Figure - available from: Food Engineering Reviews
This content is subject to copyright. Terms and conditions apply.
Source publication
Near-infrared (NIR) spectroscopy as a low-cost technique with its non-destructive fast nature, precision, control, accuracy, repeatability, and reproducibility has been extensively employed in most industries for food quality measurements. Its coupling to different modeling techniques has been identified as a way of improving the accuracy and robus...
Similar publications
This study aimed to compare the organoleptic and nutritional quality of four sheep meats produced in Morocco. This comparison was carried out by analyzing the proximate composition, amino acid profile, and mineral content of meat. The majority of the evaluated parameters were influenced by genetic and geographical factors (p < 0.05). The longissimu...
Citations
... In comparison to hyperspectral imaging technology, the advantages of traditional NIR spectroscopy technology are convenience, low cost, high inspection efficiency, and multi-index measurement capability [15]. Recent improvements in miniaturization and mathematical tools has led to a wide application of NIR spectroscopy technology in the quality analysis of agricultural products, such as fruit and seeds [16]. In terms of fruit quality evaluation, NIR spectroscopy technology has been used for fruit sorting by detecting fruit sugar content and internal bruising in a commercial packing line with a speed of five or more fruits per second. ...
The harvest year of maize seeds has a significant impact on seed vitality and maize yield. Therefore, it is vital to identify new seeds. In this study, an on-line near-infrared (NIR) spectra collection device (899–1715 nm) was designed and employed for distinguishing maize seeds harvested in different years. Compared with least squares support vector machine (LS-SVM), k-nearest neighbor (KNN), and extreme learning machine (ELM), the partial least squares discriminant analysis (PLS-DA) model has the optimal recognition performance for maize seed harvest years. Six different preprocessing methods, including Savitzky–Golay smoothing (SGS), standard normal variate transformation (SNV), multiplicative scatter correction (MSC), Savitzky–Golay 1 derivative (SG-D1), Savitzky–Golay 2 derivative (SG-D2), and normalization (Norm), were used to improve the quality of the spectra. The Monte Carlo cross-validation uninformative variable elimination (MC-UVE), competitive adaptive reweighted sampling (CARS), bootstrapping soft shrinkage (BOSS), successive projections algorithm (SPA), and their combinations were used to obtain effective wavelengths and decrease spectral dimensionality. The MC-UVE-BOSS-PLS-DA model achieved the classification with an accuracy of 88.75% using 93 features based on Norm preprocessed spectral data. This study showed that the self-designed NIR collection system could be used to identify the harvested years of maize seed.
... Due to the larger margin created and linear separation by the algorithm, the classification is more precise. SVM is one of the robust techniques used in the detection of meat adulteration in its products in recent times [102]. ...
... Choosing between linear and nonlinear algorithms depends on the complexity of the relationships in the data. Linear algorithms may be sufficient for simpler relationships , while nonlinear algorithms can capture more intricate patterns (Zareef et al., 2020). In practice, a combination of linear and nonlinear algorithms may be employed to ensure the flexibility needed for accurate calibration and prediction in NIR analysis. ...
NIR sensors, in conjunction with advanced chemometric algorithms, have proven to be a powerful and efficient tool for intelligent quality evaluation of sweetpotato roots throughout the entire supply chain. By leveraging NIR data in different wavelength ranges, the physicochemical, nutritional and antioxidant compositions, as well as variety classification of sweetpotato roots during the different stages were adequately evaluated, and all findings involving quantitative and qualitative investigations from the beginning to the present were summarized and analyzed comprehensively. All chemometric algorithms including both linear and nonlinear employed in NIR analysis of sweetpotato roots were introduced in detail and their calibration performances in terms of regression and classification were assessed and discussed. The challenges and limitations of current NIR application in quality evaluation of sweetpotato roots are emphasized. The prospects and trends covering the ongoing advancements in software and hardware are suggested to support the sustainable and efficient sweetpotato processing and utilization.
... Inspection based on images of structures is one of the non-invasive methods in the health monitoring of structures (Choudhary et al., 2021). Among the methods of artificial intelligence, artificial neural networks have been used in many pieces of research due to their high speed and ability to model relationships non-linearly (Zareef et al., 2020). Although neural networks have been successfully used in many damage detection methods, they still have problemsthe sensitivity of these networks to input changes Xu et al., 2019). ...
Purpose
This study aims to obtain methods to identify and find the place of damage, which is one of the topics that has always been discussed in structural engineering. The cost of repairing and rehabilitating massive bridges and buildings is very high, highlighting the need to monitor the structures continuously. One way to track the structure's health is to check the cracks in the concrete. Meanwhile, the current methods of concrete crack detection have complex and heavy calculations.
Design/methodology/approach
This paper presents a new lightweight architecture based on deep learning for crack classification in concrete structures. The proposed architecture was identified and classified in less time and with higher accuracy than other traditional and valid architectures in crack detection. This paper used a standard dataset to detect two-class and multi-class cracks.
Findings
Results show that two images were recognized with 99.53% accuracy based on the proposed method, and multi-class images were classified with 91% accuracy. The low execution time of the proposed architecture compared to other valid architectures in deep learning on the same hardware platform. The use of Adam's optimizer in this research had better performance than other optimizers.
Originality/value
This paper presents a framework based on a lightweight convolutional neural network for nondestructive monitoring of structural health to optimize the calculation costs and reduce execution time in processing.
... Consequently, this method can assist in prioritizing further research on suspicious samples and saving time. Additionally, the utilization of portable devices available in the market enables swift initial screening of samples (26,27). ...
Background: Olive oil is one of the most essential components of the Mediterranean diet, obtained by mechanical extraction from the Olea europaea tree. Based on organoleptic properties (odor and taste) and the amount of free fatty acids, it is divided into three categories: olive oil, virgin olive oil, and extra virgin olive oil. Due to the expensive production procedure of extra virgin olive oil, it is prone to adulteration with low-quality olive oils and other vegetable oils. Objectives: The current study focused on determining the authenticity of olive oil using near-infrared spectroscopy as a non-destructive method in conjunction with chemometrics. Methods: In this study, 100 samples of olive oils, comprising 34 domestic and 66 industrial olive oils, were purchased from the markets of Tehran and Roudbar. Common adulterants such as corn, canola, sunflower, and soybean oils were considered. Binary and ternary mixtures of olive oil with these vegetable oils were prepared and analyzed. Spectra were collected over the range of 12000 cm-1 to 4000 cm-1, and the data were preprocessed using SNV and Detrend before principal component analysis (PCA). Results: The results indicated that corn oil and canola oil were the dominant adulterants in the olive oil samples, likely due to their inexpensiveness and availability in Iran. Conclusions: Since multiple types of fraud were identified in the examined samples, it is recommended that future studies investigate other forms of fraud simultaneously. Additionally, the results demonstrated that principal component analysis could effectively categorize different samples with acceptable discrimination.
... In recent years, it has been employed in many industries to analyze the chemical composition of organic samples, drugs, food, and other compounds. In particular, the food industry is used for the quantitative and qualitative analysis of foods such as meat, fruit, grain, dairy products, and beverages [16,40,120]. ...
... ANNs excel in modeling nitrate leaching due to their capacity to capture complex non-linear relationships in environmental data 96 . Their adaptability suits dynamic systems, recognizing intricate patterns and interactions among variables 97 . Moreover, ANNs can handle missing data, ensuring meaningful predictions for nitrate leaching, making them effective tools for understanding and predicting the behavior of this environmental process. ...
An accurate assessment of nitrate leaching is important for efficient fertiliser utilisation and groundwater pollution reduction. However, past studies could not efficiently model nitrate leaching due to utilisation of conventional algorithms. To address the issue, the current research employed advanced machine learning algorithms, viz., Support Vector Machine, Artificial Neural Network, Random Forest, M5 Tree (M5P), Reduced Error Pruning Tree (REPTree) and Response Surface Methodology (RSM) to predict and optimize nitrate leaching. In this study, Urea Super Granules (USG) with three different coatings were used for the experiment in the soil columns, containing 1 kg soil with fertiliser placed in between. Statistical parameters, namely correlation coefficient, Mean Absolute Error, Willmott index, Root Mean Square Error and Nash–Sutcliffe efficiency were used to evaluate the performance of the ML techniques. In addition, a comparison was made in the test set among the machine learning models in which, RSM outperformed the rest of the models irrespective of coating type. Neem oil/ Acacia oil(ml): clay/sulfer (g): age (days) for minimum nitrate leaching was found to be 2.61: 1.67: 2.4 for coating of USG with bentonite clay and neem oil without heating, 2.18: 2: 1 for bentonite clay and neem oil with heating and 1.69: 1.64: 2.18 for coating USG with sulfer and acacia oil. The research would provide guidelines to researchers and policymakers to select the appropriate tool for precise prediction of nitrate leaching, which would optimise the yield and the benefit–cost ratio.
... The spectrum generated by the spectroscopic techniques requires interpretation for detecting adulteration in food samples by understanding the correlation between the spectral data and the sample characteristic, and the process is termed as calibration process in spectroscopy (Zareef et al., 2020). Manual calibration is a challenging task due to the overlapping of peaks, noises, and effects of external factors in spectral data (Mousa et al., 2021). ...
... Smoothing techniques lower the amount of high-frequency noise or random variations in spectra, which improves the ratio of signal to noise, and usually, smoothing is combined with other pre-processing methods to eliminate the noises. Moving average, the Savitzky-Golay (SG) algorithm and Gaussian smoothing are the commonly used methods to eliminate small-scale noise, improve the clarity of spectral features, and enable easier identification and analysis (Zareef et al., 2020). SG algorithm is a widely used algorithm in spectroscopic data processing. ...
... This correction improves the accuracy of subsequent analysis, particularly when comparing samples with varying scattering properties. SNV removes the variation in slope and does the correction in scatter effects, while light scattering correction is done by MSC (Zareef et al., 2020). Normalization techniques aim to eliminate intensity variations between spectra caused by factors such as differences in sample thickness, concentration, or instrumental response. ...
... The NIR spectroscopy belongs to the absorption spectrum of molecular vibration frequency doubling and frequency combination. This is especially true for hydrogen-based chemical bonds (such as O-H, C-H, and N-H) (Zareef et al., 2020). Therefore, sensitive chemical groups with unique spectral information can be characterized for qualitative and quantitative analysis (Li et al., 2020a). ...
In recent years, the food industry has shown a growing interest in the development of rapid and nondestructive analytical methods. However, the utilization of a solitary nondestructive detection technique offers only a constrained extent of physical or chemical insights regarding the sample under examination. To overcome this limitation, the amalgamation of spectroscopy with data fusion strategies has emerged as a promising approach. This comprehensive review delves into the fundamental principles and merits of low‐level, mid‐level, and high‐level data fusion strategies within the domain of food analysis. Various data fusion techniques encompassing spectra‐to‐spectra, spectra‐to‐machine vision, spectra‐to‐electronic nose, and spectra‐to‐nuclear magnetic resonance are summarized. Moreover, this review also provides an overview of the latest applications of spectral data fusion techniques (SDFTs) for classification, adulteration, quality evaluation, and contaminant detection within the purview of food safety analysis. It also addresses current challenges and future prospects associated with SDFTs in real‐world applications. Despite the extant technical intricacy, the ongoing evolution of online data fusion platforms and the emergence of smartphone‐based multi‐sensor fusion detection technology augur well for the pragmatic realization of SDFTs, endowing them with formidable capabilities for both qualitative and quantitative analysis in the realm of food analysis.
... The comparison of all probabilistic and non-probabilistic models developed in the study on the basis of accuracy on test dataset revealed that ANN outperformed all other classification models with highest accuracy at 95% followed by SVM and LDA at 90% while 80% accuracy was observed for RF and logistic regression [78]. The F1-Score, which balances precision and recall, highlighted the superiority of ANN with a score of 0.952, followed by LDA and SVM at 0.909, SVM at 0.909, RF at 0.833, and logistic regression at 0.818 (Table 1). ...
