• Journal of the Korean Society for Precision Engineering
• /
• v.31 no.1
• /
• pp.43-50
• /
• 2014

This paper introduces a robot platform which can do weeding while traveling between rice seedlings stably against irregular land surface of a paddy field. Also, an autonomous navigation technique that can track on stable state without any damage of the seedlings in the working area is proposed. Detection of the rice seedlings and avoidance knocking down by the robot platform is achieved by the sensor fusion of a laser range finder (LRF) and an inertial measurement unit (IMU). These sensors are also used to control navigating direction of the robot to keep going along the column of rice seedling consistently. Deviation of the robot direction from the rice column that is sensed by the LRF is fed back to a proportional and derivative controller to obtain stable adjustment of navigating direction and get proper returning speed of the robot to the rice column.

• Journal of Biosystems Engineering
• /
• v.41 no.3
• /
• pp.273-280
• /
• 2016

Purpose: This experiment was conducted to detect water stress in terms of the moisture content of cucumber seedlings under water stress condition using a hyperspectral image acquisition system, linear regression analysis, and partial least square regression (PLSR) to achieve a non-destructive measurement procedure. Methods: Changes in the reflectance spectrum of cucumber seedlings under water stress were measured using hyperspectral imaging techniques. A model for estimating moisture content of cucumber seedlings was constructed through a linear regression analysis that used the moisture content of cucumber seedlings and a normalized difference vegetation index (NDVI). A model using PLSR that used the moisture content of cucumber seedlings and reflectance spectrum was also created. Results: In the early stages of water stress, cucumber seedlings recovered completely when sub-irrigation was applied. However, the seedlings suffering from initial wilting did not recover when more than 42 h passed without irrigation. The reflectance spectrum of seedlings under water stress decreased gradually, but increased when irrigation was provided, except for the seedlings that had permanently wilted. From the results of the linear regression analysis using the NDVI, the model excluding wilted seedlings with less than 20% (n=97) moisture content showed a precision ($R^2$ and $R^2_{\alpha}$) of 0.573 and 0.568, respectively, and accuracy (RE) of 4.138% and 4.138%, which was higher than that for models including all seedlings (n=100). For PLS regression analysis using the reflectance spectrum, both models were found to have strong precision ($R^2$) with a rating of 0.822, but accuracy (RMSE and RE) was higher in the model excluding wilted seedlings as 5.544% and 13.65% respectively. Conclusions: The estimation model of the moisture content of cucumber seedlings showed better results in the PLSR analysis using reflectance spectrum than the linear regression analysis using NDVI.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• v.11 no.1
• /
• pp.88-92
• /
• 2006

• Korean Journal of Remote Sensing
• /
• v.34 no.4
• /
• pp.611-624
• /
• 2018

The percentage of moisture content in rice before harvest is crucial to reduce the economic loss in terms of yield, quality and drying cost. This paper discusses the application of artificial neural network (ANN) in developing a reliable prediction model using the low altitude fixed-wing unmanned air vehicle (UAV) based reflectance value of green, red, and NIR and statistical moisture content data. A comparison between the actual statistical data and the predicted data was performed to evaluate the performance of the model. The correlation coefficient (R) is 0.862 and the mean absolute percentage error (MAPE) is 0.914% indicate a very good accuracy of the model to predict the moisture content in rice before harvest. The model predicted values are matched well with the measured values($R^2=0.743$, and Nash-Sutcliffe Efficiency = 0.730). The model results are very promising and show the reliable potential to predict moisture content with the error of prediction less than 7%. This model might be potentially helpful for the rice production system in the field of precision agriculture (PA).

• Asian-Australasian Journal of Animal Sciences
• /
• v.12 no.8
• /
• pp.1171-1176
• /
• 1999

The precision and reliability of the Computer Image Analysis technique using a desk top computer for extracting information from carcass cross section scans was evaluated by the repeatability (R) and coefficient of variation (CV) for error variance. The 6th and 7th ribs cross section of carcasses from 55 fattened Japanese Black steers were used. The image analysis was conducted using a desk top computer (Macintosh-Apple Vision 1710 Display) connected to a scanner and an image capture camera. Two software applications, Adobe Photoshop and Mac Scope were used interchangeably. The information extracted and measured were individual muscle area, circumference length, long and short axes lengths, muscle direction; distance between any two muscle centers of gravity; cross section total area, lean, fat, and bone. The information was extracted after the processes of scanning, digitization, masking, muscle separation, and binarization. When using the Computer Image Analysis technique by desk top computer, proper digitization and selection of scanning resolution are very important in order to obtain accurate information. The R-values for muscle area, circumference, long and axes lengths, and direction ranged from 0.95 to 0.99, whereas those of the distance between any two muscle centers of gravity ranged from 0.96 to 0.99, respectively. For the cross section total area, lean, fat, and bone it ranged from 0.83 to 0.99. Excellent repeatability measurements were observed for muscle direction and distance between any two muscle centers of gravity. The results indicate that the Computer Image Analysis technique using a desk top computer for extracting information from carcass cross section is reliable and has high precision.

• Journal of Biosystems Engineering
• /
• v.41 no.4
• /
• pp.304-312
• /
• 2016

Purpose: Soil strength has been measured using a cone penetrometer, which is making it difficult to obtain the spatial data required for precision agriculture. Our objectives were to evaluate real-time horizontal soil strength (RHSS) to measure soil strength in real time while moving across the field. Using the RHSS data, the tillage depth was determined, and the power consumption of a tractor and rotavators were compared. Methods: The horizontal soil-strength index (HSSI) obtained by the RHSS was compared with the cone index (CI), which was measured using a cone penetrometer. Comparison analysis in accordance with the measurement depth that increased at 5-cm interval was conducted using kriged maps at six sensing depths. For tillage control and evaluation of the power consumption, the system was installed with a potentiometer for tillage depth, a torque sensor from the rear axle, and a power take-off (PTO) shaft. Results: The HSSI was lower than the CI, but they were the same at 54.81% of the total grids for the 5-cm depth and at 3.85% for the 10-cm depth. In accordance with the recommended tillage map, tillage operations between 0 and 15 cm left 2.3% and 7% residue cover on the soil, and that between 20 and 10 cm covered a wider utilization of 3% and 18.4%, respectively. When the tillage depth was 15 cm, the comparison result of the power requirements between the PTO and rear axle in terms of control performance revealed that the maximum power requirements of the axle and PTO were 44.63 and 23.24 kW, respectively. Conclusions: An HSSI measurement system was evaluated by comparison with the conventional soil strength measurement system (CI) and applied to a tractor to compare the tillage power consumption. Further study is needed on its application to various farm works using a tractor for precision agriculture.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.573-587
• /
• 2022

The agricultural sector is completely different from other sectors since it completely relies on various natural and climatic factors. Climate changes have many effects, including lack of annual rainfall and pests, heat waves, changes in sea level, and global ozone/atmospheric CO₂ fluctuation, on land and agriculture in similar ways. Climate change also affects the environment. Based on these factors, farmers chose their crops to increase productivity in their fields. Many existing agricultural ontologies are either domain-specific or have been created with minimal vocabulary and no proper evaluation framework has been implemented. A new agricultural ontology focused on subdomains is designed to assist farmers using Jaccard relative extractor (JRE) and Naïve Bayes algorithm. The JRE is used to find the similarity between two sentences and words in the agricultural documents and the relationship between two terms is identified via the Naïve Bayes algorithm. In the proposed method, the preprocessing of data is carried out through natural language processing techniques and the tags whose dimensions are reduced are subjected to rule-based formal concept analysis and mapping. The subdomain ontologies of weather, pest, and soil are built separately, and the overall agricultural ontology are built around them. The gold standard for the lexical layer is used to evaluate the proposed technique, and its performance is analyzed by comparing it with different state-of-the-art systems. Precision, recall, F-measure, Matthews correlation coefficient, receiver operating characteristic curve area, and precision-recall curve area are the performance metrics used to analyze the performance. The proposed methodology gives a precision score of 94.40% when compared with the decision tree(83.94%) and K-nearest neighbor algorithm(86.89%) for agricultural ontology construction.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.388-393
• /
• 2024

The convergence of machine learning and smart farm is becoming more and more important. The purpose of this research is to quantitatively analyze machine learning and smart farm with bibliographic data from 2013 to 2023. This study analyzed the 251 articles, filtered from the Web of Science, with regard to the article publication trend, the article citation trend, the top 10 research area, and the top 10 keywords representing the articles. The quantitative analysis results reveal the four points: First, the number of article publications in machine learning and smart farm continued growing from 2016. Second, the article citations in machine learning and smart farm drastically increased since 2018. Third, Computer Science, Engineering, Agriculture, Telecommunications, Chemistry, Environmental Sciences Ecology, Material Science, Instruments Instrumentation, Science Technology Other Topics, and Physics are top 10 research areas. Fourth, it is 'machine learning', 'smart farming', 'internet of things', 'precision agriculture', 'deep learning', 'agriculture', 'big data', 'machine', 'smart' and 'smart agriculture' that are the top 10 keywords composing authors' keywords in the articles in machine learning and smart farm from 2013 to 2023.

• The Korean Journal of Applied Statistics
• /
• v.11 no.1
• /
• pp.29-39
• /
• 1998

The Farm Household Economy Survey (FHES) is carried out by the Ministry of Agriculture and Forestry every year. In this paper, we reveiwed the current status of the FHES and assessed the precision of the survey results. Finally we proposed some recommendations for improving the precision and presented the improvable directions of FHES with some feasible solutions.

• Food Science and Biotechnology
• /
• v.18 no.2
• /
• pp.561-564
• /
• 2009

A high performance liquid chromatography (HPLC) method has been developed for determination of 11 ginsenosides in black ginseng (BG, white ginseng that is subjected to 9 cycles of $95^{\circ}C$ for 3 hr). After eluted by gradient elution of water-acetonitrile without buffer in 70 min, 11 ginsenosides in BG were identified. The proposed method provided good linearity ($R^2$>0.9995), accuracy (92.2-106.6%), and intra- and interday precision (RSD<2.6%). In addition, ginsenosides compositions in white, red, and black ginsengs were investigated using this method, respectively. Interestingly, in BG, the content of ginsenoside $Rg_3$ which does not existed in white ginseng was 7.51 mg/g, approximately 20 times than that in red ginseng.