• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.358-361
• /
• 2021

In order to improve the accuracy of small target detection more effectively, this paper proposes an improved single shot detector (SSD) target detection and recognition method based on cspdarknet53, which introduces lightweight ECA attention mechanism and Feature Pyramid Network (FPN). First, the original SSD backbone network is replaced with cspdarknet53 to enhance the learning ability of the network. Then, a lightweight ECA attention mechanism is added to the basic convolution block to optimize the network. Finally, FPN is used to gradually fuse the multi-scale feature maps used for detection in the SSD from the deep to the shallow layers of the network to improve the positioning accuracy and classification accuracy of the network. Experiments show that the proposed target detection algorithm has better detection accuracy, and it improves the detection accuracy especially for small targets.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제62차 하계학술대회논문집 28권2호
• /
• pp.139-142
• /
• 2020

NB-IoT(Narrow Band Internet of Things) is an emerging LPWAN(Low Power Wide Area Network) radio technology. NB-IoT has many advantages like low power, low cost, and high coverage. However low bandwidth and low sampling rates also lead to poor positioning accuracy. This paper proposed a solution to optimize positioning accuracy under the OTDOA(Observed Time Difference of Arrival) approach by utilizing MLR(Multiple Linear Regression) models. Through the MLR model to predict the influence degree of weather(temperature, humidity, light intensity and air pressure) on the arrival time of signal transmission to improve the measurement accuracy. The improvement of measurement accuracy can greatly improve IoT applications based on NB-IoT.

• 국제학술발표논문집
• /
• The 7th International Conference on Construction Engineering and Project Management Summit Forum on Sustainable Construction and Management
• /
• pp.210-213
• /
• 2017

The construction industry has witnessed an exponential growth of drones used in the field over the past few years. Likewise, the field of maintenance has paid increasing attention to using drones with a view to improving the efficiency of condition checks in high-rise buildings and major space. Although operators manipulate drones to inspect buildings at present, drones are expected to autonomously move around without operators in a few years. Also, for indoor maintenance, it is important for drones to find accurate locations, which is implemented by real-time locating systems(RTLS). Yet, the accuracy of RTLS varies across the types of systems and indoor settings, which warrants a locating system suitable for indoor space and a location correction system designed to improve the accuracy. Hence, the current study investigated the accuracy of real-time locating systems(RTLS) for the maintenance of indoor space of buildings with drones and delved into the methods of correcting the location information to improve the accuracy of RTLS.

• 반도체디스플레이기술학회지
• /
• 제22권4호
• /
• pp.166-171
• /
• 2023

This paper presents the synaptic characteristics of IGZO memristors in neuromorphic computing, using MATLAB/Simulink and NeuroSim. In order to investigate the variations in the conductivity of IGZO memristor and the corresponding changes in the hidden layer, simulations are conducted by using the MNIST dataset. It was observed from simulation results that the recognition accuracy could be dependent on various parameters of IGZO memristor, along with the experimental exploration. Moreover, we identified optimal parameters to achieve high accuracy, showing an outstanding accuracy of 96.83% in image classification.

• 대한상한금궤의학회지
• /
• 제14권1호
• /
• pp.41-50
• /
• 2022

Objective : The purpose of this study is to explore the most suitable machine learning model algorithm for Shanghanlun diagnostic system classification using natural language processing (NLP). Methods : A total of 201 data items were collected from 『Shanghanlun』 and 『Clinical Shanghanlun』, 'Taeyangbyeong-gyeolhyung' and 'Eumyangyeokchahunobokbyeong' were excluded to prevent oversampling or undersampling. Data were pretreated using a twitter Korean tokenizer and trained by logistic regression, ridge regression, lasso regression, naive bayes classifier, decision tree, and random forest algorithms. The accuracy of the models were compared. Results : As a result of machine learning, ridge regression and naive Bayes classifier showed an accuracy of 0.843, logistic regression and random forest showed an accuracy of 0.804, and decision tree showed an accuracy of 0.745, while lasso regression showed an accuracy of 0.608. Conclusions : Ridge regression and naive Bayes classifier are suitable NLP machine learning models for the Shanghanlun diagnostic system classification.

• International journal of advanced smart convergence
• /
• 제13권2호
• /
• pp.80-87
• /
• 2024

This paper focuses on improving accuracy in constrained computing settings by employing the ReLU (Rectified Linear Unit) activation function. The research conducted involves modifying parameters of the ReLU function and comparing performance in terms of accuracy and computational time. This paper specifically focuses on optimizing ReLU in the context of a Multilayer Perceptron (MLP) by determining the ideal values for features such as the dimensions of the linear layers and the learning rate (Ir). In order to optimize performance, the paper experiments with adjusting parameters like the size dimensions of linear layers and Ir values to induce the best performance outcomes. The experimental results show that using ReLU alone yielded the highest accuracy of 96.7% when the dimension sizes were 30 - 10 and the Ir value was 1. When combining ReLU with the Adam optimizer, the optimal model configuration had dimension sizes of 60 - 40 - 10, and an Ir value of 0.001, which resulted in the highest accuracy of 97.07%.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 춘계학술대회논문집E
• /
• pp.410-415
• /
• 2001

An analytical and numerical examination of second-order fractional-step methods and boundary condition for the incompressible Navier-Stokes equations is presented. In this study, the compatibility condition for pressure Poisson equation and its boundary conditions, stability, and numerical accuracy of canonical fractional-step methods has been investigated. It has been found that satisfaction of compatibility condition depends on tentative velocity and pressure boundary condition, and that the compatible boundary conditions for type D method and approximately compatible boundary conditions for type P method are proper for divergence-free velocity for type D and approximately divergence-free for type P method. Instability of canonical fractional-step methods is induced by approximation of implicit viscous term with explicit terms, and the stability criteria have been founded with simple model problems and numerical experiments of cavity flow and Taylor vortex flow. The numerical accuracy of canonical fractional-step methods with its consistent boundary conditions shows second-order accuracy except $D_{MM}$ condition, which make approximately first-order accuracy due to weak coupling of boundary conditions.

• 수산해양기술연구
• /
• 제26권2호
• /
• pp.167-172
• /
• 1990

부산-제주간 선로상에서 정박중일 때와 항행중일 때 Loran C 위치를 관측하여 시간대별, 지역별, 침로별 위치의 정도와 편위오차를 수정하여 분석.검토한 결과는 다음과 같다. 1. 주야간별 위치의 정도는 큰 차이가 없었고, 수신점주위에 높은 산이 있을 경우 편위거리의 오차가 더욱 커졌다. 2. 정박중과 항행중에 편위거리의 평균치는 각각 0.188, 0.452마일이었고, 침로의 변화에 따른 측위오차의 변동은 거의 없었다. 3. 위치정도를 높이기 위해서는 속도보정과 측지계변환만으로도 정도가 높은 위치를 구할 수 있었다

• 한국전자파학회논문지
• /
• 제29권8호
• /
• pp.640-647
• /
• 2018

본 논문은 전투기 레이다의 표적 추적정확도(추적오차)를 분석하는 방법에 대한 연구이다. 레이다 측정 시 발생하는 측정오차, 탐지실패, radar cross section(RCS) 요동은 측정 품질을 열화시키며, 이는 추적정확도에 영향을 미치는 요인이 될 수 있다. 따라서 정확한 추적성능분석을 위해 이러한 레이다 측정 특성을 고려하는 것이 필요하다. 본 논문에서는 측정오차, 탐지확률, RCS 요동과 같은 레이다 특성을 복합적으로 활용하여 추적정확도를 분석하는 방법에 대해서 제안한다. 제안한 분석 방법을 활용한 실험을 통해 탐지확률과 RCS 요동에 의한 추적정확도 열화를 확인할 수 있었다.

• 한국항공우주학회지
• /
• 제35권8호
• /
• pp.741-746
• /
• 2007

본 논문에서는 공대지 무장의 무장투하정확도에 대한 해석기법을 제시하였다. 항공기의 전투효과도(Combat Effectiveness)를 평가하는데 있어 중요한 요인인 공격능력(Lethality)은 공대지 무장투하정확도 개선능력에 좌우된다. 항공기 초기 설계단계부터 최종 검증단계 까지 무장투하정확도에 영향을 미치는 요소들을 기술하였으며 각 요소들을 무장투하정확도에 반영하는 기법과 정량적으로 평가하는 방안을 제시하였다. 무장투하정확도 분석은 Bias error를 영으로 가정하고 Random error에 의한 투하오차만을 분석 대상으로 하였다.