• Nuclear Engineering and Technology
• /
• v.53 no.9
• /
• pp.2968-2976
• /
• 2021

This paper introduces a method to reconstruct the three-dimensional (3D) microstructure of two-phase materials, e.g., porous materials such as highly irradiated nuclear fuel, from two-dimensional (2D) sections via a multi-objective optimization genetic algorithm. The optimization is based on the comparison between the reference and reconstructed 2D sections on specific target properties, i.e., 2D pore number, and mean value and standard deviation of the pore-size distribution. This represents a multi-objective fitness function subject to weaker hypotheses compared to state-of-the-art methods based on n-points correlations, allowing for a broader range of application. The effectiveness of the proposed method is demonstrated on synthetic data and compared with state-of-the-art methods adopting a fitness based on 2D correlations. The method here developed can be used as a cost-effective tool to reconstruct the pore structure in highly irradiated materials using 2D experimental data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.3144-3164
• /
• 2019

Face recognition systems have several potential applications, such as security and biometric access control. Ongoing research is focused to develop a robust face recognition algorithm that can mimic the human vision system. Face pose, non-uniform illuminations, and low-resolution are main factors that influence the performance of face recognition algorithms. This paper proposes a novel method to handle the aforementioned aspects. Proposed face recognition algorithm initially uses 68 points to locate a face in the input image and later partially uses the PCA to extract mean image. Meanwhile, the AdaBoost and the LDA are used to extract face features. In final stage, classic nearest centre classifier is used for face classification. Proposed method outperforms recent state-of-the-art face recognition algorithms by producing high recognition rate and yields much lower error rate for a very challenging situation, such as when only frontal ($0^{\circ}$) face sample is available in gallery and seven poses ($0^{\circ}$, ${\pm}30^{\circ}$, ${\pm}35^{\circ}$, and ${\pm}45^{\circ}$) as a probe on the LFW and the CMU Multi-PIE databases.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1494-1507
• /
• 2018

Intelligent human identification using face information has been the research hotspot ranging from Internet of Things (IoT) application, intelligent self-service bank, intelligent surveillance to public safety and intelligent access control. Since 2D face images are usually captured from a long distance in an unconstrained environment, to fully exploit this advantage and make human recognition appropriate for wider intelligent applications with higher security and convenience, the key difficulties here include gray scale change caused by illumination variance, occlusion caused by glasses, hair or scarf, self-occlusion and deformation caused by pose or expression variation. To conquer these, many solutions have been proposed. However, most of them only improve recognition performance under one influence factor, which still cannot meet the real face recognition scenario. In this paper we propose a multi-scale parallel convolutional neural network architecture to extract deep robust facial features with high discriminative ability. Abundant experiments are conducted on CMU-PIE, extended FERET and AR database. And the experiment results show that the proposed algorithm exhibits excellent discriminative ability compared with other existing algorithms.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.427-428
• /
• 2019

칠교놀이는 해외에서는 Tangram이라고 불리며 아주 예전부터 전해져 내려오는 세계적인 놀이이다. 친구와 여럿이서 놀이를 할 수 있을 뿐만아니라 혼자서도 즐길 수 있다. 칠교놀이는 특히 창의력 향상에 도움을 주는데 이번 논문에서는 혼자서 쉽게 칠교놀이를 즐길 수 있도록 비전시스템과 라즈베리파이를 이용해서 칠교를 카메라로 인식해 성공하면 보상으로 사탕을 지급하는 놀이를 개발해 보았다. 자판기에 동전을 넣으면, 게임을 시작해서 칠교놀이의 문제를 하나씩 맞출 때 마다 사탕 한 개가 지급되는 방식으로 4차산업혁명 시대에 걸맞는 재미있는 칠교놀이 게임을 만들어 보았다. 본 논문은 OPENCV라이브러리와 라즈베리파이 GPIO라이브러리를 사용하였다. 사용한 부품은 웹캠, 초음파 센서, 서보모터이다. 라즈베리파이를 서버로 설정하고, PC를 클라이언트로 설정하여 서로 데이터를 주고 받을 수 있게 하였다. 라즈베리파이에 OPENCV를 설치하지 않은 이유는 OPENCV가 꽤 높은 사양이 필요하다고 판단하여 비전영상처리는 PC(클라이언트)에서 진행하고, 게임의 진행상황(정답의 여부)을 라즈베리파이(서버)에 보내는 방식으로 정하였다. 반대로 라즈베리파이에서도 동전의 투입 유무를 판단하여 PC(클라이언트)에 게임 시작 신호를 보내는 방식으로 설정하였다. 언어는 라즈베리파이와 PC둘다 Pythond으로 구현하였다.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.233-244
• /
• 2021

Recently, several ICT-based cat studies have produced some successful results, according to academic and industry sources. However, research on the level of simply identifying the cat's condition, such as the behavior and sound classification of cats based on images and sound signals, has yet to be found. In this paper, based on the veterinary scientific knowledge of cats, a practical and academic cat monitoring and disease diagnosis system is proposed to monitor the health status of the cat 24 hours a day by automatically categorizing and analyzing the behavior of the cat with location information using LSTM with a beacon sensor and a raspberry pie that can be built at low cost. Validity of the proposed system is verified through experimentation with cats in actual custody (the accuracy of the cat behavior classification and location identification was 96.3% and 92.7% on average, respectively). Furthermore, a rule-based disease analysis system based on the veterinary knowledge was designed and implemented so that owners can check whether or not the cats have diseases at home (or can be used as an auxiliary tool for diagnosis by a pet veterinarian).

• Fisheries and Aquatic Sciences
• /
• v.26 no.4
• /
• pp.282-293
• /
• 2023

Nile perch and Nile tilapia are major commercial species in Uganda, and thus require continuous production. However, their production is impacted by anthropogenic activities such as fishing in breeding habitats. The aim of this study was to identify and characterize Nile perch and Nile tilapia fish breeding habitats on Lake Kyoga. Water quality, lake bottom, fish and vegetation type samples were collected from 20 sites in April of 2021 and 2022. Key informant interviews were conducted with experienced fishermen at five fish landing sites. The water quality parameters indicated significant difference within the sites using analysis of variance. Sandy and muddy bottom types were equally spread at 40% each by use of a pie chart. Fish gonads showed no significant difference among the 20 sites. Bivariate correlation analysis of the vegetation types indicated a strong negative correlation with Nile perch while Nile tilapia had a positive correlation. Principal component analysis of the water quality, fish gonads and habitat vegetation components cumulatively contributed 82.5% in characterizing a fish breeding habitat. Four sites for Nile perch and four sites for Nile tilapia were characterized as breeding sites on Lake Kyoga and are recommended for mapping and gazettement as breeding habitats for sustainable fisheries management.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.22-31
• /
• 2023

Governments around the world are enacting laws mandating explainable traceability when using AI(Artificial Intelligence) to solve real-world problems. HAI(Human-Centric Artificial Intelligence) is an approach that induces human decision-making through Human-AI collaboration. This research presents a case study that implements the Human-AI collaboration to achieve explainable traceability in governmental data analysis. The Human-AI collaboration explored in this study performs AI inferences for generating labels, followed by AI interpretation to make results more explainable and traceable. The study utilized an example dataset from the Ministry of Oceans and Fisheries to reproduce the Human-AI collaboration process used in actual policy-making, in which the Ministry of Science and ICT utilized R&D PIE(R&D Platform for Investment and Evaluation) to build a government investment portfolio.

• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.180-184
• /
• 2024

Since COVID-19, many foreign tourists have visited Korea for medical tourism. When statistical data were checked from 2022, after COVID-19, the number of foreign patients visiting Korea for two years was 24.8 million, an increase of 70.1% from 2020. It was confirmed that it has achieved a 50% level compared to 2019 (Statistics Office, 2023). Therefore, to create a development plan by linking medical tourism and wellness tourism, the purpose of this study is to find the link between medical tourism and wellness tourism as big data and present a development plan. In this research method, medical tourism, and wellness tourism for two years from 2022 to 2023 from the post-COVID period as big data are set as central keywords to compare text data to find common points. When analyzing wellness tourism and medical tourism, it was confirmed that most wellness tourism had a greater frequency than medical tourism. This confirmed that wellness tourism occupies a larger pie than medical tourism. As a result, when checking the word frequency, it was confirmed that wellness tourism and medical tourism share a lot as complex tourism products, and when checking 2-gram, to attract many medical tourists, it is necessary to combine medical tourism clusters and wellness tourism according to each other's characteristics among local governments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.12A
• /
• pp.925-932
• /
• 2009

Precise temperature monitoring is the major preconditioning to supervise quality losses within the transport chain for fresh products. ISO/IEC18000-6REV1 defines new protocols supporting BAP(Battery Assisted Passive) RFID tag which is completely compatible with EPCglobal Class1 Generation2 specification. In this paper, we designed a modem supporting BAP RFID tag with FPGA(Field Programmable Gate Array) and implemented sensor data processing function defined in ISO/IEC18000-6REV1. The transmit block of the modem supports pulse shaping filter and the output signal of the implemented RFID reader is satisfied with the spectrum mask defined in the standard. The receive block of the modem uses Gardner TED to synchronize timing of symbol. In this paper, we designed a modem supporting ISO/IEC18000-6REV1 standard and developed a RFID reader sndard. The developed RFID reader sndard can recognize sensor tag and passive tag in the wireless environment and supports real-time processing of the sensor data in the embedded linux platform.

• Journal of Digital Contents Society
• /
• v.18 no.6
• /
• pp.1135-1142
• /
• 2017

In this paper, we propose IoT based smart CCTV security service to prevent crime in blind spot and prevent unexpected fire or danger. In the proposed method, a RC (Radio Control) car is made using Raspberry pie, and a camera and various modules are installed in an RC car. It was then implemented using Raspbian O / S, Apache Web Server, Shell script, Python, PHP, HTML, CSS, Javascript. The RC car provides a security service that informs the manager of the situation by judging the risk of the scene with modules such as video, voice and temperature. Experimental results show that the transmission time of video and audio information is less than 0.1 second. In addition, real-time status transmission was possible in AVG, emergency, and manual mode. It is expected that the proposed method will be applied to the development of smart city by applying it to unmanned vehicles, drones and the like.