• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.830-841
• /
• 2023

Tokenization is the process of segmenting the input text into smaller units of text, and it is a preprocessing task that is mainly performed to improve the efficiency of the machine learning process. Various tokenization methods have been proposed for application in the field of natural language processing, but studies have primarily focused on efficiently segmenting text. Few studies have been conducted on the Korean language to explore what tokenization methods are suitable for document classification task. In this paper, an exploratory study was performed to find the most suitable tokenization method to improve the performance of a representative spatio-temporal document classifier in Korean. For the experiment, a convolutional neural network model was used, and for the final performance comparison, tasks were selected for document classification where performance largely depends on the tokenization method. As a tokenization method for comparative experiments, commonly used Jamo, Character, and Word units were adopted. As a result of the experiment, it was confirmed that the tokenization of word units showed excellent performance in the case of representative spatio-temporal document classification task where the semantic embedding ability of the token itself is important.

• 4차산업연구
• /
• 제4권1호
• /
• pp.1-9
• /
• 2024

Purpose: Education is the part of a fundamental human right across the world. In recent years, the trend of virtual education has increased tremendously. The paper aims to find the impact of adoption, accessibility, interactions, knowledge, and satisfaction on the success of transformation towards virtual education. Research design, data and methodology: Primary data has been gathered through the use of responses from students taking admission in virtual higher education to standardized questionnaires. Of the 250, only 122 were considered complete and have been used in further studies. Convinced random sampling method has been used. The results were evaluated using the Likert Five-Point Scale. For applying these statistical tools software SmartPLS and SPSS 19 have been used. The fitness of the model has been re-checked through an Artificial Neural Network (ANN). Result: Results derived that adoption, accessibility, and interactions have a significant impact on knowledge, knowledge influences satisfaction level and satisfaction have a meaningful impact on the success of transformation towards virtual education. Conclusion: It can be concluded that virtual education has the potential to change the future of the education system and its potential in India. The highest importance is due to satisfaction (100%), adoption (98.7%), knowledge (91.4%), accessibility (62%), and interaction (29.2%).

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2024년도 제69차 동계학술대회논문집 32권1호
• /
• pp.45-46
• /
• 2024

본 논문에서는 Self-Attention 기반 딥러닝 기법인 Dense Prediction Transformer(DPT) 모델을 MVTec Anomaly Detection(MVTec AD) 데이터셋에 적용하여 실제 산업 제품 이미지 내 이상 부분을 분할하는 연구를 진행하였다. DPT 모델의 적용을 통해 기존 Convolutional Neural Network(CNN) 기반 이상 탐지기법의 한계점인 지역적 Feature 추출 및 고정된 수용영역으로 인한 문제를 개선하였으며, 실제 산업 제품 데이터에서의 이상 분할 시 기존 주력 기법인 U-Net의 구조를 적용한 최고 성능의 모델보다 1.14%만큼의 성능 향상을 보임에 따라 Self-Attention 기반 딥러닝 기법의 적용이 산업 제품 이상 분할에 효과적임을 입증하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.438-455
• /
• 2024

Recently, many unsupervised learning-based models have emerged for Just Noticeable Difference (JND) estimation, demonstrating remarkable improvements in accuracy. However, these models suffer from a significant drawback is that their heavy reliance on handcrafted priors for guidance. This restricts the information for estimating JND simply extracted from regions that are highly related to handcrafted priors, while information from the rest of the regions is disregarded, thus limiting the accuracy of JND estimation. To address such issue, on the one hand, we extract the information for estimating JND in an Adversarial Complementary Learning (ACoL) way and propose an ACoL-JND network to estimate the JND by comprehensively considering the handcrafted priors-related regions and non-related regions. On the other hand, to make the handcrafted priors richer, we take two additional priors that are highly related to JND modeling into account, i.e., Patterned Masking (PM) and Contrast Masking (CM). Experimental results demonstrate that our proposed model outperforms the existing JND models and achieves state-of-the-art performance in both subjective viewing tests and objective metrics assessments.

• Wind and Structures
• /
• 제38권1호
• /
• pp.75-91
• /
• 2024

Reliable wind signal reconstruction can be beneficial to the operational safety of long-span bridges. Non-Gaussian characteristics of wind signals make the reconstruction process challenging. In this paper, non-Gaussian wind signals are converted into a combined prediction of two kinds of features, actual wind speeds and wind angles of attack. First, two decomposition techniques, empirical mode decomposition (EMD) and variational mode decomposition (VMD), are introduced to decompose wind signals into intrinsic mode functions (IMFs) to reduce the randomness of wind signals. Their principles and applicability are also discussed. Then, four artificial intelligence (AI) algorithms are utilized for wind signal reconstruction by combining the particle swarm optimization (PSO) algorithm with back propagation neural network (BPNN), support vector regression (SVR), long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM), respectively. Measured wind signals from a bridge site in a deep-cutting gorge are taken as experimental subjects. The results showed that the reconstruction error of high-frequency components of EMD is too large. On the contrary, VMD fully extracts the multiscale rules of the signal, reduces the component complexity. The combination of VMD-PSO-Bi-LSTM is demonstrated to be the most effective among all hybrid models.

• Nuclear Engineering and Technology
• /
• 제56권4호
• /
• pp.1254-1266
• /
• 2024

This study investigates the application of supercritical carbon dioxide (S-CO₂) direct-cycle micro modular reactors (MMRs) in primary frequency control (PFC), which is a scenario characterized by significant load fluctuations that has received less attention compared to secondary load-following. Using a modified GAMMA + code and a deep neural network-based turbomachinery off-design model, the authors conducted an analysis to assess the behavior of the reactor core and fluid system under different PFC scenarios. The results indicate that the acceptable range for sudden relative electricity output (REO) fluctuations is approximately 20%p which aligns with the performance of combined-cycle gas turbines (CCGTs) and open-cycle gas turbines (OCGTs). In S-CO₂ direct-cycle MMRs, the control of the core operates passively within the operational range by managing coolant density through inventory control. However, when PFC exceeds 35%p, system control failure is observed, suggesting the need for improved control strategies. These findings affirm the potential of S-CO₂ direct-cycle MMRs in PFC operations, representing an advancement in the management of grid fluctuations while ensuring reliable and carbon-free power generation.

• Geomechanics and Engineering
• /
• 제37권4호
• /
• pp.395-418
• /
• 2024

The epicentral region of earthquakes is typically where liquefaction-related damage takes place. To determine the maximum distance, such as maximum epicentral distance (R_e), maximum fault distance (R_f), or maximum hypocentral distance (R_h), at which an earthquake can inflict damage, given its magnitude, this study, using a recently updated global liquefaction database, multiple ML models are built to predict the limiting distances (R_e, R_f, or R_h) required for an earthquake of a given magnitude to cause damage. Four machine learning models LSTM (Long Short-Term Memory), BiLSTM (Bidirectional Long Short-Term Memory), CNN (Convolutional Neural Network), and XGB (Extreme Gradient Boosting) are developed using the Python programming language. All four proposed ML models performed better than empirical models for limiting distance assessment. Among these models, the XGB model outperformed all the models. In order to determine how well the suggested models can predict limiting distances, a number of statistical parameters have been studied. To compare the accuracy of the proposed models, rank analysis, error matrix, and Taylor diagram have been developed. The ML models proposed in this paper are more robust than other current models and may be used to assess the minimal energy of a liquefaction disaster caused by an earthquake or to estimate the maximum distance of a liquefied site provided an earthquake in rapid disaster mapping.

• 한국산업융합학회 논문집
• /
• 제27권1호
• /
• pp.161-172
• /
• 2024

Approximately 89% of all capsizing accidents involve small vessels, and despite their relatively high accident rates, small vessels are not subject to ship stability regulations. Small vessels, where the provision of essential basic design documents for stability calculations is omitted, face challenges in directly calculating their stability. In this study, considering that the majority of domestic coastal small vessels are of the Chine-type design, the goal is to establish the major hull form characteristic data of vessels, which can be identified from design documents such as the general arrangement drawing, as input data. Through the application of a deep learning approach, specifically a multilayer neural network structure, we aim to infer hydrostatic curves, operational draft ranges, and more. The ultimate goal is to confirm the possibility of directly calculating the initial stability of small vessels.

• International journal of advanced smart convergence
• /
• 제13권1호
• /
• 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.

• Earthquakes and Structures
• /
• 제27권3호
• /
• pp.177-189
• /
• 2024

Accurately predicting the failure modes of reinforced concrete (RC) columns is essential for structural design and assessment. In this study, the challenges of imbalanced datasets and complex feature selection in machine learning (ML) methods were addressed through an optimized ML approach. By combining feature selection and oversampling techniques, the prediction of seismic failure modes in rectangular RC columns was improved. Two feature selection methods were used to identify six input parameters. To tackle class imbalance, the Borderline-SMOTE1 algorithm was employed, enhancing the learning capabilities of the models for minority classes. Eight ML algorithms were trained and fine-tuned using k-fold shuffle split cross-validation and grid search. The results showed that the artificial neural network model achieved 96.77% accuracy, while k-nearest neighbor, support vector machine, and random forest models each achieved 95.16% accuracy. The balanced dataset led to significant improvements, particularly in predicting the flexure-shear failure mode, with accuracy increasing by 6%, recall by 8%, and F1 scores by 7%. The use of the Borderline-SMOTE1 algorithm significantly improved the recognition of samples at failure mode boundaries, enhancing the classification performance of models like k-nearest neighbor and decision tree, which are highly sensitive to data distribution and decision boundaries. This method effectively addressed class imbalance and selected relevant features without requiring complex simulations like traditional methods, proving applicable for discerning failure modes in various concrete members under seismic action.