Traditional Methods Research Articles

A Parametric Design Method for Engraving Patterns on Thin Shells.

Designing thin-shell structures that are diverse, lightweight, and physically viable is a challenging task for traditional heuristic methods. To address this challenge, we present a novel parametric design framework for engraving regular, irregular, and customized patterns on thin-shell structures. Our method optimizes pattern parameters such as size and orientation, to ensure structural stiffness while minimizing material consumption. Our method is unique in that it works directly with shapes and patterns represented by functions, and can engrave patterns through simple function operations. By eliminating the need for remeshing in traditional FEM methods, our method is more computationally efficient in optimizing mechanical properties and can significantly increase the diversity of shell structure design. Quantitative evaluation confirms the convergence of the proposed method. We conduct experiments on regular, irregular, and customized patterns and present 3D printed results to demonstrate the effectiveness of our approach.

Accurate Vision-Based PCB Positioning Using Cosine-Convolutional Neural Networks

Object positioning is a fundamental task for assembly and inspection operations in the electronic industry. Traditional methods such as template matching and feature-point detection have been applied for object positioning. They are however computationally expensive and are generally affected by environmental changes. Deep learning models based on Convolutional Neural Network (CNN) have also been used for object positioning. They are computationally very efficient but can be sensible under environmental variations such as illumination and noise. In this article, a Cosine-Convolution operation is proposed with the objective of minimizing the effects of illumination variations. The proposed Cosine-Convolution can substitute any convolutional operation in a CNN-based regressor for positioning tasks. The proposed convolution is based on cosine-measure that normalizes the convolution between an image window and a filter at local scope. The proposed Cosine-Convolutional Neural Network (Cosine-CNN) performs more accurate than the traditional CNN under environment variations, including illumination changes, noise, defocusing and template occlusion. The experimental results reveal that the proposed model can reach mean prediction errors smaller than 1 pixel and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1^\circ$</tex-math> </inline-formula> for object shift and rotation, regardless of the environmental variations. The method is computationally very fast, with an average evaluation time of 1.2-ms for real-time PCB positioning. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The training of deep learning models based on Convolutional Neural Network (CNN) can be tedious. Image samples with different illumination settings must be provided to have an efficient and robust model, which may not be easy to acquire or synthesize. This study proposes a solution to the challenge of illumination variations in images for the object positioning task in Printed Circuit Boards (PCB). A new Convolutional operation called Cosine-Convolutional that normalizes the traditional Convolution is introduced to overcome the illumination variations in the input images. Experimental results demonstrate that the proposed Cosine-Convolutional operation is less sensitive against lightning variations with respect to the training images.

Breast cancer detection employing stacked ensemble model with convolutional features.

Breast cancer is a major cause of female deaths, especially in underdeveloped countries. It can be treated if diagnosed early and chances of survival are high if treated appropriately and timely. For timely and accurate automated diagnosis, machine learning approaches tend to show better results than traditional methods, however, accuracy lacks the desired level. This study proposes the use of an ensemble model to provide accurate detection of breast cancer. The proposed model uses the random forest and support vector classifier along with automatic feature extraction using an optimized convolutional neural network (CNN). Extensive experiments are performed using the original, as well as, CNN-based features to analyze the performance of the deployed models. Experimental results involving the use of the Wisconsin dataset reveal that CNN-based features provide better results than the original features. It is observed that the proposed model achieves an accuracy of 99.99% for breast cancer detection. Performance comparison with existing state-of-the-art models is also carried out showing the superior performance of the proposed model.

Fast Clustering by Directly Solving Bipartite Graph Clustering Problem.

Spectral clustering (SC) has been widely used in many applications and shows excellent performance. Its high computational cost limits its applications; many strategies including the anchor technique can partly alleviate the high computational cost problem. However, early methods ignore the fact that SC usually involves two stages: relaxation and postprocessing, i.e., it relaxes the discrete constraints to continuous constraints, and then conducts the postprocessing to get the discrete solution, which is time-consuming and deviates from directly solving the primal problem. In this article, we first adopt the bipartite graph strategy to reduce the time complexity of SC, and then an improved coordinate descent (CD) method is proposed to solve the primal problem directly without singular value decomposition (SVD) and postprocessing, i.e., directly solving the primal problem not approximately solving. Experiments on various real-world benchmark datasets show that the proposed method can get better solutions faster with better clustering performance than traditional optimization methods. Furthermore, it can jump out of local minima of traditional methods and continue to obtain better local solutions. Moreover, compared with other clustering methods, it also shows its superiority.

Fast Clustering via Maximizing Adaptively Within-Class Similarity.

Clustering aims to make data points in the same group have higher similarity or make data points in different groups have lower similarity. Therefore, we propose three novel fast clustering models motivated by maximizing within-class similarity, which can obtain more instinct clustering structure of data. Different from traditional clustering methods, we divide all n samples into m classes by the pseudo label propagation algorithm first, and then m classes are merged to c classes ( ) by the proposed three co-clustering models, where c is the real number of categories. On the one hand, dividing all samples into more subclasses first can preserve more local information. On the other hand, proposed three co-clustering models are motivated by the thought of maximizing the sum of within-class similarity, which can utilize the dual information between rows and columns. Besides, the proposed pseudo label propagation algorithm can be a new method to construct anchor graphs with linear time complexity. A series of experiments are conducted on both synthetic and real-world datasets and the experimental results show the superior performance of three models. It is worth noting that for the proposed models, FMAWS2 is the generalization of FMAWS1 and FMAWS3 is the generalization of other two.

Multimodal Medical Image Fusion based on the VGG19 Model in the NSCT Domain

Aim: To deal with the drawbacks of the traditional medical image fusion methods, such as the low preservation ability of the details, the loss of edge information, and the image distortion, as well as the huge need for the training data for deep learning, a new multi-modal medical image fusion method based on the VGG19 model and the non-subsampled contourlet transform (NSCT) is proposed, whose overall objective is to simultaneously make the full use of the advantages of the NSCT and the VGG19 model. Methodology: Firstly, the source images are decomposed into the high-pass and low-pass subbands by NSCT, respectively. Then, the weighted average fusion rule is implemented to produce the fused low-pass sub-band coefficients, while an extractor based on the pre-trained VGG19 model is constructed to obtain the fused high-pass subband coefficients. Result and Discussion: Finally, the fusion results are reconstructed by the inversion transform of the NSCT on the fused coefficients. To prove the effectiveness and the accuracy, experiments on three types of medical datasets are implemented. Conclusion: By comparing seven famous fusion methods, both of the subjective and objective evaluations demonstrate that the proposed method can effectively avoid the loss of detailed feature information, capture more medical information from the source images, and integrate them into the fused images.

Shape-Scale Co-Awareness Network for 3D Brain Tumor Segmentation.

The accurate segmentation of brain tumor is significant in clinical practice. Convolutional Neural Network (CNN)-based methods have made great progress in brain tumor segmentation due to powerful local modeling ability. However, brain tumors are frequently pattern-agnostic, i.e. variable in shape, size and location, which can not be effectively matched by traditional CNN-based methods with local and regular receptive fields. To address the above issues, we propose a shape-scale co-awareness network (S2CA-Net) for brain tumor segmentation, which can efficiently learn shape-aware and scale-aware features simultaneously to enhance pattern-agnostic representations. Primarily, three key components are proposed to accomplish the co-awareness of shape and scale. The Local-Global Scale Mixer (LGSM) decouples the extraction of local and global context by adopting the CNN-Former parallel structure, which contributes to obtaining finer hierarchical features. The Multi-level Context Aggregator (MCA) enriches the scale diversity of input patches by modeling global features across multiple receptive fields. The Multi-Scale Attentive Deformable Convolution (MS-ADC) learns the target deformation based on the multiscale inputs, which motivates the network to enforce feature constraints both in terms of scale and shape for optimal feature matching. Overall, LGSM and MCA focus on enhancing the scale-awareness of the network to cope with the size and location variations, while MS-ADC focuses on capturing deformation information for optimal shape matching. Finally, their effective integration prompts the network to perceive variations in shape and scale simultaneously, which can robustly tackle the variations in patterns of brain tumors. The experimental results on BraTS 2019, BraTS 2020, MSD BTS Task and BraTS2023-MEN show that S2CA-Net has superior overall performance in accuracy and efficiency compared to other state-of-the-art methods. Code: https://github.com/jiangyu945/S2CA-Net.

Randomizing Human Brain Function Representation for Brain Disease Diagnosis.

Resting-state fMRI (rs-fMRI) is an effective tool for quantifying functional connectivity (FC), which plays a crucial role in exploring various brain diseases. Due to the high dimensionality of fMRI data, FC is typically computed based on the region of interest (ROI), whose parcellation relies on a pre-defined atlas. However, utilizing the brain atlas poses several challenges including 1) subjective selection bias in choosing from various brain atlases, 2) parcellation of each subject's brain with the same atlas yet disregarding individual specificity; 3) lack of interaction between brain region parcellation and downstream ROI-based FC analysis. To address these limitations, we propose a novel randomizing strategy for generating brain function representation to facilitate neural disease diagnosis. Specifically, we randomly sample brain patches, thus avoiding ROI parcellations of the brain atlas. Then, we introduce a new brain function representation framework for the sampled patches. Each patch has its function description by referring to anchor patches, as well as the position description. Furthermore, we design an adaptive-selection-assisted Transformer network to optimize and integrate the function representations of all sampled patches within each brain for neural disease diagnosis. To validate our framework, we conduct extensive evaluations on three datasets, and the experimental results establish the effectiveness and generality of our proposed method, offering a promising avenue for advancing neural disease diagnosis beyond the confines of traditional atlas-based methods. Our code is available at https://github.com/mjliu2020/RandomFR.

Identification of Cortex Cercis chinensis Decoction Pieces from Different Growth Origins Using Raman Spectroscopy

The complexity of traditional Chinese medicine (TCM) components and the time-consuming of traditional detection methods make it necessary and meaningful to establish rapid and efficient identification techniques. This study explores the potential of Raman spectroscopy, a non-destructive technique offering details of molecular structure, for rapid and accurate identification. Cortex Cercis chinensis (CCC) decoction pieces from diverse geographical origins, Anhui, Sichuan, Zhejiang, and Hubei, were collected and analyzed using Raman spectroscopy at 785 nm, and the Raman characteristic peaks were analyzed. MATLAB software was employed to analyze the similarity between the spectra of CCC decoction pieces, and the original Raman spectral data were transformed into first and second derivative spectra. The results revealed distinct Raman spectral characteristics of carbohydrates and glycosidic bonds (characteristic peaks at 480, 531, 549, 873, 946 and 1086 cm−1). The correlation coefficients of the all the four samples from different origins ranged from 0.9625 to 0.9912, while the coincidence coefficients ranged from 0.9602 to 0.9934. The first and second derivative demonstrated significantly different peaks within specific ranges, 180–200, 280–380, and 680–740 cm−1 for first derivatives, 160–300, 340–400 and 420–480 cm−1 for second derivatives. These obvious differences in first and second derivative spectra of Raman spectra of CCC decoction pieces demonstrated the different growth origins. In conclusion, the study demonstrated the ability of Raman spectroscopy to accurately differentiate CCC decoction pieces from different geographical growth origin. These findings provided a basis for further application of Raman spectra characteristic fingerprints to be used in quality control for rapid identification of the quality and origin of TCM raw materials.

A Deep Learning Approach Considering Image Background for Pneumonia Identification Using Explainable AI (XAI).

Pneumonia mainly refers to lung infections caused by pathogens, such as bacteria and viruses. Currently, deep learning methods have been applied to identify pneumonia. However, the traditional deep learning methods for pneumonia identification take less account of the influence of the lung X-ray image background on the model's testing effect, which limits the improvement of the model's accuracy. In this paper, we propose a deep learning method that considers image background factors and analyzes the proposed method with explainable deep learning for explainability. The essential idea is to remove the image background, improve the pneumonia recognition accuracy, and apply the Grad-CAM method to obtain an explainable deep learning model for pneumonia identification. In the proposed approach, (1) preliminary deep learning models for pneumonia X-ray image identification without considering the background are built; (2) deep learning models for pneumonia X-ray image identification with background consideration are built to improve the accuracy of pneumonia identification; (3) Grad-CAM method is employed to analyze the explainability. The proposed approach improves the accuracy of pneumonia identification, and the highest accuracy of VGG16 reaches 95.6%. The proposed approach can be applied to real pneumonia identification for early detection and treatment.

Effect of Combined Training With Balance, Strength, and Plyometrics on Physical Performance in Male Sprint Athletes With Intellectual Disabilities.

Individuals with intellectual disabilities often face unique challenges in physical capabilities, making traditional training methods less effective for their specific needs. This study aimed to investigate the effect of combining balance, plyometric, and strength (CBPS) training with sprint training on physical performance in male athletes with intellectual disabilities. Twenty-seven participants were randomly assigned to either a CBPS group or a control group that only maintained their regular sprint training. Participants underwent pre- and posttraining tests, including measures of balance, jumping, agility, and sprinting ability. The results showed that the CBPS group demonstrated significant improvements (p < .05) in one-leg stance, crossover-hop jump, squat jump, countermovement jump, and 10- and 30-m sprint at posttraining compared with pretraining. CBPS training combined with sprinting significantly improves physical performance in male athletes with intellectual disabilities, suggesting implications for tailored training programs to enhance their physical fitness and overall health.

Stress Classification and Vital Signs Forecasting for IoT-Health Monitoring.

Health monitoring embedded with intelligence is the demand of the day. In this era of a large population with the emergence of a variety of diseases, the demand for healthcare facilities is high. Yet there is scarcity of medical experts, technicians for providing healthcare to the people affected with some medical problem. This article presents an Internet of Things (IoT) system architecture for health monitoring and how data analytics can be applied in the health sector. IoT is employed to integrate the sensor information, data analytics, machine intelligence and user interface to continuously track and monitor the health condition of the patient. Considering data analytics as the major part, we focused on the implementation of stress classification and forecasted the future values from the recorded data using sensors. Physiological vitals like Pulse, oxygen level percentage (SpO2), temperature, arterial blood pressure along with the patients age, height, weight and movement are considered. Various traditional and ensemble machine learning methods are applied to stress classification data. The experimental results have shown that a hypertuned random forest algorithm has given a better performance with an accuracy of 94.3%. In a view that knowing the future values in prior helps in quick decision making, critical vitals like pulse, oxygen level percentage and blood pressure have been forecasted. The data is trained with ML and neural network models. GRU model has given better performance with lower error rates of 1.76, 0.27, 5.62 RMSE values and 0.845, 0.13, 2.01 MAE values for pulse, SpO2 and blood pressure respectively.

Quality and Quantity Control of Mitochondria Injection Into Single Cells With Robot-Aided Micro-Manipulation System

Mitochondrial dysfunction plays a significant role in the development of fatal diseases such as aging, cancer, and Alzheimer’s. Transferring mitochondria to cells is a new and potential treatment for mitochondrial DNA (mtDNA)-related illnesses. This article describes a novel technique to control the quality and quantity of mitochondria injected into single live cells using a robot-aided microneedle and optical tweezers (OTs)-based micromanipulation system. Isolated mitochondria and cells are patterned in a 1-dimensional (1-D) array in a microfluidic device, and a robot-aided microneedle collects the predefined number of functional mitochondria with the help of OTs. Then, the microneedle precisely and non-invasively injects these collected mitochondria into single live cells. Given that the two manipulation tools of OTs and microneedle were used, a switch controller strategy is developed to enable mitochondria trapping and injection with OTs and microneedle-based micromanipulator, respectively. The effectiveness of the developed robotic system is experimentally demonstrated with automated injections of isolated mitochondria into HeLa and mesenchymal stem cells (aMSCs). A precise and efficient quality and quantity control of mitochondria injection was possible by using Ots in conjunction with microneedle and microfluidics technologies. Quality-and quantity-controlled ability is analyzed and compared with the traditional mitochondria transfer method (co-culture). Biological tests are further conducted to assess the viability of mitochondria recipient cells. Experimental results demonstrate that the developed system can non-invasively transfer healthy mitochondria into single live cells while precisely controlling the quantity and quality of injected mitochondria. The proposed mitochondrial transfer method has the potential to advance precision medicine methods, particularly for cellular therapy of (mtDNA)-related diseases. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This study was motivated by the problem of inefficient methods of mitochondria injection into single, small, living cells. Due to the issue of microneedle clogging, existing mitochondria injection methods can only inject mitochondria into cells with a 0.3 to 2% efficiency. To address this issue, we have developed an automated method of mitochondria injection into cells that can inject mitochondria into single cells non-invasively with an efficiency of up to 80 %. Existing methods of mitochondria injection also ignored the heterogeneity of mitochondria, such as functionality and the precise number of mitochondria prior to injection. Our methodology can efficiently and precisely control the quality and quantity of mitochondria injection into single cells, which can be useful for the discovery of new information concerning precision medicine, particularly in diseases associated with mtDNA.

Segmentation Method of Concrete Small Cracks Based on UAV Images

Introduction:: Cracks are one of the major problems in modern concrete buildings, especially in locations that are difficult to map manually, such as bridges and high-rise buildings. Accurate analysis of unmanned aerial vehicle (UAV) images has become the key to determining whether a building needs maintenance. Methods:: Traditional image processing methods are easily interfered by high-frequency background. Neural network methods need fine datasets, which increase labor costs. Therefore, this paper proposes a segmentation algorithm based on UNet3+ network. After obtaining the UAV image, the rough location of the crack can be obtained by only rough labeling. And then, the sample balance can be carried out by clipping the target area. The UNet3+ network is used to train the processed datasets and extract the region of interest to ignore the non-target texture. Finally, the region of interest is further segmented by color clustering and edge detection methods. Results:: The proposed method can detect the cracks accurately. In all test images, the relative errors are less than 13%. Especially in test images whose width is less than 0.2mm, the maximum absolute error is only 0.0237mm, which is completely acceptable in actual production. The proposed method has higher practicability in the detection of concrete crack images taken by UAV. The results show that the proposed method outperforms the cutting-edge method published in the journal "Sensor", when the background is complex. Conclusion:: The proposed method can segment and detect cracks effectively, which can remove the high-frequency interference region from the images.

Learning-Assisted Fast Determination of Regularization Parameter in Constrained Image Reconstruction.

To leverage machine learning (ML) for fast selection of optimal regularization parameter in constrained image reconstruction. Constrained image reconstruction is often formulated as a regularization problem and selecting a good regularization parameter value is an essential step. We solved this problem using an ML-based approach by leveraging the finding that for a specific constrained reconstruction problem defined for a fixed class of image functions, the optimal regularization parameter value is weakly subject-dependent and the dependence can be captured using few experimental data. The proposed method has four key steps: a) solution of a given constrained reconstruction problem for a few (say, 3) pre-selected regularization parameter values, b) extraction of multiple approximated quality metrics from the initial reconstructions, c) predicting the true quality metrics values from the approximated values using pre-trained neural networks, and d) determination of the optimal regularization parameter by fusing the predicted quality metrics. The effectiveness of the proposed method was demonstrated in two constrained reconstruction problems. Compared with L-curve-based method, the proposed method determined the regularization parameters much faster and produced substantially improved reconstructions. Our method also outperformed state-of-the-art learning-based methods when trained with limited experimental data. This paper demonstrates the feasibility and improved reconstruction quality by using machine learning to determine the regularization parameter in constrained reconstruction. The proposed method substantially reduces the computational burden of the traditional methods (e.g., L-curve) or relaxes the requirement of large training data by modern learning-based methods, thus enhancing the practical utility of constrained reconstruction.

Autonomous Vision-Based Navigation and Stability Augmentation Control of a Biomimetic Robotic Hammerhead Shark

The application potential of robotic fish embedded with intelligent visual navigation algorithms in underwater autonomous operation is on full display recently. However, the existing visual navigation methods are limited by the underwater visual conditions and the motion characteristics of robotic fish. To this end, this paper proposes a novel autonomous navigation framework integrated with visual stabilization control. In practice, a stereo vision-based navigation network is proposed to generate the guidance law. On this basis, a biomimetic robotic hammerhead shark with a controllable cephalofoil is developed, and a nonlinear model predictive controller for cephalofoil stabilization relying on the dynamic model is elaborately designed. Extensive simulations and underwater experiments are conducted to validate the effectiveness and superiority of the proposed methods, which significantly enhance exploration efficiency and reduce image jitter by 26.02% compared to the traditional methods. The obtained results provide a new idea for underwater robots to autonomously explore the ocean. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper is motivated by the problem of vision-based underwater autonomous navigation for a biomimetic robotic fish that possesses underwater visual stability and good maneuverability. The existing visual navigation networks usually generate unexpected navigation instructions when dealing with complex or ambiguous underwater scenes. Additionally, image jitter caused by the rhythmic motion of robotic fish can lead to navigation failure. This paper suggests an integrated navigation framework that includes a biomimetic platform design, a visual stabilization controller, and an intelligent underwater navigation network. Specifically, a novel sphyrnidae-inspired robotic shark is designed as a new platform with superior motion performance. To enhance underwater visual stability, a nonlinear model predictive control-based visual stabilization controller is proposed. Furthermore, a deep stereo attention navigation network based on a parallax attention mechanism is proposed to improve the generalization of vision-based autonomous navigation. A series of underwater search experiments on the robotic shark demonstrate the effectiveness and superiority of the proposed navigation framework. Hopefully, our proposed methods can provide valuable guidance and support for universal underwater robot navigation to accomplish practical marine tasks, such as underwater rescue, resource exploitation, biological observation, and so on.

A Multivariable, Adaptive, Robust, Primary Control Enforcing Predetermined Dynamics of Interest in Islanded Microgrids Based on Grid-Forming Inverter-Based Resources

This paper proposes a multivariable, adaptive, robust (MAR) control strategy for islanded inverter-based resources (IBRs) operating as grid-forming inverters. The proposed method is employed in the inner control loop of the primary layer in the hierarchical or decentralized structures for the islanded operation of microgrids. The MAR control scheme is responsible for stabilizing IBRs’ output voltage in autonomous operations of microgrids, considering mismatched input voltage disturbances from the grid side and a large amount of system uncertainty. The control methodology introduced in this paper does not rely on the system’s physical parameters, such as microgrid topology, load dynamics, LCL filters, and output connectors. As a result, there is no need to know the nominal values or the bounds of uncertainties in system dynamics. The MAR control method uses online adaptation rules first to identify and then adjust the control parameters of the closed-loop system based on an arbitrary dynamic model. In other words, the MAR method replaces the actual dynamics of IBRs with predetermined dynamics of interest. Simulation results in the MATLAB/Simulink environment confirm the capability of the scheme introduced for the closed-loop stabilization and voltage regulation in the presence of disturbances and a significant amount of uncertainty under various case studies; moreover, comparative simulations by comparing the presented method with other studies using sliding mode control are provided. Finally, experiments verify the effectiveness and practicality of the proposed MAR control scheme. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Inverter-based resources are integral parts of current and especially future power and energy systems; with increasing concerns about carbon footprints, the tendency to substitute traditional synchronous generators with inverter-based resources increases. This transition towards the widespread use of power electronics devices needs careful studies regarding the stability and control of power converters. Although existing studies are addressing potential control system challenges, they suffer from complex mathematical computations and the need for the system’s preliminary information. With this in mind, this study proposes a multivariable, adaptive, robust control strategy for the inner voltage control loop of grid-forming inverters. This method utilizes online estimation algorithms to identify inverter-based resources’ parameters and tune control system parameters simultaneously, making it applicable even to cases with slow parameter variations caused by aging or environmental changes. It can compensate for potential voltage disturbances from the grid side and enable the designer to replace undesirable dynamics of inverter-based resource units with arbitrary and stable dynamics of interest. In fact, unlike traditional methods that need control parameters and gains to be tuned to achieve a proper dynamic response, the control system designer can choose reference dynamics and enforce the closed-loop system to imitate the dynamical model selected. This model is usually chosen based on established priorities, such as response time and other transient behaviors. Moreover, this method does not require complex mathematical and algebraic calculations to design and implement. It can be easily applied to inverter-based resource units after selecting the desired reference dynamics, as shown through this study’s experimental result. The above points give this method a competitive edge over the existing algorithms, especially in practical applications.

Reducing the Impact of Time Evolution on Source Code Authorship Attribution via Domain Adaptation

Source code authorship attribution is an important problem in practical applications such as plagiarism detection, software forensics, and copyright disputes. Recent studies show that existing methods for source code authorship attribution can be significantly affected by time evolution, leading to a decrease in attribution accuracy year by year. To alleviate the problem of Deep Learning (DL)-based source code authorship attribution degrading in accuracy due to time evolution, we propose a new framework called Time D omain A daptation (TimeDA) by adding new feature extractors to the original DL-based code attribution framework that enhances the learning ability of the original model on source domain features without requiring new or more source data. Moreover, we employ a centroid-based pseudo-labeling strategy using neighborhood clustering entropy for adaptive learning to improve the robustness of DL-based code authorship attribution. Experimental results show that TimeDA can significantly enhance the robustness of DL-based source code authorship attribution to time evolution, with an average improvement of 8.7% on the Java dataset and 5.2% on the C++ dataset. In addition, our TimeDA benefits from employing the centroid-based pseudo-labeling strategy, which significantly reduced the model training time by 87.3% compared to traditional unsupervised domain adaptive methods.

ИССЛЕДОВАНИЕ ТЕХНИЧЕСКИХ РЕШЕНИЙ ПО РЕАЛИЗАЦИИ НАГРУЗОЧНОГО МОМЕНТА ПРИ ИСПЫТАНИИ ЭЛЕКТРИЧЕСКИХ МАШИН

The main methods of testing electrical machines are considered. It has been determined that the tradi-tional method of implementing the load moment has significant limitations. It is proposed to use an electromagnetic brake based on a hysteresis machine. This method of organizing the load torque is universal and can be used to test machines of different power and rotation speed

Enhancing pier local scour prediction in the presence of floating debris

AbstractLocal scour poses a grave threat to bridge foundations, potentially causing catastrophic collapses. This study uses FLOW-3D with the Reynolds-Averaged Navier-Stokes model to analyze pier scour and dune formation under bridges. It focuses on submerged debris shapes near the water's surface. Results closely match experiments when specific conditions are met. The study introduces an innovative approach to debris impact assessment. Instead of traditional methods, it proposes a novel equation accounting for debris's effective area and elevation. This enhances reliability by over 20%, improving scour depth assessment in debris-laden scenarios. This advances the understanding of debris's role in local scour, benefiting bridge design and management practices.