• 전자공학회논문지B
• /
• 제31B권1호
• /
• pp.49-56
• /
• 1994

This paper describes the design principles and methods of electronic processor for thermal imager with the SPRITE detector, operating in the 8-12 micron band. The thermal imager consists of a optical scanner containing the detector and an electrical signal processor. The optical scanner utilizing rotating polygon and oscillating mirror, is 2-dimensional serial/parallel scan type using 5 elements of the detector. And the electronic processor has pre-processing of 5 chnanel's thermal signal from the detector, and performs digital scan conversion to reform the parallel data stream into serial analog data compatible with conventional RS-170 video. Through the designed electronic processor, we have acquired a satisfactory thermal image. And the MRTD (Minimum Resolvable Temperature Difference) is 0.5$^{\circ}$K at 7.5 cycles/mm.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1011-1011
• /
• 2001

In general, NIR reflectance spectra (whether recorded using log(1/R) or the Kubelka-Munk function) are not linear functions of the concentration of the absorbers which we are measuring. There are several causes for this non-linearity, the most commonly cited one being front surface reflection. However, non-linearity also arises from the effects of particle size, sample thickness, void fraction, and experimental arrangement. In this talk, we will attempt to isolate the effects of the various causes, and show the effects of each, using both theoretical calculations and actual data. The listener should then be able to assess where we stand in our quest to produce “linear” data through pre-processing and/or alternate collection schemes.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 추계학술대회 논문집 학회본부 B
• /
• pp.797-799
• /
• 1999

In this paper, we design the Multi-FNN(Fuzzy-Neural Networks) using HCM Method. The proposed Multi-FNN uses simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rules. Also, We use HCM(Hard C-Means) method of clustering technique for improvement of output performance from pre-processing of input data. The parameters such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. We use the training and testing data set to obtain a balance between the approximation and the generalization of our model. Several numerical examples are used to evaluate the performance of the our model. From the results, we can obtain higher accuracy and feasibility than any other works presented previously.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.132-135
• /
• 2004

Building information plays a key role in diverse applications such as urban planning, telecommunication and environment monitoring. Automatic building extraction has been a prime interest in the field of GIS and photogrammetry. In this paper, we presented an automatic approach for building extraction from lidar data. The proposed approach is divided into four processes: pre-processing, filtering, segmentation and building extraction. Experimental results showed that the proposed method detected most of buildings with less commission and omission errors.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.163-168
• /
• 2008

KOMPSAT-3 is expected to provide data with 80-cm spatial resolution, which can be used to detect environmental change and create thematic maps such as land-use and land-cover maps. However, to analyze environmental change, change-detection technologies that use multi-resolution and high-resolution satellite images simultaneously must be developed and linked to each other. This paper describes a GIS-based strategy and methodology for revealing global and local environmental change. In the pre-processing step, we performed geometric correction using satellite, auxiliary, and training data and created a new classification system. We also describe the available technology for connecting global and local change-detection analysis.

• 한국CDE학회논문집
• /
• 제14권4호
• /
• pp.271-280
• /
• 2009

An experience based training system concerning various fire situations which may result many casualties has been required to make rapid decision and improve the responsiveness. Recently, the necessity of virtual reality (VR) based training system which can replace a dangerous full-scale fire training and be easily adopted to the training or evaluation process is increasing. This study constructed tile virtual environment according to pre-defined scenarios, utilized the FDS(Fire Dynamics Simulator), three dimensional computational fire analysis program, to derive numerically simulated data on the propagation of fire. Finally, by visualizing the realistic fire and smoke behavior through virtual reality technique and implementing real-time interaction, we developed a VR-based fire training simulator. Also, in order to ensure the sense for tile real of a virtual world and reaI-time performance at the same time, we proposed appropriate data processing and space search algorithms, demonstrate d the value of proposed method through experiments.

• Journal of Electrical Engineering and Technology
• /
• 제13권1호
• /
• pp.485-492
• /
• 2018

In this paper, we propose facial expression recognition using CNN (Convolutional Neural Network), one of the deep learning technologies. The proposed structure has general classification performance for any environment or subject. For this purpose, we collect a variety of databases and organize the database into six expression classes such as 'expressionless', 'happy', 'sad', 'angry', 'surprised' and 'disgusted'. Pre-processing and data augmentation techniques are applied to improve training efficiency and classification performance. In the existing CNN structure, the optimal structure that best expresses the features of six facial expressions is found by adjusting the number of feature maps of the convolutional layer and the number of nodes of fully-connected layer. The experimental results show good classification performance compared to the state-of-the-arts in experiments of the cross validation and the cross database. Also, compared to other conventional models, it is confirmed that the proposed structure is superior in classification performance with less execution time.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 봄 학술논문 발표대회
• /
• pp.229-230
• /
• 2022

With the development of digital technology, construction companies at home and abroad are in the process of computerizing work and site information for the purpose of improving work efficiency. To this end, various technologies such as BIM, digital twin, and AI-based safety management have been developed, but the accuracy and completeness of the related technologies are insufficient to be applied to the field. In this paper, the learning data that has undergone a pre-processing process optimized for recognition of construction information based on structural members is trained on an existing artificial intelligence model to improve recognition accuracy and evaluate its effectiveness. The artificial intelligence model optimized for the structural member created through this study will be used as a base technology for the technology that needs to confirm the safety of the structure in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.420-437
• /
• 2024

There are some problems in network traffic classification (NTC), such as complicated statistical features and insufficient training samples, which may cause poor classification effect. A NTC architecture based on one-dimensional Convolutional Neural Network (CNN) and transfer learning is proposed to tackle these problems and improve the fine-grained classification performance. The key points of the proposed architecture include: (1) Model classification--by extracting normalized rate feature set from original data, plus existing statistical features to optimize the CNN NTC model. (2) To apply transfer learning in the classification to improve NTC performance. We collect two typical network flows data from Youku and YouTube, and verify the proposed method through extensive experiments. The results show that compared with existing methods, our method could improve the classification accuracy by around 3-5%for Youku, and by about 7 to 27% for YouTube.

• 대한원격탐사학회지
• /
• 제40권3호
• /
• pp.257-268
• /
• 2024

Drone-mounted hyperspectral sensors (DHSs) have revolutionized remote sensing in agriculture by offering a cost-effective and flexible platform for high-resolution spectral data acquisition. Their ability to capture data at low altitudes minimizes atmospheric interference, enhancing their utility in agricultural monitoring and management. This study focused on addressing the challenges of radiometric and geometric distortions in preprocessing drone-acquired hyperspectral data. Radiometric correction, using the empirical line method (ELM) and spectral reference panels, effectively removed sensor noise and variations in solar irradiance, resulting in accurate surface reflectance values. Notably, the ELM correction improved reflectance for measured reference panels by 5-55%, resulting in a more uniform spectral profile across wavelengths, further validated by high correlations (0.97-0.99), despite minor deviations observed at specific wavelengths for some reflectors. Geometric correction, utilizing a rubber sheet transformation with ground control points, successfully rectified distortions caused by sensor orientation and flight path variations, ensuring accurate spatial representation within the image. The effectiveness of geometric correction was assessed using root mean square error(RMSE) analysis, revealing minimal errors in both east-west(0.00 to 0.081 m) and north-south directions(0.00 to 0.076 m).The overall position RMSE of 0.031 meters across 100 points demonstrates high geometric accuracy, exceeding industry standards. Additionally, image mosaicking was performed to create a comprehensive representation of the study area. These results demonstrate the effectiveness of the applied preprocessing techniques and highlight the potential of DHSs for precise crop health monitoring and management in smart agriculture. However, further research is needed to address challenges related to data dimensionality, sensor calibration, and reference data availability, as well as exploring alternative correction methods and evaluating their performance in diverse environmental conditions to enhance the robustness and applicability of hyperspectral data processing in agriculture.