Menu

Menu controller icon

Walton Institute Researcher Proposes Novel Approach for Milk Quality Analysis

Posted: 22-03-2024

Tags:

  • Walton News

Walton Institute at South East Technological University (SETU) PhD Researcher Rahul Umesh Mhapsekar’s research, which focuses on milk quality and is funded by VistaMilk SFI Research Centre, has been published in prestigious journal IEEE Transactions on Emerging Topics in Computational Intelligence. Rahul’s publication, titled “Hybrid Blended Deep Learning Approach for Milk Quality Analysis” is available here

Hybrid Blended Deep Learning (HyBDL)

Traditional Machine Learning (ML) algorithms struggle with the complexity of milk spectral data and pre-processing challenges, while Deep Learning (DL) offers promise but hasn’t been extensively applied to Milk Quality Analysis (MQA). To address this gap, Rahul’s research proposes a novel approach called Hybrid Blended Deep Learning (HyBDL). 

“HyBDL combines various DL architectures to improve accuracy and reduce errors in milk quality classification,” says Rahul. “Compared to traditional DL and Blended DL models, HyBDL demonstrated superior performance, achieving 98.03% accuracy and lower Mean Squared Error (MSE) scores. 

“It also consumes less power and energy while being faster to train than the traditional RNN models, making it suitable for real-world applications. The research also delves into making the DL models reproducible on different devices by validating it on different edge devices. Reproducibility is one of the key aspects of AI which many studies do not address. It is done in this research to validate the results.”

HyBDL Architecture.

According to Rahul, this research has numerous real-world implications:

  • Consumer Confidence and Health: Consumers can feel more confident about the safety and quality of the milk they consume. Knowing that advanced AI technology is employed for rigorous quality monitoring reduces concerns about potential health risks associated with consuming adulterated or low-quality milk products.
  • Trust in Dairy Products: Improved milk quality monitoring can enhance trust in dairy products and the dairy industry as a whole.
  • Environmental Impact: Efficient milk quality monitoring contributes to reducing environmental impacts by minimising waste and optimising production processes. 
  • Technological Advancement: The development of Hybrid Blended Deep Learning (HyBDL) models for milk quality analysis showcases the application of cutting-edge technology in agriculture, highlighting the potential of AI to revolutionize various sectors beyond traditional tech domains.
  • Accessibility and Affordability: The exploration of edge processing for training complex DL models opens up possibilities for implementing real-time milk quality monitoring in various settings, including small-scale dairy farms and processing plants. This could lead to improved accessibility and affordability of high-quality dairy products.
  • Continuous Improvement and Future Prospects: The emphasis on future work, such as expanding the dataset and exploring additional DL models, highlights a commitment to continuous improvement and innovation in milk quality analysis. 

Future Work

Rahul says, “For future work, it will be interesting to see how the model performs when more adulterants are added to the multiclass classification problem. A larger dataset can be useful to further verify our results, and the use of other DL models which are useful for datasets with uncertainties, such as rough autoencoders, and deep temporal dictionary learning would be beneficial for performance comparison with our model. Using model compression techniques to lower the complexity of the model may also reduce energy consumption and will be applied in future work to reduce the memory footprint.”

According to Rahul, this novel Deep Learning model could potentially be also used for other applications.

We also asked Rahul what the potential application of this research could offer industry, now or in the future. He explains:

  • Dairy Processing Plants: Implementing HyBDL models for real-time milk quality monitoring in dairy processing plants can improve efficiency and accuracy in quality control processes. This ensures that only high-quality milk is processed and packaged, enhancing product quality and reducing waste.
  • Quality Assurance in Dairy Farms: Dairy farms can utilize HyBDL models to monitor milk quality at various stages of production, from milking to storage. This allows farmers to identify and address potential quality issues promptly.
  • Food Safety Regulations Compliance: HyBDL models can assist dairy industry stakeholders in complying with food safety regulations and standards. 
  • Precision Livestock Farming: HyBDL models can be integrated into precision livestock farming systems to monitor individual animal health and performance metrics related to milk production. 

This research is funded by VistaMilk SFI Research Centre. For more information on VistaMilk visit www.vistamilk.ie.