• 한국전자통신학회논문지
• /
• 제16권1호
• /
• pp.75-80
• /
• 2021

인공 지능은 놀라운 혜택을 제공하는 우리 삶의 중요한 부분이 되고 있다. 이와 관련하여 얼굴 표정 인식은 최근 수십 년 동안 컴퓨터 비전 연구자들 사이에서 뜨거운 주제 중 하나였다. 저해상도 이미지의 작은 데이터 세트를 분류하려면 새로운 소규모 심층 합성곱 신경망 모델을 개발해야 한다. 이를 위해 소규모 데이터 세트에 적합한 방법을 제안한다. 이 모델은 기존 심층 합성곱 신경망 모델에 비해 총 학습 가능 가중치 측면에서 메모리의 일부만 사용하지만 FER2013 및 FERPlus 데이터 세트에서 매우 유사한 결과를 보여준다.

• 대한임베디드공학회논문지
• /
• 제17권5호
• /
• pp.265-272
• /
• 2022

As the risk of lung cancer has increased, early-stage detection and treatment of cancers have received a lot of attention. Among various medical imaging approaches, computer tomography (CT) has been widely utilized to examine the size and growth rate of lung nodules. However, the process of manual examination is a time-consuming task, and it causes physical and mental fatigue for medical professionals. Recently, many computer-aided diagnostic methods have been proposed to reduce the workload of medical professionals. In recent studies, encoder-decoder architectures have shown reliable performances in medical image segmentation, and it is adopted to predict lesion candidates. However, localizing nodules in lung CT images is a challenging problem due to the extremely small sizes and unstructured shapes of nodules. To solve these problems, we utilize atrous spatial pyramid pooling (ASPP) to minimize the loss of information for a general U-Net baseline model to extract rich representations from various receptive fields. Moreover, we propose mixed-up attention mechanism of reverse, boundary and convolutional block attention module (CBAM) to improve the accuracy of segmentation small scale of various shapes. The performance of the proposed model is compared with several previous attention mechanisms on the LIDC-IDRI dataset, and experimental results demonstrate that reverse, boundary, and CBAM (RB-CBAM) are effective in the segmentation of small nodules.

• 산업경영시스템학회지
• /
• 제18권36호
• /
• pp.193-203
• /
• 1995

The production management system software which can be applied In the medium and small companies is developed. Since the medium and small companies hesitate to install the computer system for production management owing to the lack of funds and the complexities of operation, the system is made to be used in PC and only requires minimum input data. This system is composed of interrelated modules for receive/order release, inventory management MRP, new product registration, document management and production scheduling. In this paper the architecture of the system, functions of each module, and information processing procedures of each funtion are discussed.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.1243-1244
• /
• 2022

In recent years, the growing interest in off-site construction has led to factories scaling up their manufacturing and production processes in the construction sector. Consequently, continuous large-scale site monitoring in low-variability environments, such as prefabricated components production plants (precast concrete production), has gained increasing importance. Although many studies on computer vision-based site monitoring have been conducted, challenges for deploying this technology for large-scale field applications still remain. One of the issues is collecting and transmitting vast amounts of video data. Continuous site monitoring systems are based on real-time video data collection and analysis, which requires excessive computational resources and network traffic. In addition, it is difficult to integrate various object information with different sizes and scales into a single scene. Various sizes and types of objects (e.g., workers, heavy equipment, and materials) exist in a plant production environment, and these objects should be detected simultaneously for effective site monitoring. However, with the existing object detection algorithms, it is difficult to simultaneously detect objects with significant differences in size because collecting and training massive amounts of object image data with various scales is necessary. This study thus developed a large-scale site monitoring system using edge computing and a small-object detection system to solve these problems. Edge computing is a distributed information technology architecture wherein the image or video data is processed near the originating source, not on a centralized server or cloud. By inferring information from the AI computing module equipped with CCTVs and communicating only the processed information with the server, it is possible to reduce excessive network traffic. Small-object detection is an innovative method to detect different-sized objects by cropping the raw image and setting the appropriate number of rows and columns for image splitting based on the target object size. This enables the detection of small objects from cropped and magnified images. The detected small objects can then be expressed in the original image. In the inference process, this study used the YOLO-v5 algorithm, known for its fast processing speed and widely used for real-time object detection. This method could effectively detect large and even small objects that were difficult to detect with the existing object detection algorithms. When the large-scale site monitoring system was tested, it performed well in detecting small objects, such as workers in a large-scale view of construction sites, which were inaccurately detected by the existing algorithms. Our next goal is to incorporate various safety monitoring and risk analysis algorithms into this system, such as collision risk estimation, based on the time-to-collision concept, enabling the optimization of safety routes by accumulating workers' paths and inferring the risky areas based on workers' trajectory patterns. Through such developments, this continuous large-scale site monitoring system can guide a construction plant's safety management system more effectively.

• 인터넷정보학회논문지
• /
• 제18권6호
• /
• pp.7-13
• /
• 2017

In this paper, we propose a novel dynamic subchannel grouping (DSG) algorithm to maximize the system capacity considering intended proper outage probability for the downlink of enterprise small-cell networks (ESNs). In the proposed DSG scheme, a local gateway (LGW) which is installed in a building dynamically divides the frequency bandwidth into different numbers of subchannel groups (SGs) based on the numbers of small-cell access points (SAPs) and small-cell user equipments (SUEs) per floor. Then, the LGW assigns the SGs to SAPs and the SAPs allocate them to their serving SUEs. Through simulation results, we show that the proposed DSG scheme is appropriate for the ESNs compared to the conventional small-cell networks in which all SAPs use the number of fixed SGs in terms of the system capacity and outage probability.

• 대한안전경영과학회지
• /
• 제18권3호
• /
• pp.137-145
• /
• 2016

To promote the efficiency of production process of small and medium sized company, government conducts production information business that collects and analyzes information of production field automatically and helps process' controlling and supervising by supporting costs of purchase, installment, etc. of hard-software and network related to middle and small sized company intending e-Manufacturing of production field with computer and information & communication network. As a result, the number of middle and small sized companies that introduce and manage production information system is increased. Therefore, the purposes of this research are to arrange contents of production information system introduced to solve current problems of middle and small sized companies and analyze effects of small and middle sized companies' introduction through example companies.

• 인터넷정보학회논문지
• /
• 제22권5호
• /
• pp.9-16
• /
• 2021

Recently, the traffic volume of mobile communications increases rapidly and the small-cell is one of the solutions using two offload schemes, i.e., local IP access (LIPA) and selected IP traffic offload (SIPTO), to reduce the end-to-end delay and amount of mobile data traffic in the core network (CN). However, 3GPP describes the concept of LIPA and SIPTO and there is no decision algorithm to decide the path from source nodes (SNs) to destination nodes (DNs). Therefore, this paper proposes a dynamic mobile data traffic offload scheme using small-cells to decide the path based on the SN and DN, i.e., macro user equipment, small-cell user equipment (SUE), and multimedia server, and type of the mobile data traffic for the real-time and non-real-time. Through analytical models, it is shown that the proposed offload scheme outperforms the conventional small-cell network in terms of the delay of end-to-end mobile data communications and probability of the mobile data traffic in the CN for the heterogeneous networks.

• International journal of advanced smart convergence
• /
• 제13권1호
• /
• pp.1-11
• /
• 2024

Cognitive small cell networks, consisting of macro-cells and small cells, are foreseen as a promising candidate solution to address 5G spectrum scarcity. Recently, many technological issues (such as spectrum sensing, spectrum sharing) related to cognitive small cell networks have been studied, but the common control channel (CCC) establishment problem has been ignored. CCC is an indispensable medium for control message exchange that could have a huge significant on transmitter-receiver handshake, channel access negotiation, topology change, and routing information updates, etc. Therefore, establishing CCC in cognitive small cell networks is a challenging problem. In this paper, we propose a potential game theory-based approach for CCC establishment in cognitive radio networks. We design a utility function and demonstrate that it is an exact potential game with a pure Nash equilibrium. To maintain the common control channel list (CCL), we develop a CCC update algorithm. The simulation results demonstrate that the proposed approach has good convergence. On the other hand, it exhibits good delay and overhead of all networks.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제1권1호
• /
• pp.87-94
• /
• 1997

"In computer-assisted learning (CAL), small group problem-solving instruction is efficient. CAL should shift the focus of school mathematics toward goals for problem solving and mathematical modeling. For the shift, the roles and responsibilities for teachers are very important in CAL" (Heid et al. 1990).

• 대한전자공학회논문지TC
• /
• 제43권2호
• /
• pp.81-87
• /
• 2006

MEMS 공정을 이용하여 작은 접지면과 광대역 특성을 가지는 소형 안테나를 제작하였다. 광대역 특성을 얻기 위해서 다층기판을 사용하였으며, 패치 안테나는 네개의 패치로 나누어져 있고 각각의 패치는 금속선으로 연결되어 있다. 한 개의 마스크 공정으로 간단한 제작이 가능하다. 두개의 마이크로스트립 안테나를 만들었다 A 타입 안테나는 패치들이 금속선으로 연결된 안테나이고 B 타입 안테나는 금속선으로 연결이 안된 안테나이다. 제안된 안테나의 크기는 $8{\times}12{\times}2mm^3$ 이었으며 측정결과 A 타입은 5.3GHz 중심주파수에 420MHz 대역폭, B 타입은 5.66 GHB중심주파수에 480MHz 대역폭을 가지는 것으로 나타났다.