2017 4th International Conference on Systems and Informatics (ICSAI)最新文献_第6页

Terminological ontology learning based on LDA 基于LDA的术语本体学习

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248539

Zhijie Lin

引用次数: 1

Detection and segmentation of occluded vehicles based on symmetry analysis 基于对称性分析的被遮挡车辆检测与分割

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248385

Xiubo Ma, Xiongwei Sun

引用次数: 5

A multi-dimensional assessment system for technology readiness levels 技术准备水平的多维评估系统

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248394

Shanqing Li, Xiaozhao Xing, Shengmei Du

引用次数: 0

Adaptive calibration method based on state space model for eye gaze HCI system 基于状态空间模型的眼注视HCI系统自适应标定方法

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248276

Jiao Xu, Qijie Zhao

引用次数: 0

Smart class schedule with indoor positioning 智能课程表，室内定位

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248368

Zoltán Horváth, D. Jaisut, Adel Osztopanyi, Kitti Sugar

引用次数: 0

Level set method of cell image segmentation based on combinations of edge, region and prior information 基于边缘、区域和先验信息组合的水平集细胞图像分割方法

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248477

Yiyi Chen, Hanxu Sun, Huihua Yang, Xipeng Pan

引用次数: 2

Designing smart manufacturing workplace utilizing fuzzy screening approach 利用模糊筛选方法设计智能制造工作场所

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248363

S. Aly, M. Pelikán, I. Vrana

引用次数: 3

Mixed types of soft set and its extended model based decision making 基于决策的混合类型软集及其扩展模型

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248366

Ma Xiuqin, Hongwu Qin

引用次数: 1

Pancreatic cancer biomarker detection using recursive feature elimination based on Support Vector Machine and large margin distribution machine 基于支持向量机和大边际分布机的递归特征消除胰腺癌生物标志物检测

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248514

Yidan Lv, Yan Wang, Yongfei Tan, Wei Du, Keke Liu, Hao Wang

{"title":"Pancreatic cancer biomarker detection using recursive feature elimination based on Support Vector Machine and large margin distribution machine","authors":"Yidan Lv, Yan Wang, Yongfei Tan, Wei Du, Keke Liu, Hao Wang","doi":"10.1109/ICSAI.2017.8248514","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248514","url":null,"abstract":"Pancreatic cancer acts as one of the leading causes of cancer-connective deaths. Its five-year overall survival rate being reported is about 7.7% from 2006 to 2012 by the National Cancer Institute. One of the main causes for its poor prognosis is because its non-typical symptoms make early diagnosis very challenging. Therefore, a predominant strategy for early accurate detection and prognostication on pancreatic cancer is vital to the whole course of comprehensive therapy. In this research, we proposed a method which combined Recursive Feature Elimination (RFE) method based on Support Vector Machine (SVM) and Large Margin Distribution Machine (LDM) to identify potential biomarkers for pancreatic cancer. In our experiments, we have strengthened the process of RFE to achieve better performance. The dataset GSE15471 we adopted are from GEO database with 39 pairs of pancreatic ductal carcinoma and adjacent control pancreatic tissues. Through experiments, a panel of twelve genes was identified as biomarkers in pancreatic cancer with 91.28% classification accuracy. The universality of the candidate genes was examined on another dataset GSE28735 and the classification accuracy was higher than 80%. In addition, by using the SVM, LDM and BP classifiers, we compared the ordered feature sets generated by our proposed method with T-test, SVM-RFE and LDM-RFE, and the results indicated our proposed method obtained higher average classification accuracy.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131529463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Combining color feature for scale adaptive correlation filter tracker 结合颜色特征进行尺度自适应相关滤波跟踪

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248465

Cong Li, Cunyue Lu, Xun Zhao, Baomin Zhang, Hongyu Wang

{"title":"Combining color feature for scale adaptive correlation filter tracker","authors":"Cong Li, Cunyue Lu, Xun Zhao, Baomin Zhang, Hongyu Wang","doi":"10.1109/ICSAI.2017.8248465","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248465","url":null,"abstract":"In order to improve the robustness of correlation filtering(CF) tracker, and solve the problems that the traditional CF methods cannot overcome the change of the object scale and the color information was not used. A scale adaptive correlation filtering tracker based on color feature fusion is proposed. Firstly, we transform the target search area of the image from RGB color space to Lab color space, and then extract the three channel Lab color features of the search area. Secondly, we combine the color feature and HOG feature into multi-channel feature. The multi-channel correlation filter was employed to locate the center of the target. Finally, the target scale model is established by Lab color feature. Acquiring different scales image block from the target position at the current frame. We get the optimal target scale by comparing with the scale model. Experiments were performed on 35 public benchmark challenging color sequences and compared with other 5 tracking methods. The results show that our proposed approach outperforms state-of-the-art tracking methods, and has a real-time tracking speed of 66 frames/s.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121774573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2