Search Results (21,766)

Laboratory and industrial tests were conducted to study the impact of grinding media material on key indicators such as grinding product particle size, sodium cyanide consumption, gold recovery rate, unit power consumption, and ball consumption. Laboratory test results indicate that the reasonable mixing of ceramic and steel balls can achieve an increase of more than 2.8% in the fineness of the grinding product (−0.038 mm), an increase of 0.3% in the gold recovery rate, and a decrease of 1.3 kg/t in the consumption of sodium cyanide. Industrial trial studies indicate that, compared to the traditional steel ball scheme, using a ceramic ball to steel ball mass ratio of 3:1 under conditions of processing 50,000 tons of gold concentrate annually can save a total of 1.31 million yuan in annual ball consumption, electricity consumption, and cyanide consumption costs. Additionally, the improved recovery rate generates an additional economic benefit of 3.63 million yuan, resulting in an annual comprehensive economic benefit increase of 4.94 million yuan. In summary, in gold cyanide leaching grinding, the mixture ratio between ceramic balls and steel balls demonstrates significant potential for energy conservation, cost reduction, and efficiency enhancement, providing a theoretical basis and technical support for subsequent process optimization and green gold extraction. Full article

This study addresses the problem of anomaly detection in water treatment systems by proposing a hybrid VAE–LSTM model with a combined loss function that integrates reconstruction and prediction errors. Following the signal flow of wastewater treatment systems, data acquisition, transmission, and cyberattack scenarios were simulated, and a dual-dimensional learning framework of “feature space—temporal space” was designed: the VAE learns latent data distributions and computes reconstruction errors, while the LSTM models temporal dependencies and computes prediction errors. Anomaly decisions are made through feature extraction and weighted scoring. Experimental comparisons show that the proposed fusion model achieves an accuracy of approximately 0.99 and an F1-Score of about 0.75, significantly outperforming single models such as Isolation Forest and One-Class SVM. It can accurately identify attack anomalies in devices such as the LIT101 sensor and MV101 actuator, e.g., water tank overflow and state transitions, with reconstruction errors primarily beneath 0.08 ensuring detection reliability. In terms of time efficiency, Isolation Forest is suitable for real-time preliminary screening, while VAE-LSTM adapts to high-precision detection scenarios with an “offline training (423 s) + online detection (1.39 s)” mode. This model provides a practical solution for intelligent monitoring of industrial water treatment systems. Future research will focus on model lightweighting, enhanced data generalization, and integration with edge computing to improve system applicability and robustness. The proposed approach breaks through the limitations of traditional single models, demonstrating superior performance in detection accuracy and scenario adaptability. It offers technical support for improving the operational efficiency and security of water treatment systems and serves as a paradigm reference for anomaly detection in similar industrial systems. Full article

Egg weight monitoring provides critical data for calculating the feed-to-egg ratio, and improving poultry farming efficiency. Installing a computer vision monitoring system in egg collection systems enables efficient and low-cost automated egg weight measurement. However, its accuracy is compromised by egg clustering during transportation and low-contrast edges, which limits the widespread adoption of such methods. To address this, we propose an egg measurement method based on a computer vision and multi-feature extraction and regression approach. The proposed pipeline integrates two artificial neural networks: Central differential-EfficientViT YOLO (CEV-YOLO) and Egg Weight Measurement Network (EWM-Net). CEV-YOLO is an enhanced version of YOLOv11, incorporating central differential convolution (CDC) and efficient Vision Transformer (EfficientViT), enabling accurate pixel-level egg segmentation in the presence of occlusions and low-contrast edges. EWM-Net is a custom-designed neural network that utilizes the segmented egg masks to perform advanced feature extraction and precise weight estimation. Experimental results show that CEV-YOLO outperforms other YOLO-based models in egg segmentation, with a precision of 98.9%, a recall of 97.5%, and an Average Precision (AP) at an Intersection over Union (IoU) threshold of 0.9 (AP90) of 89.8%. EWM-Net achieves a mean absolute error (MAE) of 0.88 g and an R² of 0.926 in egg weight measurement, outperforming six mainstream regression models. This study provides a practical and automated solution for precise egg weight measurement in practical production scenarios, which is expected to improve the accuracy and efficiency of feed-to-egg ratio measurement in laying hen farms. Full article

The daily behavioral patterns of giraffes reflect their health status and well-being. Behaviors such as licking, walking, standing, and eating are not only essential components of giraffes’ routine activities but also serve as potential indicators of their mental and physiological conditions. This is particularly relevant in captive environments such as zoos, where certain repetitive behaviors may signal underlying well-being concerns. Therefore, developing an efficient and accurate automated behavior detection system is of great importance for scientific management and welfare improvement. This study proposes a multi-behavior automatic detection method for giraffes based on YOLO11-Pose and the spatial-adaptive two-stream network (SATSN). Firstly, YOLO11-Pose is employed to detect giraffes and estimate the keypoints of their mouths. Observation-Centric SORT (OC-SORT) is then used to track individual giraffes across frames, ensuring temporal identity consistency based on the keypoint positions estimated by YOLO11-Pose. In the SATSN, we propose a region-of-interest extraction strategy for licking behavior to extract local motion features and perform daily behavior classification. In this network, the original 3D ResNet backbone in the slow pathway is replaced with a video transformer encoder to enhance global spatiotemporal modeling, while a Temporal Attention (TA) module is embedded in the fast pathway to improve the representation of fast motion features. To validate the effectiveness of the proposed method, a giraffe behavior dataset consisting of 420 video clips (10 s per clip) was constructed, with 336 clips used for training and 84 for validation. Experimental results show that for the detection tasks of licking, walking, standing, and eating behaviors, the proposed method achieves a mean average precision (mAP) of 93.99%. This demonstrates the strong detection performance and generalization capability of the approach, providing robust support for automated multi-behavior detection and well-being assessment of giraffes. It also lays a technical foundation for building intelligent behavioral monitoring systems in zoos. Full article

This study investigated the isolation and formulation of a bacterial conditioner as a biostimulant for Triticum durum (durum wheat) under salinity stress. An Algerian alkaline–saline soil was sampled, characterized for its physical and chemical characteristics and its culturable and total microbial community (16S rRNA gene metabarcoding). Three bacterial strains showing high 16S rRNA gene similarity to Pseudomonas putida, Bacillus proteolyticus, and Niallia nealsonii were selected for their plant growth-promoting (PGP) traits under different salinity levels, including phosphate solubilisation (194 µg mL⁻¹), hormone production (e.g., gibberellin up to 56 µg mL⁻¹), and good levels of hydrocyanic acid, ammonia, and siderophores. N. nealsonii maintained high indole production under saline conditions, while B. proteolyticus displayed enhanced indole synthesis at higher salt concentrations. Siderophore production remained stable for P. putida and N. nealsonii, whereas for B. proteolyticus a complete inhibition was registered in the presence of salt stress. The consortium density and application were tested under controlled conditions using Medicago sativa as a model plant. The effective biostimulant formulation was tested on Triticum durum under greenhouse experiments. Bacterial inoculation significantly improved plant growth in the presence of salt stress. Root length increased by 91% at 250 mM NaCl. Shoot length was enhanced by 112% at 500 mM NaCl. Total chlorophyll content increased by 208% at 250 mM NaCl. The chlorophyll a/b ratio increased by 117% at 500 mM. Also, reduced amounts of plant extracts were necessary to scavenge 50% of radicals (−22% at 250 mM compared to the 0 mM control). Proline content increased by 20% at both 250 mM and 500 mM NaCl. These results demonstrate the potential of beneficial bacteria as biostimulants to mitigate salt stress and enhance plant yield in saline soils. Full article

Cracks are vital warning signs to reflect the structural deterioration in concrete constructions and buildings. However, their diverse and complex morphologies make accurate segmentation challenging. Deep learning-based methods effectively alleviate the low accuracy of traditional methods, while they are limited by the receptive field and computational efficiency, resulting in suboptimal performance. To address this challenging problem, we propose a novel framework termed High-frequency Refined Mamba with Snake Perception Attention module (HFR-Mamba) for more accurate crack segmentation. HFR-Mamba effectively refines Mamba’s global dependency modeling by extracting frequency domain features and the attention mechanism. Specifically, HFR-Mamba consists of the High-frequency Refined Mamba encoder, the Snake Perception Attention (SPA) module, and the Multi-scale Feature Fusion decoder. The encoder uses Discrete Wavelet Transform (DWT) to extract high-frequency texture features and utilizes the Refined Visual State Space (RVSS) module to fuse spatial features and high-frequency components, which effectively refines the global modeling process of Mamba. The SPA module integrates snake convolutions with different directions to filter background noise from the encoder and highlight cracks for the decoder. For the decoder, it adopts a multi-scale feature fusion strategy and a strongly supervised approach to enhance decoding performance. Extensive experiments show HFR-Mamba achieves state-of-the-art performance in IoU, DSC, Recall, Accuracy, and Precision indicators with fewer parameters, validating its effectiveness in crack segmentation. Full article

The Denoising Wavelet Transform Convolutional Long Short-Term Memory Network (DWTConvLSTM) is a novel ionospheric total electron content (TEC) spatiotemporal prediction model proposed in 2025 that can simultaneously consider high-frequency and low-frequency features while suppressing noise. However, it also has flaws as it only considers unidirectional temporal features in spatiotemporal prediction. To address this issue, this paper adopts a bidirectional structure and designs a bidirectional DWTConvLSTM model that can simultaneously extract bidirectional spatiotemporal features from TEC maps. Furthermore, we integrate a lightweight attention mechanism called Convolutional Additive Self-Attention (CASA) to enhance important features and attenuate unimportant ones. The final model was named CASA-BiDWTConvLSTM. We validated the effectiveness of each improvement through ablation experiments. Then, a comprehensive comparison was performed on the 11-year Global Ionospheric Maps (GIMs) dataset, involving the proposed CASA-BiDWTConvLSTM model and several other state-of-the-art models such as C1PG, ConvGRU, ConvLSTM, and PredRNN. In this experiment, the dataset was partitioned into 7 years for training, 2 years for validation, and the final 2 years for testing. The experimental results indicate that the RMSE of CASA-BiDWTConvLSTM is lower than those of C1PG, ConvGRU, ConvLSTM, and PredRNN. Specifically, the decreases in RMSE during high solar activity years are 24.84%, 16.57%, 13.50%, and 10.29%, respectively, while the decreases during low solar activity years are 26.11%, 16.83%, 11.68%, and 7.04%, respectively. In addition, this article also verified the effectiveness of CASA-BiDWTConvLSTM from spatial and temporal perspectives, as well as on four geomagnetic storms. Full article

This paper presents an integrated downhole risk prevention and control system designed to enhance safety, efficiency and sustainability in deep-well drilling operations. The system incorporates advanced measurement processing, risk evaluation, and intelligent data transmission technologies for real-time monitoring of nine key drilling parameters, such as downhole drilling pressure, bending moment, and torque, etc. Bench tests and field trials demonstrated the system’s reliability in accurately capturing and transmitting data under high-pressure, high-temperature conditions. For instance, it successfully monitored bottom-hole pressure up to 61.4 MPa and temperature to 120.8 °C, allowing for early detection of abnormal events such as pressure kicks and torsional stick-slip. The system was laboratory-tested to withstand bottom-hole pressures up to 61.4 MPa and temperatures of 120.8 °C. During field trials, the tool operated safely under actual downhole conditions of approximately 59.2 MPa and 115 °C, which are within its rated limits. The system also facilitated automated controlled actions, including mud weight and pump rate control, to prevent incidents. These results underscore the system’s potential to significantly improve real-time and intelligent process control, minimize operational risks, and advancing the sustainability of drilling practices. The approach marks a step forward in intelligent drilling technologies, supporting proactive decision-making in energy extraction. Future work will extend this system to ultra-deep and high-temperature wells while integrating advanced AI-based analytics for further optimization. Full article

This systematic literature review addresses the critical challenge of ensuring robustness and adaptability in AI-based machine health monitoring (MHM) systems. While the field has seen a surge in research, a significant gap exists in understanding how to effectively manage data scarcity, unknown fault types, and the integration of diverse data streams for real-world industrial applications. The problem is magnified by the rarity of failure events, which leads to imbalanced datasets and hampers the generalizability of predictive models. To synthesize the current state of research and identify key solutions, we followed a rigorous, modified PRISMA methodology. A comprehensive search across Scopus, IEEE Xplore, Web of Science, and Litmaps initially yielded 3235 records. After a multi-stage screening process, a final corpus of 85 peer-reviewed studies was selected. Data were extracted and synthesized based on a thematic framework of 13 core research questions. A bibliometric analysis was also conducted to quantify publication trends and research focus areas. The analysis reveals a rapid increase in research, with publications growing from 1 in 2018 to 35 in 2025. Key findings highlight the adoption of transfer learning and generative AI to combat data scarcity, with multimodal data fusion emerging as a crucial strategy for enhancing diagnostic accuracy. The most active research themes were found to be Predictive Maintenance and Edge Computing, with 12 and 10 references, respectively, while critical areas like standardization remain under-explored. Overall, this review shows that AI benefits machine health monitoring but still faces challenges in reproducibility, benchmarking, and large-scale validation. Its main limitation is the focus on English peer-reviewed studies, excluding industry reports and non-English work. Future research should develop standardized datasets, energy-efficient edge AI, and socio-technical frameworks for trust and transparency. The study offers a structured overview, a roadmap for future work, and underscores the importance of AI in Industry 4.0. Full article

Background/Objectives: Diabetic nephropathy (DN) is a major complication of diabetes and a leading cause of end-stage renal disease, a condition associated with high mortality risks. Recently, supplementation with probiotics and postbiotics has been attracting attention. Especially, metabolites of natural products bioconverted by beneficial bacteria have emerged as a novel therapeutic intervention for metabolic diseases, including diabetes, due to the enhanced bioavailability of their metabolites. This study investigated the alleviating effects of metabolites derived from guava leaf extract bioconverted by Limosilactobacillus fermentum (GBL) on renal inflammation in type 2 diabetic mice. Methods: For this purpose, diabetes was induced in male C57BL/6J mice by a high-fat diet and streptozotocin injection (80 mg/kg BW) twice. Subsequently, mice with fasting blood glucose levels higher than 300 mg/dL were administered metabolites of L. fermentum (LF) (50 mg/kg BW/day) or guava leaf extract bioconverted by L. fermentum (GBL) (50 mg/kg BW/day) by oral gavage for 15 weeks. Results: GBL demonstrated potential in alleviating hyperglycemia-induced DN in diabetic mice. It markedly improved hyperglycemia, glucose tolerance, and morphological alterations, which might stem from activation of key regulators of energy metabolism. GBL uniquely reduced advanced glycation end products (AGEs) and suppressed nucleotide-binding oligomerization domain-like receptor family pyrin domain-containing 3 (NLRP3) inflammasome and nuclear factor kappa-light-chain-enhancer of activated B cells (NF-κB)-driven inflammatory pathways, which significantly alleviated oxidative stress and apoptosis. Conclusions: This highlights the distinct therapeutic efficacy of GBL in addressing DN, primarily through its effects on renal inflammation. Taken together, GBL can be used as a promising nutraceutical to mitigate hyperglycemia and its associated renal inflammation, thereby alleviating the progression of DN. Full article

Background/Objectives: Gastrointestinal nematode infections represent a major constraint to sheep production globally, with widespread drug resistance requiring alternative control strategies. Methods: This systematic review combined genome-wide association study findings to understand the genetic basis underlying parasite resistance traits in sheep. Following PRISMA guidelines, we identified 22 studies including 28,033 samples from 32 breeds across 11 countries, extracting 1580 candidate genes associated with resistance traits, including fecal egg count, packed cell volume, and immunoglobulin levels. Gene prioritization analysis using ToppGene identified 75 high-confidence candidate genes. Results: Functional enrichment analysis revealed significant involvement of the JAK-STAT signaling pathway, inflammatory response processes, and immune-related biological functions. Protein–protein interaction network analysis identified nine key hub genes: TNF, STAT3, STAT5A, PDGFB, ADRB2, MAPT, ITGB3, SMO, and GH1. The JAK-STAT pathway emerged as particularly important, with multiple core genes involved in cytokine signaling and immune cell development. These findings demonstrate that parasite resistance involves complex interactions between inflammatory responses, immune signaling networks, and metabolic processes. Conclusions: This comprehensive genetic framework provides essential insights for developing genomic selection strategies and marker-assisted breeding programs to enhance natural parasite resistance in sheep, offering a sustainable approach to reducing drug dependence and improving animal welfare in global sheep production systems. Full article

This study reports on green-synthesized zinc oxide nanoparticles (ZnONPs), focusing on their physicochemical characterization, photocatalytic properties, and agricultural applications. Dynamic light scattering (DLS) analysis revealed a mean hydrodynamic diameter of 337.3 nm and a polydispersity index (PDI) of 0.400, indicating moderate polydispersity and nanoparticle aggregation, typical of biologically synthesized systems. High-resolution transmission electron microscopy (HR-TEM) showed predominantly spherical particles with an average diameter of ~28 nm, exhibiting slight agglomeration. Energy-dispersive X-ray spectroscopy (EDX) confirmed the elemental composition of zinc and oxygen, while X-ray diffraction (XRD) analysis identified a hexagonal wurtzite crystal structure with a dominant (002) plane and an average crystallite size of ~29 nm. Photoluminescence (PL) spectroscopy displayed a distinct near-band-edge emission at ~462 nm and a broad blue–green emission band (430–600 nm) with relatively low intensity. The ultraviolet–visible spectroscopy (UV–Vis) absorption spectrum of the synthesized ZnONPs exhibited a strong absorption peak at 372 nm, and the optical band gap was calculated as 2.67 eV using the Tauc method. Fourier-transform infrared spectroscopy (FTIR) analysis revealed both similarities and distinct differences to the pigeon extract, confirming the successful formation of nanoparticles. A prominent absorption band observed at 455 cm⁻¹ was assigned to Zn–O stretching vibrations. X-ray photoelectron spectroscopy (XPS) analysis showed that raw pigeon droppings contained no Zn signals, while their extract provided organic biomolecules for reduction and stabilization, and it confirmed Zn²⁺ species and Zn–O bonding in the synthesized ZnONPs. Photocatalytic degradation assays demonstrated the efficient removal of pollutants from sewage water, leading to significant reductions in total dissolved solids (TDS), chemical oxygen demand (COD), and total suspended solids (TSS). These results are consistent with reported values for ZnO-based photocatalytic systems, which achieve biochemical oxygen demand (BOD) levels below 2 mg/L and COD values around 11.8 mg/L. Subsequent reuse of treated water for irrigation yielded promising agronomic outcomes. Wheat and barley seeds exhibited 100% germination rates with ZnO NP-treated water, which were markedly higher than those obtained using chlorine-treated effluent (65–68%) and even the control (89–91%). After 21 days, root and shoot lengths under ZnO NP irrigation exceeded those of the control group by 30–50%, indicating enhanced seedling vigor. These findings demonstrate that biosynthesized ZnONPs represent a sustainable and multifunctional solution for wastewater remediation and agricultural enhancement, positioning them as a promising candidate for integration into green technologies that support sustainable urban development. Full article

Brain tumors are highly malignant diseases that severely threaten the nervous system and patients’ lives. MRI is a core technology for brain tumor diagnosis and treatment due to its high resolution and non-invasiveness. However, existing YOLO-based models face challenges in brain tumor MRI image detection and segmentation, such as insufficient multi-scale feature extraction and high computational resource consumption. This paper proposes an improved lightweight brain tumor detection and instance segmentation model named FALS-YOLO, based on YOLOv8n-Seg and integrating three key modules: FLRDown, AdaSimAM, and LSCSHN. FLRDown enhances multi-scale tumor perception, AdaSimAM suppresses noise and improves feature fusion, and LSCSHN achieves high-precision segmentation with reduced parameters and computational burden. Experiments on the tumor-otak dataset show that FALS-YOLO achieves Precision (B) of 0.892, Recall (B) of 0.858, mAP@0.5 (B) of 0.912 in detection, and Precision (M) of 0.899, Recall (M) of 0.863, mAP@0.5 (M) of 0.917 in segmentation, outperforming YOLOv5n-Seg, YOLOv8n-Seg, YOLOv9s-Seg, YOLOv10n-Seg and YOLOv11n-Seg. Compared with YOLOv8n-Seg, FALS-YOLO reduces parameters by 31.95%, computational amount by 20.00%, and model size by 32.31%. It provides an efficient, accurate and practical solution for the automatic detection and instance segmentation of brain tumors in resource-limited environments. Full article

The search for natural additives from underutilized halophytes and fruit by-products aligns with circular economy principles, addressing consumer demand for healthier and more sustainable alternatives to salt and synthetic antioxidants in foods. Salicornia ramosissima, a halophytic plant rich in minerals, and Malpighia emarginata (acerola), a fruit rich in bioactive compounds, were selected for their potential to enhance meat preservation while reducing reliance on conventional salt and chemical additives. This study evaluated the effects of replacing salt with S. ramosissima powder (1% and 2%) and adding acerola extract (0.3%) in Mertolenga D.O.P. beef hamburgers. Control, 1% salt, acerola, and salicornia formulations were analyzed over 10 days for the following: (1) microbial counts (mesophiles, psychrotrophics, Enterobacteriaceae, Pseudomonas spp., Brochothrix thermosphacta, lactic acid bacteria, fungi, Salmonella spp., and E. coli); (2) physicochemical parameters (pH, a_w, and CIE-Lab color); and (3) sensory attributes (odor, color, and freshness). Higher Salicornia concentrations negatively affected color (lower a* values) and sensory perception (darker appearance). Acerola extract improved color stability and delayed the development of off-odors, contributing to higher freshness scores throughout storage. No significant differences in microbial counts were observed between treatments. Overall, acerola and low-dose Salicornia showed potential as natural ingredients for meat preservation, with minimal impact on physicochemical and microbiological quality. These findings support the use of halophytes and fruit extracts in sustainable meat preservation strategies. Full article

Accurate prediction of food delivery time is crucial for enhancing operational efficiency and customer satisfaction in real-world logistics and intelligent dispatch systems. To address this challenge, this study proposes a novel symmetric optimization prediction framework, termed SymOpt-CNSVR. The framework is designed to leverage the strengths of both deep learning and statistical learning models in a complementary architecture. It employs a Convolutional Neural Network (CNN) to extract and assess the importance of multi-feature data. An Enhanced Superb Fairy-Wren Optimization Algorithm (ESFOA) is utilized to optimize the diverse hyperparameters of the CNN, forming an optimal adaptive feature extraction structure. The significant features identified by the CNN are then fed into a Support Vector Regression (SVR) model, whose hyperparameters are optimized using Bayesian optimization, for final prediction. This combination reduces the overall parameter search time and incorporates probabilistic reasoning. Extensive experimental evaluations demonstrate the superior performance of the proposed SymOpt-CNSVR model. It achieves outstanding results with an R² of 0.9269, MAE of 3.0582, RMSE of 4.1947, and MSLE of 0.1114, outperforming a range of benchmark and state-of-the-art models. Specifically, the MAE was reduced from 4.713 (KNN) and 5.2676 (BiLSTM) to 3.0582, and the RMSE decreased from 6.9073 (KNN) and 6.9194 (BiLSTM) to 4.1947. The results confirm the framework’s powerful capability and robustness in handling high-dimensional delivery time prediction tasks. Full article