• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.6-10
• /
• 2023

High-potential data can be predicted and stored in the cache to prevent cache misses, thus reducing the processor's request and wait times. As a result, the processor can work non-stop, hiding memory latency. By utilizing the temporal/spatial locality of memory access, the prefetcher introduced to improve the performance of these computers predicts the following memory address will be accessed. We propose a prefetcher that applies the GRU model, which is advantageous for handling time series data. Display the currently accessed address in binary and use it as training data to train the Gated Recurrent Unit model based on the difference (delta) between consecutive memory accesses. Finally, using a GRU model with learned memory access patterns, the proposed data prefetcher predicts the memory address to be accessed next. We have compared the model with the multi-layer perceptron, but our prefetcher showed better results than the Multi-Layer Perceptron.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.251-256
• /
• 2023

International diesel prices play a crucial role in various sectors such as industry, transportation, and energy production, exerting a significant impact on the global economy and international trade. In particular, an increase in international diesel prices can burden consumers and potentially lead to inflation. However, previous studies have primarily focused on gasoline. Therefore, this study aims to propose an international diesel price prediction model. To achieve this goal, we utilize various global economic indicators and train a linear regression model, which is one of the machine learning methodologies. This model clearly identifies the relationship between global economic indicators and international diesel prices while providing highly accurate predictions. It is expected to aid in understanding overall economic trends including market changes.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.4
• /
• pp.159-163
• /
• 2006

In this paper a data-driven method to improve the performance of the Jacobian adaptation (JA) for the noisy speech recognition is proposed. In stead of constructing the reference HMM by using the model composition method like the parallel model combination (PMC), we propose to train the reference HMM directly with the noisy speech. This was motivated from the idea that the directly trained reference HMM will model the acoustical variations due to the noise better than the composite HMM. For the estimation of the Jacobian matrices, the Baum-Welch algorithm is employed during the training. The recognition experiments have been done to show the improved performance of the proposed method over the Jacobian adaptation as well as other model compensation methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1223-1237
• /
• 2024

Autonomous vehicles use onboard sensors to sense the surrounding environment. In complex autonomous driving scenarios, the detection and recognition capabilities are constrained, which may result in serious accidents. An efficient way to enhance the detection and recognition capabilities is establishing collaborations with the neighbor vehicles. However, the collaborations introduce additional challenges in terms of the data heterogeneity, communication cost, and data privacy. In this paper, a novel personalized federated learning framework is proposed for addressing the challenges and enabling efficient collaborations in autonomous driving environment. For obtaining a global model, vehicles perform local training and transmit logits to a central unit instead of the entire model, and thus the communication cost is minimized, and the data privacy is protected. Then, the inference similarity is derived for capturing the characteristics of data heterogeneity. The vehicles are divided into clusters based on the inference similarity and a weighted aggregation is performed within a cluster. Finally, the vehicles download the corresponding aggregated global model and train a personalized model which is personalized for the cluster that has similar data distribution, so that accuracy is not affected by heterogeneous data. Experimental results demonstrate significant advantages of our proposed method in improving the efficiency of collaborative perception and reducing communication cost.

• 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.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.514-523
• /
• 2024

In the Internet of Medical Things, due to the sensitivity of medical information, data typically need to be retained locally. The training model of heart disease data can predict patients' physical health status effectively, thereby providing reliable disease information. It is crucial to make full use of multiple data sources in the Internet of Medical Things applications to improve model accuracy. As network communication speeds and computational capabilities continue to evolve, parties are storing data locally, and using privacy protection technology to exchange data in the communication process to construct models is receiving increasing attention. This shift toward secure and efficient data collaboration is expected to revolutionize computer modeling in the healthcare field by ensuring accuracy and privacy in the analysis of critical medical information. In this paper, we train and test a multiparty decision tree model for the Internet of Medical Things on a heart disease dataset to address the challenges associated with developing a practical and usable model while ensuring the protection of heart disease data. Experimental results demonstrate that the accuracy of our privacy protection method is as high as 93.24%, representing a difference of only 0.3% compared with a conventional plaintext algorithm.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.4_2
• /
• pp.925-933
• /
• 2024

Identification of potential technology convergence opportunities is crucial to drive innovation and growth in modern enterprises. In this study, we proposed a framework to explore technological convergence opportunities based on CPC code sequences from patents by utilizing the BERT model. We relied on the BERT architecture to train a new model using about 1.3 million patents registered at the Korean Intellectual Property Office, and achieved an accuracy of approximately 73% based on HitRate@10 metric. A case study using patents related to wearable technologies was conducted to demonstrate practicability and effectiveness of the proposed framework. The key contributions of this research include: (1) enabling in-depth analysis that takes into account the complex interactions between CPC codes and contextual variability; (2) enabling the exploration of diverse technology convergence scenarios beyond simple sequential patterns. This study is one of the first studies to apply the BERT model for exploring technology convergence opportunities, and is expected to contribute to the establishment of technology innovation and R&D strategies by providing a more accurate and practical tool for enhancing the speed and efficiency of technology opportunity-related decision-making processes.

• Journal of Korean Neurosurgical Society
• /
• v.47 no.4
• /
• pp.287-290
• /
• 2010

Objective : The authors evaluated the accuracies and ease of use of several commonly used microanastomosis training models (synthetic tube, chicken wing, and living rat model). Methods : A survey was conducted among neurosurgeons and neurosurgery residents at a workshop held in 2009 at the authors' institute. Questions addressed model accuracy (similarity to real vessels and actual procedures) and practicality (availability of materials and ease of application in daily practice). Answers to each question were rated using a 5-point scale. Participants were also asked what types of training methods they would chose to improve their skills and to introduce the topic to other neurosurgeons or neurosurgery residents. Results : Of the 24 participants, 20 (83.3%) responded to the survey. The living rat model was favored for model accuracy (p<0.001; synthetic tube $-0.95{\pm}0.686$, chicken wing, $0.15{\pm}0.587$, and rat, $1.75{\pm}0.444$) and the chicken wing model for practicality (p<0.001; synthetic tube $-1.55{\pm}0.605$, chicken wing, $1.80{\pm}0.523$, and rat,$1.30{\pm}0.923$). All (100%) chose the living rat model for improving their skills, and for introducing the subject to other neurosurgeons or neurosurgery residents, the chicken wing and living rat models were selected by 18 (90%) and 20 (100%), respectively. Conclusion : Of 3 methods examined, the chicken wing model was found to be the most practical, but the living rat model was found to represent reality the best. We recommend the chicken wing model to train surgeons who have mastered basic techniques, and the living rat model for experienced surgeons to maintain skill levels.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.817-826
• /
• 2022

AI technology is being successfully introduced in many fields, and models deployed as a service are deployed with black box environment that does not expose the model's information to protect intellectual property rights and data. In a black box environment, attackers try to steal data or parameters used during training by using model output. This paper proposes a method of inferring the type of model to directly find out the composition of layer of the target model, based on the fact that there is no attack to infer the information about the type of model from the deep learning model. With ResNet, VGGNet, AlexNet, and simple convolutional neural network models trained with MNIST datasets, we show that the types of models can be inferred using the output values in the gray box and black box environments of the each model. In addition, we inferred the type of model with approximately 83% accuracy in the black box environment if we train the big and small relationship feature that proposed in this paper together, the results show that the model type can be infrerred even in situations where only partial information is given to attackers, not raw probability vectors.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.26 no.2
• /
• pp.139-146
• /
• 2013

This study is to update of vibration power generating model and to analyze electromotive force on subway. Analysis of electromotive force using power generation depending on classification of locations which are ballast bed and concrete bed. As the section between Seocho and Bangbae in the line 2 subway was changed from ballast bed to concrete bed, it could be analyzed at same condition, train, section. Induced electromotive force equation by Faraday's law was updated using Bayesian regression and correlation analysis with calculate value and experiment value. Using the updated model, it could get 40mV per one power generation in ballast bed, and it also could get 4mV per one power generation in concrete bed. If the updated model apply to subway or any train, it will be more effective to get electric power. In addition to that, it will be good to reduce greenhouse gas and to build a green traffic network.