API recommendation systems for novice programmers should prioritize usability and inspiration rather than merely pursuing the “best result”. Existing retrieval-based approaches, whether relying on direct similarity matching or using query expansion to generate clarification options, still cannot recover missing task semantics and often introduce additional ambiguity and interaction overhead. Learning-based methods, including neural architectures and recent LLM-driven techniques, require substantial data or strong prompt dependence and provide limited transparency, making it difficult to align model outputs with novice programmers' actual intent. To address these limitations, we propose IOCAPI (Intention-Oriented andContext-AwareAPIRecommendation), a reasoning-driven framework that integrates LLMs, LCMs, and in-context learning. It mainly contains three components: (1) Intent Detector, which refines the query and derives task semantics through model-generated I/O exemplars; (2) Code Generator, which produces representative code snippets under the confirmed I/O constraints; and (3) Task Bridger, which consolidates the results into actionable API recommendations with interpretable code examples. Evaluations on three public datasets show that IOCAPI attains a 35.7% BLEU improvement over APIGen and an 11.1% MRR gain over CLEAR, and achieves higher MAP scores than GPT-4 zero-shot, few-shot, and chain-of-thought baselines by 102%, 11.2%, and 21.8%, respectively. A controlled user study involving seven real programming tasks further provides empirical observations of IOCAPI's behavior in practice. Compared with KAHAID, IOCAPI obtained higher average scores in Correctness (1.67 vs. 1.00), Usability (1.76 vs. 0.40), and Inspiration (1.40 vs. 0.26).

ABSTRACT Accurate identification of rice diseases is a prerequisite for improving rice yield and quality. However, the rice diseases are complex, and the existing identification models have the problem of weak ability to extract rice disease features. To address this issue, this paper proposes a rice disease identification model with enhanced feature extraction capability, named GDS‐YOLO. The proposed GDS‐YOLO model improves the YOLOv8n model by introducing the GsConv module, the Dysample module, the spatial context‐aware module (SCAM) and WIoU v3 loss functions. The GsConv module reduces the model's number of parameters and computational complexity. The Dysample module reduces the loss of the rice diseases feature during the extraction process. The SCAM module allows the model to ignore the influence of complex backgrounds and focus on extracting rice disease features. The WIoU v3 loss function optimises the regression box loss of rice disease features. Compared with the YOLOv8n model, the P and mAP50 of GDS‐YOLO increased by 5.4% and 4.1%, respectively, whereas the number of parameters and GFLOPS decreased by 23% and 10.1%, respectively. The experimental results show that the model proposed in this paper reduces the model complexity to a certain extent and achieves good rice diseases identification results.

The intensification and automation of the pig farming industry have created an urgent need for cost-effective and efficient identification of individual pigs. Pig identification is crucial for disease prevention and control, pork quality traceability, genetic breeding, and insurance services. To address the challenges faced by existing noncontact pig face recognition models in overcoming strong environmental interference in pigsties and the minimal differences among pig faces, this paper proposes a convolutional neural network based on multi-granularity semantic analysis (MGSNet). By integrating pixel-level, component-level, and object-level semantic features, the model significantly improves recognition performance in complex scenarios. Specifically, the model addresses challenges such as environmental interference and high similarity among individual pigs. Experimental results show that the algorithm achieves a high test accuracy of 92.50% on a dataset of 10 pigs collected from actual pig farms, with lightweight network parameters. Through deconvolution and gradient-weighted class activation mapping techniques, the feature extraction process of the model is visually interpretable, providing reliable technical support for farmers. The research findings can be directly applied to precision feeding, disease monitoring, breeding optimization, and other scenarios, promoting the comprehensive adoption of smart agriculture.

This study aims to explore the stabilization problem of state-based fuzzy switched dynamic systems with Lévy noise, non-differentiable delay and actuator saturation through a novel intermittent output feedback control mechanism. Firstly, the delay studied in this study is non-differentiable, eliminating the harsh condition that the delay in the existing conventional system must be differentiable or even require the derivative to be less than 1, and replacing the existing common Brownian motion with Lévy noise that is more realistic to simulate the inevitable stochastic noise in the system, which has more theoretical research significance and exploration value. Subsequently, by means of dynamic output feedback mechanism, a new intermittent output feedback control scheme is designed to replace the conventional intermittent state feedback control scheme, which has important practicability and flexibility in practical control. Especially, a novel stabilization criterion is developed by selecting a novel switching-Lyapunov function in combination with two novel lemma pairs for solving non-differentiable terms and actuator saturation. Furthermore, two additional algorithms are given to maximize the attraction domain of the closed-loop system and to minimize the control gain matrix in order to minimize the control cost. Finally, a numerical example is used to verify the validity of the developed results, and a meaningful additional practical electronic circuit model is provided to prove its practicability and superiority.

This article tackles the sampled-data control issue for a class of time-scale-type systems (TSTSs) subject to denial-of-service (DoS) attacks. A novel sampled-data control protocol, that incorporate the backward-jump-like operator (BJLO), is proposed to ensure compatibility with the discontinuity of time scales. Furthermore, a generalized Halanay-like inequality (GHLI) is proposed to address the effects of time scale discontinuities and DoS attacks on sampling intervals. Compared with the common Halanay inequality (CHI) used in continuous-time sampled-data systems, the GHLI accommodates TSTSs and permits some sampling intervals that exceed the constraints of the CHI. By leveraging the GHLI and the proposed sampled-data control protocol, the exponential stability criterion is derived for TSTSs under DoS attacks. This article culminates with two simulation examples and the micro-grid case study conducted to validate the proposed results.

Abstract RGB‐D salient object detection (SOD) is to detect salient objects from one RGB image and its depth data. Although related networks have achieved appreciable performance, they are not ideal for mobile devices since they are cumbersome and time‐consuming. The existing lightweight networks for RGB‐D SOD use depth information as additional input, and integrate depth information with colour image, which achieve impressive performance. However, the quality of depth information is uneven and the acquisition cost is high. To solve this issue, depth‐aware strategy is first combined to propose a lightweight SOD model, Depth‐Aware Lightweight network (DAL), using only RGB maps as input, which is applied to mobile devices. The DAL's framework is composed of multi‐level feature extraction branch, specially designed channel fusion module (CF) to perceive the depth information, and multi‐modal fusion module (MMF) to fuse the information of multi‐modal feature maps. The proposed DAL is evaluated on five datasets and it is compared with 14 models. Experimental results demonstrate that the proposed DAL outperforms the state‐of‐the‐art lightweight networks. The proposed DAL has only 5.6 M parameters and inference speed of 39 ms. Compared with the best‐performing lightweight method, the proposed DAL has fewer parameters, faster inference speed, and higher accuracy.

Abstract Since the number of features of the dataset is much higher than the number of patterns, the higher the dimension of the data, the greater the impact on the learning algorithm. Dimension disaster has become an important problem. Feature selection can effectively reduce the dimension of the dataset and improve the performance of the algorithm. Thus, in this paper, A feature selection algorithm based on P systems (P-FS) is proposed to exploit the parallel ability of cell-like P systems and the advantage of evolutionary algorithms in search space to select features and remove redundant information in the data. The proposed P-FS algorithm is tested on five UCI datasets and an edible oil dataset from practical applications. At the same time, the P-FS algorithm and genetic algorithm feature selection (GAFS) are compared and tested on six datasets. The experimental results show that the P-FS algorithm has good performance in classification accuracy, stability, and convergence. Thus, the P-FS algorithm is feasible in feature selection.

To protect edge and texture information, when removing salt‐and‐pepper (SP) noise in grayscale images, a support vector machine (SVM) denoising method is employed. First, a mapping relation between the neighborhood signal pixels and the central pixel is designed. The size of the neighborhood is a 5 × 5 region, with a signal pixel in the center. In this region, a 25‐dimensional input sample is constructed using the correlation between the neighborhood pixels and the eight‐direction fractional integral operators. The center signal pixel acts as the corresponding output sample to provide a training sample. Then, the SVM is trained with all training samples, and the SVM denoising model is obtained. Next, the center pixel value is estimated using the SVM denoising model in every 5 × 5 region with a noise pixel in the center. Finally, the noise pixel values are replaced with the estimated values of the SVM. The experiments demonstrate that the best denoising effect is obtained when the fractional integral order is in the range of 1.8 ± 0.1. The proposed method produces a visually pleasing denoised image and obtains superior image quality assessment indicators. Our method has significant advantages compared with state‐of‐the‐art denoisers when a low level of noise is present.