High Accuracy Of Method Research Articles

How Accurate Are Simulations and Experiments for the Lattice Energies of Molecular Crystals?

Molecular crystals play a central role in a wide range of scientific fields, including pharmaceuticals and organic semiconductor devices. However, they are challenging systems to model accurately with computational approaches because of a delicate interplay of intermolecular interactions such as hydrogen bonding and Van der Waals dispersion forces. Here, by exploiting recent algorithmic developments, we report the first set of diffusion MonteCarlo lattice energies for all 23molecular crystals in the popular and widely used X23 dataset. Comparisons with previous state-of-the-art lattice energy predictions (on a subset of the dataset) and a careful analysis of experimental sublimation enthalpies reveals that high-accuracy computational methods are now at least as reliable as (computationally derived) experiments for the lattice energies of molecular crystals. Overall, this work demonstrates the feasibility of high-level explicitly correlated electronic structure methods for broad benchmarking studies in complex condensed phase systems, and signposts a route towards closer agreement between experiment and simulation.

A real-time and high-accuracy railway obstacle detection method using lightweight CNN and improved transformer

With the sustained development of railway transportation, the urgent necessity to improve train operation safety makes obstacle detection become the research focus. However, existing railway obstacle detectors still face challenges in balancing detection accuracy and speed during the shunting process. In addition, they are not robust enough in real-world railway environments, especially in complex scenes involving small obstacles. To address these problems, this paper presents a real-time and high-accuracy railway obstacle detection model using lightweight CNN and improved transformer (RH-Net) for detecting railway obstacles efficiently to guarantee traffic safety. First, the Lightweight Feature Extraction Module (LEM) is designed to minimize the model’s computational load while maintaining its feature extraction ability. Then, the Improved Transformer Module (IFM) is developed to boost the model’s ability about stably extract global contextual information. Finally, the Enhanced Multi-Scale Feature Fusion Module (EFM) is proposed to optimize the detection of obstacles with different sizes, especially small objects. In the experiments on railway dataset, RH-Net achieves optimal detection performance on GeForce GTX 1080Ti (96.99% mAP and 135 FPS) and Jetson Xavier NX (97.02% mAP and 43 FPS), which is significantly superior to the existing detection models. Experimental results show that RH-Net has excellent detection ability, which can accurately and efficiently detect obstacles in complicated railway environments. Moreover, the experiments on MS COCO indicate that RH-Net can achieve more satisfactory detection performance than existing state-of-the-art methods. Therefore, the proposed model can be well-applied to more complex real-world scenes for multiple object detection.

Fall detection algorithm based on global and local feature extraction

Falls have become one of the main causes of injury and death among the elderly. A high-accuracy fall detection method can effectively detect falls in the elderly, thereby reducing the probability of injury and mortality. This paper proposes a fall detection algorithm based on global and local feature extraction. Specifically, we design a dual-stream network, with one branch composed of a convolutional neural network and a regional attention module for extracting local features from images. The other branch consists of an improved Transformer for extracting global features from images. The local and global features are then fused using a feature fusion module for classification, enabling fall detection. Experimental results show that the proposed approach achieves accuracies of 99.55% and 99.75% when tested with UP-Fall Detection Dataset and Le2i Fall Detection Dataset.

Converter Capacitor Temperature Estimation Based on Continued Training LSTM under Variable Load Conditions.

Capacitors are crucial components in power electronic converters, responsible for harmonic elimination, energy buffering, and voltage stabilization. However, they are also the most susceptible to damage due to their operational environment. Accurate temperature estimation of capacitors is essential for monitoring their condition and ensuring the reliability of the converter system. This paper presents a novel method for estimating the core temperature of capacitors using a long short-term memory (LSTM) algorithm. The approach incorporates a continued training mechanism to adapt to variable load conditions in converters. Experimental results demonstrate the proposed method's high accuracy and robustness, making it suitable for real-time capacitor temperature monitoring in practical applications.

Rapid species discrimination of similar insects using hyperspectral imaging and lightweight edge artificial intelligence.

Species discrimination of insects is an important aspect of ecology and biodiversity research. The traditional methods based on human visual experience and biochemical analysis cannot strike a balance between accuracy and timeliness. Morphological identification using computer vision and machine learning is expected to solve this problem, but image features have poor accuracy for very similar species and usually require complicated networks that are unfriendly to portable edge devices. In this work, we propose a fast and accurate species discrimination method of similar insects using hyperspectral features and lightweight machine learning algorithm. Feature regions selection, feature spectra selection and model quantification are used for the optimization of discriminating network. The experimental results of six similar butterfly species in the genus of Graphium show that, compared with morphological recognition with machine vision, our work achieves a higher accuracy of 92.36 ± 3.04% and a shorter inference time of 0.6 ms, with the tiny-size convolutional neural network deployed on a neural network chip. This study provides a rapid and high-accuracy species discrimination method for insects with high appearance similarity and paves the way for field discriminations using intelligent micro-spectrometer based on on-chip microstructure and artificial intelligence chip.

Optical image analysis for graphene layer detection: Enhanced green channel methodology

Graphene, a material of increasing research interest, requires accurate layer identification due to its sensitivity to layer count. Existing methods for graphene layer number identification are either time-consuming or of low accuracy, with high-accuracy methods often requiring expensive processes. This paper aims to address this challenge by proposing a cost-effective and efficient approach. Specifically, the current work highlights only the green channel—one of the three primary color channels (red, green, blue) that make up an optical image—from images of exfoliated graphene flakes for layer count identification. A linear regression is performed between pixel position and substrate green channel value, and this effect is subtracted from the entire optical image to mitigate background effects. By storing the range of green channel values for each type of flake (monolayer, bilayer, or tri-layer) based on a few images, we establish thresholds for identifying different types of layers in a particular setup. Additionally, our methodology allows for flexible threshold tuning using a single reference image, enabling adjustment to changes in detection setup such as illumination level, magnification, or microscope used. Demonstrating high accuracy and flexibility, this methodology presents a suitable technique for graphene layer number identification without the need for large datasets or expensive instruments.

A high-accuracy single-frame 3D reconstruction method with color speckle projection for pantograph sliders

The carbon slider of the pantograph is a crucial component in the high-speed rail power system, and regular maintenance is of great significance. 2D-based approach is susceptible to inaccuracies caused by defects, rainwater, stains, and other factors. Due to the weak texture and uneven reflectance of the slider, it is difficult to obtain accurate 3D information through a single-frame approach. To address this issue, this paper proposes a high-accuracy 3D imaging method for sliders, successfully resolving the long-standing problem of low reconstruction accuracy and limited generalization in pantograph reconstruction. Firstly, high-precision disparity maps of industrial component are generated using the binocular Gray Code phase-shifting method as the Ground Truth, and the color speckle pattern is subsequently utilized as the input for the model. Secondly, we propose a split-cost volume approach that achieves cost aggregation using only 2D decoding-encoding operations. Furthermore, disparity regression is utilized to provide the initial disparity for the GRU(Gated Recurrent Unit), thereby accelerating the convergence speed of the model. Quantitative experiments of optical standard sphere validated that the proposed method could achieve 3D reconstruction with a radius error of no more than 0.07 mm. The pantograph reconstruction results showed that the average absolute error of the carbon slider did not exceed 0.21 mm under reasonable exposure time and the working distance at which focus has been achieved, which meets the requirements of industrial inspection.

High-accuracy method for modeling nucleation and growth of particles

High-accuracy method for modeling nucleation and growth of particles

Effects of inclination angle and fluid parameters on binary fluid convection in a tilted rectangular cavity

Thermal convection of binary fluid mixtures with negative separation ratios in a tilted rectangular cavity heated from below is numerically investigated using a high-accuracy finite-difference method. The fluids under consideration are Newtonian fluids with the Prandtl number (Pr) and Lewis number (Le) in the ranges of 0.01≤Pr≤10 and 0.001≤Le≤1, respectively. Extensive direct numerical simulations are conducted to explore the dynamics of the system by varying the control parameters, namely, the relative Rayleigh number (r) and the inclination angle of the cavity (β) together with the separation ratio (ψ) in the ranges of 1.0≤r≤2.0, 0°≤β≤90°, and −0.6≤ψ≤0. It is found that the inclination angle leads to a distinct trend for heat and mass transfer: the Nusselt number first decreases for small β, then gradually increases for moderate β, and finally decreases again for large β when r varies from 1.4 to 2.0. The optimal inclination angle lies in the range of 54°≤β∗≤64°, where the heat transport peaks. The Sherwood number initially decreases for small β, then increases with increasing β, and finally remains constant for large β. We present the bifurcation diagram of the solutions for different separation ratios, focusing on the distinct variation trends of the inclination angle. The corresponding heat- and mass-transfer properties of the flow on different branches of the bifurcation diagram are investigated. Furthermore, we explore the effect of the relative Rayleigh number, Prandtl number and Lewis number as well as the separation ratio on heat and mass transfer for various inclination angles, and obtain the Nusselt number as a function of the separation ratio and inclination angle.

Estimating high spatio-temporal resolution XCO2 using spatial features deep fusion model

The high temporal-spatial resolution estimation of XCO2 data is foundational for precision quantification of carbon dioxide sources and sinks at a regional scale. This study proposed an advanced XCO2 data estimation method, using spatial features deep fusion. Leveraging convolutional neural network (CNN) principles, SpatialFusionNet—a module was designed to amalgamate geographical features within a defined spatial range. This module captures and integrates the spatial characteristics of meteorological and surface environmental factors, enhancing its application to the XCO2 estimation model. Building upon machine learning methods including Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Deep Neural Network (DNN), combined with the SpatialFusionNet module, the spatial features deep fusion models were constructed utilizing relationships among OCO-2 satellite XCO2 trajectory monitoring data in China, Copernicus Atmospheric Monitoring Service (CAMS) XCO2 reanalysis data, and meteorological factors, surface vegetation, and meteorological factors. Model performance improvements were significant, with SVM, DNN, and XGBoost showing respective RMSE reductions of 1.297 ppm, 0.480 ppm, and 0.200 ppm in ten-fold cross-validation based on OCO-2 trajectory samples. In data validation with TCCON Hefei station, the correlation between inversion data and ground-based data reached 0.85, affirming the method's high accuracy. Employing the spatial feature extraction module combined with DNN, the 2015 XCO2 annual spatial distribution of China, analyzing temporal-spatial distribution characteristics in China was generated. The DNN model, combining the SpatialFusionNet module, significantly contributes to the estimation of high temporal-spatial resolution XCO2 datasets, facilitating fine-scale quantification of regional carbon cycling.

Genetic diversity of the Turkish accessions of two progenitor species, Triticum baeoticum Boiss. and Triticum urartu Thum. ex Gandil., using DArTSeq markers

AbstractThe aim of this study was to reveal the intra and interspecies differences between Triticum baeoticum and Triticum urartu using Diversity Arrays Technology sequencing (DArTseq) on 94 accessions representing Turkish populations. Seeds were gathered from the US Department of Agriculture, and from the Turkish Seed Gene Bank. Isolated and purified DNA samples were sent to Diversity Arrays Technologies for DArTseq. After the necessary quality filtering, a total of 16,898 and 100,103 loci were obtained respectively from the single nucleotide polymorphism (SNP) and SilicoDArT datasets. ADMIXTURE software was used to reveal the intra and interspecies population structures. Analysis of molecular variance was carried out to reveal the variance between the populations of the T. urartu and T. baeoticum species. Principal coordinate analysis was conducted to visualize the main sources of variation between the populations on a 2-dimensional plane. To reveal the evolutionary relationship, SNP dataset was used to reconstruct the phylogenetic dendrograms by using the maximum likelihood statistical method and the unweighted pair group method with arithmetic mean clustering algorithm. As a result of this study, the accessions of T. urartu and T. baeoticum species formed separate clusters and revealed as two different species. In line with the results obtained, it is obvious that the identification of some accessions should be re-evaluated. The results demonstrated that DArTseq, is a fast, low-cost, and high-accuracy method that can be used in species and population discrimination and an effective tool for Gene Bank management.

Finite Elements with Switch Detection for numerical optimal control of nonsmooth dynamical systems with set-valued heaviside step functions

This paper develops high-accuracy methods for the numerical solution of optimal control problems subject to nonsmooth differential equations with set-valued Heaviside step functions. An important subclass of these systems are Filippov systems. By writing the Heaviside step function as the solution map of a linear program and using its optimality conditions, the initial nonsmooth system is rewritten into an equivalent Dynamic Complementarity System (DCS). The Finite Elements with Switch Detection (FESD) method (Nurkanović et al., 2024) was originally developed for Filippov systems transformed via Stewart’s reformulation into DCS (Stewart, 1990). This paper extends it to the above mentioned class of nonsmooth systems. The key ideas are to start with a standard Runge–Kutta method for the DCS and to let the integration step sizes to be degrees of freedom. Then, additional conditions are introduced to allow implicit but accurate switch detection and to remove possible spurious degrees of freedom when no switches occur. The theoretical properties of the FESD method are studied. The motivation for these developments is to obtain a computationally tractable formulation of nonsmooth optimal control problems. Numerical simulations and optimal control examples are used to illustrate the favorable properties of the proposed approach. All methods introduced in this paper are implemented in the open-source software package nosnoc (Nurkanović and Diehl, 2022).

Correction for geometric distortion in the flattened representation of pipeline external surface

Conventional cameras often produce external pipeline surface images with significant perspective-projection distortions, making determining the type and size of defects on the pipeline surface difficult. To address this issue, we present a novel approach for correcting the geometric distortion of a constant diameter pipeline (CDP) external surface image based on apparent contour pairs (ACPs). First, the camera is calibrated and the real projection position of ACPs accurately extracted. Second, a single-view perspective projection model of the CDP is adopted to realize a three-dimensional reconstruction of the pipeline. Subsequently, the flattened image of the CDP’s outer surface is obtained by performing equidistant sampling of cross sections, determining the visibility of discrete points, and mapping projection points onto a flat surface. Simulations and real experiments demonstrated the high accurate method in the correction of CDP images. Experiments conducted under different outdoor scenarios confirmed the robustness of the proposed method.

MPASL: multi-perspective learning knowledge graph attention network for synthetic lethality prediction in human cancer.

Synthetic lethality (SL) is widely used to discover the anti-cancer drug targets. However, the identification of SL interactions through wet experiments is costly and inefficient. Hence, the development of efficient and high-accuracy computational methods for SL interactions prediction is of great significance. In this study, we propose MPASL, a multi-perspective learning knowledge graph attention network to enhance synthetic lethality prediction. MPASL utilizes knowledge graph hierarchy propagation to explore multi-source neighbor nodes related to genes. The knowledge graph ripple propagation expands gene representations through existing gene SL preference sets. MPASL can learn the gene representations from both gene-entity perspective and entity-entity perspective. Specifically, based on the aggregation method, we learn to obtain gene-oriented entity embeddings. Then, the gene representations are refined by comparing the various layer-wise neighborhood features of entities using the discrepancy contrastive technique. Finally, the learned gene representation is applied in SL prediction. Experimental results demonstrated that MPASL outperforms several state-of-the-art methods. Additionally, case studies have validated the effectiveness of MPASL in identifying SL interactions between genes.

The convergence of high-accuracy three-point compact computational method for structural derivative anomalous diffusion–advection model

The convergence of high-accuracy three-point compact computational method for structural derivative anomalous diffusion–advection model

A high-accuracy intelligent fault diagnosis method for aero-engine bearings with limited samples

As a crucial component supporting aero-engine functionality, effective fault diagnosis of bearings is essential to ensure the engine's reliability and sustained airworthiness. However, practical limitations prevail due to the scarcity of aero-engine bearing fault data, hampering the implementation of intelligent diagnosis techniques. This paper presents a specialized method for aero-engine bearing fault diagnosis under conditions of limited sample availability. Initially, the proposed method employs the refined composite multiscale phase entropy (RCMPhE) to extract entropy features capable of characterizing the transient signal dynamics of aero-engine bearings. Based on the signal amplitude information, the composite multiscale decomposition sequence is formulated, followed by the creation of scatter diagrams for each sub-sequence. These diagrams are partitioned into segments, enabling individualized probability distribution computation within each sector, culminating in refined entropy value operations. Thus, the RCMPhE addresses issues prevalent in existing entropy theories such as deviation and instability. Subsequently, the bonobo optimization support vector machine is introduced to establish a mapping correlation between entropy domain features and fault types, enhancing its fault identification capabilities in aero-engine bearings. Experimental validation conducted on drivetrain system bearing data, actual aero-engine bearing data, and actual aerospace bearing data demonstrate remarkable fault diagnosis accuracy rates of 99.83%, 100%, and 100%, respectively, with merely 5 training samples per state. Additionally, when compared to the existing eight fault diagnosis methods, the proposed method demonstrates an enhanced recognition accuracy by up to 28.97%. This substantiates its effectiveness and potential in addressing small sample limitations in aero-engine bearing fault diagnosis.

Land Use Change Mapping and Analysis Using Remote Sensing and GIS: A Case Study in Tam Ky City, Quang Nam Province, Vietnam

Changes in land use/land cover (LULC) play a critical role in effective natural resource management, monitoring, and development, particularly within the realm of urban planning. In the examination of Tam Ky city, Quang Nam province, Vietnam, spanning from 2000 to 2020, remote sensing and Geographic Information System (GIS) techniques were employed. The Landsat satellite data (Landsat 7 ETM+ for 2000, Landsat 5 TM for 2010, and Landsat 8 OLI for 2022) underwent analysis using the supervised classification method in ArcGIS 10.8 software to identify and categorize six primary LULC classes: water bodies, agriculture, settlements, vegetation, construction, and bare soil/rocks. The reliability of the classification was evaluated through k values, revealing high accuracy with values of 0.951, 0.953, and 0.950 for the years 2000, 2010, and 2020, respectively. Notable shifts in LULC were observed during the period from 2000 to 2020. The areas covered by vegetation and settlements expanded by 53 and 1300 ha, respectively, while water bodies, agriculture, construction, and bare soil/rocks experienced reductions of 466, 48, 413, and 425 ha, respectively. To facilitate a rapid assessment, the study also incorporated the normalized difference vegetation index (NDVI) and normalized difference built-up index (NDBI). The trends identified in this study are consistently aligned with the results of the supervised classification. The identified changes in LULC pose a substantial environmental threat, and the study's outcomes serve as a valuable asset for future land use planning and management in the area. The method's high accuracy enhances the dependability of the results, making them crucial for well-informed decision-making and sustainable development initiatives.

Improving Target Geolocation Accuracy with Multi-View Aerial Images in Long-Range Oblique Photography

Target geolocation in long-range oblique photography (LOROP) is a challenging study due to the fact that measurement errors become more evident with increasing shooting distance, significantly affecting the calculation results. This paper introduces a novel high-accuracy target geolocation method based on multi-view observations. Unlike the usual target geolocation methods, which heavily depend on the accuracy of GNSS (Global Navigation Satellite System) and INS (Inertial Navigation System), the proposed method overcomes these limitations and demonstrates an enhanced effectiveness by utilizing multiple aerial images captured at different locations without any additional supplementary information. In order to achieve this goal, camera optimization is performed to minimize the errors measured by GNSS and INS sensors. We first use feature matching between the images to acquire the matched keypoints, which determines the pixel coordinates of the landmarks in different images. A map-building process is then performed to obtain the spatial positions of these landmarks. With the initial guesses of landmarks, bundle adjustment is used to optimize the camera parameters and the spatial positions of the landmarks. After the camera optimization, a geolocation method based on line-of-sight (LOS) is used to calculate the target geolocation based on the optimized camera parameters. The proposed method is validated through simulation and an experiment utilizing unmanned aerial vehicle (UAV) images, demonstrating its efficiency, robustness, and ability to achieve high-accuracy target geolocation.

Electric Polarization from a Many-Body Neural Network Ansatz.

Abinitio calculation of dielectric response with high-accuracy electronic structure methods is a long-standing problem, for which mean-field approaches are widely used and electron correlations are mostly treated via approximated functionals. Here we employ a neural network wave function ansatz combined with quantum MonteCarlo method to incorporate correlations into polarization calculations. On a variety of systems, including isolated atoms, one-dimensional chains, two-dimensional slabs, and three-dimensional cubes, the calculated results outperform conventional density functional theory and are consistent with the most accurate calculations and experimental data. Furthermore, we have studied the out-of-plane dielectric constant of bilayer graphene using our method and reestablished its thickness dependence. Overall, this approach provides a powerful tool to accurately describe electron correlation in the modern theory of polarization.

Sensor Head Temperature Distribution Reconstruction of High-Precision Gravitational Reference Sensors with Machine Learning.

Temperature fluctuations affect the performance of high-precision gravitational reference sensors. Due to the limited space and the complex interrelations among sensors, it is not feasible to directly measure the temperatures of sensor heads using temperature sensors. Hence, a high-accuracy interpolation method is essential for reconstructing the surface temperature of sensor heads. In this study, we utilized XGBoost-LSTM for sensor head temperature reconstruction, and we analyzed the performance of this method under two simulation scenarios: ground-based and on-orbit. The findings demonstrate that our method achieves a precision that is two orders of magnitude higher than that of conventional interpolation methods and one order of magnitude higher than that of a BP neural network. Additionally, it exhibits remarkable stability and robustness. The reconstruction accuracy of this method meets the requirements for the key payload temperature control precision specified by the Taiji Program, providing data support for subsequent tasks in thermal noise modeling and subtraction.