Determination of the optimal number of components in independent components analysis

Chemometrics-driven monitoring of cheese ripening: a multimodal spectroscopic and scanning electron microscopy investigation

The integration of spectroscopic techniques with chemometrics offers a means to monitor quality changes in dairy products throughout processing and storage. This study employed Attenuated Total Reflectance-Mid-Infrared Spectroscopy (ATR-MIR) coupled with Independent Components Analysis (ICA), and 3D Front-Face Fluorescence Spectroscopy (FFFS) paired with Common Components and Specific Weight Analysis (CCSWA). The research focused on Cheddar cheeses aged for 1, 2, 3, and 5 years, alongside Comté cheeses aged for 6, 9, and 12 months. The adopted approach offered valuable insights into the intricate cheese aging process within the food matrix. The ICA proportions and CCSWA scores highlighted the significant impact of biochemical transformations during maturation on the aging process. The extracted independent components (ICs) revealed variations in the vibration modes of amides, lipids, amino acids, and organic acids, facilitating the distinction between different cheese age categories. Additionally, CCSWA outcomes identified age-related differences through shifts in tryptophan fluorescence characteristics as the cheeses aged. These results were consistent with the observed alterations in the microstructure of cheese samples over time, corroborated by Scanning Electron Microscopy (SEM) imagery. The introduced multimodal methodology serves as a significant asset for determining the ripening stage of various types of cheese, offering a detailed perspective of cheese maturation beneficial to the dairy industry and researchers.

Monitoring of cellulose-rich biowaste co-digestion with 3D fluorescence spectroscopy and mass spectrometry-based metabolomics

Anaerobic digestion (AD) is a promising waste management strategy that reduces landfilling while generating biogas. Anaerobic co-digestion involves mixing two or more substrates to enhance the nutrient balance required for microorganism growth and thus improve the degradation. Monitoring AD is crucial for comprehending the biological process, optimizing process stability, and achieving efficient biogas production. In this work, we have used three dimensional excitation emission fluorescence spectroscopy and mass spectrometry metabolomics, two complementary techniques, to monitor the anaerobic co-digestion (AcoD) of cellulose, ash wood or oak wood with food waste. The two approaches were compared together and to the biogas production records. Results of this experiment demonstrated the complementarity of both analytical techniques with the measurement of the biogas production since 3D fluorescence spectroscopy and MS metabolomics revealed the earlier molecular changes occurring in the bioreactors, mainly associated with the hydrolysis step, whereas the biogas production data reflected the biological activity in the last step of the digestion. Moreover, in all cases, the three data sets effectively delineated the differences among the substrates. While the two wood substrates were poorly degradable as they were richer in aromatic compounds, cellulose was highly degradable and was characterized by the production of several glycolipids. Then, the three tested AcoDs resulted in a similar 3D EEM fluorescence and metabolomics profiles, close to the one observed for the AD of food waste alone, indicating that the incorporation of the food waste drove the molecular degradation events in the AcoDs. Substrate-specific differences were appreciated from the biogas production data. The overall results of this research are expected to provide insight into the design of guidelines for monitoring AcoD.

CW_ICA: an efficient dimensionality determination method for independent component analysis

Independent component analysis (ICA) is a widely used blind source separation method for signal pre-processing. The determination of the number of independent components (ICs) is crucial for achieving optimal performance, as an incorrect choice can result in either under-decomposition or over-decomposition. In this study, we propose a robust method to automatically determine the optimal number of ICs, named the column-wise independent component analysis (CW_ICA). CW_ICA divides the mixed signals into two blocks and applies ICA separately to each block. A quantitative measure, derived from the rank-based correlation matrix computed from the ICs of the two blocks, is utilized to determine the optimal number of ICs. The proposed method is validated and compared with the existing determination methods using simulation and scalp EEG data. The results demonstrate that CW_ICA is a reliable and robust approach for determining the optimal number of ICs. It offers computational efficiency and can be seamlessly integrated with different ICA methods.

Non-targeted detection of grape molasses adulteration with sugar and apple molasses by mid-infrared spectroscopy coupled to independent components analysis

In the light of the current food security crisis, food adulteration has resurfaced on the international scene, inflicting potential safety issues and leading more and more consumers into deception. This situation led food control actors to remobilise their potential to face this problem, particularly in terms of analytical chemistry competencies. Similar to honey, grape molasses may be considered very likely to be adulterated leading to quality and authenticity issues, especially in the Eastern Mediterranean, where it is widely consumed as a traditional sweetener. This work reports the use of attenuated total reflectance-mid-infrared spectroscopy (ATR-MIR) coupled to chemometrics, as an alternative to complex, expensive and time-consuming analytical techniques, in the aim of detecting fraudulent glucose, fructose, sucrose and apple molasses additions to pure grape molasses. After collecting a widespread unadulterated grape molasses database, spiked samples with increasing concentrations (w/w) of the selected adulterants were prepared. In order to establish a qualitative model, whose potential is to detect adulteration and discriminate between the different adulterants, samples underwent ATR-MIR analyses without any prior preparation, and the collected spectral data were subjected to independent components analysis (ICA), where Random_ICA was used to retrieve the optimal number of independent components (ICs). Thereupon, the extraction of seven ICs allowed the establishment of a qualitative model with a clear discrimination between molasses adulterated with fructose, sucrose and glucose syrup, relying on MIR specific signals and incorporated ratios of the different adulterants. However, it failed in detecting apple molasses adulteration, calling for the development of a different analytical approach. The developed model underwent a verification step using a control set recorded on a different spectrometer, proving its potential to provide reproducible discrimination and classification rates.

Novel feature extraction method for signal analysis based on independent component analysis and wavelet transform

Feature extraction is an important part of data processing that provides a basis for more complicated tasks such as classification or clustering. Recently many approaches for signal feature extraction were created. However, plenty of proposed methods are based on convolutional neural networks. This class of models requires a high amount of computational power to train and deploy and large dataset. Our work introduces a novel feature extraction method that uses wavelet transform to provide additional information in the Independent Component Analysis mixing matrix. The goal of our work is to combine good performance with a low inference cost. We used the task of Electrocardiography (ECG) heartbeat classification to evaluate the usefulness of the proposed approach. Experiments were carried out with an MIT-BIH database with four target classes (Normal, Vestibular ectopic beats, Ventricular ectopic beats, and Fusion strikes). Several base wavelet functions with different classifiers were used in experiments. Best was selected with 5-fold cross-validation and Wilcoxon test with significance level 0.05. With the proposed method for feature extraction and multi-layer perceptron classifier, we obtained 95.81% BAC-score. Compared to other literature methods, our approach was better than most feature extraction methods except for convolutional neural networks. Further analysis indicates that our method performance is close to convolutional neural networks for classes with a limited number of learning examples. We also analyze the number of required operations at test time and argue that our method enables easy deployment in environments with limited computing power.

Raman mapping coupled to self-modelling MCR-ALS analysis to estimate active cosmetic ingredient penetration profile in skin

Confocal Raman mapping (CRM) is a powerful, label free, non-destructive tool, enabling molecular characterization of human skin with applications in the dermo-cosmetic field. Coupling CRM to multivariate analysis can be used to monitor the penetration and permeation of active cosmetic ingredients (ACI) after topical application. It is presently illustrated how multivariate curve resolution alternating least squares (MCR-ALS) can be applied to detect and semi-quantitatively describe the diffusion profile of Delipidol, a commercially available slimming ACI, from Raman spectral maps. Although the analysis outcome can be critically dependent on the a priori selection of the number of regression components, it is demonstrated that profiling of the kinetics of diffusion into the skin can be established with or without additionnal spectral equality constraints in the multivariate analysis, with similar results. Ultimately, MCR-ALS, applied without spectral equality contraints, specifically identifies the ACI as one of main spectral components enabling to investigate its distribution and penetration into the stratum corneum and underlying epidermis layers.

Independent components analysis (ICA) at the "cocktail-party" in analytical chemistry

Independent components analysis (ICA) is a probabilistic method, whose goal is to extract underlying component signals, that are maximally independent and non-Gaussian, from mixed observed signals. Since the data acquired in many applications in analytical chemistry are mixtures of component signals, such a method is of great interest. In this article recent ICA applications for quantitative and qualitative analysis in analytical chemistry are reviewed. The following experimental techniques are covered: fluorescence, UV-VIS, NMR, vibrational spectroscopies as well as chromatographic profiles. Furthermore, we reviewed ICA as a preprocessing tool as well as existing hybrid ICA-based multivariate approaches. Finally, further research directions are proposed. Our review shows that ICA is starting to play an important role in analytical chemistry, and this will definitely increase in the future.