• Current Optics and Photonics
• /
• 제7권5호
• /
• pp.545-556
• /
• 2023

This paper introduces volume-sharing multi-aperture imaging (VMAI), a potential approach proposed for volume reduction in space-borne imagers, with the aim of achieving high-resolution ground spatial imagery using deep learning methods, with reduced volume compared to conventional approaches. As an intermediate step in the VMAI payload development, we present a phase-1 design targeting a 1-meter ground sampling distance (GSD) at 500 km altitude. Although its optical imaging capability does not surpass conventional approaches, it remains attractive for specific applications on small satellite platforms, particularly surveillance missions. The design integrates one wide-field and three narrow-field cameras with volume sharing and no optical interference. Capturing independent images from the four cameras, the payload emulates a large circular aperture to address diffraction and synthesizes high-resolution images using deep learning. Computational simulations validated the VMAI approach, while addressing challenges like lower signal-to-noise (SNR) values resulting from aperture segmentation. Future work will focus on further reducing the volume and refining SNR management.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.228-230
• /
• 2020

The emergence of collaborative learning to the public is to tackle the user's privacy issue in centralized learning by bringing the AI models to the data source or client device for training Collaborative learning employs computing and storage resources on the client's device. Thus, it is privacy preserved by design. In harmony, blockchain is also prominent since it does not require an intermediary to process a transaction. However, these approaches are not yet fully ripe to be implemented in the real world, especially for the complex system (several challenges need to be addressed). In this work, we present the performance of collaborative learning and potential use case of blockchain. Further, we discuss privacy issues in the system.

• 전기학회논문지
• /
• 제66권7호
• /
• pp.1100-1104
• /
• 2017

A detector-based approach shows the limited performances for the defect inspections such as shallow fine cracks and indistinguishable defects from background. Deep learning technique is widely used for object recognition and it's applications to detect defects have been gradually attempted. Deep learning requires huge scale of learning data, but acquisition of data can be limited in some industrial application. The possibility of applying CNN which is one of the deep learning approaches for surface defect inspection is investigated for industrial parts whose detection difficulty is challenging and learning data is not sufficient. VOV is adopted for pre-processing and to obtain a resonable number of ROIs for a data augmentation. Then CNN method is applied for the classification. Three CNN networks, AlexNet, VGGNet, and mofified VGGNet are compared for experiments of defects detection.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.107-109
• /
• 2007

The recently-developed off-line learning control approaches for the rejection of periodic disturbances utilize the specific property that the learning system tends to oscillate in steady state. Unfortunately, the prior works have not clarified how closely the learning system should approach the steady state to achieve the rejection of periodic disturbances to satisfactory level. In this paper, we address this issue extensively for the class of linear systems. We also attempt to remove the effect of other aperiodic disturbances on the rejection of the periodic disturbances effectively. In fact, the proposed learning control algorithm can provide very fast convergence performance in the presence of aperiodic disturbance. The effectiveness and practicality of our work is demonstrated through mathematical, performance analysis as well as various simulation results.

• 정보과학회 논문지
• /
• 제43권7호
• /
• pp.751-762
• /
• 2016

본고에서는 양자역학 기반의 기계학습인 양자 기계학습의 현황과 전망을 조망하고자 한다. 양자역학 기반의 양자컴퓨팅이 보여준 혁신적인 계산속도 개선에 힘입어 기계학습 분야에 양자컴퓨팅 알고리즘을 적용하는 연구는 빅데이터 시대의 도래에 따라 최근 집중적인 관심을 받고 있다. 고전적인 기계학습 알고리즘들에 양자컴퓨팅을 접목하여 획기적인 속도개선을 가능하게 하는 알고리즘 연구들과 최초의 상용 양자컴퓨터로 화제가 되고 있는 양자 담금질 알고리즘 등을 중심으로 양자 기계학습의 최신동향과 가능성을 살펴보고자 한다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권9호
• /
• pp.654-668
• /
• 2002

In this paper, we present an empirical study for improving the Korean text chunking based on machine learning and feature set selection approaches. We focus on two issues: the problem of selecting feature set for Korean chunking, and the problem of alleviating the data sparseness. To select a proper feature set, we use a heuristic method of searching through the space of feature sets using the estimated performance from a machine learning algorithm as a measure of "incremental usefulness" of a particular feature set. Besides, for smoothing the data sparseness, we suggest a method of using a general part-of-speech tag set and selective lexical information under the consideration of Korean language characteristics. Experimental results showed that chunk tags and lexical information within a given context window are important features and spacing unit information is less important than others, which are independent on the machine teaming techniques. Furthermore, using the selective lexical information gives not only a smoothing effect but also the reduction of the feature space than using all of lexical information. Korean text chunking based on the memory-based learning and the decision tree learning with the selected feature space showed the performance of precision/recall of 90.99%/92.52%, and 93.39%/93.41% respectively.

• 공학교육연구
• /
• 제23권2호
• /
• pp.24-30
• /
• 2020

This paper proposes the approaches to the evaluation of learning using concepts of artificial intelligence. Among various techniques, deep learning algorithm is employed to achieve quantitative results of evaluation. In particular, this paper focuses on the process-based evaluation instead of the result-based one using face expression. The expression is simply acquired by digital camera that records face expression when students solve sample test problems. Face expressions are trained using convolutional neural network (CNN) model followed by classification of expression data into three categories, i.e., easy, neutral, difficult. To substantiate the proposed approach, the simulation results show promising results, and this work is expected to open opportunities for intelligent evaluation system in the future.

• 전자통신동향분석
• /
• 제38권5호
• /
• pp.51-60
• /
• 2023

Quantum machine learning (QML) is an area of quantum computing that leverages its principles to develop machine learning algorithms and techniques. QML is aimed at combining traditional machine learning with the capabilities of quantum computing to devise approaches for problem solving and (big) data processing. Nevertheless, QML is in its early stage of the research and development. Thus, more theoretical studies are needed to understand whether a significant quantum speedup can be achieved compared with classical machine learning. If this is the case, the underlying physical principles may be explained. First, fundamental concepts and elements of QML should be established. We describe the inception and development of QML, highlighting essential quantum computing algorithms that are integral to QML. The advent of the noisy intermediate-scale quantum era and Google's demonstration of quantum supremacy are then addressed. Finally, we briefly discuss research prospects for QML.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2004년도 추계 종합학술대회 논문집
• /
• pp.11-16
• /
• 2004

지식 정보화 시대의 새로운 교육 형태와 패러다임으로 시간과 장소에 구애받지 않고 학습할 수 있으며 학습자 중심 교육을 제공하는 e-러닝에 대한 관심이 고조되고 있다. 그러나 기대에 비해서는 현재까지 e-러닝에 대한 폭발적인 수요와 성장은 발생하지 않고 있는데, 현재 대부분의 e-러닝 교육 형태가 기존의 일방적인 주입식 교육 형태를 단순히 디지털화 하여 학습 콘텐츠의 반복 학습을 제공하는데 그쳐 학습자들의 적극적인 참여와 관심을 이끌어 내는데 실패하였기 때문이다. e-러닝 환경에서 학습자들의 자발적인 참여를 이끌어내고 학습의 몰입도를 높이기 위해 학습 과제를 여러 명의 학생들이 상호 의존하여 공동으로 해결함으로써 학습 목표를 달성하는 형태의 협력학습에 대한 연구가 활발히 진행되고 있다. 본 논문에서는 학습자들 간의 상호작용 을 높이면서 학습행위를 촉진시키기 위한 협력 e-러닝 환경 구축 및 협력학습촉진 에이전트 적용 방안을 제시한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권6호
• /
• pp.2470-2491
• /
• 2018

Web-scale open information extraction (Open IE) plays an important role in NLP tasks like acquiring common-sense knowledge, learning selectional preferences and automatic text understanding. A large number of Open IE approaches have been proposed in the last decade, and the majority of these approaches are based on supervised learning or dependency parsing. In this paper, we present a novel method for web scale open information extraction, which employs cosine distance based on Google word vector as the confidence score of the extraction. The proposed method is a purely unsupervised learning algorithm without requiring any hand-labeled training data or dependency parse features. We also present the mathematically rigorous proof for the new method with Bayes Inference and Artificial Neural Network theory. It turns out that the proposed algorithm is equivalent to Maximum Likelihood Estimation of the joint probability distribution over the elements of the candidate extraction. The proof itself also theoretically suggests a typical usage of word vector for other NLP tasks. Experiments show that the distance-based method leads to further improvements over the newly presented Open IE systems on three benchmark datasets, in terms of effectiveness and efficiency.