• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.3889-3903
• /
• 2017

Fast and accurate localization of randomly deployed nodes is required by many applications in wireless sensor networks (WSNs). However, mobile nodes localization in WSNs is more difficult than static nodes localization since the nodes mobility brings more data. In this paper, we propose a Range-based Monte Carlo Box (RMCB) algorithm, which builds upon the Monte Carlo Localization Boxed (MCB) algorithm to improve the localization accuracy. This algorithm utilizes Received Signal Strength Indication (RSSI) ranging technique to build a sample box and adds a preset error coefficient in sampling and filtering phase to increase the success rate of sampling and accuracy of valid samples. Moreover, simplified Particle Swarm Optimization (sPSO) algorithm is introduced to generate new samples and avoid constantly repeated sampling and filtering process. Simulation results denote that our proposed RMCB algorithm can reduce the location error by 24%, 14% and 14% on average compared to MCB, Range-based Monte Carlo Localization (RMCL) and RSSI Motion Prediction MCB (RMMCB) algorithm respectively and are suitable for high precision required positioning scenes.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.765-774
• /
• 2019

In this paper, we propose a point cloud matching algorithm for multiple RGB-D cameras. In general, computer vision is concerned with the problem of precisely estimating camera position. Existing 3D model generation methods require a large number of cameras or expensive 3D cameras. In addition, the conventional method of obtaining the camera external parameters through the two-dimensional image has a large estimation error. In this paper, we propose a method to obtain coordinate transformation parameters with an error within a valid range by using depth image and function optimization method to generate omni-directional three-dimensional model using 8 low-cost RGB-D cameras.

• Journal of the Korea Society for Simulation
• /
• v.26 no.3
• /
• pp.125-139
• /
• 2017

Recently, interest in improving the quality of EMS(emergency medical services) has been increasing. Much effort is being made to innovate the EMS process. The rapid progress of ICT technology has accelerated the automation or intelligence of EMS processes. This study suggests an emergency room management method based on real-time data considering resource utilization optimization, minimization of human error and enhancement of predictability of medical care. Emergency room operation indices - Emergency care index, Short stay index, Human error inducing index, Waiting patience index - are developed. And emergency room operation rules based on these indices are presented. Simulation was performed on a virtual emergency room to verify the effectiveness of the proposed operating rule. Simulation results showed excellent performance in terms of length of stay.

• ETRI Journal
• /
• v.43 no.4
• /
• pp.603-616
• /
• 2021

Over the last few years, autonomous vehicles have progressed very rapidly. The odometry technique that estimates displacement from consecutive sensor inputs is an essential technique for autonomous driving. In this article, we propose a fast, robust, and accurate odometry technique. The proposed technique is light detection and ranging (LiDAR)-based direct odometry, which uses a spherical range image (SRI) that projects a three-dimensional point cloud onto a two-dimensional spherical image plane. Direct odometry is developed in a vision-based method, and a fast execution speed can be expected. However, applying LiDAR data is difficult because of the sparsity. To solve this problem, we propose an SRI generation method and mathematical analysis, two key point sampling methods using SRI to increase precision and robustness, and a fast optimization method. The proposed technique was tested with the KITTI dataset and real environments. Evaluation results yielded a translation error of 0.69%, a rotation error of 0.0031°/m in the KITTI training dataset, and an execution time of 17 ms. The results demonstrated high precision comparable with state-of-the-art and remarkably higher speed than conventional techniques.

• Nuclear Engineering and Technology
• /
• v.50 no.8
• /
• pp.1306-1313
• /
• 2018

The randomness and incipient nature of certain faults in reactor systems warrant a robust and dynamic detection mechanism. Existing models and methods for fault diagnosis using different mathematical/statistical inferences lack incipient and novel faults detection capability. To this end, we propose a fault diagnosis method that utilizes the flexibility of data-driven Support Vector Machine (SVM) for component-level fault diagnosis. The technique integrates separately-built, separately-trained, specialized SVM modules capable of component-level fault diagnosis into a coherent intelligent system, with each SVM module monitoring sub-units of the reactor coolant system. To evaluate the model, marginal faults selected from the failure mode and effect analysis (FMEA) are simulated in the steam generator and pressure boundary of the Chinese CNP300 PWR (Qinshan I NPP) reactor coolant system, using a best-estimate thermal-hydraulic code, RELAP5/SCDAP Mod4.0. Multiclass SVM model is trained with component level parameters that represent the steady state and selected faults in the components. For optimization purposes, we considered and compared the performances of different multiclass models in MATLAB, using different coding matrices, as well as different kernel functions on the representative data derived from the simulation of Qinshan I NPP. An optimum predictive model - the Error Correcting Output Code (ECOC) with TenaryComplete coding matrix - was obtained from experiments, and utilized to diagnose the incipient faults. Some of the important diagnostic results and heuristic model evaluation methods are presented in this paper.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.1
• /
• pp.41-49
• /
• 2021

In electronic warfare, beamforming using multiple antennas is applied for effective transmission of electronic attack signals. In order to perform an electronic attack against multiple threats using the same frequency resource, it is necessary to apply a multi-beam transmission algorithm that has been studied in wireless communication systems. For electronic attacks against multiple threats, this paper presents an MMSE(Minimum Mean-Squared Error) beam-forming technique based on the prior location information of threats and an optimization method for power allocation. In addition, the performance of the proposed method is evaluated and received signals of multiple threats are compared and analyzed.

• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.3027-3033
• /
• 2022

Background: In this study, various types of deep-learning models for predicting in vitro radiosensitivity from gene-expression profiling were compared. Methods: The clonogenic surviving fractions at 2 Gy from previous publications and microarray gene-expression data from the National Cancer Institute-60 cell lines were used to measure the radiosensitivity. Seven different prediction models including three distinct multi-layered perceptrons (MLP), four different convolutional neural networks (CNN) were compared. Folded cross-validation was applied to train and evaluate model performance. The criteria for correct prediction were absolute error < 0.02 or relative error < 10%. The models were compared in terms of prediction accuracy, training time per epoch, training fluctuations, and required calculation resources. Results: The strength of MLP-based models was their fast initial convergence and short training time per epoch. They represented significantly different prediction accuracy depending on the model configuration. The CNN-based models showed relatively high prediction accuracy, low training fluctuations, and a relatively small increase in the memory requirement as the model deepens. Conclusion: Our findings suggest that a CNN-based model with moderate depth would be appropriate when the prediction accuracy is important, and a shallow MLP-based model can be recommended when either the training resources or time are limited.

• Design & Manufacturing
• /
• v.16 no.3
• /
• pp.22-27
• /
• 2022

The demand for new processing technology that can improve productivity is increasing in industries that require large-scale and various products. In response to this demand, a robot machining system with flexibility is required. Because of the low rigidity of the robot, the robot machining system has a large error during machining and is vulnerable to vibration generated during machining. Vibration generated during machining deteriorates machining quality and reduces the durability of the machine. To solve this problem, a stage for fixing the spindle during machining is required. In order to compensate for the robot's low rigidity, a system combining a piezoelectric actuator for generating a large force and a guide mechanism to actuate with a desired direction is required. Since the rigidity of flexible hinges varies depending on the structure, it is important to optimal design the flexible hinge and high-rigidity system. The purpose of this research is to make analytic model and optimize a flexible hinge and to design a high rigidity stage. In this research, to design a flexible hinge stage, a concept design of system for high rigidity and flexure hinge modeling is carried out. Based on analytic modeling, the optimal design for the purpose of high rigidity is finished and the optimal design results is used to check the error between the modeling and actual simulation results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1200-1215
• /
• 2023

With the development of IoT and artificial intelligence, location-based services are getting more and more attention. For solving the current problem that indoor positioning error is large and generalization is poor, this paper proposes a Model Stacking Algorithm for Indoor Positioning System using WiFi fingerprinting. Firstly, we adopt a model stacking method based on Bayesian optimization to predict the location of indoor targets to improve indoor localization accuracy and model generalization. Secondly, Taking the predicted position based on model stacking as the observation value of particle filter, collaborative particle filter localization based on model stacking algorithm is realized. The experimental results show that the algorithm can control the position error within 2m, which is superior to KNN, GBDT, Xgboost, LightGBM, RF. The location accuracy of the fusion particle filter algorithm is improved by 31%, and the predicted trajectory is close to the real trajectory. The algorithm can also adapt to the application scenarios with fewer wireless access points.

• Korean Journal of Radiology
• /
• v.24 no.7
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.