Experimental Accuracy Research Articles

Integration of AI Functions for Automatic Identification of Morphological Parameters in Medical Images Using MATLAB

Introduction: Artificial intelligence (AI) is transforming medical imaging by automating complicated and challenging processes with remarkable accuracy. This paper examines the adoption of AI algorithms using MATLAB for the automated recognition of morphological structures in medical imaging. Methods: This research utilizes advanced machine learning (ML) and deep learning (DL) methods to address essential tasks like image segmentation, feature extraction, and parameter estimation. MATLAB's intuitive interface and powerful computational capabilities make it easy to create and test models for specific medical imaging tasks. Segmentation and parameter prediction are carried out with great accuracy in experiments carried out on publically available datasets, such as brain MRI and lung CT scans. In many instances, the Dice coefficients surpass 0.9. While tackling issues like data quality, model interpretability, and computational efficiency, this study emphasizes the benefits of MATLAB for developing and implementing AI solutions in healthcare. Results: The results emphasize MATLAB's capability to improve diagnostic accuracy and operational effectiveness in clinical environments, facilitating future advancements in customized medicine. There has to be effective software for automated analysis and interpretation of the ever-increasing amount of medical imaging data. Conclusions: The purpose of this research is to examine the feasibility of using MATLAB's AI features for the automated detection of morphological parameters in medical images. Here, we compare AI-driven algorithms to more conventional image processing approaches for typical morphological metrics like area, perimeter, shape descriptors, and object recognition, and we find that the former are more accurate and efficient. To verify the efficacy of the suggested AI model, statistical analysis is carried out on a dataset consisting of medical photographs.

A Force-Sensor-Less Approach for Rapid Young's Modulus Identification of Heterogeneous Soft Tissue.

Due to individual differences, accurate identification of tissue elastic parameters is essential for biomechanical modeling in surgical guidance for hepatic venous injections. This paper aims to acquire the absolute Young's modulus of heterogeneous soft tissues during endoscopic surgery with 2D ultrasound images. First, we introduced a force-sensor-less approach that utilizes a pre-calibrated soft patch with a known Young's modulus and its ultrasound images to calculate the external forces exerted by the probe on the tissue. Second, we introduced a Kriging-based inverse algorithm to identify the relative Young's modulus (RYM) between the inclusion and the background tissue. The RYM was estimated based on 2D plane strain approximation and mapped to the RYM of 3D soft tissue through a trained Kriging model. Finally, we developed a direct method to identify the background Young's modulus (BYM) based on calculated external forces and RYM. The simulation results demonstrate the high efficiency and robustness of the Kriging-based inverse algorithm in identifying RYM. Physical experiments on the three phantoms show that the errors of the identified BYM and RYM are all below 15%. The proposed methodology for Young's modulus identification is feasible and achieves satisfactory accuracy and computational efficiency in both simulations and physical experiments.

DPRA: a dual pooling attention network for point cloud classification and segmentation

Abstract Point cloud data, widely used in fields such as autonomous driving and robotic navigation, involves classification and segmentation tasks. The extraction of local and global features has become a major research focus. The paper proposes two modules: the Dual Pooling Attention model (DP-Attention) and the Residual Attention Module model (RA-MLP). DP-Attention utilizes max pooling and average pooling to compute attention, extracting information between points as well as between features to enhance local feature extraction. RA-MLP integrates self-attention and residual connections to improve global feature extraction. These modules are combined to construct the DPRA network, which is tailored for point cloud classification and segmentation tasks. The DPRA network architecture is based on the encoder-decoder structure of U-Net, using DP-Attention and RA-MLP in the encoder, and only RA-MLP in the decoder. Experimental results on three datasets demonstrate that the DPRA network achieves outstanding performance in the synthetic ModelNet40 classification experiment, with a mean class accuracy of 91.6%. It also achieves the highest mean class accuracy (85.3%) and overall accuracy (86.1%) in the real-world ScanObjectNN classification experiment. Additionally, it attains the highest mean Intersection over Union (mIoU) of 85.2% in the synthetic ShapeNet segmentation experiment. These results indicate that DPRA is applicable to various tasks, demonstrating strong generalization, robustness, and multi-task learning capabilities.

Multi-parameter estimation of the state of two interfering photonic qubits

Abstract A two-photon interfering technique based on polarization-resolved measurements is presented for the simultaneous estimation with maximum quantum sensitivity of multiple parameters associated with the polarization state of two interfering photonic qubits. This estimation is achieved by exploiting a novel interferometric technique based on polarization-resolved two-photon interference. The experimental feasibility and accuracy of this technique is shown, even when a limited number of sampling measurements is employed. This work is relevant for the development of quantum technologies with photonic qubits and sheds light on the physics at the interface between multiphoton interference, boson sampling, multi-parameter quantum sensing, and quantum information processing.

Sensory Feedback Improvement of BCI Robotics for Movement Control

Brain-computer interfaces have great potential in motor control and rehabilitation. In related research fields, how to effectively monitor users has always been a research focus. Many studies have found that the performance of brain-computer interfaces can be effectively improved by improving and integrating feedback methods. This article reviews the four main types of feedback currently available, including visual feedback, auditory feedback, vibration, and electrical stimulation in tactile feedback, and introduces their principles and applications. This article summarizes the improvements in experimental accuracy and efficiency brought about by these sensory feedbacks in research and finally proposes limitations and future development trends.

Quantitative Study of Swin Transformer and Loss Function Combinations for Face Anti-Spoofing

Face anti-spoofing (FAS) has always been a hidden danger in network security, especially with the widespread application of facial recognition systems. However, some current FAS methods are not effective at detecting different forgery types and are prone to overfitting, which means they cannot effectively process unseen spoof types. Different loss functions significantly impact the classification effect based on the same feature extraction without considering the quality of the feature extraction. Therefore, it is necessary to find a loss function or a combination of different loss functions for spoofing detection tasks. This paper mainly aims to compare the effects of different loss functions or loss function combinations. We selected the Swin Transformer as the backbone of our training model to extract facial features to ensure the accuracy of the ablation experiment. For the application of loss functions, we adopted four classical loss functions: cross-entropy loss (CE loss), semi-hard triplet loss, L1 loss and focal loss. Finally, this work proposed combinations of Swin Transformers and different loss functions (pairs) to test through in-dataset experiments with some common FAS datasets (CelebA-Spoofing, CASIA-MFSD, Replay attack and OULU-NPU). We conclude that using a single loss function cannot produce the best results for the FAS task, and the best accuracy is obtained when applying triplet loss, cross-entropy loss and Smooth L1 loss as a loss combination.

DisDock: A Deep Learning Method for Metal Ion-Protein Redocking.

The structures of metalloproteins are essential for comprehending their functions and interactions. The breakthrough of AlphaFold has made it possible to predict protein structures with experimental accuracy. However, the type of metal ion that a metalloprotein binds and the binding structure are still not readily available, even with the predicted protein structure. In this study, we present DisDock, a deep learning method for predicting protein-metal docking. DisDock takes distogram of randomly initialized protein-ligand configuration as input and outputs the distogram of the predicted binding complex. It combines the U-net architecture with self-attention modules to enhance model performance. Taking inspiration from the physical principle that atoms in closer proximity display a stronger mutual attraction, this predictor capitalizes on geometric information to uncover latent characteristics indicative of atom interactions. To train our model, we employ a high-quality metalloprotein dataset sourced from the Mother of All Databases (MOAD). Experimental results demonstrate that our approach outperforms other existing methods in prediction accuracy for various types of metal ions.

Ab initio calculations of electric field gradients in H-bond rich molecular crystals with nearly experimental accuracy.

Ab initio calculations of electric field gradients (EFGs) in molecular crystals have advanced significantly due to the gauge including projector augmented wave (GIPAW) formalism, which accounts for the infinite periodicity in crystals. However, theoretical accuracies still lag behind experimental ones, making it challenging to distinguish experimentally distinguishable similar structures, a deficiency largely attributed to the limitation of GIPAW codes to generalized gradient approximation (GGA) density functional theory (DFT) functionals. In this study, we investigate whether hybrid DFT functionals can enhance the EFG calculation accuracy and the associated geometry optimization. Using the many-body expansion method, we focus on nitrogen EFGs in amino acids with complex H-bonding, which are often poorly described with GGA functionals. Our results show that both functionals provide highly accurate calculations that surpass current studies and approach experimental precision. The accuracies are also almost three times higher than available GIPAW/GGA calculations in the literature. However, we show that this difference is not due to the GGA functional but rather due to the improper selection of the nitrogen quadrupole moment.

Ultimate Strength Analysis of Aluminium Honeycomb Sandwich Panels Subjected to Uniaxial Compressive Loads and Lateral Pressure

Ultimate strength is critical for hull structures because it determines the maximum load the structure can withstand before catastrophic failure. Aluminium honeycomb sandwich panels provide excellent energy absorption and a high strength-to-weight ratio. However, further investigation of honeycomb sandwich panel structural performance is needed in typical marine conditions. This study focuses on the numerical analysis of honeycomb sandwich panels employing the nonlinear finite element method through the commercial software ANSYS. It investigates their performance under uniaxial compression and varying lateral pressure conditions while considering different cell edge lengths and core height configurations. Several structural configurations are compared to the experimental work published in the literature. Enhanced by experimental accuracy, the present study is a further step in expanding the application of honeycomb sandwich panels for ship hull applications that may lead to light and energy-efficient structures.

Numerical testing method and mechanical property evaluation of large particle size asphalt mixture.

The large particle size asphalt mixture with nominal maximum aggregate size 53 mm(LSAM-50) has good technical and economic performance and will become an effective technical way to build a full-thick long-life asphalt pavement with Chinese characteristics. In order to reveal the mechanical properties and influencing factors of LSAM-50 in depth, a numerical test method for the mechanical properties of the large particle size LSAM-50 asphalt mixture was developed, and a reasonable specimen size for LSAM-50 performance test was proposed by combining the numerical test and the indoor test. The results show that: LSAM-50 numerical test conditions are the calculation time step 10-3 s/step, the loading rate is 2 mm/min (uniaxial compression numerical test) and 50 mm/min (splitting numerical test) when LSAM-50 numerical experiment calculation rate and numerical experiment accuracy are better; after the size of the specimen reaches 200×160mm, the influence of the size effect is eliminated. The reasonable specimen size of LSAM-50 is Φ200mm×h160mm; the LSAM-50 numerical test method and the indoor test have low error Less than 10%.

Bending behavior and influence parameter optimization of connection joints of disc-buckle type formwork support

In order to systematically study the bending behavior of the connection joints of the disc-buckle type formwork support, the accurate numerical model of the disc-buckle type connection joints was obtained through the experimental on the bending behavior of the connection joints of the disc-buckle type, and the bending moment-rotation curve of the joints was verified. The analysis of the failure mode and stress distribution of the joints reveals the importance of the bending behavior of each component. By establishing an accurate numerical model of the joint, the accuracy of the bending experiment of the joint was verified, and the parametric analysis of the influence factors such as the depth of the wedge insertion the disk-plate, the initial position of the wedge insertion the disk-plate, the thickness of the wedge, material constitutive of the wedge and the thickness of the disk-plate was carried out to grasp the influence of the relevant parameters on the bending behavior of the joint. The results shown that the connection joints of the disc-buckle type formwork support were a typical semi-rigid connection joints. The thickness of the disk-plate plays a decisive role in the joint bending capacity, and the optimum thickness of the disk-plate was 10 mm. The thickness of the wedge was proportional to the joint bending capacity, and the optimal thickness of the wedge was 7 mm. The drop depth of the wedge should not exceed 6 mm during the locking process and the most suitable yield strength of the wedge was set to 450–500 MPa.

Multiclass Steroid Profiling in Short-Finned Pilot Whale Blubber Using Liquid Chromatography-Tandem Mass Spectrometry (LC-MS/MS).

Wildlife scientists are quantifying steroid hormones in a growing number of tissues and employing novel methods that must undergo validation before application. This study tested the accuracy and precision of liquid chromatography-tandem mass spectrometry (LC-MS/MS) methods for use on blubber samples from short-finned pilot whales (Globicephala macrorhynchus). We expanded upon a method for corticosteroid quantification by adding analytes and optimizing internal standard (IS) application. We optimized a method for the quantification of seven steroid hormones using LC-MS/MS with a C18 column. We assessed the accuracy and precision of this updated C18 method and an existing biphenyl method for use with pilot whale blubber by conducting a spike recovery experiment and calculating percent recovery and relative standard deviation (RSD) for each analyte. To explore the potential for running this method with fewer matched ISs, we compared the performance of multiple ISs for each analyte. All 11 adrenal and gonadal analytes showed good accuracy and precision in the spike recovery experiment, with recoveries between 82% and 110% and recovery RSDs below 10%. The C18 method detected all analytes at endogenous concentrations, except aldosterone. Although endogenous DHEA was detected, variability was high. IS comparisons showed 10 of 11 analytes could be calculated with comparable accuracy and precision using an IS substitute, but some substitutions significantly altered the analyte concentrations calculated. The C18 method was not sensitive enough for endogenous aldosterone detection. DHEA, which has not been previously quantified in blubber, was detected in all samples, but with high variability at lower concentrations. The methods in this study provide reliable detection and quantification of the other nine hormones tested and can be used for assessments of adrenal and gonadal steroid hormones from whales. Laboratories can reduce costs through IS substitution but should consider how these substitutions affect results.

Submillimeter-Wave Spectroscopy of the CH3O Radical.

The methoxy radical, CH3O, has long been studied experimentally and theoretically by spectroscopists because it displays a weak Jahn-Teller effect in its electronic ground state, combined with a strong spin-orbit interaction. In this work, we report an extension of the measurement of the pure rotational spectrum of the radical in its vibrational ground state in the submillimeter-wave region (350-860 GHz). CH3O was produced by H-abstraction from methanol using F atoms, and its spectrum was probed in absorption using an association of source-frequency modulation and Zeeman modulation spectroscopy. All the observed transitions together with available literature data in ν = 0 were combined and fit using an effective Hamiltonian allowing to reproduce the data at their experimental accuracy. The newly measured transitions involve significantly higher frequencies and rotational quantum numbers than those reported in the literature (f < 860 GHz and N ≤ 15 instead of 372 GHz and 7, respectively), which results in significant improvements in the spectroscopic parameters determination. The present model is well constrained and allows a reliable calculation of the rotational spectrum of the radical over the entire microwave to submillimeter-wave domain. It can be used with confidence for future searches of CH3O in the laboratory and in the interstellar medium.

Irregular seeds DEM parameters prediction based on 3D point cloud and GA-BP-GA optimization

Due to the small and irregular shapes of vegetable seeds, modeling them is challenging, and the imprecision of physical parameters hinders the performance of vegetable seeders, impeding simulation development. In this study, seeds of cucumber, pepper, and tomato were seen as examples. A 3D point cloud reconstruction method based on Structure-from-Motion Multi-View Stereo (SfM-MVS) was employed to accurately extract 3D models of small and irregularly shaped seeds. Corresponding discrete element models were established. Combining physical and simulation experiments on seed angle of repose(AOR), significant parameters influencing seed AOR and their ranges were identified through Plackett–Burman Design (PBD) and steepest ascent test. Within this range, the GA-BP-GA algorithm was used to accurately inverse the optimal parameter combination. The results indicate that the SfM-MVS 3D point cloud reconstruction method can extract more detailed shape information of small and irregularly shaped seeds. The GA-BP-GA algorithm achieved an inversion of physical parameters with the smallest relative error of cucumber, pepper, and tomato seeds being 0.26%, 0.98%, and 0.51%, respectively. Through experimental comparative analysis, the feasibility and accuracy of this method in calibrating discrete element parameters for small and irregularly shaped seeds were validated. The established seed models and calibrated parameters in this study can be implemented to the simulation optimization design of vegetable seeders, enhancing development efficiency and operational performance.

Intelligent optoelectrowetting digital microfluidic system for real-time selective parallel manipulation of biological droplet arrays.

Optoelectrowetting technology generates virtual electrodes to manipulate droplets by projecting optical patterns onto the photoconductive layer. This method avoids the complex design of the physical circuitry of dielectricwetting chips, compensating for the inability to reconstruct the electrode. However, the current technology relies on operators to manually position the droplets, draw optical patterns, and preset the droplet movement paths. It lacks real-time feedback on droplet information and the ability for independent droplet control, which can lead to droplet miscontrol and contamination. This paper presents a combination of optoelectrowetting with deep learning algorithms, integrating software and a photoelectric detection platform, and develops an optoelectrowetting intelligent control system. First, a target detection algorithm identifies droplet characteristics in real-time and automatically generate virtual electrodes to control movement. Simultaneously, a tracking algorithm outputs trajectories and ID information for efficient droplet arrays tracking. The results show that the system can automatically control the movement and fusion of multiple droplets in parallel and realize the automatic arrangement and storage of disordered droplet arrays without any additional electrodes and sensing devices. Additionally, through the automated control of the system, the cell suspension can be precisely cultured in the specified medium according to experimental requirements, and the growth trend is consistent with that observed in the well plate, significantly enhancing the experiment's flexibility and accuracy. In this paper, we propose an intelligent method applicable to the automated manipulation of discrete droplets. This method would play a crucial role in advancing the applications of digital microfluidic technology in biomedicine and other fields.

Beyond AlphaFold2: The Impact of AI for the Further Improvement of Protein Structure Prediction.

Protein structure prediction is fundamental to molecular biology and has numerous applications in areas such as drug discovery and protein engineering. Machine learning techniques have greatly advanced protein 3D modeling in recent years, particularly with the development of AlphaFold2 (AF2), which can analyze sequences of amino acids and predict 3D structures with near experimental accuracy. Since the release of AF2, numerous studies have been conducted, either using AF2 directly for large-scale modeling or building upon the software for other use cases. Many reviews have been published discussing the impact of AF2 in the field of protein bioinformatics, particularly in relation to neural networks, which have highlighted what AF2 can and cannot do. It is evident that AF2 and similar approaches are open to further development and several new approaches have emerged, in addition to older refinement approaches, for improving the quality of predictions. Here we provide a brief overview, aimed at the general biologist, of how machine learning techniques have been used for improvement of 3D models of proteins following AF2, and we highlight the impacts of these approaches. In the most recent experiment on the Critical Assessment of Techniques for Protein Structure Prediction (CASP15), the most successful groups all developed their own tools for protein structure modeling that were based at least in some part on AF2. This improvement involved employing techniques such as generative modeling, changing parameters such as dropout to generate more AF2 structures, and data-driven approaches including using alternative templates and MSAs.

Prediction accuracy of discrete choice experiments in health-related research: a systematic review and meta-analysis

Discrete choice experiments (DCEs) are increasingly used to inform the design of health products and services. It is essential to understand the extent to which DCEs provide reliable predictions outside of experimental settings in real-world decision-making situations. We aimed to compare the prediction accuracy of stated preferences with real-world choices, as modelled from DCE data. We searched six databases for health-related studies that used DCE to assess external validity and reported on predicted versus real-world choices, up to July 2024. A generalised linear mixed model was used for a meta-analysis to jointly pool the sensitivity and specificity. Heterogeneity was assessed using the I 2 statistic, and sources of heterogeneity using meta-regression. This study is registered with PROSPERO (CRD42023451545). We identified 14 relevant studies, of which 10 were included in the meta-analysis. Most studies were conducted in high-income countries (11/14, 79%) from the European region (9/14, 64%) and analysed using mixed logit models (5/14, 36%). Pooled sensitivity and specificity estimates were 89% (95% CI:77-95, I 2=97%) and 52% (95% CI:32-72, I 2=95%), respectively. The area under the SROC curve (AUC) was 0.81 (95% CI:0.77-0.84). Our meta-regression found that DCEs for prevention-related choices had higher sensitivity than treatment-related choices. DCEs conducted under clinical settings and analysed using the heteroskedastic multinomial logit model, incorporating systematic preference heterogeneity and random opt-out utility, had higher specificity than non-clinical settings and alternative models. DCEs are valuable for capturing health-related preferences and possess reasonable external validity to predict health-related behaviours, particularly for opt-in choices. Contextual factors (e.g., type of intervention, study setting, analysis method) influenced the predictive accuracy. JJO is supported by an Australian National Health and Medical Research Council Emerging Leadership Investigator Grant (GNT1193955). EBG is supported by the Dutch Research Council (NWO-Talent-Scheme-Vidi-Grant No, 09150171910002). YZ is supported by an Australian Government Research Training Program (RTP) scholarship.

Nonlinear memristor model with exact solution allows for ex situ reservoir computing training and in situ inference.

Memristive physical reservoir computing is a promising approach for solving data classification and temporal processing tasks. This method exploits the nonlinear dynamics of physical, low-power devices to achieve high-dimensional mapping of input signals. Ion-channel-based memristors, which operate with similar voltages, currents, and timescales as biological synapses, are promising due to their rich dynamics, especially for use in biological edge settings. Accurate modeling of their dynamics is essential for optimizing network hyperparameters ex situ to save time and energy. Here, a generalized sigmoidal growth model of ion-channel memristor conductance is presented and shown to be more accurate in predicting dynamics than linear or logistic models. Using the exact solution of the proposed sigmoidal model, the MNIST handwritten digit classification task is optimized and trained ex situ, then tested in situ with the same trained weights. This approach achieved an experimental testing accuracy of 90.6%.

Estimation of Wind Turbine Blade Icing Volume Based on Binocular Vision

Icing on wind turbine blades in cold and humid weather has become a detrimental factor limiting their efficient operation, and traditional methods for detecting blade icing have various limitations. Therefore, this paper proposes a non-contact ice volume estimation method based on binocular vision and improved image processing algorithms. The method employs a stereo matching algorithm that combines dynamic windows, multi-feature fusion, and reordering, integrating gradient, color, and other information to generate matching costs. It utilizes a cross-based support region for cost aggregation and generates the final disparity map through a Winner-Take-All (WTA) strategy and multi-step optimization. Subsequently, combining image processing techniques and three-dimensional reconstruction methods, the geometric shape of the ice is modeled, and its volume is estimated using numerical integration methods. Experimental results on volume estimation show that for ice blocks with regular shapes, the errors between the measured and actual volumes are 5.28%, 8.35%, and 4.85%, respectively; for simulated icing on wind turbine blades, the errors are 5.06%, 6.45%, and 9.54%, respectively. The results indicate that the volume measurement errors under various conditions are all within 10%, meeting the experimental accuracy requirements for measuring the volume of ice accumulation on wind turbine blades. This method provides an accurate and efficient solution for detecting blade icing without the need to modify the blades, making it suitable for wind turbines already in operation. However, in practical applications, it may be necessary to consider the impact of illumination and environmental changes on visual measurements.

Influence of Different Measuring Backgrounds on the Classification of Multilayer Polyolefin Films Using a Near-Infrared Handheld Spectrometer.

The low thickness of plastic films poses a challenge when using near-infrared (NIR) spectroscopy as it affects the spectral quality and classification. This research focuses on offering a solution to the challenge of classifying multilayer plastic film materials with a focus on polyolefin multilayer plastics. It presents the importance of spectral quality on accurate classification. The aim is to demonstrate the suitability of the handheld NIR spectrometer in classifying multilayer polyolefin films and assess the impact of various measuring backgrounds (white tile, Teflon, aluminum, copper, silver, and gold) on classification accuracy in the wavelength range of 1596-2396 nm. Metallic backgrounds have been found to enhance spectral quality and classification accuracy. The classification accuracy was consistently high, ranging from 96.55% to 100%, with aluminum and gold backgrounds yielding the best results in theoretical accuracy. In experimental classification, the accuracy reached 100% when any metallic backgrounds were used. Conversely, Teflon showed a theoretically high accuracy of 96.21% but only achieved an experimental accuracy of 72.2%. These findings suggest that using metallic backgrounds can improve the spectral quality and classification of plastics with low thickness (films) and complex material composition (multilayers).