Boosting Ensemble Learning for Hyperspectral Image Classification Using Tangent Collaborative Representation

Recently, Collaborative Representation Classification (CRC) has attracted much attention in hyperspectral image analysis. Due to uses the tangent plane to estimate the local manifold of the test sample. Tangent Collaborative Representation Classification (TCRC) achieve better performance. Furthermore, in order to improve the classification accuracy and reliability of hyperspectral remote sensing images, a novel Boosting-based Tangent Collaborative Representation ensemble method (Boost TCRC) for hyperspectral image classification is proposed. In this algorithm, Boost TCRC algorithm choose TCRC as base classifier and adjust the weight of the training samples adaptively by using the principle of Boosting. Increasing the weight of the misclassified samples so that the classifier concentrates on the training samples that are difficult to classify. Then assigns the weights according to the classification performance of the base classifier based on the residual domain fusion. Finally, the principle of minimum reconstruction error is adopted to classify the test sample. The performance of the proposed algorithm was comprehensively evaluated by hyperspectral remote sensing image data such as HyMap (Hyperspectral Mapper) and AVIRIS (Airbone Visible Infrared Imaging Spectrometer). The Boosting method can effectively improve the classification effect of the TCRC algorithm. For HyMap data, the overall classification accuracy and kappa coefficient of Boost TCRC algorithm are 93.73% and 0.920 8 respectively. Two precision values are higher than TCRC algorithm by 2.82% and 0.032 3, and are higher than the AdaBoost ELM algorithm by 1.81% and 0.022 5. For AVIRIS data, the overall classification accuracy and kappa coefficient of Boost TCRC algorithm are 84.11% and 0.8120 respectively. Two precision values are higher than TCRC algorithm by 3.97% and 0.049 3, and are higher than AdaBoost ELM algorithm by 12.02% and 0.143 6.     

Near-infrared spectroscopy and imaging in food quality and safety

Over the last two decades, near-infrared spectroscopy (NIRS) has established itself as a non-destructive analytical technique in a variety of disciplines. However, recent technological advancements in hardware design and data mining techniques have unleashed the potential of NIRS to become a tool of choice for routine analyses of agricultural products. The current paper synthesizes the status of NIRS in the agri-food industry in terms of hardware and software development as well as the direction in which the NIRS research is headed. An extensive review of literature reveals that the emphasis on hardware development is focused on developing compact, robust, and portable spectrometers and hyperspectral imaging (HSI) systems. The software development on the other hand is geared towards developing better preprocessing, analyses, and modeling techniques using chemometrics, support vector machines, and artificial neural networks. The four main agri-food sectors identified to be the beneficiaries of this research revolution are grain quality monitoring; post-harvest handling of fruits and vegetables; identification of contaminants in animal produce and feed; and food safety and authenticity. Apart from discussing the aforementioned topics, the paper also provides food scientists some working knowledge on parameters crucial to the performance of spectral and imaging systems. It is expected that further development of NIRS will help agricultural and food scientists to enhance the quality and safety of our food.     

Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques

Penicillium fungi are among the main defects that may affect the commercialization of citrus fruits. Economic losses in fruit production may become enormous if an early detection of that kind of fungi is not carried out. That early detection is usually based either on UltraViolet light carried out manually. This work presents a new approach based on hyperspectral imagery for defect segmentation. Both the physical device and the data processing (geometric corrections and band selection) are presented. Achieved results using classifiers based on Artificial Neural Networks and Decision Trees show an accuracy around 98%; it shows up the suitability of the proposed approach.     

Development of Solar Spectroradiometer for Meteorological Observation

A new generation of solar spectroradiometerhas been developed by CUST/JRSI to improve solarirradiance observation data underhyperspectral resolution. It is based on the grating spectroradiometer with a back-thinned CCD linear image sensor and is operated in a hermetically sealed enclosure. The solar spectroradiometer is designed to measure the solar spectral irradiance from 300nm to 1100nm wavelength range with the spectral resolution of 2nm (the full width at half maximum). The optical bench is optimized to minimize stray light. The Peltier device is used to stabilize the temperature of CCD sensor to 25℃, while the change of temperature of CCD sensor is controlled to ±1℃ by the dedicated Peltierdriver and control circuit.     

Quantifying spectral changes experienced by plasmonic nanoparticles in a cellular environment to inform biomedical nanoparticle design

Metal nanoparticles (NPs) scatter and absorb light in precise, designable ways, making them agile candidates for a variety of biomedical applications. When NPs are introduced to a physiological environment and interact with cells, their physicochemical properties can change as proteins adsorb on their surface and they agglomerate within intracellular endosomal vesicles. Since the plasmonic properties of metal NPs are dependent on their geometry and local environment, these physicochemical changes may alter the NPs'' plasmonic properties, on which applications such as plasmonic photothermal therapy and photonic gene circuits are based. Here we systematically study and quantify how metal NPs'' optical spectra change upon introduction to a cellular environment in which NPs agglomerate within endosomal vesicles. Using darkfield hyperspectral imaging, we measure changes in the peak wavelength, broadening, and distribution of 100-nm spherical gold NPs'' optical spectra following introduction to human breast adenocarcinoma Sk-Br-3 cells as a function of NP exposure dose and time. On a cellular level, spectra shift up to 78.6 ± 23.5 nm after 24 h of NP exposure. Importantly, spectra broaden with time, achieving a spectral width of 105.9 ± 11.7 nm at 95% of the spectrum''s maximum intensity after 24 h. On an individual intracellular NP cluster (NPC) level, spectra also show significant shifting, broadening, and heterogeneity after 24 h. Cellular transmission electron microscopy (TEM) and electromagnetic simulations of NPCs support the trends in spectral changes we measured. These quantitative data can help guide the design of metal NPs introduced to cellular environments in plasmonic NP-mediated biomedical technologies.     

高光谱数据融合研究

多传感器的遥感数据融合在城市规划、土地利用、矿产探测、军事侦察等领域有着非常广泛的应用前景。本文高光谱图像光谱分辨率高、空间分辨率低、多光谱图像空间分辨率高、光谱分辨率高的特点,阐述了其数据融合。特别介绍了CRISP锐化算法。     

两种DXA骨密度体模比较研究

研究比较国产QC-2型腰椎骨密度体模(以下称QC-2体模)和欧洲脊椎骨密度体模(以下称ESP体模)在双能X射线全身骨密度仪(以下称DXA)检定中的差异性。用DXA仪器对这两种体模分别进行检测,对测量结果进行比较分析。(1)QC-2型体模和ESP型体分别被仪器进行测量时,仪器测量的BMD同两个体模的BMD相比,误差分别在-15.1%~11.5%和-16.1%~12.5%之间;而且,两个体模的各自标称值与相应的仪器测量值之间,分别都有非常好的线性关系,r0.99。(2)用回归方程进行校正后,仪器值(BMD)与两个体模的各自的标称值之间的误差分别在-3.8%~4.4%和在-3.8%~4.4%之间。用成对样本均数比较方法,对校正结果进行统计分析,经配对t检验,二者结果没有显著差异(P0.05)。表明这两种腰椎骨密度体模都能用于双能X射线全身骨密度仪(DXA)的检定。     

PET/CT图像融合精度测试体模与测试方法研究

通过自主研制的体模,测试PET/CT图像融合精度,并验证体模的可行性和有效性。采集PET/CT融合图像数据,利用IDL和Matlab软件测量圆柱棒及试管在PET、CT图像中的坐标值,两坐标值的差值即为图像融合精度。自制体模通过模拟热区和冷区,可以准确、快速地测量PET/CT图像融合精度,该体模可对日常质量控制项目的体模进行测试。     

星载超光谱成像仪摆镜系统轴系的误差分析与设计

摆镜系统轴系的精度会影响星载超光谱成像仪的成像质量。轴系设计时采用了向心推力球轴承来调整轴系的装配误差。分析了摆镜系统工作时影响轴系精度的几个误差源,包括零件的尺寸误差、同轴度误差、配合误差等,按照误差理论设计并计算了各误差值,得到轴系的径向晃动误差和角运动误差。对加工好的轴系进行精度检测,实验结果符合理论结果,验证了该摆镜系统的轴系结构设计的合理性和可靠性,为该类航天运动部件的轴系结构设计提供了参考依据。     

Multivariate image analysis: A review with applications

Nowadays, image analysis is becoming more important because of its ability to perform fast and non-invasive low-cost analysis on products and processes. Image analysis is a wide denomination that encloses classical studies on gray scale or RGB images, analysis of images collected using few spectral channels (sometimes called multispectral images) or, most recently, data treatments to deal with hyperspectral images, where the spectral direction is exploited in its full extension. Pioneering data treatments in image analysis were applied to simple images mainly for defect detection, segmentation and classification by the Computer Science community. From the late 80s, the chemometric community joined this field introducing powerful tools for image analysis, which were already in use for the study of classical spectroscopic data sets and were appropriately modified to fit the particular characteristics of image structures. These chemometric approaches adapt to images of all kinds, from the simplest to the hyperspectral images, and have provided new insights on the spatial and spectroscopic information of this kind of data sets. New fields open by the introduction of chemometrics on image analysis are exploratory image analysis, multivariate statistical process control (monitoring), multivariate image regression or image resolution. This paper reviews the different techniques developed in image analysis and shows the evolution in the information provided by the different methodologies, which has been heavily pushed by the increasing complexity of the image measurements in the spatial and, particularly, in the spectral direction.