检索结果-南通市图书馆

Spatial-Aware Supervised Learning for Hyper-Spectral Image Classification Comprehensive Assessment

Journal of Donghua University(English Edition) 2016年第6期33卷 954-960页

作者： soomro bushra naz XIAO Liang soomro Shahzad Hyder MOLAEI Mohsen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China

A comprehensive assessment of the *** mpervised learning algorithms for *** image （HSI） classification was presented. For this purpose, standard support vector machines （ SVMs ）, mudttnomial logistic regression （ MLR ） and sparse representation （SR） based supervised learning algorithm were compared both theoretically and experimentally. Performance of the discussed techniques was evaluated in terms of overall accuracy, average accuracy, kappa statistic coefficients, and sparsity of the solutions. Execution time, the computational burden, and the capability of the methods were investigated by using probabilistie analysis. For validating the accuracy a classical benchmark AVIRIS Indian pines data set was used. Experiments show that integrating *** context can further improve the accuracy, reduce the misclassltication error although the cost of computational time will be increased.

关键词： learning algorithms hyper-spectral image classification support vector machine(SVM) multinomial logistic regression(MLR) elastic net regression(ELNR) sparse representation(SR) spatial-aware

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Multi-material Bio-inspired Soft Octopus Robot for Underwater Synchronous Swimming

引用

Journal of Bionic Engineering 2022年第5期19卷 1229-1241页

作者： Faheem Ahmed Muhammad Waqas bushra Shaikh Umair Khan Afaque Manzoor soomro Suresh Kumar Hina Ashraf Fida Hussain Memon Kyung Hyun Choi Department of Mechatronics Engineering Jeju National UniversityJeju 63243South Korea Department of Electrical Engineering Sukkur IBA UniversityAirport RoadSukkur 65200SindhPakistan Advanced Micro Mechatronics and Energy Lab Sukkur IBA UniversitySukkur 65200Pakistan Department of Ocean Sciences Jeju National UniversityJeju 63243South Korea

Inspired by the simple yet amazing morphology of the Octopus, we propose the design, fabrication, and characterization of multi-material bio-inspired soft Octopus robot (Octobot). 3D printed molds for tentacles and head were used. The tentacles of the Octobot were casted using Ecoflex-0030 while head was fabricated using relatively flexible material, i.e., OOMOO-25. The head is attached to the functionally responsive tentacles (each tentacle is of 79.12 mm length and 7 void space diameter), whereas Shape Memory Alloy (SMA) muscle wires of 0.5 mm thickness are used in Octobot tentacles for dual thrust generation and actuation of Octobot. The tentacles were separated in two groups and were synchronously actuated. Each tentacle of the developed Octobot contains a pair of SMA muscles (SMA-α and SMA-β). SMA-α muscles being the main actuator, was powered by 9 V, 350 mA power supply, whereas SMA-β was used to provide back thrust and thus helps to increase the actuation frequency. Simulation work of the proposed model was performed in the SolidWorks environment to verify the vertical velocity using the octopus tentacle actuation. The design morphology of Octobot was optimized using simulation and TRACKER software by analyzing the experimental data of angle, displacement, and velocity of real octopus. The as-developed Octobot can swim at variable frequencies (0.5–2 Hz) with the average speed of 25 mm/s (0.5 BLS). Therefore, the proposed soft Octopus robot showed an excellent capability of mimicking the gait pattern of its natural counterpart.

关键词： Bio-inspired Octopus Octobot Sub-surface Soft robotics Swimming

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

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：