• 디지털산업정보학회논문지
• /
• 제13권4호
• /
• pp.81-90
• /
• 2017

This paper presents a smart seat for correction of driver posture while driving. We introduce good postures with seat height, seat angle, head height, back of knees, distances of foot pedals, tilt of seat, etc. There have been some studies on correction of good posture while driving, effects of driving environment on driver's posture, sitting strategies based on seating pressure distribution, estimation of driver's standard postures, and others. However, there are a few studies on guide of good postures while driving for problem of driver's posture using machine leaning. Therefore, we suggest a smart seat for correction of driver's posture based on machine leaning, 1) developed the system to get postures by 10 piezoelectric effect element, 2) collect piezoelectric values from 37 drivers and 28 types of cars, 3) suggest 4 types of good postures while driving, 4) analyze test postures by kNN. As the results, we can guide good postures for bad or problems of postures while driving.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1516-1529
• /
• 2016

While global manufacturing is becoming more competitive due to variety of customer demand, increase in production cost and uncertainty in resource availability, the future ability of manufacturing industries depends upon the implementation of Smart Factory. With the convergence of new information and communication technology, Smart Factory enables manufacturers to respond quickly to customer demand and minimize resource usage while maximizing productivity performance. This paper presents the development of a big data analytics platform architecture for Smart Factory. As this platform represents a conceptual software structure needed to implement data-driven decision-making mechanism in shop floors, it enables the creation and use of diagnosis, prediction and optimization models through the use of data analytics and big data. The completion of implementing the platform will help manufacturers: 1) acquire an advanced technology towards manufacturing intelligence, 2) implement a cost-effective analytics environment through the use of standardized data interfaces and open-source solutions, 3) obtain a technical reference for time-efficiently implementing an analytics modeling environment, and 4) eventually improve productivity performance in manufacturing systems. This paper also presents a technical architecture for big data infrastructure, which we are implementing, and a case study to demonstrate energy-predictive analytics in a machine tool system.

• 대한임베디드공학회논문지
• /
• 제18권6호
• /
• pp.285-292
• /
• 2023

With the wide spread of smart farms and the advancements in IoT technology, it is easy to obtain additional data in addition to crop images. Consequently, deep learning-based crop disease diagnosis research utilizing multimodal data has become important. This study proposes a crop disease diagnosis method using multimodal supervised contrastive learning by expanding upon the multimodal self-supervised learning. RandAugment method was used to augment crop image and time series of environment data. These augmented data passed through encoder and projection head for each modality, yielding low-dimensional features. Subsequently, the proposed multimodal supervised contrastive loss helped features from the same class get closer while pushing apart those from different classes. Following this, the pretrained model was fine-tuned for crop disease diagnosis. The visualization of t-SNE result and comparative assessments of crop disease diagnosis performance substantiate that the proposed method has superior performance than multimodal self-supervised learning.

• International journal of advanced smart convergence
• /
• 제13권2호
• /
• pp.258-266
• /
• 2024

E-learning systems have proliferated in recent years, particularly in the wake of the global COVID-19 pandemic. For kids, there isn't a specific online learning platform available, though. To do this, new conceptual models of training and learning software that are adapted to the abilities and preferences of end users must be created. Young pupils: those in kindergarten, preschool, and elementary school are unique subjects with little research history. From the standpoint of software technology, young students who have never had access to a computer system are regarded as specific users with high expectations for the functionality and interface of the software, social network connectivity, and instantaneous Internet communication. In this study, we suggested creating an electronic learning management system that is web-based and appropriate for primary school pupils. User-centered design is the fundamental technique that was applied in the development of the system that we are proposing. Test findings have demonstrated that students who are using the digital environment for the first time are studying more effectively thanks to the online learning management system.

• 전기전자학회논문지
• /
• 제22권3호
• /
• pp.829-835
• /
• 2018

기존의 전력 시스템에서 불필요하게 생성되거나 낭비되는 예비전력을 감소시키고 에너지 사용 효율을 개선하기 위한 연구가 최근 활발히 진행되고 있다. 본 연구에서는 전기기기들의 전원 제어를 통한 에너지 사용 효율을 개선하기 위해 스마트그리드의 요소 기술 중 하나인 스마트미터기를 개발하며, 실시간으로 측정된 전력 사용량을 딥 러닝을 통해 전력 사용량의 트렌드를 분석 및 예측한다. 이후 예측된 전력 사용량과 실시간 전력 사용량을 비교하여 전기기기들의 전원을 제어하는 알고리즘을 제안 및 개발한다. 제안한 딥 러닝 기반의 스마트미터기의 성능을 확인하기 위해서 실제 전력 소비 환경을 구축하였고, 실시간으로 전력 사용 데이터를 확보하여 딥 러닝 모델에 학습시킨 뒤 전력 사용량을 예측하였다. 예측된 값과 실제 사용량을 실시간으로 비교하여 예측을 벗어난 기기들의 전원을 제어하여, 전력 사용량을 감소시키고 에너지 사용 효율이 개선되는 결과를 확인하였다.

• 한국위성정보통신학회논문지
• /
• 제9권2호
• /
• pp.91-95
• /
• 2014

스마트폰이나 테블릿 컴퓨터 등 스마트 모바일 단말기는 다양한 프로그램의 사용이 가능하고 데이터 통신 및 개인화 서비스를 통한 소셜네트워킹 서비스가 가능하다 이러한 특성으로 인해 특이 우리나라 사이버대학교에서는 이미 많은 인프라를 구축했으며 이러한 모바일 장비에 적합한 강의를 제공하고 있다. 그러나 여러 모바일 장비 중에서 스마트폰 사용 비중이 월등이 높지만 작은 디스플레이 환경은 학습자의 강의 수강(시청)에 다소 불편함이 발생해서 학습능률을 저하시키는 요소가 될 수 있다. 이런 학습저하 요소를 극복하기 위해서는 작은 디스플레이에서 효과적으로 학습할 수 있는 콘텐츠 레이아웃이 필요하다. 본 논문에서는 학습효과 향상용 스마트폰 교육 미디어 제작을 위해 황금분할, 황금나선 이론을 기반으로 한 외적체제를 연구하여 스마트폰 콘텐츠 개발에 활용할 레이아웃을 벡터방식인 일러스트 프로그램으로 개발해 플렛폼을 제시하였다.

• International journal of advanced smart convergence
• /
• 제10권4호
• /
• pp.110-116
• /
• 2021

This paper proposed a real-time earlobe detection system using deep learning on the web. Existing deep learning-based detection methods often find independent objects such as cars, mugs, cats, and people. We proposed a way to receive an image through the camera of the user device in a web environment and detect the earlobe on the server. First, we took a picture of the user's face with the user's device camera on the web so that the user's ears were visible. After that, we sent the photographed user's face to the server to find the earlobe. Based on the detected results, we printed an earring model on the user's earlobe on the web. We trained an existing YOLO v5 model using a dataset of about 200 that created a bounding box on the earlobe. We estimated the position of the earlobe through a trained deep learning model. Through this process, we proposed a real-time earlobe detection system on the web. The proposed method showed the performance of detecting earlobes in real-time and loading 3D models from the web in real-time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권9호
• /
• pp.3138-3150
• /
• 2021

Multimedia services on the Internet are continuously increasing. Accordingly, the demand for a technology for efficiently delivering multimedia traffic is also constantly increasing. The multicast technique, that delivers the same content to several destinations, is constantly being developed. This technique delivers a content from a source to all destinations through the multicast tree. The multicast tree with low cost increases the utilization of network resources. However, the finding of the optimal multicast tree that has the minimum link costs is very difficult and its calculation complexity is the same as the complexity of the Steiner tree calculation which is NP-complete. Therefore, we need an effective way to obtain a multicast tree with low cost and less calculation time on SDN-based smart network platforms. In this paper, we propose a new multicast tree generation algorithm which produces a multicast tree using an agent trained by model-based meta reinforcement learning. Experiments verified that the proposed algorithm generated multicast trees in less time compared with existing approximation algorithms. It produced multicast trees with low cost in a dynamic network environment compared with the previous DQN-based algorithm.

• 스마트미디어저널
• /
• 제13권3호
• /
• pp.45-52
• /
• 2024

오늘날 점점 증가하는 위협 환경에서는 보안 이벤트에 대한 신속하고 효과적인 탐지 및 대응이 필수적이다. 이러한 문제를 해결하기 위해 많은 기업과 조직에서는 다양한 보안관제시스템을 도입하여 보안 위협에 대응하고 있다. 그러나 기존 보안관제시스템은 보안 이벤트의 복잡성과 다양한 특성으로 인해 어려움을 겪고 있다. 본 연구에서는 인공지능 기반의 자동화된 통합보안관제시스템 모델을 제안하였다. 인공지능 기술인 딥러닝을 기반으로 하여 다양한 보안 이벤트에 대해 효과적인 탐지와 이를 처리하는 기능들을 제공한다. 이를 위해 모델은 기존의 보안관제시스템 한계를 극복하기 위하여 다양한 인공지능 알고리즘과 머신러닝 방법을 적용한다. 제안된 모델은 운영자의 업무량을 줄이고 효율적인 운영을 보장하며 보안 위협에 대한 신속한 대응을 지원하게 될 것이다.

• 정보교육학회논문지
• /
• 제15권1호
• /
• pp.67-76
• /
• 2011

본 논문은 스마트 기기의 터치 인터페이스를 활용하여 학습자가 직접 입체 학습 콘텐츠를 제어함으로써 보다 실감적인 교육 환경을 구축하고자 한다. 또한 기존의 입체 학습 콘텐츠는 제작의 어려움으로 인해 콘텐츠 확보와 제공에 한계가 있어 교사 및 학습자가 직접 콘텐츠를 제작하고 공유할 수 있도록 프레임워크를 설계하였다. 프레임워크는 직관적인 XML 언어로 구성되고 안드로이드가 탑재된 기기에서 재생 및 저작이 가능하도록 어플리케이션을 구현하였으며 콘텐츠 공유를 위한 서버 환경도 구축하였다. 제안한 프레임워크는 전문가 평가를 통해 타당성을 검증한 결과 새로운 학습 콘텐츠 활용 가능성 면에서 긍정적으로 분석되었다.