Experimental Comparison Research Articles

Biomechanically-informed emotion recognition algorithm of sports athletes based on deep neural network

The environment of sports competition is changing rapidly, and there is a certain relationship between athletes’ decision-making and executive functions and athletes’ emotions. Positive emotions can enhance reaction inhibition, while negative emotions will damage the inhibition function. Therefore, identifying the emotions of athletes in sports competitions can help coaches quickly grasp the emotional state of athletes, so as to make targeted decisions. With the advent of the era of big data and the continuous in-depth development of deep neural networks, the emergence of various networks and network models has not only made rational use of a large amount of data, but also promoted the continuous development of emotion recognition. This paper takes the research on the emotion recognition algorithm of sports athletes as the object, uses the faster CNN network to recognize the facial emotion, modifies the backbone network model and loss function parameters in the network, selects the best performing network through comparative experiments, and applies it to the research field of emotion recognition algorithm of sports athletes. While understanding the emotional state of athletes in sports competitions, it lays a solid foundation for the follow-up study of athletes’ emotional recognition algorithm in sports competitions. The main research contents of this paper are as follows: firstly, this paper selects data sets with different characteristics, classifies them according to the status of athletes in sports competitions, and labels the data sets. Secondly, Fast Region-based Convolutional Neural Networks (R-CNN) is used to train the labeled data set and obtain the model, and compare the accuracy in different model and loss function parameter conditions. Finally, according to the experimental comparison results, the network with the highest accuracy is selected and applied to the research of athletes’ emotion recognition algorithm in sports competitions.

PhiSiCal-Checkup: A Bayesian framework to validate amino acid conformations within experimental protein structures

As structural biology and drug discovery depend on high-quality protein structures, assessment tools are essential. We describe a new method for validating amino-acid conformations: "PhiSiCal ([Formula: see text]al) Checkup." Twenty new joint probability distributions in the form of statistical mixture models explain the empirical distributions of dihedral angles [Formula: see text] of canonical amino acids in experimental protein structures. Marginal and conditional probability distributions for subsets of dihedral angles are derived from these joint mixture models. Together, these distributions are employed to measure rapidly the information-theoretic "favorability" of any proposed experimental protein structure. The inferred statistical models and measures overcome several shortcomings and afford improvements over the current state of the art in amino-acid conformation verification. Experimental comparisons are made against current protein conformation verification software. In a number of examples, we pick up outliers that are invisible to current methods. We also calculate, as part of verification, the sensitivity of favorability to small changes in a proposed structure accounting for the precision of coordinates. In some cases a near neighbor of a proposed amino-acid conformation may be either less or more favorable. This raises the question, is the current reliance on fixed "thresholds" for validation a good thing? PhiSiCal-Checkup is freely available for online and offline (open-source) use from https://lcb.infotech.monash.edu.au/phisical/checkup.

Towards Secure Internet of Things: A Coercion-Resistant Attribute-Based Encryption Scheme with Policy Revocation.

With the development and application of the Internet of Things (IoT), the volume of data generated daily by IoT devices is growing exponentially. These IoT devices, such as smart wearable devices, produce data containing sensitive personal information. However, since IoT devices and users often operate in untrusted external environments, their encrypted data remain vulnerable to potential privacy leaks and security threats from malicious coercion. Additionally, access control and management of these data remain critical issues. To address these challenges, this paper proposes a novel coercion-resistant ciphertext-policy attribute-based encryption scheme. The scheme leverages chameleon hashing to enhance deniable encryption, achieving coercion resistance, thereby enabling IoT data to resist coercion attacks. Moreover, the scheme employs attribute-based encryption to secure IoT data, enabling fine-grained access control and dynamic user access management, providing a secure and flexible solution for vast IoT data. We construct the scheme on a composite order bilinear group and provide formal proofs for its coercion resistance, correctness, and security. Finally, through experimental comparisons, we demonstrate the efficiency and feasibility of the proposed scheme.

Lightweight Lung-nodule Detection Model Combined with Multidimensional Attention Convolution.

Early and timely detection of pulmonary nodules and initiation treatment can substantially improve the survival rate of lung carcinoma. However, current detection methods based on convolutional neural networks (CNNs) cannot easily detect pulmonary nodules owing to low detection accuracy and the difficulty in detecting small-sized pulmonary nodules; meanwhile, more accurate CNN-based models are slow and require high hardware specifications. The aim of this study is to develop a detection model that achieves both high accuracy and real-time performance, ensuring effective and timely results. In this study, based on YOLOv5s, a concentrated-comprehensive convolution (C3_ODC) module with multidimensional attention is designed in the convolutional layer of the original backbone network for enhancing the feature-extraction capabilities of the model. Moreover, lightweight convolution is combined with weighted bidirectional feature pyramid networks (BiFPNs) to form a GS-BiFPN structure that enhances the fusion of multiscale features while reducing the number of model parameters. Finally, Focal Loss is combined with the normalized Wasserstein distance (NWD) to optimize the loss function. Focal loss focuses on carcinoma-positive samples to mitigate class imbalance, whereas the NWD enhances the detection performance of small lung nodules. In comparison experiments against the YOLOv5s, the proposed model improved the average precision by 8.7% and reduced the number of parameters and floating-point operations by 5.4% and 8.2%, respectively, while achieving 116.7 frames per second. The proposed model balances high detection accuracy against real-time requirements.

A deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognition

Coal-gangue recognition technology plays an important role in the intelligent realization of integrated working faces and coal quality improvement. However, the existing methods are easily affected by high dust, noise, and other disturbances, resulting in unstable recognition results that make it difficult to meet the needs of industrial applications. To realize accurate recognition of coal-gangue in noisy environments, this paper proposes an end-to-end multi-scale feature fusion convolutional neural network (MCNN-BILSTM) based gangue recognition method, which can automatically learn and fuse complementary information from multiple signal components of vibration signals. It combines traditional filtering methods and the idea of multi-scale learning, which can expand the breadth and depth of the feature learning process. the breadth and depth of the feature learning process. Moreover, to strengthen the expression of key features, a feature weighting method based on the attention mechanism is combined to give adaptive weights to different features. Finally, the experimental platform of a tail beam of coal-gangue impact hydraulic support is built, and several comparative experiments are carried out. The comprehensive comparison experiments show that the method shows strong adaptability, robustness, and noise resistance under various complex noise environments, and is suitable for complex practical industrial sites.

Review and experimental comparison of speckle-tracking algorithms for X-ray phase contrast imaging.

X-ray speckles have been used in a wide range of experiments, including imaging (and tomography), wavefront sensing, spatial coherence measurements, X-ray photon correlation spectroscopy and ptychography. In this review and experimental comparison, we focus on using X-ray near-field speckle grains as wavefront markers and numerical methods for retrieving the phase information they contain. We present the most common tracking methods, introducing the existing algorithms with their specifications and comparing their performances under various experimental conditions. This comparison includes applications to different types of samples: phantoms for quantitative analysis and complex samples for assessing image quality. Our goal is to unify concepts from several speckle tracking methods using consistent terminology and equation formalism, while keeping the discussion didactic and accessible to a broad audience.

Identification of diabetic retinopathy lesions in fundus images by integrating CNN and vision mamba models.

Diabetic retinopathy, a retinal disorder resulting from diabetes mellitus, is a prominent cause of visual degradation and loss among the global population. Therefore, the identification and classification of diabetic retinopathy are of utmost importance in the clinical diagnosis and therapy. Currently, these duties are extensively carried out by manual examination utilizing the human visual system. Nevertheless, manual examination is sometimes arduous, time-consuming, and prone to errors. Deep learning-based methods have recently demonstrated encouraging results in several areas, such as image categorization and natural language mining. The majority of deep learning techniques developed for medical image analysis rely on convolutional modules to extract the inherent structure of images within a certain local receptive field. Furthermore, transformer-based models have been utilized to tackle medical image processing problems by capitalizing on global connections among distant pixels in the images. Considering these analyses, this work presents a comprehensive deep learning model that combines convolutional neural network and vision mamba models. This model is designed to accurately identify and classify diabetic retinopathy lesions displayed in fundus images. Furthermore, the vision mamba component incorporates the bidirectional state space method and positional embedding to enable the location sensitivity of visual data samples and meet the conditions for global relationship context. An evaluation of the suggested method was carried out by comparison experiments between state-of-the-art algorithms and the proposed methodology. Empirical findings demonstrate that the suggested methodology surpasses the most advanced algorithms on the datasets that are accessible openly. Hence, the suggested approach may be regarded as a helpful tool for therapeutic processes.

Research on Modelling Capability of English Multimodal File Search based on Transformer

With the exponential growth of file data in the multimedia era, file retrieval ability to achieve effective data management has become a hot research field. Based on people’s English file search needs, this paper proposes an English multimodal file search model based on transformer. Through ablation experiments on two public data sets and comparison experiments with the benchmark model, the effectiveness and superiority of the proposed transformers algorithm model in multi-modal data processing are verified. The multi-modal fusion retrieval system can usually achieve better performance than the single-modal retrieval system. This experiment focuses on three modes: Audio, Image and Text. The experimental results show that the proposed method can not only improve the efficiency of file search, but also extract modal features and perform feature fusion better. In the future, we can further explore different types of other attention mechanisms or integrate a variety of different architectures to further enhance the feasibility and superiority of multimodal file search

GRL-PUL: predicting microbe-drug association based on graph representation learning and positive unlabeled learning.

Extensive research has confirmed the widespread presence of microorganisms in the human body and their crucial impact on human health, with drugs being an effective method of regulation. Hence it is essential to identify potential microbe-drug associations (MDAs). Owing to the limitations of wet experiments, such as high costs and long durations, computational methods for binary classification tasks have become valuable alternatives for traditional experimental approaches. Since validated negative MDAs are absent in existing datasets, most methods randomly sample negatives from unlabeled data, which evidently leads to false negative issues. In this manuscript, we propose a novel model based on graph representation learning and positive-unlabeled learning (GRL-PUL), to infer potential MDAs. Firstly, we screen reliable negative samples by applying weighted matrix factorization and the PU-bagging strategy on the known microbe-drug bipartite network. Then, we combine muti-model attributes and constructed a microbe-drug heterogeneous network. After that, graph attention auto-encoder module, an encoder combining graph convolutional networks and graph attention networks, is introduced to extract informative embeddings based on the microbe-drug heterogeneous network. Lastly, we adopt a modified random forest as the final classifier. Comparison experiments with five baseline models on three benchmark datasets show that our model surpasses other methods in terms of the AUC, AUPR, ACC, F1-score and MCC. Moreover, several case studies show that GRL-PUL could capably predict latent MDAs. Notably, we further verify the effectiveness of a reliable negative sample selection module by migrating it to other state-of-the-art models, and the experimental results demonstrate its ability to substantially improve their prediction performance.

UAV target tracking method based on global feature interaction and anchor-frame-free perceptual feature modulation.

Target tracking techniques in the UAV perspective utilize UAV cameras to capture video streams and identify and track specific targets in real-time. Deep learning UAV target tracking methods based on the Siamese family have achieved significant results but still face challenges regarding accuracy and speed compatibility. In this study, in order to refine the feature representation and reduce the computational effort to improve the efficiency of the tracker, we perform feature fusion in deep inter-correlation operations and introduce a global attention mechanism to enhance the model's field of view range and feature refinement capability to improve the tracking performance for small targets. In addition, we design an anchor-free frame-aware feature modulation mechanism to reduce computation and generate high-quality anchors while optimizing the target frame refinement computation to improve the adaptability to target deformation motion. Comparison experiments with several popular algorithms on UAV tracking datasets, such as UAV123@10fps, UAV20L, and DTB70, show that the algorithm balances speed and accuracy. In order to verify the reliability of the algorithm, we built a physical experimental environment on the Jetson Orin Nano platform. We realized a real-time processing speed of 30 frames per second.

Four-Dimensional Aircraft Trajectory Prediction with a Generative Deep Learning and Clustering Approach

Medium- and long-term four-dimensional (4D) aircraft trajectory prediction (TP) is a critical technology in air traffic management (ATM). This paper addresses the issue of existing medium- and long-term TP methods that are difficult to accurately fit aircraft trajectory data distributions. We propose a 4D TP method based on K-medoids clustering and conditional tabular generative adversarial networks (CTGAN), called C-CTGAN. Comparative experiments with four long short-term memory (LSTM)-based models and the original CTGAN model show that the proposed model’s TP accuracy is significantly higher than others when predicting medium- and long-term trajectories. When using the trajectory datasets without holding and a prediction time span of 10 min, compared to the convolutional neural network (CNN)-LSTM model, the C-CTGAN model reduces the mean absolute errors (MAEs) of core trajectory parameters, such as latitude, longitude, geometric altitude, and ground speed, by 69.89, 15.00, 74.07, and 84.21%, respectively. Compared to the original CTGAN model, the MAE is reduced by 20.43, 39.09, 31.98, and 17.07%, respectively. When using the trajectory datasets with holding, compared to the CNN-LSTM model, the C-CTGAN model shows MAE reductions of 14.08, 23.68, 31.46, and 2.86%, respectively. Compared to the original CTGAN, the reduction is 34.88, 2.69, 23.16, and 73.91%, respectively.

A method of enhanced shear wave elastography based on Chirp coded excitation.

Shear Wave Elastography (SWE) is an imaging technique that detects shear waves generated by tissue excited by Acoustic Radiation Force (ARF), and characterizes the mechanical properties of soft tissue by analyzing the propagation velocity of shear wave. ARF induces a change in energy density through the nonlinear propagation of ultrasound waves, which drives the tissue to generate shear waves. However, the amplitude of shear waves generated by ARF is weak, and the shear waves are strongly attenuated in vivo. Furthermore, the shear waves are usually drowned out by noise at deep locations, which presents a challenge in the detection of shear waves and low signal-to-noise ratios. In this paper, we investigate the feasibility of applying the Chirp coded signal for shear wave excitation (Chirp-SWE) in ARF-based shear wave elastography. The use of Chirp coded excitation of push waveforms was employed to enhance the action of ARF, thereby effectively exciting shear waves. Comparative experiments were carried out with conventional sine long pulses (SWE) and the Barker coded signal (Barker-SWE). The analysis of theoretical and simulation results revealed that Chirp-SWE could increase the excitation energy by approximately 10% compared to conventional SWE and Barker-SWE. The results of the elastic phantom experiments demonstrated that the average peak axial particle velocity obtained by Chirp-SWE was approximately 30%-50% higher, which facilitated the formation of a more stable shear wave. Additionally, it exhibited a higher signal-to-noise ratio during elasticity measurements. The in vitro liver experiments further validated the feasibility of implementing Chirp-SWE in tissues. The results demonstrated the feasibility and advantages of Chirp coded excitation of push waveforms in improving shear wave elastography results. It is expected that this will enhance the accuracy and robustness of soft tissue elastography.

Indented metallic bipolar plates for vanadium redox flow batteries

The standard industrial vanadium redox flow battery (VRFB) stack is made of thick graphite bipolar plates to support the flow field required for optimal circulation of electrolyte. These thick plates suffer from electrolyte seepage, poor mechanical properties, and high machining and processing costs. In the present study, we report on the use of metallic bipolar plates for the construction of the VRFB cell. We show, through comprehensive electrochemical and hydrodynamic investigations, that Hastelloy C276, a corrosion-resistant high Nickel alloy, is a suitable bipolar plate material in VRFB cells. We show further that surface texture modification, in the form of a mix of concave and convex spherical indentations on the metallic bipolar plate, can have beneficial effects on cell performance. Comparative experiments on medium-size cells of a nominal area of 440 cm2 operating in the current density range of 75–125 mA/cm2 show that discharge energy gains of 25% or higher can be obtained together with a 10–15% reduction in pressure drop in comparison with similar cells with flat bipolar plates. It is posited that the concave indentations spread over the entire area ensure uniform electrolyte circulation while regions of low and high electrode compression create flow channeling possibilities that lead to reduced pressure drop.

Analog Spiking U-Net integrating CBAM&ViT for medical image segmentation

SNNs are gaining popularity in AI research as a low-power alternative in deep learning due to their sparse properties and biological interpretability. Using SNNs for dense prediction tasks is becoming an important research area. In this paper, we firstly proposed a novel modification on the conventional Spiking U-Net architecture by adjusting the firing positions of neurons. The modified network model, named Analog Spiking U-Net (AS U-Net), is capable of incorporating the Convolutional Block Attention Module (CBAM) into the domain of SNNs. This is the first successful implementation of CBAM in SNNs, which has the potential to improve SNN model’s segmentation performance while decreasing information loss. Then, the proposed AS U-Net (with CBAM&ViT) is trained by direct encoding on a comprehensive dataset obtained by merging several diabetic retinal vessel segmentation datasets. Based on the experimental results, the provided SNN model achieves the highest segmentation accuracy in retinal vessel segmentation for diabetes mellitus, surpassing other SNN-based models and most ANN-based related models. In addition, under the same structure, our model demonstrates comparable performance to the ANN model. And then, the novel model achieves state-of-the-art(SOTA) results in comparative experiments when both accuracy and energy consumption are considered (Fig. 1). At the same time, the ablative analysis of CBAM further confirms its feasibility and effectiveness in SNNs, which means that a novel approach could be provided for subsequent deployment and hardware chip application. In the end, we conduct extensive generalization experiments on the same type of segmentation task (ISBI and ISIC), the more complex multi-segmentation task (Synapse), and a series of image generation tasks (MNIST, Day2night, Maps, Facades) in order to visually demonstrate the generality of the proposed method.

Study on PCD tool wear in pulsed laser assisted turning Al-50wt % Si alloy

Al-50wt % Si alloy is widely used in aerospace, automotive, electronic packaging and other fields due to its excellent material properties. However, the presence of reinforced particle phase differing in hardness from the alloy matrix phase leads to significant tool wear during turning with PCD tools. Therefore, this paper proposes a pulsed laser assisted turning (PLAT) method combining pulsed laser with conventional turning, which has unique advantages in reducing PCD tool wear. The effects of laser power, pulse width and frequency on tool wear during PLAT were studied by comparative experiments. And the potential mechanism of PLAT to reduce tool wear was revealed by finite element simulation. The results shown that PLAT effectively reduces PCD tool wear compared with conventional turning (CT). The increase of laser pulse width will aggravate tool wear. While, the increase of laser pulse frequency will reduce tool wear. Temperature is the main factor affecting the wear form. The tool mainly experiences abrasive wear at low temperature. However, the predominant type of tool wear shifts to adhesion as the increasing temperature. At the same time, EDS analysis shows that the rise in temperature results in an elevation of the O element content within the wear region, which proves that temperature is also the decisive factor affecting oxidative wear. This study provides valuable insights into actual machining involving Al-50wt % Si alloys and gives strategies for reducing PCD tool wear using PLAT.

A comparative study on drilling characteristics of unidirectional thermosetting CF/epoxy and thermoplastic CF/PEEK composites

Thermoplastic carbon fiber reinforced polyetheretherketone (CF/PEEK) composites are increasingly utilized as substitutes for thermosetting carbon fiber reinforced epoxy (CF/epoxy) composites in high-end equipment, due to their superior mechanical performance and sustainable manufacturability. For both composite components, drilling is an indispensable operation in the manufacturing process. To distinguish the drilling characteristics of the two composites, comparative experiments on drilling unidirectional CF/epoxy and CF/PEEK under different parameters were conducted in this paper. Several aspects, including chip formation, drilling temperature, thrust force, hole damage, and dimensional accuracy, were examined. Particularly, the impact of fiber cutting angle on exit and hole wall damage was considered. Results demonstrate that due to the higher ductility and toughness of PEEK, CF/PEEK produces continuous chips, higher drilling temperatures, higher thrust forces, and smaller damage areas than that of CF/epoxy. However, CF/PEEK has more serious hole wall subsurface damage and poorer dimensional accuracy since PEEK is sensitive to temperature. Consequently, unlike CF/epoxy, increasing spindle speeds at the low feed cannot improve the hole quality of CF/PEEK. Moreover, the hole damage distribution of both composites is strongly associated with the fiber cutting angle. This study provides guidance for high-performance machining of CF/PEEK.

ICH-PRNet: a cross-modal intracerebral haemorrhage prognostic prediction method using joint-attention interaction mechanism.

Accurately predicting intracerebral hemorrhage (ICH) prognosis is a critical and indispensable step in the clinical management of patients post-ICH. Recently, integrating artificial intelligence, particularly deep learning, has significantly enhanced prediction accuracy and alleviated neurosurgeons from the burden of manual prognosis assessment. However, uni-modal methods have shown suboptimal performance due to the intricate pathophysiology of the ICH. On the other hand, existing cross-modal approaches that incorporate tabular data have often failed to effectively extract complementary information and cross-modal features between modalities, thereby limiting their prognostic capabilities. This study introduces a novel cross-modal network, ICH-PRNet, designed to predict ICH prognosis outcomes. Specifically, we propose a joint-attention interaction encoder that effectively integrates computed tomography images and clinical texts within a unified representational space. Additionally, we define a multi-loss function comprising three components to comprehensively optimize cross-modal fusion capabilities. To balance the training process, we employ a self-adaptive dynamic prioritization algorithm that adjusts the weights of each component, accordingly. Our model, through these innovative designs, establishes robust semantic connections between modalities and uncovers rich, complementary cross-modal information, thereby achieving superior prediction results. Extensive experimental results and comparisons with state-of-the-art methods on both in-house and publicly available datasets unequivocally demonstrate the superiority and efficacy of the proposed method. Our code is at https://github.com/YU-deep/ICH-PRNet.git.

A computational fluid dynamics analysis of the aerodynamic influence of angles of attack on the Skylon spaceplane

This paper explores the aerodynamic behavior of a reusable launch vehicle, the Skylon spaceplane, for different angles of attack at Mach 5. The goal is to determine how aerodynamic effects manifest at various angles of attack and compare it with the theoretical data along with the determination of total time required for such computational fluid dynamics (CFD) simulations. The analysis focuses on the aerodynamics of the Skylon spaceplane and the Synergistic Air-Breathing Rocket Engine to understand their impact on single-stage reusable vehicles in the aerospace sector. This work is also crucial for paving the way for CFD simulations in future research in this sector. The total time consumed by the simulation and the possibility of using its data for other less time-consuming methods, such as convolutional neural networks, are considered. This research establishes a foundation for understanding the aerodynamic effects of specific angles of attack by comparing theoretical and simulation values. Results are produced for angles of attack of −60°, −45°, −30°, −15°, 0°, +15°, +30°, +45°, and +60° at Mach 5. The lift coefficient CL and drag coefficient CD are analyzed using the shear-stress transport k–ω model, and a comparison is made between the theoretical and simulated values. Finally, errors are calculated to understand the variation between the computed and theoretical values, as experimental data comparison is expensive and experimental data are often confidential.

Experimental Comparison of Single‐Fiber Bidirectional Amplification of O‐Band Bismuth‐Doped Fiber Amplifier Based on Coupler and Circulator

Experimental Comparison of Single‐Fiber Bidirectional Amplification of O‐Band Bismuth‐Doped Fiber Amplifier Based on Coupler and Circulator

Tsunami Debris Damming Forces and Associated Coefficients for Elevated Coastal Structure Columns: Experimental Comparison to ASCE 7-22 Minimum Design Loads

Tsunami Debris Damming Forces and Associated Coefficients for Elevated Coastal Structure Columns: Experimental Comparison to ASCE 7-22 Minimum Design Loads