• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.3
• /
• pp.57-63
• /
• 2009

The rapid growth of computer-based image database, necessity of a system that can manage an image information is increasing. This paper presents a region-based image retrieval method using the combination of color(autocorrelogram), texture(CWT moments) and shape(Hu invariant moments) features. As a color feature, a color autocorrelogram is chosen by extracting from the hue and saturation components of a color image(HSV). As a texture, shape and position feature are extracted from the value component. For efficient similarity confutation, the extracted features(color autocorrelogram, Hu invariant moments, and CWT moments) are combined and then precision and recall are measured. Experiment results for Corel and VisTex DBs show that the proposed image retrieval algorithm has 94.8% Precision, 90.7% recall and can successfully apply to image retrieval system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.1
• /
• pp.1-5
• /
• 2009

This paper suggests to apply mirror-reflected method based 2D emotion recognition database to 3D application. Also, it makes facial expression of fuzzy modeling using probability of emotion. Suggested facial expression function applies fuzzy theory to 3 basic movement for facial expressions. This method applies 3D application to feature vector for emotion recognition from 2D application using mirror-reflected multi-image. Thus, we can have model based on fuzzy nonlinear facial expression of a 2D model for a real model. We use average values about probability of 6 basic expressions such as happy, sad, disgust, angry, surprise and fear. Furthermore, dynimic facial expressions are made via fuzzy modelling. This paper compares and analyzes feature vectors of real model with 3D human-like avatar.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.1
• /
• pp.23-39
• /
• 2005

As developing satellite communication, the tracking range of the moving objects which move in local area is expanded to the whole world. However previous logistics management system is able to monitor freight which transporting in local area using mobile communication system. In this paper, we propose the reefer container management system that manages the location information and other related information such as temperature, humidity of container using the satellite system. The proposed system consists of three parts; data collector, satellite communication manager, reefer container information manager. And the proposed system uses the moving object index for managing the trajectory of container and tracing the location of container or vessel that is transporting the container, and supports various services such as reefer container and vessel tracking, container control and container statistics to logistic companies like shipper and forwarding agent. And the system can be increasing the quality of container transportation service to the shipper, and it makes the efficient management of reefer container to the shipping company.

• Journal of Digital Contents Society
• /
• v.15 no.1
• /
• pp.129-136
• /
• 2014

Wi-Fi fingerprinting system is a very popular positioning method used in indoor spaces. The system depends on Wi-Fi Received Signal Strength (RSS) from Access Points (APs). However, the Wi-Fi RSS is changeable by multipath fading effect and interference due to walls, obstacles and people. Therefore, the Wi-Fi fingerprinting system produces low position accuracy. Also, Wi-Fi signals pass through walls. For this reason, the existing system cannot distinguish users' floor. To solve these problems, this paper proposes a LED fingerprinting system for accurate indoor positioning. The proposed system uses a received optical power from LEDs and LED-Identification (LED-ID) instead of the Wi-Fi RSS. In training phase, we record LED fingerprints in database at each place. In serving phase, we adopt a K-Nearest Neighbor (K-NN) algorithm for comparing existing data and new received data of users. We show that our technique performs in terms of CDF by computer simulation results. From simulation results, the proposed system shows that a positioning accuracy is improved by 8.6 % on average.

• Journal of Korea Multimedia Society
• /
• v.10 no.11
• /
• pp.1398-1406
• /
• 2007

Providing natural and efficient access to the fast growing multimedia information is a critical aspect for content-based information system. Query by humming system allows the user to find a song by humming part of the tune form music database. Conventional music information retrieval systems use a high precision pitch extraction method. However, it is very difficult to extract true pitch perfectly. So, In this paper, we propose to use YIN parameter with applying the reliability to reduce the pitch extraction errors. And we describes developed music information retrieval method based on a query by humming system which uses reliable feature extraction. Developed system is based on a continuous dynamic programming algorithm with features including pitch, duration and energy along with their confidence measures. The experiment showed that the proposed method could reduce the errors of the top-10 7.2% and the top-1 9.1% compared with the cepsturm based multiple pitch candidate. The overall retrieval system achieved 92.8% correct retrieval in the top-10 rank list on a database of 155 songs.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.523-526
• /
• 2003

생체정보를 이용한 보안 솔루션이 활발하게 연구되고 있는 가운데, 지문은 가장 널리 사용되고 또한 중점적으로 연구되고 있는 생체특징의 하나로 자리잡았다. 지문인식 시스템에 사용되는 지문 입력기는 광학식, 반도체식 등 다양하나 입력방식은 주로 압착날인식으로 회전식과 달리 손가락 끝을 입력창에 대어 그 순간 접촉된 면의 지문만을 입력받게 된다. 그러므로 입력된 지문영상은 전체지문과 비교했을 때 극히 일부분에 불과하여, 이러한 제한된 영역으로부터 획득된 지문영상들을 비교한다면 비록 동일 지문이라 할지라도 획득 위치의 상이함으로 인해 타인 지문으로 오인식할 소지가 있다. 또한 특징점에 기반한 지문인증 알고리즘의 경우에는 두 지문으로부터 추출된 특징점의 위치 및 상태 정보의 신뢰성에 전적으로 의존하게되므로 특징점의 오추출 및 누락이 전체 시스템 성능을 좌우하게된다. 그러므로 가능한한 넓은 영역의 지문을 사용하고 신뢰할 만한 특징 추출 결과를 얻는 것이 에러율을 개선하는데 필수적이라 하겠다. 이에, 본 논문에서는 사용자 등록시 한 지문에서 획득한 복수의 지문영상을 이용하여 정렬 및 정합 과정을 거친 후 지문영상의 영역을 확장하고 해당 지문영상에서 추출된 특징점을 비교하여 유효하지 않은 특징점을 제거하는 과정을 통하여 등록시 저장되는 특징점 템플릿의 신뢰도를 높여주는 방법을 제안하였다. 제안된 알고리즘은 결과의 객관성을 확보하기 위하여 FVC 2002에서 제공하는 데이터베이스로 테스트한 결과 2.12%의 EER(Equal Error Rate)을 얻을 수 있었다.

• The KIPS Transactions:PartA
• /
• v.18A no.4
• /
• pp.159-164
• /
• 2011

In this paper, we suggest the active multi-agent middleware for the sensor network application. For this, firstly we design and implement the active rule based mobile agent middleware. The mobile agent in the proposed system visits the destination sensor nodes according to the migration list offered by the meta table in the name space of the naming agent, acquires and transmits sensor data according to the purpose and needs through the active rules, and directly executes the actions corresponding to the optional events(changed sensor data and/or time etc.). And then, we show the potential applicability of the active rule based mobile agent middleware in various active sensor networks through the interaction with the rule base system and context database system.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.5
• /
• pp.354-361
• /
• 2023

Big data analysis systems apply NoSQL databases like MongoDB to store, process, and analyze diverse forms of large-scale data. MongoDB offers scalability and fast data processing speeds through distributed processing and data replication, depending on its configuration. This paper investigates the suitable MongoDB environment configurations for implementing big data analysis systems. For performance evaluation, we configured both single-node and multi-node environments. In the multi-node setup, we expanded the number of data nodes from two to three and measured the performance in each environment. According to the analysis, the processing speeds for complex data structures with three or more dimensions are approximately 5.75% faster in the single-node environment compared to an environment with two data nodes. However, a setting with three data nodes processes data about 25.15% faster than the single-node environment. On the other hand, for simple one-dimensional data structures, the multi-node environment processes data approximately 28.63% faster than the single-node environment. Further research is needed to practically validate these findings with diverse data structures and large volumes of data.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.4
• /
• pp.128-136
• /
• 2011

To monitor and predict the change of coastal environment according to the construction of Saemangeum sea dyke and the development of land reclamation, we have done real-time and periodic ocean observation and numerical simulation since 2002. Saemangeum coastal environmental data can be largely classified to marine meteorology, ocean physics and circulation, water quality, marine geology and marine ecosystem and each part of data has been generated continuously and accumulated over about 10 years. The collected coastal environmental data are huge amounts of heterogeneous dataset and have some characteristics of multi-dimension, multivariate and spatio-temporal distribution. Thus the implementation of information system possible to data collection, processing, management and service is necessary. In this study, through the implementation of Saemangeum coastal environmental information system using geographic information system, it enables the integral data collection and management and the data querying and analysis of enormous and high-complexity data through the design of intuitive and effective web user interface and scientific data visualization using statistical graphs and thematic cartography. Furthermore, through the quantitative analysis of trend changed over long-term by the geo-spatial analysis with geo- processing, it's being used as a tool for provide a scientific basis for sustainable development and decision support in Saemangeum coast. Moreover, for the effective web-based information service, multi-level map cache, multi-layer architecture and geospatial database were implemented together.

• Journal of Navigation and Port Research
• /
• v.31 no.8
• /
• pp.645-652
• /
• 2007

As a method to improve the present operational and safe function in navigation this paper developed an efficient and economical integrated system of ship's information. This system is, systematically and comprehensively, to monitor, save, analyse, and display information on navigation and environment around own ship in real time by connecting one user to another through an on-board LAN or data communication via satellite so that many users on board can obtain simultaneously and easily the information in real time not only in the wheelhouse and engine room but also in many robins and ship's offices. And it consists of four(5) components; data distribution program, database of navigational and engine-related information, multi-functional monitoring program, ship management program and other application program.