• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3836-3854
• /
• 2022

The student group division is benefit for universities to do the student management based on the group profile. With the widespread use of student smart cards on campus, especially where students living in campus residence halls, students' daily activities on campus are recorded with information such as smart card swiping time and location. Therefore, it is feasible to depict the students with the daily activity data and accordingly group students based on objective measuring from their campus behavior with some regular student attributions collected in the management system. However, it is challenge in feature representation due to diverse forms of the student data. To effectively and comprehensively represent students' behaviors for further student group division, we proposed to adopt activity data from student smart cards and student attributes as input data with taking account of activity and attribution relationship types from different perspective. Specially, we propose a novel student group division method based on a multi-view student attribute heterogeneous information network (MSA-HIN). The network nodes in our proposed MSA-HIN represent students with their multi-dimensional attribute information. Meanwhile, the edges are constructed to characterize student different relationships, such as co-major, co-occurrence, and co-borrowing books. Based on the MSA-HIN, embedded representations of students are learned and a deep graph cluster algorithm is applied to divide students into groups. Comparative experiments have been done on a real-life campus dataset collected from a university. The experimental results demonstrate that our method can effectively reveal the variability of student attributes and relationships and accordingly achieves the best clustering results for group division.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제6권8호
• /
• pp.343-352
• /
• 2017

OPC UA로 명명된 국제 표준 IEC62541은 스마트 그리드(Smart Grid)와 스마트 팩토리(Smart Factory)의 응용 플랫폼을 위한 통신 프로토콜이다. 2011년 IEC TC57 그룹에서 표준화되었으며, 다른 표준들과의 협업을 통해 점차 사용범위를 넓히고 있다. 전기자동차 보급을 위한 정부 차원의 노력("전기차 충전인프라 확산 캠페인")으로 인해 스마트 팩토리에서 충전을 시도하는 전기자동차의 수는 점차적으로 증가할 것을 예상된다. 제어되지 않는 무분별한 전기자동차 충전으로 인해 스마트 팩토리의 최대수요전력을 초과하는 문제를 발생시킬 수 있다. 그러므로 스마트 팩토리 내에 전기자동차 충전 시 피크부하를 관리할 필요성이 있다. 그러나 현재의 전기자동차 충전을 위한 표준은 스마트 팩토리의 통신 프로토콜과 다르다. 다시 말해서, 편의성을 높이고, 부담을 줄 일 수 있는 프로토콜의 개발 또는 호환성 제공에 관한 연구가 필요하다. 본 논문은 스마트 팩토리에 설치되는 전기자동차 충전 시스템을 스마트 팩토리 관리시스템과 통합 관리하기 위한 플랫폼에 관한 것이다. 본 논문에서는 IEC61851과 IEC62541에 기반을 둔 전기자동차 충전기 관리 시스템을 구현한다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권1호
• /
• pp.49-54
• /
• 2016

Regarding global and local factors of a set of features, a given single image or multiple images is a common approach in image processing. This paper introduces an application of an adaptive version of non-local filter whose original version searches non-local similarity for removing noise. Since most images involve texture partner in both foreground and background, extraction of signified regions with texture is a challenging task. Aiming to the detection of visual attention regions for images with texture, we present the contrast analysis of image patches located in a whole image but not nearby with assistance of the adaptive filter for estimation of non-local divergence. The method allows extraction of signified regions with texture of images of wild life. Experimental results for a benchmark demonstrate the ability of the proposed method to deal with the mentioned challenge.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권1호
• /
• pp.35-43
• /
• 2015

Over the past couple of years, tremendous progress has been made in applying deep learning (DL) techniques to computer vision. Especially, deep convolutional neural networks (DCNNs) have achieved state-of-the-art performance on standard recognition datasets and tasks such as ImageNet Large-Scale Visual Recognition Challenge (ILSVRC). Among them, GoogLeNet network which is a radically redesigned DCNN based on the Hebbian principle and scale invariance set the new state of the art for classification and detection in the ILSVRC 2014. Since there exist various deep learning techniques, this review paper is focusing on techniques directly related to DCNNs, especially those needed to understand the architecture and techniques employed in GoogLeNet network.

• 대한원격탐사학회지
• /
• 제27권6호
• /
• pp.761-771
• /
• 2011

The sensitivity of microwave scattering to the dielectric properties and the geometric structure of soil surfaces makes radar remote sensing a challenge for a wide range of environmental issues directly related to the condition of natural surfaces. Especially, the potential for retrieving soil moisture with a high spatial and/or temporal resolution represents a significant contribution to hydrological and ecological modeling. This paper aims to review the current state of the art in SAR technology and methodological issues towards the discovery of a new potential accurate monitoring of soil moisture changes. In this paper, important parameters or constraints significantly affect the sensitivity of the measurements to soil moisture, such as roughness statistics, spatial resolution, and local topography, are discussed to improve the applicability of SAR remote sensing techniques. This study particularly intends to discuss important notes for developing smart and reliable methods capable of retrieving geophysical information.

• Smart Structures and Systems
• /
• 제6권2호
• /
• pp.135-146
• /
• 2010

This paper presents the perspective of the Structural Mechanics program of the Air Force Office of Scientific Research (AFOSR) on the damage assessment of structures for the period 2006-2009 when the author was serving as Program Manager at AFOSR. It is found that damage assessment of structures plays a very important role in assuring the safety and operational readiness of US Air Force fleet. The current fleet has many aging aircraft, which poses a considerable challenge for the operators and maintainers. The nondestructive evaluation technology is rather mature and able to detect damage with considerable reliability during the periodic maintenance inspections. The emerging structural health monitoring methodology has great potential, because it will use on-board damage detection sensors and systems, will be able to offer on-demand structural health bulletins. Considerable fundamental and applied research is still needed to enable the development, implementation, and dissemination of structural health monitoring technology.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권12호
• /
• pp.6133-6151
• /
• 2017

The field of periocular biometrics has gained wide attention as an alternative or supplemental means to conventional biometric traits such as the iris or the face. Periocular biometrics provide intermediate resolution between the iris and the face, which enables it to support both. We have developed a periocular recognition system by using uniform Multiscale Local Binary Pattern (uMLBP) and attribute features. The proposed system has been evaluated in terms of major factors that need to be considered on a mobile platform (e.g., distance and facial pose) to assess the feasibility of the use of periocular biometrics on mobile devices. Experimental results showed 98.7% of rank-1 identification accuracy on a subset of the Face Recognition Grand Challenge (FRGC) database, which is the best performance among similar studies.

• EDISON SW 활용 경진대회 논문집
• /
• 제6회(2017년)
• /
• pp.506-510
• /
• 2017

Based on the Jansen mechanism theory, a walking robot is developed, which is able to trace a line. In order to find the optimized legs, GL(Ground Length), GAC(Ground Angle Coefficient) and Grashof criteria are utilized in m.sketch program as well as EdisonDesign program. Many types of design are applied to sensors and controls, and the functionality is checked. Finally, a prototype line tracer robot is manufactured using aduino parts and smart boards. The prototype robot is test run to check the validity of the design, and modifications are applied to improve the performance according to each test result until the best design is achieved.

• EDISON SW 활용 경진대회 논문집
• /
• 제4회(2015년)
• /
• pp.491-495
• /
• 2015

Currently, selfie stick, a monopod take selfie photographs, got its popularity. Cradle used to connect selfie stick and smartphone usually uses electric force of spring to get smartphone fixed. But, using electric forces makes it hard to attach and detach smartphone from the cradle and gives possibility of smartphone falling down. CoQue suggests new solution of smartphone cradle by using cable tie (patent number US 8407863 B2) instead of electric force. It will give more easy and stable way of using selfie stick.

• Smart Structures and Systems
• /
• 제5권4호
• /
• pp.427-442
• /
• 2009

In this paper, the acceptability of system identification results for health monitoring of instrumented bridges is addressed. This is conducted by comparing the confidence intervals of identified modal parameters for a bridge in California, namely Truckee I80/Truckee river bridge, with the change of these parameters caused by several damage scenarios. A challenge to the accuracy of the identified modal parameters involves consequences regarding the damage detection and health monitoring, as some of the identified modal information is essentially not useable for acquiring a reliable damage diagnosis of the bridge system. Use of strong motion data has limitations that should not be ignored. The results and conclusions underline these limitations while presenting the opportunities offered by system identification using strong motion data for better understanding and monitoring the health of bridge systems.