A5103382253- Food Supply Chain Traceability
- Animal Behavior and Welfare Studies
- Blockchain Technology Applications and Security
- Speech and Audio Processing
- Privacy, Security, and Data Protection
- Privacy-Preserving Technologies in Data
- Advanced Chemical Sensor Technologies
- Infant Health and Development
- Speech Recognition and Synthesis
- Smart Agriculture and AI
Inner Mongolia Agricultural University
2024-2025
Inner Mongolia Academy of Agricultural & Animal Husbandry Sciences
2025
Soochow University
2015
Individual recognition of Holstein cows is the basis for realizing precision dairy farming. Current machine vision individual systems usually rely on fixed vertical illumination and top-view camera perspectives or require complex systems, these requirements limit their promotion in practical applications. To solve this problem, a lightweight cow feature extraction network named CowBackNet designed paper. This not affected by angle lighting changes suitable farm environments. Secondly, fusion...
In precision feeding, non-contact and pressure-free monitoring of sheep feeding behavior is crucial for health optimizing production management. The experimental conditions real-world environments differ when using acoustic sensors to identify behaviors, leading discrepancies consequently posing challenges achieving high-accuracy classification in complex environments. This study enhances the performance by integrating deep spectrogram features characteristics associated with behavior. We...
With rapid advancements in computing, communication, and storage technologies, innovative machine-learning training methods have emerged. One prominent approach is federated learning, which enables collaborative model without sharing original data sets ensures security privacy. However, learning faces challenges, including low-edge node participation, untrustworthy nodes, untraceable data. This research combines theory with blockchain technology, proposing a hybrid blockchain-based algorithm...
Due to differences between normal and whispered speech, traditional feature performed poorly for recognition.In this paper, a novel approach speech representation is proposed based on Gabor filtering tensor factorization.The sparse extracted by processing the data samples in structure.The simulation results indicate that our able improve recognition performance.