Marine microplastics (MPs) contamination has become an enormous hazard to aquatic creatures and human life. For MP identification, many Machine learning (ML) based approaches have been proposed using Attenuated Total Reflection Fourier Transform Infrared Spectroscopy (ATR-FTIR). One major challenge for training MP identification models now is the imbalanced and inadequate samples in MP datasets, especially when these conditions are combined with copolymers and mixtures. To improve the ML performance in identifying MPs, data augmentation method is an effective approach. This work utilizes Explainable Artificial Intelligence (XAI) and Gaussian Mixture Models (GMM) to reveal the influence of FTIR spectral regions in identifying each type of MPs. Based on the identified regions, this work proposes a Fingerprint Region based Data Augmentation (FRDA) method to generate new FTIR data to supplement MP datasets. The evaluation results show that FRDA outperforms the existing spectral data augmentation approaches.
1 January 2018 in Journal of the Mechanical Behavior of Biomedical Materials
The burgeoning crisis of plastic waste accumulation necessitates innovative approaches towards sustainable packaging solutions. Polylactic acid (PLA), a leading biopolymer, emerges as a promising candidate in this realm, especially for environmentally friendly packaging. PLA is renowned for its compostable properties, offering a strategic avenue to mitigate plastic waste. However, its dependency on specific industrial composting conditions, characterized by elevated temperatures, humidity, and thermophilic microbes, limits its utility for household composting. This study aims to bridge the research gap in PLA’s recyclability and explore its feasibility in mechanical recycling processes. The research focuses on assessing the mechanical characteristics of PLA and PLA-based composites post-recycling. Specifically, we examined the effects of two extrusion methods—conical and parallel—on PLA and its composites containing 20 wt.% basalt fibers (BF). The recycling process encompassed repeated cycles of hot melt extrusion (HME), followed by mechanical grinding to produce granules. These granules were then subjected to injection moulding (IM) after 1, 3 and 5 recycling cycles. The tensile properties of the resulting IM-produced bars provided insights into the material’s durability and stability. The findings reveal that both PLA and PLA/BF composites retain their mechanical integrity through up to 5 cycles of mechanical recycling. This resilience underscores PLA’s potential for integration into existing recycling streams, addressing the dual challenges of environmental sustainability and waste management. The study contributes to the broader understanding of PLA’s lifecycle and opens new possibilities for its application in eco-friendly packaging, beyond the limits of composting. The implications of these findings extend towards enhancing the circularity of biopolymers and reducing the environmental footprint of plastic packaging.