In order to solve the problem of large model computing power consumption, this paper proposes a novel model compression algorithm. Firstly, this paper proposes an interpretable weight allocation method for the loss between a student network (a network model with poor performance), a teacher network (a network model with better performance) and real label. Then, different from the previous simple pruning and fine-tuning, this paper performs knowledge distillation on the pruned model, and quantifies the residual weights of the distilled model. The above operations can further reduce the model size and calculation cost while maintaining the model accuracy. The experimental results show that the weight allocation method proposed in this paper can allocate a relatively appropriate weight to the teacher network and real tags. On the cifar-10 dataset, the pruning method combining knowledge distillation and quantization can reduce the memory size of resnet32 network model from 3726 KB to 1842 KB, and the accuracy can be kept at 93.28%, higher than the original model. Compared with similar pruning algorithms, the model accuracy and operation speed are greatly improved.

The present study proposes a novel deep-learning model for remote sensing image enhancement. It maintains image details while enhancing brightness in the feature extraction module. An improved hierarchical model named Global Spatial Attention Network (GSA-Net), based on U-Net for image enhancement, is proposed to improve the model’s performance. To circumvent the issue of insufficient sample data, gamma correction is applied to create low-light images, which are then used as training examples. A loss function is constructed using the Structural Similarity (SSIM) and Peak Signal-to-Noise Ratio (PSNR) indices. The GSA-Net network and loss function are utilized to restore images obtained via low-light remote sensing. This proposed method was tested on the Northwestern Polytechnical University Very-High-Resolution 10 (NWPU VHR-10) dataset, and its overall superiority was demonstrated in comparison with other state-of-the-art algorithms using various objective assessment indicators, such as PSNR, SSIM, and Learned Perceptual Image Patch Similarity (LPIPS). Furthermore, in high-level visual tasks such as object detection, this novel method provides better remote sensing images with distinct details and higher contrast than the competing methods.

This work implements an intelligent forest monitoring system using the Internet of things (IoT) with the wireless network communication technology of a low-power wide-area network (LPWAN), a long range (LoRa), and a narrow-band Internet of things (NB-IoT). A solar micro-weather station with LoRa-based sensors and communications was built to monitor the forest status and information such as the light intensity, air pressure, ultraviolet intensity, CO₂, etc. Moreover, a multi-hop algorithm for the LoRa-based sensors and communications is proposed to solve the problem of long-distance communication without 3G/4G. For the forest without electricity, we installed solar panels to supply electricity for the sensors and other equipment. In order to avoid the problem of insufficient solar panels due to insufficient sunlight in the forest, we also connected each solar panel to a battery to store electricity. The experimental results show the implementation of the proposed method and its performance.

A compact cat swarm optimization scheme (cCSO) is proposed in this paper, which is designed to solve application domains plagued with limited memory and less-computation power, as a member of cat swarm optimization algorithms (CSO), it composes of two sub-modes, i.e., tracing and seeking modes, so it keeps the same search logic of CSO. On the other hand, cCSO inherits the main feature of compact algorithms, a normal probabilistic model is used to represent the population of solutions instead of processing an actual population, which ensures the cCSO to have the modest memory requirement. The updating vector for the probabilistic model provides a clear moving direction for cats in next step. A cat without historical position and velocity is applied in the algorithm. When the cat is in seeking mode, it employs a differential operator to update the cat’s position, which makes it possible for the cat to have multiple searching directions. Experimental results show that cCSO has pretty performance compared with respect to some population-based testing benchmarks. And it also shows superior performance in convergence rate to some compact optimization algorithms. The case study of gray image segmentation proves that it suits for solving the optimization problem by limited hardware.

Infrared small-target detection remains a critical challenge in military reconnaissance, environmental monitoring, forest-fire prevention, and search-and-rescue operations, owing to the targets’ extremely small size, sparse texture, low signal-to-noise ratio, and complex background interference. Traditional convolutional neural networks (CNNs) struggle to detect such weak, low-contrast objects due to their limited receptive fields and insufficient feature extraction capabilities. To overcome these limitations, we propose a Multi-Scale Edge-Aware Convolution (MEAC) module that enhances feature representation for small infrared targets without increasing parameter count or computational cost. Specifically, MEAC fuses (1) original local features, (2) multi-scale context captured via dilated convolutions, and (3) high-contrast edge cues derived from differential Gaussian filters. After fusing these branches, channel and spatial attention mechanisms are applied to adaptively emphasize critical regions, further improving feature discrimination. The MEAC module is fully compatible with standard convolutional layers and can be seamlessly embedded into various network architectures. Extensive experiments on three public infrared small-target datasets (SIRSTD-UAVB, IRSTDv1, and IRSTD-1K) demonstrate that networks augmented with MEAC significantly outperform baseline models using standard convolutions. When compared to eleven mainstream convolution modules (ACmix, AKConv, DRConv, DSConv, LSKConv, MixConv, PConv, ODConv, GConv, and Involution), our method consistently achieves the highest detection accuracy and robustness. Experiments conducted across multiple versions, including YOLOv10, YOLOv11, and YOLOv12, as well as various network levels, demonstrate that the MEAC module achieves stable improvements in performance metrics while slightly increasing computational and parameter complexity. These results validate the MEAC module’s significant advantages in enhancing the detection of small and weak objects and suppressing interference from complex backgrounds. These results validate MEAC’s effectiveness in enhancing weak small-target detection and suppressing complex background noise, highlighting its strong generalization ability and practical application potential.

Nowadays, there is a tradeoff between the deep-learning module-compression ratio and the module accuracy. In this paper, a strategy for refining the pruning quantification and weights based on neural network filters is proposed. Firstly, filters in the neural network were refined into strip-like filter strips. Then, the evaluation of the filter strips was used to refine the partial importance of the filter, cut off the unimportant filter strips and reorganize the remaining filter strips. Finally, the training of the neural network after recombination was quantified to further compress the computational amount of the neural network. The results show that the method can significantly reduce the computational effort of the neural network and compress the number of parameters in the model. Based on experimental results on ResNet56, this method can reduce the number of parameters to 1/4 and the amount of calculation to 1/5, and the loss of model accuracy is only 0.01. On VGG16, the number of parameters is reduced to 1/14, the amount of calculation is reduced to 1/3, and the accuracy loss is 0.5%.