• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.109-121
• /
• 2024

In various manufacturing processes such as textiles and automobiles, when equipment breaks down or stops, the machines do not work, which leads to time and financial losses for the company. Therefore, it is important to detect equipment abnormalities in advance so that equipment failures can be predicted and repaired before they occur. Most equipment failures are caused by bearing failures, which are essential parts of equipment, and detection bearing anomaly is the essence of PHM(Prognostics and Health Management) research. In this paper, we propose a preprocessing algorithm called SWT-SVD, which analyzes vibration signals from bearings and apply it to an anomaly transformer, one of the time series anomaly detection model networks, to implement bearing anomaly detection model. Vibration signals from the bearing manufacturing process contain noise due to the real-time generation of sensor values. To reduce noise in vibration signals, we use the Stationary Wavelet Transform to extract frequency components and perform preprocessing to extract meaningful features through the Singular Value Decomposition algorithm. For experimental validation of the proposed SWT-SVD preprocessing method in the bearing anomaly detection model, we utilize the PHM-2012-Challenge dataset provided by the IEEE PHM Conference. The experimental results demonstrate significant performance with an accuracy of 0.98 and an F1-Score of 0.97. Additionally, to substantiate performance improvement, we conduct a comparative analysis with previous studies, confirming that the proposed preprocessing method outperforms previous preprocessing methods in terms of performance.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.57-67
• /
• 2024

This research investigates training methods for large language models to accurately identify sentiments and comprehend information about increasing and decreasing fluctuations in the financial domain. The main goal is to identify suitable datasets that enable these models to effectively understand expressions related to financial increases and decreases. For this purpose, we selected sentences from Wall Street Journal that included relevant financial terms and sentences generated by GPT-3.5-turbo-1106 for post-training. We assessed the impact of these datasets on language model performance using Financial PhraseBank, a benchmark dataset for financial sentiment analysis. Our findings demonstrate that post-training FinBERT, a model specialized in finance, outperformed the similarly post-trained BERT, a general domain model. Moreover, post-training with actual financial news proved to be more effective than using generated sentences, though in scenarios requiring higher generalization, models trained on generated sentences performed better. This suggests that aligning the model's domain with the domain of the area intended for improvement and choosing the right dataset are crucial for enhancing a language model's understanding and sentiment prediction accuracy. These results offer a methodology for optimizing language model performance in financial sentiment analysis tasks and suggest future research directions for more nuanced language understanding and sentiment analysis in finance. This research provides valuable insights not only for the financial sector but also for language model training across various domains.

• Convergence Security Journal
• /
• v.24 no.1
• /
• pp.59-68
• /
• 2024

With advancements in artificial intelligence technology, intelligent CCTV systems are being deployed across various environments, such as river bridges and construction sites. However, a conflict arises regarding the opening and closing of rooftop access points due to concerns over potential accidents and crime incidents and their role as emergency evacuation spaces. While the relevant law typically mandates the constant opening of designated rooftop access points, closures are often tacitly permitted in practice for security reasons, with a lack of appropriate legal measures. In this context, this study proposes a detection system utilizing intelligent CCTV to respond to emergencies that may occur on rooftops. We develop a system based on the YOLOv5 object detection model to detect assault and suicide attempts by jumping, introducing a new metric to assess them. Experimental results demonstrate that the proposed system rapidly detects assault and suicide attempts with high accuracy. Additionally, through a legal analysis of rooftop access point management, deficiencies in the legal framework regarding rooftop access and CCTV installation are identified, and improvement measures are proposed. With technological and legal improvements, we believe that crime and accident incidents in rooftop environments will decrease.

• Korean Journal of Radiology
• /
• v.21 no.10
• /
• pp.1165-1177
• /
• 2020

Objective: To assess the feasibility of applying a deep learning-based denoising technique to coronary CT angiography (CCTA) along with iterative reconstruction for additional noise reduction. Materials and Methods: We retrospectively enrolled 82 consecutive patients (male:female = 60:22; mean age, 67.0 ± 10.8 years) who had undergone both CCTA and invasive coronary artery angiography from March 2017 to June 2018. All included patients underwent CCTA with iterative reconstruction (ADMIRE level 3, Siemens Healthineers). We developed a deep learning based denoising technique (ClariCT.AI, ClariPI), which was based on a modified U-net type convolutional neural net model designed to predict the possible occurrence of low-dose noise in the originals. Denoised images were obtained by subtracting the predicted noise from the originals. Image noise, CT attenuation, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were objectively calculated. The edge rise distance (ERD) was measured as an indicator of image sharpness. Two blinded readers subjectively graded the image quality using a 5-point scale. Diagnostic performance of the CCTA was evaluated based on the presence or absence of significant stenosis (≥ 50% lumen reduction). Results: Objective image qualities (original vs. denoised: image noise, 67.22 ± 25.74 vs. 52.64 ± 27.40; SNR [left main], 21.91 ± 6.38 vs. 30.35 ± 10.46; CNR [left main], 23.24 ± 6.52 vs. 31.93 ± 10.72; all p < 0.001) and subjective image quality (2.45 ± 0.62 vs. 3.65 ± 0.60, p < 0.001) improved significantly in the denoised images. The average ERDs of the denoised images were significantly smaller than those of originals (0.98 ± 0.08 vs. 0.09 ± 0.08, p < 0.001). With regard to diagnostic accuracy, no significant differences were observed among paired comparisons. Conclusion: Application of the deep learning technique along with iterative reconstruction can enhance the noise reduction performance with a significant improvement in objective and subjective image qualities of CCTA images.

• Journal of Korean Society of Archives and Records Management
• /
• v.24 no.3
• /
• pp.23-44
• /
• 2024

In recent years, there has been a significant increase in the importance of curation services that analyze user information requests to provide tailored information within extensive information resources. This study aims to identify user information needs by analyzing search term logs from the Presidential Archives Portal to enhance the utilization value of presidential records, which possess high historical significance. In addition, by evaluating the portal's search performance, this study seeks to determine whether the Presidential Archives Portal is providing archival information services that meet users' information needs and to suggest areas for improvement through digital record curation services. To achieve these objectives, topic analysis and word network analysis were conducted based on search term logs spanning the past eight years. The search quality of the Presidential Archives Portal was evaluated from an accuracy perspective, focusing on areas with high user demand, and recommendations were drawn based on the results of the analysis. As a preliminary study for digital record curation of presidential records, this study is significant because it identifies specific user information needs and quantifies the search quality of archival portal sites to improve user satisfaction.

• Journal of the Korean earth science society
• /
• v.37 no.7
• /
• pp.420-433
• /
• 2016

The purpose of this study is to improve the calibration matrixes of 2-D and 3-D convective rainfall rates (CRR) using the brightness temperature of the infrared $10.8{\mu}m$ channel (IR), the difference of brightness temperatures between infrared $10.8{\mu}m$ and vapor $6.7{\mu}m$ channels (IR-WV), and the normalized reflectance of the visible channel (VIS) from the COMS satellite and rainfall rate from the weather radar for the period of 75 rainy days from April 22, 2011 to October 22, 2011 in Korea. Especially, the rainfall rate data of the weather radar are used to validate the new 2-D and 3-DCRR calibration matrixes suitable for the Korean peninsula for the period of 24 rainy days in 2011. The 2D and 3D calibration matrixes provide the basic and maximum CRR values ($mm\;h^{-1}$) by multiplying the rain probability matrix, which is calculated by using the number of rainy and no-rainy pixels with associated 2-D (IR, IR-WV) and 3-D (IR, IR-WV, VIS) matrixes, by the mean and maximum rainfall rate matrixes, respectively, which is calculated by dividing the accumulated rainfall rate by the number of rainy pixels and by the product of the maximum rain rate for the calibration period by the number of rain occurrences. Finally, new 2-D and 3-D CRR calibration matrixes are obtained experimentally from the regression analysis of both basic and maximum rainfall rate matrixes. As a result, an area of rainfall rate more than 10 mm/h is magnified in the new ones as well as CRR is shown in lower class ranges in matrixes between IR brightness temperature and IR-WV brightness temperature difference than the existing ones. Accuracy and categorical statistics are computed for the data of CRR events occurred during the given period. The mean error (ME), mean absolute error (MAE), and root mean squire error (RMSE) in new 2-D and 3-D CRR calibrations led to smaller than in the existing ones, where false alarm ratio had decreased, probability of detection had increased a bit, and critical success index scores had improved. To take into account the strong rainfall rate in the weather events such as thunderstorms and typhoon, a moisture correction factor is corrected. This factor is defined as the product of the total precipitable waterby the relative humidity (PW RH), a mean value between surface and 500 hPa level, obtained from a numerical model or the COMS retrieval data. In this study, when the IR cloud top brightness temperature is lower than 210 K and the relative humidity is greater than 40%, the moisture correction factor is empirically scaled from 1.0 to 2.0 basing on PW RH values. Consequently, in applying to this factor in new 2D and 2D CRR calibrations, the ME, MAE, and RMSE are smaller than the new ones.

• Journal of the Korean earth science society
• /
• v.39 no.2
• /
• pp.139-153
• /
• 2018

The sea surface wind field has long been obtained from satellite scatterometers or passive microwave radiometers. However, the importance of satellite altimeter-derived wind speed has seldom been addressed because of the outstanding capability of the scatterometers. Satellite altimeter requires the accurate wind speed data, measured simultaneously with sea surface height observations, to enhance the accuracy of sea surface height through the correction of sea state bias. This study validates the wind speeds from the satellite altimeters (GFO, Jason-1, Envisat, Jason-2, Cryosat-2, SARAL) and analyzes characteristics of errors. In total, 1504 matchup points were produced using the wind speed data of Ieodo Ocean Research Station (IORS) and of Korea Meteorological Administration (KMA) buoys at Marado and Oeyeondo stations for 10 years from December 2007 to May 2016. The altimeter wind speed showed a root mean square error (RMSE) of about $1.59m\;s^{-1}$ and a negative bias of $-0.35m\;s^{-1}$ with respect to the in-situ wind speed. Altimeter wind speeds showed characteristic biases that they were higher (lower) than in-situ wind speeds at low (high) wind speed ranges. Some tendency was found that the difference between the maximum and minimum value gradually increased with distance from the buoy stations. For the improvement of the accuracy of altimeter wind speed, an equation for correction was derived based on the characteristics of errors. In addition, the significance of altimeter wind speed on the estimation of sea surface height was addressed by presenting the effect of the corrected wind speeds on the sea state bias values of Jason-1.

• Progress in Medical Physics
• /
• v.11 no.2
• /
• pp.123-130
• /
• 2000

The performance of an electrometer directly affects on the accuracy and precision in radiation dosimetry. This study is to list of the quality control for maintaining performance and to perform evaluation tests of an electrometer. Performance tests selected include proper polarizing voltages, warm-up and equalization time, leakages, long-term stability, linearity, and effect of ambient conditions. An electrometer connected with a rigid stem ionization chamber was evaluated with a Strontium-90 check device. Bias voltage was measured directly on the input socket. Equalization time is the time required for reaching threshold of charged state after the power is on or the bias voltage is changed. Pre- and post-signal leakages are defined as the accumulation of signal with no exposure and after exposure, respectively. Over three months period, the electrometer's long-term stability was measured by comparison of the temperature-pressure corrected readings. Linearity was expressed as the deviation of readings from multiple short exposures from one continuous exposure. Effect of ambient conditions was expressed as the zero drift of the electrometer over 17-34$^{\circ}C$ temperature ranges. For two nominal values, 300 and 500 volts, measured voltages were lower by 2.5 and 5.8%, respectively. The warm-up time, 20 minutes, was longer than the lamp time by 9 minutes and the equalization time was less than 1 minute. Without exposure, the zero-drift was 0.002 scale-unit in 15 minutes and the leakage after 10 minutes exposure was minimal. The IQ-4 was stable over 99.4% for three-month periods. Deviation from the linearity was 0.9% for measurement scale, 0.000-9.991. Over 17-34$^{\circ}C$ temperature range, the zero-drift was minimal, less than 0.2%. For a clinically-used electrometer, a list for the basic peformance evaluations is proposed. By running this program, the measurement error using an electrometer can be reduced and in turn the improvement in accuracy and precision of radiation dosimetry can be achieved.

• Progress in Medical Physics
• /
• v.21 no.1
• /
• pp.16-21
• /
• 2010

To acquire good image quality and to minimize unnecessary radiation dose to patients, it is important to ensure that the radiopharmaceutical administered is accurately measured. Quality control of radionuclide calibrators should be performed to achieve these goals. The purpose of this study is to support the quality control of radionuclide calibrators in nuclear medicine centers and to investigate the level of measurement accuracy of the radionuclide calibrators. 58 radionuclide calibrators from 45 nuclear medicine centers, 74 radionuclide calibrators from 58 nuclear medicine centers, and 60 radionuclide calibrators from 45 nuclear medicine centers were tested with I-131, Tc-99m and I-123, respectively. The results showed that 81% of calibrators for I-131, 61% of calibrators for Tc-99m and 67% of calibrators for I-123 were within ${\pm}5%$. 17% of calibrators for I-131, 20% of calibrators for Tc-99m and 15% of calibrators for I-123 had a deviation in the range 5%< $|{\Delta}|{\leq}10%$. 2% of calibrators for I-131, 19% of calibrators for Tc-99m and 18% of calibrators for I-123 had a deviation of $|{\Delta}|$ >10%. Follow-up measurements were performed on the calibrators whose error exceeded the ${\pm}10%$ limit. As a result, some of the calibrator showed an improvement and their deviation decreased below the ${\pm}10%$ limit. The results have shown that such comparisons are necessary to improve the accuracy of the measurement and to identify malfunctioning radionuclide calibrators.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.126-134
• /
• 2017

There have been numerous studies on extracting the R-peak from electrocardiogram (ECG) signals. However, most of the detection methods are complicated to implement in a real-time portable electrocardiograph device and have the disadvantage of requiring a large amount of calculations. R-peak detection requires pre-processing and post-processing related to baseline drift and the removal of noise from the commercial power supply for ECG data. An adaptive filter technique is widely used for R-peak detection, but the R-peak value cannot be detected when the input is lower than a threshold value. Moreover, there is a problem in detecting the P-peak and T-peak values due to the derivation of an erroneous threshold value as a result of noise. We propose a robust R-peak detection algorithm with low complexity and simple computation to solve these problems. The proposed scheme removes the baseline drift in ECG signals using an adaptive filter to solve the problems involved in threshold extraction. We also propose a technique to extract the appropriate threshold value automatically using the minimum and maximum values of the filtered ECG signal. To detect the R-peak from the ECG signal, we propose a threshold neighborhood search technique. Through experiments, we confirmed the improvement of the R-peak detection accuracy of the proposed method and achieved a detection speed that is suitable for a mobile system by reducing the amount of calculation. The experimental results show that the heart rate detection accuracy and sensitivity were very high (about 100%).