• 한국항해학회지
• /
• 제22권2호
• /
• pp.13-22
• /
• 1998

선재용 자동식별시스템(AIS)은 21세기에 선박식별, 감시, 통신에 사용하기 위한 중요한 해상장비가 될 것 이며, 현재 여러 선진국에서 개발중에 있다. 본 논문에서는 AIS의 기술적인 방법을 제시하고자 한다. AIS의 주요 부분은 방송트랜스폰더(broadcast transponder)이고 핵심기술은 STDMA(self-organized Time Division Multiple Access)라 불리는 고용량의 VHF 라디오 데이터링크(radio data link)이다. 해상 VHF채널로 자신의 위치와 신분(identities)을 자동적이고 주기적으로 방송하게 될 AIS가 설치된 선박들은 선상이나 VTS 센터에 있는 ECDIC의 서면에 표시가 될 것이다. AIS는 방송서비스뿐만 아니라 일대일(point topoint) 통신 서비스를 지원하게 될 것이다. 본 논문에서는 STDMA의 방안 뿐만 아니라 AIS의 구성과 동작원리 그리고 기능을 설명하고자한다. 이외에 IMO에서의 AIS에 관한 표준화 작업을 본 논문에 소개하고자 한다.

• 한국전자통신학회논문지
• /
• 제18권1호
• /
• pp.107-114
• /
• 2023

본 연구는 건축 부재 사용량 예측을 위한 인공지능 기반의 학습모델을 설계 및 구현하는 방법에 대하여 기술하였다. 인공지능(Artifical intelligence : AI) 은 기술의 발전에 힘입어 다양한 분야에서 폭넓게 활용되고 있지만, 건축설계분야 데이터의 특수성 및 빅데이터 수집의 어려움으로 인해 현장 활용도가 매우 저조한 상태이다. 따라서 건축설계분야에서 인공지능 기술을 도입할 수 있도록 건축 부재 단위의 AI문제를 발굴해 내었으며, 해당분야 데이터가 가지는 특이성을 해결하기 위한 새로운 전처리 기법을 고안하였다. 고안된 전처리 기법을 토대로 인공지능 모델을 구현하였고, 구현된 인공지능 모델의 건축 부재 사용량 예측 정확도가 실제 산업에 사용할 수 있는 수준임을 확인하였다.

• 자원환경지질
• /
• 제34권5호
• /
• pp.437-446
• /
• 2001

부산 보배견운모 광상의 프로필리틱 열수변질대에서 형성된 녹염석은 다양한 누대구조를 수반하는데, 다중결정성장 누대구조, 진동누대구조, patchy누대구조 및 강도가 약한 불규칙한 누대구조가 특징적이다. 누대구조는 주로 열수용 액의 AI Fe의 활동도에 좌우되며, 전반적으로 결정의 중심부에서는 AI, 가장자리에서는 Fe의 함량이 높다. 녹염석 의 Ps는 18.5-34.3 mot.% 범위이다. 여러 결정이 중첩하여 형성된 누대구조에서는 잔류조직이 부분적으로 흡수용해 되었으며, 이후에 결정들이 새로 성장하였다. 다중결정성장 누대구조나 진동누대구조는 열수시스템의 유체의 화학조성, 산화환원전위, 온도 등과 같은 물리화학적 변수들이 급격하게 변동하였음 지시한다

• 웰빙융합연구
• /
• 제6권2호
• /
• pp.27-31
• /
• 2023

Purpose: Establishment of a real-time monitoring system for odor control in traditional markets in Gangwon-do and a system for linking prevention facilities. Research design, data and methodology: Build server and system logic based on data through real-time monitoring device (sensor-based). A temporary data generation program for deep learning is developed to develop a model for odor data. Results: A REST API was developed for using the model prediction service, and a test was performed to find an algorithm with high prediction probability and parameter values optimized for learning. In the deep learning algorithm for AI modeling development, Pandas was used for data analysis and processing, and TensorFlow V2 (keras) was used as the deep learning library. The activation function was swish, the performance of the model was optimized for Adam, the performance was measured with MSE, the model method was Functional API, and the model storage format was Sequential API (LSTM)/HDF5. Conclusions: The developed system has the potential to effectively monitor and manage odors in traditional markets. By utilizing real-time data, the system can provide timely alerts and facilitate preventive measures to control and mitigate odors. The AI modeling component enhances the system's predictive capabilities, allowing for proactive odor management.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 추계학술대회논문집A
• /
• pp.623-628
• /
• 2001

The styling of passenger car wheels and their effect on vehicle appearance has increased in importance in recent years. The wheel designer has been given the task of insuring that a wheel design meets its engineering objectives without affecting the styling theme. The wheel and tire system is considered as a vehicle component whose dynamic modal information of the tire/wheel system are employed in the modal synthesis model of the vehicle. The Vibration characteristics of a passenger car wheel play an important role to judge a ride comfortability and quality for a passenger car. In this paper, the vibration characteristics of a AI-alloy and steel wheel for passenger car are studied. Natural frequency, damping and mode shape are determined experimentally by frequency response function method. Results show that wheel material property, size and design are parameter for shift of natural frequency and damping.

• 공학교육연구
• /
• 제23권3호
• /
• pp.41-48
• /
• 2020

In light of the 4th industrial revolution, this research identifies critical thinking education as the key component of cultivating a new pool of integrative talents. It seeks to find ways to incorporate artificial intelligence, one of the biggest upcoming innovations, into critical thinking education. This paper aims to propose an education model that raises awareness on related issues of AI and set a healthy direction for its development through debates on topics raised by the film, Ex Machina, which depicts the dangerous implications of AI technology.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.227-241
• /
• 2021

Object detection techniques based on deep learning such as YOLO have high detection performance and precision in a single channel video stream. In order to expand to multiple channel object detection in real-time, however, high-performance hardware is required. In this paper, we propose a novel back-end server framework, a real-time AI vision platform (RAVIP), which can extend the object detection function from single channel to simultaneous multi-channels, which can work well even in low-end server hardware. RAVIP assembles appropriate component modules from the RODEM (real-time object detection module) Base to create per-channel instances for each channel, enabling efficient parallelization of object detection instances on limited hardware resources through continuous monitoring with respect to resource utilization. Through practical experiments, RAVIP shows that it is possible to optimize CPU, GPU, and memory utilization while performing object detection service in a multi-channel situation. In addition, it has been proven that RAVIP can provide object detection services with 25 FPS for all 16 channels at the same time.

• 국제학술발표논문집
• /
• The 4th International Conference on Construction Engineering and Project Management Organized by the University of New South Wales
• /
• pp.597-602
• /
• 2011

A robust asset management methodology is essential for effective decision-making of maintenance, repair and rehabilitation of a bridge network. It can be achieved by a computer-based bridge management system (BMS). Successful BMS development requires a reliable bridge deterioration model, which is the most crucial component in a BMS, and an optimal management philosophy. The maintenance optimization methodology proposed in this paper is developed for a small bridge network with limited structural condition rating records. . The methodology is organized in three major components: (1) bridge health index (BHI); (2) maintenance and budget optimization; and (3) reliable Artificial Intelligence (AI) based bridge deterioration model. The outcomes of the paper will help to identify BMS implementation problems and to provide appropriate solutions for managing small bridge networks.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.335-349
• /
• 2023

Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images.

• 한국잡초학회지
• /
• 제9권2호
• /
• pp.103-107
• /
• 1989

논 제초제(除草劑) butachlor에 대한 유묘(幼苗)의 약해반응정도(藥害反應程度)가 다른 벼 5개 품종(品種)에 3가지 다른 약량(藥量)을 이앙시(移秧時)에 처리(處理)하여 이후(以後)의 생육상태(生育狀態) 및 수량구성요소(收量構成要素)와 수량(收量)을 조사(調査)하였다. 1. 약해정도(藥害程度)는 Zhy-Lian-Ai-Yun-Nam이 가장 경미하였고 다음으로 한강찰벼, 원풍벼, 청청벼, 삼성벼의 순으로 심하였다. 2. 약해(藥害)는 토장(草長)보다 분얼수(分蘖數)에 더 크게 영향하였다. 전품종(全品種)에서 주당수수(株當穗數)의 감소가 컸으나 그 정도는 품종간(品種間)에 약간의 차이가 있었다. 3. 수량(收量)은 약해(藥害)가 낮은 Zhy-Lian-Ai-Yun-Nam이 수량감소가 가장 컸고 약해가 심하였던 삼성벼와 청청벼는 약해에 비하여 수량감소가 적었는데 이는 주당수수(株當穗數)의 감소에 상응(相應)하여 주당영화수(株當潁花數)가 증가(增加)하였기 때문이다. 4. 약해(藥害)가 중간정도(中間程度)였던 한강찰벼와 원풍벼는 주당수수감소(株當穗數減少)에 따라 주당영화수(株當潁花數)가 증가하지 않았고 또 원풍벼는 1,000립중(粒重) 감소하여 수량감수가 컸다.