检索结果-南通市图书馆

Improving Generalization for Hyperspectral Image Classification:The Impact of Disjoint Sampling on Deep Models

Computers, Materials & Continua 2024年第10期81卷 503-532页

作者： Muhammad Ahmad Manuel Mazzara salvatore distefano Adil Mehmood Khan Hamad Ahmed Altuwaijri Department of Computer Science National University of Computer and Emerging SciencesChiniot35400Pakistan Institute of Software Development and Engineering Innopolis UniversityInnopolis420500Russia Dipartimento di Matematica e Informatica—MIFT University of MessinaMessina98121Italy School of Computer Science University of HullHullHU67RXUK Department of Geography College of Humanities and Social SciencesKing Saud UniversityRiyadh11451Saudi Arabia

Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art(SOTA)models e.g.,Attention Graph and Vision *** training,validation,and test sets overlap or share data,it introduces a bias that inflates performance metrics and prevents accurate assessment of a model’s true ability to generalize to new *** paper presents an innovative disjoint sampling approach for training SOTA models for the Hyperspectral Image Classification(HSIC).By separating training,validation,and test data without overlap,the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was not exposed to during training or *** demonstrate the approach significantly improves a model’s generalization compared to alternatives that include training and validation data in test data(A trivial approach involves testing the model on the entire Hyperspectral dataset to generate the ground truth *** approach produces higher accuracy but ultimately results in low generalization performance).Disjoint sampling eliminates data leakage between sets and provides reliable metrics for benchmarking progress in *** sampling is critical for advancing SOTA models and their real-world application to large-scale land mapping with Hyperspectral ***,with the disjoint test set,the performance of the deep models achieves 96.36%accuracy on Indian Pines data,99.73%on Pavia University data,98.29%on University of Houston data,99.43%on Botswana data,and 99.88%on Salinas data.

关键词： Hyperspectral image classification disjoint sampling Graph CNN spatial-spectral transformer

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

Multi Sensor-Based Implicit User Identification

引用

Computers, Materials & Continua 2021年第8期68卷 1673-1692页

作者： Muhammad Ahmad Rana Aamir Raza Manuel Mazzara salvatore distefano Ali Kashif Bashir Adil Khan Muhammad Shahzad Sarfraz Muhammad Umar Aftab Department of Computer Science National University of Computer and Emerging SciencesChiniot35400Pakistan Department of Computer Science Bahauddin Zakariya UniversityMultan66000Pakistan Institute of Software Development and Engineering Innopolis UniversityInnopolis420500Russia Dipartimento di Matematica e Informatica—MIFT University of MessinaMessina98121Italy Department of Computing and Mathematics Manchester Metropolitan UniversityManchesterUK

Smartphones have ubiquitously integrated into our home and work environments,however,users normally rely on explicit but inefficient identification processes in a controlled ***,when a device is stolen,a thief can have access to the owner’s personal information and services against the stored *** a result of this potential scenario,this work proposes an automatic legitimate user identification system based on gait biometrics extracted from user walking patterns captured by smartphone sensors.A set of preprocessing schemes are applied to calibrate noisy and invalid samples and augment the gait-induced time and frequency domain features,then further optimized using a non-linear unsupervised feature selection *** selected features create an underlying gait biometric representation able to discriminate among individuals and identify them *** classifiers are adopted to achieve accurate legitimate user *** experiments on a group of 16 individuals in an indoor environment show the effectiveness of the proposed solution:with 5 to 70 samples per window,KNN and bagging classifiers achieve 87–99%accuracy,82–98%for ELM,and 81–94%for *** proposed pipeline achieves a 100%true positive and 0%false-negative rate for almost all classifiers.

关键词： Sensors smartphone legitimate user identification

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

New Insights on the Role of the Strike-Slip Tectonics in the Late Miocene-Quaternary Evolution of Sicily

引用

International Journal of Geosciences 2019年第6期10卷 689-708页

作者： Stefano Catalano Agata Di Stefano salvatore distefano Francesco Pavano Gino Romagnoli Giuseppe Tortorici Luigi Tortorici Dipartimento di Scienze Biologiche Geologiche e Ambientali-Sezione di Scienze della Terra Università di Catania Catania Italy Consiglio Nazionale delle Ricerche Istituto di Geologia Ambientale e Geoingeneria Rome Italy

Understanding the influence of the Late Miocene-Quaternary opening of the Tyrrhenian Basin on the evolution of the external sectors of the Africa paleo-margin in Sicily, actually, represents a hard challenge, even though several, and contrasting, models have been proposed in the last decades. One open problem refers to localizing the main regional scale tectonic lineaments of Sicily that accommodated the hundreds of kilometers of lateral displacement, due to the Tyrrhenian Basin opening. In the present work, we present the results rising from a detailed field mapping carried out in relevant vast areas of central Sicily. These data enabled to reconstruct a Neogene-Quarternary kinematic evolutionary model of the collision belt of Sicily. We analyzed the northern tectonic margin of the Caltanissetta Through, which represents a structural depression hosting a thick allochthonous tectonic wedge, on which lay different unconformable thrust-top basin deposits. In more details, our study aims to reconstruct the tectono-sedimentary Late Tortonian-to-Quaternary evolution of this tectonic wedge, revealing that regional E-W-trending dextral shear zones deform and cut the NE-oriented, SE-verging, thrust-and-fold belt. The strike-slip tectonics thus controlled the deposition of different sedimentary cycles on the thrust-top basins and governed the tectonic inversion of the external sectors of the Africa paleo-margin.

关键词： Thrust and Fold Belt Accretionary Wedge Africa Paleomargin Numidian Flysch Caltanissetta through

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

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

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：