• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.295-304
• /
• 2022

The purpose of this study is to detect the sorghum panicle using YOLOv5 based on RGB images acquired by a unmanned aerial vehicle (UAV) system. The high-resolution images acquired using the RGB camera mounted in the UAV on September 2, 2022 were split into 512×512 size for YOLOv5 analysis. Sorghum panicles were labeled as bounding boxes in the split image. 2,000images of 512×512 size were divided at a ratio of 6:2:2 and used to train, validate, and test the YOLOv5 model, respectively. When learning with YOLOv5s, which has the fewest parameters among YOLOv5 models, sorghum panicles were detected with mAP@50=0.845. In YOLOv5m with more parameters, sorghum panicles could be detected with mAP@50=0.844. Although the performance of the two models is similar, YOLOv5s ( 4 hours 35 minutes) has a faster training time than YOLOv5m (5 hours 15 minutes). Therefore, in terms of time cost, developing the YOLOv5s model was considered more efficient for detecting sorghum panicles. As an important step in predicting sorghum yield, a technique for detecting sorghum panicles using high-resolution RGB images and the YOLOv5 model was presented.

• Journal of KIISE:Software and Applications
• /
• v.37 no.6
• /
• pp.455-463
• /
• 2010

In this paper, we present an approach to sentence boundary detection for web documents that builds on statistical-based methods and uses rule-based correction. The proposed system uses the classification model learned offline using a training set of human-labeled web documents. The web documents have many word-spacing errors and frequently no punctuation mark that indicates the end of sentence boundary. As sentence boundary candidates, the proposed method considers every Ending Eomis as well as punctuation marks. We optimize engine performance by selecting the best feature, the best training data, and the best classification algorithm. For evaluation, we made two test sets; Set1 consisting of articles and blog documents and Set2 of web community documents. We use F-measure to compare results on a large variety of tasks, Detecting only periods as sentence boundary, our basis engine showed 96.5% in Set1 and 56.7% in Set2. We improved our basis engine by adapting features and the boundary search algorithm. For the final evaluation, we compared our adaptation engine with our basis engine in Set2. As a result, the adaptation engine obtained improvements over the basis engine by 39.6%. We proved the effectiveness of the proposed method in sentence boundary detection.

• Korean Journal of Food Science and Technology
• /
• v.47 no.1
• /
• pp.20-26
• /
• 2015

This study aimed to establish a rapid system for discriminating the cultivation origins and cultivars of dry persimmons, using metabolite fingerprinting by Fourier transform infrared (FT-IR) spectroscopy combined with multivariate analysis. Whole-cell extracts from the sepals of four Korean cultivars and two different Chinese dry persimmons were subjected to FT-IR spectroscopy. Principle component analysis (PCA) and partial least squares discriminant analysis (PLS-DA) of the FT-IR spectral data successfully discriminated six dry persimmons into two groups depending on their cultivation origins. Principal component loading values showed that the 1750-1420 and $1190-950cm^{-1}$ regions of the FT-IR spectra were significantly important for the discrimination of cultivation origins. The accuracy of prediction of the cultivation origins and cultivars by PLS regression was 100% (p<0.01) and 85.9% (p<0.05), respectively. These results clearly show that metabolic fingerprinting of FT-IR spectra can be applied for rapid discrimination of the cultivation origins and cultivars of commercial dry persimmons.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.23 no.4
• /
• pp.345-352
• /
• 2005

In up-to-date information anger time it is caused by with business of traffic accident control and analysis and two time it accomplishes a business. National Police Office which controls a traffic accident does not execute an up-to-date technique. And, it is working yet by the hand, There is to traffic accident analysis and the research regarding the analysis against the research which it follows in geography element and composition element and an accident cause is weak. Consequently, effectively establishment and it enforces a traffic safety policy and from the hazard which it evaluates traffic accident data the system and scientific analysis against a traffic accident occurrence cause and a feature in basic must become accomplished. The research which it sees constructs a traffic accident data in GIS base. It is like that, it uses the PDA where is not the collection of data of text form in existing and at real-time it converts store and an accident data rightly in standard traffic accident data form and it will be able to manage. It was related with a space data peculiarity and the research regarding the system development with the geography analysis data about an accident cause under manifesting it accomplished.

• Journal of KIISE:Databases
• /
• v.37 no.1
• /
• pp.22-32
• /
• 2010

Location-based services have been expanded rapidly in local and overseas markets due to technological advances and increasing applications of wireless internet. Various researches have been made to manage efficiently the location information of moving objects. A basic location-based alert service provides alerting messages automatically when either entering or leaving a specific location and it is expected to become one of the most important location-based services. Location-based alert services require a location polling method to acquire current locations for a large number of moving objects. However, a simple periodical location polling method causes severe system overload because a system should keep updating location information of the moving objects ceaselessly. Most location polling algorithms for location-based alerting services are not suitable for mobile users with dynamic and unsteady moving patterns. In this paper, we propose an improved location polling algorithm for location-based alerting services to reduce the amount of location information acquisition and therefore, to decrease the system load. Various experiments show that the proposed algorithm outperforms other algorithms.

• Journal of KIISE
• /
• v.43 no.3
• /
• pp.370-379
• /
• 2016

Recently personal media were produced in a variety of ways as a lot of smart devices have been spread and services using these data have been desired. Therefore, research has been actively conducted for the media analysis and recognition technology and we can recognize the meaningful object from the media. The system using the media ontology has the disadvantage that can't classify the media appearing in the video because of the use of a video title, tags, and script information. In this paper, we propose a system to automatically classify video using the objects shown in the media data. To do this, we use a description logic-based reasoning and a rule-based inference for event processing which may vary in order. Description logic-based reasoning system proposed in this paper represents the relation of the objects in the media as activity ontology. We describe how to another rule-based reasoning system defines an event according to the order of the inference activity and order based reasoning system automatically classify the appropriate event to the category. To evaluate the efficiency of the proposed approach, we conducted an experiment using the media data classified as a valid category by the analysis of the Youtube video.

• Journal of KIISE:Computer Systems and Theory
• /
• v.26 no.8
• /
• pp.975-983
• /
• 1999

최근 네트워크의 속도가 빨라지고 멀티미디어 데이터를 다루기 위한 기술들이 개발됨에 따라 많은 멀티미디어 응용 프로그램들이 인터넷에 등장하고 있다. 그러나 이들 응용프로그램들은 수신자에게 전송되는 영상.음성의 품질이 낮기 때문에 기대만큼 빠르게 확산되지 못하고 있다. 영상.음성의 품질이 낮은 이유는 현재 인터넷이 실시간 응용프로그램이 요구하는 만큼 빠르고 신뢰성 있게 데이터를 전송할 수 없기 때문이다. 현재 인터넷의 내부구조를 바꾸지 않고 품질을 높이기 위해 많은 연구들이 진행되고 있는데 그 중 하나는 동적으로 변화하는 인터넷의 상태에 맞게 멀티캐스트 트래픽의 전송율을 조절하는 종단간의 흐름제어이다. 본 논문은 기존의 흐름제어 기법인 IVS와 RLM의 성능을 개선시키기 위한 두 가지 흐름제어 기법을 소개한다. IVS는 송신자가 주기적으로 측정된 네트워크 상태에 따라 전송율을 일정하게 조절한다. 송신자가 하나의 데이타 스트림을 생성하는 IVS와는 달리 RLM에서는 송신자가 계층적 코딩에 의하여 생성된 여러개의 데이타 스트림을 전송하고 각 수신자는 자신의 네트워크 상태에 맞게 데이타 스트림을 선택하는 기법이다. 그러나 IVS는 송신자가 전송율을 일정하게 증가시키고, RLM은 각자의 네트워크 상태를 고려하지 않고 임의의 시간에 하나 이상의 데이타 스트림을 받기 때문에 성능을 저하시킬 수 있다. 본 논문에서는 TCP-like IVS와 Adaptive RLM이라는 두 가지 새로운 기법을 소개한다. TCP-like IVS는 송신자가 전송율을 동적으로 결정하고, Adaptive RLM은 하나 이상의 데이타 스트림을 받기 위해 적당한 시간을 선택할 수 있다. 본 논문에서는 시뮬레이션을 통해 여러 가지 네트워크 구조에서 두 가지 방식이 기존의 방식에 비하여 더욱 높은 대역폭 이용율과 10~20% 정도 적은 패킷손실율을 이룬다는 것을 보여준다.Abstract Nowadays, many multimedia applications for the Internet are introduced as the network gets faster and many techniques manipulating multimedia data are developed. These multimedia applications, however, do not spread widely and are not fast as expected at their introduction time due to the poor quality of image and voice delivered at receivers. The poor quality is mainly attributed to that the current Internet can not carry data as fast and reliably as the real-time applications require. To improve the quality without modifying the internal structure of the current Internet, many researches are conducted. One of them is an end-to-end flow control of multicast traffic adapting the sending rate to the dynamically varying Internet state. This paper proposes two flow-control techniques which can improve the performance of the two conventional techniques; IVS and RLM. IVS statically adjusts the sending rate based on the network state periodically estimated. Differently from IVS in which a sender produces one single data stream, in RLM a sender transmits several data streams generated by the layered coding scheme and each receiver selects some data streams based on its own network state. The more data streams a receiver receives, the better quality of image or voice the receiver can produce. The two techniques, however, can degrade the performance since IVS increases its sending rate statically and RLM accepts one more data stream at arbitrary time regardless of the network state respectively. We introduce two new techniques called TCP-like IVS and Adaptive RLM; TCP-like IVS can determine the sending rate dynamically and Adaptive RLM can select the right time to add one more data stream. Our simulation experiments show that two techniques can achieve better utilization and less packet loss by 10-20% over various network topologies.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.3
• /
• pp.189-199
• /
• 2009

The amount of information on the Web is explosively growing as the Internet gains in popularity. However, only a small portion of the information on the Web is truly relevant or useful to the user. Thus, offering suitable information according to user demand is an important subject in information retrieval. In e-commerce, the recommender system is essential to revitalize commercial transactions, raise user satisfaction and loyalty towards the information provider. The existing recommender systems are mostly based on user data collected at servers, so user data are dispersed over several servers. Therefore, web servers that lack sufficient user behavior data cannot easily infer user preferences. Also, if the user visits the server infrequently, it may be hard to reflect the dynamically changing user's interest. This paper proposes a novel personalization system analyzing the user preference based on web documents that are accessed by the user on a user device. The system also identifies non-content blocks appearing repeatedly in the dynamically generated web documents, and adds weight to the keywords extracted from the hyperlink sentence selected by the user. Therefore, the system establishes at an early stage recommendation strategies for the web server that has little user data. Also, user profiles are generated rapidly and more accurately by identifying the information blocks. In order to evaluate the proposed system, this study collected web data and purchase history from users who have current purchase activity. Then, we computed the similarity between purchase data and the user profile. We confirm the accuracy of the generated user profile since the web page containing the purchased item has higher correlation than other item pages.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2000.11a
• /
• pp.493-503
• /
• 2000

인터넷은 "정보의 바다"라는 말처럼 날마다 방대한 양의 데이터가 쏟아져 나오고 있으며, 이런 방대한 데이터 속에서 정보를 찾기란 쉽지 않다. 그러나 인터넷 사용자들은 정확한 정보를 신속하게 언제 어디서나 획득할 수 있기를 희망한다. 현재 정보의 창고인 도서관은 더 이상의 Paper 정보가 아닌 Digital 정보로의 변화가 필요하며 각 분야에서 많은 연구가 이루어지고 있다. 연구개발정보센터(KORDIC)에서는 과학기술지역인프라 구축사업을 통해서 광주ㆍ전남권역을 시범 권역으로 선정하여 13개 대학의 도서관, 산업단지, 연구소(KORDIC)를 하나로 묶는 즉, 산ㆍ학ㆍ연이 하나가 되어 상호대차 원문 서비스를 할 수 있도록 기반을 구축하는데 목적이 두고있다. 본 시스템은 상호대차 원문 서비스를 위해 대학 간 분담수서를 통해서 분담된 도서를 원문서비스 하는 상호 협력 체제를 구축하는데 필요한 시스템이며 사용자들은 해외 저널 원문을 신청하게되고, 서비스 담당자는 신청된 해외저널원문을 Digital화해서 사용자에게 보내주는 체제를 구축하기 위해 열악한 대학에는 시스템과 통신 인프라를 지원하여 상호대차원문서비스가 가능하게 하는 것을 전제로 하고 있다. 분담수서를 통해 서비스하게 될 해외저널에 대해서는 각 대학에서 책임감을 가지고 서비스를 해야하므로 서비스의 질과 업무의 자립도를 높일 수 있으며 상호대차를 통해 산ㆍ학ㆍ연이 하나처럼 연계가 된다. 또한 해외 학술 저널 DB를 공동으로 구축하여 국내 지역별 대학소장 해외 학술 전문자료를 데이터베이스화, 전문정보망을 구축 회원기관 간 정보교류의 활성화, 대학 소장 해외 학술 전문자료의 정보 표준화 효과를 창출할 수 있으며, 분담수서를 통해 얻어지는 예산 절감으로 새로운 분야에 재투자한다면 정보의 질적, 양적 향상을 도모하게 될 것이다.것으로 나타났다.본 규격은 키, 총장, 어깨길이, 등길이, 머리길이, 머리둘레, 진동둘레, 목둘레, 가슴둘레, 허리둘레, 배둘레, 엉덩이둘레, 앞품, 뒤품, drop치를 포함하고 있고, 각 규격에서 호칭간 치수 간격도 함께 제시하고 있다. 본 연구 결과에서 보듯, 현행 8규격의 무진복의 각 호칭간 적정 허용범위를 고려해 합리적인 치수체계를 정립한다면 치수에 대한 적합도가 상당히 증가할 뿐 아니라 생산비용도 상당히 감축할 것으로 생각된다.나타났다. 4) 호감적 서비스능력 차원에서 세 독립변수간에 유의한 3원 상호작용이 존재하는 것으로 나타나( $F_{2,228}$=15.62, P<.001) 20대에 적합한 의복 착용시( $F_{2,228}$=3.98, P<.05)와 60대에 적합한 의복 착용시( $F_{2,228}$=16.55, P<.001) 점포유형과 격식차림간에는 유의한 상호작용이 존재하는 것으로 나타났다. 5) 호감을 구성하는 세 요인들이 구매의도에 미치는 영향을 조사한 결과 호감적 인상차원은 29%(P<.001), 호감적 서비스능력차원은 6%(P<.001)의 구매의도를 설명해 주는 것으로 나타났다. 본 연구결과 노년 소비자에게 호감을 주는 판매원의 외모는 구매의도에 영향을 주어 실버의류산업의 이익증대와 밀접한 연관을 갖는 서비스품질의 중요한 요인으로 밝혀졌다.중요한 요인으로 밝혀졌다.로운 단백질 EPSPS가 다른 여러 식물에 이미 존재하고 있는 단백질로서 우리가 이미 이러한 식품을 섭취할 때 이 단백질도 같이 섭취해오고 있었다는 점, 둘째. 이 단백질이 소화액 분해 실험에서 짧은 시간내에 분해가 되었다는 점, 셋째. 재조합 된 콩과 자연 콩이 성분 분석에서 차이를 나타내지 않았다는 점, 네 번째. 쥐를 통한 다양섭취

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.3
• /
• pp.301-315
• /
• 2010

Recently, competition between companies has intensified and so has the necessity of creating a new business value inventions has increased. A numbers of Business organizations are beginning to realize the importance of business process management. Processes however can often not go the way they were initially designed or non-efficient performance process model could be designed. This can be due to a lack of cooperation and understanding between business analysts and system developers. To solve this problem, business process mining which can be used as the basis of the business process re-engineering has been recognized to an important concept. Current process mining research has only focused their attention on extracting workflow-based process model from competed process logs. Thus there have a limitations in expressing various forms of business processes. The disadvantage in this method is process discovering time and log scanning time in itself take a considerable amount of time. This is due to the re-scanning of the process logs with each new update. In this paper, we will presents a modified FP-Tree algorithm for FP-Tree based business processes, which are used for association analysis in data mining. Our modified algorithm supports the discovery of the appropriate level of process model according to the user's need without re-scanning the entire process logs during updated.