• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.42 no.2
• /
• pp.202-213
• /
• 1997

In order to find out a high potential black soybean lines, of which demand has been increasing in Korea, twenty eight local cultivars were evaluated on agronomic characteristics and the classification of the cultivars was made by the cluster analysis. Days to maturity and days to growing of black soybeans were widely ranged from 58 to 82 days, and 117 to 148 days, respectively. Late maturing group showed over 140 maturity days, and heavy 100 seed weight. There was shown low yield potential in late maturing group, and growing days was positively correlated with flowering days, days to maturity, 100-seed weight and stem length, respectively. From the principal component analysis upper two components composed 76.5％ cumulative eigen value to total. Nine varietal groups were identified in relations to their affinity of the black soybeans. Selected black soybeans, Namhae-2 and Hamyang-l were field-tested and those characteristics of many pod, small seed and high yield were found out to be suitable for sprouting.

• Journal of Agricultural Extension & Community Development
• /
• v.14 no.2
• /
• pp.301-328
• /
• 2007

The purposes of this study were to classify the silver farming types and to investigate proper crops for silver farmers. Data were collected from 408 farmers returned from the urban area. Descriptive statistics were employed using SPSS/PC windows program. After then, researchers discussed the silver farming patterns and their proper crops, and tried to analyze the silver farming model. Major results were as follows: The farming aims of retirees, urban residents as well as farmers returned from the urban area were various from hobby/ leisure to income generating activities. Fourteen types of silver farming were classified by farming aim and residential area of retirees. Retirees in the hobby/leisure-oriented silver farming type can select and enjoy the various plants, animals, and insects as well as crops due to their small scale. Silver farmers in the self-sufficiency type may select crops for their food. Income-oriented silver farmers may have difficulties in choosing the proper crop. They must consider their income needs, health status and field location. Profit-oriented silver farmers with venture mind can have some business opportunities in the agricultural sectors in spite of severe competition. As the aged silver farmers have poor health, they must keep work safety rules, use the proper work-aids, and utilize the labor-saving farming system.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.671-679
• /
• 2020

In order to increase the food self-sufficiency rate, monitoring and analysis of crop conditions in the cultivated area is important, and the existing measurement methods in which agricultural personnel perform measurement and sampling analysis in the field are time-consuming and labor-intensive for this reason inefficient. In order to overcome this limitation, it is necessary to develop an efficient method for monitoring crop information in a small area where many exist. In this study, RGB images acquired from unmanned aerial vehicles and vegetation index calculated using RGB image were applied as deep learning input data to classify complex upland crops in small farmland. As a result of each input data classification, the classification using RGB images showed an overall accuracy of 80.23% and a Kappa coefficient of 0.65, In the case of using the RGB image and vegetation index, the additional data of 3 vegetation indices (ExG, ExR, VDVI) were total accuracy 89.51%, Kappa coefficient was 0.80, and 6 vegetation indices (ExG, ExR, VDVI, RGRI, NRGDI, ExGR) showed 90.35% and Kappa coefficient of 0.82. As a result, the accuracy of the data to which the vegetation index was added was relatively high compared to the method using only RGB images, and the data to which the vegetation index was added showed a significant improvement in accuracy in classifying complex crops.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.2
• /
• pp.8-13
• /
• 2021

The study for soil has been conducted separately by several areas such as soil mechanics and soil chemistry. Soil is important in terms of prediction of how the plant grow with nutrient requirement. Also, soil is important for machines to work on to solve labor shortage and save farmers from harsh environment during farm work. To meet diverse needs related to soil in agriculture, the soil related study needs to be conducted synthetically. Thus, we tried to obtain the data related to soil chemistry including pH and Electrical Conductivity (EC) with data related to soil mechanics including Cone Index (CI), moisture content, soil classification. Specifically, the condition of the field was set to be cultivated at least for five years continuously at a first step. The soil was taken from 30 sites. CI was obtained using the soil penetrometer and soil classification was conducted using sieve analysis with eight kinds of sieve. The soil was taken on December when is during winter in Korea. There was variation of data including moisture content and CI.

• Korean journal of applied entomology
• /
• v.22 no.2 s.55
• /
• pp.147-159
• /
• 1983

In general, herbicides have been classified according to selectivity, mobility. time of application, methods of application, mode of action and chemical property and structure. However, there was no generally accepted classification system for practical use in the field. The primary processes affected by the majority of herbicides are the growth process through cell elongation and/or cell division, the photosynthetic process specifically the light reaction, the oxidative phosphorylation and the integrity of the membrane systems. The usual approach in the study of the mechanism by which herbicides kill or inhibit the growth of plants is to initially determine the morphological phototoxicity systems, The mechanism by which a herbicide kills a plant or suppresses its development is actually the resultant effect of primary and secondary(or side) effects. In most instances, the death of the plant is due to the secondary effects. To induce the desired response, a herbicide must be able to gain entry into the plants and once inside, to be transported within the plant to its site(s) of activity in concentrations great enough. Obstacles to the entry and movement of herbicides in plants are generally classified by leaf and soil obstacles, translocation obstacles and biochemical obstacles, and these obstacles are also strongly influenced by plant species and by environmental factors such as light, temperature, rainfall and relative humidity. And hence, in most instances, results obtained from laboratory or greenhous vary from those of field experiment. Author attempted to classify herbicides from the field experiment using the two-dimensional ordination analysis to obtain practical information for selecting effective herbicides or to choose effective herbicide combinations for increasing herbicidal efficacy or reducing the chemical cost. Based on this two-dimensional diagram, desired herbicides or combinations were selected and further investigated for the interaction effects whether these combinations are synergistic, additive or antagonistic. From the results, it was concluded that these new approach could possibly be give more comprehensive informations about effective use of herbicide than any other systems.

• Korean Journal of Weed Science
• /
• v.2 no.2
• /
• pp.129-140
• /
• 1982

Herbicides were classified by two-dimensional ordination analysis based on the weed flora which was not controlled by application of a particular herbicide. The number of herbicide group was varied depending upon the weed community type and the experiment site. The technique of the two-dimensional ordination analysis gave more comprehensive informations about selecting of herbicides for increasing the herbicidal efficacy, for increasing the weed spectrum and for reducing the herbicide cost by mixing of herbicides. The two-dimensional ordination analysis could be used not only herbicide classification and selecting effective herbicide or herbicide combination but also can be used for the evaluation of systematic application of herbicides.

• Korean Journal of Environmental Biology
• /
• v.39 no.4
• /
• pp.581-589
• /
• 2021

Using visible-near infrared(Vis-NIR) spectra combined with machine learning methods, the feasibility of quick and non-destructive classification of Convolvulaceae species was studied. The main aim of this study is to classify six Convolvulaceae species in the field in different geographical regions of South Korea using a handheld spectrometer. Spectra were taken at 1.5 nm intervals from the adaxial side of the leaves in the Vis-NIR spectral region between 400 and 1,075 nm. The obtained spectra were preprocessed with three different preprocessing methods to find the best preprocessing approach with the highest classification accuracy. Preprocessed spectra of the six Convolvulaceae sp. were provided as input for the machine learning analysis. After cross-validation, the classification accuracy of various combinations of preprocessing and modeling ranged between 43.4% and 98.6%. The combination of Savitzky-Golay and Support vector machine methods showed the highest classification accuracy of 98.6% for the discrimination of Convolvulaceae sp. The growth stage of the plants, different measuring locations, and the scanning position of leaves on the plant were some of the crucial factors that affected the outcomes in this investigation. We conclude that Vis-NIR spectroscopy, coupled with suitable preprocessing and machine learning approaches, can be used in the field to effectively discriminate Convolvulaceae sp. for effective weed monitoring and management.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• pp.16-25
• /
• 2020

Vegetation segmentation in a field color image is a process of distinguishing vegetation objects of interests like crops and weeds from a background of soil and/or other residues. The performance of the process is crucial in automatic precision agriculture which includes weed control and crop status monitoring. To facilitate the segmentation, color indices have predominantly been used to transform the color image into its gray-scale image. A thresholding technique like the Otsu method is then applied to distinguish vegetation parts from the background. An obvious demerit of the thresholding based segmentation will be that classification of each pixel into vegetation or background is carried out solely by using the color feature of the pixel itself without taking into account color features of its neighboring pixels. This paper presents a new pixel-based segmentation method which employs a multi-layer perceptron neural network to classify the gray-scale image into vegetation and nonvegetation pixels. The input data of the neural network for each pixel are 2-dimensional gray-level values surrounding the pixel. To generate a gray-scale image from a raw RGB color image, a well-known color index called Excess Green minus Excess Red Index was used. Experimental results using 80 field images of 4 vegetation species demonstrate the superiority of the neural network to existing threshold-based segmentation methods in terms of accuracy, precision, recall, and harmonic mean.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.7 no.1
• /
• pp.123-127
• /
• 1969

The studies were conducted to know the relationship between $\beta$-amlyase activities and hardiness for the germinated seedlings of, winter wheat varieties which were classified with eye estimated cold resistance in field as, susceptible, moderate and resistant. These varieties were tested in continued five days from germination in four replicated split plot design. For the measurement of $\beta$-amylase, improved A. K. Balls method (2) was employed. Result obtained will be summarized as follows. 1. Tested varieties showed highly significant differences in $\beta$-amylase activity, while no differences were obtained between dates after germination. 2. Winter hardy varieties, Yukseung ＃3, Chin Kwang and Suwon＃85 showed higher amylase activities than the moderate hardy varieties, Jukdalma, Kangdosinryuk and Norin ＃4, while lower activities were measured in susceptible varieties, Norin ＃6, Kangdo and Norin＃12. 3. With measurement of $\beta$-amylase activity, rurther detail classification to cold resistance is seemed available than eye-estimating in the field condition. 4. In accordance with testing dates, amylase activities were not so clear on 1st, 2nd, 4th and 5th days from germination, while clear differences were found on 3rd day from germination. 5. Amylase activity obtained on 3rd day after germination is considered easy and effective method to estimate cold resistance of wheat varieties with a classification standard.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.15 no.2
• /
• pp.237-244
• /
• 1997

The goal of this research is to evaluate methodology that uses satellite data for the analysis of flood and drought damaged area. Land cover classification were performed using satellite data that were acquired at disaster periods and comparatively normal times. Damaged area was extracted by use of overlay analysis in land cover change and compared with the field survey results. The results show analysis of flood damaged area could be carried out with single scene acquired at adequate day, and are corresponded with field survey data very well. And also, some areas that had been missed in field survey were found. The suggested method proved to be more accurate and effective way for mapping inundated areas of floodplains than field survey that would be held a few month later. The results on the analysis of drought damaged area show that drained water could be detected just only in small area, and crop damaged area could not be verified in objective validity. Drought analysis by remote sensing was proved not to be adequate for practical use in this study.