Rapid prediction of acid detergent fiber content in corn stover based on NIR-spectroscopy technology

Li, Jinlong; Li, Yingsong; Lu, Yuncai; Pan, Xuyang; Zhang, Xiaolin; Liu, Yangyang; Song, Ziwei

doi:10.1016/j.ijleo.2018.11.045

Cited by 13 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advantage of MSC processing is that the spectrum of the processing results will be similar to the their average spectra [6]. SG smoothing effectively eliminates high-frequency random noise, making peaks and valleys more smooth [10]. The derivative can solve overlapping peaks produced by the additive variation of baseline intensity spectrum as the wavelength increases [8].…”

Section: Characteristics Of Raw and Pretreated Nir Spectramentioning

confidence: 99%

Optical characterization of NIR spectra for chemomectric model of cocoa pod husk fermented for animal feed

Wahyudi

Munawar

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Cocoa pods husk (CPH) fermented can be used as an alternative animal feedstuff. Near-infrared (NIR) spectroscopy has been shown in order to determine the nutritional contents of CPH fermented. This study aims to assess the characteristics of the NIR raw spectra and pretreated spectra for chemomectric model. The raw spectrum pretreatments used include multiplicative scatter correction (MSC), Savitzky-Golay smoothing (SG), and first derivative (1st D) and a combination of each pretreatment, namely MSC + SG, MSC + 1st D, SG + 1st D, and MSC + SG + 1st D. The results showed that the NIR spectrum of CPH fermented had six absorption peaks associated with CPH nutrient content such as moisture (1450 and 1940 nm), lipids (1200 and 1731 nm), starch (2380 nm), and protein (2125 nm). MSC tries to eliminate the scattering and correct the differences in the baseline and trend. SG smoothing is used to remove high-frequency random noise, and peaks. 1st D can be used for baseline correction. Combination of each pretreatment, namely MSC + SG, MSC + 1st D, SG + 1st D, and MSC + SG + 1st D. The combination of pretreatment methods can reduce scattering and noise interference such as offset, dispersion, and overlap and improve smoothness. In addition, information relating to the nutritional contents of CPH was clearly highlighted. This study concludes that a combination of pretreatment methods is better at revealing hidden information and reducing noise than a specific pretreatment method. Combination of MSC + SG pretreatment in this study is considered to generate a spectrum that has good characteristics to be used in chemometric modeling due to it is able to provide information regarding the nutritional contents of CPH clearly, both for qualification and quantification.

show abstract

Section: Characteristics Of Raw and Pretreated Nir Spectramentioning

confidence: 99%

Optical characterization of NIR spectra for chemomectric model of cocoa pod husk fermented for animal feed

Wahyudi

Munawar

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…We adopted four evaluation metrics (i.e., mean absolute percentage error (MAPE), root mean squared error (RMSE), mean absolute error (MAE) and goodness of fit (R 2 )) [39][40][41] to assess and compare the outputs of all models. The detailed formulations of the four indexes are written as follows:…”

Section: Performance Metricsmentioning

confidence: 99%

Multivariate Transfer Passenger Flow Forecasting with Data Imputation by Joint Deep Learning and Matrix Factorization

Guo

et al. 2023

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Accurate forecasting of the future transfer passenger flow from historical data is essential for helping travelers to adjust their trips, optimal resource allocation and alleviating traffic congestion. However, current studies have mainly emphasized predicting traffic parameters for a single type of transport, while lacking research into transfer passenger flow influenced by multiple factors across different transport modes. Additionally, efficient traffic prediction relies on high-quality traffic data, yet data loss issues are inevitable but often ignored. To fill these gaps, we present for the first time a reliable joint long short-term memory with matrix factorization deep learning model (i.e., Joint-IF) for accurate imputation and forecasting of transfer passenger flow between metro and bus. This hybrid Joint-IF model uses a repair-before-prediction strategy to deliver the final high-quality outputs. In particular, we simulate a variety of missing combinations under the natural conditions and apply a low-rank matrix factorization to infer those lost values. In addition, we investigate the effects of crucial parameters and spatiotemporal features on transfer flow prediction. To validate the effectiveness of Joint-IF, a large series of experiments are carried out for models’ comparison and validation on the real-world transfer passenger flow dataset of the Shenzhen public transport system, and the results show that the proposed Joint-IF performs better for both imputation and forecasting of transfer passenger flow relative to the baseline models in terms of accuracy and stability.

show abstract

“…We adopted four evaluation metrics to evaluate the effectiveness of the ST-CRMF: mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute error (MAE), and the square of determination coefficient (i.e.,

) [ 39 , 40 ]. The formulas for these indexes were defined as:

where

is the size of the index set

;

and

are the actual and predicted values, respectively;

is the average of actual values.…”

Section: Experiments Studymentioning

confidence: 99%

ST-CRMF: Compensated Residual Matrix Factorization with Spatial-Temporal Regularization for Graph-Based Time Series Forecasting

Pian

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Despite the extensive efforts, accurate traffic time series forecasting remains challenging. By taking into account the non-linear nature of traffic in-depth, we propose a novel ST-CRMF model consisting of the Compensated Residual Matrix Factorization with Spatial-Temporal regularization for graph-based traffic time series forecasting. Our model inherits the benefits of MF and regularizer optimization and further carries out the compensatory modeling of the spatial-temporal correlations through a well-designed bi-directional residual structure. Of particular concern is that MF modeling and later residual learning share and synchronize iterative updates as equal training parameters, which considerably alleviates the error propagation problem that associates with rolling forecasting. Besides, most of the existing prediction models have neglected the difficult-to-avoid issue of missing traffic data; the ST-CRMF model can repair the possible missing value while fulfilling the forecasting tasks. After testing the effects of key parameters on model performance, the numerous experimental results confirm that our ST-CRMF model can efficiently capture the comprehensive spatial-temporal dependencies and significantly outperform those state-of-the-art models in the short-to-long terms (5-/15-/30-/60-min) traffic forecasting tasks on the open Seattle-Loop and METR-LA traffic datasets.

show abstract

Rapid prediction of acid detergent fiber content in corn stover based on NIR-spectroscopy technology

Cited by 13 publications

References 15 publications

Optical characterization of NIR spectra for chemomectric model of cocoa pod husk fermented for animal feed

Optical characterization of NIR spectra for chemomectric model of cocoa pod husk fermented for animal feed

Multivariate Transfer Passenger Flow Forecasting with Data Imputation by Joint Deep Learning and Matrix Factorization

ST-CRMF: Compensated Residual Matrix Factorization with Spatial-Temporal Regularization for Graph-Based Time Series Forecasting

Contact Info

Product

Resources

About