Qualitative classification of waste garments for textile recycling based on machine vision and attention mechanisms.

The increasing volume of garment waste underscores the need for advanced sorting and recycling strategies. As a critical procedure in the secondary usage of waste clothes, qualitative classification of garments categorizes post-consumer clothes based on types and styles. However, this process currently relies on manual labor, which is inefficient, labor-intensive, and poses risks to workers. Despite efforts to implement automatic clothes classification systems, challenges persist due to visual complexities such as similar colors, deformations, and occlusions. In response to these challenges, this study introduces an enhanced intelligent machine vision system with attention mechanisms designed to automate the laborious and skill-demanding task of garment classification. Initially, a waste garment dataset comprising approximately 27,000 garments was curated using a self-developed automatic classification platform. Subsequently, the proposed attention method parameters were selected, and a series of benchmarks were conducted against state-of-the-art methods. Finally, the proposed system underwent a two-week online deployment to evaluate its running stability and sensitivity to similar colors, deformation, and occlusion in industrial production settings. The benchmarks indicate that the proposed method significantly improves classification accuracy across various models. The visualization interpretation of Grad-CAM reveals that the proposed method effectively handles complex environments by directing its focus toward garment-related pixels. Notably, the proposed system elevates classification accuracy from 68.28 % to human-level performance (>90 %) while ensuring greater running stability. This advancement holds promise for automating the classification process and potentially alleviating workers from labor-intensive and hazardous tasks associated with clothes recycling.

Enrichment of Residual Carbon in Coal Gasification Fine Slag via Wet Sieving Separation with Ultrasonic Pretreatment.

To overcome the environmental and economic challenges posed by the increasing amounts of the coal gasification slag, here, a simple and efficient method for enriching the residual carbon from the coal gasification fine slag was proposed. The residual carbon enrichment pattern in the particle size distribution of coal gasification fine slags after the ultrasonic pretreatment was mainly enriched toward the 500-250 µm and 250-125 µm particle size classes by analyzing the changes in the particle size distribution and apparent morphology. The pulp pretreatment at the ultrasonic output power of 270 W for 4 min was determined as the optimal experimental condition with respect to the yield, ash content, and ash rejection of the concentrates. Compared to the conventional wet sieving separation, the yield and ash content of the final concentrates were reduced by 7.99 and 14.96%, respectively. Moreover, the ash rejection of the final concentrates was as high as 88.51%, indicating an increment of 11.63% than the conventional wet sieving separation. Furthermore, thermogravimetric analysis confirmed that the final concentrates exhibited the lowest reactivity; however, these demonstrated had the highest carbon content (nearly 70%) with 27.27% ash content. The combustion characteristics analysis showed that the wet screening concentrate after ultrasonic pretreatment had the highest composite combustion characteristic index (S) of 3.17 × 10-8, as compared to the raw and conventional sieving concentrates.

Effect of Hydrothermal Dehydration on the Slurry Ability of Lignite.

The high moisture content limits the large-scale utilization of lignite. Hydrothermal dehydration (HTD) has been confirmed as an effective method to improve the quality of lignite for further utilization. In this study, the effects of the changes in the lignite interface properties caused by the HTD modified final temperature on the slurry ability were investigated in the range of 160-200 °C. The results indicated that with the gradual rise of the HTD modified final temperature, the content of the carboxyl groups and phenolic hydroxyl groups on the surface of lignite decreased by 21.95 and 36.34%, respectively. In the meantime, the atomic ratio of oxygen/carbon, the content of equilibrium moisture, and the thickness of the hydrated film were reduced from 0.293, 14.63%, and 34.26 nm to 0.252, 9.43%, and 13.33 nm, respectively. Therefore, these changes of interfacial properties improved the slurry ability of lignite, with higher fixed-viscosity solid concentration, lower yield stress, increased pseudo-plasticity, and gradually decreased static stability of the prepared lignite coal water slurry. hydrothermal dehydration; slurry ability; oxygen-containing functional groups; hydrated film.

Portable and multiplexed lateral flow immunoassay reader based on SERS for highly sensitive point-of-care testing.

A portable surface-enhanced Raman scattering (SERS)-based lateral flow immunoassay (LFIA) reader with multiplexed detection was developed using an integrated LFIA reaction column. The proposed LFIA reader was designed to simultaneously detect multiple samples or samples with multiple biomarkers. With the integrated LFIA reaction column, we achieved the specific detection of alpha-fetoprotein (AFP), carcinoembryonic antigen (CEA), and prostate-specific antigen (PSA) with a detection limit of 0.01 ng/mL, which was three orders of magnitude lower than that of the visual signal. We also investigated the uniformity of channels based on an eight-channel integrated LFIA reaction column. The relative standard deviation values of the SERS intensity of the eight-channel for measuring the AFP, CEA, and PSA antigens at 1323 cm-1 were 13%, 4.8%, and 5%, respectively. We detected 45 clinical serum samples of the three antigens using the proposed portable SERS-based LFIA reader to further confirm its applicability to clinical samples. The SERS signals of the positive sera were higher than those of the negative sera and their thrice standard deviation. This result indicated the practicality of the developed integrated reaction column and the proposed portable and multiplexed Raman reader. This work provides a new high-sensitivity, multiplexed, and automated SERS-based LFIA detector for use in the point-of-care setting.