The egg production of laying hens is crucial to breeding enterprises in the laying hen breeding industry. However, there is currently no systematic or accurate method to identify low-egg-production-laying hens in commercial farms, and the majority of these hens are identified by breeders based on their experience. In order to address this issue, we propose a method that is widely applicable and highly precise. First, breeders themselves separate low-egg-production-laying hens and normal-laying hens. Then, under a halogen lamp, hyperspectral images of the two different types of hens are captured via hyperspectral imaging equipment. The vertex component analysis (VCA) algorithm is used to extract the cockscomb end member spectrum to obtain the cockscomb spectral feature curves of low-egg-production-laying hens and normal ones. Next, fast continuous wavelet transform (FCWT) is employed to analyze the data of the feature curves in order to obtain the two-dimensional spectral feature image dataset. Finally, referring to the two-dimensional spectral image dataset of the low-egg-production-laying hens and normal ones, we developed a deep learning model based on a convolutional neural network (CNN). When we tested the model’s accuracy by using the prepared dataset, we found that it was 0.975 percent accurate. This outcome demonstrates our identification method, which combines hyperspectral imaging technology, an FCWT data analysis method, and a CNN deep learning model, and is highly effective and precise in laying-hen breeding plants. Furthermore, the attempt to use FCWT for the analysis and processing of hyperspectral data will have a significant impact on the research and application of hyperspectral technology in other fields due to its high efficiency and resolution characteristics for data signal analysis and processing.

Spiking neural networks (SNNs) are considered a crucial research direction to address the “storage wall” and “power wall” challenges faced by traditional artificial intelligence computing. However, developing SNN chips based on CMOS (complementary metal oxide semiconductor) circuits remains a challenge. Although memristor process technology is the best alternative to synapses, it is still undergoing refinement. In this study, a novel approach is proposed that employs tools to automatically generate HDL (hardware description language) code for constructing neuron and memristor circuits after using Python to describe the neuron and memristor models. Based on this approach, HR (Hindmash–Rose), LIF (leaky integrate-and-fire), and IZ (Izhikevich) neuron circuits, as well as HP, EG (enhanced generalized), and TB (the behavioral threshold bipolar) memristor circuits are designed to construct the most basic connection of a SNN: the neuron–memristor–neuron circuit that satisfies the STDP (spike-timing-dependent-plasticity) learning rule. Through simulation experiments and FPGA (field programmable gate array) prototype verification, it is confirmed that the IZ and LIF circuits are suitable as neurons in SNNs, while the $X$ variables of the EG memristor model serve as characteristic synaptic weights. The EG memristor circuits best satisfy the STDP learning rule and are suitable as synapses in SNNs. In comparison to previous works on hardware spiking neurons, the proposed method needed fewer area resources for creating spiking neurons models on FPGA. The proposed SNN basic components design method, and the resulting circuits, are beneficial for architectural exploration and hardware–software co-design of SNN chips.

Accurate and real-time electrical load identification technology has emerged as a critical requirement for ensuring electrical safety and enabling optimized energy management. However, traditional load identification methods have obvious limitations in feature extraction efficiency and computational energy consumption. This paper focuses on intelligent power load perception, proposing a Fast Continuous Wavelet Transform (FCWT) method based on Morlet wavelet. By adopting a frequency-domain zero-removal strategy to eliminate redundant computations, the proposed method reduces the computational complexity of frequency-domain convolution by 43.64% while maintaining high resolution. Furthermore, an FCWT-Spiking Neural Network (FCWT-SNN) framework is proposed by integrating FCWT and neural network techniques. The time-frequency features are fed into a LIF spiking neural network, which leverages spike sparsity to achieve low-power inference. The proposed architecture achieves 99.98% and 98.46% recognition accuracy on the open-source DataSet_SEIN_1 and PLAID datasets, respectively. Compared to conventional CNN architectures, the FCWT-SNN maintains comparable performance while reducing computational load by 97.3% and energy consumption by 98.5%. The methodology not only provides a high precision, low power technical solution for dynamic monitoring of power systems but also introduces novel research perspectives for time-domain signal feature extraction and identification.

To achieve efficient and rapid detection of durian sugar content—with potential extension to maturity assessment of other fruits—this study proposes a novel hybrid framework integrating Fast Continuous Wavelet Transform (FCWT) and Spatiotemporal Backpropagation-based Spiking Neural Network (STBP-SNN). Hyperspectral images of durian pulp were collected within the 900–1700 nm wavelength range, and samples were categorized into three sugar levels (high, medium, low) to establish a targeted evaluation system for sugar content grading.FCWT was employed for multi-scale time-frequency analysis, converting one-dimensional spectral curves into two-dimensional feature matrices to capture fine-grained spectral variations that are critical for distinguishing sugar levels. These feature matrices were then input to the STBP-SNN, which leverages the unique dynamics of spiking neurons to effectively extract spatiotemporal features from hyperspectral data and perform accurate classification. The experimental results indicated that the proposed framework achieved an average test accuracy of around 96%, highlighting its robustness in discriminating durian sugar content. By integrating advanced spectral feature extraction (FCWT) with intelligent spatiotemporal classification (STBP-SNN), the framework provides a scalable and reliable solution for fruit quality assessment, especially for precision grading of internal quality indicators like sugar content.