• Journal of Auto-vehicle Safety Association
• /
• v.14 no.2
• /
• pp.39-44
• /
• 2022

This paper presents LiDAR static obstacle map based vehicle position correction algorithm for urban autonomous driving. Real Time Kinematic (RTK) GPS is commonly used in highway automated vehicle systems. For urban automated vehicle systems, RTK GPS have some trouble in shaded area. Therefore, this paper represents a method to estimate the position of the host vehicle using AVM camera, front camera, LiDAR and low-cost GPS based on Extended Kalman Filter (EKF). Static obstacle map (STOM) is constructed only with static object based on Bayesian rule. To run the algorithm, HD map and Static obstacle reference map (STORM) must be prepared in advance. STORM is constructed by accumulating and voxelizing the static obstacle map (STOM). The algorithm consists of three main process. The first process is to acquire sensor data from low-cost GPS, AVM camera, front camera, and LiDAR. Second, low-cost GPS data is used to define initial point. Third, AVM camera, front camera, LiDAR point cloud matching to HD map and STORM is conducted using Normal Distribution Transformation (NDT) method. Third, position of the host vehicle position is corrected based on the Extended Kalman Filter (EKF).The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment and showed better performance than only lane-detection algorithm. It is expected to be more robust and accurate than raw lidar point cloud matching algorithm in autonomous driving.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.17-25
• /
• 2023

The alarming global prevalence of Type 2 Diabetes Mellitus (T2DM) has catalyzed an urgent need for robust, early diagnostic methodologies. This study unveils a pioneering approach to predicting T2DM, employing the Extreme Gradient Boosting (XGBoost) algorithm, renowned for its predictive accuracy and computational efficiency. The investigation harnesses a meticulously curated dataset of 4303 samples, extracted from a comprehensive Chinese research study, scrupulously aligned with the World Health Organization's indicators and standards. The dataset encapsulates a multifaceted spectrum of clinical, demographic, and lifestyle attributes. Through an intricate process of hyperparameter optimization, the XGBoost model exhibited an unparalleled best score, elucidating a distinctive combination of parameters such as a learning rate of 0.1, max depth of 3, 150 estimators, and specific colsample strategies. The model's validation accuracy of 0.957, coupled with a sensitivity of 0.9898 and specificity of 0.8897, underlines its robustness in classifying T2DM. A detailed analysis of the confusion matrix further substantiated the model's diagnostic prowess, with an F1-score of 0.9308, illustrating its balanced performance in true positive and negative classifications. The precision and recall metrics provided nuanced insights into the model's ability to minimize false predictions, thereby enhancing its clinical applicability. The research findings not only underline the remarkable efficacy of XGBoost in T2DM prediction but also contribute to the burgeoning field of machine learning applications in personalized healthcare. By elucidating a novel paradigm that accentuates the synergistic integration of multifaceted clinical parameters, this study fosters a promising avenue for precise early detection, risk stratification, and patient-centric intervention in diabetes care. The research serves as a beacon, inspiring further exploration and innovation in leveraging advanced analytical techniques for transformative impacts on predictive diagnostics and chronic disease management.

• Journal of Biosystems Engineering
• /
• v.21 no.3
• /
• pp.325-335
• /
• 1996

Visual features are crucial for monitoring the growth state, indexing the drying performance, and grading the quality of oak mushrooms. A computer vision system with neural net information processing technique was utilized to quantize quality factors of a dried oak mushrooms distributed over the cap and gill sides. In this paper, visual feature extraction algorithm were integrated with the neural net processing to deal with various fuzzy patterns of mushroom shapes and to compensate the fault sensitiveness of the crisp criteria and heuristic rules derived from the image processing results. The proposed algorithm improved the segmentation of the skin features of each side, the identification of cap and gill surfaces, the identification of stipe states and removal of the stipe, etc. And the visual characteristics of dried oak mushrooms were analyzed and primary visual features essential to tile quality evaluation were extracted and quantized. In this study, black and white gray images were captured and used for the algorithm development.

• Journal of Advanced Technology Convergence
• /
• v.2 no.2
• /
• pp.9-14
• /
• 2023

This study is shown the result of the first year to develop an export 1050MPa-class lightweight ductile iron castings Austempered control arm through the research process to obtain the following results. First, the structure of the optimal design Layout design and development of the component, and then achieve them through the Control Arm rigidity and optimal structure design and robust design of the focus areas of the expected stress Control Arm. Second, to develop a Control Arm reflects the high rigidity and high performance lightweight structures. Control Arm them developed to meet the design and rigidity as required by the consumer through the hollow, and to develop a process for the Core. Third, through optimum alloy composition and heat treatment methods will be derived to derive the amount of iron alloy (Cu, Ni, Mo) and Austempered heat treated and tempered condition. Fourth, through the development of optimum molding technology development component to develop the optimum ADI for the low-stiffness, high-rigidity component development, it attempts to develop a high-strength casting forming technology..

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.140-140
• /
• 2021

Urban flood management is a crucial and challenging task, particularly in developed cities. Therefore, accurate prediction of urban flooding under heavy precipitation is critically important to address such a challenge. In recent years, machine learning techniques have received considerable attention for their strong learning ability and suitability for modeling complex and nonlinear hydrological processes. Moreover, a survey of the published literature finds that hybrid computational intelligent methods using nature-inspired algorithms have been increasingly employed to predict or simulate the streamflow with high reliability. The present study is aimed to propose a novel approach, an ensemble tree, Bayesian Additive Regression Trees (BART) model incorporating a nature-inspired algorithm to predict hourly multi-step ahead streamflow. For this reason, a hybrid intelligent model was developed, namely GA-BART, containing BART model integrating with Genetic algorithm (GA). The Jungrang urban basin located in Seoul, South Korea, was selected as a case study for the purpose. A database was established based on 39 heavy rainfall events during 2003 and 2020 that collected from the rain gauges and monitoring stations system in the basin. For the goal of this study, the different step ahead models will be developed based in the methods, including 1-hour, 2-hour, 3-hour, 4-hour, 5-hour, and 6-hour step ahead streamflow predictions. In addition, the comparison of the hybrid BART model with a baseline model such as super vector regression models is examined in this study. It is expected that the hybrid BART model has a robust performance and can be an optional choice in streamflow forecasting for urban basins.

• Smart Media Journal
• /
• v.12 no.5
• /
• pp.28-35
• /
• 2023

In this study, we propose a new light-weight model RoutingConvNet with fewer parameters to improve the applicability and practicality of speech emotion recognition. To reduce the number of learnable parameters, the proposed model connects bidirectional MFCCs on a channel-by-channel basis to learn long-term emotion dependence and extract contextual features. A light-weight deep CNN is constructed for low-level feature extraction, and self-attention is used to obtain information about channel and spatial signals in speech signals. In addition, we apply dynamic routing to improve the accuracy and construct a model that is robust to feature variations. The proposed model shows parameter reduction and accuracy improvement in the overall experiments of speech emotion datasets (EMO-DB, RAVDESS, and IEMOCAP), achieving 87.86%, 83.44%, and 66.06% accuracy respectively with about 156,000 parameters. In this study, we proposed a metric to calculate the trade-off between the number of parameters and accuracy for performance evaluation against light-weight.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.151-151
• /
• 2023

An accurate prediction of the hydrodynamic maneuvering darivatives is essential to desing a robust control system of a UUV(unmanned underwater vehicle). Typically, these derivatives were estimated by either the towing tank experiment or semi-empirical methods. With the enhancement of high performance computing capacity, a numerical analysis using computational fluid dynamics has reach the level of experiment. Therefore, the aims of the present research are to numerically develop a computational model for the vertical planar motion mechanism of a UUV and to estimate the hydrodynamics loads in 6-DOF. The target structure of the present study was manta type UUV (12meter length). The numerical model was developed in 1/ 6 model scale. Numerical results were compared with the results of the towing tank experiment for validation. In the present study, a commercial RANS-based viscous solver STARCCM+ (ver 17.06) was used.

• Journal of Microbiology and Biotechnology
• /
• v.33 no.8
• /
• pp.1091-1100
• /
• 2023

Human papillomavirus (HPV) types 16 and 18 are the major causes of cervical lesions and are associated with 71% of cervical cancer cases globally. However, public health infrastructures to support cervical cancer screening may be unavailable to women in low-resource areas. Therefore, sensitive, convenient, and cost-efficient diagnostic methods are required for the detection of HPV16/18. Here, we designed two novel methods, real-time ERA and ERA-LFD, based on enzymatic recombinase amplification (ERA) for quick point-of-care identification of the HPV E6/E7 genes. The entire detection process could be completed within 25 min at a constant low temperature (35-43℃), and the results of the combined methods could be present as the amplification curves or the bands presented on dipsticks and directly interpreted with the naked eye. The ERA assays evaluated using standard plasmids carrying the E6/E7 genes and clinical samples exhibited excellent specificity, as no cross-reaction with other common HPV types was observed. The detection limits of our ERA assays were 10⁰ and 10¹ copies/µl for HPV16 and 18 respectively, which were comparable to those of the real-time PCR assay. Assessment of the clinical performance of the ERA assays using 114 cervical tissue samples demonstrated that they are highly consistent with real-time PCR, the gold standard for HPV detection. This study demonstrated that ERA-based assays possess excellent sensitivity, specificity, and repeatability for HPV16 and HPV18 detection with great potential to become robust diagnostic tools in local hospitals and field studies.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.401-404
• /
• 2003

In this paper, $H_2$, $H_{\infty}$, and mixed $H_2/H_{\infty}$ FIR filters are newly proposed for discrete-time state space signal models. The proposed filters require linearity, unbiased property, FIR structure, and independence of the initial state information in addition to the performance criteria in both $H_2$ and $H_{\infty}$ sense. It is shown that $H_2$, $H_{\infty}$, and mixed $H_2/H_{\infty}$ FIR filter design problems can be converted into convex programming problems via linear matrix inequalities (LMIs) with a linear equality constraint. Simulation studies illustrat that the proposed FIR filter is more robust against uncertainties and has faster convergence than the conventional IIR filters. the conventional IIR filters.

• Journal of Surface Science and Engineering
• /
• v.56 no.6
• /
• pp.420-426
• /
• 2023

We prepared a highly sensitive hydrogen (H₂) sensor based on Indium oxides (In₂O₃) porous nanoparticles (NPs) loaded with Platinum (Pt) nanoparticle in the range of 1.6~5.7 at.%. In₂O₃ NPs were fabricated by microwave irradiation method, and decorations of Pt nanoparticles were performed by electroless plating on In₂O₃ NPs. Crystal structures, morphologies, and chemical information on Pt-loaded In₂O₃ NPs were characterized by grazing-incident X-ray diffraction, field-emission scanning electron microscopy, energy-dispersive X-ray spectroscopy, respectively. The effect of the Pt nanoparticles on the H₂-sensing performance of In₂O₃ NPs was investigated over a low concentration range of 5 ppm of H₂ at 150-300 ℃ working temperatures. The results showed that the H₂ response greatly increased with decreasing sensing temperature. The H₂ response of Pt loaded porous In₂O₃ NPs is higher than that of pristine In₂O₃ NPs. H₂ gas selectivity and high sensitivity was explained by the extension of the electron depletion layer and catalytic effect. Pt loaded porous In₂O₃ NPs sensor can be a robust manner for achieving enhanced gas selectivity and sensitivity for the detection of H₂.