• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.326-334
• /
• 2022

In this paper, we propose speech enhancement algorithm as a pre-processing for robust speech recognition in noisy environments. Auxiliary-function-based Independent Vector Analysis (AuxIVA) is performed with weighted covariance matrix using time-varying variances with scaling factor from target masks representing time-frequency contributions of target speech. The mask estimates can be obtained using Neural Network (NN) pre-trained for speech extraction or diffuseness using Coherence-to-Diffuse power Ratio (CDR) to find the direct sounds component of a target speech. In addition, outputs for omni-directional noise are closely chained by sharing the time-varying variances similarly to independent subspace analysis or IVA. The speech extraction method based on AuxIVA is also performed in Independent Low-Rank Matrix Analysis (ILRMA) framework by extending the Non-negative Matrix Factorization (NMF) for noise outputs to Non-negative Tensor Factorization (NTF) to maintain the inter-channel dependency in noise output channels. Experimental results on the CHiME-4 datasets demonstrate the effectiveness of the presented algorithms.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.28 no.4
• /
• pp.41-50
• /
• 2022

Purpose: This study aims to suggest an analysis model finding the relationship between building scale characteristics of Public-use facilities and infectious disease outbreaks around senior leisure welfare facilities and the features and their scopes where quarantine resources are to be concentrated. Methods: Reviewing previous studies found the user characteristics of senior leisure welfare facilities and scale characteristics of urban architectures. The data preprocessing was performed after collecting building data and infectious disease outbreak data in the analysis area. This study derived data for attributes of building size and frequency of infectious disease outbreaks in Public-use facilities around senior leisure welfare facilities. A computing algorithm was implemented to analyze the correlation between the building size characteristics and the infectious disease outbreak frequency as per the change of the spatial scope. Results: The results of this study are as follows: First, the suggested model was to analyze the correlation between the infection frequency and the number of senior leisure welfare facilities, the number of Public-use facilities, building area, total floor area, site area, height, building-to-land ratio, and floor area ratio varied as per the change of spatial scope. Second, correlation results varied between the infection frequency and the number of senior leisure welfare facilities, the number of Public-use facilities, building area, total floor area, site area, height, building-to-land ratio, and floor area ratio. Third, a negative correlation appeared in the analysis between the number of senior leisure welfare facilities and infection frequency. And positive correlations appeared noticeably in the study between the number of Public-use facilities, building area, total floor area, height, building-to-land ratio, and floor area ratio. Implications: This study can be used as primary data on the utilization of limited quarantine resources by analyzing the relationship between the Public-use facilities around the senior leisure welfare facilities and the spread of infectious diseases. In addition, it suggests that infectious disease prevention measures are necessary considering the spatial scope of the analysis area and the size of buildings.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.6
• /
• pp.13-23
• /
• 2022

In this paper, we propose a detailed component image classification algorithm by fashion item for unstructured data retrieval in the fashion field. Due to the COVID-19 environment, AI-based online shopping malls are increasing recently. However, there is a limit to accurate unstructured data search with existing keyword search and personalized style recommendations based on user surfing behavior. In this study, pre-processing using Mask R-CNN was conducted using images crawled from online shopping sites and then classified components for each fashion item through CNN. We obtain the accuaracy for collar of the shirt's as 93.28%, the pattern of the shirt as 98.10%, the 3 classese fit of the jeans as 91.73%, And, we further obtained one for the 4 classes fit of jeans as 81.59% and the color of the jeans as 93.91%. At the results for the decorated items, we also obtained the accuract of the washing of the jeans as 91.20% and the demage of jeans accuaracy as 92.96%.

• Journal of Space Technology and Applications
• /
• v.2 no.2
• /
• pp.104-120
• /
• 2022

The Small Scale magNetospheric and Ionospheric Plasma Experiment (SNIPE)'s scientific goal is to observe spatial and temporal variations of the micro-scale plasma structures on the topside ionosphere. The four 6U CubeSats (~10 kg) will be launched into a polar orbit at ~500 km. The distances of each satellite will be controlled from 10 km to more than ~1,000 km by the formation flying algorithm. The SNIPE mission is equipped with identical scientific instruments, Solid-State Telescopes(SST), Magnetometers(Mag), and Langmuir Probes(LP). All the payloads have a high temporal resolution (sampling rates of about 10 Hz). Iridium communication modules provide an opportunity to upload emergency commands to change operational modes when geomagnetic storms occur. SNIPE's observations of the dimensions, occurrence rates, amplitudes, and spatiotemporal evolution of polar cap patches, field-aligned currents (FAC), radiation belt microbursts, and equatorial and mid-latitude plasma blobs and bubbles will determine their significance to the solar wind-magnetosphere-ionosphere interaction and quantify their impact on space weather. The formation flying CubeSat constellation, the SNIPE mission, will be launched by Soyuz-2 at Baikonur Cosmodrome in 2023.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.57-66
• /
• 2022

The Road Management Administration is cracking down on overloaded vehicles by installing low-speed or high-speed WIMs at toll gates and main lines on expressways. However, in recent years, the act of intelligently evading the overloaded-vehicle control system of the Road Management Administration by illegally manipulating the variable axle of an overloaded truck is increasing. In this manipulation, when entering the overloaded-vehicle checkpoint, all axles of the vehicle are lowered to pass normally, and when driving on the main road, the variable axle of the vehicle is illegally lifted with the axle load exceeding 10 tons alarmingly. Therefore, this study developed a technology to detect the state of the variable axle of a truck driving on the road using roadside camera images. In particular, this technology formed the basis for cracking down on overloaded vehicles by lifting the variable axle after entering the checkpoint and linking the vehicle with the account information of the checkpoint. Fundamentally, in this study, the tires of the vehicle were recognized using the Mask RCNN algorithm, the recognized tires were virtually arranged before and after the checkpoint, and the height difference of the vehicle was measured from the arrangement to determine whether the variable axle was lifted after the vehicle left the checkpoint.

• Journal of The Korean Association of Information Education
• /
• v.26 no.4
• /
• pp.229-238
• /
• 2022

At the time of discussing the 2022 revised curriculum, the demand for normalization of information education is increasing. This study was conducted on the case of the information curriculum for the upper elementary grades responding to such needs. For 14 6th grade students of Elementary School B in K Metropolitan City, 4 core areas of the information curriculum, including computing system, data, algorithm & programming, and digital culture, were covered through classes. Cooperative classes were conducted between students by using the cloud-based application according to the class. In addition, it was intended to supplement the curriculum by suggesting ideas for artificial intelligence education area, and to improve the density of research with additional investigation on foreign information education cases. However, the need for independent organization of the information curriculum was strongly confirmed in that the current curriculum for information classes lacked sufficient school hours and had to be operated in combination with other subjects in the form of a project for this case study. It is hoped that this study will serve as a small foundation for the establishment of the information curriculum for the upper elementary grades in the future.

• Composites Research
• /
• v.36 no.1
• /
• pp.16-24
• /
• 2023

This paper presents a multi-scale progressive fatigue damage model incorporating the model for interfacial debonding between fibers and matrix. The micromechanics model for the progressive interface debonding was adopted, which defined the four different interface phases: (1) perfectly bonded fibers; (2) mild imperfect interface; (3) severe imperfect interface; and (4) completely debonded fibers. As the number of cycles increases, the progressive transition from the perfectly bonded state to the completely debonded fiber state occurs. Eshelby's tensor for each imperfect state is calculated by the linear spring model for a damaged interface, and effective elastic properties are obtained using the multi-phase homogenization method. The fatigue damage evolution formulas for fiber, matrix and interface were proposed to demonstrate the fatigue behavior of CFRP laminates under cyclic loading. The material parameters for the fiber/matrix fatigue damage were characterized using the chaotic firefly algorithm. The model was implemented into the UMAT subroutine of ABAQUS, and successfully validated with flat-bar UD laminate specimens ([0]₈,[90]₈, [30]₁₆) of AS4/3501-6 graphite/epoxy composite.

• Composites Research
• /
• v.36 no.1
• /
• pp.53-58
• /
• 2023

The PIC design method is assigning different stacking sequences for each shell element through the preliminary FE analysis. In previous study, machine learning was applied to the PIC design method in order to assign the region efficiently, and the training data is labeled by dividing each region into tension, compression, and shear through the preliminary FE analysis results value. However, since buckling is not considered, when buckling occurs, it can't be divided into appropriate loading type. In the present study, it was proposed PIC-NTL (PIC design using novel technique for analyzing load type) which is method for applying a novel technique for analyzing load type considering buckling to the conventional PIC design. The stress triaxiality for each ply were analyzed for buckling analysis, and the representative loading type was designated through the determined loading type within decision area divided into two regions of the same size in the thickness direction of the elements. The input value of the training data and label consisted in coordination of element and representative loading type of each decision area, respectively. A machine learning model was trained through the training data, and the hyperparameters that affect the performance of the machine learning model were tuned to optimal values through Bayesian algorithm. Among the tuned machine learning models, the SVM model showed the highest performance. Most effective stacking sequence were mapped into PIC tube based on trained SVM model. FE analysis results show the design method proposed in this study has superior external loading resistance and energy absorption compared to previous study.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.383-400
• /
• 2023

Air pollution-related diseases are escalating worldwide, with the World Health Organization (WHO) estimating approximately 7 million annual deaths in 2022. The rapid expansion of industrial facilities, increased emissions from various sources, and uncontrolled release of odorous substances have brought air pollution to the forefront of societal concerns. In South Korea, odor is categorized as an independent environmental pollutant, alongside air and water pollution, directly impacting the health of local residents by causing discomfort and aversion. However, the current odor management system in Korea remains inadequate, necessitating improvements. This study aims to enhance the odor management system by analyzing 1,010,749 data points collected from odor sensors located in Osong, Chungcheongbuk-do, using an Ensemble-Based Multi-Region Integrated Odor Concentration Prediction Model. The research results demonstrate that the model based on the XGBoost algorithm exhibited superior performance, with an RMSE of 0.0096, significantly outperforming the single-region model (0.0146) with a 51.9% reduction in mean error size. This underscores the potential for increasing data volume, improving accuracy, and enabling odor prediction in diverse regions using a unified model through the standardization of odor concentration data collected from various regions.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.9
• /
• pp.381-386
• /
• 2023

Many existing test case generation researchers extract test cases from models. However, research on generating test cases from natural language requirements is required in practice. For this purpose, the combination of natural language analysis and requirements engineering is very necessary. However, Requirements analysis written in Korean is difficult due to the diverse meaning of sentence expressions. We research test case generation through natural language requirement definition analysis, C3Tree model, cause-effect graph, and decision table steps as one of the test case generation methods from Korean natural requirements. As an intermediate step, this paper generates test cases from C3Tree model-based decision tables using meta-modeling. This method has the advantage of being able to easily maintain the model-to-model and model-to-text transformation processes by modifying only the transformation rules. If an existing model is modified or a new model is added, only the model transformation rules can be maintained without changing the program algorithm. As a result of the evaluation, all combinations for the decision table were automatically generated as test cases.