LAUSR

BACKGROUND The acoustic detection model of activity signals based on deep learning could detect wood-boring pests accurately and reliably. However, the black-box characteristics of the deep learning model limited the credibility of the results and hindered its application. Aiming at the reliability and interpretability of the model, this paper designed an active interpretable model called DalPNet (Dynamic Acoustic Larvae Prototype Network), which used the prototype to assist model decisions and achieve more flexible model explanation through dynamic feature patch computation. RESULTS In the experiments, the average recognition accuracy of the DalPNet on simple test set and anti-noise test set of Semanotus bifasciatus larval activity signals reached 99.3% and 98.5%, respectively. The quantitative evaluation of interpretability was measured by the RAUC (Relative Area Under the Curve) and the CS (Cumulative Slop) of the accuracy change curve in this paper. In the experiments, the RAUC and the CS of DalPNet were 0.2923 and -1.1891, respectively. And according to the visualization results, the explanation results of DalPNet were more accurate in locating the bite pulses of the larvae and could better focus on multiple bite pulses in one signal, which showed better performance compared to the baseline model. CONCLUSION The experimental results demonstrated that the proposed DalPNet had better explanation while ensuring recognition accuracy. In view of that, it could improve the trust of forestry custodians in the activity signals detection model and was helpful to the practical application of the model in the forestry field. This article is protected by copyright. All rights reserved.