scholarly journals Spatial Spectral Band Selection for Enhanced Hyperspectral Remote Sensing Classification Applications

2020 ◽  
Vol 6 (9) ◽  
pp. 87 ◽  
Author(s):  
Ruben Moya Torres ◽  
Peter W.T. Yuen ◽  
Changfeng Yuan ◽  
Johathan Piper ◽  
Chris McCullough ◽  
...  
Keyword(s):  
Mutual Information ◽  
Classification Accuracy ◽  
High Efficiency ◽  
Spectral Band ◽  
Band Selection ◽  
Practical Applications ◽  
Remote Sensing Classification ◽  
Spectral Bands ◽  
Kennedy Space ◽  
First Time

Despite the numerous band selection (BS) algorithms reported in the field, most if not all have exhibited maximal accuracy when more spectral bands are utilized for classification. This apparently disagrees with the theoretical model of the ‘curse of dimensionality’ phenomenon, without apparent explanations. If it were true, then BS would be deemed as an academic piece of research without real benefits to practical applications. This paper presents a spatial spectral mutual information (SSMI) BS scheme that utilizes a spatial feature extraction technique as a preprocessing step, followed by the clustering of the mutual information (MI) of spectral bands for enhancing the efficiency of the BS. Through the SSMI BS scheme, a sharp ’bell’-shaped accuracy-dimensionality characteristic that peaks at about 20 bands has been observed for the very first time. The performance of the proposed SSMI BS scheme has been validated through 6 hyperspectral imaging (HSI) datasets (Indian Pines, Botswana, Barrax, Pavia University, Salinas, and Kennedy Space Center (KSC)), and its classification accuracy is shown to be approximately 10% better than seven state-of-the-art BS schemes (Saliency, HyperBS, SLN, OCF, FDPC, ISSC, and Convolution Neural Network (CNN)). The present result confirms that the high efficiency of the BS scheme is essentially important to observe and validate the Hughes’ phenomenon in the analysis of HSI data. Experiments also show that the classification accuracy can be affected by as much as approximately 10% when a single ‘crucial’ band is included or missed out for classification.

scholarly journals An Investigation of Spectral Band Selection for Hyperspectral LiDAR Technique

Electronics ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 148
Author(s):  
Hui Shao ◽  
Yuwei Chen ◽  
Wei Li ◽  
Changhui Jiang ◽  
Haohao Wu ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Spectral Band ◽  
Selection Method ◽  
Experimental Results ◽  
Laser Source ◽  
Band Selection ◽  
Support Vector ◽  
Svm Classifier ◽  
Feature Parameters ◽  
Spectral Bands

Hyperspectral LiDAR (HSL) has been widely discussed in recent years, which attracts increasing attention of the researchers in the field of electronic information technology. With the application of supercontinuum laser source, it is now possible to develop an HSL system, which can collect spectral and spatial information of targets simultaneously. Meanwhile, eye-safety and miniature HSL device with multiple spectral bands are given more priorities in on-site applications. In this paper, we tempt to investigate how to select spectral bands with a selection method. The proposed method consists of three steps: first, the variances among the classes based on hyperspectral feature parameters, termed inter-class variances, are calculated; second, the channels are sorted based on corresponding variances in descending order, and those with the two highest values are adopted as the initial input of classification; finally, the channels are selected successively from the rest of the sorted sequence until the classification accuracy reaches 100%. To test the performance of the proposed method, we collect 91/71-channel hyperspectral measurements of four different categories of materials with 5 nm spectral resolution using an acousto-optic tunable filter (AOTF) based HSL. Experimental results demonstrate that the proposed method could achieve higher classification accuracy than a random band selection method with different classifiers (naïve Bayes (NB) and support vector machine (SVM)) regardless of classification feature parameters (echo maximum and reflectance). To reach 100% accuracy, it demands 8–9 channels on average by echo maximum and 4–5 channels on average by reflectance based on NB classifier; these figures are 3–4 by echo maximum and 2–3 by reflectance with SVM classifier. The proposed method can complete classification task much faster than the random selection method. We further confirm the specific channels for the classification of different materials, and find that the optimal channels vary with different materials. The experimental results prove that the optimal band selection of HSL system for classification is reliable.

Parasitic Flux Analysis of Cooled Infrared Detectors for Space Applications

2017 ◽  
Vol 67 (2) ◽  
pp. 193
Author(s):  
Ankur Jain ◽  
Amiya Biswas
Keyword(s):  
Infrared Detector ◽  
Optical Design ◽  
Spectral Band ◽  
Low Noise ◽  
Flux Analysis ◽  
Optical Elements ◽  
Space Applications ◽  
Practical Applications ◽  
Spectral Bands ◽  
Infrared Imager

An infrared imager measures radiations emitted by an object in specified spectral bands to determine change in object’s characteristics over a period of time. A typical infrared imager consists of focusing optics and a cryogenically cooled two-dimensional infrared detector array mounted on the cold tip of an active micro-cooler vacuum sealed with an optical window, typically known as integrated detector cooler assembly (IDCA). Detection of feeble radiant flux from the intended target in a narrow spectral band requires a highly sensitive low noise sensor array with high well capacity. However, in practical applications the performance of an infrared imager is limited by the parasitic thermal emissions from optical elements and emissions from IDCA components like vacuum window, Dewar walls which are generally kept at ambient temperature. To optimise the performance of imager it becomes imperative to estimate these parasitic fluxes and take corrective actions to minimise their effects. This paper explains an analytical model developed to estimate parasitic fluxes generated from different components of a long wave infrared imager. Validation of the developed model was carried out by simulations in ZEMAX optical design software using ray trace method after analytical computations in MATLAB.

scholarly journals Spatial Mutual Information Based Hyperspectral Band Selection for Classification

2015 ◽  
Vol 2015 ◽  
pp. 1-7 ◽  
Author(s):  
Anthony Amankwah
Keyword(s):  
Mutual Information ◽  
Supervised Classification ◽  
Band Selection ◽  
Support Vector ◽  
Spatial Dependency ◽  
Information Redundancy ◽  
Spectral Bands ◽  
Validation Criteria ◽  
Selection For

The amount of information involved in hyperspectral imaging is large. Hyperspectral band selection is a popular method for reducing dimensionality. Several information based measures such as mutual information have been proposed to reduce information redundancy among spectral bands. Unfortunately, mutual information does not take into account the spatial dependency between adjacent pixels in images thus reducing its robustness as a similarity measure. In this paper, we propose a new band selection method based on spatial mutual information. As validation criteria, a supervised classification method using support vector machine (SVM) is used. Experimental results of the classification of hyperspectral datasets show that the proposed method can achieve more accurate results.

scholarly journals Hyperspectral band selection and modeling of soil organic matter content in a forest using the Ranger algorithm

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0253385
Author(s):  
Yuanyuan Shi ◽  
Junyu Zhao ◽  
Xianchong Song ◽  
Zuoyu Qin ◽  
Lichao Wu ◽  
...  
Keyword(s):  
Organic Matter ◽  
Soil Organic Matter ◽  
Prediction Model ◽  
Goodness Of Fit ◽  
Spectral Band ◽  
Organic Matter Content ◽  
Band Selection ◽  
Support Vector ◽  
Spectral Bands ◽  
Modeling Accuracy

Effective soil spectral band selection and modeling methods can improve modeling accuracy. To establish a hyperspectral prediction model of soil organic matter (SOM) content, this study investigated a forested Eucalyptus plantation in Huangmian Forest Farm, Guangxi, China. The Ranger and Lasso algorithms were used to screen spectral bands. Subsequently, models were established using four algorithms: partial least squares regression, random forest (RF), a support vector machine, and an artificial neural network (ANN). The optimal model was then selected. The results showed that the modeling accuracy was higher when band selection was based on the Ranger algorithm than when it was based on the Lasso algorithm. ANN modeling had the best goodness of fit, and the model established by RF had the most stable modeling results. Based on the above results, a new method is proposed in this study for band selection in the early phase of soil hyperspectral modeling. The Ranger algorithm can be applied to screen the spectral bands, and ANN or RF can then be selected to construct the prediction model based on different datasets, which is applicable to establish the prediction model of SOM content in red soil plantations. This study provides a reference for the remote sensing of soil fertility in forests of different soil types and a theoretical basis for developing portable equipment for the hyperspectral measurement of SOM content in forest habitats.

scholarly journals Chemical Modification of Combusted Coal Gangue for U(VI) Adsorption: Towards a Waste Control by Waste Strategy

2021 ◽  
Vol 13 (15) ◽  
pp. 8421
Author(s):  
Yuan Gao ◽  
Jiandong Huang ◽  
Meng Li ◽  
Zhongran Dai ◽  
Rongli Jiang ◽  
...  
Keyword(s):  
Structural Analysis ◽  
High Efficiency ◽  
Low Cost ◽  
Chemical Activation ◽  
Cost Effective ◽  
Coal Gangue ◽  
Order Kinetic ◽  
Practical Applications ◽  
Detailed Structural Analysis ◽  
Alkaline Conditions

Uranium mining waste causes serious radiation-related health and environmental problems. This has encouraged efforts toward U(VI) removal with low cost and high efficiency. Typical uranium adsorbents, such as polymers, geopolymers, zeolites, and MOFs, and their associated high costs limit their practical applications. In this regard, this work found that the natural combusted coal gangue (CCG) could be a potential precursor of cheap sorbents to eliminate U(VI). The removal efficiency was modulated by chemical activation under acid and alkaline conditions, obtaining HCG (CCG activated with HCl) and KCG (CCG activated with KOH), respectively. The detailed structural analysis uncovered that those natural mineral substances, including quartz and kaolinite, were the main components in CCG and HCG. One of the key findings was that kalsilite formed in KCG under a mild synthetic condition can conspicuous enhance the affinity towards U(VI). The best equilibrium adsorption capacity with KCG was observed to be 140 mg/g under pH 6 within 120 min, following a pseudo-second-order kinetic model. To understand the improved adsorption performance, an adsorption mechanism was proposed by evaluating the pH of uranyl solutions, adsorbent dosage, as well as contact time. Combining with the structural analysis, this revealed that the uranyl adsorption process was mainly governed by chemisorption. This study gave rise to a utilization approach for CCG to obtain cost-effective adsorbents and paved a novel way towards eliminating uranium by a waste control by waste strategy.

High-efficiency ternary polymer solar cells with optimized morphology of active layers enabled by few-layered β-InSe nanosheets

Nanoscale ◽  
2021 ◽  
Vol 13 (14) ◽  
pp. 6871-6883
Author(s):  
Jianming Wang ◽  
Huangzhong Yu ◽  
Chunli Hou
Keyword(s):  
Solar Cells ◽  
High Efficiency ◽  
Polymer Solar Cells ◽  
Active Layers ◽  
Ternary Polymer ◽  
First Time

Herein, few-layered β-InSe nanosheets are introduced into the active layers of polymer solar cells as morphological modifiers for the first time. 

scholarly journals Vacancy tuned thermoelectric properties and high spin filtering performance in graphene/silicene heterostructures

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Zainab Gholami ◽  
Farhad Khoeini
Keyword(s):  
Electric Fields ◽  
High Spin ◽  
High Efficiency ◽  
Practical Applications ◽  
External Electric Fields ◽  
Ferromagnetic Exchange ◽  
High Spin Polarization ◽  
Filtering Effect ◽  
Spin Switching ◽  
Spin Filtering

AbstractThe main contribution of this paper is to study the spin caloritronic effects in defected graphene/silicene nanoribbon (GSNR) junctions. Each step-like GSNR is subjected to the ferromagnetic exchange and local external electric fields, and their responses are determined using the nonequilibrium Green’s function (NEGF) approach. To further study the thermoelectric (TE) properties of the GSNRs, three defect arrangements of divacancies (DVs) are also considered for a larger system, and their responses are re-evaluated. The results demonstrate that the defected GSNRs with the DVs can provide an almost perfect thermal spin filtering effect (SFE), and spin switching. A negative differential thermoelectric resistance (NDTR) effect and high spin polarization efficiency (SPE) larger than 99.99% are obtained. The system with the DV defects can show a large spin-dependent Seebeck coefficient, equal to Ss ⁓ 1.2 mV/K, which is relatively large and acceptable. Appropriate thermal and electronic properties of the GSNRs can also be obtained by tuning up the DV orientation in the device region. Accordingly, the step-like GSNRs can be employed to produce high efficiency spin caloritronic devices with various features in practical applications.

scholarly journals High-Efficiency Polarizer Reflectarray Antennas for Data Transmission Links from a CubeSat

Electronics ◽  
2021 ◽  
Vol 10 (15) ◽  
pp. 1802
Author(s):  
Eduardo Martinez-de-Rioja ◽  
Daniel Martinez-de-Rioja ◽  
Rafael López-Sáez ◽  
Ignacio Linares ◽  
Jose A. Encinar
Keyword(s):  
Circular Polarization ◽  
Data Transmission ◽  
High Efficiency ◽  
High Gain ◽  
Dual Band ◽  
Left Handed ◽  
Linearly Polarized ◽  
Flat Profile ◽  
First Time ◽  
Collimated Beam

This paper presents two designs of high-efficiency polarizer reflectarray antennas able to generate a collimated beam in dual-circular polarization using a linearly polarized feed, with application to high-gain antennas for data transmission links from a Cubesat. First, an 18 cm × 18 cm polarizer reflectarray operating in the 17.2–22.7 GHz band has been designed, fabricated, and tested. The measurements of the prototype show an aperture efficiency of 52.7% for right-handed circular polarization (RHCP) and 57.3% for left-handed circular polarization (LHCP), both values higher than those previously reported in related works. Then, a dual-band polarizer reflectarray is presented for the first time, which operates in dual-CP in the frequency bands of 20 GHz and 30 GHz. The proposed antenna technology enables a reduction of the complexity and cost of the feed chain to operate in dual-CP, as a linear-to-circular polarizer is no longer required. This property, combined with the lightweight, flat profile and low fabrication cost of printed reflectarrays, makes the proposed antennas good candidates for Cubesat applications.

scholarly journals Ruthenium Sensitizers and Their Applications in Dye-Sensitized Solar Cells

2012 ◽  
Vol 2012 ◽  
pp. 1-21 ◽  
Author(s):  
Yuancheng Qin ◽  
Qiang Peng
Keyword(s):  
Solar Cells ◽  
High Efficiency ◽  
Low Cost ◽  
Dye Sensitized Solar Cells ◽  
Ruthenium Complexes ◽  
Practical Applications ◽  
Photovoltaic Energy ◽  
Dye Sensitized ◽  
Sensitized Solar Cells ◽  
Excellent Stability

Dye-sensitized solar cells (DSSCs) have attracted considerable attention in recent years due to the possibility of low-cost conversion of photovoltaic energy. The DSSCs-based ruthenium complexes as sensitizers show high efficiency and excellent stability, implying potential practical applications. This review focuses on recent advances in design and preparation of efficient ruthenium sensitizers and their applications in DSSCs, including thiocyanate ruthenium sensitizers and thiocyanate-free ruthenium sensitizers.

Sign in / Sign up

Export Citation Format

Share Document