Optimizing feature selection with gradient boosting machines in PLS regression for predicting moisture and protein in multi-country corn kernels via NIR spectroscopy.

Differences in moisture and protein content impact both nutritional value and processing efficiency of corn kernels. Near-infrared (NIR) spectroscopy can be used to estimate kernel composition, but models trained on a few environments may underestimate error rates and bias. We assembled corn samples from diverse international environments and used NIR with chemometrics and partial least squares regression (PLSR) to determine moisture and protein. The potential of five feature selection methods to improve prediction accuracy was assessed by extracting sensitive wavelengths. Gradient boosting machines (GBMs), particularly CatBoost and LightGBM, were found to effectively select crucial wavelengths for moisture (1409, 1900, 1908, 1932, 1953, 2174 nm) and protein (887, 1212, 1705, 1891, 2097, 2456 nm). SHAP plots highlighted significant wavelength contributions to model prediction. These results illustrate GBMs' effectiveness in feature engineering for agricultural and food sector applications, including developing multi-country global calibration models for moisture and protein in corn kernels.

Knowledge of gendered needs among the planners and policy makers for prevention of NCDs in Bangladesh: a qualitative exploration.

BACKGROUND: Globally, non-communicable diseases (NCDs) are increasingly the primary cause of mortality and morbidity among women. Like many developing countries, Bangladesh also faces a growing burden of NCDs. The "Multisectoral Action Plan for Prevention and Control of Non-communicable Diseases, 2018-2025" signifies Bangladesh's commitment to comprehensively combating the rising burden of NCDs. This study investigates the perceptions of those involved in developing the action plan and if/how a gender lens was incorporated into its implementation. METHODS: In-depth interviews were conducted with 25 key individuals involved in a high-level committee to develop and implement Bangladesh's multisectoral action plan to address the burden of NCDs. Data were collected between July and November 2021, and thematic analysis was conducted. RESULTS: The findings revealed that interviewees believed the multisectoral action plan adopted a population-wide approach without considering gender-specific needs. This study presents the explanations for this inattention under five themes: (1) A population-level approach to NCD prevention; (2) Understanding women's health beyond reproductive health; (3) Absence of gender-specific programs; (4) Lack of consideration of gender constraints on physical activity; and (5) Lack of collaborative efforts to address NCDs beyond the health ministry. CONCLUSION: In conclusion, governments in countries like Bangladesh can develop more effective strategies to reduce the disease burden of NCDs among women by recognizing and addressing the gendered nature of preventive health. This can be achieved by promoting gender-responsive research, programs, and policy initiatives that consider women's specific health concerns, ultimately leading to better health outcomes for all.

Advancements, limitations and challenges in hyperspectral imaging for comprehensive assessment of wheat quality: An up-to-date review.

The potential of hyperspectral imaging technology (HIT) for the determination of physicochemical and nutritional components, evaluation of fungal/mycotoxins contamination, wheat varieties classification, identification of non-mildew-damaged wheat kernels, as well as detection of flour adulteration is comprehensively illustrated and reviewed. The latest findings (2018-2023) of HIT in wheat quality evaluation through internal and external attributes are compared and summarized in detail. The limitations and challenges of HIT to improve assessment accuracy are clearly described. Additionally, various practical recommendations and strategies for the potential application of HIT are highlighted. The future trends and prospects of HIT in evaluating wheat quality are also mentioned. In conclusion, HIT stands as a cutting-edge technology with immense potential for revolutionizing wheat quality evaluation. As advancements in HIT continue, it will play a pivotal role in shaping the future of wheat quality assessment and contributing to a more sustainable and efficient food supply chain.

Correction: Low-cost electronic-nose (LC-e-nose) systems for the evaluation of plantation and fruit crops: recent advances and future trends.

Correction for 'Low-cost electronic-nose (LC-e-nose) systems for the evaluation of plantation and fruit crops: recent advances and future trends' by Marcus Vinicius da Silva Ferreira et al., Anal. Methods, 2023, https://doi.org/10.1039/D3AY01192E.

Low-cost electronic-nose (LC-e-nose) systems for the evaluation of plantation and fruit crops: recent advances and future trends.

An electronic nose (e-nose) is a device designed to recognize and classify odors. The equipment is built around a series of sensors that detect the presence of odors, especially volatile organic compounds (VOCs), and generate an electric signal (voltage), known as e-nose data, which contains chemical information. In the food business, the use of e-noses for analyses and quality control of fruits and plantation crops has increased in recent years. Their use is particularly relevant due to the lack of non-invasive and inexpensive methods to detect VOCs in crops. However, the majority of reports in the literature involve commercial e-noses, with only a few studies addressing low-cost e-nose (LC-e-nose) devices or providing a data-oriented description to assist researchers in choosing their setup and appropriate statistical methods to analyze crop data. Therefore, the objective of this study is to discuss the hardware of the two most common e-nose sensors: electrochemical (EC) sensors and metal oxide sensors (MOSs), as well as a critical review of the literature reporting MOS-based low-cost e-nose devices used for investigating plantations and fruit crops, including the main features of such devices. Miniaturization of equipment from lab-scale to portable and convenient gear, allowing producers to take it into the field, as shown in many appraised systems, is one of the future advancements in this area. By utilizing the low-cost designs provided in this review, researchers can develop their own devices based on practical demands such as quality control and compare results with those reported in the literature. Overall, this review thoroughly discusses the applications of low-cost e-noses based on MOSs for fruits, tea, and coffee, as well as the key features of their equipment (i.e., advantages and disadvantages) based on their technical parameters (i.e., electronic and physical parts). As a final remark, LC-e-nose technology deserves significant attention as it has the potential to be a valuable quality control tool for emerging countries.

Non-destructive optical sensing technologies for advancing the egg industry toward Industry 4.0: A review.

The egg is considered one of the best sources of dietary protein, and has an important role in human growth and development. With the increase in the world's population, per capita egg consumption is also increasing. Ground-breaking technological developments have led to numerous inventions like the Internet of Things (IoT), various optical sensors, robotics, artificial intelligence (AI), big data, and cloud computing, transforming the conventional industry into a smart and sustainable egg industry, also known as Egg Industry 4.0 (EI 4.0). The EI 4.0 concept has the potential to improve automation, enhance biosecurity, promote the safeguarding of animal welfare, increase intelligent grading and quality inspection, and increase efficiency. For a sustainable Industry 4.0 transformation, it is important to analyze available technologies, the latest research, existing limitations, and prospects. This review examines the existing non-destructive optical sensing technologies for the egg industry. It provides information and insights on the different components of EI 4.0, including emerging EI 4.0 technologies for egg production, quality inspection, and grading. Furthermore, drawbacks of current EI 4.0 technologies, potential workarounds, and future trends were critically analyzed. This review can help policymakers, industrialists, and academicians to better understand the integration of non-destructive technologies and automation. This integration has the potential to increase productivity, improve quality control, and optimize resource management toward sustainable development of the egg industry.

Organic compound-based nanozymes for agricultural herbicide detection.

Nanozymes are increasingly being used for agricultural applications, but their adoption is limited as they are generally considered toxic, have low cost-effectiveness, and pose complexity of fabrication. In this study, an organic compound-based, peroxidase-like nanozyme (OC nanozyme) was developed for use in the agricultural environment. This nanozyme was synthesized through a self-assembled one-pot particle synthesis process, interacting with urea and the metal ion to form a homogenous nanoparticle containing partially mimicked cofactors (Fe-N) of the natural enzyme. The OC nanozyme exhibited decent kinetic properties (H2O2/Km:0.056 mM and Vmax:2.19 µM s-1) and pH stability. The OC nanozyme was successfully used to detect glyphosate via integrated colorimetric assay, with a good limit of detection (LOD) of at least 0.001 ng mL-1. The authors envision that this agricultural-friendly OC nanozyme holds great potential for a wide range of agricultural applications.

Global calibration for non-targeted fraud detection in quinoa flour using portable hyperspectral imaging and chemometrics.

Quinoa is one of the highest nutritious grains, and global consumption of quinoa flour has increased as people pay more attention to health. Due to its high value, quinoa flour is susceptible to adulteration. Cross-contamination between quinoa flour and other flour can be easily neglected due to their highly similar appearance. Therefore, detecting adulteration in quinoa flour is important to consumers, industries, and regulatory agencies. In this study, portable hyperspectral imaging in the visible near-infrared (VNIR) spectral range (400-1000 nm) was applied as a rapid tool to detect adulteration in quinoa flour. Quinoa flour was adulterated with wheat, rice, soybean, and corn in the range of 0-98% with 2% increments. Partial least squares regression (PLSR) models were developed, and the best model for detecting the % authentic flour (quinoa) was obtained by the raw spectral data with R2p of 0.99, RMSEP of 3.08%, RPD of 8.77, and RER of 25.32. The model was improved, by selecting only 13 wavelengths using bootstrapping soft shrinkage (BOSS), to R2p of 0.99, RMSEP of 2.93%, RPD of 9.18, and RER of 26.60. A visualization map was also generated to predict the level of quinoa in the adulterated samples. The results of this study demonstrate the ability of VNIR hyperspectral imaging for adulteration detection in quinoa flour as an alternative to the complicated traditional method.

Antioxidant assessment of agricultural produce using fluorescence techniques: a review.

The study of bioactive compounds like food antioxidants is getting huge attention and curiosity by researchers and other relevant stakeholders (e.g., food and pharmaceutical industries) due to their health benefits. However, the currently available protocols to estimate the antioxidant activity of foods are time-consuming, destructive, require complex procedures for sample preparation, need technical persons, and not possible for real-time application, which are very important for large-scale or industrial applications. On the other hand, fluorescence spectroscopy and imaging techniques are relatively new, fast, mostly nondestructive, and possible to apply real-time to detect the antioxidants of foods. However, there is no review article on fluorescence techniques for estimating antioxidants in agricultural produces. Therefore, the present review comprehensively summarizes the overview of fluorescence phenomena, techniques (i.e., spectroscopy and computer vision), and their potential to monitor antioxidants in fruits and vegetables. Finally, opportunities and challenges of fluorescence techniques are described toward developing next-generation protocols for antioxidants measurement. Fluorescence techniques (both spectroscopy and imaging) are simpler and faster than available traditional methods of antioxidants measurement. Moreover, the fluorescence imaging technique has the potential to apply in real-time antioxidant identification in agricultural produce such as fruits and vegetables. Therefore, this technique might be used as a next-generation protocol for qualitative and quantitative antioxidants measurement after improvements like new material technologies for sensor (detector) and light sources for higher sensitivity and reduce the cost of implementing real-world applications.

Optical sensing as analytical tools for meat tenderness measurements - A review.

Meat tenderness is the most important attribute related to consumer satisfaction. No analytical tool is currently available to measure or predict tenderness in real-time. Therefore, direct measurement of meat tenderness is not possible in the meat industry. Several reviews are available on optical sensing technologies for meat; however, no comprehensive review is available on optical sensing for meat tenderness. The simplicity, accuracy, and limited sample preparation have made optical techniques the best tools for determining meat tenderness. This paper reviews the perspectives and aspects of conventional tenderness measurement tools along with some selected optical sensing technologies for meat tenderness. Additionally, the major challenges of optical sensing techniques and future trends will also be addressed. If adequately optimized, optical sensing techniques could be incorporated into the production line to measure tenderness in real-time for correct labeling, pricing, and screening of meat to better provide consumers with the products they desire.

Risk communication and community engagement in the context of COVID-19 response in Bangladesh: a qualitative study.

Background: The global COVID-19 pandemic profoundly impacted nations worldwide, and Bangladesh was no exception. In response, the government of Bangladesh implemented community awareness initiatives aimed at containing the spread of the virus, aligned with international guidelines and recommendations. Despite these efforts, a lack of comprehensive community awareness programs played an essential role during the pandemic, not the preventive measures. A qualitative study employing framing theory was conducted to gain a deeper insight into how the social context influenced risk communication and community response throughout the COVID-19 pandemic in Bangladesh. Methods: The study was conducted in four selected districts of Bangladesh from February to May 2022 using complementary data collection methods, including key informant interviews, in-depth interviews, and focus group discussions with purposely selected participants. Data were analyzed thematically by following six steps of the thematic analysis process. Codes were developed based on the data and summarized into themes and sub-themes grounded on the codes. Results: The findings indicate that the government of Bangladesh, along with development partners and non-government organizations, made a significant effort to raise awareness about COVID-19 in the community. However, there were certain limitations to this effort. These include a lack of social science and public health approaches to understanding the pandemic; inadequate coordination among the authorities for COVID-19 prevention and control; technological and geographical barriers for disseminating messages; the living conditions and lack of facilities; socio-cultural norms in understanding the COVID-19 health messages, and the gendered understanding of the messages. The findings also revealed that the awareness activities remained a one-way approach to inform the people and faced challenges to actively engage and create ownership of the community in the pandemic response. Conclusion: The study identified gaps in implementing risk communication and community engagement strategies in Bangladesh during the COVID-19 pandemic. Increasing focus on public health and prioritizing community ownership is essential to designing a more effective community awareness campaign. This approach will help ensure that health messages are communicated effectively and tailored to different communities' needs.

Production of Reactive Oxygen Species via Nanobubble Water Improves Radish Seed Water Absorption and the Expression of Aquaporin Genes.

Nanobubbles (NBs) stimulate seed germination; however, the mechanism of the promotion effect of NBs remains unclear. The impact of NBs on seed water absorption was investigated; we subsequently studied the genes associated with the response of radish seeds to NB water and used RNA sequencing to generate their expression profiles, especially those of aquaporin genes. NB water significantly promoted germination. The times at which 50% of the germinating seeds achieved germination (T50) for the submerged radish seeds in NB and control water were 11.6 and 17.4 h, respectively. NB water-germinated radish seeds showed a water uptake rate coefficient that was 15% higher than that of those germinated in control water. Through GO enrichment and cluster analyses, it was evident that NB water significantly increased the level of expression of the genes associated with the following activities: oxidoreductase, peroxidase, and antioxidant. Our results demonstrated that NB water increases the water uptake rate of radish seeds via two mechanisms. The NB water-produced exogenous hydroxyl radical (•OH) increases the seed coat's water permeability and enhances cell wall loosening, and NB water increases the aquaporin gene expression level of radish seeds.

A Rapid Ethnographic Assessment of Cultural and Social Perceptions and Practices About COVID-19 in Bangladesh: What the Policy Makers and Program Planners Should Know.

Anthropological literature on health beliefs and practices related to COVID-19 is scarce, particularly in low and middle-income countries. We conducted a qualitative research on perceptions of COVID-19 among slum residents of Dhaka, Bangladesh from November 2020 through January, 2021. Methods included in-depth interviews and photo elicitation with community residents. Interviews were transcribed and analyzed thematically. Results show scientific explanations of COVID-19 conflicted with interviewees' cultural and spiritual beliefs such as: coronavirus is a disease of rich, sinful people; the virus is a curse from Allah to punish sinners. Interviewees rejected going to hospitals in favor of home remedies, and eschewed measures such as mask-wearing or social distancing instead preferring to follow local beliefs. We have highlighted a gap between community beliefs about the pandemic and science-led interventions proposed by health professionals. For public health policy to be more effective it requires a deeper understanding of and response to community perceptions.

Impact of the COVID-19 lockdown on intimate partner violence: Issues of non-reporting in Bangladesh.

INTRODUCTION: COVID-19 pandemic induced lockdown as prevention and control measure, forced people globally to limit their movements and to stay at home for extended period of time. The objective of this study was to analyze the impact of lockdown on intimate partner violence in Bangladesh. METHODS: We conducted a secondary research by employing a Poisson regression model to estimate the effect of pandemic-led lockdown policy on the change in the number of intimate partner violence-related calls during pandemic using national emergency helpline 999 call logs. Data from January 2019 to May 2020 for 64 districts produced 1088 district-month-year observations which had been used for the main analysis. RESULTS: We found a 46% decrease in the incidence rate of intimate partner violence-related calls during the pandemic after adjusting for year, month, district fixed-effects-suggesting, non-reporting of the violence might have exacerbated during lockdown. CONCLUSION: While increasing rate of intimate partner violence is one side of issue, non-reporting of it has received less attention and during the lockdown non-reporting might grow large and have severe health impacts for women.

Effect of variable selection algorithms on model performance for predicting moisture content in biological materials using spectral data.

Variable selection is a critical step for designing a dedicated multispectral real-time system from multicollinearity spectral data. It improves the prediction ability of the calibration model and provides faster prediction by reducing the curse of dimensionality. The main objective of this study was to compare the effect of variables selection algorithms on model performance for predicting moisture content in red meat using visible and near-infrared (VNIR) hyperspectral imaging in the spectral range of 400-1000 nm and corn using near-infrared (NIR) spectroscopy in the spectral range of 1100-2498 nm. Six variable selection algorithms including the size of the regression coefficient (RC), variable importance in projection (VIP), genetic algorithm (GA), competitive adaptive reweighted sampling (CARS), successive projection algorithm (SPA), and stepwise regression (SWR) were tested and compared to realize their effects on the model performance for predicting moisture content in red meat and corn. The model based on competitive adaptive reweighted sampling-partial least squares regression (CARS-PLSR) was the best model to predict moisture content in red meat and corn. The results indicated the effectiveness of variable selection for providing the feature wavelengths to design a low-cost, real-time multispectral system.

Identification of informative spectral ranges for predicting major chemical constituents in corn using NIR spectroscopy.

Many studies have been conducted using NIR spectroscopy to predict corn constituents; however, a systematic investigation of the spectral sub-regions under the scope of overtones and combinations has not been performed. In this study, the corn spectra were divided into second overtones (1100-1388 nm), first overtones (1390-1852 nm), and combinations (1852-2498 nm). Then, using variable importance in projection and genetic algorithm, each region was inspected sequentially to identify the most informative sub-region for each attribute to improve interpretability. The identified spectral subsets were further tuned to select the most influential bands for each attribute. The sub-regions in combinations bands was most informative for predicting water (1908-2108 nm, 2 bands), oil (2176-2304 nm, 6 bands), and protein (2130-2190 nm, 3 bands), whereas the first overtones region was the best for predicting starch (1452-1770 nm, 5 bands). Results provided valuable information for potential hardware and software improvements.

An overview of recent advances and applications of FT-IR spectroscopy for quality, authenticity, and adulteration detection in edible oils.

Authenticity and adulteration detection are primary concerns of various stakeholders, such as researchers, consumers, manufacturers, traders, and regulatory agencies. Traditional approaches for authenticity and adulteration detection in edible oils are time-consuming, complicated, laborious, and expensive; they require technical skills when interpreting the data. Over the last several years, much effort has been spent in academia and industry on developing vibrational spectroscopic techniques for quality, authenticity, and adulteration detection in edible oils. Among them, Fourier transforms infrared (FT-IR) spectroscopy has gained enormous attention as a green analytical technique for the rapid monitoring quality of edible oils at all stages of production and for detecting and quantifying adulteration and authenticity in edible oils. The technique has several benefits such as rapid, precise, inexpensive, and multi-analytical; hence, several parameters can be predicted simultaneously from the same spectrum. Associated with chemometrics, the technique has been successfully implemented for the rapid detection of adulteration and authenticity in edible oils. After presenting the fundamentals, the latest research outcomes in the last 10 years on quality, authenticity, and adulteration detection in edible oils using FT-IR spectroscopy will be highlighted and described in this review. Additionally, opportunities, challenges, and future trends of FT-IR spectroscopy will also be discussed.

Application of NIR spectroscopy and multivariate analysis for Non-destructive evaluation of apple moisture content during ultrasonic drying.

Direct-contact ultrasonic drying is a novel approach to dehydrate fruits and vegetables to reduce microbial growth and post-harvest loss while preserving nutrients and the quality of the final product. Moisture content is a critical component for food behavior during drying, and its accurate evaluation in real-time is essential for food quality control. This study conveys the potential implementation of portable near-infrared spectroscopy (NIRS) combined with multivariate analysis for real-time assessment of moisture content in apple slices during direct-contact ultrasonic drying. Partial least squares regression (PLSR) and Gaussian process regression (GPR) models were developed, and their performances for different pre-treatments methods and data partitioning algorithms were evaluated with both internal cross-validation and an external dataset. Three wavelengths were selected by SPA (1359, 1517, and 1594 nm) which were then used to introduce a closed-form equation for moisture content prediction with R2p = 0.99 and RMSEP = 3.32%. The results revealed that portable NIRS combined with multivariate analysis is quite promising for monitoring and evaluating the moisture content during ultrasonic drying.

Characterizing the interactions between copper ions and dissolved organic matter using fluorescence excitation-emission matrices with two-dimensional Savitzky-Golay second-order differentiation.

Monitoring dissolved organic matter (DOM) content in aquatic environments is crucial for not only understanding the dynamics of heavy metals but also predicting their bioavailability. Fluorescence spectroscopy is typically employed to characterise DOM. Here, the interaction between DOM and trace metals was investigated by combining excitation-emission matrix (EEM) quenching with two-dimensional Savitzky-Golay second-order differentiation (2D-SG-2nd-df) analysis. The 2D-SG-2nd-df analysis decomposed the EEM spectra of commercial humic acid (HA) samples into six separate fluorescence peaks, which agreed with the results obtained through conventional parallel factor (PARAFAC) analysis. Compared with PARAFAC modeling, the 2D-SG-2nd-df approach provided more valid and reliable results when the dataset contained distinct samples. Moreover, since the results obtained from 2D-SG-2nd-df for each sample are independent, shifts in the peak wavelength can be reproduced more efficiently using this method. Triplicate titration experiments showed clear differences in HA-copper interactions for samples with different HA composition and molecular weight. The binding strength between copper and low-molecular-weight DOM in water was weaker than that observed for high-molecular-weight DOM. The results obtained in this study will serve as a basis for applying 2D-SG-2nd-df not only to DOM but also to other samples studied using EEM measurements.

Online monitoring of red meat color using hyperspectral imaging.

A hyperspectral imaging system in the spectral range of 400-1000 nm was tested to develop an online monitoring system for red meat (beef, lamb, and pork) color in the meat industry. Instead of selecting different sets of important wavelengths for beef, lamb, and pork, a set of feature wavelengths were selected using the successive projection algorithm for red meat colors (L*, a*, b) for convenient industrial application. Only six wavelengths (450, 460, 600, 620, 820, and 980 nm) were further chosen as predictive feature wavelengths for predicting L*, a*, and b* in red meat. Multiple linear regression models were then developed and predicted L*, a*, and b* with coefficients of determination (R(2)p) of 0.97, 0.84, and 0.82, and root mean square error of prediction of 1.72, 1.73, and 1.35, respectively. Finally, distribution maps of meat surface color were generated. The results indicated that hyperspectral imaging has the potential to be used for rapid assessment of meat color.