Expert advice on crop management is often written informally, and in such text a number can easily be assigned the wrong role or attached to the wrong operation, material, or measurement basis. We propose QS-IE, a knowledge extraction method constrained by quantity and operation scope. Its unit of extraction is a complete quantitative fact. Given a shared set of numeric candidates and a single base model, QS-IE selects complete candidates from several prompting strategies, verifies them against the source text, and applies scope constraints, so that every extracted quantity stays linked to its source evidence. We built a corpus of 4006 texts on tomato cultivation. Two researchers with agrono... More >

Full-cycle management of greenhouse tomato requires continuous information on crop state together with estimates of daily water and nutrient use, yet destructive biomass measurements are sparse, and a single fixed model shared across resources is prone to stage-dependent negative transfer. This study proposes Dual-Path Multi-timescale Fusion (DPMF), a development-aware framework for reconstructing crop state from sparse observations and estimating daily resource fluxes. The state path combines a process-based dry-matter prior with a gated recurrent unit trained on three kinds of supervision: point states, biomass increments between adjacent samples, and cumulative harvested-fruit dry matter.... More >

Accurate bus arrival time prediction supports passenger information services and transit dispatching, but irregular sampling and time-varying traffic conditions make the task strongly nonlinear. This paper proposes a Spatial Attention Multi-Scale Traffic-State Gated Long Short-Term Memory (SA-MS-TG-LSTM) network. Seven trajectory features are constructed from Global Positioning System (GPS) records, including acceleration, congestion index, and speed volatility. Scale-preserving Spatial Feature Attention (SFA) first reweights the feature dimensions, and three Traffic-State Gated Long Short-Term Memory (TG-LSTM) branches subsequently encode the latest 5, 10, and 15 time steps. Their outputs a... More >

Unmanned Aerial Vehicles (UAVs) increasingly rely on wireless guidance and control links which are vulnerable to spoofing and false command injection attacks. Conventional protection mechanisms primarily rely on cryptographic authentication, which may not be sufficient under compromised or replay-based attack scenarios. This paper proposes a physics-informed, wind-aware angle-of-arrival (AoA) consistency validation framework for real-time rejection of spoofed guidance signals. The proposed method exploits geometric consistency between the expected line-of-sight (LOS) direction to a legitimate guidance transmitter and the measured signal bearing at the UAV. The expected bearing is computed fr... More >

Intermittent daily rainfall requires temporal pattern extraction and correction of newly observed prediction errors. This paper presents an event-triggered convolutional neural network--long short-term memory model with prediction-error closed-loop feedback (ECF-CNN-LSTM) for seasonal one-day-ahead rainfall forecasting. A 30-day window supplies 31 causal rainfall-history and calendar features. A binary gate controls a zero-initialized, bounded residual and learns from the expected prediction errors of its inactive and active alternatives. A separate chronological controller uses each newly observed error to adjust subsequent forecasts. The single-series Tengzhou, Shandong dataset contains 97... More >

Target value assessment is a critical component of operational decision-making; however, existing methodologies suffer from the rigidity of static models in dynamic battlefield environments and the scarcity of specialized domain-specific data. To address these problems, we propose DECIS, a framework for adaptive decision support based on Retrieval-Augmented Generation (RAG). DECIS operates through a cohesive three-stage architecture centered on two core functions: first, RAG is employed to intelligently match optimal assessment strategies to dynamic contexts, thereby mitigating the challenge of limited military corpora; second, the Large Language Model (LLM) component autonomously generates... More >

Fire and smoke detection in electric vehicle environments is essential for safety monitoring, yet existing methods often perform poorly under low-light conditions because of weak feature representation, flame overexposure, and limited nighttime data. In addition, many detection models cannot effectively balance accuracy and real-time efficiency, which restricts their deployment in practical applications. To address these issues, this study proposes a lightweight dual-branch detection framework for low-light fire and smoke recognition in electric vehicle environments. The proposed method integrates reflectance enhancement, adaptive feature weighting, and multi-scale feature learning within a... More >

This paper proposes an enhanced U-Net-based segmentation framework for road crack detection that effectively addresses issues such as incomplete segmentation, detail loss, environmental complexity, and crack-pixel imbalance. The model integrates multiple functional modules to improve segmentation performance across varying crack types and scales. Specifically, an atrous residual convolution (ARC) module is embedded in the encoder to expand the receptive field and capture large-scale features. A multiple attention fusion module (MAFM), combined with an efficient channel attention mechanism, is introduced at the bridge stage to emphasize crack-relevant features. In the decoder, a defect correc... More >