• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.421-441
• /
• 2021

Fruit detection in orchards is one of the most crucial tasks for designing the visual system of an automated harvesting robot. It is the first and foremost tool employed for tasks such as sorting, grading, harvesting, disease control, and yield estimation, etc. Efficient visual systems are crucial for designing an automated robot. However, conventional fruit detection methods always a trade-off with accuracy, real-time response, and extensibility. Therefore, an improved method is proposed based on coarse-to-fine multitask cascaded convolutional networks (MTCNN) with three aspects to enable the practical application. First, the architecture of Fruit-MTCNN was improved to increase its power to discriminate between objects and their backgrounds. Then, with a few manual labels and operations, synthetic images and labels were generated to increase the diversity and the number of image samples. Further, through the online hard example mining (OHEM) strategy during training, the detector retrained hard examples. Finally, the improved detector was tested for its performance that proved superior in predicted accuracy and retaining good performances on portability with the low time cost. Based on performance, it was concluded that the detector could be applied practically in the actual orchard environment.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.54 no.2
• /
• pp.7-14
• /
• 2012

To analyze any given situation, it is necessary to have information on elements which affect the situation. Particularly, there is greater variability in both frequency and magnitude of agricultural product prices as they are affected by various unpredictable factors such as weather conditions etc. This is the reason why it is difficult for the farmers to maintain their stable income through agricultural production and marketing. In this research, attempts are made to quantify the entropy of various situations inherent in the price changes so that the stability of farmers' income can be increased. Through this research, we developed an entropy model which can quantify the uncertainties of price changes using the probability distribution of price changes. The model was tested for its significance by comparing its simulation outcomes with actual ranges and standard deviations of price variations of the past using monthly agricultural product prices data. We confirmed that the simulation results reflected the features of the ranges and standard deviations of actual price variations. Also, it is possible for us to predict standard deviations for changed prices which will occur after a certain time using the information entropy obtained from relevant agricultural product price data before the time.

• Journal of Family Resource Management and Policy Review
• /
• v.9 no.1
• /
• pp.1-15
• /
• 2005

This study was designrd to determination factors of purchase expansion for environment-friendly agricultural products on consumers. The 310 subjects formatted questionnaires were analyzed to frequency, percentage, descriptives, T-test and logistic regression by SPSS WIN 10.0. The results were as follows : First, it is proved that degree of cognition, standard of information acquisition, basis of valuation were significant variables, Second, it is revealed that the producer and the direct deal, the consumer organization's co-op and the food floor of large-sized discount hoarded goods for purchase places of environment-friendly agricultural products were significant variables. Third, it is proved that reduction in a price the improvement matter for purchase expansion of environment-friendly agricultural products was determination factors. Forth, it is proved that age and income for purchase expansion of environment-friendly agricultural products was determination factors. Accordingly, we should find the positive factors of purchase and consumption that it will become an important subject for environment-friendly agricultural products on consumers.

• Proceedings of the Korean Society of Sericultural Science Conference
• /
• 2005.11a
• /
• pp.46-46
• /
• 2005

• Journal of The Korean Society of Agricultural Engineers
• /
• v.48 no.7
• /
• pp.65-72
• /
• 2006

Event mean concentration (EMC) of nitrogen (N) and phosphorus (P) is primary information for non-point source pollution assessment of a watershed. The EMCs for various types of agriculture such as dairy and crop farming under different climate and geologic conditions are not fully investigated. A diary- and cropfarming complex agricultural watershed in Piedmont region in Maryland, USA has been monitored for 10 years as a section 319 national monitoring program of US EPA. Dairy manure was the main source of fertilizer for crop farming in this watershed. Observed mean concentrations of N and P for each event were analyzed. Distribution of EMCs for N and P showed a wide range of variations. Representative EMCs of T-N and $NO_{3}-N$ tended to be higher than those reported for other agricultural watersheds. This study confirmed that site-specific EMC information for various agricultural practices is required for better assessment of non-point source pollution using EMC method.

• Journal of Korean Society of Rural Planning
• /
• v.2 no.2
• /
• pp.81-90
• /
• 1996

In this paper, the basic planning for the creation of consolidated agricultural institutions of Choongcheongnam -Do and its management schemes were established. These institutions, including rural development office, farmers'training institution, original seeding field of farm crops, agriculturial information center, packing design center, agricultural machinery repair center, agricultural scientific conference hall, agricultural museum, agricultural park, farmers'hall and event plaza, are planned to be created. The required area for the site is 1,246,781 m2. 281-22 Jongkyung-Ri, Sinam-Myun, Yesan-Gun, Choongcheongnam-Do and its surroundings is a proper site for the creation of'consolidated agricultural institution because the actual conditions of the soil, traffic network, irrigation and drainage, tourist routes and human resources are very good. The layout of the facilities that would comprise an agricultural institution was organized in consideration of the functions and roles of each facility and the relationships among facilities in this consolidated agricultural institution. It is desirable that the headquaters of consolidated agricultural institution oversees the management department, the planning $.$ administration $.$ information department, the rural development office, the farmers'training institution, the original seeding field of farm crops and the agricultural park.

• Journal of Korean Society of Rural Planning
• /
• v.23 no.4
• /
• pp.49-59
• /
• 2017

The importance of information system evaluation has increased according to ICT development and this evaluation is required for objective verification. The aim of this study is to develop evaluation indicators for web-based information system and verify the availability of these evaluation indicators through applying to agricultural water integrated information system. This study finds and provides eight evaluation items and 64 indicators for a web-based information system using $3{\times}3$ Mandal-Art matrix that is a tool for creating creative ideas. These evaluation items are design, contents, navigation, stability, community, convenience, usefulness, and accuracy. Total 64 evaluation indicators were presented by deriving eight evaluation items for each using $9{\times}9$ Mandal-Art matrix. When evaluating information system using evaluation indicators, it can be identified the vulnerable items in the information system. Also, the comprehensive results of the information system could be understood when appearing a single score after weighting. In addition, it can also help to prepare a questionnaire for evaluation systematically.

• Journal of the Korea Institute of Building Construction
• /
• v.9 no.6
• /
• pp.99-104
• /
• 2009

This study is the basic design of a P-C-M support system for Agricultural Facilities. By utilizing this system, many users of Agricultural Facilities can easily obtain a large amount of information, ranging from procurement to maintenance. The procurement phase suppliesthe user with agricultural facilities information, economical analysis, and corporation information for procurement decisions. Furthermore, this phase shows the shape or format of the agricultural facilities, the main materials, as well as information on the cultivated crops. The construction phase shows information about agricultural facility-related laws, as well as standard drawings or a construction guide. The maintenance phase shows a guide of maintenance-related checklists. With the results of a basic design of a P-C-M Support System for Agricultural Facilities, the P-C-M support system menu tree is established.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.4
• /
• pp.976-982
• /
• 2010

Agricultural products are one of the major food, But in recent years, It's not easy for Consumers to buy them. Cause there are not sure about the quality of the cheap foreign agricultural product imported. There are not even sure where they have been produced, Some excessive use of domestic pesticides, And Environmental pollution caused by soil contamination of plantation, It's not only matter with the conscience of the Sellers and producers. The government recommends agricultural producers to attach the mark to identify where the products are made originally. However, if producers do not comply with the recommendation, it become useless. Recently, because of the increased interest to health and food, Consumers want accurate and reliable information about The agricultural products, They buy. In this paper, Based on the RFID technology, RFID tags attached to agricultural products when consumers buy, Through the RFID reader to read RFID tags, Which make Easy to accurately convey Production of agricultural information and safety information to consumers. These features have been implemented with the traceability system.

• Journal of Agricultural Extension & Community Development
• /
• v.1 no.1
• /
• pp.29-36
• /
• 1994

The demand for agricultural information system are small but expanding in Korea. Use of information system in farm extension hilps both farmers and extensionists. This study undertakes surveys of literature on information system and extension to finds their relationship. Use of the information system can make extension service more effective if it is developed to meet following factors; 1) consider real farm problem; 2) solve the problems; 3) generate more values than costs; 4) consider real farm environments; 5) comprehensive enough to consider all relevant knowledge domain; 6) sensitive enough to meet the changes in farm environment; 7) educational and easy to learn; 8) easy to maintain.