• The Korean Journal of Physiology and Pharmacology
• /
• v.23 no.2
• /
• pp.131-139
• /
• 2019

Manually reviewing electroencephalograms (EEGs) is labor-intensive and demands automated seizure detection systems. To construct an efficient and robust event detector for experimental seizures from continuous EEG monitoring, we combined spectral analysis and deep neural networks. A deep neural network was trained to discriminate periodograms of 5-sec EEG segments from annotated convulsive seizures and the pre- and post-EEG segments. To use the entire EEG for training, a second network was trained with non-seizure EEGs that were misclassified as seizures by the first network. By sequentially applying the dual deep neural networks and simple pre- and post-processing, our autodetector identified all seizure events in 4,272 h of test EEG traces, with only 6 false positive events, corresponding to 100% sensitivity and 98% positive predictive value. Moreover, with pre-processing to reduce the computational burden, scanning and classifying 8,977 h of training and test EEG datasets took only 2.28 h with a personal computer. These results demonstrate that combining a basic feature extractor with dual deep neural networks and rule-based pre- and post-processing can detect convulsive seizures with great accuracy and low computational burden, highlighting the feasibility of our automated seizure detection algorithm.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.6
• /
• pp.287-295
• /
• 2022

With the dramatic increase in mobile usage, more and more businesses see the potential of m-commerce. This study focuses on a subcategory of m-commerce, a mobile shopping application. To understand the purchase intention via m-commerce applications, this study is aimed to identify the main factors that are related to the applications and explore the influence of these factors on consumers' mobile shopping intention. This study uses quantitative research methods and selects Vietnam as its case study. The survey responses of 450 Vietnamese mobile shoppers were analyzed using partial least squares structural equation modeling (PLS-SEM). The results indicated that online reviews, e-service quality, and information quality are significant predictors of behavior intention, and perceived risk negatively influences consumer online purchase intention via the applications. The content enriches the combined research of detailed and possible models with quality dimensions and risk perception. Practitioners such as e-retailers and developers can enhance the quality of applications and determine strategies to reach potential users and maximize revenue. M-commerce providers should pay adequate attention to credible and influential online reviews since mobile shoppers heavily rely on reading reviews before buying a product.

• Advances in Computational Design
• /
• v.7 no.3
• /
• pp.253-279
• /
• 2022

This study investigated and predicted the Marshall stability of glass-fiber asphalt mix, carbon-fiber asphalt mix and glass-carbon-fiber asphalt (hybrid) mix by using machine learning techniques such as Artificial Neural Network (ANN), Support Vector Machine (SVM) and Random Forest(RF), The data was obtained from the experiments and the research articles. Assessment of results indicated that performance of the Artificial Neural Network (ANN) based model outperformed applied models in training and testing datasets with values of indices as; coefficient of correlation (CC) 0.8492 and 0.8234, mean absolute error (MAE) 2.0999 and 2.5408, root mean squared error (RMSE) 2.8541 and 3.3165, relative absolute error (RAE) 48.16% and 54.05%, relative squared error (RRSE) 53.14% and 57.39%, Willmott's index (WI) 0.7490 and 0.7011, Scattering index (SI) 0.4134 and 0.3702 and BIAS 0.3020 and 0.4300 for both training and testing stages respectively. The Taylor diagram also confirms that the ANN-based model outperforms the other models. Results of sensitivity analysis show that Carbon fiber has a major influence in predicting the Marshall stability. However, the carbon fiber (CF) followed by glass-carbon fiber (50GF:50CF) and the optimal combination CF + (50GF:50CF) are found to be most sensitive in predicting the Marshall stability of fibrous asphalt concrete.

• Smart Structures and Systems
• /
• v.28 no.6
• /
• pp.799-810
• /
• 2021

When monitoring the structural integrity of a bridge using data collected through accelerometers, identifying the profile of the load exerted on the bridge from the vehicles passing over it becomes a crucial task. In this study, the speed and location of vehicles on the deck of a bridge is reconfigured using real-time video to implicitly associate the load applied to the bridge with the response from the bridge sensors to develop an image-based deep learning network model. Instead of directly measuring the load that a moving vehicle exerts on the bridge, the intention in the proposed method is to replace the correlation between the movement of vehicles from CCTV images and the corresponding response by the bridge with a neural network model. Given the framework of an input-output-based system identification, CCTV images secured from the bridge and the acceleration measurements from a cantilevered beam are combined during the process of training the neural network model. Since in reality, structural damage cannot be induced in a bridge, the focus of the study is on identifying local changes in parameters by adding mass to a cantilevered beam in the laboratory. The study successfully identified the change in the material parameters in the beam by using the deep-learning neural network model. Also, the method correctly predicted the acceleration response of the beam. The proposed approach can be extended to the structural health monitoring of actual bridges, and its sensitivity to damage can also be improved through optimization of the network training.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.132-132
• /
• 2021

Access to accurate spatial precipitation in many hydrological studies is necessary. Existence of many mountains with diverse topography in South Korea causes different spatial distribution of precipitation. Rain gauge stations show accurate precipitation information in points, but due to the limited use of rain gauge stations and the difficulty of accessing them, there is not enough accurate information in the whole area. Weather radars can provide an integrated precipitation information spatially. Despite this, weather radar data have some errors that can not provide accurate data, especially in heavy rainfall. In this study, some location-based variable like aspect, elevation, plan curvature, profile curvature, slope and distance from the sea which has most effect on rainfall was considered. Then Automatic Weather Station data was used for spatial training of variables in each event. According to this, K-fold cross-validation method was combined with Adaptive Neuro-Fuzzy Inference System. Based on this, 80% of Automatic Weather Station data was used for training and validation of model and 20% was used for testing and evaluation of model. Finally, spatial distribution of precipitation for 1×1 km resolution in Gwangdeoksan radar station was estimates. The results showed a significant decrease in RMSE and an increase in correlation with the observed amount of precipitation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.738-754
• /
• 2024

Side-channel analysis (SCA) is a cryptanalytic technique that exploits physical leakages, such as power consumption or electromagnetic emanations, from cryptographic devices to extract secret keys used in cryptographic algorithms. Recent studies have shown that training SCA models with semi-supervised learning can effectively overcome the problem of few labeled power traces. However, the process of training SCA models using semi-supervised learning generates many pseudo-labels. The performance of the SCA model can be reduced by some of these pseudo-labels. To solve this issue, we propose the HWFilter method to improve semi-supervised SCA. This method uses a Hamming Weight Pseudo-label Filter (HWPF) to filter the pseudo-labels generated by the semi-supervised SCA model, which enhances the model's performance. Furthermore, we introduce a normal distribution method for constructing the HWPF. In the normal distribution method, the Hamming weights (HWs) of power traces can be obtained from the normal distribution of power points. These HWs are filtered and combined into a HWPF. The HWFilter was tested using the ASCADv1 database and the AES_HD dataset. The experimental results demonstrate that the HWFilter method can significantly enhance the performance of semi-supervised SCA models. In the ASCADv1 database, the model with HWFilter requires only 33 power traces to recover the key. In the AES_HD dataset, the model with HWFilter outperforms the current best semi-supervised SCA model by 12%.

• Nuclear Engineering and Technology
• /
• v.56 no.4
• /
• pp.1284-1295
• /
• 2024

Due to increasing operational security demands, digital and intelligent condition monitoring of nuclear power plants is becoming more significant. However, establishing an accurate and effective anomaly detection model is still challenging. This is mainly because of data characteristics of nuclear power data, including the lack of clear class labels combined with frequent interference from outliers and anomalies. In this paper, we introduce a Transformer-based unsupervised model for anomaly detection of nuclear power data, a modified loss function based on the maximum correntropy criterion (MCC) is applied in the model training to improve the robustness. Experimental results on simulation datasets demonstrate that the proposed Trans-MCC model achieves equivalent or superior detection performance to the baseline models, and the use of the MCC loss function is proven can obviously alleviate the negative effect of outliers and anomalies in the training procedure, the F1 score is improved by up to 0.31 compared to Trans-MSE on a specific dataset. Further studies on genuine nuclear power data have verified the model's capability to detect anomalies at an earlier stage, which is significant to condition monitoring.

• The Journal of Korean Medicine
• /
• v.45 no.1
• /
• pp.80-99
• /
• 2024

Objectives: The objective of this study was to review clinical studies conducted over the last ten years that investigated weight or fat loss interventions that can preserve muscle or fat-free mass in Sarcopenic obesity Methods: PubMed, Embase, Cochrane Central Register of Controlled Trials (CENTRAL), Research Information Sharing Service (RISS) and Korea Studies Information Service (KISS) were searched for Randomized clinical trials that had investigated all-type of interventions on the management of sarcopenic obesity from October 2013 to September 2023. Results: A total of 14 studies met all the inclusion criteria. Interventions that increase muscle mass while reducing body fat at the same time included resistance training (including using elastic bands) and whole-body electromyostimulation(WB-EMS) in exercise intervention and Hypocaloric high-protein diet in nutritional intervention, exercise and nutritional combined intervention, and combination intervention of electrical acupuncture and amino acid supplementation. Among them, the most positive method of changing the body composition in sarcopenic obesity was the electric acupuncture and amino acid supplements. Conclusion: Varying diagnostic criteria and management interventions for sarcopenic obesity in the included studies made it hard to maintain homogeneity across the studies. Well-defined criteria for diagnostic sarcopenic obesity should be considered. In addition, since all of the interventions examined did not show sufficient clinical effectiveness, follow-up studies are needed to confirm effective interventions for sarcopenic obesity patients in the future.

• Journal of Astronomy and Space Sciences
• /
• v.41 no.2
• /
• pp.61-78
• /
• 2024

This study developed a real-time spacecraft pose estimation algorithm that combined a deep learning model and the least-squares method. Pose estimation in space is crucial for automatic rendezvous docking and inter-spacecraft communication. Owing to the difficulty in training deep learning models in space, we showed that actual experimental results could be predicted through software simulations on the ground. We integrated deep learning with nonlinear least squares (NLS) to predict the pose from a single spacecraft image in real time. We constructed a virtual environment capable of mass-producing synthetic images to train a deep learning model. This study proposed a method for training a deep learning model using pure synthetic images. Further, a visual-based real-time estimation system suitable for use in a flight testbed was constructed. Consequently, it was verified that the hardware experimental results could be predicted from software simulations with the same environment and relative distance. This study showed that a deep learning model trained using only synthetic images can be sufficiently applied to real images. Thus, this study proposed a real-time pose estimation software for automatic docking and demonstrated that the method constructed with only synthetic data was applicable in space.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2003.10a
• /
• pp.133-138
• /
• 2003

The prediction of protein secondary structure has been an important bioinformatics tool that is an essential component of the template-based protein tertiary structure prediction process. It has been known that the predicted secondary structure information improves both the fold recognition performance and the alignment accuracy. In this paper, we describe several novel ideas that may improve the prediction accuracy. The main idea is motivated by an observation that the protein's structural information, especially when it is combined with the evolutionary information, significantly improves the accuracy of the predicted tertiary structure. From the non-redundant set of protein structures, we derive the 'potential' parameters for the protein secondary structure prediction that contains the structural information of proteins, by following the procedure similar to the way to derive the directional information table of GOR method. Those potential parameters are combined with the frequency matrices obtained by running PSI-BLAST to construct the feature vectors that are used to train the support vector machines (SVM) to build the secondary structure classifiers. Moreover, the problem of huge model file size, which is one of the known shortcomings of SVM, is partially overcome by reducing the size of training data by filtering out the redundancy not only at the protein level but also at the feature vector level. A preliminary result measured by the average three-state prediction accuracy is encouraging.