• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.4
• /
• pp.351-361
• /
• 2014

Compared to a terrestrial communication, the high BER(Bit Error Ratio) and low channel bandwidth are the major factor of throughput degradation due to characteristics of underwater channel. Therefore, a MAC protocol must be designed to solve this problem in UWASNs(Underwater Acoustic Sensor Networks). MAC protocols for UWASNs can be classified into two major types according to the contention scheme(Contention-free scheme and Contention-based scheme). In large scale of sensor networks, a Contention-based scheme is commonly used due to time-synchronize problem of Contention-free scheme. In the contention-based scheme, Each node contends with neighbor nodes to access network channel by using Back-off algorithm. But a Slot-Time of Back-off algorithm has long delay times which are cause of decrease network throughput. In this paper, we propose a new scheme to solve this problem. The proposed scheme uses variable Slot-Time instead of fixed Slot-Time. Each node measures propagation delay from neighbors which are used by Slot-time. Therefore, Slot-Times of each node are optimized by considering node deployment. Consequently, the wasted-time for Back-off is reduced and network throughput is improved. A new mac protocol performance in throughput and delay is assessed through NS3 and compared with existing MAC protocol(MACA-U). Finally, it was proved that the MAC protocol using the proposed scheme has better performance than existing MAC protocol as a result of comparison.

• Journal of Korea Water Resources Association
• /
• v.43 no.2
• /
• pp.131-138
• /
• 2010

Due to the increased water demand and severe drought as an effect of the global warming, the effluent from wastewater treatment plants becomes considered as an alternative water source to supply agricultural, industrial, and public (gardening) water demand. The effluent from the wastewater treatment plant is a sustainable water source because of its good quality and stable amount of water discharge. In this study, the water reuse system was developed to minimize total construction cost to cope with the uncertain water demand in future using two-stage stochastic linear programming with binary variables. The pipes in the water reuse network were constructed in two stages of which in the first stage, the water demands of users are assumed to be known, while the water demands in the second stage have uncertainty in the predicted value. However, the water reuse system has to be designed now when the future water demands are not known precisely. Therefore, the construction of a pipe parallel with the existing one was allowed to meet the increased water demands in the second stage. As a result, the trade-off of construction costs between a pipe with large diameter and two pipes having small diameters was evaluated and the optimal solution was found. Three scenarios for the future water demand were selected and a hypothetical water reuse network considering the uncertainties was optimized. The results provide the information about the economies of scale in the water reuse network and the long range water supply plan.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.25 no.1
• /
• pp.51-56
• /
• 2012

Crashworthy fuel cells have been widely implemented to rotorcraft and rendered a great contribution for improving the survivability of crews and passengers. Since the embryonic stage of military rotorcraft history began, the US army has developed and practised a detailed military specification documenting the unique crashworthiness requirements for rotorcraft fuel cells to prevent most fatality due to post-crash fire. Foreign manufacturers have followed their long term experience to develop their fuel cells, and have reflected the results of crash impact tests on the trial-and-error based design and manufacturing procedures. Since the crash impact test itself takes a long-term preparation efforts together with costly fuel cell specimens, a series of numerical simulations of the crash impact test with digital mock-ups is necessary even at the early design stage to minimize the possibility of trial-and-error with full-scale fuel cells. In the present study a number of numerical simulations on fuel cell crash impact tests are performed with a crash simulation software, Autodyn. The resulting equivalent stresses are further analysed to evaluate a number of appropriate design parameters and the artificial neural network and simulated annealing method are simultaneously implemented to optimize the crashworthy performance of fuel cells.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.3
• /
• pp.31-37
• /
• 2020

Identification of the mandibular canal path in Computed Tomography (CT) scans is important in dental implantology. Typically, prior to the implant planning, dentists find a sagittal plane where the mandibular canal path is maximally observed, to manually identify the mandibular canal. However, this is time-consuming and requires extensive experience. In this paper, we propose a deep-learning-based framework to detect the desired sagittal plane automatically. This is accomplished by utilizing two main techniques: 1) a modified version of the iterative transformation network (ITN) method for obtaining initial planes, and 2) a fine searching method based on a convolutional neural network (CNN) classifier for detecting the desirable sagittal plane. This combination of techniques facilitates accurate plane detection, which is a limitation of the stand-alone ITN method. We have tested on a number of CT datasets to demonstrate that the proposed method can achieve more satisfactory results compared to the ITN method. This allows dentists to identify the mandibular canal path efficiently, providing a foundation for future research into more efficient, automatic mandibular canal detection methods.

• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.4
• /
• pp.153-161
• /
• 2018

This paper describes the performance improvement of Software (SW) digital filter using GPU (Graphical Processing Unit). The previous developed SW digital filter has a problem that it operates on a CPU (Central Processing Unit) basis and has a slow speed. The GPU was introduced to filter the data of the EAVN (East Asian VLBI Network) observation to improve the operation speed and to process data with other stations through filtering, respectively. In order to enhance the computational speed of the SW digital filter, NVIDIA Titan V GPU board with built-in Tensor Core is used. The processing speed of about 0.78 (1Gbps, 16MHz BW, 16-IF) and 1.1 (2Gbps, 32MHz BW, 16-IF) times for the observing time was achieved by filtering the 95 second observation data of 2 Gbps (512 MHz BW, 1-IF), respectively. In addition, 2Gbps data is digitally filtered for the 1 and 2Gbps simultaneously observed with KVN (Korean VLBI Network), and compared with the 1Gbps, we obtained similar values such as cross power spectrum, phase, and SNR (Signal to Noise Ratio). As a result, the effectiveness of developed SW digital filter using GPU in this research was confirmed for utilizing the data processing and analysis. In the future, it is expected that the observation data will be able to be filtered in real time when the distributed processing optimization of source code for using multiple GPU boards.

• Journal of Industrial Convergence
• /
• v.16 no.1
• /
• pp.21-26
• /
• 2018

The Seaborne Trade Volume accounts for 97% of the total. This means that the port operation management system can improve port efficiency, reducing operating costs, and the manager who manages all operations at the port needs to check and respond quickly when delays of work and equipment support is needed. Based on the real-time location information confirmation of yard automation equipment used the existing system GPS, the real-time location information confirmation system is a GPS system of the tablet, rather than a port operation system that monitors location information for the entered information, depending on the completion of the task or the start of the task. Network configurations also reduce container processing delays by using commercial LTE services that do not have shading due to containers in the yard also reduce container processing delays. Trough introduction of smart devices using Android or IOS and container processing scheduling utilizing artificial intelligence, we will build a minimum delay system with Smart Device usage of container processing applications and optimization of container processing schedule. The adoption of smart devices and the minimization of container processing delays utilizing artificial intelligence are expected to improve the quality of port services by confirming the processing containers in real time to consumers who are container information demanders.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.449-456
• /
• 2022

This study proposes a deep learning algorithm to predict crop yield using GIS (Geographic Information System) to extract soil properties from Soilgrids and soil suitability class maps. The proposed model modified the structure of a published CNN-RNN (Convolutional Neural Network-Recurrent Neural Network) based crop yield prediction model suitable for the domestic crop environment. The existing model has two characteristics. The first is that it replaces the original yield with the average yield of the year, and the second is that it trains the data of the predicted year. The new model uses the original field value to ensure accuracy, and the network structure has been improved so that it can train only with data prior to the year to be predicted. The proposed model predicted the yield per unit area of autumn cabbage for kimchi by region based on weather, soil, soil suitability classes, and yield data from 1980 to 2020. As a result of computing and predicting data for each of the four years from 2018 to 2021, the error amount for the test data set was about 10%, enabling accurate yield prediction, especially in regions with a large proportion of total yield. In addition, both the proposed model and the existing model show that the error gradually decreases as the number of years of training data increases, resulting in improved general-purpose performance as the number of training data increases.

• Journal of the Korean Society of Radiology
• /
• v.17 no.2
• /
• pp.191-199
• /
• 2023

This study aimed to propose minimized radiation doses with an optimized abdomen x-ray image, which realizes a Deep Blind Image Super-Resolution Generative adversarial network (BSRGAN) technique. Entrance surface doses (ESD) measured were collected by changing exposure conditions. In the identical exposures, abdominal images were acquired and were processed with the BSRGAN. The images reconstructed by the BSRGAN were compared to a reference image with 80 kVp and 320 mA, which was evaluated by mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). In addition, signal profile analysis was employed to validate the effect of the images reconstructed by the BSRGAN. The exposure conditions with the lowest MSE (about 0.285) were shown in 90 kVp, 125 mA and 100 kVp, 100 mA, which decreased the ESD in about 52 to 53% reduction), exhibiting PSNR = 37.694 and SSIM = 0.999. The signal intensity variations in the optimized conditions rather decreased than that of the reference image. This means that the optimized exposure conditions would obtain reasonable image quality with a substantial decrease of the radiation dose, indicating it could sufficiently reflect the concept of As Low As Reasonably Achievable (ALARA) as the principle of radiation protection.

• Korean Chemical Engineering Research
• /
• v.61 no.3
• /
• pp.388-393
• /
• 2023

The analysis of engineering data using neural network based on supervised learning has been utilized in various engineering fields such as optimization of chemical engineering process, concentration prediction of particulate matter pollution, prediction of thermodynamic phase equilibria, and prediction of physical properties for transport phenomena system. The supervised learning requires training data, and the performance of the supervised learning is affected by the composition and the configurations of the given training data. Among the frequently observed engineering data, the data is given in log-scale such as length of DNA, concentration of analytes, etc. In this study, for widely distributed log-scaled training data of virtual 100×100 images, available loss functions were quantitatively evaluated in terms of (i) confusion matrix, (ii) maximum relative error and (iii) mean relative error. As a result, the loss functions of mean-absolute-percentage-error and mean-squared-logarithmic-error were the optimal functions for the log-scaled training data. Furthermore, we figured out that uniformly selected training data lead to the best prediction performance. The optimal loss functions and method for how to compose training data studied in this work would be applied to engineering problems such as evaluating DNA length, analyzing biomolecules, predicting concentration of colloidal suspension.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.399-401
• /
• 2022

A definitive diagnosis to classify the breast malignancy status may be achieved by microscopic analysis using surgical open biopsy. However, this procedure requires experts in the specializing of histopathological image analysis directing to time-consuming and high cost. To overcome these issues, deep learning is considered practically efficient to categorize breast cancer into benign and malignant from histopathological images in order to assist pathologists. This study presents a pre-trained convolutional neural network model architecture with a 100% fine-tuning scheme and Adagrad optimizer to classify the breast cancer histopathological images into benign and malignant using a 40× magnification BreaKHis dataset. The pre-trained architecture was constructed using the InceptionResNetV2 model to generate a modified InceptionResNetV2 by substituting the last layer with dense and dropout layers. The results by demonstrating training loss of 0.25%, training accuracy of 99.96%, validation loss of 3.10%, validation accuracy of 99.41%, test loss of 8.46%, and test accuracy of 98.75% indicated that the modified InceptionResNetV2 model is reliable to predict the breast malignancy type from histopathological images. Future works are necessary to focus on k-fold cross-validation, optimizer, model, hyperparameter optimization, and classification on 100×, 200×, and 400× magnification.