• Journal of information and communication convergence engineering
• /
• v.19 no.2
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.1
• /
• pp.1-9
• /
• 2023

The problem of classifying a non-line-of-sight (NLOS) signal in a multipath channel is important to improve global navigation satellite system (GNSS) positioning accuracy in urban areas. Conventional deep learning-based NLOS signal classifiers use GNSS satellite measurements such as the carrier-to-noise-density ratio (CN_0), pseudorange, and elevation angle as inputs. However, there is a computational inefficiency with use of these measurements and the NLOS signal features expressed by the measurements are limited. In this paper, we propose a Convolutional Neural Network (CNN)-based NLOS signal classifier that receives successive Auto-correlation function (ACF) outputs according to a time-series, which is the most primitive output of GNSS signal processing. We compared the proposed classifier to other DL-based NLOS signal classifiers such as a multi-layer perceptron (MLP) and Gated Recurrent Unit (GRU) to show the superiority of the proposed classifier. The results show the proposed classifier does not require the navigation data extraction stage to classify the NLOS signals, and it has been verified that it has the best detection performance among all compared classifiers, with an accuracy of up to 97%.

• Wind and Structures
• /
• v.35 no.5
• /
• pp.297-307
• /
• 2022

Over the past few decades, the use of wind tunnels has been increasing as a result of the rapid growth of cities and the urge to build taller and non-typical structures. While the accuracy of a wind tunnel study on a tall building requires several aspects, the precise extraction of wind pressure plays a significant role in a successful pressure test. In this research study, a low-cost expandable synchronous multi-pressure sensing system (SMPSS) was developed and validated at Ryerson University's wind tunnel (RU-WT) using electronically scanning pressure sensors for wind tunnel tests. The pressure system consists of an expandable 128 pressure sensors connected to a compact data acquisition and a host workstation. The developed system was examined and validated to be used for tall buildings by comparing mean, root mean square (RMS), and power spectral density (PSD) for the base moments coefficients with the available data from the literature. In addition, the system was examined for evaluating the mean and RMS pressure distribution on a standard low-rise building and were found to be in good agreement with the validation data.

• Mass Spectrometry Letters
• /
• v.13 no.4
• /
• pp.158-165
• /
• 2022

Many therapeutic class drugs such as beta-blocker, corticosteroids, NSAIDs, etc are prohibited substances in the horse racing industry. Liquid chromatography-tandem mass spectrometry (LC-MS/MS) technology makes it possible to isolate drugs from interference, enables various drug analyses in complex biological samples due to its sensitive sensitivity, and has been successfully applied to doping control. In this paper, we describe a rapid and sensitive method based on solid-phase extraction (SPE) using solid phase cartridge and LC-MS/MS to screen for different class's 35 drug targets in equine plasma. Plasma samples were pretreated by SPE with the NEXUS cartridge consisted non-polar carbon resin and minimum buffer solvent. Chromatographic separation of the analytes was performed on ACQUITY HSS C18 column (2.1 × 150 mm, 1.8 ㎛). The elution gradient was conducted with 5 mM ammonium formate (pH 3.0) in distilled water and 0.1% formic acid in acetonitrile at a flow rate of 0.25 mL/min. The selected reaction monitoring (SRM) mode was used for drug screening with multiple transitions in the positive ionization mode. The specificity, limit of detection, recovery, and stability was evaluated for validation. The method was found to be sensitive and reproducible for drug screening. The method was applied to plasma sample analysis for the proficiency test from the Association of Racing Chemist.

• Journal of Microbiology and Biotechnology
• /
• v.32 no.11
• /
• pp.1357-1372
• /
• 2022

Heavy reliance on fossil fuels has been associated with increased climate disasters. As an alternative, microalgae have been proposed as an effective agent for biomass production. Several advantages of microalgae include faster growth, usage of non-arable land, recovery of nutrients from wastewater, efficient CO₂ capture, and high amount of biomolecules that are valuable for humans. Microalgae Chlorella spp. are a large group of eukaryotic, photosynthetic, unicellular microorganisms with high adaptability to environmental variations. Over the past decades, Chlorella has been used for the large-scale production of biomass. In addition, Chlorella has been actively used in various food industries for improving human health because of its antioxidant, antidiabetic, and immunomodulatory functions. However, the major restrictions in microalgal biofuel technology are the cost-consuming cultivation, processing, and lipid extraction processes. Therefore, various trials have been performed to enhance the biomass productivity and the lipid contents of Chlorella cells. This study provides a comprehensive review of lipid enhancement strategies mainly published in the last five years and aimed at regulating carbon sources, nutrients, stresses, and expression of exogenous genes to improve biomass production and lipid synthesis.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1059-1066
• /
• 2022

In 2020, it was estimated that more than 2.4 million households in South Korea are over 30 years old. That is, more than 40% of all houses in Korea are old and that they require proper rehabilitation. The two options to improve poor living conditions are reconstruction and remodeling. Compared to reconstruction, remodeling has advantages in terms of the construction period, cost, and environmental impact. As such, the current Korean regulations are more favorable for remodeling than reconstruction. Typically, several candidate floor plans are presented in the early stages of an apartment remodeling project. Extracting information about bearing walls and other structural elements from the multiple plans to compare those plans quantitatively is one of the essential tasks during the early stage of a project. To cope with this task, an automated data extraction method for walls and slabs from before and after remodeling plans is developed. Through the developed program, load-bearing walls, non-bearing walls, slabs, and weight changes after remodeling can be analyzed and visualized in a fast and automated manner.

• Journal of the Korean institute of surface engineering
• /
• v.34 no.6
• /
• pp.553-567
• /
• 2001

Electrodeposition technology is widely used in industry for various kinds of coatings. Modifications in this technology led to several processes to meet various requirements. Electrolysis in ionic liquids has many advantages such as low energy consumption of energy, low pollutant emission and low operating costs. Although ionic liquids have already been used in liquid/liquid extraction processes, only recently their use in electrodeposition was exploited. Electrochemical deposition of composites is an expanding area. Coupled with the progress in the synthesis of nanometric powder, this research will open a large number of innovative materials. Pulse current plating is another electrodeposition technique which yields improved coatings. Although electrodeposition is now regarded as an environmental non-friendly process, it is economically viable and has many inherent advantages. For certain applications, alternatives to electrodeposition have not yet been fully implemented. Hence, continued research in this technology is warranted. This article reviews some recent advances in electrodeposition technology. Aspects of electrodeposition such as electrolysis in ionic liquids, electrodeposition of composites, pulse current plating techniques, metal and alloy deposition, compound deposition and effects of additives are discussed in this review.

• Nuclear Engineering and Technology
• /
• v.55 no.3
• /
• pp.827-838
• /
• 2023

Centrifugal pump is a key part of nuclear power plant systems, and its health status is critical to the safety and reliability of nuclear power plants. Therefore, fault diagnosis is required for centrifugal pump. Traditional fault diagnosis methods have difficulty extracting fault features from nonlinear and non-stationary signals, resulting in low diagnostic accuracy. In this paper, a new fault diagnosis method is proposed based on the improved particle swarm optimization (IPSO) algorithm-based variational modal decomposition (VMD) and relevance vector machine (RVM). Firstly, a simulation test bench for rotor faults is built, in which vibration displacement signals of the rotor are also collected by eddy current sensors. Then, the improved particle swarm algorithm is used to optimize the VMD to achieve adaptive decomposition of vibration displacement signals. Meanwhile, a screening criterion based on the minimum Kullback-Leibler (K-L) divergence value is established to extract the primary intrinsic modal function (IMF) component. Eventually, the factors are obtained from the primary IMF component to form a fault feature vector, and fault patterns are recognized using the RVM model. The results show that the extraction of the fault information and fault diagnosis classification have been improved, and the average accuracy could reach 97.87%.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.71.1-71.1
• /
• 2021

We perform disk-halo decomposition of the Large Magellanic Cloud (LMC) using a novel HI velocity field extraction method, aimed at better deriving its HI kinematics and thus mass distribution in the galaxy including both baryons and dark matter. We decompose all the line-of-sight velocity profiles of the combined HI data cube of the LMC, taken from the Australia Telescope Compact Array (ATCA) and Parkes radio telescopes with an optimal number of Gaussian components. For this, we use a novel tool, the so-called BAYGAUD which performs profile decomposition based on Bayesian MCMC techniques. From this, we disentangle turbulent non-ordered HI gas motions from the decomposed gas components, and produce an HI bulk velocity field which better follows the global circular rotation of the galaxy. From a 2D tilted-ring analysis of the HI bulk velocity field, we derive the rotation curve of the LMC after correcting for its transverse, nutation and precession motions. The dynamical contributions of baryons like stars and gaseous components which are derived using the Spitzer 3.6 micron image and the HI data are then subtracted from the total kinematics of the LMC. Here, we present the bulk HI rotation curve, the mass models of stars and gaseous components, and the resulting dark matter density profile of the LMC.