Transformer network for time series prediction via wavelet packet decomposition by Zhichao Wu, Aiye Shi, Yan Ping Tao

“…Although, conventional time series processing methods—such as multi-scale feature extraction or Transformer-based algorithms—produce superior prediction results, when dealing with data that contain morenoise and outliers, the prediction ability of such methods can suffer. …”
Get full text

Application of Variational Mode Decomposition based on the FOA and in Bearing Fault Diagnosis by Chang Liu, Yanxue Wang, Jianwei Yang

“…It is difficult to extract early fault signatures under strong background noise and pulse interference. Thus， a new fault diagnosis method is proposed based on the variational mode decomposition and fruit fly optimization algorithm （FOA）. …”
Get full text

An experimental method for detecting objects in an aqueous environment by Kuzmin Yuri, Proshkin Stanislav

“…The experimental configuration employs a parallel arrangement of a generator and two receiving electrode antennas. A key feature of this technique is its ability to distinguish an object's unique flow characteristic from ambient noise. …”
Get full text

High Precision Piston Error Sensing of Segmented Telescope Based on Frequency Domain Filtering by Dequan Li, Dong Wang

“…The representation of feature image that reflects each submirror's piston error which obtained by this method is the same.Therefore, regardless of the number or the arrangement of submirrors, the single shallow convolutional neural network trained by any of the extracted submirror interference image dataset can be used to achieve high-precision detection of different submirror piston errors.Finally, simulation experiment results show the effectiveness of the proposed method.…”
Get full text

Common-Ground Bridgeless Unity Power Factor Single-Phase Rectifier by Ivo Barbi, Hugo Rolando Estofanero Larico

“…A non-optimized experimental prototype was developed and tested in the laboratory to validate the operating principle and the results of theoretical analysis. The distinctive feature of the proposed rectifier is that it eliminates the leakage current that circulates through the parasitic capacitances existing between the power semiconductor and heatsink, which causes common-mode electromagnetic interference in conventional boost-based PFC rectifiers.…”
Get full text

Indoor Wi-Fi fingerprint localization method based on CSI tensor decomposition by Mu ZHOU, Yuexin LONG, Qiaolin PU, Yong WANG, Wei HE

“…Aiming at the problem that as the scale of the fingerprint database increases, the training cost and processing complexity of CSI fingerprints will also greatly increase, an indoor Wi-Fi fingerprint localization method based on CSI tensor decomposition was proposed.Firstly, the tensor decomposition algorithm based on the PARAFAC (parallel factor) analysis model and the ALS (alternate least squares) iterative algorithm were combined to reduce the interference of the environment.Then, the tensor wavelet decomposition algorithm was used to extract the feature and obtain the CSI fingerprint.Finally, a localization model was established based on the PLSR (partial least squares regression) algorithm to realize the location estimation.Experimental results show that the confidence probability of the proposed method is 94.88% within 4 m localization error, which verifies that the proposed method has good localization performance while fitting the relationship between CSI location fingerprints and location coordinates.…”
Get full text

Wavefront Sensor for the Determination of Nanostructured Surface Defects by V.V. Buchenko, A.A. Goloborodko, V.V. Lendel, O.S. Oberemok

“…The comparison of the theoretical calculations and experimental results of the influence of interference phenomena on the determination of the parameters and the structure of the refractive index is presented. …”
Get full text

Automatic Quality Assessment of Speech-Driven Synthesized Gestures by Zhiyuan He

“…We noticed that recurrent neural networks (RNN) have advantages in modeling advanced spatiotemporal feature sequences, which are very suitable for use in the processing of synthetic gesture video data. …”
Get full text

Fault Diagnosis of Rolling Bearings based on VMD and Symmetric Difference Energy Operator Demodulation by Qin Bo, Wang Zuda, Guo Huili, Sun Guodong, Chen Shuai, Wang Jianguo

“…The experimental results show that compared with the traditional energy operator,the proposed method can effectively extract the fault feature,and can restrain the false interference frequency and highlight the fault characteristic frequency,more conducive to roller bearing fault diagnosis.…”
Get full text

Fault diagnosis of mining rolling bearings based on Superlet Transform and OD-ConvNeXt-ELA by WU Xinzhong, LUO Kang, TANG Shoufeng, HE Zexu, CHEN Qi

“…In response to the limitations of current fault diagnosis methods for mining rolling bearings, which suffer from limited feature extraction capabilities and poor generalization, a fault diagnosis method based on Superlet Transform (SLT) and OD-ConvNeXt-ELA was proposed. …”
Get full text

Red Raspberry Maturity Detection Based on Multi-Module Optimized YOLOv11n and Its Application in Field and Greenhouse Environments by Rongxiang Luo, Xue Ding, Jinliang Wang

“…This module enhances the network’s multi-scale feature extraction capabilities, reduces the interference of background noise, improves the recognition of structural details, and optimizes the spatial resolution of the image through the dynamic sampling mechanism. …”
Get full text

Construction and application of foundational models for intelligent processing of microseismic events in mines by Anye CAO, Maotao LI, Xu YANG, Yao YANG, Sen LI, Yaoqi LIU, Changbin WANG

“…A comprehensive dataset containing over 300 000 microseismic waveforms was established, incorporating three key innovations: multi-scale convolutional modules for multi-dimensional feature extraction, an adaptive feature fusion strategy for noise-resistant signal representation, and a feature-aggregated multi-head attention mechanism for temporal sequence modeling. …”
Get full text

Research on Face Local Attribute Detection Method Based on Improved SSD Network Structure by Qun Luo, Zhendong Liu

“…The existing face detection methods usually had the problem of low accuracy of face recognition in the environment of occlusion interference, which was limited when applied to the face detection task in complex scenes. …”
Get full text

Research on Small Target Detection Algorithm for Autonomous Vehicle Scenarios by Sheng Tian, Kailong Zhao, Lin Song

“…This model incorporates a multiscale feature fusion network and leverages the lightweight GhostNet module to reduce model parameters. …”
Get full text

From Convolutional Networks to Vision Transformers: Evolution of Deep Learning in Agricultural Pest and Disease Identification by Mengyao Zhang, Chaofan Liu, Zihan Li, Baoquan Yin

“…In recent years, deep learning has gradually become the preferred solution for the intelligent identification of pests and diseases by virtue of its powerful automatic feature extraction and complex data-processing capabilities. …”
Get full text

Improved Dual-tree Complex Wavelet Packet Transform with Application to Fault Diagnosis by She Bo, Tian Fuqing, Liang Weige

“…The experimental results show that the weak fault feature of gearbox submerged in strong interference can be effectively extracted,and the feasibility and effectiveness of this method are verified.…”
Get full text

CSI feedback algorithm for massive MIMO systems based on SFNet by ZHANG Yun, HUANG Jingwei, XU Sunwu, GAO Gui, YU Shujuan, ZHAO Shengmei

“…SFNet integrated a traditional convolutional neural network (CNN) and Transformer architecture, incorporating a spatial-frequency block designed to leverage global information and a multi-scale adaptive spatial attention gate for fusing local and global features. Fast Fourier convolution and a dynamic feature fusion mechanism were utilized to activate more input information, adjust the receptive field, selectively highlight spatially correlated features, suppress interference, and allow the network to achieve advanced performance with extremely low computational complexity. …”
Get full text

Railway safety monitoring algorithm based on distributed optical fiber vibration sensor by Fuyang CHEN, Bin JIANG, Yu SHA

“…Aiming at the monitoring problem of the human climbing behaviour existing along the railway,a railway safety detection algorithm based on distributed optical fiber vibration sensors was proposed by combining the distributed optical fiber sensing technology and signal analysis technology.The surrounding vibration was sensed and transmitted through the optical cables laid along the fence network of the railway,and then the Internet of things (IoT) connection between the railway and monitoring algorithm was built to realize the intelligent monitoring of the climbing behavior.In view of the complicated surrounding environment of the railway and more interference,the Hamming window and wavelet threshold denoising method were used to filter the signal of each frame to improve the signal-to-noise ratio of the vibration signal.In the selection of features,the power spectrum and short-time over-level rate of the signal were extracted from the time domain and frequency domain respectively as a joint feature to determine whether there was climbing or creeping behavior.Since that the climbing behavior was spatially continuous,the minimum alarm range was set to filter out alarms with a too small range,which improved the accuracy of the monitoring system.…”
Get full text

Reformulation in Early 20th Century Substandard Italian by Giulio Scivoletto

“…These markers are affected by hypercorrection, interference, and structural simplification, reflecting the sociolinguistic dynamics of <i>italiano popolare</i>. …”
Get full text

Low illumination image enhancement algorithm of CycleGAN coal mine based on attention mechanism and Dilated convolution by Yuanbin WANG, Yaru GUO, Jia LIU, Xu WANG, Bingchao WU, Meng LIU

“…In order to improve the detail feature extraction ability of the generator network, the image enhancement network was constructed by using the Parameter-Free Attention Mechanism (simAM) and the Dual-Channel Attention Mechanism (CBAM) to improve the anti-interference ability of the model in complex background, so that the model could recover the image detail features better, which improved the anti-interference ability of the model under complex background and made the model recover the detail features better. …”
Get full text