Stacking Method Research Articles

A New Crustal Thickness and VP/VS Model of the Indochina Peninsula

Abstract The Indochina peninsula is formed by the collision of continental terranes, magmatic arcs, and suture zones due to the closure of the Palaeo-Tethys oceans during the Mesozoic and has experienced complex tectonic activities during the Cenozoic. Crustal thickness and VP/VS of the peninsula can help better understand its tectonics and formation, so we generate a new high-precision crust model for this region via the receiver function H−κ stacking method. The Khorat plateau has thicker crust (∼36.3 km) than other regions (∼32.4 km), whereas the elevation is similar (<500 m) or even lower. The poor correlation between crustal thickness and elevation suggests that there are other factors controlling the Khorat plateau elevation, for example, negative buoyancy of the lithosphere mantle. High crustal VP/VS (1.79–1.83) observed in southern Khorat plateau and southeastern Indochina Terrane indicates a mafic crustal composition that is consistent with extensive Late Cenozoic basaltic volcanism. Furthermore, our new model reveals high crustal VP/VS (1.81–1.95) in the east of the Nan suture and north of Khorat plateau, which could be interpreted as mafic–ultramafic intrusions in the continental back-arc basin east of the Sukhothai arc in the Late Palaeozoic. Our model does not support the existence of the eastward branch of the midlower crustal flow of the Tibetan plateau because a crustal weak layer would be too thin or too dispersed to flow.

Enhancing transparency and fairness in automated credit decisions: an explainable novel hybrid machine learning approach

This paper uses a generalised stacking method to introduce a novel hybrid model that combines a one-dimensional convolutional neural network 1DCNN with extreme gradient boosting XGBoost. We compared the predictive accuracies of the proposed hybrid architecture with three conventional algorithms-1DCNN, XGBoost and logistic regression (LR) using a dataset of over twenty thousand peer-to-peer (P2P) consumer credit observations. By leveraging the SHAP algorithm, the research provides a detailed analysis of feature importance, contributing to the model’s predictions and offering insights into the overall and individual significance of different features. The findings demonstrate that the hybrid model outperforms the LR, XGBoost and 1DCNN models in terms of classification accuracy. Furthermore, the research addresses concern regarding fairness and bias by showing that removing potentially discriminatory features, such as age and gender, does not significantly impact the hybrid model’s classification capabilities. This suggests that fair and unbiased credit scoring models can achieve high effectiveness levels without compromising accuracy. This paper makes significant contributions to academic research and practical applications in credit risk management by presenting a hybrid model that offers superior classification accuracy and promotes interpretability using the model agnostic SHAP framework.

Hardware automatic test scheme and intelligent analyze application based on machine learning model

Abstract Hardware testing has always been the core of hardware development, and improving the performance and efficiency of hardware testing is very important for hardware development. Because hardware quality management is insufficient, many large hardware tools were developed using manual workshop technology in the past and could hardly be maintained. This can lead to the cancellation of the project, causing major personnel and property losses. Improving hardware quality and ensuring security are very complex problems. Hardware testing is usually conducted through manual and automatic testing, and the limitations of manual testing are increasingly obvious. So hardware automatic testing technology has attracted people’s attention in recent years. It has become an important research direction in the field hardware testing and can overcome many problems of traditional testing methods. Strict test rules, based on standards and scores, provide a fully automated test process. With the continuous improvement of network technology, the functions and scope of hardware are constantly enriched and expanded. With the acceleration of hardware updates and development, this has brought a heavy burden to the previous hardware testing work. The purpose of this article was to study the application of machine learning technology in the field of hardware automatic testing and provide an appropriate theoretical basis for optimizing testing methods. This article introduced the research methods of hardware automatic testing technology, introduced three automatic testing framework models, and summarized the application of machine learning in hardware testing. It included hardware security and reliability analysis, hardware defect prediction, and source-based research. Then, this article studied the defect prediction model and machine learning algorithm and constructed a hardware defect prediction model based on machine learning based on the theory. First, the data were preprocessed, and then, the Stacking method was used to build a comprehensive prediction model, and four prediction results evaluation indicators were established. In the experiment part, the defect prediction results of the hardware automatic test model were studied. The results showed that the hardware defect prediction model based on machine learning had higher accuracy, recall rate, F_measure and area under curve. Compared with other models, the average accuracy of the hardware defect prediction model in this article was 0.092 higher, which was more suitable for automatic hardware testing and analysis.

Forecasting Heart Disease Risk with a Stacking-Based Ensemble Machine Learning Method

As one of the main causes of sickness and mortality, heart disease, also known as cardiovascular disease, must be detected early in order to be prevented and treated. The rapid development of computer technology presents an opportunity for the cross-combination of medicine and informatics. A novel stacking model called SDKABL is presented in this work. It uses three classifiers, namely K-Nearest Neighbor (KNN), Decision Tree (DT), and Support Vector Machine (SVM) at the base layer and the Bidirectional Long Short-Term Memory based on Attention Mechanisms (ABiLSTM) model at the meta layer for the ultimate prediction. For lowering the temporal complexity and enhancing the model’s accuracy, the dimensionality reduction approach is seen to be crucial. Principal Component Analysis (PCA) was utilized in SDKABL to minimize dimensionality and facilitate feature fusion. Using several performance measures, including precision, F1-score, accuracy, recall, and Receiver Operating Characteristic (ROC) score, the performance of SDKABL was compared to that of other independent classifiers. The experimental findings demonstrate that our proposed model combining individual classifiers with the stacking method helps improve the prediction model’s accuracy.

Multi‐layer structure design, fabrication and numerical simulations of 3D woven spacer fabric composites with improved mechanical properties

AbstractThe 3D woven spacer fabric lightweight composites (WSFC) show promising applications in construction, transportation and aerospace. In this study, the 3D WSFC with different structural variations (e.g., layer thicknesses, stacking and face layer thickening) were designed and fabricated. The fracture strengths of single‐layer WSFC in the weft direction with layer thicknesses of 5, 10 and 15 mm were 54.4, 14.3, and 5.4 MPa. In the weft direction, the fracture strengths of double‐ and triple‐stacked 3D WSFCs were 30.6 and 21.7 MPa, which improved 1.1 times and 3.0 times as compared with those of original single‐layer 3D WSFCs, respectively. The double‐ and triple‐stacked WSFC also had large flexural deformation. The 3D WSFC with double‐layer misaligned stacking had the similar flexural strengths in both directions, which obviously reduced the performance differentiation of 3D WSFC in different directions. With the addition of face layer fabric, the mechanical performances of 3D WSFC were notably enhanced, and the damage modes were changed from brittle failure to ductile failure. Furthermore, a multi‐scale model of 3D WSFC with different structural variations was developed for numerical simulation to analyze the stress distribution and damage mechanism.Highlights Stacking design obviously improves mechanical properties of 3D WSFC. WSFC with misaligned stacking has similar flexural strengths. A multi‐scale elastic–plastic damage model for 3D WSFC is established. Damage modes of WSFC are changed with the stacking method.

Numerical simulation and experimental analysis of thermal conduction and stress in laser cladding repair of thin-walled parts

To minimize the deformation of thin-walled parts during the laser cladding process and enhance the quality of the repaired parts, the Finite Element Abaqus software was used to develop a thermal conduction and 3D stress model, the heat source used in the experiments was a double ellipsoid heat source model. This model simulates the thermal process and the deformation resulting from residual stresses in the laser cladding process on a titanium alloy substrate with a thickness of 2 mm. Through the simulation, the temperature field of the substrate at the end of each pass was obtained, and the cladding sequence with the smallest temperature gradient during the multi-pass laser melting process was determined. By combining simulation and practice, the multilayer stacking pattern was optimized to achieve deformation control. Analog simulation experiments indicate that the optimized single-layer multi-pass laser cladding method results in less heat accumulation and thermal stress compared to the unidirectional sequential scanning method. The flatness test results show that the specimens have less deformation with the optimized multilayer stacking method. In addition, the metallographic organisation of the two cladding specimens is analysed in this paper, and the results show that the optimised specimens exhibit excellent microstructures and properties.

Application of interlayer perforation and installation of transparent elements in the technology of duplicated decorative polymer films

Objectives. To develop technologies for producing multilayer films of transparent thermoplastic polymers; to study methods of modifying their supramolecular structure; and to determine their optical properties by means of optical-polarization methods for the use of modified films as decorative and design materials in modern architecture.Methods. Industrial samples of polystyrene, low-density polyethylene, polypropylene, and polyvinyl chloride films from various manufacturers (Don Polimer, Vektor, and Sibur) were the objects of the study. The optical properties of the films were studied by means polarized-light spectrophotometry. In order to modify the supramolecular structure of the polymers, the surfaces of the films were treated under isometric conditions with volatile solvents or their aqueous solutions. Parts of the layers of multilayer films were removed by cutting with a punching knife using a press or with a manual device for perforating printing materials.Results. The spectral characteristics of multilayer films of several transparent thermoplastic polymers in polarized light were determined. The study showed that a wide palette of colors and contrasting images can be obtained by mechanically removing part of the layers of multilayer films. The phenomenon of pseudo-disappearance of the outermost layer was discovered after treatment of a stack of films under isometric conditions with volatile solvents or their aqueous solutions.Conclusions. Based on the example of large-scale production thermoplastics, it was shown that a combination of technological methods of stacking, perforation, and local plasticization of films of transparent thermoplastic polymers can produce pleochroic multicolor materials for a range of human activities. The possibility of hidden coding of information on multilayer packaging materials, and its visualization and instrumental reading in polarized light was confirmed by color differential and contrast of 150 and 60 units, respectively. It was also shown that several monochrome tones of different lightness and brightness can be obtained by varying the number of layers or perforating the films in multilayer materials.

Stacking Ensemble Method to Predict the Pool Boiling Heat Transfer of Nanomaterial-Coated Surface

Abstract The boiling heat transfer coefficient is important information for designing thermal devices for effective thermal management. It is affected by several factors like surface roughness and wettability of the surface. So, it is necessary to create a model for the accurate prediction. This article aims to use the stacking ensemble method to predict the boiling heat transfer coefficient (BHTC). To improve the performance of the prediction of the stacking model, AdaBoost regression and Random Forest regression are chosen as the base learner, and meta estimator linear regression is selected. Datasets are generated from a pool boiling experiment of carbon nanotube and graphene oxide (CNT + GO)-coated surface. Results have depicted that the stacking method outperformed individual models. It is found that the accuracy of the stacking ensemble model is 99.1% efficient with mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) values of 0.016, 0.0004, and 0.021, respectively.

Applying deep learning-based ensemble model to [18F]-FDG-PET-radiomic features for differentiating benign from malignant parotid gland diseases.

To develop and identify machine learning (ML) models using pretreatment 2-deoxy-2-[18F]fluoro-D-glucose ([18F]-FDG)-positron emission tomography (PET)-based radiomic features to differentiate benign from malignant parotid gland diseases (PGDs). This retrospective study included 62 patients with 63 PGDs who underwent pretreatment [18F]-FDG-PET/computed tomography (CT). The lesions were assigned to the training (n = 44) and testing (n = 19) cohorts. In total, 49 [18F]-FDG-PET-based radiomic features were utilized to differentiate benign from malignant PGDs using five different conventional ML algorithmic models (random forest, neural network, k-nearest neighbors, logistic regression, and support vector machine) and the deep learning (DL)-based ensemble ML model. In the training cohort, each conventional ML model was constructed using the five most important features selected by the recursive feature elimination method with the tenfold cross-validation and synthetic minority oversampling technique. The DL-based ensemble ML model was constructed using the five most important features of the bagging and multilayer stacking methods. The area under the receiver operating characteristic curves (AUCs) and accuracies were used to compare predictive performances. In total, 24 benign and 39 malignant PGDs were identified. Metabolic tumor volume and four GLSZM features (GLSZM_ZSE, GLSZM_SZE, GLSZM_GLNU, and GLSZM_ZSNU) were the five most important radiomic features. All five features except GLSZM_SZE were significantly higher in malignant PGDs than in benign ones (each p < 0.05). The DL-based ensemble ML model had the best performing classifier in the training and testing cohorts (AUC = 1.000, accuracy = 1.000 vs AUC = 0.976, accuracy = 0.947). The DL-based ensemble ML model using [18F]-FDG-PET-based radiomic features can be useful for differentiating benign from malignant PGDs. The DL-based ensemble ML model using [18F]-FDG-PET-based radiomic features can overcome the previously reported limitation of [18F]-FDG-PET/CT scan for differentiating benign from malignant PGDs. The DL-based ensemble ML approach using [18F]-FDG-PET-based radiomic features can provide useful information for managing PGD.

Fabrication of functional surfaces using layer height method in material extrusion type 3D printing

Various layer stacking methods have been employed in material extrusion type three-dimensional (3D) printing to utilize their potential for addressing the inherent technological limitation of reduced surface quality due to layer stacking. The process involved fabricating a material extrusion type 3D printed mold using diverse layer height-changing methods and subsequently replicating the surface pattern with the polymer. This approach is called the layer height method (LHM) and comprises three distinct variations. The first method involves altering the height of the individual layers to generate diverse surface morphologies and, consequently, varying the range of water contact angles. The second method focuses on rapid layer height changes to facilitate liquid deposition within regions with low contact angles. Finally, a layer height gradient was systematically established within the mold, resulting in a wettability gradient surface capable of controlling the movement of water droplets across the surface. The performance of these functional surfaces was successfully validated using various experimental methods. This study introduces a manufacturing technique based on changing layer heights within the framework of material extrusion-type 3D printing technology. A wide range of intricate and diverse functional surfaces can be produced by extending the manufacturing method proposed in this study to 3D printing technologies beyond the scope of material extrusion type 3D printing.

A Study on Hyperspectral Soil Moisture Content Prediction by Incorporating a Hybrid Neural Network into Stacking Ensemble Learning

The accurate prediction of soil moisture content helps to evaluate the quality of farmland. Taking the black soil in the Nanguan District of Changchun City as the research object, this paper proposes a stacking ensemble learning model integrating hybrid neural networks to address the issue that it is difficult to improve the accuracy of inversion soil moisture content by a single model. First, raw hyperspectral data are processed by removing edge noise and standardization. Then, the gray wolf optimization (GWO) algorithm is adopted to optimize a convolutional neural network (CNN), and a gated recurrent unit (GRU) and an attention mechanism are added to construct a hybrid neural network model (GWO–CNN–GRU–Attention). To estimate soil water content, the hybrid neural network model is integrated into the stacking model along with Bagging and Boosting algorithms and the feedforward neural network. Experimental results demonstrate that the GWO–CNN–GRU–Attention model proposed in this paper can better predict soil water content; the stacking method of integrating hybrid neural networks overcomes the limitations of a single model’s instability and inferior accuracy. The relative prediction deviation (RPD), root mean square error (RMSE), and coefficient of determination (R2) on the test set are 4.577, 0.227, and 0.952, respectively. The average R2 and RPD increased by 0.056 and 1.418 in comparison to the base learner algorithm. The study results lay a foundation for the fast detection of soil moisture content in black soil areas and provide a data source for intelligent irrigation in agriculture.

Pattern recognition of control charts based on data feature enhancement and ensemble learning of classifiers for dimensional accuracy of products

Product quality in manufacturing is directly related to the reliability, durability and safety of the product. Product quality can be controlled by building a product control chart pattern recognition model. The complexity and temporal sequence of product quality data make it difficult to extract effective control chart features, and it is difficult for common classifiers to play an effective role for each control chart pattern category, thus affecting the accuracy of pattern recognition. Therefore, this paper proposes a data feature enhancement processing method that combines Smote algorithm and smooth shift processing. This method reveals data features by performing feature enhancement processing on raw data and extracts statistical and shape features for dimensionality reduction to improve recognition accuracy and efficiency. Based on this approach, this paper also proposes an ensemble learning model based on the Stacking method, which incorporates BP, ELM, PNN and SVM classifiers for control chart pattern recognition. Through extensive experimental validation, the data feature enhancement method improves the accuracy of the weak classifier normal pattern recognition by 30%, and effectively reduces the misclassification in the quality control process. The ensemble learning model is stronger than the weak classifier, and its recognition accuracy can reach 97.31%.

Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differences

The aim of this study was to develop a medical imaging and comprehensive stacked learning-based method for predicting high- and low-risk thymoma. A total of 126 patients with thymomas and 5 patients with thymic carcinoma treated at our institution, including 65 low-risk patients and 66 high-risk patients, were retrospectively recruited. Among them, 78 patients composed the training cohort, while the remaining 53 patients formed the validation cohort. We extracted 1702 features each from the patients’ arterial-, venous-, and plain-phase images. Pairwise subtraction of these features yielded 1702 arterial-venous, arterial-plain, and venous-plain difference features each. The Mann‒Whitney U test and least absolute shrinkage and selection operator (LASSO) and SelectKBest methods were employed to select the best features from the training set. Six models were built with a stacked learning algorithm. By applying stacked ensemble learning, three machine learning algorithms (XGBoost, multilayer perceptron (MLP), and random forest) were combined by XGBoost to produce the the six basic imaging models. Then, the XGBoost algorithm was applied to the six basic imaging models to construct a combined radiomic model. Finally, the radiomic model was combined with clinical information to create a nomogram that could easily be used in clinical practice to predict the thymoma risk category. The areas under the curve (AUCs) of the combined radiomic model in the training and validation cohorts were 0.999 (95% CI 0.988–1.000) and 0.967 (95% CI 0.916–1.000), respectively, while those of the nomogram were 0.999 (95% CI 0.996–1.000) and 0.983 (95% CI 0.990–1.000). This study describes the application of CT-based radiomics in thymoma patients and proposes a nomogram for predicting the risk category for this disease, which could be advantageous for clinical decision-making for affected patients.

Realization of equivalent multi-level DOEs by the stack of two few-level DOEs using phase dividing

Multi-level DOEs are always desired for the wider application. However, they require more accurate fabrication and expensive production costs. This paper presents an improved stacked DOEs method. Based on the phase distribution of t-level DOEs, a phase dividing method is used to divide the phase of t-level DOEs into m and n-level DOEs (t = n × m), the equivalent t-level DOEs can be realized by the stack of m and n-level DOEs. A 16-level beam shaping DOE is taken as an example to explore the method. The 4 and 4-level (or 2 and 8-level) stacked DOEs show the CV of 3.69% and diffractive efficiency of 98.11%, which is similar to 3.58% and 98.11% of a 16-level DOE. In addition, the tolerance of the stack method is also analyzed in horizontal displacement, vertical displacement, and angular deviation of stacked DOEs. The proposed stacked DOEs method can eliminate the need to directly manufacture multi-level DOEs with more steps, thus providing the possibility of reducing cost and fabricating difficulty.

Automatic Age and Gender Recognition Using Ensemble Learning

The use of speech-based recognition technologies in human–computer interactions is increasing daily. Age and gender recognition, one of these technologies, is a popular research topic used directly or indirectly in many applications. In this research, a new age and gender recognition approach based on the ensemble of different machine learning algorithms is proposed. In the study, five different classifiers, namely KNN, SVM, LR, RF, and E-TREE, are used as base-level classifiers and the majority voting and stacking methods are used to create the ensemble models. First, using MFCC features, five base-level classifiers are created and the performance of each model is evaluated. Then, starting from the one with the highest performance, these classifiers are combined and ensemble models are created. In the study, eight different ensemble models are created and the performances of each are examined separately. The experiments conducted with the Turkish subsection of the Mozilla Common Voice dataset show that the ensemble models increase the recognition accuracy, and the highest accuracy of 97.41% is achieved with the ensemble model created by stacking five classifiers (SVM, E-TREE, RF, KNN, and LR). According to this result, the proposed ensemble model achieves superior accuracy compared to similar studies in recognizing age and gender from speech signals.

Atomic-Thin WS2 Kirigami for Bidirectional Polarization Detection.

The assembly and patterning engineering in two-dimensional (2D) materials hold importance for chip-level designs incorporating multifunctional detectors. At present, the patterning and stacking methods of 2D materials inevitably introduce impurity instability and functional limitations. Here, the space-confined chemical vapor deposition method is employed to achieve state-of-the-art kirigami structures of self-assembled WS2, featuring various layer combinations and stacking configurations. With this technique as a foundation, the WS2 nano-kirigami is integrated with metasurface design, achieving a photodetector with bidirectional polarization-sensitive detection capability in the infrared spectrum. Nano-kirigami can eliminate some of the uncontrollable factors in the processing of 2D material devices, providing a freely designed platform for chip-level multifunctional detection across multiple modules.

Coordinate system setting for post-machining of impeller shape by wire arc DED and evaluation of processing efficiency

Wire arc additive manufacturing (WAAM) is a direct energy deposition (DED) process that uses arc welding. It is a method of stacking beads made by melting metal wires with an arc heat source generated by a short-circuit current. Compared to other metal additive manufacturing methods, this process can be used to quickly produce large and complex-shaped metal parts. However, due to the multi-bead stacking method, the surface is highly curved and the dimensional errors are large; therefore, post-processing of the surface by cutting is required. Impellers, which are widely used in various industries, have complex shapes and high material consumption during cutting; therefore, the WAAM process can improve the manufacturing efficiency. In this study, a manufacturing process for an impeller with a diameter of 160 mm was developed by using the WAAM process. A 6-bladed fan-type impeller used for high-pressure fluid delivery was similarly modeled, and the product was additively manufactured using an Inconel 625 alloy wire. Manufacturing conditions that ensure productivity and quality or the product were determined through experimentation. Considering the post-processing of the WAAM-fabricated structure, the robot and tool paths of the impeller model were designed, and the error in the process coordinate system caused by attaching and detaching the workpiece between the two processes was reduced. Through the post-processing of the WAAM-fabricated structure, the production efficiency and process reliability were verified when the conventional manufacturing method and WAAM process were applied.

Regional ecological risk assessment through the application of production-living-ecology land use function indicators: a case study of the eco-economic zone of Yellow River Delta.

To date, land use structure information has been employed extensively for ecological risk assessment (ERA) purpose in regional/landscape scales; in contrast, land use function (LUF) information-based ERA research is still scarce. Therefore, it is necessary to carry out more ERA case studies in macroscale with the help of pertinent LUF indicators. As an important way to construct production-living-ecology LUF indexes, this study employs the weighted stacking method and related economic statistical data for regional ecological risk assessment (RERA) purpose within Yellow River Delta High-efficiency Eco-economic Zone (YRDHEZ), China. This YRDHEZ-RERA research pointed out that (1) it was rational to use a series of economic statistical data to more comprehensively and precisely characterize regional production and living function grades in YRDHEZ. (2) The Yellow River Delta had lower agriculture and non-agriculture production functions, whereas the rest of the zone had higher production functions. (3) Most people lived in the south part, whereas north coastal zone had very low population density; the east part had higher per capita disposable income of urban/rural households than that of west. (4) The south part of the zone had higher production/living functions and integrated ecological risk source intensity than those of north coastal zone, whereas the coastal zone had higher ecology function, eco-environmental vulnerability, and final integrated ecological risk than those of inland region. As for regional ecological risk management, establishing nature reserve with strict spatial governance for coastal/estuarine wetlands and coordinating production/ecology functions of coastal salterns/breeding ponds are relevant feasible measures.

Characterization of the Core Face Irradiation Fixture at the Pennsylvania State University Breazeale Reactor

An efficient stacking method was applied to a multi-foil activation characterization of a core face fixture in Penn State’s TRIGA reactor using STAYSL PNNL software. The adjusted neutron energy spectra from the STAYSL PNNL software are in good agreement with the input MCNP models. The validated MCNP model was then used to predict the neutron energy spectrum within the core face fixture with a new lead shielding assembly in between the fixture and the core. Additional irradiation environment details such as the estimated gamma ray dose rates and sample temperatures provide a more comprehensive view of the core face fixture beyond the neutron energy spectrum, especially for more sensitive materials.

Van der Waals mid-wavelength infrared detector linear array for room temperature passive imaging.

Passive imaging for mid-wave infrared (MWIR) is resistant to atmospheric pollutants, guaranteeing image clarity and accuracy. Arrayed photodetectors can simultaneously perform radiation sensing to improve efficiency. Room temperature van der Waals (vdWs) photodetectors without lattice matching have evolved rapidly with optimized stacking methods, primarily for single-pixel devices. The urgent need to implement arrayed devices aligns with practical demands. Here, we present an 8 by 1 black phosphorus/molybdenum sulfide (BP/MoS2) vdWs photodetector linear array with a fill-factor of ~77%, fabricated using a temperature-assisted sloping transfer method. The flat interface and uniform thickness facilitate carrier transport and minimize pixel nonuniformities, showing an average peak detectivity (D*) of 2.34 × 109 cm·Hz1/2·W-1 in the mid-wave infrared region. Compared to a single pixel, push-broom scanning passive imaging is eight times more efficient and further enhanced through mean filtering and fast Fourier transform filtering for strip noise correction. Our study offers guidance on vdWs arrayed devices for engineering applications.