• 한국음향학회지
• /
• 제42권4호
• /
• pp.357-363
• /
• 2023

다양한 신호가 혼합된 수중 신호로부터 각각의 신호를 분리하는 기술은 오랫동안 연구되어왔지만, 낮은 품질의 수중 신호의 특성 상 쉽게 해결되지 않는 문제이다. 현재 주로 사용되는 방법은 Short-time Fourier transform을 사용하여 수신된 음향신호의 스펙트로그램을 얻은 뒤, 주파수의 특성을 분석하여 신호를 분리하는 기술이다. 하지만 매개변수의 최적화가 까다롭고, 스펙트로그램으로 변환하는 과정에서 위상 정보들이 손실되는 한계점이 지적되었다. 본 연구에서는 이러한 문제를 해결하기 위해 긴 시계열 신호 처리에서 좋은 성능을 보인 Dual-path Recurrent Neural Network을 기반으로, 다중 채널 센서로부터 생성된 입력신호인 3차원 텐서를 처리할 수 있도록 변형된 Tripple-path Recurrent Neural Network을 제안한다. 제안하는 기술은 먼저 다중 채널 입력 신호를 짧은 조각으로 분할하고 조각 내 신호 간, 구성된 조각간, 그리고 채널 신호 간의 각각의 관계를 고려한 3차원 텐서를 생성하여 로컬 및 글로벌 특성을 학습한다. 제안된 기법은, 기존 방법에 비해 개선된 Root Mean Square Error 값과 Scale Invariant Signal to Noise Ratio을 가짐을 확인하였다.

• 문화기술의 융합
• /
• 제9권2호
• /
• pp.475-481
• /
• 2023

머신러닝과 같은 소프트웨어가 일상생활에 매우 큰 영향력을 발휘하고 있는 상황에서, 소프트웨어의 개발비용을 평가하는 비용 모델의 중요성이 지속적으로 증가하고 있다. 비용 모델로서 LOC(Line of Code)와 M/M(Man-Month) 모델은 소프트웨어의 양적인 요소들을 측정하는 비용모델이다. 이와는 달리, FP(Function Point)는 소프트웨어의 기능적 특징들을 평가하는 비용모델로서 소프트웨어의 질적인 요소를 평가한다는 점에서 효과적이다. 그러나 FP는 머신러닝 소프트웨어의 주요한 요소들을 평가하지 않기 때문에 머신러닝 소프트웨어를 평가하는데 한계를 가진다. 본 논문은 확장형 FP(Extended Function Point, ExFP)를 제안한다. 확장형 FP는 머신러닝의 주요 특징인 하이퍼 파라미터와 그것의 최적화에 대한 복잡도를 반영하여 소프트웨어의 기능적 요소를 평가하도록 확장하였기 때문에 머신러닝과 같은 최신 소프트웨어에의 비용 평가에 적합하다. 머신러닝 소프트웨어의 특징을 반영한 평가를 통해 제안된 확장형 FP의 효용성을 보였다.

• Geomechanics and Engineering
• /
• 제34권2호
• /
• pp.155-171
• /
• 2023

Aiming at the grouting treatment of water inflow in karst conduits, a visualized experiment system for conduit-type grouting blocking was developed. Through the improved water supply system and grouting system, and the optimized multisource information monitoring system, the real-time observation of diffusion and deposition of slurry, and the data acquisition of pressure and velocity during the whole process of grouting were realized, which breaks through the problem that the monitoring element is easy to fail due to slurry adhesion in conventional test system. Based on the grouting experiments in static and flowing water, the diffusion and deposition behavior of the quick-setting slurry under different working conditions were analyzed. The temporal and spatial variation behavior of the pressure and velocity were studied, and the blocking mechanism of the grouting were further revealed. The results showed that: (1) Under the flowing water condition, the counter-flow diffusion distance of slurry was negatively correlated with the flow water velocity and the volume ratio of cement and sodium silicate (C-S ratio), and positively correlated with the grouting volume. The slurry deposition thickness was negatively correlated with the flowing water velocity, and positively correlated with the grouting volume and C-S ratio. (2) The pressure increased slowly before blocking of the flowing water and rapidly after blocking in karst conduits. (3) With the continuous progress of grouting, the flowing water velocity decreased slowly first, then significantly, and finally tended to be stable. According to the research results, some engineering recommendations were put forward for the grouting treatment of the conduit-type water inflow disaster, which has been successfully applied in the treatment project of the China Resources Cement (Pingnan) Limestone Mine. This study provided some guidance and reference for the parameter optimization of grouting for the treatment projects of water inflow in karst conduits.

• 대한원격탐사학회지
• /
• 제40권1호
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.

• 대한조선학회논문집
• /
• 제60권6호
• /
• pp.424-432
• /
• 2023

This study deals with the design of a safety device around a leisure boat propeller. The safety device is to be designed to minimize performance degradation attached to propulsors in coastal waters. These devices, important for preventing propeller accidents, negatively gives influence boat performance, especially at higher speeds. In order to minimize the negative effect, the accelerating ducts, normally used in ESDs (Energy Saving Devices) have been chosen as a safety device. The present study aims to design an optimal duct (minimizing negative effect) through the parametric study. Based on the Marine 19A nozzle, the nozzle's thickness and angle were varied to obtain the optimum parameter in the preliminary design by the computational fluid dynamics program Star-CCM+ Ver. 15.02. In the detailed design, a NACA 4-digit Airfoil shape resembling the Marine 19A by modification at the trailing edge was chosen and the optimum shape was chosen according to variation of camber, thickness, and incidence angle for optimization. The optimally designed duct shows a speed decrease of about 10% in the sea trial result, which is much smaller than the normal speed decrease of at least 30%. The present designing method can give wide applications to the leisure boat because the wake is almost the same due to using the outboard propulsor.

• 한국인터넷방송통신학회논문지
• /
• 제23권6호
• /
• pp.1-7
• /
• 2023

본 논문은 인공지능 기술을 활용하여 일반 도로와 침수 도로를 분류하는 학습모델을 개발하였다. 다양한 데이터 증강기법을 사용하여 학습 데이터의 다양성을 확장하며, 여러 환경에서도 좋은 성능을 보이는 모델을 구현하였다. CNN 기반의 Resnet152v2 모델을 사전 학습모델로 활용하여, 전이 학습을 진행하였다. 모델의 학습 과정에서 다양한 파라미터 튜닝 및 최적화 과정을 거쳐 최종 모델의 성능을 향상하였다. 학습은 파이선으로 Google Colab NVIDIA Tesla T4 GPU를 사용하여 구현하였고, 테스트 결과 시험 데이터 세트에서 매우 높은 정확도로 침수상황을 탐지함을 알 수 있었다.

• Advances in nano research
• /
• 제16권4호
• /
• pp.341-352
• /
• 2024

This study investigates the heat and mass transfer characteristics of a MoS₂ nanoparticle suspension in ethylene glycol over a porous stretching sheet. MoS₂ nanoparticles are known for their exceptional thermal and chemical stability which makes it convenient for enhancing the energy and mass transport properties of base fluids. Ethylene glycol, a common coolant in various industrial applications is utilized as the suspending medium due to its superior heat transfer properties. The effects of variable thermal conductivity, variable mass diffusivity, thermal radiation and thermophoresis which are crucial parameters in affecting the transport phenomena of nanofluids are taken into consideration. The governing partial differential equations representing the conservation of momentum, energy, and concentration are reduced to a set of nonlinear ordinary differential equations using appropriate similarity transformations. R software and MATLAB-bvp5c are used to compute the solutions. The impact of key parameters, including the nanoparticle volume fraction, magnetic field, Prandtl number, and thermophoresis parameter on the flow, heat and mass transfer rates is systematically examined. The study reveals that the presence of MoS₂ nanoparticles curbs the friction between the fluid and the solid boundary. Moreover, the variable thermal conductivity controls the rate of heat transfer and variable mass diffusivity regulates the rate of mass transfer. The numerical and statistical results computed are mutually justified via tables. The results obtained from this investigation provide valuable insights into the design and optimization of systems involving nanofluid-based heat and mass transfer processes, such as solar collectors, chemical reactors, and heat exchangers. Furthermore, the findings contribute to a deeper understanding of stretching sheet systems, such as in manufacturing processes involving continuous casting or polymer film production. The incorporation of MoS₂-C₂H₆O₂ nanofluids can potentially optimize temperature distribution and fluid dynamics.

• 대한영상의학회지
• /
• 제83권6호
• /
• pp.1229-1239
• /
• 2022

최근 인공지능기술은 자기공명영상(이하 MRI)의 폭넓은 분야에서 임상적 활용가치를 보여주고 있다. 특히, MRI에서 영상획득과정의 효율성 및 복원된 영상의 품질을 향상시키기 위한 목적으로 인공지능모델의 개발이 활발하다. 임상에서 활용되는 다양한 MRI 프로토콜에서 인공지능은 병렬영상기법과 같은 기존 가속화 방법 대비 추가적인 영상획득시간을 가능하게 해줄 수 것으로 기대된다. 또한, 펄스시퀀스 디자인, 영상의 인공물 감소, 자동화된 품질평가와 같은 영역에서도 인공지능모델은 도움을 줄 수 있는 연구 결과들이 소개되고 있다. 또한, 영상분석 과정에서 중요한 장비 및 프로토콜의 영향을 줄여줄 수 있는 방법으로도 인공지능 기반의 접근이 이루어지고 있다. 본 종설에서는 MRI 영상의 획득 과정에서 최근 인공지능기술들이 적용되고 있는 분야 및 해당 분야에서의 인공지능기술의 개발 및 적용과 관련된 현안들을 소개하고자 한다.

• 한국전기전자재료학회논문지
• /
• 제37권4호
• /
• pp.382-393
• /
• 2024

유체 디스펜싱(fluid dispensing) 방식인 Microplotter 시스템은 압전 소자를 통한 초음파 펌핑(pumpin)을 기반으로 유체를 분사한다. 이 기법은 넓은 범위의 점도를 가진 다양한 물질들이 마이크로 사이즈로 프린팅 되는 것을 가능하게 한다. 본 논문에서는 디스펜서 프린팅 기술에 대해 소개하고 장비를 이용한 다양한 공정을 이해 및 응용에 목적을 두고 있다. 또한, 분사 강도, 분사 시 팁의 높이, 분사 속도와 같은 매개변수들을 조절하여 장비의 최적화 방법에 대해 설명하고자 한다. 금속 나노 입자, 탄소나노튜브, DNA, 단백질 등 광범위한 유체와 호환된다는 Microplotter의 장점을 이용함으로써 인쇄전자, 생명공학, 화학공학 등 다양한 분야에서 활용될 것으로 기대된다.

• 드라이브 ㆍ 컨트롤
• /
• 제21권2호
• /
• pp.44-52
• /
• 2024

In this study, we predicted PTO power requirements based on torque predicted by the discrete element method and the multi-body dynamics coupling method. Six different scenarios were simulated to predict PTO power requirements in different soil conditions. The first scenario was a tillage operation on cohesionless soil, and the field was modeled using the Hertz-Mindlin contact model. In the second through sixth scenarios, tillage operations were performed on viscous soils, and the field was represented by the Hertz-Mindlin + JKR model for cohesion. To check the influence of surface energy, a parameter to reproduce cohesion, on the power requirement, a simple regression analysis was performed. The significance and appropriateness of the regression model were checked and found to be acceptable. The study findings are expected to be used in design optimization studies of agricultural machinery by predicting power requirements using the discrete element method and the multi-body dynamics coupling method and analyzing the effect of soil cohesion on the power requirement.