Zhijie Luo

Digital microfluidic biochips (DMFBs) find extensive applications in biochemical experiments, medical diagnostics, and safety-critical domains, with their reliability dependent on efficient online testing technologies. However, traditional random search algorithms suffer from slow convergence and susceptibility to local optima under complex fluidic constraints. This paper proposes a hybrid optimization method based on priority strategy and an improved sparrow search algorithm for DMFB online test path planning. At the algorithmic level, the improved sparrow search algorithm incorporates three main components: tent chaotic mapping for population initialization, cosine adaptive weights together with Elite Opposition-based Learning (EOBL) to balance global exploration and local exploitation, and a Gaussian perturbation mechanism for fine-grained refinement of promising solutions. Concurrently, this paper proposes an intelligent rescue strategy that integrates global graph-theoretic pathfinding, local greedy heuristics, and space–time constraint verification to establish a closed-loop decision-making system. The experimental results show that the proposed algorithm is efficient. On the standard 7 × 7–15 × 15 DMFB benchmark chips, the shortest offline test path length obtained by the algorithm is equal to the length of the Euler path, indicating that, for these regular layouts, the shortest test path has reached the known optimal value. In both offline and online testing, the shortest paths found by the proposed method are better than or equal to those of existing mainstream algorithms. In particular, for the 15 × 15 chip under online testing, the proposed method reduces the path length from 543 and 471 to 446 compared with the IPSO and IACA algorithms, respectively, and reduces the standard deviation by 53.14% and 39.4% compared with IGWO in offline and online testing.

The growth of aquaculture poses significant challenges for disease management, impacting economic sustainability and global food security. Traditional diagnostics are slow and require expertise, while current deep learning models, including CNNs and Transformers, face a trade-off between capturing global symptom context and maintaining computational efficiency. This paper introduces FishMambaNet, a novel framework that integrates selective state space models (SSMs) with convolutional networks for accurate and efficient fish disease diagnosis. FishMambaNet features two core components: the Fish Disease Detection State Space block (FSBlock), which models long-range symptom dependencies via SSMs while preserving local details with gated convolutions, and the Multi-Scale Convolutional Attention (MSCA) mechanism, which enriches multi-scale feature representation with low computational cost. Experiments demonstrate state-of-the-art performance, with FishMambaNet achieving a mean Average Precision at 50% Intersection over Union (mAP@50) of 86.7% using only 4.3 M parameters and 10.7 GFLOPs, significantly surpassing models like YOLOv8-m and RT-DETR. This work establishes a new paradigm for lightweight, powerful disease detection in aquaculture, offering a practical solution for real-time deployment in resource-constrained environments.

The sustainable cultivation of agarwood, a high-value tree species, is significantly threatened by foliar pests, requiring efficient and accurate monitoring solutions. While deep learning is widely used, mainstream models face inherent limitations: Convolutional Neural Networks have restricted receptive fields and Transformers incur high computational complexity, complicating the balance of accuracy and efficiency for tiny pest detection in complex environments. To address these challenges, a novel Adaptive State-space Convolutional Fusion Network (ASCNet) is proposed. Its core component, the Adaptive State-space Convolutional Fusion Block (ASBlock), integrates the global context modeling of state-space models—which have linear complexity—with the local feature extraction of convolutional networks through a dual-path adaptive fusion mechanism. A Grouped Spatial Shuffle Downsampling (GSD) module replaces standard strided convolutions to preserve fine-grained spatial details during downsampling. For small object detection, a Normalized Wasserstein Distance (NWD)-based loss function mitigates the sensitivity of traditional IoU to minor localization errors. Evaluations on a new agarwood pest dataset show that ASCNet outperforms state-of-the-art detectors (including the YOLO series, RT-DETR, and Gold-YOLO), achieving a maximum mAP@50 of 93.0 ± 0.2% and mAP@50:95 of 71.2 ± 0.3% with high computational efficiency. The results confirm ASCNet as a robust and effective solution for intelligent pest monitoring in high-value crops like agarwood.

Electrowetting display technology is increasingly prevalent in modern microfluidic and electronic paper applications, yet it remains susceptible to micro-scale defects such as screen burn-in, charge trapping, and pixel wall deformation. These defects often exhibit low contrast, irregular morphology, and scale diversity, posing significant challenges for conventional detection methods. To address these issues, we propose ASAF-Net, a novel lightweight network incorporating adaptive attention mechanisms for real-time electrowetting defect detection. Our approach integrates three key innovations: a Multi-scale Partial Convolution Fusion Attention module that enhances feature representation with reduced computational cost through channel-wise partitioning; an Adaptive Scale Attention Fusion Pyramid that introduces a dedicated P2 layer for micron-level defect detection across four hierarchical scales; and a Shape-IoU loss function that improves localization accuracy for irregular small targets. Evaluated on a custom electrowetting defect dataset comprising seven categories, ASAF-Net achieves a state-of-the-art mAP@0.5 of 0.982 with a miss detection rate of only 1.5%, while operating at 112 FPS with just 9.82 M parameters. Comparative experiments demonstrate its superiority over existing models such as YOLOv8 and RT-DETR, particularly in detecting challenging defects like charge trapping. This work provides an efficient and practical solution for high-precision real-time quality inspection in electrowetting display manufacturing.

Recent advancements in computer vision technology have significantly improved pest classification. However, pests of the same species exhibit distinct morphological changes throughout different life periods. Traditional methods apply the same feature extraction techniques to all periods, limiting classification precision. In addition to its inherent visual characteristics, pest images contain implicit growth period information. To address this issue, we propose a Pest Classification Model Integrating Growth Period Prior Knowledge. The model is composed of three sub-modules where: i) A deep learning network first identifies the growth periods of pests, and this prior knowledge is then used to guide the text encoder of the CLIP pre-trained model in generating period-specific textual features. ii) A parallel deep learning network extracts visual features from pest images. iii) An efficient low-rank multimodal fusion module integrates textual and visual features through parameter-optimized tensor decomposition, significantly improving classification accuracy across pest developmental phases. To evaluate its effectiveness, a dataset containing pests at different growth periods was constructed from Sichuan Agricultural University's pest dataset. Experimental results show that GPPK4PCM outperforms well-established deep learning neural networks. Compared to other advanced models, the proposed model excels in pest and disease classification tasks, effectively handling significant morphological differences across life periods.

A digital microfluidic (DMF) system based on electrowetting on dielectrics (EWOD) is a new technology that is able to manipulate microlitre droplets on the plane. Conventional EWOD devices have difficulty achieving high integration and a large number of electrodes due to the limitation of electrical connections. To realize the precise control of multiple droplets in a large-area EWOD device, we propose a programmable high integration and resolution DMF device based on a thin film transistor array (TFTA) – EWOD in this paper. The TFTA backplane with thousands of individually addressable electrodes used in electrowetting displays (EWDs) is integrated into this device. A source integrated circuit (IC) and a gate IC are bonded on the substrate glass of the device as the driver chip. A TFTA-EWOD device with $\mathrm {320 \times 240}$ electrodes is designed, fabricated and tested in our experiments. Furthermore, a matching droplet control system with detection and feedback functions was developed and implemented. This system is capable of detecting and analysing individual droplet status while concurrently continuing with other droplet manipulations on the TFTA-EWOD device. The experimental results show that different droplet manipulations, including dispensing, merging and transport, can be carried out successfully on this device. We also successfully applied the proposed device and system to a colorimetric enzymatic assay to show that the proposed scheme is capable of chemical analysis experiments. There are no additional errors introduced by the proposed TFTA-EWOD device. The designed device and matching system proposes a programmable high integration, high resolution, and universal solution for complex DMF applications. We hope that the proposed device and system can provide an experimental platform to other research teams who focus on DMF applications.