Multiparameter Sensing of Oxygen and pH at Biological Interfaces via Hyperspectral Imaging of Luminescent Sensor Nanoparticles.

Chemical dynamics in biological samples are seldom stand-alone processes but represent the outcome of complicated cascades of interlinked reaction chains. In order to understand these processes and how they correlate, it is important to monitor several parameters simultaneously at high spatial and temporal resolution. Hyperspectral imaging is a promising tool for this, as it provides broad-range spectral information in each pixel, enabling the use of multiple luminescent indicator dyes, while simultaneously providing information on sample structures and optical properties. In this study, we first characterized pH- and O2-sensitive indicator dyes incorporated in different polymer matrices as optical sensor nanoparticles to provide a library for (hyperspectral) chemical imaging. We then demonstrate the successful combination of a pH-sensitive indicator dye (HPTS(DHA)3), an O2-sensitive indicator dye (PtTPTBPF), and two reference dyes (perylene and TFPP), incorporated in polymer nanoparticles for multiparameter chemical imaging of complex natural samples such as green algal biofilms (Chlorella sorokiniana) and seagrass leaves (Zostera marina) with high background fluorescence. We discuss the system-specific challenges and limitations of our approach and further optimization possibilities. Our study illustrates how multiparameter chemical imaging with hyperspectral read-out can now be applied on natural samples, enabling the alignment of several chemical parameters to sample structures.

Quantitative measurement of internal quality of carrots using hyperspectral imaging and multivariate analysis.

The study aimed to measure the carotenoid (Car) and pH contents of carrots using hyperspectral imaging. A total of 300 images were collected using a hyperspectral imaging system, covering 472 wavebands from 400 to 1000 nm. Regions of interest (ROIs) were defined to extract average spectra from the hyperspectral images (HIS). We developed two models: least squares support vector machine (LS-SVM) and partial least squares regression (PLSR) to establish a quantitative analysis between the pigment amounts and spectra. The spectra and pigment contents were predicted and correlated using these models. The selection of EWs for modeling was done using the Successive Projections Algorithm (SPA), regression coefficients (RC) from PLSR models, and LS-SVM. The results demonstrated that hyperspectral imaging could effectively evaluate the internal attributes of carrot cortex and xylem. Moreover, these models accurately predicted the Car and pH contents of the carrot parts. This study provides a valuable approach for variable selection and modeling in hyperspectral imaging studies of carrots.

Parameter-based transfer learning for severity classification of atopic dermatitis using hyperspectral imaging.

BACKGROUND/PURPOSE: Because atopic dermatitis (AD) is a chronic inflammatory skin condition that causes structural changes, there is a growing need for noninvasive research methods to evaluate this condition. Hyperspectral imaging (HSI) captures skin structure features by exploiting light wavelength variations in penetration depth. In this study, parameter-based transfer learning was deployed to classify the severity of AD using HSI. Therefore, we aimed to obtain an optimal combination of classification results from the four models after constructing different source- and target-domain datasets. METHODS: We designated psoriasis, skin cancer, eczema, and AD datasets as the source datasets, and the set of images acquired via hyperspectral camera as the target dataset for wavelength-specific AD classification. We compared the severity classification performances of 96 combinations of sources, models, and targets. RESULTS: The highest classification performance of 83% was achieved when ResNet50 was trained on the augmented psoriasis dataset as the source, with the resulting parameters used to train the model on the target Near-infrared radiation (NIR) dataset. The second highest classification accuracy of 81% was achieved when ResNet50 was trained on the unaugmented psoriasis dataset as the source, with the resulting parameters used to train the model on the target R dataset. ResNet50 demonstrated potential as a generalized model for both the source and target data, also confirming that the psoriasis dataset is an effective training resource. CONCLUSION: The present study not only demonstrates the feasibility of the severity classification of AD based on hyperspectral images, but also showcases combinations and research scalability for domain exploration.

Hyperspectral Proximal Sensing for Estimating Photosynthetic Capacities at Leaf and Canopy Scales.

Agronomists, plant breeders, and plant biologists have been promoting the need to develop high-throughput methods to measure plant traits of interest for decades. Measuring these plant traits or phenotypes is often a bottleneck since skilled personnel, resources, and ample time are required. Additionally, plant phenotypic traits from only a select number of breeding lines or varieties can be quantified because the "gold standard" measurement of a desired trait cannot be completed in a timely manner. As such, numerous approaches have been developed and implemented to better understand the biology and production of crops and ecosystems. In this chapter, we explain one of the recent approaches leveraging hyperspectral measurements to estimate different aspects of photosynthesis. Notably, we outline the use of hyperspectral radiometer and imaging to rapidly estimate two of the rate-limiting steps of photosynthesis: the maximum rate of the carboxylation of Rubisco (Vcmax) and the maximum rate of electron transfer or regeneration of RuBP (Jmax).

Near-infrared hyperspectral imaging and robust statistics for in vivo non-melanoma skin cancer and actinic keratosis characterisation.

One of the most common forms of cancer in fair skinned populations is Non-Melanoma Skin Cancer (NMSC), which primarily consists of Basal Cell Carcinoma (BCC), and cutaneous Squamous Cell Carcinoma (SCC). Detecting NMSC early can significantly improve treatment outcomes and reduce medical costs. Similarly, Actinic Keratosis (AK) is a common skin condition that, if left untreated, can develop into more serious conditions, such as SCC. Hyperspectral imagery is at the forefront of research to develop non-invasive techniques for the study and characterisation of skin lesions. This study aims to investigate the potential of near-infrared hyperspectral imagery in the study and identification of BCC, SCC and AK samples in comparison with healthy skin. Here we use a pushbroom hyperspectral camera with a spectral range of ≈ 900 to 1600 nm for the study of these lesions. For this purpose, an ad hoc platform was developed to facilitate image acquisition. This study employed robust statistical methods for the identification of an optimal spectral window where the different samples could be differentiated. To examine these datasets, we first tested for the homogeneity of sample distributions. Depending on these results, either traditional or robust descriptive metrics were used. This was then followed by tests concerning the homoscedasticity, and finally multivariate comparisons of sample variance. The analysis revealed that the spectral regions between 900.66-1085.38 nm, 1109.06-1208.53 nm, 1236.95-1322.21 nm, and 1383.79-1454.83 nm showed the highest differences in this regard, with <1% probability of these observations being a Type I statistical error. Our findings demonstrate that hyperspectral imagery in the near-infrared spectrum is a valuable tool for analyzing, diagnosing, and evaluating non-melanoma skin lesions, contributing significantly to skin cancer research.

Identification of Olives Using In-Field Hyperspectral Imaging with Lightweight Models.

During the growing season, olives progress through nine different phenological stages, starting with bud development and ending with senescence. During their lifespan, olives undergo changes in their external color and chemical properties. To tackle these properties, we used hyperspectral imaging during the growing season of the olives. The objective of this study was to develop a lightweight model capable of identifying olives in the hyperspectral images using their spectral information. To achieve this goal, we utilized the hyperspectral imaging of olives while they were still on the tree and conducted this process throughout the entire growing season directly in the field without artificial light sources. The images were taken on-site every week from 9:00 to 11:00 a.m. UTC to avoid light saturation and glitters. The data were analyzed using training and testing classifiers, including Decision Tree, Logistic Regression, Random Forest, and Support Vector Machine on labeled datasets. The Logistic Regression model showed the best balance between classification success rate, size, and inference time, achieving a 98% F1-score with less than 1 KB in parameters. A reduction in size was achieved by analyzing the wavelengths that were critical in the decision making, reducing the dimensionality of the hypercube. So, with this novel model, olives in a hyperspectral image can be identified during the season, providing data to enhance a farmer's decision-making process through further automatic applications.

Acceleration of Hyperspectral Skin Cancer Image Classification through Parallel Machine-Learning Methods.

Hyperspectral imaging (HSI) has become a very compelling technique in different scientific areas; indeed, many researchers use it in the fields of remote sensing, agriculture, forensics, and medicine. In the latter, HSI plays a crucial role as a diagnostic support and for surgery guidance. However, the computational effort in elaborating hyperspectral data is not trivial. Furthermore, the demand for detecting diseases in a short time is undeniable. In this paper, we take up this challenge by parallelizing three machine-learning methods among those that are the most intensively used: Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGB) algorithms using the Compute Unified Device Architecture (CUDA) to accelerate the classification of hyperspectral skin cancer images. They all showed a good performance in HS image classification, in particular when the size of the dataset is limited, as demonstrated in the literature. We illustrate the parallelization techniques adopted for each approach, highlighting the suitability of Graphical Processing Units (GPUs) to this aim. Experimental results show that parallel SVM and XGB algorithms significantly improve the classification times in comparison with their serial counterparts.

An Adaptive Partial Least-Squares Regression Approach for Classifying Chicken Egg Fertility by Hyperspectral Imaging.

Partial least-squares (PLS) regression is a well known chemometric method used for predictive modelling, especially in the presence of many variables. Although PLS was not initially developed as a technique for classification tasks, scientists have reportedly used this approach successfully for discrimination purposes. Whereas some non-supervised learning approaches, including, but not limited to, PCA and k-means clustering, do well in identifying/understanding grouping and clustering patterns in multidimensional data, they are limited when the end target is discrimination, making PLS a preferable alternative. Hyperspectral imaging data on a total of 672 fertilized chicken eggs, consisting of 336 white eggs and 336 brown eggs, were used in this study. Hyperspectral images in the NIR region of the 900-1700 nm wavelength range were captured prior to incubation on day 0 and on days 1-4 after incubation. Eggs were candled on incubation day 5 and broken out on day 10 to confirm fertility. While a total number of 312 and 314 eggs were found to be fertile in the brown and white egg batches, respectively, the total number of non-fertile eggs in the same set of batches was 23 and 21, respectively. Spectral information was extracted from a segmented region of interest (ROI) of each hyperspectral image and spectral transmission characteristics were obtained by averaging the spectral information. A moving-thresholding technique was implemented for discrimination based on PLS regression results on the calibration set. With true positive rates (TPRs) of up to 100% obtained at selected threshold values of between 0.50 and 0.85 and on different days of incubation, the results indicate that the proposed PLS technique can accurately discriminate between fertile and non-fertile eggs. The adaptive PLS approach was, thereby, presented as suitable for handling hyperspectral imaging-based chicken egg fertility data.

Prediction of Soluble-Solid Content in Citrus Fruit Using Visible-Near-Infrared Hyperspectral Imaging Based on Effective-Wavelength Selection Algorithm.

Citrus fruits were sorted based on external qualities, such as size, weight, and color, and internal qualities, such as soluble solid content (SSC), acidity, and firmness. Visible and near-infrared (VNIR) hyperspectral imaging techniques were used as rapid and nondestructive techniques for determining the internal quality of fruits. The applicability of the VNIR hyperspectral imaging technique for predicting the SSC in citrus fruits was evaluated in this study. A VNIR hyperspectral imaging system with a wavelength range of 400-1000 nm and 100 W light source was used to acquire hyperspectral images from citrus fruits in two orientations (i.e., stem and calyx ends). The SSC prediction model was developed using partial least-squares regression (PLSR). Spectrum preprocessing, effective wavelength selection through competitive adaptive reweighted sampling (CARS), and outlier detection were used to improve the model performance. The performance of each model was evaluated using the coefficient of determination (R2) and root mean square error (RMSE). In the present study, the PLSR model was developed using only a citrus cultivar. The SSC prediction CARS-PLSR model with outliers removed exhibited R2 and RMSE values of approximatively 0.75 and 0.56 °Brix, respectively. The results of this study are expected to be useful in similar fields such as agricultural and food post-harvest management, as well as in the development of an online system for determining the SSC of citrus fruits.

Research on SPAD Estimation Model for Spring Wheat Booting Stage Based on Hyperspectral Analysis.

With the rapid progression of agricultural informatization technology, the methodologies of crop monitoring based on spectral technology are constantly upgraded. In order to carry out the efficient, precise and nondestructive detection of relative chlorophyll (SPAD) during the booting stage, we acquired hyperspectral reflectance data about spring wheat vertical distribution and adopted the fractional-order differential to transform the raw spectral data. After that, based on correlation analysis, fractional differential spectra and fractional differential spectral indices with strong correlation with SPAD were screened and fused. Then, the least-squares support vector machine (LSSSVM) and the least-squares support vector machine (SMA-LSSSVM) optimized on the slime mold algorithm were applied to construct the estimation models of SPAD, and the model accuracy was assessed to screen the optimal estimation models. The results showed that the 0.4 order fractional-order differential spectra had the highest correlation with SPAD, which was 9.3% higher than the maximum correlation coefficient of the original spectra; the constructed two-band differential spectral indices were more sensitive to SPAD than the single differential spectra, in which the correlation reached the highest level of 0.724. The SMA-LSSSVM model constructed based on the two-band fractional-order differential spectral indices was better than the single differential spectra and the integration of both, which realized the assessment of wheat SPAD.

Macro-micro exploration on dynamic interaction between aflatoxigenic Aspergillus flavus and maize kernels using Vis/NIR hyperspectral imaging and SEM technology.

Aspergillus flavus and its toxic metabolites-aflatoxins infect and contaminate maize kernels, posing a threat to grain safety and human health. Due to the complexity of microbial growth and metabolic processes, dynamic mechanisms among fungal growth, nutrient depletion of maize kernels and aflatoxin production is still unclear. In this study, visible/near infrared (Vis/NIR) hyperspectral imaging (HSI) combined with the scanning electron microscope (SEM) was used to elucidate the critical organismal interaction at kernel (macro-) and microscopic levels. As kernel damage is the main entrance for fungal invasion, maize kernels with gradually aggravated damages from intact to pierced to halved kernels with A. flavus were cultured for 0-120 h. The spectral fingerprints of the A. flavus-maize kernel complex over time were analyzed with principal components analysis (PCA) of hyperspectral images, where the pseudo-color score maps and the loading plots of the first three PCs were used to investigate the dynamic process of fungal infection and to capture the subtle changes in the complex with different hardness of the maize matrix. The dynamic growth process of A. flavus and the interactions of fungus-maize complexes were explained on a microscopic level using SEM. Specifically, fungus morphology, e.g., hyphae, conidia, and conidiophore (stipe) was accurately captured on the microscopic level, and the interaction process between A. flavus and nutrient loss from the maize kernel tissues (i.e., embryo, and endosperm) was described. Furthermore, the growth stage discrimination models based on PLSDA with the results of CCRC = 100 %, CCRV = 97 %, CCRIV = 93 %, and the prediction models of AFB1 based on PLSR with satisfactory performance (R2C = 0.96, R2V = 0.95, R2IV = 0.93 and RPD = 3.58) were both achieved. In conclusion, the results from both macro-level (Vis/NIR-HSI) and micro-level (SEM) assessments revealed the dynamic organismal interactions in A. flavus-maize kernel complex, and the detailed data could be used for modeling, and quantitative prediction of aflatoxin, which would establish a theoretical foundation for the early detection of fungal or toxin contaminated grains to ensure food security.

Essential spectral pixels-based improvement of UMAP classifying hyperspectral imaging data to identify minor compounds in food matrix.

Classifying big data in hyperspectral imaging (HSI) can be challenging when minor (low-concentrated) compounds are present in actual samples, as for chemical additives and adulterants in food matrix. Herein, we propose a new strategy to classify HSI data for the identification of adulterants in food material for the first time. This strategy is based on the selection of essential spectral pixels of full HSI data followed by the feature space construction using uniform manifold approximation and projection as well as the data clustering utilizing hierarchical clustering analysis on the reduced data (named ESPs-UMAP-HCA). We apply our approach to analyze two real NIR datasets and four new Raman datasets. Compared with non-ESPs UMAP-HCA and t-distributed stochastic neighbor embedding combined with ESPs and HCA (ESPs-t-SNE-HCA), the developed strategy provides well-separated clusters for major and minor compounds in food matrix. Finally, the adulterants as minor compounds are accurately identified, which is confirmed by the fact that the extracted spectra of them perfectly match with their pure spectra. In addition, their locations are found in the contribution map even though they are present in a few pixels. What's more, the proposed strategy does not need any a priori knowledge of the data structure and the class memberships and therefore reduced the studied difficulty and confirmation bias in the analysis of big HSI datasets. Overall, the proposed ESPs-UMAP-HCA method could be a potential approach for food adulteration detection.

Use of an uncrewed surface vehicle and near infrared hyperspectral imaging for sampling and analysis of aquatic microplastics.

Data on MP in aquatic environments have low resolution in space and time. Scaling up sampling and increasing analysis throughput are the main bottlenecks. We combined two approaches: an uncrewed surface vehicle (USV) and near infrared hyperspectral imaging (NIR-HSI) for sampling and analysis of MP > 300 µm. We collected 35 water samples over 4 d in a coastal area. Samples were analyzed using NIR-HSI and Fourier transform infrared spectroscopy (FTIR). Spiked samples were used to determine recovery. We conclude that using a USV can mitigate issues of traditional trawls like scalability, repeatability, and contamination. NIR-HSI detects more polyethylene but less polypropylene than FTIR analysis and reduces analysis time significantly. Highly variable concentrations were found at both sampling locations, with mean MP concentration of 0.28 and 0.01 MP m-3 for location A and B respectively. USV sampling in tandem with NIR-HSI is an effective analytical pipeline for MP monitoring.

Rapid and Non-Destructive Prediction of Moisture Content in Maize Seeds Using Hyperspectral Imaging.

The moisture content of corn seeds is a crucial indicator for evaluating seed quality and is also a fundamental aspect of grain testing. In this experiment, 80 corn samples of various varieties were selected and their moisture content was determined using the direct drying method. The hyperspectral imaging system was employed to capture the spectral images of corn seeds within the wavelength range of 1100-2498 nm. By utilizing seven preprocessing techniques, including moving average, S-G smoothing, baseline, normalization, SNV, MSC, and detrending, we preprocessed the spectral data and then established a PLSR model for comparison. The results show that the model established using the normalization preprocessing method has the best prediction performance. To remove spectral redundancy and simplify the prediction model, we utilized SPA, CASR, and UVE algorithms to extract feature wavelengths. Based on three algorithms (PLSR, PCR, and SVM), we constructed 12 predictive models. Upon evaluating these models, it was determined that the normalization-SPA-PLSR algorithm produced the most accurate prediction. This model boasts high RC2 and RP2 values of 0.9917 and 0.9914, respectively, along with low RMSEP and RMSECV values of 0.0343 and 0.0257, respectively, indicating its exceptional stability and predictive capabilities. This suggests that the model can precisely estimate the moisture content of maize seeds. The results showed that hyperspectral imaging technology provides technical support for rapid and non-destructive prediction of corn seed moisture content and new methods in seed quality evaluation.

Non-destructive detection of defective maize kernels using hyperspectral imaging and convolutional neural network with attention module.

Rapid, effective and non-destructive detection of the defective maize kernels is crucial for their high-quality storage in granary. Hyperspectral imaging (HSI) coupled with convolutional neural network (CNN) based on spectral and spatial attention (Spl-Spal-At) module was proposed for identifying the different types of maize kernels. The HSI data within 380-1000 nm of six classes of sprouted, heat-damaged, insect-damaged, moldy, broken and healthy kernels was collected. The CNN-Spl-At, CNN-Spal-At and CNN-Spl-Spal-At models were established based on the spectra, images and their fusion features as inputs for the recognition of different kernels. Further compared the performances of proposed models and conventional models were built by support vector machine (SVM) and extreme learning machine (ELM). The results indicated that the recognition ability of CNN with attention series models was significantly better than that of SVM and ELM models and fused features were more conducive to expressing the appearance of different kernels than single features. And the CNN-Spl-Spal-At model had an optimal recognition result with high average classification accuracy of 98.04 % and 94.56 % for the training and testing sets, respectively. The recognition results were visually presented on the surface image of kernels with different colors. The CNN-Spl-Spal-At model was built in this study could effectively detect defective maize kernels, and it also had great potential to provide the analysis approaches for the development of non-destructive testing equipment based on HSI technique for maize quality.

Coral reefs in transition: Temporal photoquadrat analyses and validation of underwater hyperspectral imaging for resource-efficient monitoring in Guam.

The island of Guam in the west Pacific has seen a significant decrease in coral cover since 2013. Lafac Bay, a marine protected area in northeast Guam, served as a reference site for benthic communities typical of forereefs on the windward side of the island. The staghorn coral Acropora abrotanoides is a dominant and characteristic ecosystem engineer of forereef communities on exposed shorelines. Photoquadrat surveys were conducted in 2015, 2017, and 2019, and a diver-operated hyperspectral imager (i.e., DiveRay) was used to survey the same transects in 2019. Machine learning algorithms were used to develop an automated pipeline to assess the benthic cover of 10 biotic and abiotic categories in 2019 based on hyperspectral imagery. The cover of scleractinian corals did not differ between 2015 and 2017 despite being subjected to a series of environmental disturbances in these years. Surveys in 2019 documented the almost complete decline of the habitat-defining staghorn coral Acropora abrotanoides (a practically complete disappearance from about 10% cover), a significant decrease (~75%) in the cover of other scleractinian corals, and a significant increase (~55%) in the combined cover of bare substrate, turf algae, and cyanobacteria. The drastic change in community composition suggests that the reef at Lafac Bay is transitioning to a turf algae-dominated community. However, the capacity of this reef to recover from previous disturbances suggests that this transition could be reversed, making Lafac Bay an excellent candidate for long-term monitoring. Community analyses showed no significant difference between automatically classified benthic cover estimates derived from the hyperspectral scans in 2019 and those derived from photoquadrats. These findings suggest that underwater hyperspectral imagers can be efficient and effective tools for fast, frequent, and accurate monitoring of dynamic reef communities.

Enhanced deep unrolling networks for snapshot compressive hyperspectral imaging.

Snapshot compressive hyperspectral imaging necessitates the reconstruction of a complete hyperspectral image from its compressive snapshot measurement, presenting a challenging inverse problem. This paper proposes an enhanced deep unrolling neural network, called EDUNet, to tackle this problem. The EDUNet is constructed via the deep unrolling of a proximal gradient descent algorithm and introduces two innovative modules for gradient-driven update and proximal mapping reflectivity. The gradient-driven update module leverages a memory-assistant descent approach inspired by momentum-based acceleration techniques, for enhancing the unrolled reconstruction process and improving convergence. The proximal mapping is modeled by a sub-network with a cross-stage spectral self-attention, which effectively exploits the inherent self-similarities present in hyperspectral images along the spectral axis. It also enhances feature flow throughout the network, contributing to reconstruction performance gain. Furthermore, we introduce a spectral geometry consistency loss, encouraging EDUNet to prioritize the geometric layouts of spectral curves, leading to a more precise capture of spectral information in hyperspectral images. Experiments are conducted using three benchmark datasets including KAIST, ICVL, and Harvard, along with some real data, comprising a total of 73 samples. The experimental results demonstrate that EDUNet outperforms 15 competing models across four metrics including PSNR, SSIM, SAM, and ERGAS.

Improving the geographical origin classification of Radix glycyrrhizae (licorice) through hyperspectral imaging assisted by U-Net fine structure recognition.

Radix glycyrrhizae (licorice) is extensively employed in traditional Chinese medicine, and serves as a crucial raw material in industries such as food and cosmetics. The quality of licorice from different origins varies greatly, so classification of its geographical origin is particularly important. This study proposes a technique for fine structure recognition and segmentation of hyperspectral images of licorice using deep learning U-Net neural networks to segment the tissue structure patterns (phloem, xylem, and pith). Firstly, the three partitions were separately labeled using the Labelme tool, which was utilized to train the U-Net model. Secondly, the obtained optimal U-Net model was applied to predict three partitions of all samples. Lastly, various machine learning models (LDA, SVM, and PLS-DA) were trained based on segmented hyperspectral data. In addition, a threshold method and a circumcircle method were applied to segment licorice hyperspectral images for comparison. The results revealed that compared with the threshold segmentation method (which yielded SVM classifier accuracies of 99.17%, 91.15%, and 92.50% on the training set, validation set, and test set, respectively), the U-Net segmentation method significantly enhanced the accuracy of origin classification (99.06%, 94.72% and 96.07%). Conversely, the circumcircle segmentation method did not effectively improve the accuracy of origin classification (99.65%, 91.16% and 92.13%). By integrating Raman imaging of licorice, it can be inferred that the U-Net model, designed for region segmentation based on the inherent tissue structure of licorice, can effectively improve the accuracy origin classification, which has positive significance in the development of intelligence and information technology of Chinese medicine quality control.

Nondestructive detection of saponin content in Panax notoginseng powder based on hyperspectral imaging.

This study investigated the feasibility of using hyperspectral imaging (HSI) technique to detect the saponin content in Panax notoginseng (PN) powder. The reflectance hyperspectral images of PN powder samples were collected in the spectral range of 400.6-999.9 nm. Savitzky-golay (SG) smoothing combined with detrending correction was utilized to preprocess the original spectral data. Two model population analysis (MPA) based methods, namely bootstrapping soft shrinkage (BOSS) and iteratively retains informative variables (IRIV) were employed to extract feature wavelengths from the full spectra. A generalized normal distribution optimization based extreme learning machine (GNDO-ELM) model was proposed to establish calibration model between spectra and saponin content, and compared with existing methods (GA-ELM, PSO-ELM and SSA-ELM). The result showed that the IRIV-GNDO-ELM model gave the best performance, with coefficient of determination for prediction (R2P) of 0.953 and root mean square error for prediction (RMSEP) of 0.115%. Therefore, it is possible to determine the saponin content of PN powder by using HSI technique.