• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.589-591
• /
• 2023

현재 수치예보 시스템은 항공기, 위성 등 다양한 센서에서 얻은 다종 관측 데이터를 동화하여 대기 상태를 추정하고 있지만, 관측변수 또는 물리량이 서로 다른 관측들을 처리하기 위한 계산 복잡도가 매우 높다. 본 연구에서 기존 시스템의 계산 효율성을 개선하여 관측을 평가하거나 전처리하는 데에 효율적으로 활용하기 위해, 각 관측의 특성을 고려한 자기 지도학습 방법을 통해 멀티모달 기상관측으로부터 실제 대기 상태를 추정하는 방법론을 제안하고자 한다. 비균질적으로 수집되는 멀티모달 기상관측 데이터를 융합하기 위해, (i) 기상관측의 heterogeneous network를 구축하여 개별 관측의 위상정보를 표현하고, (ii) pretext task 기반의 self-supervised learning을 바탕으로 개별 관측의 특성을 표현한다. (iii) Graph neural network 기반의 예측 모델을 통해 실제에 가까운 대기 상태를 추정한다. 제안하는 모델은 대규모 수치 시뮬레이션 시스템으로 수행되는 기존 기술의 한계점을 개선함으로써, 이상 관측 탐지, 관측의 편차 보정, 관측영향 평가 등 관측 전처리 기술로 활용할 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.57-67
• /
• 2021

Recently, multi-modal deep learning techniques that combine heterogeneous data for deep learning analysis have been utilized a lot. In particular, studies on the synthesis of Text to Image that automatically generate images from text are being actively conducted. Deep learning for image synthesis requires a vast amount of data consisting of pairs of images and text describing the image. Therefore, various data augmentation techniques have been devised to generate a large amount of data from small data. A number of text augmentation techniques based on synonym replacement have been proposed so far. However, these techniques have a common limitation in that there is a possibility of generating a incorrect text from the content of an image when replacing the synonym for a noun word. In this study, we propose a text augmentation method to replace words using word hierarchy information for noun words. Additionally, we performed experiments using MSCOCO data in order to evaluate the performance of the proposed methodology.

• KIISE Transactions on Computing Practices
• /
• v.21 no.1
• /
• pp.64-69
• /
• 2015

Place awareness is an essential for location-based services that are widely provided to smartphone users. However, traditional GPS-based methods are only valid outdoors where the GPS signal is strong and also require symbolic place information of the physical location. In this paper, environmental sounds and images are used to recognize important aspects of each place. The proposed method extracts feature vectors from visual, auditory and location data recorded by a smartphone with built-in camera, microphone and GPS sensors modules. The heterogeneous feature vectors were then learned by an ensemble learning method that learns each group of feature vectors for each classifier respectively and votes to produce the highest weighted result. The proposed method is evaluated for place recognition using a data group of 3000 samples in six places and the experimental results show a remarkably improved recognition accuracy when using all kinds of sensory data comparing to results using data from a single sensor or audio-visual integrated data only.

• Journal of The Korean Association of Information Education
• /
• v.9 no.1
• /
• pp.79-86
• /
• 2005

With the rapid advance of computer and communication technology, the amount of data transferred is also increasing more than ever. The recent trend of education systems is connecting related information semantically in different systems in order to improve the utilization of computerized information Therefore, Web-based teaching-learning is developing in the ubiquitous learning direction that learners select and organize the contents, time and order of learning by themselves. That is, it is evolving to provide teaching-learning environment adaptive to individual learners' characteristics (their level of knowledge, pattern of study, areas of interest). This paper proposes the efficient evaluation method of learning contents in a mediator for the integration of heterogeneous information resources. This means that the autonomy of a remote server can be preserved to the highest degree. In addition, this paper proposes the adaptive optimization of learning contents such that available storage in a mediator can be highly utilized at any time. In order to differentiate the recent usage of a learning content from the past, the accumulated usage frequency of a learning content decays as time goes by.

• East Asian Economic Review
• /
• v.25 no.4
• /
• pp.403-424
• /
• 2021

AdaBoost tweaks the sample weight for each training set used in the iterative process, however, it is demonstrated that it provides more correlated errors as the boosting iteration proceeds if models' accuracy is high enough. Therefore, in this study, we propose a novel way to improve the performance of the existing AdaBoost algorithm by employing heterogeneous models and a stochastic twist. By employing the heterogeneous ensemble, it ensures different models that have a different initial assumption about the data are used to improve on diversity. Also, by using a stochastic algorithm with a decaying convergence rate, the model is designed to balance out the trade-off between model prediction performance and model convergence. The result showed that the stochastic algorithm with decaying convergence rate's did have a improving effect and outperformed other existing boosting techniques.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3836-3854
• /
• 2022

The student group division is benefit for universities to do the student management based on the group profile. With the widespread use of student smart cards on campus, especially where students living in campus residence halls, students' daily activities on campus are recorded with information such as smart card swiping time and location. Therefore, it is feasible to depict the students with the daily activity data and accordingly group students based on objective measuring from their campus behavior with some regular student attributions collected in the management system. However, it is challenge in feature representation due to diverse forms of the student data. To effectively and comprehensively represent students' behaviors for further student group division, we proposed to adopt activity data from student smart cards and student attributes as input data with taking account of activity and attribution relationship types from different perspective. Specially, we propose a novel student group division method based on a multi-view student attribute heterogeneous information network (MSA-HIN). The network nodes in our proposed MSA-HIN represent students with their multi-dimensional attribute information. Meanwhile, the edges are constructed to characterize student different relationships, such as co-major, co-occurrence, and co-borrowing books. Based on the MSA-HIN, embedded representations of students are learned and a deep graph cluster algorithm is applied to divide students into groups. Comparative experiments have been done on a real-life campus dataset collected from a university. The experimental results demonstrate that our method can effectively reveal the variability of student attributes and relationships and accordingly achieves the best clustering results for group division.

• Computers and Concrete
• /
• v.32 no.6
• /
• pp.625-637
• /
• 2023

The application of ML approaches in determining the resisting capacity of fire damaged RC columns is introduced in this paper, on the basis of analysis data driven ML modeling. Considering the characteristics of the structural behavior of fire damaged RC columns, the representative five approaches of Kernel SVM, ANN, RF, XGB and LGBM are adopted and applied. Additional partial monotonic constraints are adopted in modelling, to ensure the monotone decrease of resisting capacity in RC column with fire exposure time. Furthermore, additional suggestions are also added to mitigate the heterogeneous composition of the training data. Since the use of ML approaches will significantly reduce the computation time in determining the resisting capacity of fire damaged RC columns, which requires many complex solution procedures from the heat transfer analysis to the rigorous nonlinear analyses and their repetition with time, the introduced ML approach can more effectively be used in large complex structures with many RC members. Because of the very small amount of experimental data, the training data are analytically determined from a heat transfer analysis and a subsequent nonlinear finite element (FE) analysis, and their accuracy was previously verified through a correlation study between the numerical results and experimental data. The results obtained from the application of ML approaches show that the resisting capacity of fire damaged RC columns can effectively be predicted by ML approaches.

• Journal of Internet Computing and Services
• /
• v.22 no.5
• /
• pp.27-33
• /
• 2021

With the broad adoption of the Internet of Things (IoT) in a variety of scenarios and application services, management and orchestration entities require upgrading the traditional architecture and develop intelligent models with ultra-reliable methods. In a heterogeneous network environment, mission-critical IoT applications are significant to consider. With erroneous priorities and high failure rates, catastrophic losses in terms of human lives, great business assets, and privacy leakage will occur in emergent scenarios. In this paper, an efficient resource slicing scheme for optimizing federated learning in software-defined IoT (SDIoT) is proposed. The decentralized support vector regression (SVR) based controllers predict the IoT slices via packet inspection data during peak hour central congestion to achieve a time-sensitive condition. In off-peak hour intervals, a centralized deep neural networks (DNN) model is used within computation-intensive aspects on fine-grained slicing and remodified decentralized controller outputs. With known slice and prioritization, federated learning communications iteratively process through the adjusted resources by virtual network functions forwarding graph (VNFFG) descriptor set up in software-defined networking (SDN) and network functions virtualization (NFV) enabled architecture. To demonstrate the theoretical approach, Mininet emulator was conducted to evaluate between reference and proposed schemes by capturing the key Quality of Service (QoS) performance metrics.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.29-41
• /
• 2022

Recently, with the development of deep learning technology, a variety of huge models with excellent performance have been devised by pre-training massive amounts of text data. However, in order for such a model to be applied to real-life services, the inference speed must be fast and the amount of computation must be low, so the technology for model compression is attracting attention. Knowledge distillation, a representative model compression, is attracting attention as it can be used in a variety of ways as a method of transferring the knowledge already learned by the teacher model to a relatively small-sized student model. However, knowledge distillation has a limitation in that it is difficult to solve problems with low similarity to previously learned data because only knowledge necessary for solving a given problem is learned in a teacher model and knowledge distillation to a student model is performed from the same point of view. Therefore, we propose a heterogeneous knowledge distillation method in which the teacher model learns a higher-level concept rather than the knowledge required for the task that the student model needs to solve, and the teacher model distills this knowledge to the student model. In addition, through classification experiments on about 18,000 documents, we confirmed that the heterogeneous knowledge distillation method showed superior performance in all aspects of learning efficiency and accuracy compared to the traditional knowledge distillation.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.872-884
• /
• 2022

With the development of the IoT industry, different types of time series data are being generated in various industries, and it is evolving into research that reproduces and utilizes it through re-integration. In addition, due to data processing speed and issues of the utilization system in the actual industry, there is a growing tendency to compress the size of data when using time series data and integrate it. However, since the guidelines for integrating time series data are not clear and each characteristic such as data description time interval and time section is different, it is difficult to use it after batch integration. In this paper, two integration methods are proposed based on the integration criteria setting method and the problems that arise during integration of time series data. Based on this, integration framework of a heterogeneous time series data was constructed that is considered the characteristics of time series data, and it was confirmed that different heterogeneous time series data compressed can be used for integration and various machine learning.