Partial Least Squares Research Articles

Data-Driven State of Health Interval Prediction for Lithium-Ion Batteries

The accurate prediction of the state of health (SOH) for lithium-ion batteries is a key factor for improving the performance of battery management systems (BMS). However, traditional point prediction methods are difficult to effectively eliminate errors due to the uncertainty of variables and application environments. This paper presents a model for predicting the interval of lithium-ion batteries based on health indicators (HIs) during charging, which addresses the limitations of current point prediction in practical applications. First, twelve HIs are extracted from the current and voltage variables of the charging process. Secondly, feature selection is performed by random forest (RF) training, and the selected HIs are dimensioned using partial least squares (PLS). Finally, a long short-term memory network (LSTM) combined with quantile regression (QR) is used to derive the quantile values of the prediction points and each quantile is employed as input information for Gaussian kernel density estimation (KDE) to obtain the SOH probability density distribution. The experimental results based on the NASA PCOE Li-ion battery dataset and CALCE Li-ion battery dataset show that the SOH interval coverage is more than 90% and the average width of the interval is less than 0.294.

Associations between Neonicotinoid, Pyrethroid, and Organophosphate Insecticide Metabolites and Neurobehavioral Performance in Ecuadorian Adolescents.

Organophosphate and pyrethroid insecticides can affect children's neurodevelopment and increase inflammation. Limited evidence exists among adolescents and on whether inflammation may mediate pesticide-neurobehavior associations. We examined the associations between insecticide metabolite concentrations and neurobehavior among adolescents in Ecuadorian agricultural communities. We included 520 participants aged 11-17 years. We measured urinary insecticide metabolites (mass spectrometry) and neurobehavior (NEPSY-II). Associations were adjusted for socio-demographic and anthropometric characteristics. The associations of insecticide mixtures with neurobehavior were evaluated using PLS regression, and mediation by inflammatory biomarkers (TNF-α, IL-6, CRP, SAA, sICAM-1, sVCAM-1 and sCD-14) was conducted. Among organophosphates, para-nitrophenol (PNP) and 3,5,6-Trichloro-2-pyridinol (TCPy) were inversely associated with Social Perception (score difference per 50% increase [β 50% ] = -0.26 [95%CI: - 1.07, -0.20] and -0.10 [-0.22, 0.01], respectively). PNP and TCPy also had significant inverse associations with Attention/Inhibitory Control at concentrations >60 th percentile (β 50% = -0.26 [95%CI: -0.51, -0.01] and β 50% = -0.22 [95%CI: -0.43, -0.00], respectively). The pyrethroid, 3-phenoxybenzoic acid (3-PBA), was inversely associated with Language (β 50% = -0.13 [95%CI: -0.19, -0.01]) and had a negative quadratic association with Attention/Inhibitory Control. The neonicotinoid 5-Hydroxy imidacloprid (OHIM) was positively associated with Memory/Learning (β 50% = 0.20 [95%CI: 0.04, 0.37]). Mixtures of all insecticides were significantly negatively related to all domains, except for Memory/Learning, which was positively associated. No mediation by inflammatory markers on these associations was observed. Concurrent organophosphate, pyrethroid, and the mixtures of all metabolites were associated with lower performance in all domains except for Memory/Learning. Neonicotinoids were positively associated with Memory/Learning and Social Perception scores.

Green Economy Innovation in Attracting Youth to Pond Fish Farming Profession

The purpose of this study was to determine and analyze the effect of youth perceptions on interest in the fish farming profession mediated by green economy. The approach used in this research is a causal approach. The population in this study were village youth in Sungelebak, Sungegeneng Kec, Lamongan Kab. The sample in this study used simple random sampling with 100 respondents. The data collection technique in this study used a questionnaire technique. The data analysis technique in this study uses a quantitative approach using statistical analysis using the Auter Model Analysis test, Inner Model Analysis, and Hypothesis Test. Data processing in this study used the PLS (Partial Least Square) software program. The results of this study prove that directly youth perceptions and green economy have a significant effect on interest in the fish farming profession and indirectly green economy is able to mediate the effect of youth perceptions on interest in the fish farming profession. Highlights: Significant Relationships: Youth perceptions and green economy significantly influence interest in fish farming. Mediation Effect: Green economy acts as a mediator between youth perceptions and fish farming interest. Methodology: Utilized a causal approach with 100 respondents from Sungelebak village through questionnaires and PLS software. Keywords: Youth Perception, Green Economic, Interest in Fish Farming Profession

Striking the Balance: How Workplace Flexibility Enhances Engagement and Performance of Employees working in Public and Private settings

This study investigates the relationships between workplace flexibility, employee engagement, and performance of employees working in public and private settings. The purpose is to understand how flexible work arrangements influence employee engagement and overall performance across various industries. This research was conducted using a descriptive quantitative method. A structured questionnaire was used to collect data from 400 employees across finance, technology, healthcare, and manufacturing industries. The measurement model’s reliability was evaluated using the partial least square (PLS) structural equation modeling (SEM) approach (see table 3). Cronbach alpha (α) and composite reliability (CR) values were used. A prognosis model evaluation shows that all of the variables have SRMR values of 0.082 and NFI values of 0.914, suggesting that the model accurately matches with the experimental data. The Q2 predict value for employee performance (EP) of 0.352 shows excellent predictive relevance with a significant impact size. In comparison, the Q2 predict predictive value for Employee Engagement (EENG) is 0.185, indicating good predictive relevance with a modest impact size. These Q2Predict values are higher than the required minimum threshold of 0.00, indicating that the model is highly predictive for each variable. Furthermore, the Q2 effect sizes for EENG and EPC show that they have a significant impact on the endogenous variable (WPFX). SmartPLS 3.3.9 used the PLS algorithm as well as the bootstrapping approach to evaluate the presented hypothesis. Table 6 shows the beta values that demonstrate the intensity and significance of the positive link between the dependent and independent variables, where employee engagement acts as both a moderator and mediator. By including both mediation and moderation in the same model, you can gain a more comprehensive understanding of how workplace flexibility impacts employee performance, considering the mediating role of employee engagement and the moderating effect of its level. In addition to the above analysis, In addition, demographic factors are tested by Manova.

The Influence Of Brand Image, Taste, And Price Perception On Purchasing Decisions For Sarimi Instant Noodles In Surabaya

Sarimi is a brand of instant noodles in Indonesia produced by Indofood CBP Sukses Makmur which was launched in 1982. Just like other instant noodle products, sarimi is sold in various types of products and flavors according to consumer needs. With so many brands of instant noodles in Indonesia, the reality is that sales of Sarimi instant noodles have decreased from year to year. This research aims to determine the influence of brand image, taste and price perception on purchasing decisions for sarimi instant noodles. The population of this study were Active Students of UPN "Veteran" East Java who had purchased and consumed sarimi instant noodles in Surabaya. This research used a quantitative method with 80 respondents collected using purposive sampling, namely, the sampling technique was determined using special or specific criteria for the sample. Meanwhile, the analysis used was Partial Least Square (PLS). The research results show that brand image, taste and price perception have a positive and significant effect on purchasing decisions for sarimi instant noodles.

Evaluation of the Effect of Commercialization of Technology in Creating Sustainable Competitive Advantage of Knowledge-based Companies Emphasizing the Moderating Role of Environmental Factors

The present study aimed at designing a structural equation model of the effect of technology commercialization performance on creating sustainable competitive advantage of knowledgeable companies with an emphasis on the moderating environmental factors.Research population includes 133 managers of knowledge based companies at the center for the growth and development of science and technology Park of East Azerbaijan University and based on the Cochran formula, the sample size was measured to be 99, and selection by stratified random sampling method, and the standard questionnaire is distributed among them. The research is applied in nature and the method is descriptive and survey. Then, the data were analyzed using smart pls software for partial least squares (PLS) path modeling. The results show that the technology commercialization performance has a positive effect on the competitive sustainable advantage of knowledge-based companies, as well as the role of variable moderating environmental factors (market turbulence, competitive intensity and technological turbulence) in the path between the technology commercialization performance and the sustainable competitive advantage of knowledge-based companies.

Inline Raman spectroscopy as process analytical technology for SARS-CoV-2 VLP production.

The present work focused on inline Raman spectroscopy monitoring of SARS-CoV-2 VLP production using two culture media by fitting chemometric models for biochemical parameters (viable cell density, cell viability, glucose, lactate, glutamine, glutamate, ammonium, and viral titer). For that purpose, linear, partial least square (PLS), and nonlinear approaches, artificial neural network (ANN), were used as correlation techniques to build the models for each variable. ANN approach resulted in better fitting for most parameters, except for viable cell density and glucose, whose PLS presented more suitable models. Both were statistically similar for ammonium. The mean absolute error of the best models, within the quantified value range for viable cell density (375,000-1,287,500 cell/mL), cell viability (29.76-100.00%), glucose (8.700-10.500g/), lactate (0.019-0.400g/L), glutamine (0.925-1.520g/L), glutamate (0.552-1.610g/L), viral titer (no virus quantified-7.505 log10 PFU/mL) and ammonium (0.0074-0.0478g/L) were, respectively, 41,533 ± 45,273cell/mL (PLS), 1.63 ± 1.54% (ANN), 0.058 ± 0.065g/L (PLS), 0.007 ± 0.007g/L (ANN), 0.007 ± 0.006g/L (ANN), 0.006 ± 0.006g/L (ANN), 0.211 ± 0.221 log10 PFU/mL (ANN), and 0.0026 ± 0.0026g/L (PLS) or 0.0027 ± 0.0034g/L (ANN). The correlation accuracy, errors, and best models obtained are in accord with studies, both online and offline approaches while using the same insect cell/baculovirus expression system or different cell host. Besides, the biochemical tracking throughout bioreactor runs using the models showed suitable profiles, even using two different culture media.

Fluorescence and Hyperspectral Sensors for Nondestructive Analysis and Prediction of Biophysical Compounds in the Green and Purple Leaves of Tradescantia Plants

The application of non-imaging hyperspectral sensors has significantly enhanced the study of leaf optical properties across different plant species. In this study, chlorophyll fluorescence (ChlF) and hyperspectral non-imaging sensors using ultraviolet-visible-near-infrared shortwave infrared (UV-VIS-NIR-SWIR) bands were used to evaluate leaf biophysical parameters. For analyses, principal component analysis (PCA) and partial least squares regression (PLSR) were used to predict eight structural and ultrastructural (biophysical) traits in green and purple Tradescantia leaves. The main results demonstrate that specific hyperspectral vegetation indices (HVIs) markedly improve the precision of partial least squares regression (PLSR) models, enabling reliable and nondestructive evaluations of plant biophysical attributes. PCA revealed unique spectral signatures, with the first principal component accounting for more than 90% of the variation in sensor data. High predictive accuracy was achieved for variables such as the thickness of the adaxial and abaxial hypodermis layers (R2 = 0.94) and total leaf thickness, although challenges remain in predicting parameters such as the thickness of the parenchyma and granum layers within the thylakoid membrane. The effectiveness of integrating ChlF and hyperspectral technologies, along with spectroradiometers and fluorescence sensors, in advancing plant physiological research and improving optical spectroscopy for environmental monitoring and assessment. These methods offer a good strategy for promoting sustainability in future agricultural practices across a broad range of plant species, supporting cell biology and material analyses.

A novel feature screening algorithm for low-resolution LIBS spectrum elemental quantification

This study presents an innovative approach that integrates Laser-Induced Breakdown Spectroscopy (LIBS) with chemometrics for the quantitative analysis of Si, Ca, Al, and Mg in geological samples. Given the spectral redundancy in low-resolution LIBS devices, the study employs pre-processing techniques, such as AirPLS, Wavelet Transform (WT), and normalization to mitigate spectral noise. Enhanced feature threshold searching is achieved by incorporating SHapley Additive exPlanations (SHAP) and LightGBM into the Boruta algorithm, substantially improving quantitative analysis models based on Support Vector Regression (SVR) and Partial Least Squares Regression (PLSR). The modified Boruta-SVR model demonstrated remarkable robustness, with R2 values of 0.9862, 0.9873, 0.9882, and 0.9916, and RMSE values of 0.8099, 0.324, 0.1378, and 0.2382, respectively, for Si, Ca, Al, and Mg. The results confirm that the Boruta-based feature selection method, when applied to low-resolution LIBS spectra, outperforms traditional methods, capturing unique sample features under mixed spectral peak conditions, thereby enhancing the robustness of quantitative analysis models.

Quantitatively characterization of rare earth ore by terahertz time-domain spectroscopy

The Bayan Obo deposit is the world’s largest polymetallic associated minerals deposit of rare earths, iron and niobium, and the rarity of its physical properties restrict the knowledge and understanding of its laws. Taking the high-grade mixed rare earth concentrate of Bayan Obo as the research object, terahertz time-domain spectroscopy (THz-TDS) has been adopted for the systematic investigation of high-grade rare earth concentrate base on the traditional X-ray fluorescence (XRF), X-ray diffraction (XRD), scanning electron microscopy (SEM) and thermogravimetric-differential thermal analysis (TG-DTA). The absorption coefficient and refractive index of high-grade rare earth ores and their associated minerals of fluorite and dolomite, are all investigated by terahertz time-domain spectroscopy. The terahertz spectral response is affected by the type of mineral and its content. The acquired rare earth terahertz spectral data are processed by correlation analysis. Three machine learning algorithms, Partial Least Squares Regression (PLSR), Random forest (RF) and Multilayer Perceptron (MLP), are used to achieve quantitative detection of their concentrations and components with the coefficient of determination R2 of the absorption coefficient of the optical parameter reaching up to 0.975, 0.992 and 0.984, respectively. This work promotes the growing understanding of terahertz transmission spectroscopy of rare earth-bearing minerals, which can be used to help guide the search for minerals, and to detect, identify as well as quantify them in geology. Terahertz time-domain spectroscopy supplies a new method for study of rare earth resources, and the comprehensive development and utilization of resources in the Bayan Obo deposit.

Determination of terpene-based VOCs emitted from pine wood using NIR spectroscopy

ABSTRACT In the search for a quick and less labor-intensive method for determining terpene emissions of high emitting wood like Pinus sylvestris, this study utilized near-infrared spectroscopy (NIR) combined with multivariate analysis methods and compared it to the standard measurement method according to the EN 16516 standard. The spectra were measured on the surface of solid-wood samples and correlated with the simultaneously determined air concentrations of terpenes. For α-pinene and 3-carene, prediction models were created using partial least squares regression (PLSR). Both work with determination coefficients of 0.77 and a Root Mean Square Error of Prediction (RMSEP) of 12% of the maximum emissions achievable in this study. A model based on the sum of the two terpenes was built and tested to determine the predictive capability of multiple similar substances simultaneously from the NIR recording. The model performs slightly worse, with a determination coefficient of 0.71 and RMSEP of 13%. Despite continuous expansion of the datasets for multiple models, no better metrics were achieved, likely because of the heterogeneous structure of wood when scanning a solid-wood surface. Systematic deviations were observed in particularly low reference ranges, which may indicate non-linearity in the relationship between terpenes and the NIR signal.

Enhancing the fermentation rate and aroma compounds of kiwi wine via the addition of nitrogen during the stationary phase

Nitrogen addition is a viable strategy for preventing sluggish or stuck fermentation and enhancing aroma profiles in the winemaking industry. Herein, nitrogen, in the form of amino acids mixture or diammonium hydrogen phosphate (DAP), was added at different fermentation periods to investigate its effects on the fermentation characteristics, non-volatile compounds and aroma profiles of kiwi wines. Both the amino acids mixture and DAP shortened fermentation time by 1–2 days and balanced organic acid proportion by reducing malic acid content and increasing citric acid content. Adding DAP significantly decreased higher alcohols content, whereas higher alcohols content was remarkably increased with amino acids mixture supplementation. Furthermore, nitrogen addition during the stationary phase was most conducive to synthesizing other beneficial aromas, especially acetate esters and medium-chain fatty acid ethyl esters (MCFAEEs), and improving the perception of tropical fruity and cream aromas in kiwi wines. Partial least-squares regression (PLSR) results showed there was a tight correlation between amino acids and volatile compounds. This study provides an insight into the development of high-quality kiwi wine and should serve as the theoretical foundation to support the application of nitrogen addition in the wine industry.

Pengaruh Brand Image, Kualitas Produk, dan Persepsi Harga terhadap Keputusan Pembelian Produk The Body Shop di Kota Surabaya

The Body Shop is a beauty brand known for its commitment to environmental responsibility. However, between 2019 and 2023, The Body Shop experienced a decline due to various factors. This research aims to examine whether Brand Image, Product Quality, and Price Perception influence consumers' purchasing decisions for The Body Shop products in Surabaya. The population in this study consists of residents of Surabaya who have purchased and used The Body Shop products. This research employs a quantitative method with 115 respondents selected through purposive sampling, a sampling technique based on specific criteria. The analysis applied in this study is Partial Least Square (PLS). The research results indicate that Brand Image, Product Quality, and Price Perception have a positive and significant impact on purchasing decisions for The Body Shop products in Surabaya..

Ecotoxicological risk assessment of active pharmaceutical ingredients (APIs) against different aquatic species leveraging intelligent consensus prediction and i-QSTTR modeling

The increasing presence of active pharmaceutical ingredients (APIs) in aquatic ecosystems, driven by widespread human use, poses significant risks, including acute and chronic toxicity to aquatic species. However, the scarcity of experimental toxicity data on APIs and related compounds due to the high costs, time requirements, and ethical concerns associated with animal testing hinders comprehensive risk assessment. In response, we developed quantitative structure-toxicity relationship (QSTR) and interspecies quantitative structure toxicity-toxicity relationship (i-QSTTR) models for three key aquatic species: zebrafish, water fleas, and green algae, using NOEC as an endpoint, following OECD guidelines. Algae, daphnia, and fish, recognized as standard organisms in toxicity testing, are crucial bio-indicators due to their size, transparency, adaptability, and regulatory acceptance. We used partial least squares (PLS) and multiple linear regression (MLR) methods for model development alongside machine learning techniques such as Random Forest (RF), Support Vector Machines (SVM), K-nearest Neighbor (kNN), and Neural Networks (NN) to enhance the predictivity. Lipophilicity, electronegativity, unsaturation, a molecular cyclized degree in molecular structure, large fragments, aliphatic secondary C(sp2), and R–CR–R groups were identified as critical biomarkers for API toxicity. Screening of the PPDB (pesticide properties databases) and DrugBank validated the practical application of these models, offering valuable tools for regulatory decisions, safer API design, and the preservation of aquatic biodiversity.

The Impact of Ethic and Competence on Audit Quality (Accountability as Moderating Variable)

Purpose: This study used accountability as a moderating variable to examine the impact of ethics and competence on audit quality. Methodology: The data used in this study were derived from a questionnaire survey distributed to respondents from October to December 2023. The respondents for this study were Badan Pemeriksa Keuangan (BPK) head office auditors at State Financial Auditor III. The respondents were selected using purposive sampling criteria. The final sample comprised 69 respondents. This study used the structural equation Modelling (SEM) approach with Smart Partial Least Square (PLS) software to analyze the data. Results: The findings show that ethics and competence positively affect audit quality. Accountability as a moderating variable strengthens the impact of ethics on audit quality. However, accountability does not influence the effect of competence on audit quality. Limitations: This research used a method of distributing questionnaires to several respondents online so that the questions from respondents regarding the questionnaires could not be confirmed directly. In addition, this study uses only two audit attributes as determinants of audit quality. Contribution: This research will provide an understanding of BPK stakeholders regarding the importance of ethics and competence for BPK auditors. Additionally, it is expected that they will not attempt to influence BPK auditors to commit ethical violations. Furthermore, this research is meritorious for BPK to investigate the factors that can encourage the accountability of auditors’ attitudes to improve audit quality.

The Effects of Technology Utilization in the Learning Process on Students' Psychological Well-being: The Perspectives of Constructivism Theory

<span lang="EN-AU">This research aims to make a significant contribution to the understanding of constructivism in the context of education through an in-depth exploration of the use of technology in the learning process and its impact on the psychological well-being of students. The study employs a quantitative approach, utilizing structural equation modeling (SEM) and Partial Least Square (PLS) for analysis. The research participants consist of 100 university students in Malang, Indonesia, selected to complete an online questionnaire. The study results indicate that the integration of technology into the learning process has a positive and significant impact on students' psychological well-being. The application of constructivism theory as a conceptual foundation for understanding the influence of technology in learning demonstrates that students' interactive role in constructing knowledge has a substantial effect. The use of various platforms such as Google Drive, Google Docs, Microsoft Office, Zoom, Google Meet, Canvas, Moodle, Grammarly, and Mendeley creates a learning context that facilitates collaboration, active participation, and the development of students' social skills. In the context of students' mental well-being, technology helps alleviate burdens by providing flexibility in completing tasks, stimulating a sense of connection through collaboration, and offering psychological support.</span>

Quantification of soluble protein content and characterization of protein secondary structure by Raman spectroscopy combined with chemometrics

In the large-scale industrialized production of soymilk, the accurate monitoring of protein content and its secondary structure is crucial to guarantee product quality and enhance nutritional value, while traditional protein detection methods have significant limitations. In this study, Raman spectroscopy was used to characterize the changes in the relative content of protein secondary structures during boiling, in which the α-helix structure was converted to other unstable secondary structures, indicating that the protein was thermally denatured. The study also accurately predicted the soluble protein content of soymilk for the first time by combining Raman spectroscopy and chemometrics based on algorithms such as Partial Least Squares (PLS), Least Squares Support Vector Machines (LSSVM), and Artificial Neural Networks (ANN). The results showed that the relative percentage deviation (RPD) values of all models were greater than 2, indicating that the models all possessed a certain degree of robustness; The PLS-based regression prediction model (with an average RPD value of 3.5592 and an average R2p of 0.9597) had the best overall prediction. The study's results can guide the soymilk production industry into online monitoring of soymilk quality.

Development of ventilator-associated pneumonia (VAP) prevention model in the hospital based on Six Sigma and VAP Bundle

Background & Objective: Ventilator-Associated Pneumonia (VAP) is the leading cause of death in Healthcare-Associated Infections (HCAI), with 30-day mortality of 59% of patients with ventilator devices. The aim of this research was to develop a VAP prevention model in the intensive care unit (ICU) based on Six Sigma and VAP Bundle, involving individual, organizational and work characteristics factors. Methodology: This research was carried out in the ICU, Poltekkes Kemenkes Malang, Malang, Indonesia, using a cross-sectional design. The research subjects were nurses, selected using a simple random sampling technique. All variables were measured through filling out questionnaires. Next, the measurement data was analyzed using Partial Least Square (PLS), based on Six Sigma and VAP Bundle. Results: Based on Six Sigma and VAP Bundle, the results of the analysis of the effects of the three factors on the implementation of VAP prevention were: 1) for individual factors, path coefficient = 0.189 and P = 0.000, so it was interpreted that this factor had a significant effect on the implementation of VAP prevention; 2) for organizational factors, path coefficient = 0.496 and P = 0.003, so it was interpreted that this factor also had a significant effect; 3) for the work characteristics factors, path coefficient = 0.289 and P = 0.000, so this factor also had a significant effect on the implementation of VAP prevention. Conclusion: Based on the research results, a VAP prevention model based on Six Sigma and VAP bundle was successfully built in the ICU, which involved organizational factors, work characteristics and individual factors. Abbreviations: HCAI - Healthcare-Associated Infections; HAP - Hospital-acquired pneumonia; PLS - Partial Least Square; SOP - standard operating procedure; VAP - ventilator-associated pneumonia; Keywords: Ventilator-Associated Pneumonia, VAP, Prevention; Six Sigma, VAP Bundle; Intensive Care Unit; organizational factors; work characteristics; individual factors Citation: Yuswanto TJA, Ernawati N, SolikhahFK, Nugroho HSW. Development of a prevention model for ventilator-associated pneumonia based on Six Sigma and VAP bundle. Anaesth. pain intensive care 2024;28(5):876−882; DOI: 10.35975/apic.v28i5.2574 Received: July 14, 2024; Reviewed: July 28, 2024; Accepted: July 28, 2024

Quantitative physics-physiology relationship modeling of human emotional response to Shu music.

Music perception is one of the most complex human neurophysiological phenomena invoked by sensory stimuli, which infers an internal representation of the structured events present in a piece of music and then forms long-term echoic memory for the music. An intrinsic relationship between the basic acoustic property (physics) of music and human emotional response (physiology) to the music is suggested, which can be statistically modeled and explained by using a novel notion termed as quantitative physics-physiology relationship (QPPR). Here, we systematically analyzed the complex response profile of people to traditional/ancient music in the Shu area, a geographical concept located in the Southwest China and one of three major origins of the Chinese nation. Chill was utilized as an indicator to characterize the response strength of 18 subjects to an in-house compiled repertoire of 86 music samples, consequently creating a systematic subject-to-sample response (SSTSR) profile consisting of 1,548 (18 × 86) paired chill elements. The multivariate statistical correlation of measured chill values with acoustic features and personal attributes was modeled by using random forest (RF) regression in a supervised manner, which was compared with linear partial least square (PLS) and non-linear support vector machine (SVM). The RF model exhibits possessed strong fitting ability (r F 2 = 0.857), good generalization capability (r P 2 = 0.712), and out-of-bag (OOB) predictability (r O 2 = 0.731) as compared to SVM and, particularly, PLS, suggesting that the RF-based QPPR approach is able to explain and predict the emotional change upon musical arousal. It is imparted that there is an underlying relationship between the acoustic physical property of music and the physiological reaction of the audience listening to the music, in which the rhythm contributes significantly to emotional response relative to timbre and pitch. In addition, individual differences, characterized by personal attributes, is also responsible for the response, in which gender and age are most important.

Application of antioxidant peptide‐based coating on fresh‐cut apple

SummaryFresh‐cut apples are susceptible to enzymatic browning and spoilage. The objective of this study was to evaluate the effect of different coatings on fresh‐cut apples and develop a predictive model for their shelf life. The apples were treated with antioxidant peptide from Candida utilis (CUH), carboxymethyl chitosan (CMCS), and composite coatings, and their physicochemical properties were subsequently evaluated. Key factors identified through correlation analysis of shelf life were used as input parameters for a partial least squares regression (PLSR) model to predict the shelf life of fresh‐cut apples treated with different coatings. The results indicate that CUH, CMCS, and CUH‐CMCS coatings effectively delay the deterioration of fresh‐cut apples. Notably, the CUH‐CMCS composite coating demonstrated superior performance, showing only a slight 3.50% increase in the browning index (BI) during storage. Minimal changes were observed in weight loss and firmness, while overall total acidity (TA) and pH exhibited slight decreases. Moreover, the levels of ascorbic acid (Vc), polyphenol oxidase (PPO), and peroxidase (POD) were significantly lower compared to the control group, and the total bacterial count increased by no more than 0.7 log CFU g−1. The PLSR model accurately predicted the shelf life of fresh‐cut apples treated with different coatings, with and values both exceeding 0.90. The research results indicate that the coating and model developed in this study offer a novel approach for preserving and managing fresh‐cut apples.