Search Results (206)

In partially observable adversarial environments, heterogeneous unmanned aerial vehicle (UAV) swarms must generate tasks online from noisy observations while respecting platform capabilities, consumable resources, and structural dependencies among tasks. This paper proposes a task graph generation method that converts local observations, target beliefs, and UAV resource states into executable task graphs with explicit resource semantics and inter-task relations. The method first constructs a sufficiently expressive candidate task graph in the belief and resource spaces. An offline search teacher then evaluates future trajectory particles, resource feasibility, and structural interaction values to produce supervision for node selection, marginal task value, and relation prediction. A relation-biased graph attention network learns to generate task graphs online, and a task manager further performs task filtering, dependency repair, conflict completion, and resource checking. Simulation results under complex observation pressure and unseen adversarial strategies show that the proposed method consistently improves structural generation quality and execution feasibility. Compared with Graphormer, it improves the task-graph utility, task-edge F1-score, and executable-graph ratio by 5.83%, 5.41%, and 2.68%, respectively, while reducing the infeasible-task ratio by 35.14%. These results indicate that combining an offline search teacher with resource-constrained graph modeling provides an effective front-end task organization mechanism for heterogeneous UAV swarm planning. Full article

The rapid rise in Android applications has fueled a significant surge in the creation and distribution of malicious apps by cybercriminals. Numerous tools and applications are utilized to detect Android malware apps. However, they cannot effectively detect the latest or zero-day Android malware apps because these tools rely on conventional signature-based approaches. Therefore, more advanced intelligent techniques are investigated to overcome the inherent limitations of the traditional signature-based detection techniques. Nevertheless, the use of intelligent machine learning techniques with a large number of features is resource-intensive and time-consuming in resource-constrained mobile environments. This paper proposes a novel hybrid intelligent approach for Android malware detection that integrates a two-stage Correlation–Differential Evolution-based feature selection (Corr-DE) with gradient-boosting tree ensembles, including LightGBM and XGBoost. In the first stage, a correlation-based filter is employed to reduce feature redundancy by selecting the top 30% of most relevant static and dynamic features. In the second stage, Differential Evolution is utilized to identify an optimal subset of discriminative features, thereby enhancing detection performance. Accordingly, LightGBM and XGBoost are trained effectively using the optimal features and then employed to maximize the detection performance of Android malware apps. The experimental results demonstrate that both LightGBM and XGBoost with Corr-DE feature selection achieved high levels of Android malware detection, with overall accuracy of 95.78% and 95.51%, respectively, while the LightGBM and XGBoost with Corr-DE contributed to reducing the feature space substantially by 83% (reducing the feature space from 420 to 72 features). Full article

The high-value utilization of construction and demolition waste is critical for sustainable development in the building sector. However, in construction and demolition waste (CDW) recycling supply chains, existing studies lack a systematic analysis of pricing mechanisms for such recycled CDW as substrate products, particularly regarding interest coordination and the quantification of green value. To reveal the bargaining mechanism between farmers as recyclers and processors and supermarkets as retailers under an asymmetric bargaining structure, this study applies Nash bargaining theory to construct a dynamic game model. The study revealed that (1) when the green degree of a product reaches a certain level, it can obtain a sustainable market premium and create a stable income space for both parties. (2) The relative strength of the bargaining power between the two sides significantly affects the impact of market base scale changes on profit distribution. When the bargaining power of the supermarket is lower than the threshold and the bargaining power of the farmers is higher than the threshold, the difference in profit between the farmers and the supermarket is negatively correlated with the market base scale of the CDW as a substrate. (3) The green sensitivity level of consumers affects the difference in profit of the main body with the government subsidy to farmers. This level is determined by the value of the green sensitivity coefficient of consumers and presents a differentiated adjustment effect in different value ranges, which in turn affects the transmission direction of government subsidies to profit distribution. (4) When the green sensitivity coefficient and the green communication intensity of farmers and the investment level are lower than the corresponding critical values, the difference in social welfare with or without subsidies is positively correlated with the amount of the subsidy. This study provides decision support for farmers and supermarkets in designing rational bargaining strategies and offers insights for improving coordination and sustainability in construction and demolition waste recycling supply chains. Full article

Differential Liberation Expansion (DLE) and viscosity tests are core elements of the Pressure–Volume–Temperature (PVT) laboratory suite used to characterize reservoir oils under depletion and to support compositional modeling and reservoir simulation. Nevertheless, both DLE and viscosity testing remain expensive and time-consuming due to specialized equipment, strict operating procedures, and the need for experienced laboratory personnel. Building on our prior work that introduced the proximity-informed Local Interpolation Model (LIM) framework for Constant Composition Expansion (CCE), this study demonstrates how the same end-to-end, neighborhood-based workflow is applied to DLE and viscosity test data. A target fluid is embedded in a compositional–thermodynamic descriptor space and paired with a small set of thermodynamically similar fluids drawn from a PVT data archive. Within this locality, LIM is used to infer DLE behavior by combining local interpolation for key scalar quantities (e.g., saturation-point and endpoint PVT values) with shape-preserving reconstruction of pressure-dependent curves. For viscosity, the same approach reconstructs the oil viscosity curve ${\mu }_o\left(p\right)$ across the undersaturated and saturated regions. Evaluation on a proprietary database of DLE and viscosity tests shows strong agreement across diverse fluids for both DLE and oil viscosity trends. For example, across Tier 1–3 fluids, the mean curve mean absolute percentage error (MAPE) is 1.01% for $B_o$, 0.51% for ${\rho }_o$, and 1.32% for the liberated-gas $Z$-factor, while the conditioned baseline viscosity workflow yields a mean diphasic-branch MAPE of 7.75%. This supports reducing reliance on new DLE and viscosity measurements while maintaining engineering-grade fidelity in reservoir engineering and simulation workflows. This approach has been fully automated through software so it can be set up and directly utilized by the field operators on their own databases to significantly reduce their fluid sampling and laboratory analysis costs. Moreover, the proposed (artificial intelligence) AI model does not use others’ data, respecting data privacy and data ownership. Full article

In mining TBM excavation, the mineralogical heterogeneity of rock significantly impacts tunneling efficiency and rock-breaking performance. The cutting process of tunnel boring machine (TBM) double-disc cutters is significantly influenced by the combined effects of mineral composition differences and cutter spacing parameters. In this study, a heterogeneous granite model was constructed using the finite–discrete element method (FDEM), with quartz content fixed at 30%. Different mineral compositions were generated by adjusting the proportions of feldspar and mica, and a double-disc cutter–rock contact model was employed with various cutter spacings to perform numerical cutting simulations. Cutter work was calculated by integrating the force–displacement curves, rock-breaking efficiency was evaluated by the specific energy (SE) defined as the energy consumed per unit rock chip area, and fracture types, as well as fragmentation volumes, were identified. The results show that the total input energy ranged from 2.2 to 3.4 mJ, reaching a peak at medium cutter spacings of 50–70 mm; as feldspar content increased, the overall energy level rose significantly. Rock-breaking efficiency was relatively high at medium cutter spacings, and the favorable spacing range shifted from approximately 50 mm to 60 mm when feldspar content increased from 40–50% to 60%. Excessively small spacing led to a higher proportion of crushing and repeated damage, while overly large spacing weakened crack interactions, both of which reduced efficiency. Overall, cutter spacing mainly controlled the crack interaction patterns, whereas the feldspar–mica ratio dominated energy utilization. These findings suggest that, in practical TBM excavation, cutter spacing should be reasonably optimized according to the mineral composition of the surrounding rock to avoid energy waste caused by extreme spacing and to achieve a balance between efficiency and energy consumption. Full article

As a key task in remote sensing analysis, semantic segmentation of remote sensing images (RSI) underpins many practical applications. Despite its importance, obtaining dense pixel-wise annotations remains labor-intensive and time-consuming. Unsupervised domain adaptation (UDA) offers a promising solution by utilizing knowledge from labeled source domains for unlabeled target domains, yet its effectiveness is often compromised by significant distribution shifts arising from variations in imaging conditions. To address this challenge, we propose a depth-aware adaptation network (DAAN), a novel two-branch network that explicitly leverages complementary depth information from a digital surface model (DSM) to enhance cross-domain remote sensing segmentation. Unlike conventional UDA methods that primarily focus on semantic features, DAAN incorporates depth data to build a more generalized feature space. This network introduces three key components: an adaptive feature aggregator (AFA) for progressive semantic-depth feature fusion, a gated prediction selection unit (GPSU) that selectively integrates predictions to mitigate the impact of noisy depth measurements, and misalignment-focused residual refinement (MFRR) module that emphasizes poorly aligned target regions during training. Experiments on the ISPRS and GAMUS datasets demonstrate the effectiveness of the proposed method. In particular, DAAN achieves an mIoU of 50.53% and an F1 score of 65.75% for cross-domain segmentation on ISPRS to GAMUS, outperforming models without depth information by 9.17% and 8.99%, respectively. These results demonstrate the advantage of integrating auxiliary geometric information to improve model generalization on unlabeled remote sensing datasets, contributing to higher mapping accuracy, more reliable automated analysis, and enhanced decision-making support. Full article

Lossless image compression is pivotal for deep-space exploration. Considering the requirements of deep-space exploration for a high compression ratio and real-time processing, traditional image compression algorithms have garnered significant attention. However, existing algorithms struggle with real-time processing speed and compression degradation in high-noise regions, failing to meet the throughput demands of next-generation sensors. To address these challenges, this paper proposes a high-throughput and noise-resilient lossless image compression architecture, named HT-NRC, for deep-space CMOS cameras. First, to overcome the throughput bottleneck, we introduce a parallel processing method, which is built on index-based dispatch and Reorder mechanism. This is achieved by dynamically distributing pixel streams into parallel cores and utilizing a Reorder Buffer for sequence restoration. Second, to mitigate low compression efficiency in noisy backgrounds, we present a Heterogeneous Dual-Path Coding scheme. This system adaptively separates structural information for predictive coding and stochastic noise for raw packing with Bit-Plane Slicing (BPS) strategy. The proposed architecture was implemented on a Xilinx Virtex-7 FPGA (Xilinx, Inc., San Jose, CA, USA). Operating at 100 MHz, the system achieves a processing throughput of 414.7 Mpixel/s and a high average compression ratio under deep-space image datasets, while consuming an estimated total on-chip power of only 2.1 W. Experimental results show that our proposed method substantially outperforms existing baseline methods. Specifically, compared to the optimized serial JPEG-LS implementation processing one pixel per clock cycle, our parallel architecture achieves an approximately 314.7% increase in processing throughput. Full article

Rice blast, caused by Magnaporthe oryzae, is a devastating fungal disease threatening global rice production, with annual yield losses ranging from 10% to 30% in epidemic regions. Conventional detection methods rely on visual inspection and laboratory diagnosis, which are limited by subjectivity, time-consuming procedures, and the inability to detect early-stage infections. Hyperspectral imaging technology offers a highly promising method for detecting rice blast disease. It can capture the physiological and biochemical changes that occur in plant tissues before the appearance of visible symptoms. In this study, we propose a Convolutional-State Space Hybrid Network (CS-HybridNet) featuring a dual-branch deep learning architecture that synergistically combines a ConvNeXt-based spatial branch with a LiteMamba-based global spatial branch (which models long-range spatial dependencies with spectral embeddings). Principal component analysis was employed to reduce the dimensionality from 360 hyperspectral bands to 16 principal components, retaining 99.09% of the original information while significantly improving computational efficiency. An adaptive feature fusion module effectively integrates spatial texture features with spectral features, enabling complementary information utilization. Experimental results on a dataset comprising 166 hyperspectral images demonstrate that CS-HybridNet achieves 96.30% ± 1.38% accuracy, 98.33% precision, 95.16% recall, and an AUC–ROC value of 0.971 on the independent test set, outperforming traditional machine learning methods and existing deep learning models by 3.5–12.8% in accuracy. Ablation studies validate the effectiveness of each component. This research demonstrates the efficacy of spatial-spectral fusion architecture for automated plant disease detection and establishes a technical foundation for the development of intelligent crop disease monitoring systems. Full article

Monitoring suspended-sediment concentration (SSC) is essential to better understand how sediment transport could adversely affect water availability for human communities and ecosystems. Aquatic remote sensing methods are increasingly utilized to estimate SSC and turbidity in rivers; however, an evaluation of their quantitative performance is limited. This study evaluates the performance of three multispectral sensors, which vary in resolution and ease of deployment, to estimate turbidity in the Colorado River: the Multispectral Instrument (MSI) on board the European Space Agency’s Sentinel-2 satellite, an industrial-grade 10-band dual camera system mounted on a cable car, and a consumer-grade 6-band dual camera system positioned on the riverbank. We use multivariate linear regression to compare in situ turbidity measurements with concurrent spectral reflectance data from each sensor. Models for all three sensors selected similar spectral information and resulted in mean errors <35% in predicting turbidity. A cross-sensor comparison showed that little accuracy is lost when applying models developed for satellite-based systems to ground-based systems, and vice versa. Transferability of satellite-based models to ground-based systems could support continuous water-quality monitoring between satellite overpasses and avoid issues associated with cloud interference. Conversely, continuously operating ground-based systems could be used to rapidly establish datasets and models for application in satellite imagery, thus accelerating remote sensing applications. The encouraging performance of the consumer-grade system indicates that SSC could be monitored for low cost. Full article

The prediction of fatigue life is critical in the design process, and current models offer a viable alternative to costly and time-consuming experimental fatigue testing. The constitutive fatigue model used integrates low-cycle and high-cycle fatigue behavior. This model is grounded on the concept of fatigue damage evolution and incorporates a moving endurance surface within the stress space, eliminating the need for ambiguous cycle-counting methods. An interesting observation is that many polymers exhibit macroscopic fatigue characteristics, specifically, the form of the $S-N$ curve similar to those observed in metals. Consequently, all fatigue model parameters were expressed in terms of the well-established Coffin–Manson–Basquin model parameters. However, the constitutive mathematical modeling itself is computationally time-consuming, particularly when applied to predict high-cycle fatigue across large design spaces. Therefore, the proposed model was utilized exclusively to generate high-quality data for training machine learning models that offer significantly improved computational efficiency. The high-cycle fatigue design of polymers and other ductile materials, traditionally dependent on expensive and time-consuming experimental methods, is now expedited through an advanced modeling framework that combines constitutive mathematical modeling with AI-based approaches. Full article

Accurate intraoperative differentiation between malignant and benign breast tissues, particularly the assessment of lymph node status and tumor margins, is critical for surgical decision-making and prognosis. Traditional histopathological methods, such as frozen section analysis, are time-consuming and labor-intensive. Magnetic Particle Imaging (MPI) is a novel, radiation-free modality that senses the microenvironmental properties of tissues through the dynamic response of magnetic tracers. In this study, we propose a diagnostic method utilizing the higher-order harmonic response of magnetic nanoparticles. Various ex vivo breast tissue samples were immersed in Synomag-50 nanoparticles. Using a custom-built MPI spectrometer (5 kHz excitation, 9 mT amplitude) operating in spectroscopic mode, we implemented a rapid acquisition protocol in which each sample was measured 10 times, with 0.1 s per cycle. We analyzed the magnetic response spectrum and calculated the ratio of the third to the fifth harmonic ($H_3/H_5$). Histological analysis confirmed the effective infiltration of MNPs into the interstitial spaces. The repeated measurement data demonstrated high stability. A distinct stepwise increase in harmonic ratios was observed from normal tissue to tumor-adjacent tissue and finally to malignant tumors. Specifically, malignant samples showed ratios that generally exceeded 2.2, whereas benign samples remained below 2.0. These preliminary findings suggest that the harmonic ratio could serve as a sensitive biomarker reflecting the microenvironmental constraints associated with malignancy. This study validates the feasibility of utilizing MPI signal harmonics as a quantitative metric with rapid signal acquisition capabilities for differentiating benign and malignant lymph nodes. Full article

We consider a network of a residential heating system (RHS) composed of two types of agents: a prosumer and a consumer. Both are connected to a community heating system (CHS), which supplies non-intermittent thermal energy for space heating and domestic hot water. The prosumer utilizes a combination of solar thermal collectors and CHS heat, whereas the consumer depends entirely on the CHS. Any excess heat generated by the prosumer can either be stored on-site or fed back into the CHS. Weather conditions, modeled as a common noise term, affect both agents simultaneously. The prosumer’s objective is to minimize the expected discounted total cost, taking into account storage charging and discharging losses as well as uncertainties in future heat production and demand. This leads to a stochastic optimal control problem addressed through dynamic programming techniques. Scenario-based analyses are then performed to examine how different parameters influence both the value function and the resulting optimal control strategies. For a common noise coefficient ${\sigma }_0=0.4$, the prosumer incurs an approximate $16.08\%$ increase in the aggregated discounted cost from the case of no common noise. For a discharging efficiency ${\eta }_E={\displaystyle \frac{1}{0.9}}$, the maximum aggregated discounted cost increases by approximately $1.85\%$ as compared to the perfect discharging efficiency. Similarly, for a charging efficiency ${\eta }_E=0.9$, we observe an approximate $1.94\%$ increase in the aggregated discounted cost as compared to a perfect charging efficiency. Furthermore, we derive insights into the maximum expected discounted investment that a consumer would need to make in renewable technologies in order to transition into a prosumer. Full article

Few-Shot Text Classification (FSTC) aims to classify text accurately into predefined categories using minimal training samples. Recently, prompt-tuning-based methods have achieved promising results by constructing verbalizers that map input data to the label space, thereby maximizing the utilization of pre-trained model features. However, existing verbalizer construction methods often rely on external knowledge bases, which require complex noise filtering and manual refinement, making the process time-consuming and labor-intensive, while approaches based on pre-trained language models (PLMs) frequently overlook inherent prediction biases. Furthermore, conventional data augmentation methods focus on modifying input instances while overlooking the integral role of label semantics in prompt tuning. This disconnection often leads to a trade-off where increased sample diversity comes at the cost of semantic consistency, resulting in marginal improvements. To address these limitations, this paper first proposes a novel Bayesian Mutual Information-based method that optimizes label mapping to retain general PLM features while reducing reliance on irrelevant or unfair attributes to mitigate latent biases. Based on this method, we propose two synergistic generators that synthesize semantically consistent samples by integrating label word information from the verbalizer to effectively enrich data distribution and alleviate sparsity. To guarantee the reliability of the augmented set, we propose a Low-Entropy Selector that serves as a semantic filter, retaining only high-confidence samples to safeguard the model against ambiguous supervision signals. Furthermore, we propose a Difficulty-Aware Adversarial Training framework that fosters generalized feature learning, enabling the model to withstand subtle input perturbations. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods on most few-shot and full-data splits, with F1 score improvements of up to +2.8% on the standard AG’s News benchmark and +1.0% on the challenging DBPedia benchmark. Full article

Background: The Ames test, a biological assay employing various strains of Salmonella typhimurium, serves as a cornerstone in genetic toxicology for evaluating the mutagenic and potentially carcinogenic properties of chemical compounds. However, experimental testing is resource-intensive and time-consuming for screening the vast chemical space of existing and novel drug candidates in pharmaceutical development. Methods: To address this limitation, we have developed the Ames Mutagenicity Predictor web application, which predicts mutagenic activity in the Ames test for given structural formulas across a comprehensive panel of different bacterial strains. The application utilizes advanced structure–activity relationship (SAR) models generated by PASS (Prediction of Activity Spectra for Substances) v2024 software. The training set comprised 3250 compounds with experimentally determined mutagenicity across 69 different strains, compiled from peer-reviewed literature and established databases, and 4285 non-mutagenic compounds from the WWAD as negative examples. Results: Leave-one-out cross-validation (LOOCV) of the 69 strain-specific models yielded an average Invariant Accuracy of Prediction (IAP) of about 0.944, and for the unspecified mutagenicity, a value of 0.962 was obtained. Conclusions: These validated models have been integrated into a freely accessible web application Ames Mutagenicity Predictor that enables users to input compound structures through multiple formats: a built-in chemical editor, SMILES notation, or compound name search. The application generates comprehensive reports detailing the predicted probability of positive Ames test results for each individual strain, providing researchers with detailed mutagenicity profiles. Full article

Amid evolving consumer demands, product design increasingly emphasizes the deeper needs for emotional resonance and cultural identity. Taking Liao–Jin dynasty silk as a case study, this study explores a digital regeneration pathway for traditional cultural colors, evolving from “form–color restoration” to “emotional awakening.” The study focuses on transforming the emotional imagery—such as “mighty” and “dignified”—embedded in the colors of Liao–Jin silk into perceptible, customizable color experiences for modern consumers. To achieve this, an emotional color customization system was constructed through the integration of Interactive Genetic Algorithms (IGA) with the PAD emotional model. Within this system, cultural emotional semantics (e.g., “Powerful,” “Victory”) were quantified as target anchor points in PAD space. The matching degree between color schemes and target emotions is calculated based on user feedback, and is utilized as a fitness function to drive evolution. An experiment was conducted with 48 volunteer evaluators using Liao–Jin silk. Results demonstrated that, compared to traditional IGA, this method achieved significant improvements in emotional matching accuracy: average fitness increased by 34.00%, maximum fitness rose by 10.76%, and the spiritual essence of Liao–Jin culture was more effectively translated into color schemes that evoke positive user emotions. This research offers an innovative solution for cultural heritage digitization, advancing from “form–color restoration” to “emotional and spiritual regeneration.” It also provides a viable approach for intelligent emotional design in fields such as apparel design, cultural creativity, and digital cultural heritage preservation. Full article