A5071448105- Studies on Chitinases and Chitosanases
- Imbalanced Data Classification Techniques
- Artificial Intelligence in Healthcare
- Protein Hydrolysis and Bioactive Peptides
- Nematode management and characterization studies
- Enzyme Production and Characterization
- Brain Tumor Detection and Classification
- Advanced Graph Neural Networks
- Microbial Metabolites in Food Biotechnology
Kangwon National University
2014
Insurance companies have focused on medicare fraud detection to reduce financial losses and reputational harm because causes tens of billions dollars in damage annually. This study demonstrates that can be significantly enhanced by introducing graph analysis with considering the relationships among medical providers, beneficiaries, physicians. We use open-source tabular datasets containing beneficiary information, inpatient claims, outpatient indications about potential fraudulent providers....
This study demonstrates that the performance of Medicare fraud detection models can be improved by applying graph neural networks to graph-structured datasets. Tens billions dollars are lost yearly. Therefore, insurance companies constantly attempt enhance alleviate economic losses and reputational damage. While traditional rule-based or machine learning have been extensively studied for detection, has used in very few studies. Thus, a model applies GraphSAGE algorithm, network, datasets...
진균류의 세포벽은 다양한 결합의 글루칸과 키틴질로 구성되었으며 이들의 생활사 전체에 해당하는 균사생장과 분화과정에서 키틴질 분해효소(chitinase)를 생성한다. 먹물버섯의 하나인 Coprinellus congregatus는 전 동안 최소 2종 이상의 chitinase를 Chi1은 균사시기부터 버섯의 자가분해 시기까지 고르게 생성되며, chitinase 2는 버섯 시기에 다량 생성된다. Chi1의 cDNA 유전자를 Pichia pastoris의 발현벡터의 pPICZB 벡터의 c-myc과 6x Histidine tag을 포함하는 Chi1 재조합 단백질 발현벡터를 구축하고 이를 발현시킨 후, tag에 의한 affinity chromatography 방법으로 단백질을 정제하였다. 정제된 endochitinase의 기질인 4-nitrophenyl N,N',N"-triacetyl-<TEX>${\beta}$</TEX>-D-chitotrioside에 대하여 활성을 보였다. 기질로...