• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권10호
• /
• pp.3211-3229
• /
• 2022

To solve the problems existing in the process of Weibo disaster rumor recognition, such as lack of corpus, poor text standardization, difficult to learn semantic information, and simple semantic features of disaster rumor text, this paper takes Sina Weibo as the data source, constructs a dataset for Weibo disaster rumor recognition, and proposes a deep learning model BERT_AT_Stacked LSTM for Weibo disaster rumor recognition. First, add adversarial disturbance to the embedding vector of each word to generate adversarial samples to enhance the features of rumor text, and carry out adversarial training to solve the problem that the text features of disaster rumors are relatively single. Second, the BERT part obtains the word-level semantic information of each Weibo text and generates a hidden vector containing sentence-level feature information. Finally, the hidden complex semantic information of poorly-regulated Weibo texts is learned using a Stacked Long Short-Term Memory (Stacked LSTM) structure. The experimental results show that, compared with other comparative models, the model in this paper has more advantages in recognizing disaster rumors on Weibo, with an F1_Socre of 97.48%, and has been tested on an open general domain dataset, with an F1_Score of 94.59%, indicating that the model has better generalization.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.147-150
• /
• 2008

This study refers to develop a semi-automatic extraction of agricultural land use and vegetation information using high resolution satellite images. Data of IKONOS satellite image (May 25 of 2001) and QuickBird satellite image (May 1 of 2006) which resembles with the spatial resolution and spectral characteristics of KOMPSAT3. The precise agricultural land use classification was tried using ISODATA unsupervised classification technique and the result was compared with on-screen digitizing land use accompanying with field investigation. For the extraction of vegetation information, three crops of paddy, com and red pepper were selected and the spectral characteristics were collected during each growing period using ground spectroradiometer. The vegetation indices viz. RVI, NDVI, ARVI, and SAVI for the crops were evaluated. The evaluation process is under development using the ERDAS IMAGINE Spatial Modeler Tool.

• 한국농림기상학회지
• /
• 제6권2호
• /
• pp.94-106
• /
• 2004

Determining those gaps in agricultural and other information to improve agrometeorological analyses for agriculture is a large task. The effective integration of appropriate data systems, including remote sensing systems, with agricultural systems modelling capability is described as a worthy outcome in this endeavour. Data issues, including those associated with data length, quality, maintenance, and archiving remain serious issues to be addressed. The role of remote sensing and geographic information systems in agrometeorology is important and is explored here. The value of simulation models to provide the synthesis for future agrometeorological requirements is further elucidated.

• 농촌계획
• /
• 제21권3호
• /
• pp.33-45
• /
• 2015

The oversea export of agricultural-product about item and quantity has not increased recently; especially the fresh-product has a tough issue because of period of production, price large fluctuations, customs clearance, quarantine, and uncertainty about actual locality, we need the information based construction to exchange information quickly about whole range of export and to focus capacity of participation subject for increasing the export. In this study we design the agricultural-product transaction information system based on crowdsourcing to transact the agricultural-product and the information of influencing benefit directly, and the information offering about export-procedure from participation of customs clearance, finance, distribution, buyer, and producer's guild, etc. We expect the producer's guild about agriculture that has not participate the trade to be able to export the agricultural-product and the stabilization of price to transact the product of collapsed or boomed through the agricultural-product information system based on crowdsourcing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2012-2027
• /
• 2019

Nutritional disorders are one of the most common diseases of crops and they often result in significant loss of agricultural output. Moreover, the imbalance of nutrition element not only affects plant phenotype but also threaten to the health of consumers when the concentrations above the certain threshold. A number of disease identification systems have been proposed in recent years. Either the time consuming or accuracy is difficult to meet current production management requirements. Moreover, most of the systems are hard to be extended, only detect a few kinds of common diseases with great difference. In view of the limitation of current approaches, this paper studies the effects of different trace elements on crops and establishes identification system. Specifically, we analysis and acquire eleven types of tomato nutritional disorders images. After that, we explore training and prediction effects and significances of super resolution of identification model. Then, we use pre-trained enhanced deep super-resolution network (EDSR) model to pre-processing dataset. Finally, we design and implement of diagnosis system based on deep learning. And the final results show that the average accuracy is 81.11% and the predicted time less than 0.01 second. Compared to existing methods, our solution achieves a high accuracy with much less consuming time. At the same time, the diagnosis system has good performance in expansibility and portability.

• 산업융합연구
• /
• 제21권9호
• /
• pp.133-142
• /
• 2023

농촌인구 감소, 고령화 심화, 기후변화 등으로 지속적으로 악화되고 있는 한국농업의 생산여건 변화에 효과적으로 대응하기 위해 디지털 정보기술 활용이 중요해졌다. 이에 본 연구는 성향점수매칭법을 이용하여 농가의 정보화 기기 활용 선택에 미치는 요인과 정보화 기기 활용이 농산물 판매에 미치는 효과를 분석하였다. 분석 결과, 연령이 낮은 농가, 교육수준이 높은 농가, 선도농가들이 정보화 기기 활용 채택 가능성이 높은 것으로 나타났다. 연령, 경영규모, 영농형태 등 유사한 특성을 가진 농가라면 농업경영에 정보화 기기를 활용하는 농가가 더 높은 농산물 판매 수입을 올리는 것이 확인되었다. 따라서 농가의 정보화 기기의 활용능력을 높이는 것은 농가소득을 향상시킬 수 있다는 시사점을 제공한다. 정보화 기기 보급 및 농업정보를 활용할 수 있는 능력을 농가들이 가질 수 있도록 정부의 농업·농촌 분야 정보화 지원 사업이 중요하다 할 수 있으며, 정보 기술에 근거한 과학적 영농 및 마케팅 활동이 이루어질 수 있는 정보 인프라 구축에도 적극적인 투자가 이루어져야 할 것이다.

• Journal of Biosystems Engineering
• /
• 제29권6호
• /
• pp.544-552
• /
• 2004

This study was conducted to suggest the efficient gathering and recycling method of disused agricultural machinery in rural environment. In order to suggest this methods, the keeping means, maintenance, disused period and kinds of agricultural machinery were investigated. The results obtained in this study were as follows : The disused agricultural machinery have been leaved on the vacant lot of a farmhouse and an around field for $2\~5\;years$. The leaving reason of the disused agricultural machinery was low interesting and gathering price for the disused agricultural machinery. The present situation for recycling method was using as a scrap iron, however to increase recycling percent the disassembling process has to divide as using and parts concretely. And the design of agricultural machinery was considered the easiness of a disassemble and assemble the agricultural machinery. To manage and supply efficiently for the second-hand parts of agricultural machinery need to the establishment of circulation information center and internet site for the parts.

• Agribusiness and Information Management
• /
• 제1권1호
• /
• pp.3-18
• /
• 2009

This research aims to examine consumers' general types of information search and their unsatisfactory factors in purchasing agricultural products on electronic commerce and analyze consumers' behavioral characteristics. As study subjects, 802 consumers who have visited the home pages of 14 households or companies, whose home pages are actively managed, were sampled. As a research tool, pop-up post and e-mail were used as research tools and questionnaires were asked three times. The date on research result were analyzed using SPSS 13 statistics package in terms of frequency, percentage, descriptive statistics, one-way ANOVA and correlation analysis.

• 농촌계획
• /
• 제16권1호
• /
• pp.9-20
• /
• 2010

The aim of this paper is to identify Korean agricultural and agri-manufacturing cluster using a multi-regional input-output model. This paper derives a representative set of five agricultural and agri-manufacturing clusters in Korea in terms of spatial and industrial interdependency. The results show that agriculture and agri-manufacturing clusters agglomerated in Seoul Metropolitan Area and Chungcheong Area are linked both production and manufacture functions, whereas Gangwon Area is more focused on production and Jeolla Area is more concentrated on manufacture.

• Agribusiness and Information Management
• /
• 제5권2호
• /
• pp.17-26
• /
• 2013

The purpose of this study is to prove that new values for the agricultural food area can be created by combining various big data collected in the agricultural food area and analyzing them in an appropriate analysis method. For this, the analysis techniques generally used were studied, and the use of the big data in the various areas of the current society was explored through practical application instances. In addition, by the current status and analysis instances of the big data use in the agricultural food area, this study was conducted to verify how the new values found were being used.