Heterogeneous fusion of biometric and deep physiological features for accurate porcine cough recognition.

Accurate identification of porcine cough plays a vital role in comprehensive respiratory health monitoring and diagnosis of pigs. It serves as a fundamental prerequisite for stress-free animal health management, reducing pig mortality rates, and improving the economic efficiency of the farming industry. Creating a representative multi-source signal signature for porcine cough is a crucial step toward automating its identification. To this end, a feature fusion method that combines the biological features extracted from the acoustic source segment with the deep physiological features derived from thermal source images is proposed in the paper. First, acoustic features from various domains are extracted from the sound source signals. To determine the most effective combination of sound source features, an SVM-based recursive feature elimination cross-validation algorithm (SVM-RFECV) is employed. Second, a shallow convolutional neural network (named ThermographicNet) is constructed to extract deep physiological features from the thermal source images. Finally, the two heterogeneous features are integrated at an early stage and input into a support vector machine (SVM) for porcine cough recognition. Through rigorous experimentation, the performance of the proposed fusion approach is evaluated, achieving an impressive accuracy of 98.79% in recognizing porcine cough. These results further underscore the effectiveness of combining acoustic source features with heterogeneous deep thermal source features, thereby establishing a robust feature representation for porcine cough recognition.

Ammonia storage and slip under steady and transient state in close-coupled SCR.

The close-coupled selective catalytic reduction (cc-SCR) catalyst is an effective technology to reduce tailpipe NOx emission during cold start. This paper investigated the optimal ammonia storage under steady and transient state in the cc-SCR. The study showed that a trade-off between NOx conversion efficiency and ammonia slip is observed on the pareto solutions under steady state, and the optimal ammonia storage is calculated with ammonia slip less than 10 µL/L based on the China Ⅵ emission legislation. The rapid temperature increase will lead to severe ammonia slip in the transient test cycle. A simplified 0-D calculation method on ammonia slip under transient state is proposed based on kinetic model of ammonia adsorption and desorption. In addition, the effect of ammonia storage, catalyst temperature and temperature increasing rate on ammonia slip are analyzed. The optimal ammonia storage is calculated with maximum ammonia slip less than 100 µL/L according to the oxidation efficiency of ammonia slip catalyst (ASC) downstream cc-SCR. It was found that the optimal ammonia storage under transient state is much lower than that under steady state in cc-SCR at lower temperature, and a phase diagram is established to analyze the influence of temperature and temperature increasing rate on optimal ammonia storage.

Research on Four-Dimensional Innovative Intelligent Education Platform Based on Cloud Edge-End Architecture.

In order to solve the problem of backward talent training mode in agriculture-related colleges and universities, this paper proposed a scheme to build a smart teaching platform by using cloud architecture, combining virtualization and twinning technology. The intelligent teaching platform is developed using the 5G converged network architecture and cloud edge system architecture. The intelligent teaching platform has realized such teaching modes as real scene teaching, combination of virtual and real teaching, immersive teaching, multi-teacher collaborative teaching and live interactive teaching. The smart teaching platform has established a new model of digital education, with the functions of teaching, teaching research, teaching management and teaching evaluation, and provides smart teaching cloud services for teachers and students of agriculture-related colleges and universities as well as external tutors. The research of multi-dimensional evaluation system solves the precise management of teaching process. The teaching effect has been significantly improved, and the management cost has been reduced, which meets the goal of training new agricultural talents in agricultural and forestry colleges.