http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Mining Frequent Sub-hypergraph in an Uncertain Hypergraph for Knowledge Transfer
Xing Wang,Bin-Xing Fang,Hui He,Hong-Li Zhang 보안공학연구지원센터 2015 International Journal of Database Theory and Appli Vol.8 No.4
The knowledge transfer learning can generalize across domains where the types of objects and variables are different. Previous studies ignored connectivity and creativity of domain knowledge. Thus, these studies just transfer knowledge from a source domain to a target domain that not effectively use the knowledge from other domains. We proposed a method, called Multi-domain second order knowledge integration (MSKI), for integrating to address this problem. We hybridize and create new knowledge, which is formalized into an uncertain hypergraph. Then, we proposed a method to mine frequent sub-hypergraph from the uncertain hypergraph (MFS-UHG). The frequent sub-hypergraphs are pivot knowledge, which has to be transferred with high priority. We embed the pivot knowledge in the progress of MLN structure learning. The experimental evaluation on four domain datasets shows that the MSKI outperforms state-of-the-art MLN-based transfer learning.
A Dependence Stability Bound based on the VC Dimension for Relational Classification
Xing Wang,Hui He,Bin-Xing Fang,Hong-Li Zhang 보안공학연구지원센터 2015 International Journal of Database Theory and Appli Vol.8 No.3
Relational classification (RC) is concerned with the application of statistical learning to relational data. RC models do not have improved stability to smooth the perturbations generated by variations in the correlation between the relational data. Therefore, few studies have attempted to derive a bound and develop a stability learning framework for RC models. To solve this problem, we derive a learning bound with a new measure dependence stability and a limited Vapnik–Chervonenkis (VC) dimension. Based on the learning bound, we then design a stable learning framework that serves as a guideline for the development of new learning algorithms for a broad class of RC models. Applying a Markov logic network on synthesized and real-world datasets, our experimental results demonstrate that our bound can be tight if the RC model has appropriate dependence stability and limited VC dimension and our learning framework increases the stability of RC models while reducing the deviation between empirical risk and true risk.
Data-driven prognostics method for turbofan engine degradation using hybrid deep neural network
Bin Xue,Zhong-bin Xu,Xing Huang,Peng-cheng Nie 대한기계학회 2021 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.35 No.12
Powerful sequence modeling capability for massive multi-sensor data enables deep-learning-based methods to obtain accurate remaining useful life (RUL) estimations. Hybrid neural networks, with learned representations based on various networks, have enhanced the prognostics accuracies than single networks. However, assembly strategies that are limited to either parallel or serial, and insufficient utilization of single networks restrict the development of hybrid networks for more complex problems. This paper proposes a datadriven method using hybrid multi-scale convolutional neural network (MSCNN) and bidirectional long short-term memory (BLSTM) network (namely HMCB network) for RUL estimation. The framework of the network includes two parallel paths. One is composed of MSCNN and BLSTM in serial and the other is a BLSTM path. The HMCB network integrates the merits of multi-scale spatial feature extraction of MSCNN and sequence learning capacity of BLSTM. Validated by C-MAPSS dataset, the HMCB network demonstrates noticeably higher prognostic accuracy than other state-of-the-art methods.
Liu, Xing-Long,Wang, Bin,Zhao, Lin-Bo,Jia, Zhen-Yu,Shi, Hai-Bin,Liu, Sheng The Korean Neurosurgical Society 2022 Journal of Korean neurosurgical society Vol.65 No.4
Objective : To evaluate the safety and efficacy of an overlapped stenting-assisted coiling technique in treating vertebral artery dissecting aneurysm (VADA) via Low-profile Visualized Intraluminal Support (LVIS) stent-within-Neuroform EZ stent. Methods : From January 2017 to June 2019, 18 consecutive patients with VADAs (ruptured : unruptured=5 : 13) were treated with the overlapping stents assisted-coiling technique in our center. The overlapping manner was a Neuroform EZ stent being deployed first, followed by LVIS stents placement using the 'shelf' technique. The patients' clinical characteristics, technical feasibility and safety, and immediate and follow-up angiographic results were retrospectively reviewed. Results : Seventeen (94.4%) procedures were technically successful with an exact deployment of the stents and patent parent or perforator arteries. The immediate angiographies after procedure confirmed Raymond class I, II, and III occlusion of VADAs were in 12 (66.7%), two (11.1%), and four cases (22.2%), respectively. Post-procedural complications developed in one patient (5.6%) with minor brainstem infarctions, which resulted from an in-stent thrombosis during the procedure. Angiographic follow-up at 5.7 months (range 3 to 9 months) demonstrated Raymond class I and II occlusion were in all cases (100%). The modified Rankin Scale scores at 21.3 months (range 15 to 42 months) 0-2 in 17 cases (94.4%) and three in one case (5.6%). Conclusion : Overlapping stents via LVIS stent-within-Neuroform EZ stent combined with coiling is safe and effective for patients with VADA in the midterm results.
Zhang, Chun-Xing,Liang, Long,Zhang, Bin,Chen, Wen-Bo,Liu, Hong-Jun,Liu, Chun-Ling,Zhou, Zheng-Gen,Liang, Chang-Hong,Zhang, Shui-Xing Asian Pacific Journal of Cancer Prevention 2015 Asian Pacific journal of cancer prevention Vol.16 No.8
Background: This study was conducted to analyze positron emission tomography (PET) / computed tomography (CT) and magnetic resonance imaging (MRI) performance with oropharyngeal non-Hodgkin's lymphoma (ONHL).Materials and Methods: The complete image data of 30 ONHL cases were analyzed, all patients were performed PET / CT and MRI examination before the treatment, with the time interval of these two inspections not exceeding 14 days. The distribution, morphology, MRI signal characteristics, enhancement feature, standardized uptake value (SUV) max value and lymph node metastasis way of the lesions were analyzed. Results: Among the 30 cases, 23 cases were derived from the B-cell (76.7%), 5 cases were derived from the peripheral T cells (16.7%) and 2 cases were derived from the NK/T cells (6.7%). 19 cases exhibited the palatine tonsil involvement (63.3%). As for the lesion appearance, 10 cases appeared as mass, 8 cases were the diffused type and 12 cases were the mixed type. 25 cases exhibited the SUVmax value of PET / CT primary lesions as 11 or more (83.3%). MRI showed that all patients exhibited various degrees of parapharyngeal side-compressed narrowing, but MRI still exhibited the high-signal fat, and the oropharyngeal mucosa was intact. 25 cases were associated with the neck lymph node metastasis, among who 22 cases had no necrosis in the metastatic lymph nodes, while the rest 3 cases exhibited the central necrosis in the metastatic lymph nodes. Conclusions: PET / CT and MRI have important value in diagnosing and determining the lesion extent of ONHL.
Study on Corner Reflectors Identification in Highway Deformation Monitoring
Xue Min Xing,De Bao Wen,Fang Bin Zhou 보안공학연구지원센터 2014 International Journal of Multimedia and Ubiquitous Vol.9 No.12
CRInSAR is a newly developed technique to monitor ground deformation. In CRInSAR algorithm, the identification of Corner Reflectors in SAR images is necessary. Due to the uncertainty of traditional identification method, a new method based on the intensity and correlation coefficient of each CR candidates in SAR images is presented. The method has been successfully used to determine the locations of 11 CRs installed along a highway in six SAR images over the study area. The results show that the identification accuracy of the new method is about 1 pixel. It is effective and reliable especially in the area with lots of lightspots around the CR points. The method proposed can play important role in the highway deformation monitoring within CRInSAR algorithm.
Hong, Guo-Bin,Zhou, Jing-Xing,Sun, Hua-Bin,Li, Chun-Yang,Song, Li-Qing Asian Pacific Journal of Cancer Prevention 2012 Asian Pacific journal of cancer prevention Vol.13 No.6
Purpose: Pancreatic carcinoma is one of the most malignant tumors of the alimentary system, with relatively high incidence rates. The purpose of this study was to assess the efficacy and safety of two regimens for advanced pancreatic carcinoma: continuous transarterial infusion versus systemic venous chemotherapy with gemcitabine and 5-fluorouracil. Methods: Of the 48 patients with advanced pancreatic carcinoma receiving chemotherapy with gemcitabine and 5-fluorouracil, 24 received the selective transarterial infusion, and 24 the systemic chemotherapy. For the continuous transarterial infusion group (experimental group), all patients received gemcitabine 1000 mg/$m^2$, given by 30-minute transarterial infusion, on day 1 of a 4-week cycle for 2 cycles, and a dose of 600 mg/$m^2$ 5-fluorouracil was infused on days 1~5 of a 4-week cycle for 2 cycles. For the systemic venous group (control group), gemcitabine and 5-fluorouracil were infused through a peripheral vein, a dose of 1000 mg/$m^2$ gemcitabine being administrated over 30 min on days 1 and 8 of a 4-week cycle for 2 cycles, and a dose of 600 mg/$m^2$ 5-fluorouracil was infused on days 1~5 of a 4-week cycle for 2 cycles. The effectiveness and safety were evaluated after 2 cyclesaccording to WHO criteria. Results:The objective effective rate in transarterial group was 33.3% versus 25% in the systemic group, the difference not being significant (P=0.626). Clinical benefit rates(CBR) in the transarterial and systemic groups were 83.3% and 58.3%, respectively (P=0.014). The means and medians for survival time in transarterial group were higher than those of the systemic group (P < 0.005). at the same time, the adverse effects did not significantly differ between the two groups (P > 0.05). Conclusion: Continuous transarterial infusion chemotherapy with gemcitabine and 5-fluorouracil could improve clinical benefit rate and survival time of patients with advanced pancreatic carcinoma, compared with systemic venous chemotherapy. Since adverse effects were limited in the transarterial group, the regimen of continuous transarterial infusion chemotherapy can be used more extensively in clinical practice. A CT and MRI conventional sequence can be used for efficacy evaluation after chemotherapy in pancreatic carcinoma.