• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4776-4794
• /
• 2020

We propose a rapid adaptive learning framework for streaming object detection, called EER-ASSL. The method combines the expected error reduction (EER) dependent rollback learning and the active semi-supervised learning (ASSL) for a rapid adaptive CNN detector. Most CNN object detectors are built on the assumption of static data distribution. However, images are often noisy and biased, and the data distribution is imbalanced in a real world environment. The proposed method consists of collaborative sampling and EER-ASSL. The EER-ASSL utilizes the active learning (AL) and rollback based semi-supervised learning (SSL). The AL allows us to select more informative and representative samples measuring uncertainty and diversity. The SSL divides the selected streaming image samples into the bins and each bin repeatedly transfers the discriminative knowledge of the EER and CNN models to the next bin until convergence and incorporation with the EER rollback learning algorithm is achieved. The EER models provide a rapid short-term myopic adaptation and the CNN models an incremental long-term performance improvement. EER-ASSL can overcome noisy and biased labels in varying data distribution. Extensive experiments shows that EER-ASSL obtained 70.9 mAP compared to state-of-the-art technology such as Faster RCNN, SSD300, and YOLOv2.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.358-358
• /
• 2000

An iterative learning control technique based on a linear quadratic optimal criterion is proposed for temperature uniformity control of a silicon wafer in rapid thermal processing.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 추계 학술대회 학술발표 논문집
• /
• pp.95-98
• /
• 2003

In this paper, an adaptive fuzzy neural control of unknown nonlinear systems based on the rapid learning algorithm is proposed for optimal parameterization. We combine the advantages of fuzzy control and neural network techniques to develop an adaptive fuzzy control system for updating nonlinear parameters of controller. The Fuzzy Neural Network(FNN), which is constructed by an equivalent four-layer connectionist network, is able to learn to control a process by updating the membership functions. The free parameters of the AFN controller are adjusted on-line according to the control law and adaptive law for the purpose of controlling the plant track a given trajectory and it's initial values are off-line preprocessing, In order to improve the convergence of the learning process, we propose a rapid learning algorithm which combines the error back-propagation algorithm with Aitken's $\delta$$\^$2/ algorithm. The heart of this approach ls to reduce the computational burden during the FNN learning process and to improve convergence speed. The simulation results for nonlinear plant demonstrate the control effectiveness of the proposed system for optimal parameterization.

• Biomolecules & Therapeutics
• /
• 제30권2호
• /
• pp.179-183
• /
• 2022

Traditionally, pathologists microscopically examine tissue sections to detect pathological lesions; the many slides that must be evaluated impose severe work burdens. Also, diagnostic accuracy varies by pathologist training and experience; better diagnostic tools are required. Given the rapid development of computer vision, automated deep learning is now used to classify microscopic images, including medical images. Here, we used a Inception-v3 deep learning model to detect mouse lung metastatic tumors via whole slide imaging (WSI); we cropped the images to 151 by 151 pixels. The images were divided into training (53.8%) and test (46.2%) sets (21,017 and 18,016 images, respectively). When images from lung tissue containing tumor tissues were evaluated, the model accuracy was 98.76%. When images from normal lung tissue were evaluated, the model accuracy ("no tumor") was 99.87%. Thus, the deep learning model distinguished metastatic lesions from normal lung tissue. Our approach will allow the rapid and accurate analysis of various tissues.

• 대한원격탐사학회지
• /
• 제39권3호
• /
• pp.269-282
• /
• 2023

본 연구는 딥러닝 모델(deep learning model)을 활용하여 토지피복분류를 수행하였으며 입력 이미지의 크기, Stride 적용 등 데이터세트(dataset)의 조절을 통해 토지피복분류를 위한 최적의 딥러닝 모델 선정을 목적으로 하였다. 적용한 딥러닝 모델은 3종류로 Encoder-Decoder 구조를 가진 U-net과 DeeplabV3+, 두 가지 모델을 결합한 앙상블(Ensemble) 모델을 활용하였다. 데이터세트는 RapidEye 위성영상을 입력영상으로, 라벨(label) 이미지는 Intergovernmental Panel on Climate Change 토지이용의 6가지 범주에 따라 구축한 Raster 이미지를 참값으로 활용하였다. 딥러닝 모델의 정확도 향상을 위해 데이터세트의 질적 향상 문제에 대해 주목하였으며 딥러닝 모델(U-net, DeeplabV3+, Ensemble), 입력 이미지 크기(64 × 64 pixel, 256 × 256 pixel), Stride 적용(50%, 100%) 조합을 통해 12가지 토지피복도를 구축하였다. 라벨 이미지와 딥러닝 모델 기반의 토지피복도의 정합성 평가결과, U-net과 DeeplabV3+ 모델의 전체 정확도는 각각 최대 약 87.9%와 89.8%, kappa 계수는 모두 약 72% 이상으로 높은 정확도를 보였으며, 64 × 64 pixel 크기의 데이터세트를 활용한 U-net 모델의 정확도가 가장 높았다. 또한 딥러닝 모델에 앙상블 및 Stride를 적용한 결과, 최대 약 3% 정확도가 상승하였으며 Semantic Segmentation 기반 딥러닝 모델의 단점인 경계간의 불일치가 개선됨을 확인하였다.

• 대한원격탐사학회지
• /
• 제36권5_1호
• /
• pp.823-833
• /
• 2020

안정적인 작물 생산을 위하여 국내 농업지역에 대한 효과적인 작황 모니터링 기법의 요구가 증대되고 있다. 본 연구에서는 작물 재배지역 추출을 위하여 딥러닝 기법을 이용한 분류 모델을 개발하고, 이를 위성영상에 적용하고자 하였다. 이를 위하여, 식생분석에 유용한 blue, green, red, red-edge, NIR 밴드를 포함하고 있는 RapidEye 위성영상을 이용하여 작물 재배지역에 대한 훈련자료를 구축하고, 이를 활용하여 국내 양파 및 마늘 작물에 대한 재배면적을 추정하고자 하였다. 대기보정된 RapidEye 위성영상을 활용하여 훈련자료를 구축하였으며, 작물지역의 분류를 위하여 대표적인 의미론적 분할을 위한 딥러닝 모델인 FC-DenseNet을 이용하여 딥러닝 모델을 생성하였다. 최종적인 작물 재배지역은 지적도와의 결합을 통하여 객체 기반의 자료로 생성하였다. 실험결과, 대기보정된 훈련자료를 이용하여 학습된 FC-DenseNet 모델은 훈련에 사용되지 않은 타 지역의 작물 재배지역을 효과적으로 검출할 수 있음을 확인하였다.

• 전자공학회논문지S
• /
• 제35S권3호
• /
• pp.1-8
• /
• 1998

In this paper, we propose a Neural Call Admission Control (CAC) method using a Sparse Distributed Memory(SDM). CAC is a key technology of TM network traffic control. It should be adaptable to the rapid and various changes of the ATM network environment. conventional approach to the ATM CAC requires network analysis in all cases. So, the optimal implementation is said to be very difficult. Therefore, neural approach have recently been employed. However, it does not mett the adaptability requirements. because it requires additional learning data tables and learning phase during CAC operation. We have proposed a neural network CAC method based on SDM that is more actural than conventioal approach to apply it to CAC. We compared it with previous neural network CAC method. It provides CAC with good adaptability to manage changes. Experimenatal results show that it has rapid adaptability and stability without additional learning table or learning phase.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.476-483
• /
• 2022

The novel coronavirus pandemic has had a significant impact on society and everyday life. The pandemic imposed a global shutdown leading to many challenges such as the suspension of academic programs at universities. The result of this suspension contributed to the rapid overnight migration of educational activities from traditional face-to-face learning to a virtual environment which until then was unfamiliar to both instructors and students. This study identified the experiences faced by built environment higher education instructors in KwaZulu-Natal, South Africa during this sudden switch to online teaching and learning. This pilot study employed a quantitative research approach to survey instructor experiences on online teaching and learning during a global pandemic. The data was computed and analyzed using IBM Statistical Package for Social Sciences (SPSS) version 27. Descriptive statistics were used to analyze the data collected. The study sample comprised of 20 higher education instructors in the region of the KwaZulu Natal province in South Africa. Findings from the study revealed that instructors faced adaptive challenges with rapidly having to redesign and remodel the mode of academic course delivery and assessments to suit an online platform. Additionally, instructors observed that students faced technological challenges such as connectivity and navigating the online learning management system platforms. The challenges identified by instructors and students can be effectively transformed to opportunities for future learning under the 'new normal'.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.805-807
• /
• 2021

In-hospital cardiac arrest is a significant problem for medical systems. Although the traditional early warning systems have been widely applied, they still contain many drawbacks, such as the high false warning rate and low sensitivity. This paper proposed a strategy that involves a deep learning approach based on a novel interpretable deep tabular data learning architecture, named TabNet, for the Rapid Response System. This study has been processed and validated on a dataset collected from two hospitals of Chonnam National University, Korea, in over 10 years. The learning metrics used for the experiment are the area under the receiver operating characteristic curve score (AUROC) and the area under the precision-recall curve score (AUPRC). The experiment on a large real-time dataset shows that our method improves compared to other machine learning-based approaches.

• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.304-311
• /
• 2021

The relevance of the research involves outlining the need for modern professionals to acquire new competencies. In the conditions of rapid civilizational progress, in order to meet the requirements of the labor market in the knowledge society, there is a readiness for continuous training as an indicator of professional success. The purpose of the research is to identify the impact of various forms of application of information technologies for lifelong learning in order to provide the continuous self-development of each person without cultural or age restrictions and on the basis of rapid digital progress. A high level (96%) of need of the adult population in continuing education with the use of digital technologies has been established. The most effective ways to implement the concept of "lifelong learning" have been identified (educational camps, lifelong learning, mass open online courses, Makerspace activities, portfolio use, use of emoji, casual game, scientific research with iVR game, implementation of digital games, work in scientific cafes). 2 basic objectives of continuing professional education for adults have been outlined (continuous improvement of qualifications and obtaining new qualifications). The features of ICT application in adult education have been investigated by using the following methods, namely: flexibility in terms of easy access to ideas, solving various problems, orientation approach, functional learning, group or individual learning, integration of leisure, personal and professional activities, gamification. The advantages of application of information technologies for continuous education (economic, time, and adaptive) have been revealed. The concept of continuous adult learning in the context of digitalization has been concluded. The research provides a description of the structural principles of the concept of additional education; a system of information requests of the applicant, as well as basic technologies for lifelong learning. The research indicates the lack of comprehensive research in the relevant field. The practical significance of the research results lies in the possibility of using the obtained results for a wider acquaintance of the adult population with the importance of the application of lifelong learning for professional activities and the introduction of methods for its implementation in the educational policy of the state.