Exploratory analysis of hyperspectral FTIR data obtained from environmental microplastics samples

Wander, Lukas; Vianello, Alvise; Vollertsen, Jes; Westad, Frank; Braun, Ulrike; Paul, Andrea

doi:10.1039/c9ay02483b

Cited by 51 publications

(37 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…UMAP optimization is weighted between conserving the relative positions of points through the established connections and separating different classes via the points’ labels. The graph resulting from UMAP connections between training points for participant two after applying FDA and PCA is depicted in Figure 2 a, whereas the same points distribution with the same connections after applying UMAP is shown in Figure 2 b. UMAP [ 31 , 32 ] algorithm has many hyperparameters to tune its manifold. One manifold can preserve the original structure of the data, whereas another separates the classes non-linearly.…”

Section: Methodsmentioning

confidence: 99%

“…No dimensions were removed as it was found that UMAP’s chosen manifold, given a non-correlated set of features, separates the classes more consistently throughout time. It is notable to mention that PCA has been coupled with UMAP [ 31 , 32 ] in the literature for different purposes, such as data analysis and visualization, than that of the proposed pipeline.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Machine Learning Processing Pipeline for Reliable Hand Gesture Classification of FMG Signals with Stochastic Variance

Asfour

Menon

Jiang

2021

Sensors

View full text Add to dashboard Cite

ForceMyography (FMG) is an emerging competitor to surface ElectroMyography (sEMG) for hand gesture recognition. Most of the state-of-the-art research in this area explores different machine learning algorithms or feature engineering to improve hand gesture recognition performance. This paper proposes a novel signal processing pipeline employing a manifold learning method to produce a robust signal representation to boost hand gesture classifiers’ performance. We tested this approach on an FMG dataset collected from nine participants in 3 different data collection sessions with short delays between each. For each participant’s data, the proposed pipeline was applied, and then different classification algorithms were used to evaluate the effect of the pipeline compared to raw FMG signals in hand gesture classification. The results show that incorporating the proposed pipeline reduced variance within the same gesture data and notably maximized variance between different gestures, allowing improved robustness of hand gestures classification performance and consistency across time. On top of that, the pipeline improved the classification accuracy consistently regardless of different classifiers, gaining an average of 5% accuracy improvement.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

A Machine Learning Processing Pipeline for Reliable Hand Gesture Classification of FMG Signals with Stochastic Variance

Asfour

Menon

Jiang

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Whilst single spectra, despite being time-consuming [ 53 ], can be manually searched against spectral libraries, classifying FTIR images comprising millions of spectra is challenging. Therefore, (semi)automatic data analysis methods and software have been developed for quantifying MPs from imaging-FTIR data [ 54 , 55 , 56 , 57 ]. The Match rate of reference and sample spectra is usually calculated as Pearson’s correlation coefficient, but also other algorithms such as hierarchical cluster analysis [ 51 ] and curve-fitting Python code [ 58 , 59 ] have been developed for MP research, significantly improving the classification.…”

Section: Spectroscopic Identification Of Microplasticsmentioning

confidence: 99%

Towards the Development of Portable and In Situ Optical Devices for Detection of Micro-and Nanoplastics in Water: A Review on the Current Status

et al. 2021

View full text Add to dashboard Cite

The prevalent nature of micro and nanoplastics (MP/NPs) on environmental pollution and health-related issues has led to the development of various methods, usually based on Fourier-transform infrared (FTIR) and Raman spectroscopies, for their detection. Unfortunately, most of the developed techniques are laboratory-based with little focus on in situ detection of MPs. In this review, we aim to give an up-to-date report on the different optical measurement methods that have been exploited in the screening of MPs isolated from their natural environments, such as water. The progress and the potential of portable optical sensors for field studies of MPs are described, including remote sensing methods. We also propose other optical methods to be considered for the development of potential in situ integrated optical devices for continuous detection of MPs and NPs. Integrated optical solutions are especially necessary for the development of robust portable and in situ optical sensors for the quantitative detection and classification of water-based MPs.

show abstract

“…Library search presents the advantage that it can be adapted quickly through the implementation of new or extended reference libraries, but it can be computationally intensive (Primpke et al, 2018). Recently, researchers optimized the method performance by clustering the spectra before the search, revisiting the end-members idea (Wander et al, 2020). The method, however, has yet to be implemented.…”

Section: Motivation and Significancementioning

confidence: 99%

“…Reference libraries that compile spectral signals for different polymers are available for microplastic analysis (Primpke et al, 2018). Bulk search algorithms, and other computational methods, use these libraries to automatize the process of identifying plastic polymers (Primpke et al, 2019a;Wander et al, 2020). The soil samples were analyzed in transmission mode with a spectral resolution of 8cm -1 through a spectral range from 3500 to 1300cm -1 and 8 co-added scans.…”

Section: Identification -Ftir Microscopementioning

confidence: 99%

Development and application of tests for microplastic detection in soil

Santander¹,

Alfonso²

View full text Add to dashboard Cite

China 20 Plastic mulch Sludge Flotation (NaCl) Visual sorting & μ-FTIR 78 ±13 63 ±13 PP PE PET * Polyethylene (PE), polystyrene (PS), polypropylene (PP), polyethylene terephthalate (PET), polyamide (PA), polybutylene (PB), ethylene vinyl acetate (EVA), high density polyethylene (HDPE), polyvinyl chloride (PVC), and polyurethane (PUR). ** The 'visual sorting' test requires a stereomicroscope to look for microplastics. 1 Time-of-flight secondary ion mass spectrometry. 2 Ding et al. (2020) did the visual sorting with a metallographic microscope. 3 Transmission electronic microscopy. 4 Pyrolysis coupled to gas chromatography and mass spectrometry.

show abstract

Exploratory analysis of hyperspectral FTIR data obtained from environmental microplastics samples

Abstract: Hyperspectral imaging of environmental samples with infrared microscopes is one of the preferred methods to find and characterize microplastics.

Cited by 51 publications

References 34 publications

A Machine Learning Processing Pipeline for Reliable Hand Gesture Classification of FMG Signals with Stochastic Variance

A Machine Learning Processing Pipeline for Reliable Hand Gesture Classification of FMG Signals with Stochastic Variance

Towards the Development of Portable and In Situ Optical Devices for Detection of Micro-and Nanoplastics in Water: A Review on the Current Status

Development and application of tests for microplastic detection in soil

Contact Info

Product

Resources

About