scholarly journals Classifying Reflectance Targets under Ambient Light Conditions Using Passive Spectral Measurements

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5375
Author(s):  
Ali Hamidisepehr ◽  
Michael P. Sama ◽  
Joseph S. Dvorak ◽  
Ole O. Wendroth ◽  
Michael D. Montross
Keyword(s):  
Spectral Data ◽  
Prediction Accuracy ◽  
Near Infrared ◽  
Machine Learning Algorithms ◽  
Spectral Signature ◽  
Integration Time ◽  
Ambient Light ◽  
Light Conditions ◽  
Light Spectrum ◽  
Compensation Methods

Collecting remotely sensed spectral data under varying ambient light conditions is challenging. The objective of this study was to test the ability to classify grayscale targets observed by portable spectrometers under varying ambient light conditions. Two sets of spectrometers covering ultraviolet (UV), visible (VIS), and near−infrared (NIR) wavelengths were instrumented using an embedded computer. One set was uncalibrated and used to measure the raw intensity of light reflected from a target. The other set was calibrated and used to measure downwelling irradiance. Three ambient−light compensation methods that successively built upon each other were investigated. The default method used a variable integration time that was determined based on a previous measurement to maximize intensity of the spectral signature (M1). The next method divided the spectral signature by the integration time to normalize the spectrum and reveal relative differences in ambient light intensity (M2). The third method divided the normalized spectrum by the ambient light spectrum on a wavelength basis (M3). Spectral data were classified using a two−step process. First, raw spectral data were preprocessed using a partial least squares (PLS) regression method to compress highly correlated wavelengths and to avoid overfitting. Next, an ensemble of machine learning algorithms was trained, validated, and tested to determine the overall classification accuracy of each algorithm. Results showed that simply maximizing sensitivity led to the best prediction accuracy when classifying known targets. Average prediction accuracy across all spectrometers and compensation methods exceeded 93%.

Robustness of Models Based on NIR Spectra for Sugar Content Prediction in Apples

2003 ◽  
Vol 11 (2) ◽  
pp. 97-107 ◽  
Author(s):  
Natalia Hernández Sánchez ◽  
Sébastien Lurol ◽  
Jean Michel Roger ◽  
Véronique Bellon-Maurel
Keyword(s):  
Standard Error ◽  
Prediction Accuracy ◽  
Near Infrared ◽  
Sugar Content ◽  
The Other ◽  
Ambient Light ◽  
Golden Delicious ◽  
Two Factors ◽  
The Relationship ◽  
Metrological Parameters

The sugar content of Golden Delicious apples is predicted using near infrared (NIR) spectrometry. The study focuses on the metrological characteristics of the sugar content measurement and external parameters involved in the lack of robustness of the NIR-based model. The external parameters were fruit temperature, spectrometer temperature and ambient light. The first two factors influenced the prediction accuracy: (i) a fruit temperature variation altered the prediction, the relationship seems to be described by a non-linear model within the considered temperature range, (ii) a variation of the spectrometer temperature also altered the prediction, the relationship is described by a linear function for a temperature between 4 and 30°C. Ambient light did not show to have any influence on the NIR-based model. The analysis of the metrological parameters showed a satisfactory repeatibility in sugar prediction with a low error, 0.073°Brix. The model reproducibility was good regarding bias-corrected standard error of prediction ( SEPc) without significant differences between experiments, on the other hand a bias remained even if the previous parameters were maintained constant. These results will be taken into account in future measurements, in order to improve the robustness of the NIR-based model developed for apples.

scholarly journals Simulated Annealing-Based Hyperspectral Data Optimization for Fish Species Classification: Can the Number of Measured Wavelengths Be Reduced?

2021 ◽  
Vol 11 (22) ◽  
pp. 10628
Author(s):  
John Chauvin ◽  
Ray Duran ◽  
Kouhyar Tavakolian ◽  
Alireza Akhbardeh ◽  
Nicholas MacKinnon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Simulated Annealing ◽  
Spectral Data ◽  
Near Infrared ◽  
Tunable Filter ◽  
Hyperspectral Data ◽  
Machine Learning Algorithms ◽  
Imaging Systems ◽  
Large Set ◽  
Scanning Method

Relative to standard red/green/blue (RGB) imaging systems, hyperspectral imaging systems offer superior capabilities but tend to be expensive and complex, requiring either a mechanically complex push-broom line scanning method, a tunable filter, or a large set of light emitting diodes (LEDs) to collect images in multiple wavelengths. This paper proposes a new methodology to support the design of a hypothesized system that uses three imaging modes—fluorescence, visible/near-infrared (VNIR) reflectance, and shortwave infrared (SWIR) reflectance—to capture narrow-band spectral data at only three to seven narrow wavelengths. Simulated annealing is applied to identify the optimal wavelengths for sparse spectral measurement with a cost function based on the accuracy provided by a weighted k-nearest neighbors (WKNN) classifier, a common and relatively robust machine learning classifier. Two separate classification approaches are presented, the first using a multi-layer perceptron (MLP) artificial neural network trained on sparse data from the three individual spectra and the second using a fusion of the data from all three spectra. The results are compared with those from four alternative classifiers based on common machine learning algorithms. To validate the proposed methodology, reflectance and fluorescence spectra in these three spectroscopic modes were collected from fish fillets and used to classify the fillets by species. Accuracies determined from the two classification approaches are compared with benchmark values derived by training the classifiers with the full resolution spectral data. The results of the single-layer classification study show accuracies ranging from ~68% for SWIR reflectance to ~90% for fluorescence with just seven wavelengths. The results of the fusion classification study show accuracies of about 95% with seven wavelengths and more than 90% even with just three wavelengths. Reducing the number of required wavelengths facilitates the creation of rapid and cost-effective spectral imaging systems that can be used for widespread analysis in food monitoring/food fraud, agricultural, and biomedical applications.

Estimation of grape Isabel's quality in pre-harvest based on spectral signature

2020 ◽  
Vol 1 (1) ◽  
pp. 011-013
Author(s):  
Maria Aparecida Lima ◽  
Antônio Odair Santos
Keyword(s):  
Phenolic Compounds ◽  
Spectral Data ◽  
Near Infrared ◽  
Motor Vehicle ◽  
Spectral Signature ◽  
Grape Quality ◽  
Calibration Models ◽  
Non Destructive

A non-destructive technique, that estimate the quality of the grape, was used in a vineyard, aiming to evaluate the logistics of use a portable infrared equipment [NIRs] (Brimrose Corp, USA) incorporated in a motor vehicle. The equipment estimate in the field quantifies phenolic compounds from the Isabel grape through spectral data. The spectra were taken in clusters of grapes, in the 2017 and 2018 harvests. The Near Infrared instrumentations were connected to a laptop and positioned in a micro-tractor (Gator-John Deere) to travel the vineyard. The phenolic compounds were estimates using predetermined calibration models. This methodology proved to be promising for estimating the grape quality.

scholarly journals (Near-Infrared) Fluorescence-Guided Surgery Under Ambient Light Conditions: A Next Step to Embedment of the Technology in Clinical Routine

2016 ◽  
Vol 23 (8) ◽  
pp. 2586-2595 ◽  
Author(s):  
Nynke S. van den Berg ◽  
Mitsuharu Miwa ◽  
Gijs H. KleinJan ◽  
Takayuki Sato ◽  
Yoshiki Maeda ◽  
...  
Keyword(s):  
Near Infrared ◽  
Ambient Light ◽  
Light Conditions ◽  
Clinical Routine ◽  
Near Infrared Fluorescence ◽  
Guided Surgery ◽  
Fluorescence Guided Surgery

Machine Learning Approach for Predicting Lane-Change Maneuvers using the SHRP2 Naturalistic Driving Study Data

2021 ◽  
pp. 036119812110035
Author(s):  
Anik Das ◽  
Mohamed M. Ahmed
Keyword(s):  
Machine Learning ◽  
Prediction Accuracy ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Lane Change ◽  
Adaptive Boosting ◽  
Extreme Gradient Boosting ◽  
Naturalistic Driving Study ◽  
Naturalistic Driving ◽  
Change Prediction

Accurate lane-change prediction information in real time is essential to safely operate Autonomous Vehicles (AVs) on the roadways, especially at the early stage of AVs deployment, where there will be an interaction between AVs and human-driven vehicles. This study proposed reliable lane-change prediction models considering features from vehicle kinematics, machine vision, driver, and roadway geometric characteristics using the trajectory-level SHRP2 Naturalistic Driving Study and Roadway Information Database. Several machine learning algorithms were trained, validated, tested, and comparatively analyzed including, Classification And Regression Trees (CART), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Support Vector Machine (SVM), K Nearest Neighbor (KNN), and Naïve Bayes (NB) based on six different sets of features. In each feature set, relevant features were extracted through a wrapper-based algorithm named Boruta. The results showed that the XGBoost model outperformed all other models in relation to its highest overall prediction accuracy (97%) and F1-score (95.5%) considering all features. However, the highest overall prediction accuracy of 97.3% and F1-score of 95.9% were observed in the XGBoost model based on vehicle kinematics features. Moreover, it was found that XGBoost was the only model that achieved a reliable and balanced prediction performance across all six feature sets. Furthermore, a simplified XGBoost model was developed for each feature set considering the practical implementation of the model. The proposed prediction model could help in trajectory planning for AVs and could be used to develop more reliable advanced driver assistance systems (ADAS) in a cooperative connected and automated vehicle environment.

scholarly journals Biomechanical, biochemical, and near infrared spectral data of bovine knee ligaments and patellar tendon

Data in Brief ◽  
2021 ◽  
Vol 36 ◽  
pp. 106976
Author(s):  
Aapo Ristaniemi ◽  
Jari Torniainen ◽  
Tommi Paakkonen ◽  
Lauri Stenroth ◽  
Mikko A.J. Finnilä ◽  
...  
Keyword(s):  
Spectral Data ◽  
Patellar Tendon ◽  
Near Infrared ◽  
Knee Ligaments ◽  
Infrared Spectral

Prediction of neutral detergent fiber content in corn stover using near-infrared spectroscopy technique

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Xuyang Pan ◽  
Laijun Sun ◽  
Guobing Sun ◽  
Panxiang Rong ◽  
Yuncai Lu ◽  
...  
Keyword(s):  
Infrared Spectroscopy ◽  
Prediction Model ◽  
Spectral Data ◽  
Corn Stover ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Cross Validation ◽  
Fiber Content ◽  
Partial Least Square ◽  
Neutral Detergent Fiber

AbstractNeutral detergent fiber (NDF) content was the critical indicator of fiber in corn stover. This study aimed to develop a prediction model to precisely measure NDF content in corn stover using near-infrared spectroscopy (NIRS) technique. Here, spectral data ranging from 400 to 2500 nm were obtained by scanning 530 samples, and Monte Carlo Cross Validation and the pretreatment were used to preprocess the original spectra. Moreover, the interval partial least square (iPLS) was employed to extract feature wavebands to reduce data computation. The PLSR model was built using two spectral regions, and it was evaluated with the coefficient of determination (R2) and root mean square error of cross validation (RMSECV) obtaining 0.97 and 0.65%, respectively. The overall results proved that the developed prediction model coupled with spectral data analysis provides a set of theoretical foundations for NIRS techniques application on measuring fiber content in corn stover.

Sign in / Sign up

Export Citation Format

Share Document