitive tests at the baseline and the follow-up, after participating in a moderate-intensity physical activity, wearing a full ensemble of the PPE. The study findings evinced the negative impact of the PPE on the firefighter's cognitive functioning, especially in short-term memory and inductive reasoning. No significant influence was found on the firefighter's long-term memory. The results were consistent when the participant's age and BMI were controlled. The outcomes of the present study will not only fill the gap in the literature, but also provide critical justification to stakeholders, including governments, policymakers, academic communities, and industry, for such efforts to improve human factors of the firefighter's PPE by realizing the negative consequences of the added layers and protective functions on their occupational safety. Study limitations and future directions were also discussed.

• International Journal of Advanced Culture Technology
• /
• v.7 no.2
• /
• pp.60-66
• /
• 2019

The purpose of this study was to compare the effect of educational smartphone app with the effect of learning using conventional paper material. We developed an educational app for nursing students to learn how to read blood pressure and how to take a pulse. Evaluated was the effect of the app-based education by measuring the short term memory (right after the education), the long term memory (a week later) and the satisfaction. 25 college nursing students participated for the experiment group using the app-based education and 25 for the control group using paper-based education. We applied for statistical analysis Fisher's exact test and Independent t-test. The satisfaction of the app user's appeared significantly higher than that of the paper material user's (t=2.322, p=0.024). The short term memory score was 0.23 points higher in the experimental group (6.46 points) than in the control group (6.23 points), which was not statistically significant (t =0.422, p =0.675). Similar result came for the long term memory (t=1.006, p=0.320). After adjusting for the effect of a college grade using ANCOVA, the effect on memory was significantly higher in the experiment group. There might be differences in learning ability between the experimental and the control groups.

• Structural Monitoring and Maintenance
• /
• v.5 no.1
• /
• pp.51-65
• /
• 2018

A number of sensing techniques have been implemented for detecting defects in civil infrastructures instead of onsite human inspections in structural health monitoring. However, the issue of faults in sensors has not received much attention. This issue may lead to incorrect interpretation of data and false alarms. To overcome these challenges, this article presents a deep learning-based method with a new architecture of Stateful Long Short Term Memory Neural Networks (S-LSTM NN) for detecting sensor fault without going into details of the fault features. As LSTMs are capable of learning data features automatically, and the proposed method works without an accurate mathematical model. The detection of four types of sensor faults are studied in this paper. Non-stationary acceleration responses of a three-span continuous bridge when under operational conditions are studied. A deep network model is applied to the measured bridge data with estimation to detect the sensor fault. Another set of sensor output data is used to supervise the network parameters and backpropagation algorithm to fine tune the parameters to establish a deep self-coding network model. The response residuals between the true value and the predicted value of the deep S-LSTM network was statistically analyzed to determine the fault threshold of sensor. Experimental study with a cable-stayed bridge further indicated that the proposed method is robust in the detection of the sensor fault.