Because the big data industry holds a significant position nowadays, Meta-Data has been adopted rapidly in various fields. In this paper, we introduce a model that exploits Meta-Data consisting of ...numerous production data to extract features using a pretrained deep learning model with image and text information. Thus, we can build a relational model between the production data to realize a recommendation system. Regarding the dataset, we determined that combining both image and text data is better than using one type of data to achieve a more accurate prediction from the relational model. Concerning the condition of two mixed languages (English and Korean), the method produces a satisfactory result. According to the relational model of the two products, we can design a recommendation system that suggests products that would be of interest to consumers. KCI Citation Count: 0
Object categorization is a hot issue of an image mining. Contextual information between objects is one of the important semantic knowledge of an image. However, the previous researches for an object ...categorization have not made full use of the contextual information, especially the spatial relations between objects. In addition, the object categorization methods, which generally use the probabilistic graphical models to implement the incorporation of contextual information with appearance of objects, are almost inevitable to evaluate the intractable partition function for normalization. In this work, we introduced fully-connected fuzzy spatial relations including directional, distance and topological relations between object regions, so the spatial relational information could be fully utilized. Then, the spatial relations were considered as well as co-occurrence and appearance of objects by using energy-based model, where the energy function was defined as the region-object association potential and the configuration potential of objects. Minimizing the energy function of whole image arrangement, we obtained the optimal label set about the image regions and addressed the evaluation of intractable partition function in conditional random fields. Experimental results show the validity and reliability of this proposed method.
선형가속기의 선량율에 따른 쐐기필터의 선량분포 권태형; Taehyeong Gwon; 김승욱 ...
Journal of the Korean Society of Radiology,
08/2015, Letnik:
9, Številka:
5
Journal Article
Odprti dostop
이 연구는 금속쐐기필터를 대신하여 동적쐐기필터를 사용할 수 있을지에 대한 적정성 평가에 관한 것이다. 선형가속기에서 발생되는 엑스선 에너지는 6 MV, 10 MV로 상용화되어있다. 금속쐐기필터의 15°, 30°, 45°, 60°에 각각 100, 200, 300, 400, 500, 600 선량율(MU/min)로 48번 조사하였고, 동적쐐기필터와의 비교를 ...위해 같은 조건으로 총 96번 조사하였다. 측정조건은 선원필름간 거리 100cm, 조사면 10×10cm 로 측정하였다. 현상된 필름을 스캔하여 선량분석프로그램으로 교정 후 분석하였고, 표준편차를 구해 선량율을 비교하였다. 동적쐐기필터는 선량, 산란선 및 치료시간을 감소시키며, 환자에 조사되는 선량이 적어 매우 유용하다. 동일한 조건에서 선량율에 따른 오차는 연관성이 없으므로 환자의 상황에 따라 고선량율의 치료를 사용하는 것도 가능할 것으로 생각된다.
This study is aimed at assessing whether dynamic wedge filters are appropriate to be used instead of physical wedge filters. The X-ray energy generated from linear accelerator is commercialize 6 MV and 10 MV. 15°, 30°, 45°, and 60° of physical wedge filter was irradiated by dose rate 100, 200, 300, 400, 500, and 600 MU/min for each angle and for comparison with a dynamic wedge filter, irradiate 96 times under the same conditions. The measurement conditions are as 100 ㎝ source-film distance and 10 × 10 ㎝ irradiated surface. A developed film was scanned and analyzed after a calibration through a dose analysis program and the dose rate was compared after calculating the standard deviation. Dynamic wedge filters make dose, scattered rays and treatment time reduced and very useful due to less irradiated doses to patients. The errors at each dose rate under the same conditions were irrelevant. Thus, treatment based on a high dose rate depending on the patient is expected to be feasible.