Review
Chemistry, Analytical
Puneet Mishra, Dario Passos, Federico Marini, Junli Xu, Jose M. Amigo, Aoife A. Gowen, Jeroen J. Jansen, Alessandra Biancolillo, Jean Michel Roger, Douglas N. Rutledge, Alison Nordon
Summary: This paper provides a critical and comprehensive review of the major benefits and potential pitfalls of current deep learning techniques used for spectral data modeling. Although it focuses on near-infrared (NIR) spectral data in chemometric tasks, many of the findings can be applied to other spectral techniques. Finally, empirical guidelines on the best practices for using deep learning for the modeling of spectral data are provided.
TRAC-TRENDS IN ANALYTICAL CHEMISTRY
(2022)
Article
Chemistry, Analytical
Dengshan Li, Lina Li
Summary: This study proposes a novel hybrid calibration transfer method, named DS-AE, which combines direct standardization (DS) and autoencoder (AE) for nonlinear dimensionality reduction, to correct the spectral differences measured on different near-infrared (NIR) instruments. DS is used to eliminate the preliminary spectral difference between the master and slave instruments, and AE is used to extract spectral features for constructing the partial least squares (PLS) calibration model. Compared with linear dimensionality reduction methods, AE learns more latent features that can better reflect the chemical information of the samples.
ANALYTICAL LETTERS
(2023)
Article
Chemistry, Analytical
H. Michael Heise, Sven Delbeck, Ralf Marbach
Summary: The study utilized noninvasive near-infrared spectroscopy for blood glucose monitoring, demonstrating the feasibility of self-monitoring through multivariate calibration. The use of a strategy called science-based calibration (SBC) relying on a priori information improved the accuracy of the results.
Article
Agronomy
Lisha Li, Bin Li, Xiaogang Jiang, Yande Liu
Summary: This study proposes a new strategy for standard-free calibration transfer based on near-infrared spectroscopy, which utilizes wavelength selection and transfer learning algorithms to transfer models between different instruments. The results show that the MEDA-REA model achieves higher prediction accuracy, and the REA method has the potential to filter wavebands and simplify the model.
Article
Chemistry, Analytical
Bai Xue, Glenn Cloud, Sergey Vishnyakov, Zubin Mehta, Evan Ramer, Feng Jin, Meiping Song, Chein- Chang
Summary: A novel method for NIR spectroscopy spectra standardization is proposed in this paper. Most existing methods for standardization require spectral data sets from both primary and secondary instruments for validation, which limits their usage. This paper investigates the issue of spectrum data order and develops a different approach based on statistical signal processing. The developed method compensates for distortion and transfers the second order statistic from the primal spectra to the secondary spectra, allowing estimation regardless of the sample statistic order. Application-driven experiments and a comparison to PDS are conducted to demonstrate the extended usage of the method in NIR spectra standardization.
ANALYTICA CHIMICA ACTA
(2023)
Article
Engineering, Electrical & Electronic
Dong-Woo Kim, Sangwook Nam
Summary: This article presents a robust calibration method, TVmmC, for linear distortions in a wide-band system with 2-D near-field imaging capabilities. The proposed method utilizes total-variation regularization via the majorization-minimization approach in a 2-D reconstructed image domain. TVmmC aims to remove severe systematic frequency-dependent errors that are commonly found in wideband systems. The novelty of TVmmC lies in its ability to provide reliable calibration results in the presence of clutter and noise, making it applicable in real operating environments. Experimental validation using a Ku-band imaging radar system confirms the effectiveness of TVmmC in producing clear images.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Chemistry, Multidisciplinary
Cheng Guo, Jin Zhang, Wensheng Cai, Xueguang Shao
Summary: This study investigates the transferability of NIR models between different fruits using two case studies. A model for predicting strawberry soluble solids content (SSC) was established with acceptable accuracy, but directly applying this model to grape and apple spectra led to degraded performance. Spectral preprocessing improved predictions, but bias remained. Calibration transfer using SS-PFCE and PLS correction was found to effectively improve the prediction of grape and apple spectra. Therefore, calibration transfer may be a feasible way to improve the transferability of NIR models for multiple fruits.
APPLIED SCIENCES-BASEL
(2023)
Article
Economics
Bertille Antoine, Lynda Khalaf, Maral Kichian, Zhenjiang Lin
Summary: This article develops a simulation-based inference procedure for partially specified models. The procedure matches auxiliary statistics to simulated counterparts without assuming identification of parameters of interest or a one-to-one binding function. The conditions for asymptotic validity of the (pseudo-)simulators along with appropriate bootstraps are characterized beyond strict and exact calibration of simulator parameters. The procedure is illustrated through examples and applications.
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
(2023)
Article
Environmental Sciences
Jehyeok Rew, Yongjang Cho, Eenjun Hwang
Summary: This study proposes a novel species distribution model that addresses spatial biases and imbalanced presence-absence data, achieving more accurate and robust prediction results for species in South Korea. By utilizing bootstrap aggregating ensembles of deep neural networks and voting methods, the model improves prediction accuracy in the face of spatial biases and imbalanced data.
Article
Biochemical Research Methods
Jana Gehlken, Martin Pour Nikfardjam, Christian Zoerb
Summary: The aroma of grapes and wines is determined by the composition and concentrations of different aroma compounds. Aroma analysis can be complex and time-consuming, so alternative methods are needed. This study developed calibration models for sensory attributes of grape mash using NIR spectroscopy, and also compared different grape model solutions in a sensory evaluation. Sensory analysis remains important, but NIR spectroscopy can provide additional and objective information about the flavor nuances and quality of grape mash and resulting wine.
ANALYTICAL AND BIOANALYTICAL CHEMISTRY
(2023)
Article
Agriculture, Multidisciplinary
Lisha Li, Xiaogang Jang, Bin Li, Yande Liu
Summary: This study proposed a new relative-error-analysis (REA) wavelength selection method based on relative errors to improve the model's robustness by eliminating bands with large deviations, aiming to simplify the model and enhance prediction accuracy.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Agricultural Engineering
M. I. S. Verissimo, C. Soares, C. F. Moreirinha, M. T. S. R. Gomes
Summary: In this study, a method based on NIR spectroscopy was used to predict the pour point and ethanol content of biodiesel mixtures. The results showed that this method has good prediction capability and is faster and more convenient compared to the traditional ASTM D97-08 procedure.
BIOMASS & BIOENERGY
(2023)
Article
Chemistry, Applied
Songguang Zhao, Selorm Yao-Say Solomon Adade, Zhen Wang, Jizhong Wu, Tianhui Jiao, Huanhuan Li, Quansheng Chen
Summary: In this study, near-infrared (NIR) spectroscopy combined with partial least squares (PLS), backpropagation neural network (BPANN), and their combination (PLS-BPANN) were used to monitor the total sugar content of kombucha. A total of 16 mathematical models were constructed and evaluated. The results showed that the PLS-BPANN model outperformed others, with a determination coefficient (R2p) of 0.9437 and a root mean square error of prediction (RMSEP) of 0.8600 g/L, indicating good verification results. The findings suggest that NIR coupled with PLS-BPANN can be a nondestructive and online technique for monitoring total sugar changes.
Article
Automation & Control Systems
Xien Yin Yap, Kim Seng Chia, Nur Aisyah Syafinaz Suarin
Summary: The study evaluated the feasibility of an adaptive ANN in transferring the ANN model from primary to secondary instruments, showing that the AANN significantly reduces the computation cost of calibration models.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2022)
Article
Spectroscopy
Huan Zhang, Xiaoyun Hu, Limei Liu, Junfu Wei, Xihui Bian
Summary: This study successfully utilized near infrared spectroscopy combined with chemometrics to quantitatively analyze the corn oil content in binary to hexanary edible blend oils. By employing spectral preprocessing and variable selection techniques, accurate prediction models were developed to determine the pure oil content in the blend oils.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2022)
Article
Energy & Fuels
Yan Huang, Yuntao Ju, Kang Ma, Michael Short, Tao Chen, Ruosi Zhang, Yi Lin
Summary: Many autonomous microgrids with high penetration of distributed generation units require optimal power flow for optimal dispatch. Existing convex relaxation methods for three-phase OPF are limited to radial networks, so a new semidefinite programming model has been developed for meshed networks, showing higher accuracy and efficiency in solving the OPF problem.
Article
Automation & Control Systems
Haoran Li, Jisheng Dai, Jianbo Xiao, Xiaobo Zou, Tao Chen, Melvin Holmose
Summary: In this study, the RAH algorithm is combined with LASSO to fit the entire solution of the LASSO problem by tracking KKT conditions and selecting the optimal regularization parameter. The results demonstrate that RAH-LASSO + PLS outperforms other methods in terms of wavelength selection and calibration.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2022)
Article
Engineering, Manufacturing
Zhongwei Chen, Guorong Zhang, Changxin Li, Yuan Yu, Tingting Chen, Qingwu Zhang, Juncheng Jiang, Tao Chen
Summary: This study successfully prepared a flame retardant EP composite with zeolites, a metal-organic framework ligand, and waste materials, showing excellent flame retardant properties. The synergistic effects of pyrolysis and the formation of various compounds contributed to the improved fire resistance of the composite, providing insights for the design of zeolite-based flame retardants for wider applications.
COMPOSITES PART A-APPLIED SCIENCE AND MANUFACTURING
(2022)
Article
Thermodynamics
Xueliang Zhu, Xuhai Pan, Yu Mei, Jiajia Ma, Hao Tang, Yucheng Zhu, Lian X. Liu, Juncheng Jiang, Tao Chen
Summary: Superheated liquid jets disintegrate into droplets due to thermal nonequilibrium induced flashing and mechanical forces during depressurization. This study investigates the breakup and droplet formation of superheated liquid jets under depressurized releases using an experimental tank. The interaction between thermodynamic and mechanical effects is discussed and a quantitative relationship is established. The results show different breakup modes and highlight the importance of considering the cooling effect in addition to thermodynamic and mechanical effects.
APPLIED THERMAL ENGINEERING
(2023)
Article
Toxicology
Marina V. Evans, Thomas E. Moxon, Guoping Lian, Benjamin N. Deacon, Tao Chen, Linda D. Adams, Annabel Meade, John F. Wambaugh
Summary: This study investigates the applicability of the Potts-Guy equation in different human skin datasets and proposes an updated regression equation that combines mechanistic and structural activity relationships. The results show that the Potts-Guy equation is more applicable to experiments focused on the epidermis, while it performs poorly for dermatomed skin and full skin. The combination approach results in improved regression fit compared to the Potts-Guy approach alone.
JOURNAL OF APPLIED TOXICOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Daniel Sebastia-Saez, Faiza Benaouda, Chui Hua Lim, Guoping Lian, Stuart A. Jones, Liang Cui, Tao Chen
Summary: This study developed a simulation model to explore the interaction between mechanical stretch and diffusion of large molecules in the skin under hypobaric pressure. The results showed that hypobaric pressure increased diffusion in the skin, leading to improved transdermal permeation.
PHARMACEUTICAL RESEARCH
(2023)
Article
Engineering, Environmental
Xueliang Zhu, Xuhai Pan, Hao Tang, Xilin Wang, Yucheng Zhu, Lian X. Liu, Juncheng Jiang, Tao Chen
Summary: In this study, a 20 L tank was used to investigate the two-phase flow behaviors during depressurized releases of superheated liquids. The researchers utilized high-speed camera and phase Doppler anemometry to analyze the characteristics of the jet and its breakup. Based on the interaction between thermodynamic and mechanical effects, quantitative criteria were developed to distinguish different breakup regimes.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2023)
Article
Thermodynamics
Xueliang Zhu, Xuhai Pan, Jiajia Ma, Yu Mei, Hao Tang, Yucheng Zhu, Lianxiang Liu, Juncheng Jiang, Tao Chen
Summary: This study investigates the dynamic behavior of superheated liquids and their impact on flashing jet during accidental releases. The results show a strong correlation between the depressurization and the initial ηp0, and flashing occurs upstream and chokes the two-phase flow, reducing the release rate. These findings provide insights for the prevention and mitigation of accidents involving superheated liquid releases.
INTERNATIONAL JOURNAL OF THERMAL SCIENCES
(2023)
Article
Pharmacology & Pharmacy
Lucy Coleman, James R. G. Adams, Will Buchanan, Tao Chen, Roberto M. M. La Ragione, Lian X. X. Liu
Summary: Chronic wounds are a significant burden to patients and healthcare systems, complicated by bacterial infection. This study screened several non-antibiotic compounds for their antibacterial and antibiofilm capabilities and found that PHMB exhibited highly effective antibacterial activity, while TPGS demonstrated potent antibiofilm properties. The combination of these two compounds resulted in a synergistic enhancement of their capability to kill bacteria and disperse biofilms. In conclusion, this work highlights the importance of combinatory approaches to treat infected chronic wounds where bacterial colonization and biofilm formation are significant issues.
Article
Spectroscopy
Anukrati Goel, Dimitrios Tsikritsis, Natalie A. Belsey, Ruth Pendlington, Stephen Glavin, Tao Chen
Summary: Stimulated Raman scattering microscopy is a label-free chemical imaging tool that can map the distribution of chemicals in the skin. This study combines SRS measurements with chemometrics to quantify the penetration profile of exogenous substances in human skin. It is the first demonstration of using SRS imaging technique with spectral unmixing methods for direct observation and mapping of chemical penetration and distribution in biological tissues.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2023)
Article
Environmental Sciences
Jinqi Yang, Yu Guo, Tao Chen, Lang Qiao, Yang Wang
Summary: This study proposed an Adaptive Time Pattern Network (ATPNet) to predict the air temperature of a greenhouse aquaponics system. The ATPNet improved the prediction performance by utilizing deep temporal features, multiple temporal patterns convolution, and a spatial attention mechanism. The ATPNet found a strong correlation between the air temperature of the system and other temperature-related parameters, leading to significant improvements in prediction accuracy compared to baseline models.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Engineering, Environmental
Zhongwei Chen, Boran Yang, Nannan Song, Tingting Chen, Qingwu Zhang, Changxin Li, Juncheng Jiang, Tao Chen, Yuan Yu, Lian X. Liu
Summary: By using machine learning, a high-performance EP composite with enhanced fire resistance was developed by incorporating OPFRs. The ML model identified fire retardants with specific molecular structures that significantly increased the LOI of EPs. Experimental validation confirmed the accuracy and reliability of the ML model.
CHEMICAL ENGINEERING JOURNAL
(2023)
Article
Toxicology
Benjamin N. Deacon, Nicola Piasentin, Qiong Cai, Tao Chen, Guoping Lian
Summary: Permeability and partition coefficients of the skin barrier are important for evaluating the absorption and safety of cosmetics and medicine. This study analyzes the relationship between skin permeability and hydrophobicity using the Potts and Guy equation and identifies significant differences in published datasets. The weak correlation and dependence of the late permeability datasets with skin lipid/water partition suggest the presence of additional non-lipid pathways or a weaker skin barrier property.
TOXICOLOGY IN VITRO
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Meng Cui, Xubo Liu, Jinzheng Zhao, Jianyuan Sun, Guoping Lian, Tao Chen, Mark D. Plumbley, Daoliang Li, Wenwu Wang
Summary: This paper introduces a new approach using audio for assessing fish feeding intensity. By creating a dataset of 3000 labelled audio clips and employing a deep learning framework, the researchers successfully classify the feeding intensity of fish.
2022 IEEE 32ND INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP)
(2022)
Review
Food Science & Technology
Arun Kumar Gupta, Urbi Pathak, Thoithoi Tongbram, Manisha Medhi, Anupun Terdwongworakul, Lembe Samukelo Magwaza, Asanda Mditshwa, Tao Chen, Poonam Mishra
Summary: Determining the maturity of citrus fruits and predicting the time of harvesting has been a challenge for producers, researchers, and food safety agencies. This review provides a correlation between maturity and internal components, overview of maturity determination techniques, and emphasizes on nondestructive methods for assessing citrus fruit maturity levels.
CRITICAL REVIEWS IN FOOD SCIENCE AND NUTRITION
(2022)