Blockchain-assisted shrimp freshness monitoring system using AI and IPFS in cold chain logistics
Soft Computing, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Basım Tarihi: 2026
- Doi Numarası: 10.1007/s00500-026-11476-8
- Dergi Adı: Soft Computing
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Applied Science & Technology Source, Compendex, INSPEC, zbMATH, Academic Search Ultimate (EBSCO), Engineering Source (EBSCO), Technology Collection (ProQuest)
- Anahtar Kelimeler: Blockchain, Cold chain logistics, Machine learning, Shrimp freshness
- Süleyman Demirel Üniversitesi Adresli: Evet
Özet
The increasing demand for seafood, particularly shrimp, necessitates robust cold chain logistics to maintain product freshness, ensure food safety, and minimize economic losses. This study proposes an integrated monitoring system that combines artificial intelligence, decentralized storage (IPFS), and private blockchain infrastructure (Hyperledger Fabric) to track and document the freshness of shrimp during cold chain transport. The proposed architecture captures image data and geolocation from vehicle-mounted edge devices, classifies shrimp freshness via the novel deep learning model PentaTriNet, and stores the results in a tamper-evident blockchain system with associated metadata. PentaTriNet, a multi-scale convolutional neural network with three parallel branches utilizing different kernel sizes, demonstrates superior performance in freshness classification tasks, achieving an F1-score of 99.23% for the “fresh” class and an overall validation accuracy of 95.50%. Comparative evaluations show that PentaTriNet outperforms popular models such as EfficientNetV2B0, Xception, and DenseNet121 in terms of both class-wise precision and generalization capability. Furthermore, the system ensures traceability and accountability by storing image hashes on IPFS and logging associated metadata to a permissioned blockchain network. In case of spoilage, automated notifications are triggered, facilitating timely intervention and reducing liability. With its modular architecture and real-time alert capabilities, the system offers a scalable solution that bridges technological innovation and industrial application in seafood logistics.