• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.1
• /
• pp.92-98
• /
• 2019

In this paper, we propose a deep learning system based on morphological neural network(MNN). The deep learning layers are morphological operation layer, pooling layer, ReLU layer, and the fully connected layer. The operations used in morphological layer are erosion, dilation, and edge detection, etc. Unlike CNN, the number of hidden layers and kernels applied to each layer is limited in MNN. Because of the reduction of processing time and utility of VLSI chip design, it is possible to apply MNN to various mobile embedded systems. MNN performs the edge and shape detection operations with a limited number of kernels. Through experiments using database images, it is confirmed that MNN can be used as a deep learning system and its performance.

• Journal of Information Processing Systems
• /
• v.17 no.6
• /
• pp.1179-1190
• /
• 2021

A data acquisition and monitoring system was developed for an automated system of a smart fish farm. The fish farm is located in Jang Hang, South Korea, and was designed as circulation filtration system. Information of every aquaculture pool was automatically measured by pH sensors, dissolved oxygen sensors, and water temperature sensors and the data were stored in the database in a remoted server. Modbus protocol was used for gathering the data which were further used to optimize the pool water quality to predict the rate of growth and death of fish, and to deliver food automatically as planned by the fish farmer. By using JSON protocol, the collected data was delivered to the user's PC and mobile phone for analysis and easy monitoring. The developed monitoring system allowed the fish farmers to improve fish productivity and maximize profits.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.377-380
• /
• 2022

본 논문에서는 모바일 기반 AR 환경에서 RGB카메라로부터 얻은 영상 분석과 DB 기반의 특징점(Feature point) 매칭을 통하여 보다 정확하게 위험 상황을 알려줄 수 있는 프레임워크를 제안한다. 본 논문에서는 RANSAC(Random sample consensus)기반의 다중 평면 방식을 이용한 특징점을 추출하고 분석하여 영상에 존재하는 장애물을 감지한다. RGB카메라로 얻은 영상을 기반으로 장애물을 검출하는 접근법은 영상에 의존하기 때문에 조명에 따른 특징점 검출이 부정확하고, 조명이나 자연광 또는 날씨에 영향을 많이 받기 때문에 어둡거나 흐린 날씨에서는 장애물 검출이 어려워진다. 이 문제를 완화하기 위해 본 논문에서는 DB기반의 특징점 매칭을 통해 조명에 관계없이 장애물을 효율적이고 정확하게 감지한다. 특징점 매칭을 이용하려면 우선 영상에서 특징점이 안정적으로 추출될 수 있는 환경인, 조명이나 자연광이 충분한 환경에서 감지된 장애물 정보를 데이터베이스화 하여 저장한다. 조명이 충분하지 않은 환경에서 사용자가 사전에 저장된 지역에 근접할 경우 특징점 분석이 아닌 DB 기반 특징점 매칭을 통해 위험 요소를 감지한다. 우리의 방법은 조명의 여부의 관계없이 효과적으로 위험을 감지할 수 있기 때문에 다양한 분야에 활용될 수 있다.

• International Journal of Computer Science & Network Security
• /
• v.24 no.8
• /
• pp.205-213
• /
• 2024

As the Restaurant industry is growing rapidly. The demand for an effortless POS (Point Of Sale) system which can make management easy is increasing. So, the purpose of this study is to digitalise the growing industry of restaurants and its consumers by utilizing cross-platform development. Crossplatform development frameworks provide great opportunities to solve the issues of handling ubiquitous devices with minimum efforts to reduce the cost and increase the stability, accessibility of the end consumers. By availing those opportunities, an Integrated POS system with cross platform is proposed. This integrated cross-platform POS system is originally designed for a single restaurant managed by its own private cloud server. This research solves the 2 major problems. One of them is the accessibility of the system on modern devices without even writing platform-specific code with the help of cross-platform development. This included web, mobile, desktops & tablets at the same time with the same codebase. Second one is handling data consistency with ubiquitous devices with the help of cloud infrastructure to make data safe and consistent more than ever. In the Development of this system Dart will be used as the primary programming language for cross-platform development. On the Cloud server system apache will be used as the web server and PHP as server side language. System will be using MySQL as the database server.

• Journal of Digital Convergence
• /
• v.14 no.5
• /
• pp.263-271
• /
• 2016

Localizing an object in image is a common task in the field of computer vision. As the existing methods provide a detection for the single object in an image, they have an utilization limit for the use of the application, due to similar objects are in the actual picture. This paper proposes an efficient method of object localization for image recognition. The new proposed method uses color correlation back-projection in the YCbCr chromaticity color space to deal with the object localization problem. Using the proposed algorithm enables users to detect and locate primary location of object within the image, as well as candidate regions can be detected accurately without any information about object counts. To evaluate performance of the proposed algorithm, we estimate success rate of locating object with common used image database. Experimental results reveal that improvement of 21% success ratio was observed. This study builds on spatially localized color features and correlation-based localization, and the main contribution of this paper is that a different way of using correlogram is applied in object localization.

• Journal of Korea Spatial Information System Society
• /
• v.6 no.1 s.11
• /
• pp.31-50
• /
• 2004

With the growth of wireless communication networks and mobile devices taking in GPS, Location-Based Service(LBS) is becoming an integral part of mobile applications. LBS can deal with location-aware features such as persons holding mobile phones or vehicles equipped with GPS, and provide the users with the location information of the features. Thus it is necessary to develop moving object database systems to store, manage, and query moving objects which change their locations continuously as time passes. In this paper, we design and implement a query processing component which deals with moving objects as a key data type. For this component, we define a new SQL-like query language(called MOQL) and as a consequence, design and implement modules that analyze and execute queries. It supports various types of operators that process range queries, infer topological relations, compute trajectories, and find k-nearest neighbors. It can be used as a subsystem if other application systems which deal moving objects and also supports ADO.NET interface that can be used to interact end-users.

• Science of Emotion and Sensibility
• /
• v.13 no.3
• /
• pp.501-510
• /
• 2010

The knowledge base on emotional information is one of the key elements in the implementation of emotion retrieval systems for contents design of Mobile devices. This study proposed a new approach to the knowledge base implementation by automatically extracting color components from full-color images. In this study, the validity of the proposed method was empirically tested. Database was developed using 100 interior images as visual stimuli and a total of 48 subjects participated in the experiment. In order to test the reliability of the proposed 'emotional information knowledge base', firstly 'recall ratio' that refers to frequencies of correct images from the retrieved images was derived. Secondly, correlation Analysis was performed to compare the ratings by the subjects to what the system calculated. Finally, the rating comparison was used to run a paired-sample t-test. The analysis demonstrated satisfactory recall ration of 62.1%. Also, a significant positive correlation (p<.01) was observed from all the emotion keywords. The paired Sample t-test found that all the emotion keywords except "casual" retrieved the images in the order from more relevant to less relevant images and the difference was statistically significant (t(9)=5.528, p<.05). Findings of this study support that the proposed 'emotional information knowledge base' established only with color information automatically extracted from images can be effectively used for such visual stimuli search tasks as commercial interior images.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.55-64
• /
• 2017

In this paper, we propose and implement an IoT based mobile smart monitoring system in the view point of safety inspection for solar power generation. The main features and contributions of proposed system are as follows. First, the proposed system model can evaluate periodically in the view point of safety inspection the conditions of the system and structure of solar power generation. Second, the proposed system automatically re-processes the measurement data of the system and structure for solar power generation and save it into database. Third, using the re-processed and saved information, the proposed system can provide the monitoring information with webpage form to both administrator and owner of solar power generation system, thus they can measure and confirm directly in the view point of safety inspection the conditions of the solar generation structure without visiting those places. Fourth, the provided web pages for the monitoring of solar power generation can be accessed regardless of the system structures. The performance evaluations of the proposed system show that the proposed monitoring system can save efficiently the data received from the sensors installed in the structure of solar power generation into the data base in the collecting server. And the proposed system can support that both administrator and user of solar power generation system access webpage in real time without considering places by using mobile phone and desktop computer and obtain the information for the conditions of the system and structure of solar power generation with graph forms.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.86-89
• /
• 2002

The purpose is to develop a system to reduce the organ movement from the respiration during the 3DCRT or IMRT. This research reports the experience of utilizing personally developed system for mobile tumors. The patients clinical database was structured for 10 mobile tumors and patient setup error measurement and immobilization device effects were investigated. The RMRD system is composed of the respiratory motion reduction device utilized in prone position and abdominal strip device(ASD) utilized in the supine position, and the analysis program, which enables the analysis on patients setup reproducibility. Dose to normal tissue between patients with RMRDs and without RMRDs was analyzed by comparing the normal tissue volume, field margins and dose volume histogram(DVH) using fluoroscopy and CT images. And, reproducibility of patients setup verify by utilization of digital images. When patients breathed freely, average movement of diaphragm was 1.2 cm in prone position in contrast to 1.6 cm in supine position. In prone position, difference in diaphragm movement with and without RMRDs was 0.5 cm and 1.2 cm, respectively, showing that PTV margins could be reduced to as much as 0.7 cm. With RMRDs, volume of the irradiated normal tissue (lung, liver) reduced up to 20 % in DVH analysis. Also by obtaining the digital image, reproducibility of patients setup verify by visualization using the real-time image acquisition, leading to practical utilization of our software. Internal organ motion due to breathing can be reduced using RMRDs, which is simple and easy to use in clinical setting. It can reduce the organ motion-related PTV margin, thereby decrease volume of the irradiated normal tissue.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.17 no.2
• /
• pp.1-9
• /
• 2013

In recent years, numerous mega-size and complex civil infrastructures have been constructed worldwide. For the more precise construction and maintenance process management of these civil infrastructures, the application of a variety of smart sensor-based structural health monitoring (SHM) systems is required. The efficient management of both sensors and collected databases is also very important. Recently, several kinds of database access technologies using Quick Response (QR) code and Augmented Reality (AR) applications have been developed. These technologies provide software tools incorporated with mobile devices, such as smart phone, tablet PC and smart pad systems, so that databases can be accessed very quickly and easily. In this paper, an AR-based structural health monitoring technique is suggested for sensor management and the efficient access of databases collected from sensor networks that are distributed at target structures. The global positioning system (GPS) in mobile devices simultaneously recognizes the user location and sensor location, and calculates the distance between the two locations. In addition, the processed health monitoring results are sent from a main server to the user's mobile device, via the RSS (really simple syndication) feed format. It can be confirmed that the AR-based structural health monitoring technique is very useful for the real-time construction process management of numerous mega-size and complex civil infrastructures.