Food Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 143831 - 143831
Published: March 1, 2025
Language: Английский
Journal of Hazardous Materials, Journal Year: 2024, Volume and Issue: 474, P. 134865 - 134865
Published: June 12, 2024
Language: Английский
Citations
18
Artificial Intelligence Review, Journal Year: 2025, Volume and Issue: 58(4)
Published: Jan. 25, 2025
Language: Английский
Citations
5
Food Chemistry, Journal Year: 2024, Volume and Issue: 462, P. 141033 - 141033
Published: Aug. 28, 2024
Language: Английский
Citations
11
Agronomy, Journal Year: 2025, Volume and Issue: 15(2), P. 489 - 489
Published: Feb. 18, 2025
The presence of non-tobacco-related materials can significantly compromise the quality tobacco. To accurately detect materials, this study introduces a lightweight and real-time detection model derived from YOLOv11 framework, named LRNTRM-YOLO. Initially, due to sub-optimal accuracy in detecting diminutive was augmented by incorporating an additional layer dedicated enhancing small targets, thereby improving overall accuracy. Furthermore, attention mechanism incorporated into backbone network focus on features efficacy model. Simultaneously, for introduction SIoU loss function, angular vector between bounding box regressions utilized define thus training efficiency Following these enhancements, channel pruning technique employed streamline network, which not only reduced parameter count but also expedited inference process, yielding more compact material detection. experimental results NTRM dataset indicate that LRNTRM-YOLO achieved mean average precision (mAP) 92.9%, surpassing baseline margin 4.8%. Additionally, there 68.3% reduction parameters 15.9% decrease floating-point operations compared Comparative analysis with prominent models confirmed superiority proposed terms its architecture, high accuracy, capabilities, offering innovative practical solution future.
Language: Английский
Citations
1
Applied Sciences, Journal Year: 2024, Volume and Issue: 14(21), P. 9821 - 9821
Published: Oct. 27, 2024
Hyperspectral imaging (HSI) is one of the non-destructive quality assessment methods providing both spatial and spectral information. HSI in food safety can detect presence contaminants, adulterants, attributes, such as moisture, ripeness, microbial spoilage, a manner by analyzing signatures components wide range wavelengths with speed accuracy. However, data be quite complicated time consuming, addition to needing some special expertise. Artificial intelligence (AI) has shown immense promise for because it so powerful at coping irrelevant information, extracting key features, building calibration models. This review various machine learning (ML) approaches applied control foods. It covers basic concepts HSI, advanced preprocessing methods, strategies wavelength selection methods. The application AI increases which inspected. happens through automation contaminant detection, classification, prediction attributes. So, enable decisions real-time reducing human error inspection. paper outlines their benefits, challenges, potential improvements while again assessing validity practical usability technologies developing reliable models monitoring. concludes that integrated state-of-the-art techniques good significantly improve safety, ML algorithms have strengths, contexts they are best applied.
Language: Английский
Citations
8
Food Control, Journal Year: 2024, Volume and Issue: 167, P. 110810 - 110810
Published: Aug. 13, 2024
Language: Английский
Citations
7
Food Chemistry, Journal Year: 2024, Volume and Issue: 462, P. 140911 - 140911
Published: Aug. 17, 2024
Language: Английский
Citations
7
Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 226, P. 109382 - 109382
Published: Aug. 27, 2024
Language: Английский
Citations
6
Biocatalysis and Agricultural Biotechnology, Journal Year: 2024, Volume and Issue: 59, P. 103260 - 103260
Published: May 29, 2024
Language: Английский
Citations
5
Comprehensive Reviews in Food Science and Food Safety, Journal Year: 2024, Volume and Issue: 23(5)
Published: Aug. 13, 2024
Abstract Food safety and authenticity analysis play a pivotal role in guaranteeing food quality, safeguarding public health, upholding consumer trust. In recent years, significant social progress has presented fresh challenges the realm of analysis, underscoring imperative requirement to devise innovative expedient approaches for conducting on‐site assessments. Consequently, cellulose paper‐based devices (PADs) have come into spotlight due their characteristics microchannels inherent capillary action. This review summarizes advances PADs various products, comprising fabrication strategies, detection methods such as mass spectrometry multi‐mode detection, sampling processing considerations, well applications screening factors assessing developed past 3 years. According above studies, face limited sample processing, inadequate multiplexing capabilities, workflow integration, while emerging innovations, use simplified pretreatment techniques, integration advanced nanomaterials, instruments portable spectrometer innovation multimodal methods, offer potential solutions are highlighted promising directions. underscores facilitating decentralized, cost‐effective, testing methodologies maintain standards. With progression interdisciplinary research, expected become essential platforms authentication thereby significantly enhancing global consumers.
Language: Английский
Citations
5