检索结果-内蒙古大学图书馆

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Xiao Han Hongpeng Wang Chongshan Fan Yaojing Li Research Laboratory of Machine Learning and Pervasive Computing Nankai University Tianjin

ISBN: (数字)9781728190105

ISBN: (纸本)9781728190112

We design a new multi-modal perception fusion system for the whole scene, which can be divided into two parts. The first part is lidar, rgbamera1, rgbamera2. The second part is RGB camera 3, RGB camera 4, depth camera. The combination of these three modes provides a close range (0.3-10 m) of environmental perception, and provides the texture and distance information of the environment in the cone-shaped blind area of lidar. Our main work is to design the experimental equipment of the proposed multi-modal perceptual fusion system, and to push forward the optimization theory with the re projection error as the objective function and analyze the multi-modal fusion sensing system. The graph structure is established, and the relative pose transformation between various modes is analyzed. In the back-end optimization part, MCPE (Minimally connected pose estimation) and PSE(Pose and structure estimation)are used to analyze and compare the system. In the experimental part, we use matlab to calibrate the binocular camera by minimizing the error of re projection. The lidar, RGB camera and depth camera are calibrated with the help of the multi-modal calibration tool (binding on ROS) proposed. It provides a solid foundation for the future experiments in perception of self-driving, UAV perception, medical field and military field.

关键词： Cameras Sensors Calibration Laser radar Sensor systems Multimodal sensors Optimization

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Nonlinear Adaptive Manifold learning for Global and Local Information

引用

Tsinghua Science and Technology 2021年第2期26卷 163-171页

作者： Jiajun Gao Fanzhang Li Bangjun Wang Helan Liang School of Computer Science and Technology Soochow UniversitySuzhou 215006China Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Provincial Key Laboratory for Computer Information Processing TechnologySoochow UniversitySuzhou 215006China

In this paper,we propose an Unsupervised Nonlinear Adaptive Manifold learning method(UNAML)that considers both global and local *** this approach,we apply unlabeled training samples to study nonlinear manifold features,while considering global pairwise distances and maintaining local topology *** method aims at minimizing global pairwise data distance errors as well as local structural *** order to enable our UNAML to be more efficient and to extract manifold features from the external source of new data,we add a feature approximate error that can be used to learn a linear ***,we add a feature approximate error that can be used to learn a linear *** addition,we use a method of adaptive neighbor selection to calculate local structural *** paper uses the kernel matrix method to optimize the original *** algorithm proves to be more effective when compared with the experimental results of other feature extraction methods on real face-data sets and object data sets.

关键词： unsupervised manifold learning global and local information,adaptive neighbor selection method kernel matrix

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization of Wildlife Recognition with Distributed learning in Ecological Surveillance

Performance Optimization of Wildlife Recognition with Distri...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Wan Dai Hongpeng Wang Yulin Song Yunwei Xin Tianjin Key Laboratory of Intelligent Robotics Tianjin Research Laboratory of Machine Learning and Pervasive Computing Nankai University Tianjin

ISBN: (数字)9781728107707

ISBN: (纸本)9781728107714

Recently, deep learning technology has been widely used in ecological environment monitoring, but there are still huge challenges in specific tasks. For example, data sets have increased over the past few years, and in a CPU environment, training is quite time consuming. In order to solve these problems, we bring up a novel and effective method to improve training speed. In this paper, we make use of multi-GPUs to achieve distributed parallel acceleration. Small and shallow networks are not suitable for distributed training, because the computation of each parameter in this network is much higher than that of multi-layer perception or automatic encoder architecture, we use convolutional neural network with parameter sharing as the training network. In this paper, the main adopted method is to compare the performance of training wildlife recognition in single GPU and multi-GPUs environments by using distributed deep learning framework TensorFlow. The experimental results show that multi-GPUs which adopt distributed architecture can significantly accelerate training time consumption than single GPU. The results of this experiment also provides strong support for our follow-up work.

关键词： Training Parallel processing Graphics processing units Distributed databases Computational modeling Data models Neural networks

来源：评论

学校读者我要写书评

暂无评论

H-TERF: A hybrid approach combining fuzzy multi-criteria decision-making techniques and enhanced random forest to improve WBAN-IoT

Internet of Things (The Netherlands)

引用

Internet of Things (The Netherlands) 2025年 32卷

作者： Khoshvaght, Parisa Tanveer, Jawad Rahmani, Amir Masoud Mohammadi, Mohammad Mehranzadeh, Amin Lansky, Jan Hosseinzadeh, Mehdi Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Engineering & Technology Duy Tan University Da Nang Viet Nam Department of Computer Science and Engineering Sejong University Seoul 05006 South Korea Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Computer Engineering Dezful Branch Islamic Azad University Dezful Iran Department of Computer Science and Mathematics Faculty of Economic Studies University of Finance and Administration Prague Czech Republic Pattern Recognition and Machine Learning Laboratory School of Computing Gachon University Seongnam South Korea

The Internet of Things (IoT) technology today has grown rapidly compared to the last few years, and the use of this technology has increased the quality of service to users day by day. The various applications of IoT have caused the attention of this innovation to enhance among different organizations. One of the important challenges of the IoT is routing, which can affect having a stable network. In this research, a hybrid approach called H-TERF (Hybrid TOPSIS and Enhanced Random Forest) is proposed for achieving efficient routing in IoT networks, specifically in Wireless Body Area Networks (WBAN). This method initially cluster nodes by using the DBSCAN clustering algorithm to optimize intra-cluster communication. Then, for routing, the nodes are ranked using the Fuzzy TOPSIS and Fuzzy AHP. This ranking is determined by several criteria, including the remaining energy of nodes, node memory, and throughput. Additionally, to manage more complex criteria such as node historical records and traffic rate, the initial ranking by the TOPSIS approach, along with the other mentioned criteria, is fed into an enhanced random forest model to identify the optimal path. This hybrid method enhances network performance in terms of lifespan, efficiency, delay, and packet delivery ratio. The outcomes of the simulation show that the suggested method surpasses existing approaches and is highly effective for application in IoT and WBAN networks. For example, the performance improvement of the proposed approach over the F-EVM, DECR, and DHH-EFO approaches in energy consumption was 20.62%, 25.85%, and 32.57%, respectively. © 2025 Elsevier B.V.

关键词： DBSCAN clustering Enhanced random forest Fuzzy AHP Fuzzy TOPSIS Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Laplacain Pair-Weight Vector Projection with Adaptive Neighbor Graph for Semi-supervised learning 1

引用

3rd International Conference on Neural computing for Advanced Applications, NCAA 2022

作者： Xue, Yangtao Zhang, Li The School of Computer Science and Technology and Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Soochow University Suzhou215006 China

ISBN: (数字)9789811961427

ISBN: (纸本)9789811961410

Recently, Laplacian pair-weight vector projection (LapPVP) algorithm was proposed for semi-supervised classification. Although LapPVP achieves a good classification performance for semi-supervised learning, it may be sensitive to noise and outliers for using the neighbor graph with a fixed similarity matrix. To remedy it, this paper proposes a novel method named Laplacain pair-weight vector projection with adaptive neighbor graph (ANG-LapPVP), in which the graph induced by the Laplacian manifold regularization is adaptively constructed by solving an optimization problem. For binary classification problems, ANG-LapPVP learns a pair of projection vectors by solving the pair-wise optimal formulations in which we maximize the between-class scatter and minimize both the within-class scatter and the adaptive neighbor graph (ANG) regularization. The ANG regularization is to learn the ANG whose similarity matrix varies with iterations, which may solve the issue of LapPVP. Thus, ANG-LapPVP simultaneously learns adaptive similarity matrices and a pair of projection vectors with an iterative process. Experimental results on an artificial and real-world benchmark datasets show the superiority of ANG-LapPVP compared to the related methods. Thus, ANG-LapPVP is promising in semi-supervised learning. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Unsupervised ensemble learning based on graph embedding for image clustering 25th

Unsupervised ensemble learning based on graph embedding for ...

引用

25th International Conference on Neural Information Processing, ICONIP 2018

作者： Luo, Xiaohui Zhang, Li Li, Fanzhang Hu, Chengxiang School of Computer Science and Technology and Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Provincial Key Laboratory for Computer Information Processing Technology Soochow University SuzhouJiangsu215006 China

ISBN: (纸本)9783030041816

Manifold learning has attracted more and more attention in machine learning for past decades. Unsupervised Large Graph Embedding (ULGE), which performs well on the large-scale data, has been proposed for manifold learning. To improve the clustering performance, a novel Unsupervised Ensemble learning based on Graph Embedding (UEL-GE) is explored, which takes ULGE to get low-dimensional embeddings of the given data and uses the K-means method to obtain the clustering results. Furthermore, the multiple clusterings are corrected by using the bestMap method. Finally, the corrected clusterings are combined to generate the final clustering. Extensive experiments on several data sets are conducted to show the efficiency and effectiveness of the proposed ensemble learning method. © Springer Nature Switzerland AG 2018.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Sample Reduction Using 1 -Norm Twin Bounded Support Vector machine 2nd

Sample Reduction Using 1 -Norm Twin Bounded Support Vector M...

引用

2nd International Conference on Neural computing for Advanced Applications, NCAA 2021

作者： Zheng, Xiaohan Zhang, Li Yan, Leilei School of Computer Science and Technology Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Soochow University Suzhou215006 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China

ISBN: (纸本)9789811651878

Twin support machine (TSVM) has a lower time complexity than support vector machine (SVM), but it has a poor ability to perform sample reduction. In order to improve the ability of TSVM to reduce sample, we propose an 1 -norm twin bounded support machine (1 -TBSVM) inspired by the sparsity of 1 -norm in feature space. The objective function of 1 -TBSVM contains the hinge loss and the 1 -norm terms, both which can induce sparsity. We solve the primal programming problems of 1 -TBSVM to prevent the disappearance of sparsity and avoid the situation that the inverse of matrix does not exist. Thus, 1 -TBSVM has a good sparsity, or a good ability to reduce sample. Experimental results on synthetic and UCI datasets indicate that 1 -TBSVM has a good ability to perform sample reduction and simultaneously enhances the classification performance. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

T CNN: a novel method for crowd counting via two-task convolutional neural network

引用

The Visual Computer 2021年第1期39卷 73-85页

作者： Zhang, Li Yan, Leilei Zhang, Mengqian Lu, Jingang Laboratory of Machine Learning and Neuromorphic Computing School of Computer Science and Technology and Joint International Research Soochow University Suzhou China

This paper investigates the issue of crowd counting for crowd images. A novel method named two-task convolutional neural network (T $$^2$$ CNN) is proposed to simultaneously learn two tasks for crowd counting: the tasks of dense degree classification and density map estimation. Basically, T $$^2$$ CNN contains two main modules: dense degree classification (DDC) and density map estimation. Generally, it is sufficient for crowd counting to estimate density maps of images. It is known that images may have different dense degrees and the local regions in the same image have different dense degrees. Thus, dense degree may provide the high-level prior of images and is excepted to help the estimation of density maps. To better estimate density maps of images, T $$^2$$ CNN incorporates the DDC module into the task of density map estimation. T $$^2$$ CNN takes the scale-adaptive convolutional neural network as the estimator of density maps, which adopts multi-scale layers to tackle the scale and perspective variations that exist in crowd images commonly. To verify the effectiveness and robustness of our model, we conduct extensive experiments on the Shanghaitech, UCF_CC_50 and WorldExpo’10 datasets. Experimental results indicate that T $$^2$$ CNN achieves good performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discriminative sparse coding by nuclear norm-driven semi-supervised dictionary learning 17th

Discriminative sparse coding by nuclear norm-driven semi-sup...

引用

17th Pacific-Rim Conference on Multimedia, PCM 2016

作者： Jiang, Weiming Zhang, Zhao Zhang, Yan Li, Fanzhang School of Computer Science and Technology & Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Soochow University Suzhou215006 China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing210023 China

ISBN: (纸本)9783319488899

In this paper, we propose a Nuclear norm-driven Semi-Supervised Dictionary learning (N-SSDL) approach for classification. N-SSDL incorporates the idea of the recent label consistent KSVD with the label propagation process that propagates label information from labeled data to unlabeled data via balancing the neighborhood reconstruction error and the label fitness error. To provide a more reliable distance metric for measuring the neighborhood reconstruction error, we apply the nuclear-norm that is proved to be suitable for modeling the reconstruction error, where the reconstruction coefficients are computed based on the sparsely reconstructed training data rather than original ones. Besides, we also use the robust l2,1-norm regularization on the label fitness error so that the measurement is robust to noise and outliers. Extensive simulations on several datasets show that N-SSDL can deliver enhanced performance over other state-of-the-arts for classification. © Springer International Publishing AG 2016.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Transductive classification by robust linear neighborhood propagation 17th

Transductive classification by robust linear neighborhood pr...

引用

17th Pacific-Rim Conference on Multimedia, PCM 2016

作者： Jia, Lei Zhang, Zhao Jiang, Weiming School of Computer Science and Technology & Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Soochow University Suzhou215006 China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing210023 China

ISBN: (纸本)9783319488899

We propose an enhanced label prediction method termed Transductive Classification Robust Linear Neighborhood Propagation (R-LNP). To encode the neighborhood reconstruction error more accurately, we apply the L2,1-norm that is proved to be very robust to noise for characterizing the manifold smoothing term. Since L2,1-norm can also enforce the neighborhood reconstruction error to be sparse in rows, i.e., entries of some rows are zeros. In addition, to enhance robustness in the process of modeling the difference between the initial labels and predicted ones, we also regularize the weighted L2,1-norm on the label fitting term, so the resulted measures would be more accurate. Compared with several transductive label propagation models, our proposed algorithm obtains state-of-the-art performance over extensive representation and classification experiments. © Springer International Publishing AG 2016.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：