0% Complete
صفحه اصلی
/
سی و یکمین کنفرانس بین المللی مهندسی برق
Kernel-Based Band Selection for Hyperspectral Image Classification
نویسندگان :
Mehdi Kamandar
1
1- دانشگاه تحصیلات تکمیلی صنعتی و فناوری پیشرفته
کلمات کلیدی :
Hyperspectral image classification،support vector machine،anisotropic Gaussian kernel،kernel-based band selection،l1 regularization،minibatch proximal gradient ascent
چکیده :
Hyperspectral image classification is a challenging task due to problems such as complex nonlinear structure of data, noisy and redundant spectral bands, and small-sample-size problem. The nonlinear support vector machine (SVM) is an excellent classifier to tackle these challenges. Selecting the most appropriate kernel and tuning its parameters for the data has a vital role in classification performance of the SVM. In this paper, an anisotropic Gaussian kernel is used. Anisotropic Gaussian kernel has a special scaling factor for each band. The scaling factors are tuned by maximizing a classifier independent separability measure with l1 regularization. The separability measure uses within-class and between-class dispersion information in the feature space. Some of the scaling factors will be zero after separability maximization due to l1 regularization, that is equivalent to removing corresponding bands from classification processes. Therefore, an embedded band selection is done to remove the destructive effect of irrelevant and redundant bands. The results show on average 5% classification accuracy improvement compared to an isotropic Gaussian kernel for classifying Indiana Pin Site hyperspectral image.
لیست مقالات
لیست مقالات بایگانی شده
تجزیه و تحلیل امواج فیبریلاتور دهلیزی به منظور طبقهبندی AF با استفاده از موجک لیدر
سارا میهن دوست
Design Investigation of a Broadband Polarization Rotator Using SIW Technology with T-Shaped Slots
Amin Azimi - Mohammad.H Neshati
Design and Implementation of a fast flexible and efficient multichannel digital filter for hearing aids
Mohammadsadegh Poushnegar - Mahmoud Tabandeh - Meysam Nesary Moghadam - Farzam Gilani - Ali Aghakasiri
Design of a Retinal Prosthesis Circuit With In-pixel Edge Detection Capability
Zahra Bonesbordi - Sayed Masoud Sayedi
On the Correction of the Boundary Deformation Errors in Microwave Imaging With Spatial Priors
Seyyed Mohammad Hosseini - Amir Ahmad Shishegar
مدل سازی و شبیه سازی جداکننده پرتو کوانتومی و تداخل گر ماخ زندر کوانتومی
محمد جواد شریفی
Accurate Methods for Automatic Detection of Characteristic Points in Electrocardiograms
Seyedeh Mersedeh Bagheri - Mohammad Pooyan
Low Cost Implementation of Neural Networks Based on Stochastic Computing
Hadi Jahanirad - Ahmad Menbari
ادغام حسگرهای رادار، لیدار و دوربین به منظور بهبود عملکرد در تشخیص اهداف برای کاربرد خودروهای خودران
سید مسعود معصومی زاده - محمد سجادی - طاها محقق - منصور نادرپور - صادق شاه سنایی - محمد علی مددی - زهرا کاوه وش - علی فتوت احمدی
An Open-Loop Time Amplifier With Zero-Gain Delay in Output for Coarse-Fine Time to Digital Converters
Seyyed Morteza Golzan - Jafar Sobhi - Ziaddin Daie Koozehkanani
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 41.7.4