Single Network Research Articles

Predicting soccer matches with complex networks and machine learning

Abstract Soccer attracts the attention of many researchers and professionals in the sports industry. Therefore, the incorporation of science into the sport is constantly growing, with increasing investments in performance analysis and sports prediction industries. This study aims to (i) highlight the use of complex networks as an alternative tool for predicting soccer match outcomes and (ii) show how the combination of structural analysis of passing networks with match statistical data can provide deeper insights into the game patterns and strategies used by teams. In order to do so, complex network metrics and match statistics were used to build machine learning models that predict the wins and losses of soccer teams in different leagues. The results showed that models based on passing networks were as effective as ‘traditional’ models, which use general match statistics. Another finding was that by combining both approaches, more accurate models were obtained than when they were used separately, demonstrating that the fusion of such approaches can offer a deeper understanding of game patterns, allowing the comprehension of tactics employed by teams relationships between players, their positions and interactions during matches. It is worth mentioning that both network metrics and match statistics were important and impactful for the mixed model. Furthermore, the use of networks with a lower granularity of temporal evolution (such as creating a network for each half of the match) performed better than a single network for the entire game.

Combined Keyword Spotting and Localization Network Based on Multi-Task Learning

The advent of voice assistance technology and its integration into smart devices has facilitated many useful services, such as texting and application execution. However, most assistive technologies lack the capability to enable the system to act as a human who can localize the speaker and selectively spot meaningful keywords. Because keyword spotting (KWS) and sound source localization (SSL) are essential and must operate in real time, the efficiency of a neural network model is crucial for memory and computation. In this paper, a single neural network model for KWS and SSL is proposed to overcome the limitations of sequential KWS and SSL, which require more memory and inference time. The proposed model uses multi-task learning to utilize the limited resources of the device efficiently. A shared encoder is used as the initial layer to extract common features from the multichannel audio data. Subsequently, the task-specific parallel layers utilize these features for KWS and SSL. The proposed model was evaluated on a synthetic dataset with multiple speakers, and a 7-module shared encoder structure was identified as optimal in terms of accuracy, direction of arrival (DOA) accuracy, DOA error, and latency. It achieved a KWS accuracy of 94.51%, DOA error of 12.397°, and DOA accuracy of 89.86%. Consequently, the proposed model requires significantly less memory owing to the shared network architecture, which enhances the inference time without compromising KWS accuracy, DOA error, and DOA accuracy.

Molecular spectral line data preprocessing container load grouping prediction algorithm based on EMD-LSTM

Unbalanced allocation of container resources in cluster environments is an urgent problem to be solved. Aiming at container load prediction and resource allocation strategy, this paper designs an astronomical data processing container load grouping prediction algorithm based on empirical mode decomposition-long short-term memory network, and proposes an adaptive recommendation value generation algorithm based on predicted load information, which can automatically allocate container computing resources according to the degree of load fluctuation. The load prediction accuracy is verified using simulated data and real astronomical observation data. The experimental results show that the algorithm proposed in this paper has higher prediction accuracy than the triple index method and the single long short-term memory network model. In the real-time preprocessing test of astronomical data, the recommendation value generation algorithm proposed in this paper can effectively improve the utilization efficiency of computing resources compared with the default strategy.

Self-supervised image change detection method based on lightweight capsule network

In response to the significant impact of speckle noise on the accuracy of SAR image change detection, the high complexity of existing capsule network based image change detection methods, and the loss of a large amount of original image information in training samples, this paper proposes a self supervised image change detection method based on the Light Capsule Network (SCapsNet). First, the log ratio operator difference graph is generated, and the "pseudo label" of training samples with high confidence is obtained through the maximum inter class variance method and fuzzy C-means clustering method, which lays the foundation for self-supervised learning; Secondly, construct a three channel training sample based on the difference map of two temporal SAR images and logarithmic ratio operators to maximize the preservation of sample information; Then, SCapsNet is designed to extract training sample features through single scale convolution, and a single scale capsule network is used to mine spatial relationships between features; Finally, comparative experiments and ablation experiments were set up and tested on 5 real SAR Datasets. The experimental results show that the The advantage of this method is to improve the operational efficiency of the method while reducing model complexity, obtain stronger robust features, suppress the adverse impact of speckle noise on change detection performance, and improve change detection performance.

Predicting Bacterial Antibiotic Resistance using MALDI-TOF Mass Spectrometry Databases with ELM Applications.

Early detection of antibiotic resistance is a crucial task, especially for vulnerable patients under prolonged treatments with a single antibiotic. To solve this, machine learning approaches have been reported in the state of art. Researchers have used MALDI-TOF MS in order to predict antibiotic resistance and/or susceptibility in bacterial samples. Weis, et al. implemented LR, LightGBM and ANN to study the antibiotic resistance on bacterial strains of Escherichia Coli, Staphylococcus Aureus, and Klebsiella Pneumoniae. Despite promising results, the models have not achieved perfect accuracy, specifically when the classes are unbalanced. On the other hand, Extreme Learning Machine (ELM) is a training algorithm for forward propagation of single hidden layer neural networks, which converges much faster than traditional methods and offers promising performance along with less programmer intervention. In this way, this study introduced improved ELMs, including two weighted ELMs proposed by Zong, and the SMOTE technique in order to create new synthetic samples of the minority class. After heuristic optimization of ELM hiper-parameters, results demonstrated 85% in accuracy and 85% in geometric mean for the classification problem in the case of weighted ELM 1 subject to the SMOTE technique of oversampling.

GRU-IKF scene taxiing trajectory prediction model based on attention mechanism

Aircraft taxi trajectory prediction helps solve operational problems such as airport taxiing conflicts and long waiting times, ensuring airport safety while improving service levels and increasing airport throughput. In view of the fact that the performance of machine learning models depends on good data sets, a method for predicting taxi trajectories of aircraft on the ground based on attention mechanism, fusion of gated recurrent unit (GRU) and improved Kalman filter algorithm (IKF) is proposed. Firstly, three independent gated recurrent unit networks are used to capture the motion state and temporal dependency of aircraft at future moments, and the attention mechanism is introduced to enhance the ability to extract data difference features and learn the mapping relationship from input to output; then, it is fused with the improved extended Kalman filter to integrate the output results of the neural network into the state prediction and update process to improve the accuracy of the predicted trajectory sequence. Finally, the effectiveness of the model was verified using the actual taxiing trajectory of aircraft at Lukou Airport. The simulation results show that the model can effectively and accurately predict the taxiing trajectory of aircraft on the surface, with an overall mean square error of about 0.00128. Compared with the single recurrent neural network (RNN), long short-term memory network (LSTM) and GRU model, the RMSE is reduced by 72.9%and respectively 39.9%, 54.7%and the prediction time is 40 ms. It can accurately and quickly predict the taxiing trajectory, which helps to reduce the operating load of the airport surface management system.

Image Stitching of Low-Resolution Retinography Using Fundus Blur Filter and Homography Convolutional Neural Network

Great advances in stitching high-quality retinal images have been made in recent years. On the other hand, very few studies have been carried out on low-resolution retinal imaging. This work investigates the challenges of low-resolution retinal images obtained by the D-EYE smartphone-based fundus camera. The proposed method uses homography estimation to register and stitch low-quality retinal images into a cohesive mosaic. First, a Siamese neural network extracts features from a pair of images, after which the correlation of their feature maps is computed. This correlation map is fed through four independent CNNs to estimate the homography parameters, each specializing in different corner coordinates. Our model was trained on a synthetic dataset generated from the Microsoft Common Objects in Context (MSCOCO) dataset; this work added an important data augmentation phase to improve the quality of the model. Then, the same is evaluated on the FIRE retina and D-EYE datasets for performance measurement using the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The obtained results are promising: the average PSNR was 26.14 dB, with an SSIM of 0.96 on the D-EYE dataset. Compared to the method that uses a single neural network for homography calculations, our approach improves the PSNR by 7.96 dB and achieves a 7.86% higher SSIM score.

Investigating 10 Yr of Volcanoacoustic Activity at Tungurahua Volcano, Ecuador, Aided by Machine Learning

Abstract Here, we present the results of applying diverse data processing and machine learning tools to investigate a very large dataset obtained from single station infrasonic recordings from the last 10 yr of the most recent period of explosive activity at Tungurahua volcano, Ecuador. To increase the quality and quantity of information extracted from the large data set and enhance pattern recognition, we combined traditional techniques with more recent ones. We divided the investigation into sequential steps: detection, discrimination, cleaning, and clustering. For the detection step, we tested the classical short-term average/long-term average algorithm and an algorithm specific for explosions detection called “Volcanic INfrasound Explosions Detector Algorithm (VINEDA)” and detected 118,516 events. To clean the detected signals from potential false positives, we used supervised classification that reduced the events to 75,483, and a catalog cleaning procedure using shallow learners including support vector machines, random forests, and a single layer neural network, trained using data from a manual catalog, to a final number of 36,359 events. This led to a sixfold increase in detected explosions compared to the manual catalog. Then, we applied hierarchical clustering to a well-studied time window of activity using two independent difference metrics: dynamic time warping and waveform cross correlation and showed the insights and drawbacks from this approach. We showed that the different techniques were able to reveal repeating and striving events between selected different eruptive phases and associated them to possible changes in eruptive dynamics. Finally, to analyze the whole dataset at once we used a convolutional autoencoder network and obtained similar results to the classical clustering in a fraction of the time. We identified different families of explosions that appeared, sometimes intermittently, and revealed various potentially competing eruptive processes during the whole time period.

Integrating Whole Slide Imaging and Artificial Intelligence Provides Higher Accuracy in Thyroid Cytology

Abstract Introduction/Objective The aim of the study is to evaluate the potential advantages of integrating Whole Slide Imaging (WSI) and Artificial Intelligence (AI) to increase efficiency and diagnostic accuracy in thyroid cytology, especially in indeterminate lesions. Methods/Case Report A retrospective database search from 2000-2023 was performed, and the concordance with the pathologists was evaluated based on the manual or AI-based Region of Interest (ROI) identification, the best- suited AI, algorithm design, color enhancement, and combination of AI and Electronic Medical Records (EMR). Results (if a Case Study enter NA) The cohort included 3285 WSI and 121,384 ROI. In 109 WSI with manually diagnosed ROI, Deep learning successfully predicted benign and malignant cases, including 11 indeterminate cases, with zero false positives or negatives for 35% of cases. In the second study with 908 WSI, 4494 ROI were identified with Convolutional Neural Network (CNN). A higher area under the curve (AUC) resulted when EMR and Machine Learning algorithm (MLA) were integrated: EMR: 0.931, MLA: 0932, EMR+ MLA; 0.962, Sensitivity: 92.0%, Specificity 90.5%. In the next study with 145 WSI, the CNN-identified ROI was presented to the same pathologist after 117 days. Perfect concordance was seen between the two methods (K score 0.924, time to diagnosis;81.59 Second). In 360 WSI, YOLOV4 algorithm was trained to detect the ROI, and detection and classification rates were used to evaluate the accuracy. It had a precision of 81.84% (3.16% more than the single detection networks of 78.68%). In the last study with 964 WSI, color augmentation improved the AUC for indeterminate cases from 88.3% to 96.2%. Conclusion CNN is a better-suited AI for whole slide imaging due to its compatibility with image data and ability to automatically detect important features without human supervision. It also removes the component of subjective bias in interpretation. Color augmentation and integration of EMR can overcome the unique challenges in thyroid indeterminate cytology.

Deep learning architecture for scatter estimation in cone-beam computed tomography head imaging with varying field-of-measurement settings.

X-ray scatter causes considerable degradation in the cone-beam computed tomography (CBCT) image quality. To estimate the scatter, deep learning-based methods have been demonstrated to be effective. Modern CBCT systems can scan a wide range of field-of-measurement (FOM) sizes. Variations in the size of FOM can cause a major shift in the scatter-to-primary ratio in CBCT. However, the scatter estimation performance of deep learning networks has not been extensively evaluated under varying FOMs. Therefore, we train the state-of-the-art scatter estimation neural networks for varying FOMs and develop a method to utilize FOM size information to improve performance. We used FOM size information as additional features by converting it into two channels and then concatenating it to the encoder of the networks. We compared our approach for a U-Net, Spline-Net, and DSE-Net, by training them with and without the FOM information. We utilized a Monte Carlo-simulated dataset to train the networks on 18 FOM sizes and test on 30 unseen FOM sizes. In addition, we evaluated the models on the water phantoms and real clinical CBCT scans. The simulation study demonstrates that our method reduced average mean-absolute-percentage-error for U-Net by 38%, Spline-Net by 40%, and DSE-net by 33% for the scatter estimation in the 2D projection domain. Furthermore, the root-mean-square error on the 3D reconstructed volumes was improved for U-Net by 43%, Spline-Net by 30%, and DSE-Net by 23%. Furthermore, our method improved contrast and image quality on real datasets such as water phantom and clinical data. Providing additional information about FOM size improves the robustness of the neural networks for scatter estimation. Our approach is not limited to utilizing only FOM size information; more variables such as tube voltage, scanning geometry, and patient size can be added to improve the robustness of a single network.

Research on the prediction of blasting fragmentation in open-pit coal mines based on KPCA-BAS-BP

The blasting block size of open-pit mines is influenced by many factors, and the influencing factors have a very complex nonlinear relationship. Traditional empirical formulas and a single neural network model cannot meet the requirements of modern blasting safety. To improve the prediction accuracy of blasting block size, the measured data of Beskuduk open-pit coal mine is used as training and testing samples. Seven factors including rock tensile strength, rock compressive strength, and blast hole spacing are selected as input variables of the prediction model. The average size of blasting fragmentation X50 is used as the output variable of the prediction model. The kernel principal component analysis (KPCA) is adopted to reduce the dimensionality of the input variables. The beetle antennae search algorithm (BAS) is selected to optimize the parameters of the initial weights and thresholds of the back propagation (BP) neural network. Finally, prediction model of blasting fragmentation in open-pit coal mine based on KPCA-BAS-BP is established. The results show that the average relative error of the model is 1.77%, and the root mean square error is 1.52%. Compared with the unoptimized BP neural network and the BP neural network optimized by the artificial bee colony algorithm (ABC) model, this model has higher prediction accuracy and is more suitable for predicting the blasting block size of open-pit coal mines, it provides a new method for predicting the fragmentation of blasting under the influence of multiple factors, filling the gap in related theoretical research, and has certain practical application value.

Smart photonic crystal hydrogels for visual glucose monitoring in diabetic wound healing

Diabetes is a global chronic disease that seriously endangers human health and characterized by abnormally high blood glucose levels in the body. Diabetic wounds are common complications which associate with impaired healing process. Biomarkers monitoring of diabetic wounds is of great importance in the diabetes management. However, actual monitoring of biomarkers still largely relies on the complex process and additional sophisticated analytical instruments. In this work, we prepared hydrogels composed of different modules, which were designed to monitor different physiological indicators in diabetic wounds, including glucose levels, pH, and temperature. Glucose monitoring was achieved based on the combination of photonic crystal (PC) structure and glucose-responsive hydrogels. The obtained photonic crystal hydrogels (PCHs) allowed visual monitoring of glucose levels in physiological ranges by readout of intuitive structural color changes of PCHs during glucose-induced swelling and shrinkage. Interestingly, the glucose response of double network PCHs was completed in 15 min, which was twice as fast as single network PCHs, due to the higher volume fraction of glucose-responsive motifs. Moreover, pH sensing was achieved by incorporation of acid-base indicator dyes into hydrogels; and temperature monitoring was obtained by integration of thermochromic powders in hydrogels. These hydrogel modules effectively monitored the physiological levels and dynamic changes of three physiological biomarkers, both in vitro and in vivo during diabetic wound healing process. The multifunctional hydrogels with visual monitoring of biomarkers have great potential in wound-related monitoring and treatment.Graphical abstract

Comparison of deep-learning multimodality data fusion strategies in mandibular osteoradionecrosis NTCP modelling using clinical variables and radiation dose distribution volumes

Objective.Normal tissue complication probability (NTCP) modelling is rapidly embracing deep learning (DL) methods, acknowledging the importance of spatial dose information. Finding effective ways to combine information from radiation dose distribution maps (dosiomics) and clinical data involves technical challenges and requires domain knowledge. We propose different multi-modality data fusion strategies to facilitate future DL-based NTCP studies.Approach.Early, joint and late DL multi-modality fusion strategies were compared using clinical and mandibular radiation dose distribution volumes. These were contrasted with single-modality models: a random forest trained on non-image data (clinical, demographic and dose-volume metrics) and a 3D DenseNet-40 trained on image data (mandibular dose distribution maps). The study involved a matched cohort of 92 osteoradionecrosis cases and 92 controls from a single institution.Main results.The late fusion model exhibited superior discrimination and calibration performance, while the join fusion achieved a more balanced distribution of the predicted probabilities. Discrimination performance did not significantly differ between strategies. Late fusion, though less technically complex, lacks crucial inter-modality interactions for NTCP modelling. In contrast, joint fusion, despite its complexity, resulted in a single network training process which included intra- and inter-modality interactions in its model parameter optimisation.Significance.This study is a pioneering effort in comparing different strategies for including image data into DL-based NTCP models in combination with lower dimensional data such as clinical variables. The discrimination performance of such multi-modality NTCP models and the choice of fusion strategy will depend on the distribution and quality of both types of data. Multiple data fusion strategies should be compared and reported in multi-modality NTCP modelling using DL.

Toughening Healable Supramolecular Double Polymer Networks Based on Hydrogen Bonding and Metal Coordination.

Double polymer networks (DNs) consist of two interpenetrating polymer networks and can offer properties that are not merely a sum of the parts. Here, we report an elastic DN made from two supramolecular polymers (SMPs) that consist of the same poly(n-butyl acrylate) (BA) backbone. The two polymers feature different non-covalent binding motifs, which form dynamic, reversible cross-links. The polymers were prepared by reversible addi-ti-on-frag-mentation chain-transfer polymerization of n-butyl acrylate and either the self-complementary hydrogen-bonding motif 2-ureido-4[1H]pyri-mi-dinone, or the 2,6-bis(1'-methyl-benz--imidazolyl)-pyridine ligand, which forms complexes with metal ions. The supramolecular DN made by these components combines features of the single networks, including high thermal stability and resistance to creep. The DN further exhibits excellent healability and displays a higher extensibility and a higher toughness than its constituents. The mechanical characteristics of the DN can be further enhanced by selectively pre-stretching one of the networks, which is readily possible due to the reversible formation of the supramolecular cross-links and their orthogonal stimuli-responsive-ness.

The Method of Diversity-Based Ensuring the Reliability of the Router in the IIoT System

The architecture of the Industrial Internet of Things (IIoT) system assumes the presence of a router as the main subsystem, which will allow connecting the subsystems into a single network and connecting them to the equipment of the Internet service provider. Failure of the router can lead to downtime of industrial equipment and the whole workshop at the industrial enterprise, and to the failure of the IIoT system as a whole. Control processing units of industrial routers (RCPU) are complex microprocessor systems (MS). Violation of their operability can be caused by both hardware (HW) and software (SW) failures. Therefore, to increase the reliability of RCPU it is reasonable to use such methods of reliability assurance as HW redundancy (duplication of processors with comparison of results), as well as the use of modern means of control and diagnostics. However, the number of HW and SW failures in RCPUs, is still quite high. In this connection, the solution of issues related to the development of methods for ensuring high reliability of RCPU is of great urgency. This paper proposes a method of ensuring the reliability of RCPU using SW diversity on the basis of priority series. The method let to choose the variant of redundancy of HW and the number of versions of SW as diversity in RCPU.

Collapse of G+/G- bands, modification of Breit–Wigner–Fano signals and structural amorphization in single wall carbon nanotube networks under great excess of sulfur

The identification of superconductivity and ferromagnetic to superconductive transitions in sulfur-modified carbons has recently attracted an important attention. Additional work is however needed to better understand the structural modification of the graphitic interfaces in presence of sulfur. Here we report on an advanced methodology which involves soaking of large amounts (in the order of 500 mg) of sulfur through several annealing cycles into bundles comprising of hollow single-wall/few-wall carbon nanotubes (SWCNTs). TEM, HRTEM, XRD and Raman spectroscopy characterization analyses reveal the presence of structural amorphization of the SWCNTs, with dramatic impact on the intensity of the G+ and a progressive vanishing of the G- signal-contribution. We demonstrate the presence of high sulfur content by employing both point and mapping energy dispersive X-rays (EDX maps) acquisitions, with high local quantities of sulfur in the order of 16 %. Interestingly, a complex variation in the contribution of the Breit-Wigner-Fano (BWF) band, with appearance of extra D, G+ and C-S band-contributions, is revealed by deconvolution-analyses. The appearance of these structural features is a clear indicator of structural amorphization of the CNTs, with consequential formation of C-S hybrid structures, which we analyze systematically with the aid of energy dispersive X-ray spectrum mapping and Raman point/mapping spectroscopy approaches.

Dynamic event-triggered finite-horizon robust suboptimal control of multi-player systems with input disturbances

This paper presents an adaptive dynamic event-triggered robust finite-horizon suboptimal control scheme for multi-player nonzero-sum game of nonlinear systems with input disturbances based on dynamic programming (ADP) and integral sliding mode (ISM) control techniques. Firstly, dynamic event-triggered adaptive ISM controllers are designed to handle input disturbances that can force the system state to remain on the sliding manifold and relax the known upper bounds condition of input disturbances. Corresponding event-triggered condition is employed for ISM controller of each player to reduce the update frequency. Then, utilizing the obtained ISM dynamics, we employ ADP-based single critic neural networks to approximate the time-varying solution of the Hamilton–Jacobi equations. Thus, the event-triggered finite-horizon suboptimal controllers can be obtained, and corresponding state-based dynamic event-triggered condition is designed to improve the resource utilization. The stability property of the closed-loop system is demonstrated through the Lyapunov technique. Finally, the effectiveness of the proposed control scheme is confirmed through two simulation examples.

SITF: A Self-Supervised Iterative Training Framework for Point Cloud Denoising

Despite existing supervised point cloud denoising methods having made great progress, they require paired ideal noisy-clean datasets for training which is expensive and impractical in real-world applications. Moreover, they may perform the denoising process multiple times with fixed network parameters for better denoising results at test time. To address above issues, this paper proposes a self-supervised iterative training framework (SITF) for point cloud denoising, which only requires single noisy point clouds and a noise model. Given an off-the-shelf denoising network and original noisy point clouds, firstly, an intermediate noisier-noisy dataset is created by adding additional noises from the known noise model to noisy point clouds (i.e. learning targets). Secondly, after training on the noisier-noisy dataset, the denoising network is employed to denoise the original noisy point clouds to obtain the learning targets for the next iteration. The above two steps are iteratively and alternatively performed to get a better and better trained denoising network. Furthermore, to get better learning targets for the next round, this paper also proposes a novel iterative denoising network (IDN) architecture of stacked source attention denoising modules. The IDN explicitly models the iterative denoising process internally within a single network via reforming the given denoising network. Experimental results show that existing supervised networks trained through the SITF can achieve competitive denoising results and even outperform supervised networks under high noise conditions. The source code can be found at: https://github.com/VCG-NJUST/SITF.

Galactica’s dis-assemblage: Meta’s beta and the omega of post-human science

AbstractReleased mid-November 2022, Galactica is a set of six large language models (LLMs) of different sizes (from 125 M to 120B parameters) designed by Meta AI to achieve the ultimate ambition of “a single neural network for powering scientific tasks”, according to its accompanying whitepaper. It aims to carry out knowledge-intensive tasks, such as publication summarization, information ordering and protein annotation. However, just a few days after the release, Meta had to pull back the demo due to the strong hallucinatory tendencies or underwhelming performances of the model. This article aims to study, through a critical threefold argument, the potential impacts of LLMs once deployed in the scientific value chain. Our first argument is a technical one. By examining the technicity of Galactica, it is possible to explain the descripancies between its promotional corporate discourse and abysmal outputs. Second, by going back to debates in both computer science and computational philosophy on the automation of abduction, we argue from the epistemological front that LLMs indeed cannot produce strong abductions and, therefore, claims about the automation of hypothesis generation remains chambering. Finally, our third argument is a sociological one. By conceptualizing the scientific field through Nancy Katherine Hayles’ cognitive assemblage theory, we aim to outline the potential steering of science by LLMs, mainly through information ordering. The core of our argument rests on the assertion that excessive control on information risks contravening a certain serendipitous aspect inherent to scientific discoveries.

Conditional Adversarial Motion Priors by a Novel Retargeting Method for Versatile Humanoid Robot Control

ABSTRACTSignificant advancements have been made in the field of humanoid robot, particularly in walking control strategies. However, achieving straight‐legged walking remains a challenge. Both the traditional model‐based and the learning‐based control methods confront with difficulties in achieving natural humanoid gait feature. To address this issue, a general motion retargeting method is developed and also evaluated for humanoid robots with different structure, size and degrees of freedom. Moreover, a conditional adversarial motion priors method is proposed based on reinforcement learning and validated on the humanoid robot GTX‐III. Through various motion segments from the motion capture database, it is shown that this method can successfully enable the humanoid robot to perform straight‐legged walking with flexible and natural transitions between different gaits within a single discriminator network.