Near-infrared Spectroscopy Research Articles

Early Detection of Cassava Vascular Bacteriosis (Xanthomonas Axonopodis pv. Manihotis) by Visible Near-infrared Spectroscopy Before the Appearance of Critical Symptoms

Cassava is a crucial crop for food and nutritional security. It is an important source of carbohydrates in African countries. Cassava crops can sometimes be infected by leaf diseases, affecting overall production and reducing farmers' incomes. Early detection is therefore essential to reduce the impact of these diseases. Light reflections from leaves are known to convey information about plant health. In this study, healthy and inoculated cassava were detected from the reflections obtained from the leaves using a USB 4000 spectrometer with a spectral range of (350-1050) nm. Artificial neural networks (ANNs) and nearest neighbours (KNNs) were used with principal components and vegetation indices as input for classification. Various performance metrics, i.e. Precision, Recall, Accuracy and F1_score for KNN, Accuracy, RMSE and R2 for ANN were calculated to evaluate the different established models. Using the principal components (PC1, PC2) we obtained the best models with the ANNs with the following metrics (R2=0.9678; RMSE=0.0146; Accuracy =98.30%) for the variety IM 84 and (R2=0.9291; RMSE=0.0354 Accuracy=91.30%) for the Yacé variety. With vegetation indices, the best performing models were obtained with KNN whose input parameters are RatiodRE_703 ((Accuracy =92.50% and F1-score=0.9449) and fWBI ((Accuracy =90% and F1-score=0.9326) for Yacé and vog 3 (Accuracy=100% and F1-score=1), DD (Accuracy=100% and F1_score=1) and dNIRmin920_980 (Accuracy=95% and F1_score=0.9373) for the IM 84. Overall, the results showed that leaf spectral reflectance can be used successfully for the early detection of cassava bacterial blight.

Neurophysiological Approach for Psychological Safety: Enhancing Mental Health in Human–Robot Collaboration in Smart Manufacturing Setups Using Neuroimaging

Human–robot collaboration (HRC) has become increasingly prevalent due to innovative advancements in the automation industry, especially in manufacturing setups. Although HRC increases productivity and efficacy, it exposes human workers to psychological stress while interfacing with collaborative robotic systems as robots may not provide visual or auditory cues. It is crucial to comprehend how HRC impacts mental stress in order to enhance occupational safety and well-being. Though academics and industrial interest in HRC is expanding, safety and mental stress problems are still not adequately studied. In particular, human coworkers’ cognitive strain during HRC has not been explored well, although being fundamental to sustaining a secure and constructive workplace environment. This study, therefore, aims to monitor the mental stress of factory workers during HRC using behavioural, physiological and subjective measures. Physiological measures, being objective and more authentic, have the potential to replace conventional measures i.e., behavioural and subjective measures, if they demonstrate a good correlation with traditional measures. Two neuroimaging modalities including electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) have been used as physiological measures to track neuronal and hemodynamic activity of the brain, respectively. Here, the correlation between physiological data and behavioural and subjective measurements has been ascertained through the implementation of seven different machine learning algorithms. The results imply that the EEG and fNIRS features combined produced the best results for most of the targets. For subjective measures being the target, linear regression has outperformed all other models, whereas tree and ensemble performed the best for predicting the behavioural measures. The outcomes indicate that physiological measures have the potential to be more informative and often substitute other skewed metrics.

Identifying the Vertical Stratification of Sediment Samples by Visible and Near-Infrared Spectroscopy

Vertical stratification in marine sediment profiles indicates physical and chemical sedimentary processes and, thus, is the first step in sedimentary research and in studying their relationship with global climate change. Traditional technologies for studying vertical stratification have low efficiency; thus, new technologies are highly needed. Recently, visible and near-infrared spectroscopy (VNIR) has been explored to rapidly determine sediment parameters, such as clay content, particle size, total carbon (TC), total nitrogen (TN), and so on. Here, we explored vertical stratification in a sediment column in the South China Sea using VNIR. The sediment column was 160 cm and divided into 160 samples by 1 cm intervals. All samples were classified into three layers by depth, that is, 0–50 cm (the upper layer), 50–100 cm (the middle layer), and 100–160 cm (the bottom layer). Concentrations of TC and TN in each sample were measured by Elementa Vario EL III. Visible and near-infrared reflectance spectra of each sample were collected by Agilent Cary 5000. A global model and several classification models for vertical stratification in sediments were established by a Support Vector Machine (SVM) after the characteristic spectra were identified using Competitive Adaptive Reweighted Sampling. In the classification models, K-means clustering and Density Peak Clustering (DPC) were employed as the unsupervised clustering algorithms. The results showed that the stratification was successful by VNIR, especially when using the combination of unsupervised clustering and machine learning algorithms. The correct classification rate (CCR) was much higher in the classification models than in the global model. And the classification models had a higher CCR using K-means combined with SVM (94.8%) and using DPC combined with SVM (96.0%). The higher CCR might be derived from the chemical classification. Indeed, similar results were also found in the chemical stratification. This study provided a theoretical basis for the rapid and synchronous measurement of chemical and physical parameters in sediment profiles by VNIR.

Near Infrared Spectroscopy (NIRS) Model Based on Transfer Learning

This study compares three transfer learning strategies for adapting convolutional neural network (CNN) models in near-infrared spectroscopy to new instruments. Strategy 1 freezes pre-trained weights except for the output layer; Strategy 2 fine-tunes all weights with new data; Strategy 3 adds new fully connected layers to the pre-trained model. Using tablet spectra to predict active pharmaceutical ingredient content, results show that fine-tuning all network weights (Strategy 2) yields the best performance. The study also finds that moderate training sample sizes balance model accuracy and resource expenditure. Transfer learning is effective for near-infrared model transfer.

In-Situ Fabricated Transparent Flexible Nanowire Device with Wavelength-Regulated Dual-Function of Photodetector and Photonic Synapse.

Integrating the dual functionalities of a photodetector and photonic synapse into a single device is challenging due to their conflicting requirements for photocurrent decay rates. This study addresses this issue by seamlessly depositing transparent indium tin oxide (ITO) electrodes onto self-oriented copper hexadecafluoro-phthalocyanine (F16CuPc) nanowires growing horizontally along hot-stamped periodic nanogrooves on a transparent flexible polyimide plastic film. This in-situ-fabricated device achieves bending-stable dual functionalities through wavelength regulation while maintaining high transparency and flexibility. Upon exposure to 450-850 nm light, the device exhibits a rapid and sensitive photoresponse with excellent bending stability, making it ideal for optical sensing in both visible and near-infrared spectra. More importantly, the device exhibits a bending-stable excitation postsynaptic current when exposed to light spikes below 405 nm. This enables the successful emulation of various biological synaptic functionalities, including paired-pulse facilitation, spike-number-dependent plasticity, spike-duration-dependent plasticity, spike-rating-dependent plasticity, configurable plasticity between short-term plasticity and long-term plasticity, and memory learning capabilities. Utilizing this device in an artificial neural network achieves a recognition rate of 95% after 57 training epochs. Its ability to switch between photodetection and synaptic modes by adjusting the light wavelength marks a significant advancement in the field of multifunctional flexible electronics based on nanowire arrays.

Using multivariate partial least squares on fNIRS data to examine load-dependent brain-behaviour relationships in aging.

Researchers implementing non-invasive neuroimaging have reported distinct load-dependent brain activity patterns in older adults compared with younger adults. Although findings are mixed, these age-related patterns are often associated with compensatory mechanisms of cognitive decline even in the absence of direct comparisons between brain activity and cognitive performance. This study investigated the effects of cognitive load on brain-behavior relationships in younger and older adults using a data-driven, multivariate partial least squares (PLS) analysis of functional near-infrared spectroscopy (fNIRS) data. We measured bilateral prefrontal brain activity in 31 older and 27 younger adults while they performed single and dual 2-back tasks. Behavioral PLS analysis was used to determine relationships between performance metrics (reaction time and error rate) and brain oxygenation (HbO) and deoxygenation (HbR) patterns across groups and task loads. Results revealed significant age-group differences in brain-behavior relationships. In younger adults, increased brain activity (i.e., increased HbO and decreased HbR) was associated with faster reaction times and better accuracy in the single task, indicating sufficient neural capacity. Conversely, older adults showed a negative correlation between HbR and error rates in the single task; however, in the dual task, they demonstrated a positive relationship between HbO and performance, indicative of compensatory mechanisms under the higher cognitive load. Overall, older adults' showed relationships with either HbR or HbO, but not both, indicating that the robustness of the relationship between brain activity and behavior varies across task load conditions. Our PLS approach revealed distinct load-dependent brain activity between age groups, providing further insight into neurocognitive aging patterns, such as compensatory mechanisms, by emphasizing the variability and complexity of brain-behavior relationships. Our findings also highlight the importance of considering task complexity and cognitive demands in interpreting age-related brain activity patterns.

A Brain Network Analysis Model for Motion Sickness in Electric Vehicles Based on EEG and fNIRS Signal Fusion

Motion sickness is a common issue in electric vehicles, significantly impacting passenger comfort. This study aims to develop a functional brain network analysis model by integrating electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) signals to evaluate motion sickness symptoms. During real-world testing with the Feifan F7 series of new energy-electric vehicles from SAIC Motor Corp, data were collected from 32 participants. The EEG signals were divided into four frequency bands: delta-range, theta-range, alpha-range, and beta-range, and brain oxygenation variation was calculated from the fNIRS signals. Functional connectivity between brain regions was measured to construct functional brain network models for motion sickness analysis. A motion sickness detection model was developed using a graph convolutional network (GCN) to integrate EEG and fNIRS data. Our results show significant differences in brain functional connectivity between participants in motion and non-motion sickness states. The model that combined fNIRS data with high-frequency EEG signals achieved the best performance, improving the F1 score by 11.4% compared to using EEG data alone and by 8.2% compared to using fNIRS data alone. These results highlight the effectiveness of integrating EEG and fNIRS signals using GCN for motion sickness detection. They demonstrate the model’s superiority over single-modality approaches, showcasing its potential for real-world applications in electric vehicles.

How Can Near‐Infrared Spectroscopy (NIRS) Help Understanding of the Psychotherapy Process? A Scoping Review of Therapeutic Interactions

AbstractIn recent years, near‐infrared spectroscopy (NIRS) has garnered significant attention for its potential clinical applications as a non‐invasive and straightforward method for measuring brain functions. While NIRS has become useful in psychiatric contexts by aiding in the differential diagnosis of depression, its application in clinical psychology is still developing. Due to its ecological validity, which allows for measurements in natural settings, NIRS shows promise in revealing the dynamic elements of the psychotherapy process. In this study, we conducted a scoping literature review of the use of NIRS in psychotherapeutic interactions, exploring its potential to unveil the complexities of psychotherapy settings involving interpersonal interactions. Employing a scoping review approach, we systematically searched the PubMed, PsycINFO, and Web of Science databases for articles published through October 19, 2023 about studies using NIRS as a measurement instrument: This yielded various therapeutic interactions. Of the 155 retrieved results that remained after the initial screening, seven met the inclusion criteria. Of these, six studies examined the synchronization of brain functions through the simultaneous brain activity measurements (hyperscanning) of two participants. The review revealed that, despite the anticipated potential of NIRS, it has become evident there is a dearth of research focusing on interactions during psychotherapy. Furthermore, the few available studies have not explored changes in line with the progression of psychotherapeutic interactions. Consequently, future studies should address whether NIRS can effectively assess alterations in brain function resulting from micro‐level events, such as the therapeutic interaction between therapists and clients during psychotherapy.

The key role of anti-solvent temperature in quantum dot/perovskite core-shell nanowire array solar cells

Combining perovskite with infrared quantum dots to construct a core-shell nanostructure nanowire array solar cell can increase the light absorption range and enhance the light absorption and carrier transport efficiency of the solar cell. However, the preparation of a perovskite absorber layer on a nanowire array with quantum dots often presents issues such as high roughness and a large number of lattice defects, which have a negative impact on the photovoltaic performance. The anti-solvent method is a commonly used technique to improve the quality of perovskite. The temperature variation of the anti-solvent can change solubility, and influence the reaction rate and crystal formation process of perovskite, thus affecting its photovoltaic performance. In this study, the quality of perovskite in the core-shell nanostructure nanowire array was improved by controlling the temperature of the anti-solvent (toluene). Experimental results show that as the temperature of toluene increases, the photovoltaic performance is gradually improved. When the toluene temperature was maintained at 75 °C, the device exhibited significantly improved photovoltaic performance with an efficiency of 12.64 %, surpassing the efficiency obtained without any anti-solvent modification. As the temperature of the anti-solvent increases, the absorption of visible and near-infrared light spectrum by the nanowire arrays is enhanced, which promotes the efficient generation of photo-generated carriers. Furthermore, defects in the nanowire arrays gradually decrease, leading to a reduction in carrier recombination. These findings provide valuable insights for advancing core-shell nanostructure nanowire array solar cells.

Rapid on-site multi-indicator detection of Polygonatum cyrtonema Hua by handheld near-infrared spectroscopy with wavelength selection

The rapid, accurate, and on-site quantitative evaluation of the 3 components (total polysaccharide, total flavonoid, and total saponin) of Polygonatum cyrtonema Hua (PCH) is of great significance to ensure the value of its medicine and food, for this purpose, a handheld near-infrared (NIR) spectrometer was used. The raw NIR spectra were preprocessed by seven methods and their combinations, then three kinds of wavelength selection algorithms, the competitive adaptive reweighted sampling (CARS), random frog (RF) sampling, and Monte Carlo uninformative variable elimination (MCUVE) were applied, and the characteristic wavelengths for total polysaccharide, total saponin, and total flavonoid in PCH were obtained, respectively. Subsequently, the partial least squares (PLS) regression models were developed. The results showed that the combination of first derivative and standard normal variate was the optimal pretreatment method, and CARS had the highest performance of the wavelength selection for total polysaccharide and total flavonoid, while RF was the highest for total saponin. With these selected wavelengths, 3 PLS prediction models were built, and their performances were validated with unknown samples, the results showed that the determination coefficient of the prediction set (R2P) of total polysaccharide, total saponin, and total flavonoid were 0.980, 0.948, and 0.942, respectively, and the corresponding root mean square error of prediction set (RMSEP) were 0.162, 0.142, and 0.052. Furthermore, the residual prediction deviations (RPDs) of the three components were all larger than 3, demonstrating the prediction performance of the models was high. Therefore, the three active functional components in PCH could be rapidly determined by a handheld NIR spectrometer, which would be beneficial for ensuring the quality of PCH.

Skeletal Muscle Oxidative Metabolism during Exercise Measured with Near Infrared Spectroscopy

This study characterized the level of oxidative metabolism in skeletal muscle during whole-body activity as a percentage of the muscle’s maximum oxidative rate (mVO2max) using near-infrared spectroscopy (NIRS). Ten healthy participants completed a progressive work test and whole-body walking and lunge exercises, while oxygen saturation was collected from the vastus lateralis muscle using near-infrared spectroscopy (NIRS). Muscle oxygen consumption (mVO2) was determined using arterial occlusions following each exercise. mVO2max was extrapolated from the mVO2 values determined from the progressive exercise test. mVO2max was 11.3 ± 3.3%/s on day one and 12.0 ± 2.9%/s on day two (p = 0.07). mVO2max had similar variation (ICC = 0.95, CV = 6.4%) to NIRS measures of oxidative metabolism. There was a progressive increase in mVO2 with walking at 3.2 Km/h, 4.8 km/h, 6.4 Km/h, and with lunges (15.8 ± 6.6%, 20.5 ± 7.2%, 26.0 ± 6.6%, and 57.4 ± 15.4% of mVO2max, respectively). Lunges showed a high reliability (ICC = 0.81, CV = 10.2%). Muscle oxidative metabolism in response to whole-body exercise can be reproducibly measured with arterial occlusions and NIRS. This method may be used to further research on mitochondrial activation within a single muscle during whole-body exercise.

Quantitative Analysis of High-Price Rice Adulteration Based on Near-Infrared Spectroscopy Combined with Chemometrics.

Near-infrared spectroscopy (NIRS) holds significant promise in detecting food adulteration due to its non-destructive, simple, and user-friendly properties. This study employed NIRS in conjunction with chemometrics to estimate the content of low-price rice flours (Nanjing, Songjing, Jiangxi silk, Yunhui) blended with high-price rice (Wuchang and Thai fragrant). Partial least squares regression (PLSR), support vector regression (SVR), and back-propagation neural network (BPNN) models were deployed to analyze the spectral data of adulterated samples and assess the degree of contamination. Various preprocessing techniques, parameter optimization strategies, and wavelength selection methods were employed to enhance model accuracy. With correlation coefficients exceeding 87%, the BPNN models exhibited high accuracy in estimating adulteration levels in high-price rice. The SPXY-SG-BPNN, SPXY-MMN-BPNN, KS-SNV-BPNN, and SPXY-SG-BPNN models showcased exceptional performance in discerning mixed Wuchang japonica, Thai fragrant indica, and Thai fragrant Yunhui rice. As shown above, NIRS demonstrated its potential as a rapid, non-destructive method for detecting low-price rice in premium rice blends. Future studies should be performed to concentrate on enhancing the models' versatility and practical applicability.

Rapid and non-invasive estimation of total phenol content and species identification in dried wild edible bolete using FT-NIR spectroscopy

The market for dried wild edible mushrooms is characterized by quality discrepancies and species disorganization, which are a matter of concern. The feasibility of using fourier transform near-infrared (FT-NIR) spectroscopy with chemometrics to predict the total phenol content and identify species was investigated in dried bolete. For the determination of total phenolic content, FT-NIR spectral acquisition, and two-dimensional correlation spectroscopy (2DCOS) image acquisition, five common species of dried edible bolete (n = 144) were utilized. The results showed that partial least squares regression (PLSR) combined with Fourier transform near-infrared spectroscopy could predict the total phenol content of dried boletes, with the best prediction coefficient of determination (R2p) = 0.79. The partial least squares discriminant analysis (PLS-DA) model accurately identified Phlebopus portentosus, with Matthews correlation coefficient (MCC), Precision (PRC), Sensitivity (SEN), and Specificity (SPE) all being 1. The support vector machines (SVM) model is performed optimally to identify processing edible bolete (Lanmaoa asiatica) with an accuracy of 100 % in the test set. 2DCOS images combined with the residual convolutional neural networks (ResNet) model demonstrated the feasibility of FT-NIR full spectral bands (10,000–4,000 cm−1) and characteristic spectral bands (6,500–4,000 cm−1) for species identification of boletes. The method applies to the case of consistent or inconsistent sample sizes between groups, with an accuracy of 1.00 for both the training and test sets. The study serves as a rapid, non-invasive, and convenient method for real-time evaluation of the quality of dried edible bolete in the market.

The Impact of Sample Quantity, Traceability Scale, and Shelf Life on the Determination of the Near-Infrared Origin Traceability of Mung Beans.

This study aims to address the gap in understanding of the impact of the sample quantity, traceability range, and shelf life on the accuracy of mung bean origin traceability models based on near-infrared spectroscopy. Mung beans from Baicheng City, Jilin Province, Dorbod Mongol Autonomous, Tailai County, Heilongjiang Province, and Sishui County, Shandong Province, China, were used. Through near-infrared spectral acquisition (12,000-4000 cm-1) and preprocessing (Standardization, Savitzky-Golay, Standard Normal Variate, and Multiplicative Scatter Correction) of the mung bean samples, the total cumulative variance contribution rate of the first three principal components was determined to be 98.16% by using principal component analysis, and the overall discriminatory correctness of its four origins combined with the K-nearest neighbor method was 98.67%. We further investigated how varying sample quantities, traceability ranges, and shelf lives influenced the discrimination accuracy. Our results indicated a 4% increase in the overall correct discrimination rate. Specifically, larger traceability ranges (Tailai-Sishui) improved the accuracy by over 2%, and multiple shelf lives (90-180-270-360 d) enhanced the accuracy by 7.85%. These findings underscore the critical role of sample quantity and diversity in traceability studies, suggesting that broader traceability ranges and comprehensive sample collections across different shelf lives can significantly improve the accuracy of origin discrimination models.

Combinatorial Order Pre-processing Search (COPS): A new pre-processing strategy for large-scale interpretable data analysis in process analytical technologies

Combinatorial Order Pre-processing Search (COPS), a novel approach for optimizing data pre-processing is proposed in this work. Unlike simultaneous hyperparameter optimization, COPS employs a priori optimization to reduce computational time while refining the search space for preprocessing sequences and combinations. It allows for setting a maximum number of pre-processing methods, while efficiently searching through combinations of methods with chemically relevant knowledge. In this work, 67 calibration datasets across various analytical techniques, including fluorescence spectroscopy, gas chromatography (GC), near-infrared spectroscopy (NIR), mid-infrared spectroscopy (MIR), visible-near-infrared spectroscopy (Vis-NIR), Raman spectroscopy, nuclear magnetic resonance (NMR) spectroscopy, and voltammetry were evaluated. COPS yielded significant improvements over existing methodologies based on design of experiment and compounded pre-processing approaches. The COPS outperformed the other methods, resulting in an average root mean square error of prediction (RMSEP) reduction of 31.7%, while also reduced the complexity (number of latent variables) of the model which allows for easier interpretation. This underscores the importance of combinatorial order set theory for the search of pre-processing method combinations (without fixing the sequence of pre-processing methods) to enhance model performance and interpretation. The novel COPS approach can be employed in process analytical technology (such as inline, online or at-line chemical sensing analytics) to enhance predictive accuracy and operational efficiency, fundamentally transforming the quality and reliability of chemical process monitoring and control.

Agro-Climatic Information to Enhance the Machine-Learning Classification of Olive Oils from Near-Infrared Spectra

Agro-Climatic Information to Enhance the Machine-Learning Classification of Olive Oils from Near-Infrared Spectra

Exploring neural efficiency in spatial cognition: A comparative study of 3D visual stimuli in virtual reality across STEM and non-STEM fields

Spatial cognition plays a crucial role in our daily lives. The relationship between spatial abilities and mathematical performance is well-established, with visuospatial training offering significant benefits in academic STEM (Science, Technology, Engineering, and Mathematics) disciplines. Developing visuospatial training requires an objective evaluation of spatial cognition and consideration of various 3D displays. This study aims to compare the neural efficiency of STEM and non-STEM individuals during mental rotation tasks (MRT) in 3D and 2.5D conditions (pseudo 3D) using virtual reality (VR). For that, we propose a novel integrative assessment of spatial cognition by combining a cost-effective VR headset and functional near-infrared spectroscopy (fNIRS). Overall, the findings reveal that STEM individuals exhibit greater neural efficiency in the dorsolateral prefrontal cortex (PFC) while solving MRT in a VR environment compared to their non-STEM counterparts. Additionally, the study shows that there is no significant difference in performance between 3D and 2.5D stimuli, suggesting that both conditions are equally suitable for MRT in VR. One possible explanation is that immersive VR reduces the distinctions between 3D models and 2.5D images, considering MRT scores and PFC activity. This research underscores the practicality and relevance of using VR and fNIRS to evaluate visuospatial tasks and the potential to identify distinct student learning profiles and enhance spatial skills. Furthermore, it highlights the potential of 2.5D stimuli as a cost-effective alternative for learning applications in VR. Here, we demonstrated that modeling the same task in 3D and 2.5D conditions can compare how humans interact with visuospatial tests, providing insights into applying VR devices to develop spatial skills.

Memory detection with concurrent behavioral, autonomic, and neuroimaging measures in a mock crime.

Concealed information test (CIT) has been utilized for long to perform single measurements. The combination of multiple measures outperforms single measures because of the diverse cognitive processes they reflect and the reduction in random errors facilitated by multiple measures. To further explore the performance of the CIT with multiple measurements, 57 participants were recruited and randomly assigned into guilty and innocent groups. Subsequently, simultaneously recorded reaction time (RT), skin conductance responses (SCRs), heart rate (HR), and neuroimaging data were collected from functional near-infrared spectroscopy (fNIRS) to detect participants' concealed information in a standard CIT. The results demonstrated that all indicators including RT (area under the curve (AUC) = 0.87), SCRs (AUC = 0.79), HR (AUC = 0.78), and fNIRS (channel 8, AUC = 0.85) could differentiate guilty and innocent groups. Importantly, the use of multiple indicators achieved higher detection efficiency (AUC = 0.96) compared to the use of any single indicator. These results illustrate the effectiveness and feasibility of integrating multiple indicators for concealed information detection in CIT.

Splanchnic and cerebral oxygenation during cyclic phototherapy in preterm infants with hyperbilirubinemia

Cyclic phototherapy (cPT) can achieve a reduction in total serum bilirubin comparable to that achieved with standard continuous PT in preterm infants. Our aim was to assess the effect of cPT on splanchnic (rSO2S) and cerebral (rSO2C) oxygenation measured by near-infrared spectroscopy (NIRS). We prospectively studied 16 infants with a gestational age of 25–34 weeks with hyperbilirubinemia requiring PT. Splanchnic regional oxygenation (rSO2S), oxygen extraction fraction (FOES), and cerebro-splanchnic oxygenation ratio (CSOR) were recorded before, during, and after cPT discontinuation. We found that rSO2S, FOES, and CSOR did not change during the study period. The overall duration of single or multiple courses of PT was 6.5 (6.0–13.5) h, but by cycling PT, the actual exposure was 3.0 (1.5–4.9) h. Twelve patients (75%) required 15 min/h cPT, and four (25%) required prolonging cPT to 30 min/h. None of the patients developed enteral feeding intolerance.Conclusions: cPT treatment of hyperbilirubinemia in preterm infants does not affect splanchnic oxygenation or intestinal oxygen blood extraction, likely due to the short exposure to PT light, and it could contribute to decreasing the risk of feeding intolerance.What is Known:• The assumption that phototherapy (PT) is innocuous with no serious adverse effects has been questioned.• Cyclic phototherapy (cPT) can achieve a reduction in total serum bilirubin comparable to that achieved with standard continuous PT in preterm infants.What is New:• Splanchnic and cerebral oxygenation measured by near-infrared spectroscopy did not change during KMC.• cPT can contribute to decrease the risk of feeding intolerance likely due to the short exposure to PT light.

Predicting water content in engine oil using SPA-ISSA-BP methods  

Contamination of engine oil with water can accelerate oil oxidation and decomposition, resulting in oil degradation. Therefore, the detection and prediction of water content in engine oil is crucial to ensure the long-term safe operation of engines. In this study, near-infrared spectroscopy was used to analyse engine oils with varying water contents. Spectral data were obtained, and various methods, including Savitzky-Golay (SG) smoothing, orthogonal signal correction (OSC), and successive projection algorithm (SPA) were employed to compare the performance differences of principal component regression models. An Improved Sparrow Searches Algorithm (ISSA) was then applied to optimise the Back-Propagation Neural Network (BPNN) for predicting water content in SAE 10W-30 engine oil. The results showed that the performance of the principal component regression model constructed from spectral data after SG smoothing, OSC, and the SPA feature wavelength selection had improved. The BPNN optimised by the improved Sparrow Search Algorithm accelerated the convergence speed of the model and effectively improved the prediction accuracy of the BPNN. The obtained coefficient of determination (R2) was 0.99103, the root mean square error (RMSE) was 2. 2136 10-4, and the mean absolute error (MAE) was 1. 8889×10-4. These results provide an effective method for detecting and predicting the water content in engine oil.