Recently, the deep neural network (DNN) has become one of the most advanced and powerful methods used in classification tasks. However, the cost of DNN models is sometimes considerable due to the huge sets of parameters. Therefore, it is necessary to compress these models in order to reduce the parameters in weight matrices and decrease computational consumption, while maintaining the same level of accuracy. In this paper, in order to deal with the compression problem, we first combine the loss function and the compression cost function into a joint function, and optimize it as an optimization framework. Then we combine the CUR decomposition method with this joint optimization framework to obtain the low-rank approximation matrices. Finally, we narrow the gap between the weight matrices and the low-rank approximations to compress the DNN models on the image classification task. In this algorithm, we not only solve the optimal ranks by enumeration, but also obtain the compression result with low-rank characteristics iteratively. Experiments were carried out on three public datasets under classification tasks. Comparisons with baselines and current state-of-the-art results can conclude that our proposed low-rank joint optimization compression algorithm can achieve higher accuracy and compression ratios.

Acoustic detection technology is a new method for early monitoring of wood-boring pests, and the effective denoising methods are the premise of acoustic detection in forests. This paper used sensors to record Semanotus bifasciatus larval feeding sounds and various environmental noises, and two kinds of sounds were mixed to obtain the noisy feeding sounds with controllable noise intensity. Then, the time domain denoising models and frequency domain denoising models were designed, and the denoising effects were compared using the metrics of a signal-to-noise ratio (SNR), a segment signal-noise ratio (SegSNR), and log spectral distance (LSD). In the experiments, the average SNR increment could achieve 17.53 dB and 11.10 dB using the in the test data using the time domain features and frequency domain features, respectively. The average SegSNR increment achieved 18.59 dB and 12.04 dB, respectively, and the average LSD between pure feeding sounds and denoised feeding sounds were 0.85 dB and 0.84 dB, respectively. The experimental results demonstrated that the denoising models based on artificial intelligence were effective methods for S. bifasciatus larval feeding sounds, and the overall denoising effect was more significant, especially at low SNRs. In view of that, the denoising models using time domain features were more suitable for the forest area and quarantine environment with complex noise types and large noise interference.

The larvae of some trunk-boring beetles barely leave traces on the outside of trunks when feeding within, rendering the detection of them rather difficult. One approach to solving this problem involves the use of a probe to pick up boring vibrations inside the trunk and distinguish larvae activity according to the vibrations. Clean boring vibration signals without noise are critical for accurate judgement. Unfortunately, these environments are filled with natural or artificial noise. To address this issue, we constructed a boring vibration enhancement model named VibDenoiser, which makes a significant contribution to this rarely studied domain. This model is built using the technology of deep learning-based speech enhancement. It consists of convolutional encoder and decoder layers with skip connections, and two layers of SRU++ for sequence modeling. The dataset constructed for study is made up of boring vibrations of Agrilus planipennis Fairmaire, 1888 (Coleoptera: Buprestidae) and environmental noise. Our VibDenoiser achieves an improvement of 18.57 in SNR, and it runs in real-time on a laptop CPU. The accuracy of the four classification models increased by a large margin using vibration clips enhanced by our model. The results demonstrate the great enhancement performance of our model, and the contribution of our work to better boring vibration detection.

Wood-boring beetles are among the most destructive forest pests. The larvae of some species live in the trunks and are covered by bark, rendering them difficult to detect. Early detection of these larvae is critical to their effective management. A promising surveillance method is inspecting the vibrations induced by larval activity in the trunk to identify whether it is infected. As convenient as it seems, it has a significant drawback. The identification process is easily disrupted by environmental noise and results in low accuracy. Previous studies have proven the feasibility and necessity of adding an enhancement procedure before identification. To this end, we proposed a small yet powerful boring vibration enhancement network based on deep learning. Our approach combines frequency-domain and time-domain enhancement in a stacked network. The dataset employed in our study comprises the boring vibrations of Agrilus planipennis larvae and various environmental noises. After enhancement, the SNR (signal-to-noise ratio) increment of a boring vibration segment reaches 18.73 dB, and our model takes only 0.46 s to enhance a 5 s segment on a laptop CPU. The accuracy of several well-known classification models showed a substantial increase using clips enhanced by our model. All experimental results proved our contribution to the early detection of larvae.