Classification of field wheat varieties based on a lightweight G-PPW-VGG11 model.

Introduction: In agriculture, especially wheat cultivation, farmers often use multi-variety planting strategies to reduce monoculture-related harvest risks. However, the subtle morphological differences among wheat varieties make accurate discrimination technically challenging. Traditional variety classification methods, reliant on expert knowledge, are inefficient for modern intelligent agricultural management. Numerous existing classification models are computationally complex, memory-intensive, and difficult to deploy on mobile devices effectively. This study introduces G-PPW-VGG11, an innovative lightweight convolutional neural network model, to address these issues. Methods: G-PPW-VGG11 ingeniously combines partial convolution (PConv) and partially mixed depthwise separable convolution (PMConv), reducing computational complexity and feature redundancy. Simultaneously, incorporating ECANet, an efficient channel attention mechanism, enables precise leaf information capture and effective background noise suppression. Additionally, G-PPW-VGG11 replaces traditional VGG11's fully connected layers with two pointwise convolutional layers and a global average pooling layer, significantly reducing memory footprint and enhancing nonlinear expressiveness and training efficiency. Results: Rigorous testing showed G-PPW-VGG11's superior performance, with an impressive 93.52% classification accuracy and only 1.79MB memory usage. Compared to VGG11, G-PPW-VGG11 showed a 5.89% increase in accuracy, 35.44% faster inference, and a 99.64% reduction in memory usage. G-PPW-VGG11 also surpasses traditional lightweight networks in classification accuracy and inference speed. Notably, G-PPW-VGG11 was successfully deployed on Android and its performance evaluated in real-world settings. The results showed an 84.67% classification accuracy with an average time of 291.04ms per image. Discussion: This validates the model's feasibility for practical agricultural wheat variety classification, establishing a foundation for intelligent management. For future research, the trained model and complete dataset are made publicly available.

A structural color hydrogel for diagnosis of halitosis and screening of periodontitis.

Oral pathogens can produce volatile sulfur compounds (VSCs), which is the main reason for halitosis and indicates the risk of periodontitis. High-sensitivity detection of exhaled VSCs is urgently desired for promoting the point-of-care testing (POCT) of halitosis and screening of periodontitis. However, current detection methods often require bulky and costly instruments, as well as professional training, making them impractical for widespread detection. Here, a structural color hydrogel for naked-eye detection of exhaled VSCs is presented. VSCs can reduce disulfide bonds within the network, leading to expansion of the hydrogel and thus change of the structural color. A linear detection range of 0-1 ppm with a detection limit of 61 ppb can be achieved, covering the typical VSC concentration in the breath of patients with periodontitis. Furthermore, visual and in situ monitoring of Porphyromonas gingivalis responsible for periodontitis can be realized. By integrating the hydrogels into a sensor array, the oral health conditions of patients with halitosis can be evaluated and distinguished, offering risk assessment of periodontitis. Combined with a smartphone capable of color analysis, POCT of VSCs can be achieved, providing an approach for the monitoring of halitosis and screening of periodontitis.

Supramolecular Photonic Hydrogel for High-Sensitivity Alkaline Phosphatase Detection via Synergistic Driving Force.

Structurally-colored photonic hydrogels which are fabricated by introducing hydrogels into thin films or photonic crystal structures are promising candidates for biosensing. Generally, the design of photonic hydrogel biosensors is based on the sensor-analyte interactions induced charge variation within the hydrogel matrix, or chemically grafting binding sites onto the polymer chains, to achieve significant volume change and color variation of the photonic hydrogel. However, relatively low anti-interference capability or complicated synthesis hinder the facile and low-cost fabrication of high-performance photonic hydrogel biosensors. Here, a facilely prepared supramolecular photonic hydrogel biosensor is developed for high-sensitivity detection of alkaline phosphatase (ALP), which is an extensively considered clinical biomarker for a variety of diseases. Responding to ALP results in the broken supramolecular crosslinking and thus increased lattice distancing of the photonic hydrogel driven by synergistic repulsive force between nanoparticles embedded in photonic crystal structure and osmotic swelling pressure. The biosensor shows sensitivity of 7.3 nm spectral shift per mU mL-1 ALP, with detection limit of 0.52 mU mL-1 . High-accuracy colorimetric detection can be realized via a smartphone, promoting point-of-care sensing and timely diagnosis of related pathological conditions.