Spectral Prediction Research Articles

A Mars Environment Chamber Coupled with Multiple In Situ Spectral Sensors for Mars Exploration.

Laboratory simulation is the only feasible way to achieve Martian environmental conditions on Earth, establishing a key link between the laboratory and Mars exploration. The mineral phases of some Martian surface materials (especially hydrated minerals), as well as their spectral features, are closely related to environmental conditions. Therefore, Martian environment simulation is necessary for Martian mineral detection and analysis. A Mars environment chamber (MEC) coupled with multiple in situ spectral sensors (VIS (visible)-NIR (near-infrared) reflectance spectroscopy, Raman spectroscopy, laser-induced breakdown spectroscopy (LIBS), and UV-VIS emission spectroscopy) was developed at Shandong University at Weihai, China. This MEC is a comprehensive research platform for Martian environmental parameter simulation, regulation, and spectral data collection. Here, the structure, function and performance of the MEC and the coupled spectral sensors were systematically investigated. The spectral characteristics of some geological samples were recorded and the effect of environmental parameter variations (such as gas pressure and temperature) on the spectral features were also acquired by using the in situ spectral sensors under various simulated Martian conditions. CO2 glow discharge plasma was generated and its emission spectra were assigned. The MEC and its tested functional units worked well with good accuracy and repeatability. China is implementing its first Mars mission (Tianwen-1), which was launched on 23 July 2020 and successfully entered into a Mars orbit on 10 February 2021. Many preparatory works such as spectral databases and prediction model building are currently underway using MECs, which will help us build a solid foundation for real Martian spectral data analysis and interpretation.

Application of spectral library prediction for parallel reaction monitoring of viral peptides.

A major part of the analysis of parallel reaction monitoring (PRM) data is the comparison of observed fragment ion intensities to a library spectrum. Classically, these libraries are generated by data‐dependent acquisition (DDA). Here, we test Prosit, a published deep neural network algorithm, for its applicability in predicting spectral libraries for PRM. For this purpose, we targeted 1529 precursors derived from synthetic viral peptides and analyzed the data with Prosit and DDA‐derived libraries. Viral peptides were chosen as an example, because virology is an area where in silico library generation could significantly improve PRM assay design. With both libraries a total of 1174 precursors were identified. Notably, compared to the DDA‐derived library, we could identify 101 more precursors by using the Prosit‐derived library. Additionally, we show that Prosit can be applied to predict tandem mass spectra of synthetic viral peptides with different collision energies. Finally, we used a spectral library predicted by Prosit and a DDA library to identify SARS‐CoV‐2 peptides from a simulated oropharyngeal swab demonstrating that both libraries are suited for peptide identification by PRM. Summarized, Prosit‐derived viral spectral libraries predicted in silico can be used for PRM data analysis, making DDA analysis for library generation partially redundant in the future.

Spectral acceleration prediction using genetic programming based approaches

Evolutionary computation (EC) is a widely used computational intelligence that facilitates the formulation of a range of complex engineering problems. This study tackled two hybrid EC techniques based on genetic programming (GP) for ground motion prediction equations (GMPEs). The first method coupled regression analysis with multi-objective genetic programming. In this way, the strategy was maximizing the accuracy and minimizing the models’ complexity simultaneously. The second approach incorporated mesh adaptive direct search (MADS) into gene expression programming to optimize the obtained coefficients. A big data set provided by the Pacific Earthquake Engineering Research Centre (PEER) was used for the model development. Two explicit formulations were developed during this effort. In those formulae, we correlated spectral acceleration to a set of seismological parameters, including the period of vibration, magnitude, the closest distance to the fault ruptured area, shear wave velocity averaged over the top 30 meters, and style of faulting. The GP-based models are verified by a comprehensive comparison with the most well-known methods for GMPEs. The results show that the proposed models are quite simple and straightforward. The high degrees of accuracy of the predictions are competitive with the NGA complex models. Correlations of the predicted data using GEP-MADs and MOGP-R models with the real observations seem to be better than those available in the literature. Three statistical measures for GMPEs, such as E (%), LLH, and EDR index, confirmed those observations.

Recognition of Moving Tracked and Wheeled Vehicles Based on Sound Analysis and Machine Learning Algorithms

The paper presents results of a preliminary study on verification of the possibility to establish simple methods to process acquired sound signals that were generated by a vehicle in motion; to determine its characteristic features for classification as a wheeled or tracked one. The analysis covered 220 signals acquired from real experiment and pre-processed with the use of power spectral density estimation (PSD) and linear prediction coding (LPC). The signal processing methods were used to generate features for which applicability in the classification process was assessed using a statistical method. The set of features was then optimised to reduce the dimensionality of data. Results of recognition obtained with the proposed non-iterative procedures for solving linearly separable problems were compared with results from standard methods, including SVM and k-NN. The developed features as well as selected methods of classification were proposed with respect to the possibility to implement them in low computational power computers for embedded applications.

Spectral Signature-Based Water Stress Characterization and Prediction of Wheat Yield under Varied Irrigation and Plant Bio-regulator Management Practices

Canopy reflectance based spectral indices help in effective irrigation scheduling of wheat for optimization of yield in water-scarce regions. A field experiment for two consecutive years (2013 to 2015) was conducted to evaluate the responses of wheat crop to exogenous application of plant bio-regulators (PBRs) in the water-scarce Deccan region of India (Baramati, Pune, Maharashtra). We predicted grain and biomass yields of wheat using water stress-sensitive spectral indices under varied water regimes. The water regimes were seven levels of irrigation water (equaling to 1.00, 0.85, 0.70, 0.55, 0.40, 0.25 and 0.10 times of cumulative open pan evaporation, CPE) and applied using a line-source sprinkler system). There were five PBRs, viz. thiourea, salicylic acid, potassium nitrate, gibberellin and ortho−silicic, with concentration 10 mM, 10 μM, 15 g L−1, 25 ppm and 8 ppm, respectively, applied at various growth stages, namely crown root initiation, flag leaf and seed milking stages. Water stress indices were computed from spectral reflectance pattern recorded at different crop growth stages using ASD FieldSpec-4 Spectroradiometer (350–2500 nm). The PBRs significantly influenced the canopy reflectance pattern and maintained superior values of water stress indices over the control (without PBRs) by stabilizing leaf pigments and water contents, controlling the stomatal opening and better water use. Among the five PBRs, thiourea and salicylic acid mitigated water stress better and improved overall grain yield (4.6–17.5%) and total biomass (3.6–15.3%). There was no significant (p < 0.05) variation in both yields (grains and biomass) up to IW: CPE 0.70, indicating that irrigation scheduling at 0.70 IW: CPE could be a better option rather than full irrigation in water-scarce areas. At flowering and milking stages, all spectral indices were correlated significantly with the wheat yields. Thus, these stages could be considered as more water-sensitive stages during entire wheat growth period. Regression models based on WI and NWI-2 accounted for 92% and 78% variation in the observed yields for grain and biomass, respectively, with minimum root-mean square error. Hence, to predict the grain and biomass yields of wheat, regression models based on WI and NWI-2 at milking stage can be used successfully.

Spectral Analysis and Prediction of the Wave Forces Acting on Coastal Bridge Decks

The wave action on a box girder-type bridge deck is experimentally investigated in this study. Two types of incident waves, namely, regular waves (RWs) and focused waves (FWs), are tested. Fourier, wavelet, and Hilbert spectra of the vertical wave forces are obtained and analyzed. Four different methods are then applied to obtain the low- and high-frequency components of the total vertical wave force. Based on the separation results, the relationship between the wave force and wave crest amplitude is thereafter examined. An empirical formula is proposed to predict the vertical wave force. It is hoped that the aforementioned empirical formula may be widely applied during bridge design.

Exploring the Suitability of UAS-Based Multispectral Images for Estimating Soil Organic Carbon: Comparison with Proximal Soil Sensing and Spaceborne Imagery

Soil organic carbon (SOC) is a variable of vital environmental significance in terms of soil quality and function, global food security, and climate change mitigation. Estimation of its content and prediction accuracy on a broader scale remain crucial. Although, spectroscopy under proximal sensing remains one of the best approaches to accurately predict SOC, however, spectroscopy limitation to estimate SOC on a larger spatial scale remains a concern. Therefore, for an efficient quantification of SOC content, faster and less costly techniques are needed, recent studies have suggested the use of remote sensing approaches. The primary aim of this research was to evaluate and compare the capabilities of small Unmanned Aircraft Systems (UAS) for monitoring and estimation of SOC with those obtained from spaceborne (Sentinel-2) and proximal soil sensing (field spectroscopy measurements) on an agricultural field low in SOC content. Nine calculated spectral indices were added to the remote sensing approaches (UAS and Sentinel-2) to enhance their predictive accuracy. Modeling was carried out using various bands/wavelength (UAS (6), Sentinel-2 (9)) and the calculated spectral indices were used as independent variables to generate soil prediction models using five-fold cross-validation built using random forest (RF) and support vector machine regression (SVMR). The correlation regarding SOC and the selected indices and bands/wavelengths was determined prior to the prediction. Our results revealed that the selected spectral indices slightly influenced the output of UAS compared to Sentinel-2 dataset as the latter had only one index correlated with SOC. For prediction, the models built on UAS data had a better accuracy with RF than the two other data used. However, using SVMR, the field spectral prediction models achieved a better overall result for the entire study (log(1/R), RPD = 1.40; R2CV = 0.48; RPIQ = 1.65; RMSEPCV = 0.24), followed by UAS and then Sentinel-2, respectively. This study has shown that UAS imagery can be exploited efficiently using spectral indices.

Spectral Prediction Features as a Solution for the Search Space Size Problem in Proteogenomics

Proteogenomics approaches often struggle with the distinction between true and false peptide-to-spectrum matches as the database size enlarges. However, features extracted from tandem mass spectrometry intensity predictors can enhance the peptide identification rate and can provide extra confidence for peptide-to-spectrum matching in a proteogenomics context. To that end, features from the spectral intensity pattern predictors MS2PIP and Prosit were combined with the canonical scores from MaxQuant in the Percolator postprocessing tool for protein sequence databases constructed out of ribosome profiling and nanopore RNA-Seq analyses. The presented results provide evidence that this approach enhances both the identification rate as well as the validation stringency in a proteogenomic setting.

Synchronization Dynamics in Non-Normal Networks: The Trade-Off for Optimality.

Synchronization is an important behavior that characterizes many natural and human made systems that are composed by several interacting units. It can be found in a broad spectrum of applications, ranging from neuroscience to power-grids, to mention a few. Such systems synchronize because of the complex set of coupling they exhibit, with the latter being modeled by complex networks. The dynamical behavior of the system and the topology of the underlying network are strongly intertwined, raising the question of the optimal architecture that makes synchronization robust. The Master Stability Function (MSF) has been proposed and extensively studied as a generic framework for tackling synchronization problems. Using this method, it has been shown that, for a class of models, synchronization in strongly directed networks is robust to external perturbations. Recent findings indicate that many real-world networks are strongly directed, being potential candidates for optimal synchronization. Moreover, many empirical networks are also strongly non-normal. Inspired by this latter fact in this work, we address the role of the non-normality in the synchronization dynamics by pointing out that standard techniques, such as the MSF, may fail to predict the stability of synchronized states. We demonstrate that, due to a transient growth that is induced by the structure’s non-normality, the system might lose synchronization, contrary to the spectral prediction. These results lead to a trade-off between non-normality and directedness that should be properly considered when designing an optimal network, enhancing the robustness of synchronization.

A hybrid genetic algorithm-neural network model for power spectral density compatible ground motion prediction

In this paper, the utility of power spectral density (PSD) in ground motion prediction for hazard analysis is examined. The main advantage of PSD is that the area under PSD of excitation gives the energy of the excitation and it is structure independent. The PSD of ground motion from past earthquakes and properties of PSD in terms of spectral moments are studied. 1487 accelerograms from 25 major past earthquakes with magnitude ranging from 4.9 to 7.9 taken from the ‘Pacific Earthquake Engineering Research Centre – Next Generation Attenuation’ database are considered. PSD of past ground motion data is used to form a hybrid genetic algorithm-neural network based attenuation relationship with magnitude of earthquake, Joyner-Boore distance and shear-wave velocity. PSD compatible time histories are generated using the proposed model. An application of the proposed model is demonstrated by developing a uniform hazard power spectral density for Delhi with a return period of 2500 years.

PO-1726: Clinical impact of spectral CT-based stopping power prediction for particle therapy planning

PO-1726: Clinical impact of spectral CT-based stopping power prediction for particle therapy planning

Effects of different particle sizes on the spectral prediction of soil organic matter

Soil organic matter (SOM) is an important criterion for soil quality. The rapid determination of SOM can provide basic data support for the implementation of precision agriculture. Although the spectral reflectance has been used to rapidly obtain the SOM content, the method is not convenient to comparisons between different research results because the selection pretreatment criteria are not the same for soil samples. In this study, soil samples were prepared with six different standards of <1 mm, 0.5–1 mm, 0.25–0.5 mm, 0.15–0.25 mm, 0.088–0.15 mm and <0.088 mm. The reflectance of the different soil samples were compared, and the correlation between the reflectance of different soil samples and SOM were analyzed, as were the modeling and precision of the predictions of SOM. The results show that the soil spectral reflectance and the correlations between the uniform samples and SOM increased with decreasing particle size. Among the six kinds of soil particles, <0.088 mm had the highest correlation with SOM, and the reciprocal correlation coefficient reached 0.84. In the process of single-variable and multivariate modeling, the mixed samples of <1 mm and <0.088 mm had a better prediction effect than the uniform sample. Although the prediction result of <1 mm was slightly worse than that of <0.088 mm, the modeling results were the same (coefficient of determination (R2) of 0.78), and the validation set also showed a satisfactory predictive ability (R2val = 0.77). The soil samples of <1 mm, regardless of the ease of comparison with other soil preparation standards or the ability to predict SOM showed a high correlation and stable predictive ability. Therefore, when measuring the soil spectrum, <1 mm would be ideal for the pre-treatment of soil samples.

Analytical Equations for Thermoacoustic Instability Sources and Acoustic Radiation from Reacting Turbulence

We seek to ascertain and understand source terms that drive thermoacoustic instability and acoustic radiation. We present a new theory based on the decomposition of the Navier-Stokes equations coupled with the mass fraction equations. A series of solutions are presented via the method of the vector Green’s function. We identify both combustion-combustion and combustion-aerodynamic interaction source terms. Both classical combustion noise theory and classical Rayleigh criterion are recovered from the presently developed more general theory. An analytical spectral prediction method is presented, and the two-point source terms are consistent with Lord Rayleigh’s instability model. Particular correlations correspond to the source terms of Lighthill, which represent the noise from turbulence and additional terms for the noise from reacting flow.

Raman spectroscopy to differentiate between fresh tissue samples of glioma and normal brain: a comparison with 5-ALA-induced fluorescence-guided surgery.

Raman spectroscopy is a biophotonic tool that can be used to differentiate between different tissue types. It is nondestructive and no sample preparation is required. The aim of this study was to evaluate the ability of Raman spectroscopy to differentiate between glioma and normal brain when using fresh biopsy samples and, in the case of glioblastomas, to compare the performance of Raman spectroscopy to predict the presence or absence of tumor with that of 5-aminolevulinic acid (5-ALA)-induced fluorescence. A principal component analysis (PCA)-fed linear discriminant analysis (LDA) machine learning predictive model was built using Raman spectra, acquired ex vivo, from fresh tissue samples of 62 patients with glioma and 11 glioma-free brain samples from individuals undergoing temporal lobectomy for epilepsy. This model was then used to classify Raman spectra from fresh biopsies from resection cavities after functional guided, supramaximal glioma resection. In cases of glioblastoma, 5-ALA-induced fluorescence at the resection cavity biopsy site was recorded, and this was compared with the Raman spectral model prediction for the presence of tumor. The PCA-LDA predictive model demonstrated 0.96 sensitivity, 0.99 specificity, and 0.99 accuracy for differentiating tumor from normal brain. Twenty-three resection cavity biopsies were taken from 8 patients after supramaximal resection (6 glioblastomas, 2 oligodendrogliomas). Raman spectroscopy showed 1.00 sensitivity, 1.00 specificity, and 1.00 accuracy for predicting tumor versus normal brain in these samples. In the glioblastoma cases, where 5-ALA-induced fluorescence was used, the performance of Raman spectroscopy was significantly better than the predictive value of 5-ALA-induced fluorescence, which showed 0.07 sensitivity, 1.00 specificity, and 0.24 accuracy (p = 0.0009). Raman spectroscopy can accurately classify fresh tissue samples into tumor versus normal brain and is superior to 5-ALA-induced fluorescence. Raman spectroscopy could become an important intraoperative tool used in conjunction with 5-ALA-induced fluorescence to guide extent of resection in glioma surgery.

Estimation of soil salt content using machine learning techniques based on remote-sensing fractional derivatives, a case study in the Ebinur Lake Wetland National Nature Reserve, Northwest China

AbstractSoil salinity is a common global environmental problem that severely restricts industrial, agricultural and human development. In Northwest China, soil salinity is a problem affecting the Lake Ebinur area and needs to be monitored and addressed. The use of optical remote sensing technology to for timely and accurate soil salinity monitoring has great potentials and can be crucial for industrial and agricultural development. Optical remote sensing technology is an important data source for monitoring of soil salinization because of its rich spectral information and high-resolution. Based on the HJ-1/HSI data of fractional derivative transformation, this paper calculated the parameters, such as the difference index (DI), normalized difference index (NDI), ratio index (RI) and salt index (SI), that can invert the spatial distribution of salinization and then calculates a particle swarm optimization support vector machine (PSO-SVM). These index parameters were used to invert the spatial distribution information of salinized soil to explore the influence of fractional derivatives on the estimation accuracy of the spatial distribution of salinized soil. The results showed the following: (1) The optimal model based on different fractional derivatives and exponential transformations was the DI transformation under the fractional derivative of 1.2-order. R2, RMSE and RPD were 0.66, 13.81 g/kg and 2.59, respectively. These data show that the model had a good prediction effect. (2) The application of fractional derivatives in the processing of hyperspectral images could highlight the spectral details of the images and enrich their pretreatment methods, which is of great significance for the inversion of the distribution of salinized soil by hyperspectral images. (3) In the lakeside area of Lake Ebinur, the soil is mainly saline to severely saline. In the northern mountainous region of Lake Ebinur, the soil is mainly non-saline soil to mildly saline soil. Finally, in the Kuitun riverbank area in the southeast of Lake Ebinur, the soils are mainly non-saline soils to mildly saline soils. The results of this study demonstrate the potential of spectral index optimization and prediction models to monitor soil salinization based on fractional derivatives. This technique highlights the spectral detail information and enriches the preprocessing methods of hyperspectral imagery, resulting in the mapping of the spatial distribution of the degree of soil salinization. This has practical importance for the prevention and control of soil salinization and its spatial extent in arid and semi-arid regions.

Quantitative NIR spectroscopy determination of coco-peat substrate moisture content: Effect of particle size and non-uniformity

The particle size and non-uniformity of solid particle samples directly affected the acquisition of samples spectral data. In this study, different particle size samples and mixed samples with two different particle size grade samples were applied to investigate the impact of particle size and non-uniformity on near-infrared (NIR) spectroscopy detection of moisture content in coco-peat substrate. Simultaneously, the pretreatment effect and capability of MSC and SNV on spectral scattering were studied. The results showed that the prediction accuracy of the spectral detection model for moisture content in coco-peat substrate was higher with smaller particle size or smaller non-uniformity; MSC and SNV had better effects on improving the accuracy of prediction models with small particle size samples or small non-uniformity samples; the optimal moisture content spectral prediction models for single particle size grade samples and mixed samples of two particle size grades could be respectively established when SNV was adopted to pretreat the samples spectral data of A and A-B. And the corresponding correlation coefficients of the two optimal models were 0.9964 and 0.9959 for calibration set, 0.9959 and 0.9957 for prediction set, respectively; the root mean square errors were 1.2299% and 1.0090% for calibration set, 1.2820% and 1.0723% for prediction set, respectively; the ratios of prediction to deviation were 10.83 and 10.51, respectively. The prediction model with the minimal spectral scattering influence could be built by combining physical pretreatment with spectral pretreatment. This study would provide a reference for reducing the scattering effect of solid particle sample spectral detection.

A Method of Evaluating Korean Articulation Quality for Rehabilitation of Articulation Disorder in Children

Articulation disorders are characterized by an inability to achieve clear pronunciation due to misuse of the articulators. In this paper, a method of detecting such disorders by comparing to the standard pronunciations is proposed. This method defines the standard pronunciations from the speeches of normal children by clustering them with three features which are the Linear Predictive Cepstral Coefficient (LPCC), the Mel-Frequency Cepstral Coefficient (MFCC), and the Relative Spectral Analysis Perceptual Linear Prediction (RASTA-PLP). By calculating the distance between the centroid of the standard pronunciation and the inputted pronunciation, disordered speech whose features locates outside the cluster is detected. 89 children (58 of normal children and 31 of children with disorders) were recruited. 35 U-TAP test words were selected and each word’s standard pronunciation is made from normal children and compared to each pronunciation of children with disorders. In the experiments, the pronunciations with disorders were successfully distinguished from the standard pronunciations.

Isolation Window Optimization of Data-Independent Acquisition Using Predicted Libraries for Deep and Accurate Proteome Profiling.

In silico spectral library prediction of all possible peptides from whole organisms has a great potential for improving proteome profiling by data-independent acquisition (DIA) and extending its scope of application. In combination with other recent improvements in the field of mass spectrometry (MS)-based proteomics, including sample preparation, peptide separation, and data analysis, we aimed to uncover the full potential of such an advanced DIA strategy by optimization of the data acquisition. The results demonstrate that the combination of high-quality in silico libraries, reproducible and high-resolution peptide separation using micropillar array columns, as well as neural network supported data analysis enables the use of long MS scan cycles without impairing the quantification performance. The study demonstrates that mean coefficient of variations of 4% were obtained even at only 1.5 data points per peak (full width at half-maximum) across different gradient lengths, which in turn improved proteome coverage up to more than 8000 proteins from HeLa cells using empirically corrected libraries and more than 7000 proteins using a whole human in silico predicted library. These data were obtained using a Q Exactive orbitrap mass spectrometer with moderate scanning speed (12 Hz) and perform very well in comparison to recent studies using more advanced MS instruments, which underline the high potential of this optimization strategy for various applications in clinical proteomics, microbiology, and molecular biology.

Low-Order Spherical Harmonic HRTF Restoration Using a Neural Network Approach

Spherical harmonic (SH) interpolation is a commonly used method to spatially up-sample sparse head related transfer function (HRTF) datasets to denser HRTF datasets. However, depending on the number of sparse HRTF measurements and SH order, this process can introduce distortions into high frequency representations of the HRTFs. This paper investigates whether it is possible to restore some of the distorted high frequency HRTF components using machine learning algorithms. A combination of convolutional auto-encoder (CAE) and denoising auto-encoder (DAE) models is proposed to restore the high frequency distortion in SH-interpolated HRTFs. Results were evaluated using both perceptual spectral difference (PSD) and localisation prediction models, both of which demonstrated significant improvement after the restoration process.

Energy efficiency in cloud computing based on mixture power spectral density prediction

Due to the budget and environmental issues, adaptive energy efficiency receives a lot of attention these days, especially for cloud computing. In the previous research, we developed a combined methodology based on nonparametric prediction and convex optimization to produce proactive energy efficiency-oriented solution. In this work, the predictive analysis was further enhanced by deriving the mixture power spectral density to model the complex cloud monitoring statistics. By engaging the improved technique to the predictive analysis, the prediction process was more adaptive to handle the fluctuation in system utilization. As a consequence, the optimization process could subsequently produce more appropriate setting for energy savings. After the infrastructure setting has been made available, the instruction of virtual machine migration was created and implemented by the cloud orchestrator. This instruction condensed the services into the pool of active facilities, satisfying the objective of power efficiency. Eventually, any physical machine out of the power configuration would be gradually terminated. Compared to our former method, the effectiveness of the proposed technique has been proven by cutting down 4.92% of energy consumption, while still maintaining a similar quality of services.