• 한국전자거래학회지
• /
• 제26권3호
• /
• pp.97-117
• /
• 2021

정기예금 가입 여부 예측은 은행의 대표적인 금융 마케팅 중 하나로, 은행은 다양한 고객 정보를 활용하여 예측 모델을 구성할 수 있다. 정기예금 가입 여부의 분류 정확도를 향상하기 위해, 많은 연구에서 기계학습 기법들을 이용하여 분류 모델들을 개발하였다. 하지만, 이러한 모델들이 만족스러운 성능을 보일지라도 모델의 의사결정 과정에 대한 근거가 적절하게 설명되지 않는다면 산업에서 활용하기가 쉽지 않다. 이러한 문제점을 해결하기 위해, 본 논문은 설명 가능한 정기예금 가입 여부 예측 기법을 제안한다. 먼저, 테이블 형식에서 우수한 성능을 도출하는 의사결정 나무 기반 앙상블 학습 기법인 랜덤 포레스트, GBM, XGBoost, LightGBM을 이용하여 분류 모델들을 개발하고, 10겹 교차검증을 통해 모델들의 분류 성능을 심층 분석한다. 다음으로, 가장 우수한 성능을 도출하는 모델에 설명 가능한 인공지능 기법인 SHAP을 적용하여 고객 정보의 영향도와 의사결정 과정 등을 해석할 수 있는 근거를 제공한다. 제안한 기법의 실용성과 타당성을 입증하기 위해, Kaggle에서 제공한 은행 마케팅 데이터 셋을 대상으로 모의실험을 진행하였으며, 데이터 셋 구성에 따라 GBM과 LightGBM 모델에 SHAP을 각기 적용하여 설명 가능한 정기예금 가입 여부를 위한 분석 및 시각화를 수행하였다.

• Molecules and Cells
• /
• 제37권7호
• /
• pp.547-553
• /
• 2014

Glioblastoma multiforme (GBM) is one of the most common brain malignancies and has a very poor prognosis. Recent evidence suggests that the presence of cancer stem cells (CSC) in GBM and the rare CSC subpopulation that is resistant to chemotherapy may be responsible for the treatment failure and unfavorable prognosis of GBM. A garlic-derived compound, Z-ajoene, has shown a range of biological activities, including anti-proliferative effects on several cancers. Here, we demonstrated for the first time that Z-ajoene specifically inhibits the growth of the GBM CSC population. CSC sphere-forming inhibition was achieved at a concentration that did not exhibit a cytotoxic effect in regular cell culture conditions. The specificity of this inhibitory effect on the CSC population was confirmed by detecting CSC cell surface marker CD133 expression and biochemical marker ALDH activity. In addition, stem cell-related mRNA profiling and real-time PCR revealed the differential expression of CSC-specific genes, including Notch, Wnt, and Hedgehog, upon treatment with Z-ajoene. A proteomic approach, i.e., reverse-phase protein array (RPPA) and Western blot analysis, showed decreased SMAD4, p-AKT, 14.3.3 and FOXO3A expression. The protein interaction map (http://string-db.org/) of the identified molecules suggested that the AKT, ERK/p38 and $TGF{\beta}$ signaling pathways are key mediators of Z-ajoene's action, which affects the transcriptional network that includes FOXO3A. These biological and bioinformatic analyses collectively demonstrate that Z-ajoene is a potential candidate for the treatment of GBM by specifically targeting GBM CSCs. We also show how this systemic approach strengthens the identification of new therapeutic agents that target CSCs.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권11호
• /
• pp.4907-4911
• /
• 2016

Glioblastoma multiforme (GBM) is the most aggressive of the gliomas, a collection of tumors arising from glia in the central nervous system. Possible associations between the human cytomegalovirus (HCMV) and the JC virus with GBM are now attracting interest. Our present aim was to investigate the prevalence of the two viruses in Iranian patients from Kerman's cities in the south of Iran. In addition, the expression rates of pp65, large T antigen and p53 proteins were assessed and their relation with GBM evaluated using reverse transcription real time PCR (rReal Time PCR). A total of 199 patients with GBM cancer were enrolled, with $mean{\pm}SD$ ages of $50.0{\pm}19.5$ and $50.7{\pm}19.6$ years for males and females, respectively. The P53 rate was dramatically low suggesting an aetiological role,. Large T antigen expression was found in JC positive samples, while the PP65 antigen was observed in patients positive for CMV and JC. HCMV products and JC virus with oncogenic potential may induce the development of various tumors including glioblastomas. The JC virus produces an early gene product, T-antigen, which has the ability to associate with and functionally inactivate well-studied tumor suppressor proteins including p53 and pRB.

• Journal of Korean Neurosurgical Society
• /
• 제43권4호
• /
• pp.194-197
• /
• 2008

Primary cerebellar glioblastoma multiforme (GBM) is a rare tumor in adults that accounts for just 1% of all cases of GBM. Due to their rarity, cerebellar GBMs are not yet completely understood about the pathogenesis and the prognosis. Here, we present a case of GBM in a 69-year-old man. Neurologic examination revealed the presence of cerebellar signs. Magnetic resonance imaging (MRI) showed a 4.5${\times}$3.6 cm-sized, ill-defined, heterogeneously enhancing mass in the left cerebellum and two patchy hyperintense lesions in the right cerebellum with minimal enhancement. After operation, glioblastoma was histologically confrimed. Postoperative radiotherapy with concomittent and adjuvant temozolomide chemotherapy was subsequently followed. Here, a case of unusual GBM in the cerebellum is reported with review of literature regarding the pathogenesis, the differential diagnosis and prognosis. There was no evidence of recurrence during postoperative one year. This patient showed a good prognosis in spite of the multiple lesions.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권14호
• /
• pp.6129-6133
• /
• 2015

miR-129-2 is frequently downregulated in multiple cancers. However, how it is silenced in cancers remains unclear. Here we investigated the expression profile and potential biological function of miR-129-2 in glioblastoma (GBM), the most common and lethal form of brain tumors in adults. We showed that miR-129-2 is lost in GBM patient specimens and cultured cell lines. miR-129-2 expression could be restored upon treatment with a histone deadetylase inhibitor (trichostatin A) but not a DNA methylation inhibitor (5-Aza-2'-deoxycytidine), and more profound effect was observed with the treatment of these two drugs in combination. Furthermore, forced expression of miR-129-2 repressed the expression of major oncogenic genes such as PDGFRa and Foxp1 in GBMs. Consistently, expression of miR-129-2 significantly inhibits GBM cell proliferation in vitro. These results reveal that miR-129-2 is epigenetically regulated and functions as a tumor suppressor gene in GBMs, suggesting it may serve as a potential therapeutic target for GBM treatment.

• 한국환경과학회지
• /
• 제28권1호
• /
• pp.125-135
• /
• 2019

For the purposes of enhancing usability of Numerical Weather Prediction (NWP), the quantitative precipitation prediction scheme by machine learning has been proposed. In this study, heavy rainfall was corrected for by utilizing rainfall predictors from LENS and Radar from 2017 to 2018, as well as machine learning tools LightGBM and XGBoost. The results were analyzed using Mean Absolute Error (MAE), Normalized Peak Error (NPE), and Peak Timing Error (PTE) for rainfall corrected through machine learning. Machine learning results (i.e. using LightGBM and XGBoost) showed improvements in the overall correction of rainfall and maximum rainfall compared to LENS. For example, the MAE of case 5 was found to be 24.252 using LENS, 11.564 using LightGBM, and 11.693 using XGBoost, showing excellent error improvement in machine learning results. This rainfall correction technique can provide hydrologically meaningful rainfall information such as predictions of flooding. Future research on the interpretation of various hydrologic processes using machine learning is necessary.

• Computers and Concrete
• /
• 제33권2호
• /
• pp.137-145
• /
• 2024

The technique of experimentally determining concrete's compressive strength for a given mix design is time-consuming and difficult. The goal of the current work is to propose a best working predictive model based on different machine learning algorithms such as Gradient Boosting Machine (GBM), Stacked Ensemble (SE), Distributed Random Forest (DRF), Extremely Randomized Trees (XRT), Generalized Linear Model (GLM), and Deep Learning (DL) that can forecast the compressive strength of ternary geopolymer concrete mix without carrying out any experimental procedure. A geopolymer mix uses supplementary cementitious materials obtained as industrial by-products instead of cement. The input variables used for assessing the best machine learning algorithm not only include individual ingredient quantities, but molarity of the alkali activator and age of testing as well. Myriad statistical parameters used to measure the effectiveness of the models in forecasting the compressive strength of ternary geopolymer concrete mix, it has been found that GBM performs better than all other algorithms. A sensitivity analysis carried out towards the end of the study suggests that GBM model predicts results close to the experimental conditions with an accuracy between 95.6 % to 98.2 % for testing and training datasets.

• Journal of Korean Neurosurgical Society
• /
• 제58권5호
• /
• pp.426-431
• /
• 2015

Objective : The purpose of this study was to evaluate the clinical efficacy of continuous low-dose temozolomide (TMZ) chemotherapy for recurrent and TMZ-refractory glioblastoma multiforme (GBM) and to study the relationship between its efficacy and microvessel density within the tumor. Methods : Thirty patients who had recurrent GBM following Stupp's regimen received TMZ daily at $50mg/m^2/day$ until tumor progression between 2007 and 2013. The median duration of continuous low-dose TMZ administration was 8 weeks (range, 2-64). Results : The median progression-free survival (PFS) of continuous low-dose TMZ therapy was 2 months (range, 0.5-16). At 6 months, PFS was 20%. The median overall survival (OS) from the start of this therapy to death was 6 months (95% CI : 5.1-6.9). Microvessel density of recurrent tumor tissues obtained by reoperation of 17 patients was $22.7{\pm}24.1/mm^2$ (mean${\pm}$standard deviation), and this was lower than that of the initial tumor ($61.4{\pm}32.7/mm^2$) (p-value=0.001). It suggests that standard TMZ-chemoradiotherapy reduces the microvessel density within GBM and that recurrences develop in tumor cells with low metabolic burden. The efficacy of continuous low-dose TMZ could not be expected in recurrent GBM cells in poor angiogenic environments. Conclusion : The efficacy of continuous low-dose TMZ chemotherapy is marginal. This study suggests the need to develop further treatment strategies for recurrent and TMZ-refractory GBM.

• Nutrition Research and Practice
• /
• 제10권4호
• /
• pp.393-397
• /
• 2016

BACKGROUND/OBJECFTIVES: Artemisinin, a natural product isolated from Gaeddongssuk (artemisia annua L.) and its main active derivative, dihydroartemisinin (DHA), have long been used as antimalarial drugs. Recent studies reported that artemisinin is efficacious for curing diseases, including cancers, and for improving the immune system. Many researchers have shown the therapeutic effects of artemisinin on tumors such as breast cancer, liver cancer and kidney cancer, but there is still insufficient data regarding glioblastoma (GBM). Glioblastoma accounts for 12-15% of brain cancer, and the median survival is less than a year, despite medical treatments such as surgery, radiation therapy, and chemotherapy. In this study, we investigated the anti-cancer effects of DHA and transferrin against glioblastoma (glioblastoma multiforme, GBM). MATERIALS/METHODS: This study was performed through in vitro experiments using C6 cells. The toxicity dependence of DHA and transferrin (TF) on time and concentration was analyzed by MTT assay and cell cycle assay. Observations of cellular morphology were recorded with an optical microscope and color digital camera. The anti-cancer mechanism of DHA and TF against GBM were studied by flow cytometry with Annexin V and caspase 3/7. RESULTS: MTT assay revealed that TF enhanced the cytotoxicity of DHA against C6 cells. An Annexin V immune-precipitation assay showed that the percentages of apoptosis of cells treated with TF, DHA alone, DHA in combination with TF, and the control group were $7.15{\pm}4.15%$, $34.3{\pm}5.15%$, $66.42{\pm}5.98%$, and $1.2{\pm}0.15%$, respectively. The results of the Annexin V assay were consistent with those of the MTT assay. DHA induced apoptosis in C6 cells through DNA damage, and TF enhanced the effects of DHA. CONCLUSION: The results of this study demonstrated that DHA, the derivative of the active ingredient in Gaeddongssuk, is effective against GBM, apparently via inhibition of cancer cell proliferation by a pharmacological effect. The role of transferrin as an allosteric activator in the GBM therapeutic efficacy of DHA was also confirmed.

• 한국융합학회논문지
• /
• 제9권1호
• /
• pp.9-20
• /
• 2018

본 논문은 법인의 전기 사내유보가 당기 연구개발 투자에 미치는 영향을 분석함으로써 미환류 소득세제가 어느 정도 효과를 거두고 있는지 실증분석 하고자 하였으며 추가로 교육훈련비를 조절변수로 사용하여 정부정책의 유효성도 알아보고자 하였다. 또한 GBM 모델을 이용하여 그 효과를 한 번 더 살펴보았다. 연구 결과 교육훈련비의 조절효과와 매개효과 모두 유의미한 효과가 있는 것으로 판단할 수 있었고 모형1, 모형2, 모형3에서 모두 이자비용과 복리후생비 변수가 99% 수준에서 유의미함을 확인할 수 있었던 반면 전기유보율은 모든 모형에서 유의미하지 않은 결과를 보여주었다. 이를 통해 정부의 미환류 소득세제 도입 취지인 사내 유보금 과세를 추진하면 기업은 그 재원으로 물적 및 인적 투자를 늘릴 것이라는 가정은 아직 그 효과가 미미한 것으로 사료된다. 추가분석으로 실시한 융합 차원에서의 GBM 모형에서도 비슷한 결과가 도출되었다. 앞으로의 과제는 미환류 소득세제의 시행기간인 3년간(2015~2017)의 시계열 분석을 통하여 정부정책의 효과를 살펴볼 필요가 있다.