To address the dynamic and uncertain challenges posed by climate variability, soil heterogeneity, water distribution, and other key factors in crop field production, intelligent decision support systems (IDSS) that integrate domain knowledge and multi-source data for irrigation, fertilization, pest and disease control, and field dynamic management, are of great importance in meeting modern agriculture’s demands for high precision, efficiency, and sustainability. By encompassing the development stages, typical practices, and technological pathways in China and developed countries, this paper summarizes the representative progress in Internet of Things (IoT), multimodal fusion, knowledge representation, reinforcement learning, reasoning, and practical applications in IDSS. Prominent research challenges include the lack of real-time or near-real-time sensor data, static domain knowledge, poor multimodal decision-making capability, weak cross-field generalization, and various implementation barriers, such as a vague definition of data governance, high costs of service infrastructure, and low user acceptance intention. To overcome these challenges, future research should prioritize the development of scalable, dynamic, robust, interpretable, and trustworthy multimodal IDSS, promote the formulation of standards, and establish an open platform for seamless model deployment, thereby facilitating the transformation from experience-driven to intelligence-driven agricultural production paradigms.

This paper introduces a $\mathrm{\Delta }-\mathrm{\Sigma }$ fractional output divider (FOD) designed for audio system-on-chip (SoC) applications with low design and implementation cost. In contrast to conventional FOD design methodologies that utilize a multi-modulus divider (MMD) or a multi-phase multiplexer (MPM) based divider incorporating complex jitter filters, the proposed FOD adopts a feed-forward architecture employing simple circuit building blocks. It leverages a $\mathrm{\Delta }-\mathrm{\Sigma }$ digital-to-frequency converter (DFC) to generate fractionally synthesized output frequencies, eliminating the synchronous constraint associated with MMD and MPM methods. The DFC employs a fully-synthesizable $\mathrm{\Delta }-\mathrm{\Sigma }$ modulator and resistor-2 resistor (R-2R) digital-to-analog converter to generate 4-level waveform patterns containing the desired output frequency information. These patterns are then processed through an integrator and a zero-crossing detector to reconstruct the fractionally divided output clock signal. Furthermore, to minimize jitter, a simple edge combiner-based jitter filter is cascaded with the DFC output. Implemented in 180 nm digital complementary metal-oxide-semiconductor process and operating at 1.2 V supply voltage, the proposed FOD offers an output frequency range of 500 kHz to 45 MHz, with $N_{\mathrm{m}\mathrm{i}\mathrm{n}}=F_{\mathrm{I}\mathrm{N}}/F_{\mathrm{O}\mathrm{U}\mathrm{T}}=4$. Specifically, It divides a 26 MHz input to generate a 6.144 MHz (128fs = 128 × 44.1 kHz) output, exhibiting a root-mean-square jitter of 3.68 ps, while consuming 0.22 mW of power.

With recent advances in oncology research, effectively utilizing patient genomic data to predict cancer status has become a significant challenge. Although previous deep learning methods based on biological knowledge have made progress, they still face limitations, such as the restricted scope and imprecision of the biological knowledge covered by the biological functional datasets used, as well as difficulties in adapting to data variations. To address these challenges, this paper proposes a novel deep learning neural network model based on a biological knowledge graph (namely BKGNet) and an adjustable connection mechanism—biological knowledge graph-enhanced cancer state prediction network with adjustable connections. Specifically, we construct a predictive neural network that leverages the richer and more precise structured biological information from the knowledge graph, providing the model with more comprehensive and accurate biological background support, thereby enhancing its ability to model complex biological relationships. We also introduce an adjustable connection mechanism that, while ensuring the rationality of biological relationships, transforms fixed biological connections into learnable connection strengths. This allows the model to flexibly adjust the interactions between biological entities. Experimental results demonstrate that BKGNet outperforms traditional machine learning and deep learning baseline models in terms of prediction accuracy, highlighting the advantages of its network architecture. Further ablation experiments validate the effectiveness of both the knowledge graph and the adjustable connection mechanism.