Rail surface damage is a critical component of high-speed railway infrastructure,directly affecting train operational stability and safety.Existing methods face limitations in accuracy and speed for small-sample,multi...Rail surface damage is a critical component of high-speed railway infrastructure,directly affecting train operational stability and safety.Existing methods face limitations in accuracy and speed for small-sample,multi-category,and multi-scale target segmentation tasks.To address these challenges,this paper proposes Pyramid-MixNet,an intelligent segmentation model for high-speed rail surface damage,leveraging dataset construction and expansion alongside a feature pyramid-based encoder-decoder network with multi-attention mechanisms.The encoding net-work integrates Spatial Reduction Masked Multi-Head Attention(SRMMHA)to enhance global feature extraction while reducing trainable parameters.The decoding network incorporates Mix-Attention(MA),enabling multi-scale structural understanding and cross-scale token group correlation learning.Experimental results demonstrate that the proposed method achieves 62.17%average segmentation accuracy,80.28%Damage Dice Coefficient,and 56.83 FPS,meeting real-time detection requirements.The model’s high accuracy and scene adaptability significantly improve the detection of small-scale and complex multi-scale rail damage,offering practical value for real-time monitoring in high-speed railway maintenance systems.展开更多
The translation activity is a process of the interlinguistic transmission of information realized by the information encoding and decoding.Encoding and decoding,cognitive practices operated in objective contexts,are i...The translation activity is a process of the interlinguistic transmission of information realized by the information encoding and decoding.Encoding and decoding,cognitive practices operated in objective contexts,are inevitably of selectivity ascribing to the restriction of contextual reasons.The translator as the intermediary agent connects the original author(encoder)and the target readers(decoder),shouldering the dual duties of the decoder and the encoder,for which his subjectivity is irrevocably manipulated by the selectivity of encoding and decoding.展开更多
Brain encoding and decoding via functional magnetic resonance imaging(fMRI)are two important aspects of visual perception neuroscience.Although previous researchers have made significant advances in brain encoding and...Brain encoding and decoding via functional magnetic resonance imaging(fMRI)are two important aspects of visual perception neuroscience.Although previous researchers have made significant advances in brain encoding and decoding models,existing methods still require improvement using advanced machine learning techniques.For example,traditional methods usually build the encoding and decoding models separately,and are prone to overfitting on a small dataset.In fact,effectively unifying the encoding and decoding procedures may allow for more accurate predictions.In this paper,we first review the existing encoding and decoding methods and discuss the potential advantages of a“bidirectional”modeling strategy.Next,we show that there are correspondences between deep neural networks and human visual streams in terms of the architecture and computational rules.Furthermore,deep generative models(e.g.,variational autoencoders(VAEs)and generative adversarial networks(GANs))have produced promising results in studies on brain encoding and decoding.Finally,we propose that the dual learning method,which was originally designed for machine translation tasks,could help to improve the performance of encoding and decoding models by leveraging large-scale unpaired data.展开更多
Considerable studies have been carried out on fault diagnosis of gears, with most of them concentrated on conventional vibration analysis. However, besides the complexity of gear dynamics, the diagnosis results in ter...Considerable studies have been carried out on fault diagnosis of gears, with most of them concentrated on conventional vibration analysis. However, besides the complexity of gear dynamics, the diagnosis results in terms of vibration signal are easily misjudged owing to the interference of sensor position or other components. In this paper, an alternative gearbox fault detection method based on the instantaneous rotational speed is proposed because of its advantages over vibration analysis. Depending on the timer/counter-based method for the pulse signal of the optical encoder, the varying rotational speed can be obtained e ectively. Owing to the coupling and meshing of gears in transmission, the excitations are the same for the instantaneous rotational speed of the input and output shafts. Thus, the di erential signal of instantaneous rotational speeds can be adopted to eliminate the e ect of the interference excitations and extract the associated feature of the localized fault e ectively. With the experiments on multistage gearbox test system, the di erential signal of instantaneous speeds is compared with other signals. It is proved that localized faults in the gearbox generate small angular speed fluctuations, which are measurable with an optical encoder. Using the di erential signal of instantaneous speeds, the fault characteristics are extracted in the spectrum where the deterministic frequency component and its harmonics corresponding to crack fault characteristics are displayed clearly.展开更多
In order to make the information transmission more efficient and reliable in a digital communication channel with limited capacity, various encoding-decoding techniques have been proposed and widely applied in many br...In order to make the information transmission more efficient and reliable in a digital communication channel with limited capacity, various encoding-decoding techniques have been proposed and widely applied in many branches of the signal processing including digital communications, data compression,information encryption, etc. Recently, due to its promising application potentials in the networked systems(NSs), the analysis and synthesis issues of the NSs under various encoding-decoding schemes have stirred some research attention. However, because of the network-enhanced complexity caused by the limited network resources, it poses new challenges to the design of suitable encoding-decoding procedures to meet certain control or filtering performance for the NSs. In this survey paper, our aim is to present a comprehensive review of the encoding-decodingbased control and filtering problems for different types of NSs.First, some basic introduction with respect to the coding-decoding mechanism is presented in terms of its engineering insights,specific properties and theoretical formulations. Then, the recent representative research progress in the design of the encodingdecoding protocols for various control and filtering problems is discussed. Some possible further research topics are finally outlined for the encoding-decoding-based NSs.展开更多
Low cost and miniaturized rotary encoders are important in automatic and precise production. Presented here is a code called Single Track Cyclic Gray Code (STCGC) that is an image etched on a single circular track of ...Low cost and miniaturized rotary encoders are important in automatic and precise production. Presented here is a code called Single Track Cyclic Gray Code (STCGC) that is an image etched on a single circular track of a rotary encoder disk read by a group of even spread reading heads to provide a unique codeword for every angular position and features such that every two adjacent words differ in exactly one component, thus avoiding coarse error. The existing construction or combination methods are helpful but not sufficient in determining the period of the STCGC of large word length and the theoretical approach needs further development to extend the word length. Three principles, such as the seed combination, short code removal and ergodicity examination were put forward that suffice determination of the optimal period for such absolute rotary encoders using STCGC with even spread heads. The optimal periods of STCGC in 3 through 29 bit length were determined and listed.展开更多
Ocean underwater exploration is a part of oceanography that investigates the physical and biological conditions for scientific and commercial purposes. And video technology plays an important role and is extensively a...Ocean underwater exploration is a part of oceanography that investigates the physical and biological conditions for scientific and commercial purposes. And video technology plays an important role and is extensively applied for underwater environment observation. Different from the conventional methods, video technology explores the underwater ecosystem continuously and non-invasively. However, due to the scattering and attenuation of light transport in the water, complex noise distribution and lowlight condition cause challenges for underwater video applications including object detection and recognition. In this paper, we propose a new deep encoding-decoding convolutional architecture for underwater object recognition. It uses the deep encoding-decoding network for extracting the discriminative features from the noisy low-light underwater images. To create the deconvolutional layers for classification, we apply the deconvolution kernel with a matched feature map, instead of full connection, to solve the problem of dimension disaster and low accuracy. Moreover, we introduce data augmentation and transfer learning technologies to solve the problem of data starvation. For experiments, we investigated the public datasets with our proposed method and the state-of-the-art methods. The results show that our work achieves significant accuracy. This work provides new underwater technologies applied for ocean exploration.展开更多
In this paper, a new kind of simple-encoding irregular systematic LDPC codes suitable for one-relay coded cooperation is designed, where the proposed joint iterative decoding is effectively performed in the destinatio...In this paper, a new kind of simple-encoding irregular systematic LDPC codes suitable for one-relay coded cooperation is designed, where the proposed joint iterative decoding is effectively performed in the destination which is in accordance with the corresponding joint Tanner graph characterizing two different component LDPC codes used by the source and relay in ideal and non-ideal relay cooperations. The theoretical analysis and simulations show that the coded cooperation scheme obviously outperforms the coded non-cooperation one under the same code rate and decoding complex. The significant performance improvement can be virtually credited to the additional mutual exchange of the extrinsic information resulted by the LDPC code employed by the source and its counterpart used by the relay in both ideal and non-ideal cooperations.展开更多
Modern satellite communication systems require on-board processing(OBP)for performance improvements,and SRAM-FPGAs are an attractive option for OBP implementation.However,SRAM-FPGAs are sensitive to radiation effects,...Modern satellite communication systems require on-board processing(OBP)for performance improvements,and SRAM-FPGAs are an attractive option for OBP implementation.However,SRAM-FPGAs are sensitive to radiation effects,among which single event upsets(SEUs)are important as they can lead to data corruption and system failure.This paper studies the fault tolerance capability of a SRAM-FPGA implemented Viterbi decoder to SEUs on the user memory.Analysis and fault injection experiments are conducted to verify that over 97%of the SEUs on user memory would not lead to output errors.To achieve a better reliability,selective protection schemes are then proposed to further improve the reliability of the decoder to SEUs on user memory with very small overhead.Although the results are obtained for a specific FPGA implementation,the developed reliability estimation model and the general conclusions still hold for other implementations.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 6226070954Jiangxi Provincial Key R&D Programme under Grant 20244BBG73002.
文摘Rail surface damage is a critical component of high-speed railway infrastructure,directly affecting train operational stability and safety.Existing methods face limitations in accuracy and speed for small-sample,multi-category,and multi-scale target segmentation tasks.To address these challenges,this paper proposes Pyramid-MixNet,an intelligent segmentation model for high-speed rail surface damage,leveraging dataset construction and expansion alongside a feature pyramid-based encoder-decoder network with multi-attention mechanisms.The encoding net-work integrates Spatial Reduction Masked Multi-Head Attention(SRMMHA)to enhance global feature extraction while reducing trainable parameters.The decoding network incorporates Mix-Attention(MA),enabling multi-scale structural understanding and cross-scale token group correlation learning.Experimental results demonstrate that the proposed method achieves 62.17%average segmentation accuracy,80.28%Damage Dice Coefficient,and 56.83 FPS,meeting real-time detection requirements.The model’s high accuracy and scene adaptability significantly improve the detection of small-scale and complex multi-scale rail damage,offering practical value for real-time monitoring in high-speed railway maintenance systems.
文摘The translation activity is a process of the interlinguistic transmission of information realized by the information encoding and decoding.Encoding and decoding,cognitive practices operated in objective contexts,are inevitably of selectivity ascribing to the restriction of contextual reasons.The translator as the intermediary agent connects the original author(encoder)and the target readers(decoder),shouldering the dual duties of the decoder and the encoder,for which his subjectivity is irrevocably manipulated by the selectivity of encoding and decoding.
基金This work was supported by the National Key Research and Development Program of China(2018YFC2001302)National Natural Science Foundation of China(91520202)+2 种基金Chinese Academy of Sciences Scientific Equipment Development Project(YJKYYQ20170050)Beijing Municipal Science and Technology Commission(Z181100008918010)Youth Innovation Promotion Association of Chinese Academy of Sciences,and Strategic Priority Research Program of Chinese Academy of Sciences(XDB32040200).
文摘Brain encoding and decoding via functional magnetic resonance imaging(fMRI)are two important aspects of visual perception neuroscience.Although previous researchers have made significant advances in brain encoding and decoding models,existing methods still require improvement using advanced machine learning techniques.For example,traditional methods usually build the encoding and decoding models separately,and are prone to overfitting on a small dataset.In fact,effectively unifying the encoding and decoding procedures may allow for more accurate predictions.In this paper,we first review the existing encoding and decoding methods and discuss the potential advantages of a“bidirectional”modeling strategy.Next,we show that there are correspondences between deep neural networks and human visual streams in terms of the architecture and computational rules.Furthermore,deep generative models(e.g.,variational autoencoders(VAEs)and generative adversarial networks(GANs))have produced promising results in studies on brain encoding and decoding.Finally,we propose that the dual learning method,which was originally designed for machine translation tasks,could help to improve the performance of encoding and decoding models by leveraging large-scale unpaired data.
基金supported by the National Natural Science Foundation of China(1127105011371183+2 种基金61403036)the Science and Technology Development Foundation of CAEP(2013A04030202013B0403068)
基金Supported by National Natural Science Foundation of China(Grant No.51575438)China Postdoctoral Science Foundation(Grant Nos.2017M623159,2018T111046)Shaanxi Provincial Postdoctoral Science Foundation of China(Grant No.2017BSHEDZZ68)
文摘Considerable studies have been carried out on fault diagnosis of gears, with most of them concentrated on conventional vibration analysis. However, besides the complexity of gear dynamics, the diagnosis results in terms of vibration signal are easily misjudged owing to the interference of sensor position or other components. In this paper, an alternative gearbox fault detection method based on the instantaneous rotational speed is proposed because of its advantages over vibration analysis. Depending on the timer/counter-based method for the pulse signal of the optical encoder, the varying rotational speed can be obtained e ectively. Owing to the coupling and meshing of gears in transmission, the excitations are the same for the instantaneous rotational speed of the input and output shafts. Thus, the di erential signal of instantaneous rotational speeds can be adopted to eliminate the e ect of the interference excitations and extract the associated feature of the localized fault e ectively. With the experiments on multistage gearbox test system, the di erential signal of instantaneous speeds is compared with other signals. It is proved that localized faults in the gearbox generate small angular speed fluctuations, which are measurable with an optical encoder. Using the di erential signal of instantaneous speeds, the fault characteristics are extracted in the spectrum where the deterministic frequency component and its harmonics corresponding to crack fault characteristics are displayed clearly.
基金supported in part by the Royal Society of the UK,the Nationa Natural Science,Foundation of China(61329301,61374039)the Program for Capability Construction of Shanghai Provincial Universities(15550502500)the Alexander von Humboldt Foundation of Germany
文摘In order to make the information transmission more efficient and reliable in a digital communication channel with limited capacity, various encoding-decoding techniques have been proposed and widely applied in many branches of the signal processing including digital communications, data compression,information encryption, etc. Recently, due to its promising application potentials in the networked systems(NSs), the analysis and synthesis issues of the NSs under various encoding-decoding schemes have stirred some research attention. However, because of the network-enhanced complexity caused by the limited network resources, it poses new challenges to the design of suitable encoding-decoding procedures to meet certain control or filtering performance for the NSs. In this survey paper, our aim is to present a comprehensive review of the encoding-decodingbased control and filtering problems for different types of NSs.First, some basic introduction with respect to the coding-decoding mechanism is presented in terms of its engineering insights,specific properties and theoretical formulations. Then, the recent representative research progress in the design of the encodingdecoding protocols for various control and filtering problems is discussed. Some possible further research topics are finally outlined for the encoding-decoding-based NSs.
基金Project(JX2004J0170) supported by the Foundation of Beijing Jiaotong University, China
文摘Low cost and miniaturized rotary encoders are important in automatic and precise production. Presented here is a code called Single Track Cyclic Gray Code (STCGC) that is an image etched on a single circular track of a rotary encoder disk read by a group of even spread reading heads to provide a unique codeword for every angular position and features such that every two adjacent words differ in exactly one component, thus avoiding coarse error. The existing construction or combination methods are helpful but not sufficient in determining the period of the STCGC of large word length and the theoretical approach needs further development to extend the word length. Three principles, such as the seed combination, short code removal and ergodicity examination were put forward that suffice determination of the optimal period for such absolute rotary encoders using STCGC with even spread heads. The optimal periods of STCGC in 3 through 29 bit length were determined and listed.
基金supported by the Jilin Science and Technology Development Plan Project (Nos. 20160209006GX, 20170309001GX and 20180201043GX)
文摘Ocean underwater exploration is a part of oceanography that investigates the physical and biological conditions for scientific and commercial purposes. And video technology plays an important role and is extensively applied for underwater environment observation. Different from the conventional methods, video technology explores the underwater ecosystem continuously and non-invasively. However, due to the scattering and attenuation of light transport in the water, complex noise distribution and lowlight condition cause challenges for underwater video applications including object detection and recognition. In this paper, we propose a new deep encoding-decoding convolutional architecture for underwater object recognition. It uses the deep encoding-decoding network for extracting the discriminative features from the noisy low-light underwater images. To create the deconvolutional layers for classification, we apply the deconvolution kernel with a matched feature map, instead of full connection, to solve the problem of dimension disaster and low accuracy. Moreover, we introduce data augmentation and transfer learning technologies to solve the problem of data starvation. For experiments, we investigated the public datasets with our proposed method and the state-of-the-art methods. The results show that our work achieves significant accuracy. This work provides new underwater technologies applied for ocean exploration.
基金Supported by the Open Research Fund of National Moblie Communications Research Laboratory of Southeast Uni-versity (No. W200704)
文摘In this paper, a new kind of simple-encoding irregular systematic LDPC codes suitable for one-relay coded cooperation is designed, where the proposed joint iterative decoding is effectively performed in the destination which is in accordance with the corresponding joint Tanner graph characterizing two different component LDPC codes used by the source and relay in ideal and non-ideal relay cooperations. The theoretical analysis and simulations show that the coded cooperation scheme obviously outperforms the coded non-cooperation one under the same code rate and decoding complex. The significant performance improvement can be virtually credited to the additional mutual exchange of the extrinsic information resulted by the LDPC code employed by the source and its counterpart used by the relay in both ideal and non-ideal cooperations.
基金supported in part by the National Key R&D Program(Grant No.2017YFE0121300)in part by the National Natural Science Foundation of China (Grant No. 61501321)+1 种基金in part by Tianjin science and technology program (Grant No. 17ZXRGGX00160)the support of the TEXEO project TEC201680339R funded by the Spanish Ministry of Economy and Competitivity
文摘Modern satellite communication systems require on-board processing(OBP)for performance improvements,and SRAM-FPGAs are an attractive option for OBP implementation.However,SRAM-FPGAs are sensitive to radiation effects,among which single event upsets(SEUs)are important as they can lead to data corruption and system failure.This paper studies the fault tolerance capability of a SRAM-FPGA implemented Viterbi decoder to SEUs on the user memory.Analysis and fault injection experiments are conducted to verify that over 97%of the SEUs on user memory would not lead to output errors.To achieve a better reliability,selective protection schemes are then proposed to further improve the reliability of the decoder to SEUs on user memory with very small overhead.Although the results are obtained for a specific FPGA implementation,the developed reliability estimation model and the general conclusions still hold for other implementations.
