• Journal of Plant Biotechnology
• /
• v.6 no.4
• /
• pp.221-227
• /
• 2004

Protocol was established for production of virus free healthy seeds using meristem ($0.3-0.5\;\cal{mm}$ in size) culture and field management under net house condition in tomato. The isolated meristem was found well established in MS liquid medium containing $0.1\;\cal{mg}\;1^{-1}\;of\;GA_3$. For shoot and root development either from primary meristem or from nodal segment of meristem derived plants, semisolid MS medium having $0.5\;\cal{mg}\;1^{-1}$ of IBA was found most effective. The elimination of the studied viruses (ToMV, CMV, ToLCV) in meristem-derived plants was confirmed by DAS-ELISA test. For field management of the virus eradicated meristem-derived plants, use of net house was found very effective measures to check viral vector visit and eventually infection. The meristem-derived plants were vigor and high yielder than the native seed derived plants and produced healthy seeds. Due to stop vector visit, no viral symptoms were observed in both $R_1\;and\;R_2$ plants cultivated in net house condition. Starting of viral infestation was observed in $R_2$ generation when they were planted in open house condition without control of vector visit. Therefore, for management of viral diseases, use of virus free meristem derived plantlets and their subsequent cultivation in soil under net house condition without using any vector killing insecticide can be recommended for producing healthy seeds in tomato. The developed protocol for environmentally healthy tomato seed production in Bangladesh may be used in the countries having similar tropical like environment conducive for viral vector visit.

• Progress in Medical Physics
• /
• v.18 no.4
• /
• pp.214-220
• /
• 2007

Diffusion tensor tractorgraphy which is based on line propagation method with brute force approach is implemented and the vector correlation function is proposed in addition to the conventional fractional anisotrophy value as a criterion to select seed points. For the whole tractography, the proposed method used 41 % less seed points than the conventional brute force approach for $FA{\geq}0.3$ and most of the fiber tracks in the outer region of white matter were removed. For the corticospinal tract passing through region of interest, the proposed method has produced similar results with 50% less seed points than conventional one.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.271-281
• /
• 2022

Manual seed classification challenges can be overcome using a reliable and autonomous seed purity identification and classification technique. It is a highly practical and commercially important requirement of the agricultural industry. Researchers can create a new data mining method with improved accuracy using current machine learning and artificial intelligence approaches. Seed classification can help with quality making, seed quality controller, and impurity identification. Seeds have traditionally been classified based on characteristics such as colour, shape, and texture. Generally, this is done by experts by visually examining each model, which is a very time-consuming and tedious task. This approach is simple to automate, making seed sorting far more efficient than manually inspecting them. Computer vision technologies based on machine learning (ML), symmetry, and, more specifically, convolutional neural networks (CNNs) have been widely used in related fields, resulting in greater labour efficiency in many cases. To sort a sample of 3000 seeds, KNN, SVM, CNN and CNN-SVM hybrid classification algorithms were used. A model that uses advanced deep learning techniques to categorise some well-known seeds is included in the proposed hybrid system. In most cases, the CNN-SVM model outperformed the comparable SVM and CNN models, demonstrating the effectiveness of utilising CNN-SVM to evaluate data. The findings of this research revealed that CNN-SVM could be used to analyse data with promising results. Future study should look into more seed kinds to expand the use of CNN-SVMs in data processing.

• Korean journal of applied entomology
• /
• v.7
• /
• pp.5-13
• /
• 1969

Present system of seed potato production in Korea has several weak points and consequently has difficulties in covering annual shortage of 60,000 tons of seed potatoes. The author has an opinion that this so called 'High land system' of seed potato production adopted by the Government should be replaced by the 'Coastal area system' which is proposed by the author and has many advantages over present 'High land system'(2). In coastal areas where enormous acreage of rice paddies are spread, mostly around the villages. the primary host plants of the vectors are found. Therefore, the only source of aphid vectors are limited to the villages. The farmer's houses scattered more sparsely also have minor importance. In the previous paper(2), the author reported that the aphid vector populations were lower in the coastalareas than at Taegwanryong where the Alpine Experiment Station for the production. of seed potatoes is located. However, the number to vectors at Okku showed rather high density, where the trap was placed at the distance of 200 m from a village where peach and Hibiscus trees, the primary hosts of Myzus pesrsicae and Aphis gossypii were grown. To clarify the flight distance from the source of the aphid vectors, a trial was carried out in the Kwanghwal area, Kimje-gun, Cholla-pukto. on the western coast. 13 traps were placed at four directions and the distances between the traps were 250 m. (Fig. I) The traps 'Were operated from June 21 to October 31. The results are shown in Table 1. A total of some 70 species of aphids were found, including 5 speceis of potato virus vectors. The vectors are as follows: I. Myzus persicae (Sulzer) 2. Aphis gossypii Glover 3. Aulacorthum solani (Kaltenbach) 4. Lipaphis erysimi (Kaltenbach) 5. Macrosiphoniella sanborni (Gillette) Out of a total of 12,797 aphids, 5,187$(48\%)$ vectors were found. The trap catches at the 13 locations are shown in Fig. 2 and the numbers of the vectors at each location for each vector, except Macro-siphoniella sanborni. of which only a single individual was caught, are shown in Fig. 3-6. Number of vectors at C (3,279) (Centre of the village) is considerably higher than that at Suwon (763); however, EI. SI. WI and NI. where the distanecs from Care 250 m, showed lower numbers of vectors than that at Taegwanryong (347). The number of vectors at NI was rather than at the other 3 locations at the distance of 250m from the village. This was because C was in the southern part of the village. Consequently NI was much closer to the village than the other 3 locations of the same distance from C. Numbers of catches of the most important vector. Myzus persicae, are shown in Fig.3. The distribution pattern is typical except $S-2\;and\;W_3$, where several farmer's houses were found. If only the rice paddies were found in these locations. the numbers of the vectors would be small as the distances increase. Numbers of catches of the other 3 vectors are shown in Fig. 4-6. From these results. the author has drawn the following conclusions: 1. The aphid vector sources at the rice paddy belt in the western coast are the villages. 2. The vector densities at the locations where the distances are 250 m from the centre of the village are lower than that at Taegwanryong. 3. The vector densities become gradually lower as the distances from the centre of village increase. However. depending on the host plant situation at each location, the vector densities are variable. These minor sources of aphid vectors may be eliminated so that seed potatoes can be grown. 4. Thus. under the direction of specialists, fields suitable for seed potato production can be found in the coastal areas.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.234-237
• /
• 2007

Road networks are important geospatial databases for various GIS (Geographic Information System) applications. Road digital maps may contain geometric spatial errors due to human and scanning errors, but manually updating roads information is time consuming. In this paper, we developed a new road features updating methodology using from multispectral high-resolution satellite image and pre-existing vector map. The approach is based on initial seed point generation using line segment matching and a modified double snake algorithm. Firstly, we conducted line segment matching between the road vector data and the edges of image obtained by Canny operator. Then, the translated road data was used to initialize the seed points of the double snake model in order to refine the updating of road features. The double snake algorithm is composed of two open snake models which are evolving jointly to keep a parallel between them. In the proposed algorithm, a new energy term was added which behaved as a constraint. It forced the snake nodes not to be out of potential road pixels in multispectral image. The experiment was accomplished using a QuickBird pan-sharpened multispectral image and 1:5,000 digital road maps of Daejeon. We showed the feasibility of the approach by presenting results in this urban area.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.9
• /
• pp.692-699
• /
• 2003

A novel rotor speed estimation method using Model Reference Adaptive Control(MRAC) is proposed to improve the performance of a sensorless vector controller. In the proposed mettled, the stator current is used as the model variable for estimating the speed. In conventional MRAC methods, the relation between the two model errors and the speed estmation error is unclear. Yet, in the proposed method, the stator current error is represented as a function of the first degree for the error value in the speed estimation. Therefore, the proposed method can produce a fast speed estimation and is robust to the parameters error In addition, the proposed method of offers a considerable improvement in the performance of a sensorless vector controller at a low speed. The superiority of the proposed method is verified by simulation and experiment in a low speed region and at a zero-speed.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.938-942
• /
• 2007

신문 기사 및 상품 평은 특정 주제나 상품을 대상으로 하여 글쓴이의 감정과 의견이 잘 나타나 있는 대표적인 문서이다. 최근 여론 조사 및 상품 의견 조사 등 다양한 측면에서 대용량의 문서의 의미적 분류 및 분석이 요구되고 있다. 본 논문에서는 문서에 나타난 내용을 기준으로 문서가 나타내고 있는 감정을 긍정과 부정의 두 가지 범주로 분류하는 시스템을 구현한다. 문서 분류의 시작은 감정을 지닌 대표적인 종자 어휘(seed word)로부터 시작하며, 자질의 선정은 한국어 특징상 감정 및 감각을 표현하는 명사, 형용사, 부사, 동사를 대상으로 한다. 가중치 부여 방법은 한글 유의어 사전을 통해 종자 어휘의 의미를 확장하여 각각의 가중치를 책정한다. 단어 벡터로 표현된 입력 문서를 이진 분류기인 지지벡터 기계를 이용하여 문서에 나타난 감정을 판단하는 시스템을 구현하고 그 성능을 평가한다.

• Korean Journal of Plant Resources
• /
• v.10 no.2
• /
• pp.107-113
• /
• 1997

Transformants of White Clover(Trifolium repens L.) were efficiently produced from immature seed derived callus cocultivated with Agrobacterium twnefaciens LBA4404 harboring plant binary vector. pBI121, using acetosyringone. The mean frequencies of transformants on the two kanamycin-containing media were 16 to 19% when the immature seed-derived calli were infected with bacteria cultured in the presence of 100$\mu$M acetosyringone compared with 7% in media without acetosyringone. Transgenic white clover was subject to molecular analysis for integration into plant nuclear genome and expression of $\beta$-glucuronidase(GUS) gene. PCR and Northern blot analyses demonstrated that GUS gene was integrated into white clover nuclear genome and expressed into its mRNA. The expression of GUS gene into its protein was confirmed by spectrophotometric assay of GUS activity.

• Journal of Korean Society of Forest Science
• /
• v.112 no.2
• /
• pp.145-156
• /
• 2023

In this study, Fourier-transform near-infrared (FT-NIR) spectra of Korean red pine seeds stored at -18℃ and 4℃ for 18 years were analyzed. To develop seed-germination prediction models, the performance of seven machine learning methods, namely XGBoost, Boosted Tree, Bootstrap Forest, Neural Networks, Decision Tree, Support Vector Machine, PLS-DA, were compared. The predictive performance, assessed by accuracy, misclassification, and area under the curve (0.9722, 0.0278, and 0.9735 for XGBoost, and 0.9653, 0.0347, and 0.9647 for Boosted Tree), was better for the XGBoost and decision tree models when compared with other models. The 54 wave-number variables of the two models were of high relative importance in seed-germination prediction and were grouped into six spectral ranges (811~1,088 nm, 1,137~1,273 nm, 1,336~1,453 nm, 1,666~1,671 nm, 1,879~2,045 nm, and 2,058~2,409 nm) for aromatic amino acids, cellulose, lignin, starch, fatty acids, and moisture, respectively. Use of the NIR spectral data and two machine learning models developed in this study gave >96% accuracy for the prediction of pine-seed germination after long-term storage, indicating this approach could be useful for non-destructive viability testing of stored seed genetic resources.

• Korean Journal of Geomatics
• /
• v.5 no.1
• /
• pp.27-34
• /
• 2005

Unsupervised classification is an important area of research in image processing because supervised classification has the disadvantages such as long task-training time and high cost and low objectivity in training information. This paper focuses on unsupervised classification, which can extract ground object information with the minimum 'Spectral Angle Distance' operation on be behalf of 'Spectral Euclidian Distance' in the clustering process. Unlike previous studies, our algorithm uses the unit vector, not the spectral distance, to compute the cluster mean, and the Single-Pass algorithm automatically determines the seed points. Atmospheric correction for more accurate results was adapted on the Hyperion data and the results were analyzed. We applied the algorithm to the Hyperion and ETM+ data and compared the results with K-Means and the former USAM algorithm. From the result, USAM classified the water and dark forest area well and gave more accurate results than K-Means, so we believe that the 'Spectral Angle' can be one of the most accurate classifiers of not only multispectral images but hyperspectral images. And also the unit vector can be an efficient technique for characterizing the Remote Sensing data.