Search Results (145)

Genetically encoded biosensors are now central tools, deployed either as intracellular reporters to advance basic research, or as whole-cell reagents that detect analytes in diverse sample-types. Across the diversity of molecular scaffolds and modes of operation, biosensors serve a common functional purpose: translating ligand presence into a readable signal. Despite this shared logic, biosensor development as a field of practice remains fragmented: different scaffolds and modalities are advanced in separate, often lab-specific pipelines with diverse assays, metrics, and design practices. Moreover, libraries, selection histories and performance data generated during routine campaigns rarely outlive the projects that produced them. In this perspective, we focus on this fragmentation as a field-level bottleneck and argue that it deserves explicit attention in its own right. We discuss how modest, incremental steps—such as structured development records, adherence to high-information screening formats, library annotation, and community-level deposition infrastructure—could make biosensor development more reproducible, more comparable, and easier to build on across projects and laboratories. We further argue that such infrastructure will become increasingly valuable as computational protein design matures—not as a competing approach, but as the source of diverse, comparable, and context-annotated experimental data that sequence-function models and design benchmarks ultimately depend on. Full article

Euclidean plane geometry problem solving is a challenging benchmark for artificial intelligence because it requires complex diagram understanding, symbolic deduction, and multi-step reasoning. Constructing effective datasets for this task requires geometric instances that are realizable, non-degenerate, structurally diverse, and paired with human-like proofs. However, existing random or template-based generation pipelines often produce redundant, singular, or infeasible candidates, causing substantial computation to be spent before useful reasoning trajectories can be extracted. To address these limitations, we present FGeo-GCG, a hybrid geometric data synthesis framework built on the FormalGeo-V2 deductive engine. It formulates Geometric Configuration Generation as an incremental linear construction process that decomposes global constraint satisfaction into local construction steps, thereby pruning invalid branches during the generation process. To improve reliability and efficiency, FGeo-GCG combines two validation stages: a safe stochastic Jacobian-rank filter estimates whether local candidate constraints contribute independent algebraic restrictions, and progressive geometric validation checks whether the resulting partial construction remains realizable and non-degenerate. By encoding incidence-, metric-, and symmetry-related dependencies within unified constraint graphs, the framework also connects geometric data synthesis with structural symmetry analysis. Validated constraint graphs are then converted into problem instances through forward deduction, goal decomposition, and multi-dimensional complexity filtering, producing proof targets without manual annotation. Experiments show that the full validation pipeline reduces the failure rate for highly constrained instances. The resulting FGeo-GCG dataset contains more than 50,000 formally validated plane geometric configurations and provides engine-derived reasoning traces and targets for future training and evaluation of neuro-symbolic geometry problem-solving systems. Full article

In class-incremental learning (CIL), a model must learn new classes while retaining previous knowledge without storing all historical data. Generative replay mitigates catastrophic forgetting by synthesizing old class samples, but conventional pipelines usually train separate generative and classification models and can be degraded by generated images of poor quality. This paper proposes the Co-Diffusion Classifier (CoDC), a unified framework based on diffusion that performs image generation and classification in a single network. CoDC attaches a classification branch to the UNet encoder and introduces an exponential noise filtering loss according to diffusion timesteps so that cleaner samples contribute more strongly to representation learning. A base task classification pre-training stage followed by collaborative training with selective parameter freezing reduces conflicts between noise prediction and semantic feature extraction. For rehearsal-free replay, generated samples are selected using confidence and feature consistency filters. Experiments on CIFAR-100, FaceScrub, and Flowers-102 show that CoDC maintains strong incremental accuracy without storing real old class exemplars. Additional comparisons that account for protocol differences with recent exemplar-free and pre-trained model methods clarify the setting in which CoDC is most directly comparable. Full article

Node-level cargo-volume forecasting in logistics sorting networks requires modeling temporal dynamics together with directed inter-node dependencies and planned topology perturbations. This study addresses 1-h-ahead forecasting under a partial-information boundary, where historical node volumes, the pre-change network structure, and planned route-topology changes are available before prediction, whereas continuous post-change dynamic edge weights and realized post-change graph states are unavailable. We propose a perturbation-aware framework that represents the sorting system as a directed network and integrates temporal features, pre-change structural descriptors, topology-change encodings, perturbation-response proxies, and similarity-assisted support for data-scarce nodes within a unified forecasting protocol. A shared random forest backbone is used only to assess the incremental value of these representations. Experiments on 57 sorting centers show that temporal dynamics dominate under stable-network conditions. Under topology perturbation, topology-change signals reduce test weighted absolute percentage error (WAPE) from 18.10% to 17.11%, and perturbation-response proxies further reduce it to 16.91%. For data-scarce nodes, similarity support reduces test WAPE from 29.43% to 26.68%, with consistent gains under 10%, 20%, and 30% sample-retention settings. These results suggest that the framework provides an interpretable and information-admissible representation strategy for node-level forecasting in directed networked systems. Full article

Aiming at the problems of glare interference, local overexposure and detail loss caused by artificial light sources such as vehicle lamps and street lamps in nighttime road scenes, as well as the challenges of existing glare suppression models with large parameters, high computational complexity and difficulty in deploying on edge devices, this paper proposes a lightweight glare suppression network (LGSNet) based on ghost depthwise separable convolution and Lightweight Parallel Attention. Based on the U-Net architecture, the network introduces ghost depthwise separable convolution blocks (GhostDSC) in the encoder and decoder, which generates ghost features through cheap linear transformations by exploiting feature map redundancy, significantly reducing model parameters and computational costs while maintaining feature representation ability. Meanwhile, a Lightweight Parallel Attention (LPA) module is designed in the decoder stage, which integrates channel attention and pixel attention in parallel, enhancing the network’s attention to glare regions and edge details with extremely low parameter increment to improve detail recovery accuracy. In addition, a joint loss function consisting of background loss, glare loss and reconstruction loss is constructed to collaboratively optimize glare suppression and detail preservation. Experimental results on the public Flare7K++ dataset and the self-built nighttime road glare dataset NRGD show that the proposed method has only 7.45 M parameters, much lower than standard U-Net and Uformer. It achieves competitive results on full-reference metrics such as PSNR, SSIM, LPIPS and no-reference metrics such as NIQE, BRISQUE, PIQE, and can effectively suppress various types of glare interference and restore obscured scene details. It achieves a superior trade-off between model complexity and enhancement performance, significantly reducing the parameter count and computational overhead compared to heavy baselines, thereby offering a highly efficient solution for resource-aware glare suppression tasks. Full article

High-frequency FY-4B aerosol optical depth (AOD) observations provide useful spatiotemporal constraints for dust nowcasting, but their application over bright deserts is limited by retrieval gaps and high-AOD uncertainty. This study develops a physics-informed spatiotemporal learning framework for 15–60 min FY-4B AOD nowcasting over the Taklimakan Desert. Historical FY-4B AOD, valid masks, ERA5 dynamic fields, model-level diagnostics, and surface constraints are organized on a unified 48 × 64 grid. An LSTM–TCN–Transformer temporal backbone is combined with spatial-context encoding, mask-aware observation encoding, and structured source–transport prediction heads to represent both temporal evolution and spatial plume structures. A physics encoder represents boundary-layer mixing, vertical wind shear, source-region emission, upwind transport, and deposition loss. Mask-aware encoding and structured prediction heads are used to handle missing retrievals, source and transport increments, high-AOD tails, and low-confidence regions. Results show that FY-4B AOD constrains the main dust-belt position and spatial extent within 1 h, with skill decreasing from 15 to 60 min. High-coverage samples show more stable spatial structures, whereas low-coverage and extreme high-AOD cases have larger peak underestimation and boundary errors. The proposed framework improves high-AOD event detection and spatial-structure preservation compared with persistence, advective persistence, ConvLSTM, and ST-UNet baselines. An additional case-based comparison with MODIS MAIAC AOD and MERRA-2 dust optical depth shows partial spatial colocation between predicted high-value footprints and independent aerosol-enhancement references; however, the reported skill scores should still be interpreted mainly as spatiotemporal consistency with the FY-4B AOD product field rather than direct validation of true atmospheric dust loading. Full article

Vision-and-Language Navigation in continuous environments (VLN-CE) requires embodied agents to ground natural language instructions into reliable long-horizon motion decisions under partial observability. Despite their strong semantic understanding and reasoning abilities, Multimodal Large Language Model (LVLM) struggle when directly applied to VLN, as they lack explicit spatial grounding, embodied memory, and awareness of geometric and reachability constraints, leading to perceptual misalignment and cascading decision errors in complex scenes. To address these limitations, we propose STAMP, a Spatial-Temporal Anchored Motion Planning framework for zero-shot VLN-CE, which systematically bridges the gap between pretrained world knowledge and embodied navigation. STAMP adopts a hierarchical design that decouples high-level semantic reasoning from low-level motion execution, enabling a frozen LVLM to operate over a structured, navigation-oriented abstraction. Its core novelty lies in a multimodal spatial-temporal anchoring mechanism that explicitly encodes instruction-relevant landmarks, action semantics, depth-aware geometry, and historical navigation context, together with an explicit Chain-of-Navigation reasoning process that constrains decision-making to navigation-critical cues. Furthermore, STAMP incrementally constructs an online, backtracking-enabled topological map, supporting robust planning under uncertainty. Extensive experiments demonstrate the effectiveness of the proposed STAMP framework, achieving performance comparable to state-of-the-art zero-shot methods on VLN-CE benchmarks and in real-world settings. Full article

Accurate volatility forecasting and timely risk early warning are foundational requirements of financial risk management: Value-at-Risk estimates, portfolio risk limits, derivative hedging ratios, and stress-test scenario calibrations all depend on forward-looking volatility signals that remain reliable when market conditions depart from average. This paper develops a public-data causal multiscale wavelet spillover learning (CMWSL) framework that jointly addresses stock-index volatility forecasting and high-volatility early warning under strict walk-forward evaluation. CMWSL integrates three components: a heterogeneous autoregressive (HAR) persistence block as the dominant linear baseline, causal stationary wavelet transform (SWT) summaries that encode within-index multiscale market dynamics, and a cross-index spillover layer that tests whether medium- and long-scale wavelet energy from peer indices carries incremental risk-relevant information. The empirical analysis covers the S&P 500, Nasdaq-100, and Dow Jones Industrial Average over a 2513-step out-of-sample evaluation period from 2016 to 2025, with forecast horizons $h\in \{1,5,10\}$ and OHLC-based volatility targets. All preprocessing, wavelet decomposition, calibration rules, and warning thresholds are re-estimated inside each rolling training window to eliminate look-ahead bias. HAR remains the strongest average model in the main Rogers–Satchell specification, confirming that daily index volatility risk is highly persistence-driven. The multiscale extension delivers statistically significant improvements at longer horizons, in richer public macro-financial information environments, and under the Parkinson target. Clark–West tests detect significant spillover gains in five of nine index–horizon cells (CW $=4.83$, $p<0.001$ for S&P 500 at $h=10$). Critically, tail-conditioned and rolling-window diagnostics show that multiscale and cross-index gains concentrate in upper-volatility regimes and synchronized stress episodes—precisely the conditions in which risk management decisions are most consequential. For market-risk early warning, a logistic classifier built on the same causal feature pipeline delivers the most stable precision–recall performance across all settings, providing an interpretable and operationally auditable alert mechanism suitable for practical risk monitoring. Full article

Angular speed is the main variable used to regulate electrical drives, where incremental encoders and tachometers are normally used to provide an effective position and speed measurement using time-fixed (the elapsed time is fixed, and the angle is measured by accumulating encoder pulses) or pulse-fixed (the number of pulses is fixed, and the time is measured by accumulating cycles of a reference clock) estimators. In both cases, errors are made in the speed calculation, which can be particularly large at low (time-fixed estimator) or high (pulse-fixed estimator) rotor speeds. Each method has different sources of errors and optimal ranges for speed measurement, which generate uncertainty in the efficiency of the electric drive. This work proposes a new speed estimation method that uses both frequency and period speed techniques. The implemented algorithm combines the estimations obtained based on the actual rotor speed and the inverse variance weighting method. The obtained results state that the resulting measured speed outperforms the time-fixed and pulse-fixed estimations across any speed range. Full article

Estimation of distribution algorithms (EDAs) are optimization methods that search for explicit probabilistic models which are used to sample promising candidate solutions. The optimization process consists of a sequence of incremental updates to an initial probabilistic model, which is then used to sample candidate solutions for the problem to be solved. EDAs use an explicit probability distribution encoded by a Bayesian network, a multivariate normal distribution, or another model class. Although some EDAs optimize the structure of the probabilistic graph model, the distribution type at each node is typically fixed; for continuous variables, the nodes generally encode normal distributions. The current paper proposes M-EDA (mixture-based estimation of distribution algorithm)—an EDA variant based on genetic algorithms which aims to identify an optimal type of probabilistic model, encoding mixtures of probability distributions and their corresponding parameters. M-EDA optimizes such mixtures in order to fit complex landscapes. These mixtures are encoded in the genetic algorithm (GA) through heterogeneous variable-length chromosomes. M-EDA was tested on several numerical optimization problems used widely in the literature on genetic algorithms and reached near-optimal solutions. It also demonstrated multimodal optimization capabilities. Finally, M-EDA was also tested on the instance selection (IS) problem, obtaining a substantial reduction in the number of selected instances, and outperforming most of the competing techniques—in accuracy on balanced datasets, and in instance-reduction rate on imbalanced or high-dimensional ones. Full article

A coupled multi-stage learning framework is presented for joint bit error rate (BER) prediction and beam angle optimization in massive multiple-input multiple-output (MIMO) systems under a controlled simulation protocol. Unlike purely sequential benchmarking pipelines, the proposed method jointly coordinates BER prediction and beam-angle selection through a shared latent representation, an uncertainty-guided refinement mechanism, a cross-stage consistency loss and alternating optimization. Ten diverse approaches are systematically evaluated across two task-specific stages: Stage 1 examines six classical and adapted methods for BER prediction, including polynomial regression and deep unfolding networks; Stage 2 investigates four machine-learning and generative adversarial network (GAN)-based approaches for angle optimization, including conditional GANs and the proposed Direct-Angle neural network. Stage 3 couples the best-performing methods into a unified hybrid architecture through a shared encoder, explicit consistency regularization and alternating cross-stage updates, thereby producing an integrated beamforming decision strategy rather than an independent cascade. It is shown through the evaluation that the coupled hybrid framework achieves 96.0% overall angle-selection accuracy, a mean BER of $8.0\times {10}^{-5}$ and 100% BER tolerance compliance within $\pm 3$ dB. In this framework, a differentiable BER surrogate initialized from a second-degree polynomial-regression teacher is coupled with the proposed Direct-Angle-NN for angle optimization. Relative to the strongest reimplemented literature baseline under the same controlled simulation assumptions, a 33.3% reduction in mean BER is achieved. Ablation experiments show that the coupling mechanism provides a modest but consistent improvement over the decoupled sequential baseline, increasing angle-selection accuracy from 93.5% to 96.0% and reducing mean BER from $1.05\times {10}^{-4}$ to $8.0\times {10}^{-5}$; the shared encoder accounts for the largest part of this gain while the consistency loss adds 0.6 percentage points. These results indicate that the shared encoder, consistency regularization and uncertainty-guided refinement improve the final beamforming decision, although the gain should be interpreted as incremental rather than as a large architectural breakthrough. A spectral efficiency of 38.0 bps/Hz and an energy efficiency of 0.466 Gbps/W are achieved with a power consumption of only 32.6 W. The theoretical discussion is presented as an analytical characterization of BER sensitivity, complemented by a computational-complexity assessment and empirical convergence diagnostics for the alternating optimization, rather than as a formal optimality proof. The effectiveness of the framework across multiple performance metrics is supported by Monte Carlo simulations, while the limitations of the current setup, including perfect CSI, uncoded QPSK, ideal hardware assumptions and a fixed beam codebook, are explicitly discussed. The complete simulation framework, including code and trained models, can be made available by the corresponding author upon reasonable request to facilitate reproducible research in massive MIMO optimization. Full article

Dynamic multicast routing in software-defined networks is challenging due to continuously changing network states, multicast branch coupling, and the dependency between local forwarding decisions and global multicast tree construction. Existing multicast routing approaches mainly rely on static heuristics or snapshot-based optimization, which makes them difficult to maintain routing adaptability and decision stability under dynamic network conditions. To address these limitations, this paper proposes a topology-aware deep reinforcement learning multicast routing algorithm, named Graph-structured Hierarchical Actor–Critic for Multicast Routing (GHAC-MR). Specifically, the multicast routing process is formulated as a sequential tree construction problem, where each forwarding action incrementally affects the subsequent multicast tree evolution. A graph-structured state representation mechanism is designed to encode network topology information, link resource states, and multicast branch dependencies, enabling the routing agent to capture structural correlations among multicast forwarding nodes. Furthermore, a hierarchical actor–critic learning architecture is introduced to jointly optimize multicast forwarding policies and long-term routing rewards, thereby improving routing adaptability and convergence stability in dynamic network environments. Experimental results on multiple representative network topologies demonstrate that the proposed GHAC-MR algorithm achieves superior performance in multicast acceptance ratio, resource utilization efficiency, and routing adaptability compared with representative heuristic, evolutionary, and reinforcement learning-based multicast routing schemes. Full article

Cyanobacterial blooms in lakes and reservoirs pose significant environmental and public health risks. This paper presents an effective exploration strategy to detect them from Autonomous Surface Vehicles (ASVs) equipped with probes, whose sensing trajectories are optimized by an AI-based planner that considers the 3D spatial-temporal evolution of the cyanobacteria concentration obtained by a multiphysics model. The planner, simultaneously working on the AI decision-making and robotic domains, optimizes the surface displacement of the ASV and the depth of its probe by solving a constrained multi-objective optimization problem that minimizes the mission duration and trajectory length, maximizes the possibilities of the probe to overpass areas with high concentration of cyanobacteria, and satisfies operational constraints (such as ASV velocity or acceleration limits, and obstacle avoidance). The optimization is supported by two well-known versions of the Non-Sorted Generic Algorithm (NSGA-II and NSGA-III) and by encoding the trajectories with spline curves whose number of control points can be fixed, progressively increased, or freely manipulated by the algorithm. The performance of different configurations of the planner is tested against six scenarios obtained from different simulations of the multiphysics model (which couples water dynamics and temperature, light transmission, daily vertical migration of the cyanobacteria and their growth). The statistical analysis of the planner results determines that NSGA-III working with variable-length chromosomes and NSGA-II with the progressive increment of spline points as the best configurations for maximizing cyanobacteria detection, and minimizing mission duration and trajectory length. Full article

The VHL–HIF-1α–VEGF axis regulates angiogenesis and metabolism. Beyond oncology, pVHL is essential for pancreatic β-cell function and is reduced in hypercaloric diet (HCD)-induced type 2 diabetes mellitus (T2DM). This study aimed to overexpress pVHL in pancreatic tissue and evaluate its effects on blood glucose levels and the expression of proteins related to glucose metabolism in the pancreas. HCD-induced diabetic C57BL/6 and BALB/c mice received a single intrapancreatic injection of an adenoviral vector (1 × 10¹² viral particles) encoding the murine Vhlh gene (AdVHL) to induce transient pVHL overexpression. The glycemic delta (post-load glucose minus fasting) and net incremental area under the curve (niAUC) were determined on days 3, 6, 9, 12, and 15 post-treatment, as the peak in GFP overexpression (used as a surrogate reporter of transduction efficiency) was detected between days 9 and 12. Immunohistochemistry (IHC) and immunofluorescence (IF) were used to assess the expression of pVHL, HIF-1α, GLUT-1, GLUT-2, and insulin in pancreatic tissue. AdVHL treatment significantly decreased the glycemic delta and niAUC in mice with T2DM (p < 0.01). On day 15 after treatment, HIF-1α and GLUT-1 expression were markedly reduced in AdVHL-treated mice (p < 0.01), while GLUT-2 and insulin were significantly increased (p < 0.01). These results were reproduced in both mouse strains. Transient overexpression of pVHL in pancreatic tissue of mice with T2DM was associated with decreased glucose levels and changes in the expression of proteins related to glucose metabolism in the pancreas, resembling a healthier phenotype than that of mice with T2DM. These findings support an important functional role of the pVHL–HIF-1α axis in pancreatic physiology, provide a proof-of-concept for further mechanistic and translational studies, and implicate pVHL in the altered glucose metabolism observed in T2DM. Full article

Worldwide, breast cancer is the leading cause of death in women. This emphasizes the significance of an accurate breast cancer detection system. This study presents a unified framework for segmentation of breast cancer using multimodal imaging, such as histopathology, MRI, mammogram, and ultrasound. This framework integrates the CNN with Transformer modules and has three core technical innovations. First, features are extracted using an encoder–decoder design. The encoder has Residual Blocks with a base channel of 32, following feature extraction, which are progressively mapped and downsampled into four stages (32 → 64 → 128 → 256) of channels. The spatial channel is reduced using MaxPool2d operations from 256 × 256 to 128 × 128, 64 × 64, 32 × 32, and 16 × 16. After further convolutional refinement, a Transformer encoder is used on the 16 × 16 feature maps in the bottleneck. The Transformer comprises four encoders with multi-head self-attention (eight heads) and a 4.0 MLP ratio, enabling the model to capture local and global contextual dependencies at the lowest resolution. The proposed framework is trained with a learning rate of 1 × 10⁻⁴, up to 50 epochs with early stopping (patience = 12), using a combined Dice and binary cross-entropy loss that balances pixel-wise accuracy and overlap-based learning. Gradient clipping with a maximum norm of 5.0 is used to ensure training stability; ReduceLROnPlateau (factor = 0.5, patience = 5) is used to dynamically adjust the learning rate; and early stopping is used to prevent overfitting. To improve generalization and enhance robustness to data variability, data augmentation techniques such as random horizontal and vertical flips, intensity variations, and small rotations (±15°) are applied. Incremental learning was implemented in this study as a warm-start fine-tuning strategy, where the model was initialized based on learned weights from a previously trained model instead of training from scratch. This is done by loading saved checkpoints of the best-performing model and continuing training on a new dataset. The performance of the proposed framework is evaluated on four publicly available datasets and one local dataset, such as BUS-UCLM, BUSI, BreastDM, TNBC NucleiSegmentation, and BCSD-2024. The impressive results are achieved with Dice scores of 0.974 on ULCM, 0.975 on BUSI, 0.971 on BreastDM, 0.904 on TNBC nuclei segmentation, and 0.982 on BCSD-2024. The proposed model consistently performed better than classical U-Net models. Full article