Search Results (83)

Time-lapse microscopy of mesenchymal stem cell (MSC) cultures allows for the quantitative observation of their self-renewal, proliferation, and differentiation. However, the rigorous comparison of two conditions, baseline (A) versus perturbation (B) (the addition of molecular factors, environmental shifts, genetic modification, etc.), remains difficult because morphology, division timing, and migratory behavior are highly heterogeneous at the single-cell scale. MSCs can be used as an in vitro model to study cell morphology and kinetics in order to assess the effect of, for example, gene therapy and prime editing in the near future. By combining static, frame-wise morphology with dynamic descriptors, we can obtain weight profiles that highlight which morphological and behavioral dimensions drive divergence. In this study, we present A/B Cells Policy: a modular, open-source Python package implementing a robust cell tracking pipeline. It integrates a YOLO-based architecture as a two-stage assignment framework with fallback and recovery passes, re-identification of lost tracks, and lineage reconstruction. The framework links descriptive statistics to a transferable system, opening up avenues for regenerative medicine, pharmacology, and early translational pipelines. It does this by providing an interpretable, measurement-based bridge between in vitro imaging and in silico intervention strategy planning. Full article

The Solar Agro Savior (SAS) is an innovative solution that is assisted by drones for the sustainable utilization of water and plant disease observation in the agriculture sector. This system integrates an alerting mechanism for humidity, moisture, and temperature variations, which affect the plants’ health and optimization in water utilization, which enhances plant yield productivity. A significant feature of the system is the efficient monitoring system in a larger region through drones’ high-resolution cameras, which enables real-time, efficient response and alerting for environmental fluctuations to the authorities. The machine learning algorithm, particularly recurrent neural networks, which is a pioneer with agriculture and pest control, is incorporated for intelligent monitoring systems. The proposed system incorporates a specialized form of a recurrent neural network, Long Short-Term Memory (LSTM), which effectively addresses the vanishing gradient problem. It also utilizes an attention-based mechanism that enables the model to assign meaningful weights to the most important parts of the data sequence. This algorithm not only enhances water utilization efficiency but also boosts plant yield and strengthens pest control mechanisms. This system also provides sustainability through the re-utilization of water and the elimination of electric energy through solar panel systems for powering the inbuilt irrigation system. A comparative analysis of variant algorithms in the agriculture sector with a machine learning approach was also illustrated, and the proposed system yielded 99% yield accuracy, a 97.8% precision value, 98.4% recall, and a 98.4% F1 score value. By encompassing solar irrigation and artificial intelligence-driven analysis, the proposed algorithm, Solar Argo Savior, established a sustainable framework in the latest agricultural sectors and promoted sustainability to protect our environment and community. Full article

The implementation of lean drilling and completion design techniques is a pivotal strategy for the petroleum and natural gas industry to achieve green, low-carbon, and intelligent transformation and innovation. These techniques significantly enhance oil and gas recovery rates. In shale gas development, the shale brittleness index plays a crucial role in evaluating fracturing ability during hydraulic fracturing. Indoor experiments on Gulong shale oil were conducted under a confining pressure of 30 MPa. Based on Rickman’s brittleness evaluation method, this study performed numerical simulations of triaxial compression tests on shale using the finite discrete element method. The fractal dimensions of the fractures formed during shale fragmentation were calculated using the box-counting method. Utilizing the obtained data, a multiple linear regression equation was established with elastic modulus and Poisson’s ratio as the primary variables, and the coefficients were normalized to propose a new brittleness evaluation method. The research findings indicate that the finite discrete element method can effectively simulate the rock fragmentation process, and the established multiple linear regression equation demonstrates high reliability. The weights reassigned for brittleness evaluation based on Rickman’s method are as follows: the coefficient for elastic modulus is 0.43, and the coefficient for Poisson’s ratio is 0.57. Furthermore, the new brittleness evaluation method exhibits a stronger correlation with the brittleness mineral index. The fractal characteristics of crack networks and the relationship between symmetry response and mechanical parameters offer a new theoretical foundation for brittle weight distribution. Additionally, the scale symmetry characteristics inherent in fractal dimensions can serve as a significant indicator for assessing complex crack morphology. Full article

Sonar images possess characteristics such as low resolution, high noise, and blurred edges. Utilizing CNNs would lead to problems such as inadequate target recognition accuracy. Moreover, due to their larger sizes and higher computational requirements, existing CNNs face deployment issues in embedded devices. Therefore, we propose a sonar image recognition algorithm optimized for the lightweight algorithm, MobileViT, by analyzing the features of sonar images. Firstly, the MobileViT block is modified by adding and redesigning the jump connection layer to capture more important features of sonar images. Secondly, the original 1 × 1 convolution is replaced with the redesigned multi-scale convolution Res2Net in the MV2 module to enhance the ability of the algorithm to learn global and local features. Finally, the IB loss is applied to address the imbalance of sample categories in the sonar dataset, assigning different weights to the samples to improve the performance of the network. The experimental results show that several proposed improvements have improved the accuracy of sonar image recognition to varying degrees. At the same time, the proposed algorithm is lightweight and can be deploy on embedded devices. Full article

The data-driven intelligent fault diagnosis method has shown great potential in improving the safety and reliability of train operation. However, the noise interference and multi-scale signal characteristics generated by the train transmission system under non-stationary conditions make it difficult for the network model to effectively learn fault features, resulting in a decrease in the accuracy and robustness of the network. This results in the requirements of train fault diagnosis tasks not being met. Therefore, a novel parallel multi-scale attention residual neural network (PMA-ResNet) for a train transmission system is proposed in this paper. Firstly, multi-scale learning modules (MLMods) with different structures and convolutional kernel sizes are designed by combining a residual neural network (ResNet) and an Inception network, which can automatically learn multi-scale fault information from vibration signals. Secondly, a parallel network structure is constructed to improve the generalization ability of the proposed network model for the entire train transmission system. Finally, by using a self-attention mechanism to assign different weight values to the relative importance of different feature information, the learned fault features are further integrated and enhanced. In the experimental section, a train transmission system fault simulation platform is constructed, and experiments are carried out on train transmission systems with different faults under non-stationary conditions to verify the effectiveness of the proposed network. The experimental results and comparisons with five state-of-the-art methods demonstrate that the proposed PMA-ResNet can diagnose 19 different faults with greater accuracy. Full article

Vertebral fracture (VF) may induce spinal cord injury that can lead to serious consequences which eventually may paralyze the entire or some parts of the body depending on the location and severity of the injury. Diagnosis of VFs is crucial at the initial stage, which may be challenging because of the subtle features, noise, and homogeneity present in the computed tomography (CT) images. In this study, Wide ResNet-40, DenseNet-121, and EfficientNet-B7 are chosen, fine-tuned, and used as base models, and a Bayesian-based probabilistic ensemble learning method is proposed for fracture detection in cervical spine CT images. The proposed method considers the prediction’s uncertainty of the base models and combines the predictions obtained from them, to improve the overall performance significantly. This method assigns weights to the base learners, based on their performance and confidence about the prediction. To increase the robustness of the proposed model, custom data augmentation techniques are performed in the preprocessing step. This work utilizes 15,123 CT images from the RSNA-2022 C-spine fracture detection challenge and demonstrates superior performance compared to the individual base learners, and the other existing conventional ensemble methods. The proposed model also outperforms the best state-of-the-art (SOTA) model by 1.62%, 0.51%, and 1.29% in terms of accuracy, specificity, and sensitivity, respectively; furthermore, the AUC score of the best SOTA model is lagging by 5%. The overall accuracy, specificity, sensitivity, and F1-score of the proposed model are 94.62%, 93.51%, 95.29%, and 93.16%, respectively. Full article

Statistics indicate that over 90% of large forest fires experience re-ignition after initial extinction. However, research on the mechanisms triggering forest fire rekindling remains largely empirical, lacking an intuitive 3D mathematical model to elucidate the process. To fill this gap, this study proposes a digital twin-based forest fire re-ignition trigger model to investigate the transition from smoldering to flaming combustion. Leveraging digital twin technology, a virtual forest environment was constructed to assess the influence of ambient wind conditions and terrain slope on the smoldering-to-flaming (StF) transition based on historical rekindling data. Subsequently, logistic regression was employed in a reverse iterative process to update the model parameters, thereby establishing a matching mechanism between the model predictions and the observed rekindling states. This approach enables the adaptive adjustment of the weights assigned to key variables (e.g., wind speed and slope) and facilitates the prediction of forest fire rekindling probability within the virtual environment. Additionally, digital twin simulations are employed to assess the 3D firefighting effectiveness of unmanned aerial vehicles (UAVs) deploying hydrogel and solidified foam extinguishing agents. This visualization of the firefighting process provides valuable insights, aiding in the development of more effective strategies for preventing and controlling fire re-ignition. Full article

Apple and beetroot pomace flour (APF and BPF), along with two sweeteners, sucrose and a blend of sucrose substitutes (erythritol, stevia, inulin, and fructose), were simultaneously incorporated into three matrices formulated with agar, pectin, or gelatin as gelling agents. The aim was to produce jelly candies with high content of dietary fiber and dietary phenolics, and reduced energy value. The simultaneous incorporation of sucrose substitutes and pomace flour resulted in decrease of Carb:Fiber and Sugar:Fiber Ratio to extremely low values of 2.7–3.4 and 1.3–1.6 respectively, as well as in Energy:Fiber Ratio decrease to 9.2–12.3 kcal/g DF. Relative Antioxidant Capacity Index (RACI), as indicator of antioxidant potential, was calculated by assigning equal weight to Folin–Ciocâlteu, DPPH and FRAP assays applied upon in vitro digestion of 18 formulations of jelly candies. Results obtained for formulations with and without sucrose, as well as with and without APF or BPF, enabled insight into effects of pomace flour addition and sucrose substitution in each gelling matrix on functional properties. The incorporation and the substitution impact on postprandial glucose response were followed in vivo. Their superimposing resulted in glycemic index below 30 and low glycemic load. Efficiency of applied approach in functionalization of confectionery burden with energy and minimization of glucose spike represent an example of agro-residues re-introduction with the highest potential contribution to anti-obesity strategy. Full article

The possibility of charging and possibly discharging electric cars can influence not only the balancing of power demand profiles in the grid and the stabilization of voltage profiles but also the appropriate management of electricity within the grid of an industrial plant equipped with its own RES resources. For this purpose, the concept of “power supply modes” can be introduced, which involves intelligent demand-side management. Each technological process in an industrial plant should be assigned a specific level of importance and priority. These priorities can be numbered according to their importance (weights) and marked with appropriate colors. One thus obtains a qualitative assessment of energy consumption within the plant (demand side) through the lens of power modes. With respect to the ability to charge electric vehicles within the plant grid, such priorities can also be assigned to individual charging options. If a given RES has sufficient generation capacity during a particular time period, the cost of charging is low. However, if the RESs are not operational during a given period (e.g., nighttime in the case of photovoltaics or during calm weather in the case of wind turbines), vehicles can still be charged but according to a different priority, which, of course, involves higher costs. By having access to data on the generation capacity of distributed RESs and knowing the preferences of employees, including the number of electric cars and the expected periods of vehicle charging, it is possible to predict the degree of use of available green energy and manage it efficiently. The analyses presented in the article represent an original approach to the flexibility of operation not only of the electricity grid but also of the internal energy system of industrial plants. It offers a novel perspective aimed at maximizing the share of RESs in the overall energy balance and minimizing the costs associated with the operation of RESs. The theoretical opportunity of sustainable sharing with employees a dedicated charging mode named “free charging”, powered by RESs, could represent an appropriate solution for CO₂ emission reduction within Scope 3, Category 3, “employee commuting”, according to the GHG Protocol requirements. The original methodology proposed in the article aligns with activities related to the energy transition. Full article

In modern knitted garment production, accurate identification of fabric texture is crucial for enabling automation and ensuring consistent quality control. Traditional manual recognition methods not only demand considerable human effort but also suffer from inefficiencies and are prone to subjective errors. Although machine learning-based approaches have made notable advancements, they typically rely on manual feature extraction. This dependency is time-consuming and often limits recognition accuracy. To address these limitations, this paper introduces a novel model, called the Differentiated Leaning Weighted DenseNet (DLW-DenseNet), which builds upon the DenseNet architecture. Specifically, DLW-DenseNet introduces a learnable weight mechanism that utilizes channel attention to enhance the selection of relevant channels. The proposed mechanism reduces information redundancy and expands the feature search space of the model. To maintain the effectiveness of channel selection in the later stages of training, DLW-DenseNet incorportes a differentiated learning strategy. By assigning distinct learning rates to the learnable weights, the model ensures continuous and efficient channel selection throughout the training process, thus facilitating effective model pruning. Furthermore, in response to the absence of publicly available datasets for fabric texture recognition, we construct a new dataset named KF9 (knitted fabric). Compared to the fabric recognition network based on the improved ResNet, the recognition accuracy has increased by five percentage points, achieving a higher recognition rate. Experimental results demonstrate that DLW-DenseNet significantly outperforms other representative methods in terms of recognition accuracy on the KF9 dataset. Full article

Weakly supervised object detection (WSOD) in remote sensing images (RSIs) achieves high-value object classification and localization by only using image-level labels. However, two problems limit its performance. Firstly, adjacent instances are often misclassified because their pseudo-labels are determined solely based on the spatial distances between them and their corresponding seed instances. Secondly, most WSOD methods assign the highest weight to the instance that covers the discriminative part of an object, thereby urging WSOD models to focus on the discriminative part rather than the whole object. To handle the first problem, a high-quality instance mining (HQIM) module, which incorporates the feature similarities between instances into the label propagation process, enabling some misclassified adjacent instances to be removed, is proposed. To tackle the second problem, a weight re-assigning (WRA) strategy, which redistributes the loss weights of instances, is proposed. Specifically, the loss weights of instances focusing on the discriminative part are exchanged with those of instances that broadly cover the whole object. Ablation studies demonstrate the effectiveness of HQIM and WRA, while comparisons with popular models on two RSI benchmarks further verify the effectiveness of our model. Full article

The semantic segmentation of high-resolution remote sensing images (HRRSIs) faces persistent challenges in handling complex architectural structures and shadow occlusions, limiting the effectiveness of existing deep learning approaches. To address these limitations, we propose an attention-focused feature enhancement network (AFENet) with a novel encoder–decoder architecture. The encoder architecture combines ResNet50 with a parallel multistage feature enhancement group (PMFEG), enabling robust feature extraction through optimized channel reduction, scale expansion, and channel reassignment operations. Building upon this foundation, we develop a global multi-scale attention mechanism (GMAM) in the decoder that effectively synthesizes spatial information across multiple scales by learning comprehensive global–local relationships. The architecture is further enhanced by an efficient feature-weighted fusion module (FWFM) that systematically integrates remote spatial features with local semantic information to improve segmentation accuracy. Experimental results across diverse scenarios demonstrate that AFENet achieves superior performance in building structure detection, exhibiting enhanced segmentation connectivity and completeness compared to state-of-the-art methods. Full article

Steam turbine blades may crack, break, or suffer other failures due to high temperatures, high pressures, and high-speed rotation, which seriously threatens the safety and reliability of the equipment. The signal characteristics of different fault types are slightly different, making it difficult to accurately classify the faults of rotating blades directly through vibration signals. This method combines a one-dimensional convolutional neural network (1DCNN) and a channel attention mechanism (CAM). 1DCNN can effectively extract local features of time series data, while CAM assigns different weights to each channel to highlight key features. To further enhance the efficacy of feature extraction and classification accuracy, a projection head is introduced in this paper to systematically map all sample features into a normalized space, thereby improving the model’s capacity to distinguish between distinct fault types. Finally, through the optimization of a supervised contrastive learning (SCL) strategy, the model can better capture the subtle differences between different fault types. Experimental results show that the proposed method has an accuracy of 99.61%, 97.48%, and 96.22% in the classification task of multiple crack fault types at three speeds, which is significantly better than Multilayer Perceptron (MLP), Residual Network (ResNet), Momentum Contrast (MoCo), and Transformer methods. Full article

Multisource data fusion technology integrates the strengths of various data sources, addressing the limitations of relying on a single source. Therefore, it has been widely applied in fields such as lithological classification and mineral exploration. However, traditional deep learning algorithms fail to distinguish the importance of different features effectively during fusion, leading to insufficient focus in the model. To address this issue, this paper introduces a ResHA network based on a hybrid attention mechanism to fuse features from ASTER remote sensing images, geochemical data, and DEM data. A case study was conducted in the Altay Orogenic Belt to demonstrate the lithological classification process. This study explored the impact of the submodule order on the hybrid attention mechanism and compared the results with those of MLP, KNN, RF, and SVM models. The experimental results show that (1) the ResHA network with hybrid attention mechanisms assigned reasonable weights to the feature sets, allowing the model to focus on key features closely related to the task. This resulted in a 7.99% improvement in classification accuracy compared with that of traditional models, significantly increasing the precision of lithological classification. (2) The combination of channel attention followed by spatial attention achieved the highest overall accuracy, 98.06%. Full article

Shack–Hartmann wavefront sensors (SHWFSs) are crucial for detecting distortions in adaptive optics systems, but the accuracy of wavefront reconstruction is often hampered by low guide star brightness or strong atmospheric turbulence. This study introduces a new method of using the Vision Transformer model to process image information from SHWFSs. Compared with previous traditional methods, this model can assign a weight value to each subaperture by considering the position and image information of each subaperture of this sensor, and it can process to obtain wavefront reconstruction results. Comparative evaluations using simulated SHWFS light intensity images and corresponding deformable mirror command vectors demonstrate the robustness and accuracy of the Vision Transformer under various guide star magnitudes and atmospheric conditions, compared to convolutional neural networks (CNNs), represented in this study by Residual Neural Network (ResNet), which are widely used by other scholars. Notably, normalization preprocessing significantly improves the CNN performance (improving Strehl ratio by up to 0.2 under low turbulence) while having a varied impact on the Vision Transformer, improving its performance under a low turbulence intensity and high brightness (Strehl ratio up to 0.8) but deteriorating under a high turbulence intensity and low brightness (Strehl ratio reduced to about 0.05). Overall, the Vision Transformer consistently outperforms CNN models across all tested conditions, enhancing the Strehl ratio by an average of 0.2 more than CNNs. Full article