• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.540-543
• /
• 2021

In this paper, we present an experimental comparative study of recurrent neural network based techniques for trajectory prediction of flight vehicles. We defined and investigated various relationships between input and output under the same experimental setup. In particular, we proposed a relationship based on the relative positions of flight vehicles. Furthermore, we conducted an ablation study on the network architectures and hyperparameters. We believe that this comprehensive comparative study serves as a reference point and guide for developers in choosing an appropriate recurrent neural network based techniques for building (flight) vehicle trajectory prediction systems.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.825-832
• /
• 2022

In this paper, we discuss the design and implementation of predictive and diagnostic models for realizing intelligent predictive models by collecting and storing the power output of agricultural photovoltaic power generation systems. Our model predicts the amount of photovoltaic power generation using RNN, LSTM, and GRU models, which are recurrent neural network techniques specialized for time series data, and compares and analyzes each model with different hyperparameters, and evaluates the performance. As a result, the MSE and RMSE indicators of all three models were very close to 0, and the R2 indicator showed performance close to 1. Through this, it can be seen that the proposed prediction model is a suitable model for predicting the amount of photovoltaic power generation, and using this prediction, it was shown that it can be utilized as an intelligent and efficient O&M function in an agricultural photovoltaic system.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.49-56
• /
• 2023

This study proposed a damage location estimation method for automated image-based port infrastructure inspection. Memory efficiency was improved by calculating the homography matrix using feature detection technology and outlier removal technology, without going through the 3D modeling process and storing only damage information. To develop an algorithm specialized for port infrastructure, the algorithm was optimized through ground-truth coordinate pairs created using images of port infrastructure. The location errors obtained by applying this to the sample and concrete wall were (X: 6.5cm, Y: 1.3cm) and (X: 12.7cm, Y: 6.4cm), respectively. In addition, by applying the algorithm to the concrete wall and displaying it in the form of an exterior damage map, the possibility of field application was demonstrated.

• Journal of Advanced Navigation Technology
• /
• v.26 no.2
• /
• pp.113-118
• /
• 2022

Motivated by people highlighting important phrases while reading or taking notes we propose a neural network training method by highlighting defective pixel areas to classify effectively defect types of images with complex background textures. To verify our proposed method we apply it to the problem of classifying the defect types of tire band fabric images that are too difficult to classify. In addition we propose a backlight highlighting technique which is tailored to the tire band fabric images. Backlight highlighting images can be generated by using both the GradCAM and simple image processing. In our experiment we demonstrated that the proposed highlighting method outperforms the traditional method in the view points of both classification accuracy and training speed. It achieved up to 13.4% accuracy improvement compared to the conventional method. We also showed that the backlight highlighting technique tailored for highlighting tire band fabric images is superior to a contour highlighting technique in terms of accuracy.

• Journal of The Korean Institute of Defense Technology
• /
• v.5 no.2
• /
• pp.10-16
• /
• 2023

This study establishes the operation concept of the 4th industrial revolution defense technology and communication facility-based 5G MUM-T system, and diagnoses our current situation, focusing on the case of US government technology policy, which is a leading country in 5G MUM-T system and operation. And to advance the operation of the 5G MUM-T system, reflect combat robots and drones in the detailed classification of weapon systems, early introduction of low-orbit 5G satellite communication, expansion of the use of 5G specialized networks and wholesale provision for demonstration and verification, establishment of a defense AI governance system, Suggests the necessity of a 3-class method for radiological weapon systems. For future research, it is important to respond to the technological evolution of 6G MUM-T and 6G NTN and compare and analyze each country's policy cases, such as China, Germany, the United Kingdom, and Japan.

• Journal of the Korean association of regional geographers
• /
• v.14 no.6
• /
• pp.664-679
• /
• 2008

This paper attempts to evaluate the local economy and the local economic development policy in Goryeong County and to propose some policy alternatives for local economic development. Goryeong County has a locational advantage, which is not just geographically proximate to Daegu, a large metropolis, but also connected directly to the national highway networks. This region can also be regarded as a rural area, in a sense that the primary industry still plays a more important role for the local economy than the secondary industry and the tertiary industry. However, it is problematic that the local economic development strategies of Goryeong are universal rather than strategic and systematic. In order to design an effective regional economic development policy, the policy makers are necessary to deliberately consider regional specificity and geo-political and geo-economic situations around the region. In addition, it is important to say that policy makers, particularly in rural regions, need to break from the fantasy of high-tech industries. In this context, I propose some region-specific and context-specific policy ideas, including the promotion of the agro-food cluster and the build-up of the em-industrial complexes specialized in mechatronics and transportation equipment manufacturing.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.560-568
• /
• 2020

In recent years, as network technology develops, the usage of streaming services by users is increasing. However, the complexity of streaming services is also increasing due to various terminal environments. Even when streaming the same content, it is necessary to re-encode the content according to the type of service. In order to solve the complexity and latency of the streaming service, Moving Picture Experts Group (MPEG) has standardized the Common Media Application Format (CMAF). In addition, as content transmission using a communication network becomes possible, the Republic of Korea's Ultra High Definition (UHD) broadcasting standard has been enacted as a hybrid standard using a broadcasting network and a communication network. The hybrid service enables various services such as transmitting additional information of contents or providing user-customized contents through a communication network. The Republic of Korea's UHD transmission standard utilizes MPEG Media Transport (MMT), and Mobile MMT is an extension of MMT to provide mobile network-specific functions. This paper proposes a method of inserting CMAF contents suitable for various streaming services using signaling messages of MMT and Mobile MMT. In addition, this paper proposes a model for content insertion system in heterogeneous network environment using broadcasting and communication networks, and verifies the validity of the proposed technology by checking the result of content insertion.

• Geophysics and Geophysical Exploration
• /
• v.26 no.3
• /
• pp.126-137
• /
• 2023

In this study, a recurrent neural network (RNN) was employed as a methodological approach to classify dolphin click signals derived from ocean monitoring data. To improve the accuracy of click signal classification, the single time series data were transformed into fractional domains using fractional Fourier transform to expand its features. Transformed data were used as input for three RNN models: long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM), which were compared to determine the optimal network for the classification of signals. Because the fractional Fourier transform displayed different characteristics depending on the chosen angle parameter, the optimal angle range for each RNN was first determined. To evaluate network performance, metrics such as accuracy, precision, recall, and F1-score were employed. Numerical experiments demonstrated that all three networks performed well, however, the BiLSTM network outperformed LSTM and GRU in terms of learning results. Furthermore, the BiLSTM network provided lower misclassification than the other networks and was deemed the most practically appliable to field data.

• Journal of Korea Water Resources Association
• /
• v.56 no.8
• /
• pp.471-484
• /
• 2023

Deep learning models based on generative adversarial neural networks are specialized in generating new information based on learned information. The deep generative models (DGMR) model developed by Google DeepMind is an generative adversarial neural network model that generates predictive radar images by learning complex patterns and relationships in large-scale radar image data. In this study, the DGMR model was trained using radar rainfall observation data from the Ministry of Environment, and rainfall prediction was performed using an generative adversarial neural network for a heavy rainfall case in August 2021, and the accuracy was compared with existing prediction techniques. The DGMR generally resembled the observed rainfall in terms of rainfall distribution in the first 60 minutes, but tended to predict a continuous development of rainfall in cases where strong rainfall occurred over the entire area. Statistical evaluation also showed that the DGMR method is an effective rainfall prediction method compared to other methods, with a critical success index of 0.57 to 0.79 and a mean absolute error of 0.57 to 1.36 mm in 1 hour advance prediction. However, the lack of diversity in the generated results sometimes reduces the prediction accuracy, so it is necessary to improve the diversity and to supplement it with rainfall data predicted by a physics-based numerical forecast model to improve the accuracy of the forecast for more than 2 hours in advance.

• Journal of Satellite, Information and Communications
• /
• v.9 no.3
• /
• pp.121-126
• /
• 2014

ETRI(Electronics and Telecommunication Research Institute) has joined National GNSS Research Center program of Defense Acquisition Program Administration and Agency for Defense Development in 2010. The research subject is technology for MSAR(Military Search and Rescue) system configuration. In this project, we analyses the ways in order to improve the accuracy, reliability, availability for MSAR system from M&S(Modeling and Simulation). The MSAR System M&S Software can be used for performance analysis of new elements, such as ground elements and satellite elements without any hardware development. In this paper, after introduction of the architecture design and functional scope of the simulator, the performance analysis result for MSAR M&S software is presented.