Search Results (11,938)

Accurate detection of field insect pests remains a significant challenge for precision agriculture due to the elongated and variable morphology of the target organisms, their frequent resemblance to complex background textures, and the long-tail distribution of species in natural datasets. While deep convolutional neural networks (CNNs) have advanced the field, they are often constrained by a limited effective receptive field and the entanglement of semantic and spatial features, which can lead to elevated false-positive rates and missed detections for low-contrast or rare targets. This paper introduces a novel detection framework that integrates state space modeling with multi-stream feature disentanglement to address these limitations. First, a visual state space module is employed as the backbone feature extractor, enabling the establishment of a global receptive field with linear computational complexity and thereby improving the perception of long-range morphological structures. Second, a Topological Feature Disentanglement Pyramid Network is proposed. This architecture explicitly separates feature representations into semantic and spatial streams and recombines them through graph convolutional interactions, which serves to suppress background interference and enhance localization precision. A meta-auxiliary detection head, active only during training, is introduced to amplify supervision signals for hard, low-contrast samples via adversarial gradient modulation. Furthermore, an implicit neural radiance field augmentation pipeline is used to generate physically consistent synthetic views of underrepresented pest classes, mitigating the negative effects of long-tail data distributions. Experimental evaluations on the public BAU-Insectv2 benchmark demonstrate that the proposed method achieves a mean average precision (mAP@0.5) of 81.8%, representing a 4.4-percentage-point improvement over a comparable baseline, while maintaining a compact parameter count of 2.33 M and an inference speed of 178.6 FPS. The framework exhibits particular efficacy in detecting elongated, minute, and rare pests, suggesting a promising technical approach for real-time, field-based pest surveillance in precision agriculture. Full article

Greenhouse microclimate regulation is challenging due to nonlinear coupling among temperature, humidity, soil moisture, and light intensity, which limits the effectiveness of conventional threshold-based and PID control strategies under time-varying environmental disturbances. This paper presents a forecast-augmented ensemble control framework that combines Random Forest, Gradient Boosting, and Support Vector Machine classifiers with one-hour-ahead weather forecasts for closed-loop greenhouse microclimate regulation. The proposed system was deployed and validated in a working greenhouse cultivating cucumber (cv. ‘Madora F1’) over 28 consecutive days. Sensor measurements and forecast inputs were processed through a unified preprocessing pipeline, while control actions were generated through majority voting and executed on Raspberry Pi 4B edge hardware with a worst-case inference latency below 18 ms. The proposed framework achieved a temperature RMSE of 0.83 °C during field deployment. For reference, RMSE values of 3.21 °C and 1.94 °C were obtained for the threshold-based and PID baseline controllers, respectively, under the adopted disturbance-consistent evaluation protocol. Compliance rates reached 96.4% for temperature, 94.1% for relative humidity, and 97.2% for soil moisture across 40,320 resampled observation intervals (60 s analysis grid) derived from the original 10 s acquisition stream. Integration of short-term weather forecasts enabled anticipatory irrigation management, reducing irrigation pump operation by 18% without compromising soil-moisture compliance and yielding an estimated annual energy saving of 158 kWh per greenhouse zone. Unlike prediction-oriented greenhouse artificial-intelligence studies, the proposed approach implements a deployable forecast-augmented closed-loop control architecture validated under continuous real-world greenhouse operation. Full article

Accurate vehicle localization must be maintained even in tunnel sections where GNSS reliability is degraded. However, conventional GNSS/INS-based localization rapidly accumulates errors in such environments, affecting lane-level decision-making and path-following stability. To address this problem, this study proposes a dedicated localization support sign for stable LiDAR observation and a point-cloud-registration-based correction algorithm. The proposed method detects a dedicated sign using a PointPillars-based detector, and the corresponding point cloud is registered to a pre-built reference map to estimate a rigid correction transform online. The sign was installed in a tunnel section of a proving ground that reproduces real-road conditions. For evaluation, the driving sequence was analyzed by separating the pre-entry section, the tunnel section before dedicated-sign recognition, and the section after dedicated-sign recognition. The proposed pipeline substantially reduced localization error after dedicated-sign recognition, compared with the GNSS/INS-only baseline. The dedicated sign also provided more stable correction than ordinary tunnel structures within the same registration pipeline. These results indicate that the proposed LiDAR-based pipeline can suppress localization drift in GNSS-degraded sections. Full article

Purpose-aware AI systems are increasingly deployed in safety-critical, multi-agent, and human-facing environments, where they must transform heterogeneous data into timely, explainable, and goal-aligned decisions under uncertainty. Existing architectures often couple perception, reasoning, communication, and security only at the pipeline level. This creates a research gap in unified semantic transformation, purpose-oriented judgment, bounded imperfection handling, and semantic self-protection. To address this gap, this paper proposes a DIKWP+BUG semantic–cognitive reference architecture for artificial-consciousness-oriented computing, without claiming definitive artificial consciousness. The architecture represents cognition through the Data–Information–Knowledge–Wisdom–Purpose (DIKWP) model and uses BUG theory to model bounded approximation, incomplete evidence, and confidence miscalibration in cross-dimensional reasoning. The model is mapped to an Artificial Consciousness Processing Unit (ACPU) reference substrate, an Artificial Consciousness Operating System (ACOS), a DIKWP semantic communication subsystem, and a concept–semantic fused security subsystem. The components are implemented through runtime emulation and evaluated in smart-city governance, autonomous-driving, and medical-triage simulations. Compared with selected baselines, the prototype increased cognitive throughput from $4.5\mathrm{k}$ to $7.8\mathrm{k}$ logged events, reduced perception–action latency from $340\mathrm{ms}$ to $120\mathrm{ms}$, reduced CPU utilization from $95\%$ to $68\%$, lowered smart-city congestion duration by $30\%$, improved emergency response time by approximately $40\%$, achieved 0 collisions versus approximately $2/10$ baseline IoV runs, and improved medical-triage accuracy from $85\%$ to $92\%$. These online-runtime results provide initial feasibility evidence under controlled simulation conditions; they do not include offline model-preparation costs and therefore should not be interpreted as end-to-end lifecycle speedups. Matched-compute ablation, statistical benchmarking, hardware prototyping, and real-world validation remain future work. Full article

Ovarian cancer is a gynecological cancer, which, if metastasized and not detected early, can cause death among women. Therefore, accurate prediction of drug responses to ovarian cancer is needed. A gynecological pathologist inspects abnormality in tissues and provides a report for patients; however, this diagnostic process (1) is difficult to undertake; (2) requires experience; and (3) is time-consuming. Moreover, existing tools are imperfect. Hence, we present a computational pipeline to improve predictions of drug response pertaining to ovarian cancer. First, we downloaded digital pathology images pertaining to ovarian responses to bevacizumab from the Cancer Imaging Archive Repository. We employed a histogram of oriented gradients for images, constructed feature vectors, and used Fisher’s linear discriminant analysis to alter data representations through dimensionality reduction. This reduced-dimensionality data was used for regression analysis, employing support vector regression coupled with various kernels and calculating the area under the ROC curve (AUC). Experimental results were validated using transformer-based models (ViT and Swin) and other deep learning (DL) models (VGG16, ResNet50, InceptionV3, MobileNetV2, and EfficientNetB6). Our approach using a radial kernel (named SVRD + R) improved AUC performance by 17% compared to the best-performing transformer-based model (ViT). Likewise, AUC performance improved by 14.9% when compared against the best DL-based model (MobileNetV2). These results demonstrate feasibility, showing that induced models via the presented AI-based pipeline can lead to superior performance when investigating prediction problems pertaining to gynecologic cancer studies. Full article

The invasive tomato leafminer, Tuta absoluta, poses a severe global threat to solanaceous crops, necessitating sustainable biocontrol solutions. Through systematic bioprospecting across several Moroccan soils, we constructed a novel library of indigenous fungal isolates using complementary Tenebrio molitor baiting and selective media methods. High-throughput phenotyping identified 49 highly pathogenic isolates, which were characterized for conidial production, thermotolerance, and virulence against T. absoluta. We discovered two lead isolates, Beauveria bassiana UCA-350 and Metarhizium robertsii UCA-329, that demonstrated superior virulence, reducing median survival time and achieving lower LC₅₀ values than most commercial reference strains. Notably, virulence was positively correlated with in vitro conidial yield, revealing a key trait linkage for strain selection. Furthermore, genus-level divergence in thermotolerance was observed, with Beauveria isolates exhibiting significantly higher heat resilience. Our integrated multi-trait screening pipeline not only delivers two potent, regionally sourced biocontrol candidates but also establishes a phenotypic selection framework that prioritizes both efficacy and production scalability, advancing the rational development of next-generation mycoinsecticides. Full article

Wheat is a major staple crop, and storage mold growth poses a severe threat to grain safety and quality stability. Natural mold development in stored wheat exhibits subtle, localized, and highly heterogeneous characteristics. Existing unimodal methods and global fusion approaches generally suffer from insufficient local feature sensitivity, hindering fine-grained mold severity grading. To address this limitation, we propose a Mask-Guided Fine-Grained Fusion Network, a weakly supervised framework based on local RGB–HSI fusion. This framework employs a dynamic parallel A/B experimental design to construct time-matched proxy labels via weakly supervised learning. A standardized preprocessing pipeline including single-kernel extraction, foreground segmentation, and cross-modal registration is established to resolve RGB–HSI spatial misalignment, ensuring physical-level spatial consistency of multimodal features. The model incorporates a Foreground-Aware Spectral Recalibration (FASR) module to suppress background noise, a Mask-Guided Dilated Cross-modal Local Attention (MDCLA) mechanism to establish fine-grained local mappings between RGB visual phenotypes and hyperspectral responses, and a sample-level adaptive fusion strategy to dynamically weight features by modal reliability, enhancing representation of complex samples across all mold stages. Experiments show that the Mask-Guided Fine-Grained Fusion Network achieves 0.9689 classification accuracy, 0.9698 Macro-F1 score, and 0.0593 Mean Absolute Error (MAE), significantly outperforming state-of-the-art unimodal deep models and global attention fusion baselines. This work provides a proof-of-principle framework for fine-grained non-destructive mold risk assessment in stored wheat. Full article

Accurate road-event detection and timely alert message dissemination are essential for the safety of connected and automated vehicles. In many scenarios, alert messages must reach not only nearby vehicles but also remote stakeholders, such as traffic management centers, cloud services, and infrastructure operators. This requirement motivates the adoption of cellular-based communication technologies in addition to short-range vehicle-to-everything (V2X) communications for data dissemination. In this work, we investigate vehicle-to-network-to-everything (V2N2X) communications for the dissemination of alert messages generated after the on-board detection of hazardous road events through machine learning (ML) algorithms. Although V2N2X connectivity is well suited for extending data dissemination beyond the local vehicular environment, its capability to guarantee prompt message delivery under strict latency constraints remains an open challenge, particularly when ML inference is integrated into the end-to-end processing pipeline. To address this issue, we develop and experimentally evaluate a proof-of-concept (PoC) platform that combines real-time road-event detection with relevant message dissemination towards both nearby and remote recipients. The proposed framework leverages 5G connectivity and publish/subscribe messaging protocols. The experimental results showcase that dissemination latency is highly influenced by both the adopted type of 5G deployment (private versus commercial networks) and the load conditions at the message broker. Full article

Reliable fault diagnosis of rotating machinery is critical for averting serious failures in modern industrial systems. While data-driven deep learning has advanced condition monitoring, its success is fundamentally predicated on the availability of independent and identically distributed (I.I.D.) datasets. In realistic operational environments, machinery frequently experiences massive domain shifts induced by varying rotational speeds. Concurrently, acquiring high-fidelity fault instances is limited compared to abundant healthy baseline data, often resulting in a long-tailed distribution. Under such data-starved conditions, conventional few-shot domain adaptation (FSDA) methodologies often may be affected by distributional erasure; global alignment objectives are mainly driven by the healthy majority, causing sparse fault signatures to be erroneously absorbed as noise and leading to severe diagnostic performance degradation. To address this setting, this study develops a physics-guided dual-stream fusion framework for extreme few-shot cross-domain fault diagnosis. The method does not treat the Laplace wavelet, STFT, CNNs, or AdaBN as newly introduced techniques. Instead, it integrates these components into a unified diagnostic pipeline designed for long-tailed target support sets under large speed shifts. A learnable Laplace wavelet convolution is used in the temporal branch to emphasize transient impact responses, while STFT spectrograms provide a complementary time-frequency representation for the two-dimensional branch. The two feature streams are then fused for target fault classification. For domain adaptation, a Strict AdaBN strategy is applied using only the target support set, rather than the target test data or a large unlabeled target pool. Under the evaluated 50 healthy + 12 fault support condition, the healthy samples provide target-domain operating-background statistics for BN recalibration, while the limited fault samples are used for supervised classifier adjustment. Experiments on the HUSTbearing and Torino DIRG datasets show that the proposed integrated framework achieves stable performance under the evaluated few-shot cross-speed settings. These results suggest that combining physics-guided Laplace convolution, time-frequency representations, and support-set-restricted BN recalibration can be useful for bearing fault diagnosis when target fault samples are limited. Full article

Grape caliber distributions are critical for packing, grading, yield estimation, and post-harvest logistics. However, estimating reliable caliber histograms from single images remains challenging due to occlusion and dense bunch structure. This work presents a two-stage monocular pipeline that integrates instance segmentation, geometry-aware representations, residual quantity correction, and structured histogram prediction. In the first stage, a YOLO-based model detects grape instances and a calibration object, enabling the construction of geometry-aware auxiliary channels and a segmentation-derived counting prior. In the second stage, these representations are used to estimate total grape count and caliber distributions. Results show that RGBDT consistently outperforms RGB, indicating that geometry-aware cues improve both histogram fidelity and counting accuracy. The framework achieves stable performance under realistic conditions while maintaining low runtime, supporting practical deployment in agricultural environments. Full article

With the expansion of ammonia energy applications, long-distance liquid ammonia pipelines are expected to support large-scale cross-regional ammonia transport. In the liquid ammonia pipeline commissioning process, gaseous ammonia purging involves ammonia–nitrogen mixing and possible liquefaction, while liquid ammonia injection may induce flashing and severe local cooling, all of which can affect commissioning safety. To characterize these thermodynamic phenomena, a transient gas–liquid two-phase flow model was established and validated using OLGA 2022.1.0 software for simulating the long-distance liquid ammonia pipeline commissioning. The model adopts the cross-sectionally averaged one-dimensional approach. A volume-corrected Soave–Redlich–Kwong (SRK) equation of state for ammonia was adapted, validated, and used to generate OLGA-compatible thermodynamic property tables. The results show that, during gaseous ammonia purging, a higher flowrate shortens the displacement time by accelerating nitrogen removal, and this effect is more pronounced at higher ambient temperatures due to enhanced molecular diffusion. Along the pipeline, pressure gradually decreases from frictional resistance, with a steeper drop near the outlet caused by gas acceleration, and temperature gradually approaches ambient through heat exchange with the pipe wall and surrounding soil. A high gaseous ammonia flowrate can cause partial liquefaction, regasification, and temperature fluctuations. During liquid ammonia injection, local condensation and slight liquid accumulation occur before the liquid front arrives, and the low-temperature region moves with the liquid front. The liquid ammonia mass flowrate has the strongest influence on the injection process, as it reduces the completion time but increases the outlet temperature, outlet pressure, and the low-temperature risk downstream of the valve. Therefore, it should be controlled within an appropriate range to balance efficiency and low-temperature safety risks. This work provides a rapid and efficient prediction model for key thermo-hydraulic parameters during liquid ammonia pipeline commissioning, and the overall analyses offer insights for on-site process design and safety control. Full article

In the field of stereo depth sensing, modern research predominantly prioritizes accuracy, yet inference speed remains a critical bottleneck for practical, real-time applications on resource-constrained platforms. Existing acceleration approaches often rely on lighter network architectures or runtime-specific optimizations, which may require architectural redesign, platform-specific tuning, or accuracy trade-offs. However, a common inefficiency remains in many stereo pipelines: feature extraction is typically performed using two separate forward passes, one for the left image and one for the right, even though both passes use the same network weights. We address this redundancy by concatenating the left and right images into a single combined tensor, enabling feature extraction in one batched pass while preserving the original network architecture. By reducing feature extraction time by up to 48.4%, our results demonstrate that this method accelerates the overall inference rate by 10% to 39% on average on Nvidia V100 and up to 28.4% on edge device, depending on the model architecture. This speedup is achieved at the expense of only a moderate increase in runtime memory consumption, while retaining the original accuracy. Because the method does not alter the core stereo network, it can be applied as a plug-and-play enhancement to both existing and newly developed stereo matching models. Full article

Small and medium enterprises routinely face a paradox in financial monitoring: their accounting documents exist, but the cost of converting heterogeneous PDFs into timely financial signals is prohibitive without dedicated analytical staff or specialized software. This paper presents a two-layer artifact, designed under Design Science Research, that bridges this gap using only public-web large language models (LLMs) and a parsimonious multi-criteria decision routine. Layer 1 implements a structured LLM-driven workflow that extracts account–value pairs from annual tax balance sheets without code, APIs, or fine-tuning. Layer 2 reconstructs auditable accounting aggregates and ranks yearly financial condition through TOPSIS with min–max normalization—a deliberate replacement for classical vector normalization, which fails when profitability indicators are negative, as routinely occurs in distress years. To avoid size effects and algebraic redundancy, the decision matrix uses only three criteria spanning liquidity, profitability, and solvency. The artifact is demonstrated in a four-year case study of an anonymized construction SME (2021–2024), with accountant-verified document-level match rates of 0.810, 0.998, 0.950, and 0.909. Equal weighting is the only weighting configuration used; a supplementary entropy-based dispersion diagnostic yields the same ordinal ranking—2024 > 2023 > 2021 > 2022—and 10,000 Monte Carlo replications, with uncertainty injected at the reconstructed-aggregate level, confirm that the extreme ranks are invariant across all runs. The contribution is methodological and practical: a transparent, low-infrastructure pipeline that brings first-pass financial screening within reach of SMEs operating under severe data and budget constraints. Full article

Supplier selection in healthcare is a complex multi-criteria decision-making (MCDM) challenge requiring a balance of sustainability, resilience, and operational efficiency. Traditional methods struggle with scalability and subjectivity when applied to large administrative datasets. This study introduces a transparent hybrid Machine Learning–MCDM (ML–MCDM) framework, validated using a U.S. Medicare dataset of 661 suppliers. The framework integrates eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) for criterion prioritization, the Full Consistency Method (FUCOM) for mathematically consistent weighting, and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) for final ranking. As the dataset lacks direct sustainability metrics, seven indicators were synthetically generated; thus, the results serve as proof-of-concept demonstration of the framework’s architecture. Specifically, XGBoost–SHAP is trained to predict a synthetically constructed Overall Performance Score (OPS), meaning that the resulting feature importance output constitutes an algorithmic consistency check—confirming that the pipeline correctly recovers importance signals deliberately embedded in the training target. For interpretability, suppliers were segmented into five performance profiles via K-Means: Strategic Partners (17.7%), Green Leaders (18.6%), Reliable Emergency Suppliers (18.2%), Balanced Performers (20.4%), and Developing Suppliers (25.1%). Carbon Footprint Score (0.408) and Emergency Response Capability (0.316) achieved the highest feature importance. FUCOM-derived weights prioritized On-Time Delivery Rate (0.272), Carbon Footprint Score (0.222), and Emergency Response Capability (0.220). The top supplier attained a TOPSIS closeness coefficient of 0.800, showing strong discrimination. Sensitivity analysis across four scenarios confirmed ranking robustness, maintaining Spearman correlations ρ ≥ 0.977. This ML–FUCOM–TOPSIS approach provides an auditable, scalable, and policy-relevant decision-support tool, enabling procurement managers to navigate high-dimensional data while ensuring operational continuity and environmental responsibility in healthcare supply chains. Full article

Burrowing crayfish are among the most important keystone species in North American ecosystems, yet they remain poorly understood. The Meadow River Mudbug (Cambarus pauleyi), native to West Virginia, was only recently described and is known from a very limited range in the Central Appalachians. During planning for an interstate pipeline, two large populations of C. pauleyi were found in the proposed right-of-way. As part of environmental compliance, salvage, relocation, and monitoring for the species were conducted from 2018 to 2024. All C. pauleyi were moved to the Meadow River Wildlife Management Area, where artificial starter burrows were created, and exclusion baskets were placed over them to prevent predation, the process of which is described herein. Monitoring showed a two-month survival rate of 74.0% to 85.5%. These results are promising for the future restoration of burrowing crayfish and other species that rely on crayfish burrows for habitat. Full article