• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.4
• /
• pp.27-39
• /
• 2024

Soil texture is determined by the proportions of sand, silt, and clay within the soil, which influence characteristics such as porosity, water retention capacity, electrical conductivity (EC), and pH. Traditional classification of soil texture requires significant sample preparation including oven drying to remove organic matter and moisture, a process that is both time-consuming and costly. This study aims to explore an alternative method by developing an AI model capable of predicting soil texture from images of pre-sorted soil samples using computer vision and deep learning technologies. Soil samples collected from agricultural fields were pre-processed using sieve analysis and the images of each sample were acquired in a controlled studio environment using a smartphone camera. Color distribution ratios based on RGB values of the images were analyzed using the OpenCV library in Python. A convolutional neural network (CNN) model, built on PyTorch, was enhanced using Digital Image Processing (DIP) techniques and then trained across nine distinct conditions to evaluate its robustness and accuracy. The model has achieved an accuracy of over 80% in classifying the images of pre-sorted soil samples, as validated by the components of the confusion matrix and measurements of the F1 score, demonstrating its potential to replace traditional experimental methods for soil texture classification. By utilizing an easily accessible tool, significant time and cost savings can be expected compared to traditional methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.1
• /
• pp.135-141
• /
• 2018

In this paper, we describe design and implementation of optimal smart home control system. Recent developments in technologies such as sensors and communication have enabled the Internet of Things to control a wide range of objects, such as light bulbs, socket-outlet, or clothing. Many businesses rely on the launch of collaborative services between them. However, traditional IoT systems often support a single protocol, although data is transmitted across multiple protocols for end-to-end devices. In addition, depending on the manufacturer of the Internet of things, there is a dedicated application and it has a high degree of complexity in registering and controlling different IoT devices for the internet of things. ARIoT system, special marking points and edge extraction techniques are used to detect objects, but there are relatively low deviations depending on the sampling data. The proposed system implements an IoT gateway of object based on OneM2M to compensate for existing problems. It supports diverse protocols of end to end devices and supported them with a single application. In addition, devices were learned by using deep learning in the artificial intelligence field and improved object recognition of existing systems by inference and detection, reducing the deviation of recognition rates.

• Journal of Ecology and Environment
• /
• v.46 no.3
• /
• pp.154-160
• /
• 2022

Background: The mango is one of the essential fruit trees for the economy of Thailand. Mango pollination relies primarily on insects. Other external forces, such as wind, are less efficient since pollen is sticky and aggregating. There is only one report from Thailand on the use of bees as mango pollinators. The study of the behavior and pollination efficiency of honey bees (Apis mellifera) and stingless bees (Tetragonula laeviceps species complex) was conducted in Nam Dokmai mango plantings in Phrao and Mae Taeng districts, Chiang Mai province, between February and March 2019. Results: Our results reveal that the honey bees commenced foraging earlier than the stingless bee. The number of flowers visited within 1 minute by honey bees was higher than that visited by stingless bees. The average numbers of honey bees and stingless bees that flew out of the hive per minute from 7 a.m. and 6 p.m. in the Phrao district were 4.21 ± 1.62 and 9.88 ± 7.63 bees/min, respectively, i.e., higher than those observed in Mae Taeng, which were 3.46 ± 1.13 and 1.23 ± 1.20 bees/min, respectively. The numbers of fruits per tree were significantly higher in the honey bee and stingless bee treatments (T1 and T2) than in the open pollination treatment (T3). The number of fruits between T1 and T2 treatments was not different. In the pollinator exclusion treatment (T4), no fruit was produced. Fruit size factors were not significantly different among T1, T2, and T3 treatments. Conclusions: Our results showed that insect pollination is crucial for mango production, especially with the Nam Dokmai variety in Northern Thailand. As pollinator exclusion treatment showed no fruit set, and pollinator treatment significantly increased the fruit sets compared to open access plots, a managed pollinator program would benefit the mango growers for better productivity. Both the honey bee and the stingless bee were shown to be effective as pollinators.

• Food Science and Preservation
• /
• v.9 no.3
• /
• pp.282-286
• /
• 2002

This study was conducted to improve the storability of onion bulbs by loading method under room temperature and to reduce the rot caused by field open storage. Allium cepa cv. Changnyungdeago, late strain, was used for the test at the storage condition of 1-row-6-stairs, 2-rows-6-stairs, 4-rows-6-stairs, 1-rows-8-stairs, 2-rows-8-stairs, and 4-rows-8-stairs. The results obtained art as follows: The mean temperature was maintained lowly 1.6∼3.2$\^{C}$ in 1-row-6-stairs and 1.3∼2.6$\^{C}$ in 2-rows-6-stairs in contrast to 4-rows-8-stairs and the relative humidity was high when loading rows increased. The rotting rates in 1-row-6-stairs, 2-rows-6-stairs, 4-rows-6-stairs, 1-rows-8-stairs, 2-rows-8-stairs, and 4-rows-8-stairs were 11.4%, 11.6%, 12.4%, 14.6%, 13.9% and 16.6%, respectively, and became higher with increased rows and stairs of loading. Total weight loss of onion bulbs were l2.2%, 12.7%, 13.8%, 15.5%, 15.2% and 18.0% in 1-row-6-stairs, 2-rows-6-stairs, 4-rows-6-stairs, 1-row-8-stairs, 2-rows-8-stairs, and 4-rows-8-stairs, respectively. The rot of onion bulbs was caused mainly by Fusarium sp., Aspergilus sp., Botrytis sp., and bacteria.

• Journal of Plant Biotechnology
• /
• v.32 no.4
• /
• pp.243-250
• /
• 2005

The coat protein gene (AF296280) of the Korean isolate Potato leafroll virus (PLRV) was cloned and the open reading frame (627 bp) was transformed into potato (Solanum tuberosum cv. Superior). Out of seventeen individual transgenic lines, five lines were identified to confer resistance to PLRV through the five generation's selection program in the greenhouse as well as isolated trial field. Successful introduction and genetic stability of coat protein gene in the genome of potato were confirmed by polymerase chain reaction (PCR), Southern blot hybridization and northern blot hybridization. Some of the transgenic lines were highly resistant to PLRV but did not show any resistance to less homologous Potato virus Y (PVY). Our results suggest that the resistance to PLRV is due to homology dependent gene silencing by sense strand coat protein gene. In addition, the results of field test through five generations showed that there were no significant differences comparing to nontransgenic potatoes in the morphological aspect of shoot as well as tuber, Ho remarkable differences were also observed in the major agronomic characters and yields except for the resistance to PLRV.

• Research in Plant Disease
• /
• v.20 no.2
• /
• pp.79-86
• /
• 2014

In order to seek more eco-friend, economic and safer quarantine method than current methyl bromide fumigation, the convergent treatment with 200 Gy of gamma irradiation and several chemicals such as nano-siver particles (NSS), sodium dichloroisocyanurate (NaDCC) was tried on the cuttings of lily in the packing of catonnage box for export. With 6 independent experiments of gamma irradiation on the three lily cultivars, cvs. Siberia, Le reve and Sorbonne, incidence and severity of lily leaf blight was investigated on leaves and petals at 8-d after infection. 200 Gy of gamma irradiation decreased at 13-25% of severity on the leaf of Sorbonne, but it increased at 2-5% of severity on the leaf of Siberia and Le reve. Chemical substitutes such as NSS and NaDCC were not effective to control of lily blight on cuttings. By 200 Gy of gamma irradiation treatment, chlorophyll contents were statistically significantly decreased at 12-d after irradiation and the longevities vaselife of fully open flower of Siberia and Sorbonne were increased at 0.4 to 1.2 days. In addition, the relative fresh weights of the gamma irradiated cuttings were severely dried compared to the non-irradiated control. On the other hands, the symptoms of phyto-toxicity of high dose gamma irradiation at 1 or 2 kGy on cv. Siberia were to be blight at the tip of bloom, bent necks of flower, and delayed the process of flowering.

• The Plant Pathology Journal
• /
• v.16 no.5
• /
• pp.269-279
• /
• 2000

Alfalfa mosaic alfamoviruses(AIMV) were isolated from infected potato (Solanum tuberosum) and azuki bean (Paseolus angularis) in Korea. Two AIMV isolated from potatoes were named as strain KR (AIMV-KR1 and KR2) and AIMV isolated from azuki bean was named as strain Az (AIMV-Az). Each isolated AIMV strain was characterized by using their host ranges, symptom developments, serological relations and nucleotide sequence analysis of coat protein (CP) gene. Strains KR1, KR2, and Az were readily transmitted to 20 of 22 inoculated plant species including bean, cowpea, tomato, tobacco, and potato. AIMV-KR1 and KR2 produced the typical symptoms like chlorotic or necrotic spots in Chenopodium quinoa and Solanum tuberosum cv. Superior. AIMV-Az caused bright yellow mosaic symptom and leaf malformation in Nicotiana glauca, which were different from the common mosaic symptom caused by AIMV-KR1 and KR2. Electron microscope observation of purified virus showed bacilliform virions containing a single-stranded plus-strand RNAs of 3.6, 2.6, 2.0 and 0.9 kbp in length, respectively, similar in size and appearance to those of Alfamovirus. In SDS-PAGE, the coat protein of the two viruses formed a consistent band that estimated to be about 24kDa. The CP genes of the AIMV strains, KR1, KR2, and Az have been amplified by RT-PCR using the specific primers designed to amplify CP gene from viral RNA-3, cloned and sequenced. Computer aided analysis of the amplified cDNA fragment sequence revealed the presence of a single open reading frame capable of encoding 221 amino acids. The nucleotide and peptide sequence of viral CP gene showed that strain KR1, KR2, and Az shared highest nucleotide sequence identities with AIMV strain 425-M at 97.7%, 98.2%, and 97.2%, respectively. CP gene sequences of two strains were almost identical compared with each other. Altogether, physical, serological, biological and molecular properties of the purified virus.

• Environmental and Resource Economics Review
• /
• v.19 no.1
• /
• pp.101-127
• /
• 2010

The purpose of the research is to tackle proximity effects (PEs) when nonmarket valuation method CVM is applied to environmental goods such as tidal flats. 1,000 households are surveyed in the ratio of national household for the research. The sample are reclassified into five areas by 30-minute distance. Log-linear are used to analysis PEs in the research. On conclusion log-linear model regarding income effects proves that PEs are apparently represented in NMVMs(${\theta}_1$ >0. ${\theta}_2$ >0 and $dum1{\neq}0$, $dum2{\neq}0$, $dum3{\neq}0$, $dum4{\neq}0$) as a result of a 5 per cent significant level of t -test and F-test, finally rejecting the null hypothesis. In addition, WTP of area I respondents shows 26 per cent more then that of area V respondents, which is from \87,969 to \64,866 in the open-ended format. Finally, the research proves that the PEs in CVM are evidently represented with the econometric model, hence the PEs have to be embedded into the questionnaire of non-market valuation methods with the environmental goods to reduce the underestimation and improve the estimation accuracy.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.5
• /
• pp.30-42
• /
• 2022

Due to the increase in construction of tunnels, the burdens of maintenance works for tunnel structures have been increasing in Korea. In addition, the increase of traffic volume and aging of materials also threatens the safety of tunnel facilities, therefore, maintenance costs are expected to increase significantly in the future. Accordingly, automated condition assessment technologies like image-based tunnel scanning system for inspection and diagnosis of tunnel facilities have been proposed. For image-based tunnel scanning system, it is key to create a planar image through stitching of multiple images captured by tunnel scanning system. In this study, performance of feature-based stitching algorithms suitable for stitching tunnel scanning images was evaluated. In order to find a suitable algorithm SIFT, ORB, and BRISK are compared. The performance of the proposed algorithm was determined by the number of feature extraction, calculation speed, accuracy of feature matching, and image stitching result. As for stitching performance, SIFT algorithm was the best in all parts of tunnel image. ORB and BRISK also showed satisfactory performance and short calculation time. SIFT can be used to generate precise planar images. ORB and BRISK also showed satisfactory stitching results, confirming the possibility of being used when real-time stitching is required.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.535-543
• /
• 2022

A drone is used to diagnose crop growth and to provide information through images in the agriculture field. In the case of using high spatial resolution drone images, growth information for each object can be produced. However, accurate object detection is required and adjacent objects should be efficiently classified. The purpose of this study is to develop a Chinese cabbage object detection algorithm using multispectral reflectance images observed from drone and computer vision techniques. Drone images were captured between 7 and 15 days after planting a Chinese cabbage from 2018 to 2020 years. The thresholds of object detection algorithm were set based on 2019 year, and the algorithm was evaluated based on images in 2018 and 2019 years. The vegetation area was classified using the characteristics of spectral reflectance. Then, morphology techniques such as dilatation, erosion, and image segmentation by considering the size of the object were applied to improve the object detection accuracy in the vegetation area. The precision of the developed object detection algorithm was over 95.19%, and the recall and accuracy were over 95.4% and 93.68%, respectively. The F1-Score of the algorithm was over 0.967 for 2 years. The location information about the center of the Chinese cabbage object extracted using the developed algorithm will be used as data to provide decision-making information during the growing season of crops.