2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)最新文献_第4页

Improving object detection accuracy with region and regression based deep CNNs 基于区域和回归的深度cnn提高目标检测精度

2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2017-12-01 DOI: 10.1109/SPAC.2017.8304297

Liang Qu, Shengke Wang, Na Yang, Long Chen, Lu Liu, Xiaoyan Zhang, Feng Gao, Junyu Dong

{"title":"Improving object detection accuracy with region and regression based deep CNNs","authors":"Liang Qu, Shengke Wang, Na Yang, Long Chen, Lu Liu, Xiaoyan Zhang, Feng Gao, Junyu Dong","doi":"10.1109/SPAC.2017.8304297","DOIUrl":"https://doi.org/10.1109/SPAC.2017.8304297","url":null,"abstract":"Object detection has made great improvements in convolutional neural networks (CNNs), which is the high-capacity visual model that yields hierarchies of discriminative features. Object detection based on CNNs is in general divided into two aspects: region based detection and regression based detection. In this paper, we aim at further advancing object detection performance by properly utilizing the complementary results of those two streams. By investigating errors of several previous state-of-the-art methods about the two streams, we discover that those detection results of two general streams are complementary in object recognition and localization. Region based methods achieve high recall but simultaneously struggle with localization problems, while regression based methods make less localization errors by iteratively regressing the object to target localization. Driven by these observations, we propose two kinds of fusion paradigms to combine the results of those two streams. One is direct fusion utilizing the complementary results of those two streams and adopting non-maximal suppression (NMS) and voting operation to make full use of the results generated by two streams. In addition, considering direct fusion may compromise the original performance of object detections, we also propose another method, modifies voting operation that just refines the box coordinate without having any other impact on the original detections and further boosts the performance by an adding operation. Extensive experiments show that our two ensemble paradigms both boost the state-of-the-art results on Pascal VOC dataset.","PeriodicalId":161647,"journal":{"name":"2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125069206","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

Self-paced learning for multi-modal fusion for alzheimer's disease diagnosis 多模态融合自定进度学习在阿尔茨海默病诊断中的应用

2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2017-12-01 DOI: 10.1109/SPAC.2017.8304253

Ning Yuan, D. Guan, Qi Zhu, Weiwei Yuan

{"title":"Self-paced learning for multi-modal fusion for alzheimer's disease diagnosis","authors":"Ning Yuan, D. Guan, Qi Zhu, Weiwei Yuan","doi":"10.1109/SPAC.2017.8304253","DOIUrl":"https://doi.org/10.1109/SPAC.2017.8304253","url":null,"abstract":"Alzheimer's disease (AD) is a sort of nervous system disease, and it may cause amnesia and executive dysfunction etc. AD seriously reduces the quality of people's life, so it is very important to improve the diagnosis accuracy of AD in its prodromal stage, mild cognitive impairment (MCI). In recent years, multi-modal methods had been proven to be effective in prediction of AD and MCI by utilizing the complementary information across different modalities in AD data. In this paper, we propose self-paced sample weighting based low-rank representation (SPLRR) to explore the latent correlation across different modalities. By imposing rank minimization on different modalities regression coefficients, we can capture the intrinsic structure among modalities. Meanwhile, we introduce self-paced learning to allot the corresponding weight to samples based on the contribution of each sample to the label in the current modality. Experiments on the Alzheimer's disease Neuroimaging Initiative (ADNI) database show that the SPLRR model obtains the better classification performance than the state-of-the-art methods.","PeriodicalId":161647,"journal":{"name":"2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125555916","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: 1

The analysis on college students' physical fitness testing data — two cases study 大学生体质测试数据分析——两个案例研究

2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2017-12-01 DOI: 10.1109/SPAC.2017.8304285

Yi Mou, Long Zhou, Weizhen Chen, Xu Zhao, Yang Liu, Chao Yang

{"title":"The analysis on college students' physical fitness testing data — two cases study","authors":"Yi Mou, Long Zhou, Weizhen Chen, Xu Zhao, Yang Liu, Chao Yang","doi":"10.1109/SPAC.2017.8304285","DOIUrl":"https://doi.org/10.1109/SPAC.2017.8304285","url":null,"abstract":"College students physical fitness test is an important means for physical fitness evaluation. The test includes body mass index(BMI), lung's capacity, 50 and 1000(male)/800(female) meters run, standing long jump, sit and reach, pull-up(male)/sit-up(female). Final result is weighted sum of the seven items. According to national standard of physical fitness for students, the weights are 15%, 15%, 20%, 10%, 20%, 10%, 10%, respectively. We can regard it as a dimensionality reduction process, which reduces the original data to one dimension. Using fixed weights, the results will neglect differences among students in different areas. Therefore, it is important to learn the weights from the data. The learned weights can not only give students a reasonable evaluation of physical ability, but also reflect the characteristics of the samples. In this paper, we present a learning model for the weights of students' physical fitness tests. The solution algorithm is also presented. We then employ proposed method to analyze two data sets, The results demonstrate that the model presented in this paper has advantages for college students physical fitness test data analysis.","PeriodicalId":161647,"journal":{"name":"2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121210337","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: 3

Leveraging the trade-off between accuracy and interpretability in a hybrid intelligent system 在混合智能系统中利用准确性和可解释性之间的权衡

2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2017-12-01 DOI: 10.1109/SPAC.2017.8304250

D. Wang, Hiok Chai Quek, A. Tan, Chun-Hui Miao, G. Ng, You Zhou

{"title":"Leveraging the trade-off between accuracy and interpretability in a hybrid intelligent system","authors":"D. Wang, Hiok Chai Quek, A. Tan, Chun-Hui Miao, G. Ng, You Zhou","doi":"10.1109/SPAC.2017.8304250","DOIUrl":"https://doi.org/10.1109/SPAC.2017.8304250","url":null,"abstract":"Neural Fuzzy Inference System (NFIS) is a widely adopted paradigm to develop a data-driven learning system. This hybrid system has been widely adopted due to its accurate reasoning procedure and comprehensible inference rules. Although most NFISs primarily focus on accuracy, we have observed an ever increasing demand on improving the interpretability of NFISs and other types of machine learning systems. In this paper, we illustrate how we leverage the trade-off between accuracy and interpretability in an NFIS called Genetic Algorithm and Rough Set Incorporated Neural Fuzzy Inference System (GARSINFIS). In a nutshell, GARSINFIS self-organizes its network structure with a small set of control parameters and constraints. Moreover, its autonomously generated inference rule base tries to achieve higher interpretability without sacrificing accuracy. Furthermore, we demonstrate different configuration options of GARSINFIS using well-known benchmarking datasets. The performance of GARSINFIS on both accuracy and interpretability is shown to be encouraging when compared against other decision tree, Bayesian, neural and neural fuzzy models.","PeriodicalId":161647,"journal":{"name":"2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122281028","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: 3

Fusion of probabilistic collaborative and sparse representation for robust image classification 融合概率协同与稀疏表示的鲁棒图像分类

2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2017-12-01 DOI: 10.1109/SPAC.2017.8304347

Zhangdan Chi, Shaoning Zeng, Jianping Gou

引用次数: 0

Gradient boosting model for unbalanced quantitative mass spectra quality assessment 非平衡质谱定量质量评价的梯度增强模型

2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2017-12-01 DOI: 10.1109/SPAC.2017.8304311

Long Chen, T. Zhang, Tianjun Li

引用次数: 5

Humanoid robot localization based on hybrid map 基于混合地图的仿人机器人定位

2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2017-12-01 DOI: 10.1109/SPAC.2017.8304331

Xiandong Xu, B. Hong, Yi Guan

引用次数: 6

Diversified shared latent structure based localization for blind persons 基于多元共享潜结构的盲人定位

2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2017-12-01 DOI: 10.1109/SPAC.2017.8304284

Yujin Wang, Dapeng Tao, Weifeng Liu

引用次数: 3

Research and implementation of parallel Lane detection algorithm based on GPU 基于GPU的并行车道检测算法的研究与实现

2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2017-12-01 DOI: 10.1109/SPAC.2017.8304303

Ying Xu, Bin Fang, X. Wu, Weibin Yang

引用次数: 0

Robust principal component analysis via joint ℓ2,1-norms minimization 基于联合最小化的鲁棒主成分分析

2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) Pub Date : 2017-12-01 DOI: 10.1109/SPAC.2017.8304243

Shuangyan Yi, Zhenyu He, Wei-Guo Yang

{"title":"Robust principal component analysis via joint ℓ2,1-norms minimization","authors":"Shuangyan Yi, Zhenyu He, Wei-Guo Yang","doi":"10.1109/SPAC.2017.8304243","DOIUrl":"https://doi.org/10.1109/SPAC.2017.8304243","url":null,"abstract":"Principal Component Analysis (PCA) is the most widely used unsupervised subspace learning method, and lots of its variants have been developed. With so many proposed PCA-like methods, it is still not clear that which features are better or worse for principal components, especially when the data suffers from outliers. To this end, we propose Robust Principal Component Analysis via joint ℓ2,1-norms minimization, which provides new insights into two crucial issues of PCA: feature selection and robustness to outliers. Unlike other PCA-like methods, the proposed method is able to select effective features for reconstruction by using the ℓ2,1-norm regularization term. More specific, we first use a ℓ2,1-norm based transformation matrix to select effective features that can effectively characterize key components (e.g., the eyes and the nose in a face image), and then use an orthogonal transformation matrix to recover the original data from the selected data representation. In this way, the key components can be well recovered by using the effective features selected by a learned transformation matrix. On the other hand, we also impose ℓ2,1-norm on a loss term to select clean samples to recover its same class samples but with outliers. A simple yet effective optimization algorithm is proposed to solve the resulting optimization problem. Experiments on six datasets demonstrate the effectiveness of the proposed method.","PeriodicalId":161647,"journal":{"name":"2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132585302","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: 4