.png){kind=icon}
Return
An efficient optimization-based incremental quantum convolutional network for milk adulteration detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engappai.2026.115054.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Adulteration in milk is a serious global challenge that poses severe health issues to a wide range of people due to its being one of the primary food sources. The adulterations in the milk, such as urea, water, surfactants, and oil, are making the detection more challenging due to their similar properties in the milk. The Sarcophilus leading pursuit optimized quantum convolutional neural network (SLPuIQCN) is proposed in this research to address the limitations and to identify the adulterations. The selection of better frames using the Sarcophilus leading pursuit optimized method (SLPu-AFS) reduces the redundant data and serves as a visual representation of the gradient line features. In addition, the features extracted using the Res Statistical Deep Textural Descriptor (ReSDT) provide a detailed representation of the complex probability distributions, local pixel variations, and textural intensities. Moreover, the Sarcophilus leading pursuit optimization (SLPuO) algorithm is developed for tuning the hyperparameters as well as to assist in the selection of better video frames. The evaluation of the model against the other approaches shows higher outcomes that show accuracy 97.09%, precision 97.47%, F1 score 97.18%, and recall 96.90% in the Omdena database.
Keywords:
milk adulteration
quantum convolutional neural network
Sarcophilus leading pursuit optimization
feature extraction
adulterant detection
Journal
IF:
8
Papers:
5.8K
Citations:
3.5W
Organization
Cited Papers
No cited papers available