Cyber-Physical Systems integrated with information technologies introduce vulnerabilities that extend beyond traditional cyber threats.Attackers can non-invasively manipulate sensors and spoof controllers,which in tur...Cyber-Physical Systems integrated with information technologies introduce vulnerabilities that extend beyond traditional cyber threats.Attackers can non-invasively manipulate sensors and spoof controllers,which in turn increases the autonomy of the system.Even though the focus on protecting against sensor attacks increases,there is still uncertainty about the optimal timing for attack detection.Existing systems often struggle to manage the trade-off between latency and false alarm rate,leading to inefficiencies in real-time anomaly detection.This paper presents a framework designed to monitor,predict,and control dynamic systems with a particular emphasis on detecting and adapting to changes,including anomalies such as“drift”and“attack”.The proposed algorithm integrates a Transformer-based Attention Generative Adversarial Residual model,which combines the strengths of generative adversarial networks,residual networks,and attention algorithms.The system operates in two phases:offline and online.During the offline phase,the proposed model is trained to learn complex patterns,enabling robust anomaly detection.The online phase applies a trained model,where the drift adapter adjusts the model to handle data changes,and the attack detector identifies deviations by comparing predicted and actual values.Based on the output of the attack detector,the controller makes decisions then the actuator executes suitable actions.Finally,the experimental findings show that the proposed model balances detection accuracy of 99.25%,precision of 98.84%,sensitivity of 99.10%,specificity of 98.81%,and an F1-score of 98.96%,thus provides an effective solution for dynamic and safety-critical environments.展开更多
The Least Squares Residual(LSR)algorithm,one of the classical Receiver Autonomous Integrity Monitoring(RAIM)algorithms for Global Navigation Satellite System(GNSS),presents a high Missed Detection Risk(MDR)for a large...The Least Squares Residual(LSR)algorithm,one of the classical Receiver Autonomous Integrity Monitoring(RAIM)algorithms for Global Navigation Satellite System(GNSS),presents a high Missed Detection Risk(MDR)for a large-slope faulty satellite and a high False Alarm Risk(FAR)for a small-slope faulty satellite.From the theoretical analysis of the high MDR and FAR cause,the optimal slope is determined,and thereby the optimal test statistic for fault detection is conceived,which can minimize the FAR with the MDR not exceeding its allowable value.To construct a test statistic approximate to the optimal one,the CorrelationWeighted LSR(CW-LSR)algorithm is proposed.The CW-LSR test statistic remains the sum of pseudorange residual squares,but the square for the most potentially faulty satellite,judged by correlation analysis between the pseudorange residual and observation error,is weighted with an optimal-slope-based factor.It does not obey the same distribution but has the same noncentral parameter with the optimal test statistic.The superior performance of the CW-LSR algorithm is verified via simulation,both reducing the FAR for a small-slope faulty satellite with the MDR not exceeding its allowable value and reducing the MDR for a large-slope faulty satellite at the expense of FAR addition.展开更多
The Least Squares Residual(LSR)algorithm is commonly used in the Receiver Autonomous Integrity Monitoring(RAIM).However,LSR algorithm presents high Missed Detection Risk(MDR)caused by a large-slope faulty satellite an...The Least Squares Residual(LSR)algorithm is commonly used in the Receiver Autonomous Integrity Monitoring(RAIM).However,LSR algorithm presents high Missed Detection Risk(MDR)caused by a large-slope faulty satellite and high False Alert Risk(FAR)caused by a small-slope faulty satellite.In this paper,the LSR algorithm is improved to reduce the MDR for a large-slope faulty satellite and the FAR for a small-slope faulty satellite.Based on the analysis of the vertical critical slope,the optimal decentralized factor is defined and the optimal test statistic is conceived,which can minimize the FAR with the premise that the MDR does not exceed its allowable value of all three directions.To construct a new test statistic approximating to the optimal test statistic,the Optimal Decentralized Factor weighted LSR(ODF-LSR)algorithm is proposed.The new test statistic maintains the sum of pseudo-range residual squares,but the specific pseudo-range residual is weighted with a parameter related to the optimal decentralized factor.The new test statistic has the same decentralized parameter with the optimal test statistic when single faulty satellite exists,and the difference between the expectation of the new test statistic and the optimal test statistic is the minimum when no faulty satellite exists.The performance of the ODFLSR algorithm is demonstrated by simulation experiments.展开更多
A large number of sparse signal reconstruction algorithms have been continuously proposed, but almost all greedy algorithms add a fixed number of indices to the support set in each iteration. Although the mechanism of...A large number of sparse signal reconstruction algorithms have been continuously proposed, but almost all greedy algorithms add a fixed number of indices to the support set in each iteration. Although the mechanism of selecting the fixed number of indexes improves the reconstruction efficiency, it also brings the problem of low index selection accuracy. Based on the full study of the theory of compressed sensing, we propose a dynamic indexes selection strategy based on residual update to improve the performance of the compressed sampling matching pursuit algorithm (CoSaMP). As an extension of CoSaMP algorithm, the proposed algorithm adopts a residual comparison strategy to improve the accuracy of backtracking selected indexes. This backtracking strategy can efficiently select backtracking indexes. And without increasing the computational complexity, the proposed improvement algorithm has a higher exact reconstruction rate and peak signal to noise ratio (PSNR). Simulation results demonstrate the proposed algorithm significantly outperforms the CoSaMP for image recovery and one-dimensional signal.展开更多
Message passing algorithms,whose iterative nature captures complicated interactions among interconnected variables in complex systems and extracts information from the fixed point of iterated messages,provide a powerf...Message passing algorithms,whose iterative nature captures complicated interactions among interconnected variables in complex systems and extracts information from the fixed point of iterated messages,provide a powerful toolkit in tackling hard computational tasks in optimization,inference,and learning problems.In the context of constraint satisfaction problems(CSPs),when a control parameter(such as constraint density)is tuned,multiple threshold phenomena emerge,signaling fundamental structural transitions in their solution space.Finding solutions around these transition points is exceedingly challenging for algorithm design,where message passing algorithms suffer from a large message fiuctuation far from convergence.Here we introduce a residual-based updating step into message passing algorithms,in which messages with large variation between consecutive steps are given high priority in the updating process.For the specific example of model RB(revised B),a typical prototype of random CSPs with growing domains,we show that our algorithm improves the convergence of message updating and increases the success probability in finding solutions around the satisfiability threshold with a low computational cost.Our approach to message passing algorithms should be of value for exploring their power in developing algorithms to find ground-state solutions and understand the detailed structure of solution space of hard optimization problems.展开更多
The dominant error source of mobile terminal location in wireless sensor networks （WSNs） is the non-line-of-sight （NLOS） propagation error. Among the algorithms proposed to mitigate the influence of NLOS propagati...The dominant error source of mobile terminal location in wireless sensor networks （WSNs） is the non-line-of-sight （NLOS） propagation error. Among the algorithms proposed to mitigate the influence of NLOS propagation error, residual test （RT） is an efficient one, however with high computational complexity （CC）. An improved algorithm that memorizes the light of sight （LOS） range measurements （RMs） identified memorize LOS range measurements identified residual test （MLSI-RT） is presented in this paper to address this problem. The MLSI-RT is based on the assumption that when all RMs are from LOS propagations, the normalized residual follows the central Chi-Square distribution while for NLOS cases it is non-central. This study can reduce the CC by more than 90%.展开更多
Wireless sensor networks (WSNs) are mostly deployed in a remote working environment, since sensor nodes are small in size, cost-efficient, low-power devices, and have limited battery power supply. Because of limited p...Wireless sensor networks (WSNs) are mostly deployed in a remote working environment, since sensor nodes are small in size, cost-efficient, low-power devices, and have limited battery power supply. Because of limited power source, energy consumption has been considered as the most critical factor when designing sensor network protocols. The network lifetime mainly depends on the battery lifetime of the node. The main concern is to increase the lifetime with respect to energy constraints. One way of doing this is by turning off redun-dant nodes to sleep mode to conserve energy while active nodes can provide essential k-coverage, which improves fault-tolerance. Hence, we use scheduling algorithms that turn off redundant nodes after providing the required coverage level k. The scheduling algorithms can be implemented in centralized or localized schemes, which have their own advantages and disadvantages. To exploit the advantages of both schemes, we employ both schemes on the network according to a threshold value. This threshold value is estimated on the performance of WSN based on network lifetime comparison using centralized and localized algorithms. To extend the network lifetime and to extract the useful energy from the network further, we go for compromise in the area covered by nodes.展开更多
X oilfield has successfully adopted horizontal wells to develop strong bottom water reservoirs, as a typical representative of development styles in the Bohai offshore oilfield. At present, many contributions to metho...X oilfield has successfully adopted horizontal wells to develop strong bottom water reservoirs, as a typical representative of development styles in the Bohai offshore oilfield. At present, many contributions to methods of inverting relative permeability curve and forecasting residual recoverable reserves had been made by investigators, but rarely involved in horizontal wells’ in bottom water reservoir. As the pore volume injected was less (usually under 30 PV), the relative permeability curve endpoint had become a serious distortion. That caused a certain deviation in forecasting residual recoverable reserves in the practical value of field directly. For the performance of water cresting, the common method existed some problems, such as no pertinence, ineffectiveness and less affecting factors considered. This paper adopts the streamlines theory with two phases flowing to solve that. Meanwhile, based on the research coupling genetic algorithm, optimized relative permeability curve was calculated by bottom-water drive model. The residual oil saturation calculated was lower than the initial’s, and the hydrophilic property was more reinforced, due to improving the pore volume injected vastly. Also, the study finally helped us enhance residual recoverable reserves degree at high water cut stage, more than 20%, taking Guantao sandstone as an example. As oil field being gradually entering high water cut stage, this method had a great significance to evaluate the development effect and guide the potential of the reservoir.展开更多
Transmission of data over the internet has become a critical issue as a result of the advancement in technology, since it is possible for pirates to steal the intellectual property of content owners. This paper presen...Transmission of data over the internet has become a critical issue as a result of the advancement in technology, since it is possible for pirates to steal the intellectual property of content owners. This paper presents a new digital watermarking scheme that combines some operators of the Genetic Algorithm (GA) and the Residue Number (RN) System (RNS) to perform encryption on an image, which is embedded into a cover image for the purposes of watermarking. Thus, an image watermarking scheme uses an encrypted image. The secret image is embedded in decomposed frames of the cover image achieved by applying a three-level Discrete Wavelet Transform (DWT). This is to ensure that the secret information is not exposed even when there is a successful attack on the cover information. Content creators can prove ownership of the multimedia content by unveiling the secret information in a court of law. The proposed scheme was tested with sample data using MATLAB2022 and the results of the simulation show a great deal of imperceptibility and robustness as compared to similar existing schemes.展开更多
This paper analyses the dynamic residual aberrations of a conformal optical system and introduces adaptive optics （AO） correction technology to this system. The image sharpening AO system is chosen as the correction...This paper analyses the dynamic residual aberrations of a conformal optical system and introduces adaptive optics （AO） correction technology to this system. The image sharpening AO system is chosen as the correction scheme.Communication between MATLAB and Code V is established via ActiveX technique in computer simulation.The SPGD algorithm is operated at seven zoom positions to calculate the optimized surface shape of the deformable mirror.After comparison of performance of the corrected system with the baseline system,AO technology is proved to be a good way of correcting the dynamic residual aberration in conformal optical design.展开更多
While the traditional trajectory planning methods are used in robotic belt grinding of blades with an uneven machining allowance distribution, it is hard to obtain the preferable profile accuracy and surface quality t...While the traditional trajectory planning methods are used in robotic belt grinding of blades with an uneven machining allowance distribution, it is hard to obtain the preferable profile accuracy and surface quality to meet the high-performance requirements of aero-engine. To solve this problem, a novel trajectory planning method is proposed in this paper by considering the developed interpolation algorithm and the machining allowance threshold. The residual height error obtained from grinding experiments of titanium alloy sample was compensated to modify the calculation model of row spacing, and a new geometric algorithm was presented to dynamically calculate the cutter contact points based on this revised calculation model and the dichotomy method. Subsequently, the off-line machining program is generated based on a double-vector controlling method to obtain an optimal contact posture. On this basis, three sets of robotic grinding tests of titanium alloy blades were conducted to investigate the advantages of the proposed method.The comparative experimental results revealed that the presented algorithm had improved the surface profile accuracy of blade by 34.2% and 55.1%, respectively. Moreover, the average machined surface roughness was achieved to 0.3 μm and the machining efficiency was obviously promoted. It is concluded that this research work is beneficial to comprehensively improve the machined quality of blades in robotic belt grinding.展开更多
Objective A classification and diagnosis model for psoriasis based on deep residual network is proposed in this paper.Which using deep learning technology to classify and diagnose psoriasis can help reduce the burden ...Objective A classification and diagnosis model for psoriasis based on deep residual network is proposed in this paper.Which using deep learning technology to classify and diagnose psoriasis can help reduce the burden of doctors,simplify the diagnosis and treatment process,and improve the quality of diagnosis.Methods Firstly,data enhancement,image resizings,and TFRecord coding are used to preprocess the input of the model,and then a 34-layer deep residual network(ResNet-34)is constructed to extract the characteristics of psoriasis.Finally,we used the Adam algorithm as the optimizer to train ResNet-34,used cross-entropy as the loss function of ResNet-34 in this study to measure the accuracy of the model,and obtained an optimized ResNet-34 model for psoriasis diagnosis.Results The experimental results based on k-fold cross validation show that the proposed model is superior to other diagnostic methods in terms of recall rate,F1-score and ROC curve.Conclusion The ResNet-34 model can achieve accurate diagnosis of psoriasis,and provide technical support for data analysis and intelligent diagnosis and treatment of psoriasis.展开更多
With the advent of Machine and Deep Learning algorithms,medical image diagnosis has a new perception of diagnosis and clinical treatment.Regret-tably,medical images are more susceptible to capturing noises despite the...With the advent of Machine and Deep Learning algorithms,medical image diagnosis has a new perception of diagnosis and clinical treatment.Regret-tably,medical images are more susceptible to capturing noises despite the peak in intelligent imaging techniques.However,the presence of noise images degrades both the diagnosis and clinical treatment processes.The existing intelligent meth-ods suffer from the deficiency in handling the diverse range of noise in the ver-satile medical images.This paper proposes a novel deep learning network which learns from the substantial extent of noise in medical data samples to alle-viate this challenge.The proposed deep learning architecture exploits the advan-tages of the capsule network,which is used to extract correlation features and combine them with redefined residual features.Additionally,thefinal stage of dense learning is replaced with powerful extreme learning machines to achieve a better diagnosis rate,even for noisy and complex images.Extensive experimen-tation has been conducted using different medical images.Various performances such as Peak-Signal-To-Noise Ratio(PSNR)and Structural-Similarity-Index-Metrics(SSIM)are compared with the existing deep learning architectures.Addi-tionally,a comprehensive analysis of individual algorithms is analyzed.The experimental results prove that the proposed model has outperformed the other existing algorithms by a substantial margin and proved its supremacy over the other learning models.展开更多
With the advent of Machine and Deep Learning algorithms,medical image diagnosis has a new perception of diagnosis and clinical treatment.Regret-tably,medical images are more susceptible to capturing noises despite the...With the advent of Machine and Deep Learning algorithms,medical image diagnosis has a new perception of diagnosis and clinical treatment.Regret-tably,medical images are more susceptible to capturing noises despite the peak in intelligent imaging techniques.However,the presence of noise images degrades both the diagnosis and clinical treatment processes.The existing intelligent meth-ods suffer from the deficiency in handling the diverse range of noise in the ver-satile medical images.This paper proposes a novel deep learning network which learns from the substantial extent of noise in medical data samples to alle-viate this challenge.The proposed deep learning architecture exploits the advan-tages of the capsule network,which is used to extract correlation features and combine them with redefined residual features.Additionally,the final stage of dense learning is replaced with powerful extreme learning machines to achieve a better diagnosis rate,even for noisy and complex images.Extensive experimen-tation has been conducted using different medical images.Various performances such as Peak-Signal-To-Noise Ratio(PSNR)and Structural-Similarity-Index-Metrics(SSIM)are compared with the existing deep learning architectures.Addi-tionally,a comprehensive analysis of individual algorithms is analyzed.The experimental results prove that the proposed model has outperformed the other existing algorithms by a substantial margin and proved its supremacy over the other learning models.展开更多
Timely and accurate gas load forecasting is critical for optimal scheduling under tight winter gas supply conditions.Under the background of the implementation of“coal-to-gas”for winter heating in rural areas of Nor...Timely and accurate gas load forecasting is critical for optimal scheduling under tight winter gas supply conditions.Under the background of the implementation of“coal-to-gas”for winter heating in rural areas of North China and the sufficient field research,this paper proposes a correction algorithm for daily average temperature based on the cumulative effect of temperature and a set of combined forecasting models for gas load forecasting based on machine learning and introduces its application through a detailed case study.In order to solve the problems of forecasting performance degradation and complexity increase caused by too many influencing factors,a combined forecasting model back-propagation-improved complete ensemble empirical mode decomposition with adaptive-noise-gated recurrent unit based on residual sequence analysis is proposed.Back propagation(BP)neural network is used to analyze the main influencing factors,so that the secondary influencing factors are reflected in the residual sequence generated by the forecasting.After decomposition,reconstruction,and re-forecast,the mean absolute percentage error(MAPE)of the combined models for the daily gas load in the case study has been controlled under 1.9%,which is significantly improved compared with each single algorithm.The forecasting error before and after the temperature correction are also compared.It is found that the MAPE with the temperature correction is reduced by 1.7%,which reflects the effectiveness of the temperature correction to eliminate the impact of temperature cumulative effect and its contribution to the improvement of the forecasting accuracy for the combined forecasting models.展开更多
目的步态识别是交通管理、监控安防领域的关键技术,为了解决现有步态识别算法无法充分捕捉和利用人体生物特征,在协变量干扰下模型精度降低的问题,本文提出一种深度提取和融合步态特征与身形特征的高精度步态识别方法。方法首先使用高...目的步态识别是交通管理、监控安防领域的关键技术,为了解决现有步态识别算法无法充分捕捉和利用人体生物特征,在协变量干扰下模型精度降低的问题,本文提出一种深度提取和融合步态特征与身形特征的高精度步态识别方法。方法首先使用高分辨率网络(high resolution network,HRNet)提取出人体骨架关键点;以残差神经网络ResNet-50(residual network)为主干,利用深度残差模块的复杂特征学习能力,从骨架信息中充分提取相对稳定的身形特征与提供显性高效运动本质表达的步态特征;设计多分支特征融合(multi-branch feature fusion,MFF)模块,进行不同通道间的尺寸对齐与权重优化,通过动态权重矩阵调节各分支贡献,把身形特征和步态特征融合为区分度更强的总体特征。结果室内数据集采用跨视角多状态CASIA-B(Institute of Automation,Chinese Academy of Sciences)数据集,本文方法在跨视角实验中表现稳健;在多状态实验中,常规组的识别准确率为94.52%,外套干扰组在同类算法中的识别性能最佳。在开放场景数据集中,模型同样体现出较高的泛化能力,相比于现有算法,本文方法的准确率提升了4.1%。结论本文设计的步态识别方法充分利用了深度残差模块的特征提取能力与多特征融合的互补优势,面向复杂识别场景仍具有较高的模型识别精度与泛化能力。展开更多
文摘Cyber-Physical Systems integrated with information technologies introduce vulnerabilities that extend beyond traditional cyber threats.Attackers can non-invasively manipulate sensors and spoof controllers,which in turn increases the autonomy of the system.Even though the focus on protecting against sensor attacks increases,there is still uncertainty about the optimal timing for attack detection.Existing systems often struggle to manage the trade-off between latency and false alarm rate,leading to inefficiencies in real-time anomaly detection.This paper presents a framework designed to monitor,predict,and control dynamic systems with a particular emphasis on detecting and adapting to changes,including anomalies such as“drift”and“attack”.The proposed algorithm integrates a Transformer-based Attention Generative Adversarial Residual model,which combines the strengths of generative adversarial networks,residual networks,and attention algorithms.The system operates in two phases:offline and online.During the offline phase,the proposed model is trained to learn complex patterns,enabling robust anomaly detection.The online phase applies a trained model,where the drift adapter adjusts the model to handle data changes,and the attack detector identifies deviations by comparing predicted and actual values.Based on the output of the attack detector,the controller makes decisions then the actuator executes suitable actions.Finally,the experimental findings show that the proposed model balances detection accuracy of 99.25%,precision of 98.84%,sensitivity of 99.10%,specificity of 98.81%,and an F1-score of 98.96%,thus provides an effective solution for dynamic and safety-critical environments.
基金co-supported by the National Natural Science Foundation of China (Nos. 41804024, 41804026)the Open Fund of Shaanxi Key Laboratory of Integrated and Intelligent Navigation of China (No. SKLIIN-20190205)
文摘The Least Squares Residual(LSR)algorithm,one of the classical Receiver Autonomous Integrity Monitoring(RAIM)algorithms for Global Navigation Satellite System(GNSS),presents a high Missed Detection Risk(MDR)for a large-slope faulty satellite and a high False Alarm Risk(FAR)for a small-slope faulty satellite.From the theoretical analysis of the high MDR and FAR cause,the optimal slope is determined,and thereby the optimal test statistic for fault detection is conceived,which can minimize the FAR with the MDR not exceeding its allowable value.To construct a test statistic approximate to the optimal one,the CorrelationWeighted LSR(CW-LSR)algorithm is proposed.The CW-LSR test statistic remains the sum of pseudorange residual squares,but the square for the most potentially faulty satellite,judged by correlation analysis between the pseudorange residual and observation error,is weighted with an optimal-slope-based factor.It does not obey the same distribution but has the same noncentral parameter with the optimal test statistic.The superior performance of the CW-LSR algorithm is verified via simulation,both reducing the FAR for a small-slope faulty satellite with the MDR not exceeding its allowable value and reducing the MDR for a large-slope faulty satellite at the expense of FAR addition.
文摘The Least Squares Residual(LSR)algorithm is commonly used in the Receiver Autonomous Integrity Monitoring(RAIM).However,LSR algorithm presents high Missed Detection Risk(MDR)caused by a large-slope faulty satellite and high False Alert Risk(FAR)caused by a small-slope faulty satellite.In this paper,the LSR algorithm is improved to reduce the MDR for a large-slope faulty satellite and the FAR for a small-slope faulty satellite.Based on the analysis of the vertical critical slope,the optimal decentralized factor is defined and the optimal test statistic is conceived,which can minimize the FAR with the premise that the MDR does not exceed its allowable value of all three directions.To construct a new test statistic approximating to the optimal test statistic,the Optimal Decentralized Factor weighted LSR(ODF-LSR)algorithm is proposed.The new test statistic maintains the sum of pseudo-range residual squares,but the specific pseudo-range residual is weighted with a parameter related to the optimal decentralized factor.The new test statistic has the same decentralized parameter with the optimal test statistic when single faulty satellite exists,and the difference between the expectation of the new test statistic and the optimal test statistic is the minimum when no faulty satellite exists.The performance of the ODFLSR algorithm is demonstrated by simulation experiments.
文摘A large number of sparse signal reconstruction algorithms have been continuously proposed, but almost all greedy algorithms add a fixed number of indices to the support set in each iteration. Although the mechanism of selecting the fixed number of indexes improves the reconstruction efficiency, it also brings the problem of low index selection accuracy. Based on the full study of the theory of compressed sensing, we propose a dynamic indexes selection strategy based on residual update to improve the performance of the compressed sampling matching pursuit algorithm (CoSaMP). As an extension of CoSaMP algorithm, the proposed algorithm adopts a residual comparison strategy to improve the accuracy of backtracking selected indexes. This backtracking strategy can efficiently select backtracking indexes. And without increasing the computational complexity, the proposed improvement algorithm has a higher exact reconstruction rate and peak signal to noise ratio (PSNR). Simulation results demonstrate the proposed algorithm significantly outperforms the CoSaMP for image recovery and one-dimensional signal.
基金supported by Guangdong Major Project of Basic and Applied Basic Research No.2020B0301030008Science and Technology Program of Guangzhou No.2019050001+2 种基金the Chinese Academy of Sciences Grant QYZDJ-SSWSYS018the National Natural Science Foundation of China(Grant No.12171479)supported by the National Natural Science Foundation of China(Grant Nos.11301339 and 11491240108)。
文摘Message passing algorithms,whose iterative nature captures complicated interactions among interconnected variables in complex systems and extracts information from the fixed point of iterated messages,provide a powerful toolkit in tackling hard computational tasks in optimization,inference,and learning problems.In the context of constraint satisfaction problems(CSPs),when a control parameter(such as constraint density)is tuned,multiple threshold phenomena emerge,signaling fundamental structural transitions in their solution space.Finding solutions around these transition points is exceedingly challenging for algorithm design,where message passing algorithms suffer from a large message fiuctuation far from convergence.Here we introduce a residual-based updating step into message passing algorithms,in which messages with large variation between consecutive steps are given high priority in the updating process.For the specific example of model RB(revised B),a typical prototype of random CSPs with growing domains,we show that our algorithm improves the convergence of message updating and increases the success probability in finding solutions around the satisfiability threshold with a low computational cost.Our approach to message passing algorithms should be of value for exploring their power in developing algorithms to find ground-state solutions and understand the detailed structure of solution space of hard optimization problems.
基金supported by the State Key Program of National Natural Science of China (Grant No.60532030)the New Century Excellent Talents in University (Grant No.NCET-08-0333)the Natural Science Foundation of Shandong Province (Grant No.Y2007G10)
文摘The dominant error source of mobile terminal location in wireless sensor networks （WSNs） is the non-line-of-sight （NLOS） propagation error. Among the algorithms proposed to mitigate the influence of NLOS propagation error, residual test （RT） is an efficient one, however with high computational complexity （CC）. An improved algorithm that memorizes the light of sight （LOS） range measurements （RMs） identified memorize LOS range measurements identified residual test （MLSI-RT） is presented in this paper to address this problem. The MLSI-RT is based on the assumption that when all RMs are from LOS propagations, the normalized residual follows the central Chi-Square distribution while for NLOS cases it is non-central. This study can reduce the CC by more than 90%.
文摘Wireless sensor networks (WSNs) are mostly deployed in a remote working environment, since sensor nodes are small in size, cost-efficient, low-power devices, and have limited battery power supply. Because of limited power source, energy consumption has been considered as the most critical factor when designing sensor network protocols. The network lifetime mainly depends on the battery lifetime of the node. The main concern is to increase the lifetime with respect to energy constraints. One way of doing this is by turning off redun-dant nodes to sleep mode to conserve energy while active nodes can provide essential k-coverage, which improves fault-tolerance. Hence, we use scheduling algorithms that turn off redundant nodes after providing the required coverage level k. The scheduling algorithms can be implemented in centralized or localized schemes, which have their own advantages and disadvantages. To exploit the advantages of both schemes, we employ both schemes on the network according to a threshold value. This threshold value is estimated on the performance of WSN based on network lifetime comparison using centralized and localized algorithms. To extend the network lifetime and to extract the useful energy from the network further, we go for compromise in the area covered by nodes.
文摘X oilfield has successfully adopted horizontal wells to develop strong bottom water reservoirs, as a typical representative of development styles in the Bohai offshore oilfield. At present, many contributions to methods of inverting relative permeability curve and forecasting residual recoverable reserves had been made by investigators, but rarely involved in horizontal wells’ in bottom water reservoir. As the pore volume injected was less (usually under 30 PV), the relative permeability curve endpoint had become a serious distortion. That caused a certain deviation in forecasting residual recoverable reserves in the practical value of field directly. For the performance of water cresting, the common method existed some problems, such as no pertinence, ineffectiveness and less affecting factors considered. This paper adopts the streamlines theory with two phases flowing to solve that. Meanwhile, based on the research coupling genetic algorithm, optimized relative permeability curve was calculated by bottom-water drive model. The residual oil saturation calculated was lower than the initial’s, and the hydrophilic property was more reinforced, due to improving the pore volume injected vastly. Also, the study finally helped us enhance residual recoverable reserves degree at high water cut stage, more than 20%, taking Guantao sandstone as an example. As oil field being gradually entering high water cut stage, this method had a great significance to evaluate the development effect and guide the potential of the reservoir.
文摘Transmission of data over the internet has become a critical issue as a result of the advancement in technology, since it is possible for pirates to steal the intellectual property of content owners. This paper presents a new digital watermarking scheme that combines some operators of the Genetic Algorithm (GA) and the Residue Number (RN) System (RNS) to perform encryption on an image, which is embedded into a cover image for the purposes of watermarking. Thus, an image watermarking scheme uses an encrypted image. The secret image is embedded in decomposed frames of the cover image achieved by applying a three-level Discrete Wavelet Transform (DWT). This is to ensure that the secret information is not exposed even when there is a successful attack on the cover information. Content creators can prove ownership of the multimedia content by unveiling the secret information in a court of law. The proposed scheme was tested with sample data using MATLAB2022 and the results of the simulation show a great deal of imperceptibility and robustness as compared to similar existing schemes.
基金Project supported by the National High Technology Research and Development Program of China (Grant No 2006AA012339)
文摘This paper analyses the dynamic residual aberrations of a conformal optical system and introduces adaptive optics （AO） correction technology to this system. The image sharpening AO system is chosen as the correction scheme.Communication between MATLAB and Code V is established via ActiveX technique in computer simulation.The SPGD algorithm is operated at seven zoom positions to calculate the optimized surface shape of the deformable mirror.After comparison of performance of the corrected system with the baseline system,AO technology is proved to be a good way of correcting the dynamic residual aberration in conformal optical design.
基金supported by the National Natural Science Foundation of China(No.52075059)the Natural Science Foundation of Chongqing(No.cstc2020jcyj-msxm X0266)。
文摘While the traditional trajectory planning methods are used in robotic belt grinding of blades with an uneven machining allowance distribution, it is hard to obtain the preferable profile accuracy and surface quality to meet the high-performance requirements of aero-engine. To solve this problem, a novel trajectory planning method is proposed in this paper by considering the developed interpolation algorithm and the machining allowance threshold. The residual height error obtained from grinding experiments of titanium alloy sample was compensated to modify the calculation model of row spacing, and a new geometric algorithm was presented to dynamically calculate the cutter contact points based on this revised calculation model and the dichotomy method. Subsequently, the off-line machining program is generated based on a double-vector controlling method to obtain an optimal contact posture. On this basis, three sets of robotic grinding tests of titanium alloy blades were conducted to investigate the advantages of the proposed method.The comparative experimental results revealed that the presented algorithm had improved the surface profile accuracy of blade by 34.2% and 55.1%, respectively. Moreover, the average machined surface roughness was achieved to 0.3 μm and the machining efficiency was obviously promoted. It is concluded that this research work is beneficial to comprehensively improve the machined quality of blades in robotic belt grinding.
基金We thank for the funding support from the Key Research and Development Plan of China(No.2017YFC1703306)Youth Project of Natural Science Foundation of Hunan Province(No.2019JJ50453)+2 种基金Project of Hunan Health Commission(No.202112072217)Open Fund Project of Hunan University of Traditional Chinese Medicine(No.2018JK02)General Project of Education Department of Hunan Province(No.19C1318).
文摘Objective A classification and diagnosis model for psoriasis based on deep residual network is proposed in this paper.Which using deep learning technology to classify and diagnose psoriasis can help reduce the burden of doctors,simplify the diagnosis and treatment process,and improve the quality of diagnosis.Methods Firstly,data enhancement,image resizings,and TFRecord coding are used to preprocess the input of the model,and then a 34-layer deep residual network(ResNet-34)is constructed to extract the characteristics of psoriasis.Finally,we used the Adam algorithm as the optimizer to train ResNet-34,used cross-entropy as the loss function of ResNet-34 in this study to measure the accuracy of the model,and obtained an optimized ResNet-34 model for psoriasis diagnosis.Results The experimental results based on k-fold cross validation show that the proposed model is superior to other diagnostic methods in terms of recall rate,F1-score and ROC curve.Conclusion The ResNet-34 model can achieve accurate diagnosis of psoriasis,and provide technical support for data analysis and intelligent diagnosis and treatment of psoriasis.
文摘With the advent of Machine and Deep Learning algorithms,medical image diagnosis has a new perception of diagnosis and clinical treatment.Regret-tably,medical images are more susceptible to capturing noises despite the peak in intelligent imaging techniques.However,the presence of noise images degrades both the diagnosis and clinical treatment processes.The existing intelligent meth-ods suffer from the deficiency in handling the diverse range of noise in the ver-satile medical images.This paper proposes a novel deep learning network which learns from the substantial extent of noise in medical data samples to alle-viate this challenge.The proposed deep learning architecture exploits the advan-tages of the capsule network,which is used to extract correlation features and combine them with redefined residual features.Additionally,thefinal stage of dense learning is replaced with powerful extreme learning machines to achieve a better diagnosis rate,even for noisy and complex images.Extensive experimen-tation has been conducted using different medical images.Various performances such as Peak-Signal-To-Noise Ratio(PSNR)and Structural-Similarity-Index-Metrics(SSIM)are compared with the existing deep learning architectures.Addi-tionally,a comprehensive analysis of individual algorithms is analyzed.The experimental results prove that the proposed model has outperformed the other existing algorithms by a substantial margin and proved its supremacy over the other learning models.
文摘With the advent of Machine and Deep Learning algorithms,medical image diagnosis has a new perception of diagnosis and clinical treatment.Regret-tably,medical images are more susceptible to capturing noises despite the peak in intelligent imaging techniques.However,the presence of noise images degrades both the diagnosis and clinical treatment processes.The existing intelligent meth-ods suffer from the deficiency in handling the diverse range of noise in the ver-satile medical images.This paper proposes a novel deep learning network which learns from the substantial extent of noise in medical data samples to alle-viate this challenge.The proposed deep learning architecture exploits the advan-tages of the capsule network,which is used to extract correlation features and combine them with redefined residual features.Additionally,the final stage of dense learning is replaced with powerful extreme learning machines to achieve a better diagnosis rate,even for noisy and complex images.Extensive experimen-tation has been conducted using different medical images.Various performances such as Peak-Signal-To-Noise Ratio(PSNR)and Structural-Similarity-Index-Metrics(SSIM)are compared with the existing deep learning architectures.Addi-tionally,a comprehensive analysis of individual algorithms is analyzed.The experimental results prove that the proposed model has outperformed the other existing algorithms by a substantial margin and proved its supremacy over the other learning models.
基金financial support from Science and Technology Major Project of Inner Mongolia Autonomous Region of China(2021ZD0038).
文摘Timely and accurate gas load forecasting is critical for optimal scheduling under tight winter gas supply conditions.Under the background of the implementation of“coal-to-gas”for winter heating in rural areas of North China and the sufficient field research,this paper proposes a correction algorithm for daily average temperature based on the cumulative effect of temperature and a set of combined forecasting models for gas load forecasting based on machine learning and introduces its application through a detailed case study.In order to solve the problems of forecasting performance degradation and complexity increase caused by too many influencing factors,a combined forecasting model back-propagation-improved complete ensemble empirical mode decomposition with adaptive-noise-gated recurrent unit based on residual sequence analysis is proposed.Back propagation(BP)neural network is used to analyze the main influencing factors,so that the secondary influencing factors are reflected in the residual sequence generated by the forecasting.After decomposition,reconstruction,and re-forecast,the mean absolute percentage error(MAPE)of the combined models for the daily gas load in the case study has been controlled under 1.9%,which is significantly improved compared with each single algorithm.The forecasting error before and after the temperature correction are also compared.It is found that the MAPE with the temperature correction is reduced by 1.7%,which reflects the effectiveness of the temperature correction to eliminate the impact of temperature cumulative effect and its contribution to the improvement of the forecasting accuracy for the combined forecasting models.
文摘目的步态识别是交通管理、监控安防领域的关键技术,为了解决现有步态识别算法无法充分捕捉和利用人体生物特征,在协变量干扰下模型精度降低的问题,本文提出一种深度提取和融合步态特征与身形特征的高精度步态识别方法。方法首先使用高分辨率网络(high resolution network,HRNet)提取出人体骨架关键点;以残差神经网络ResNet-50(residual network)为主干,利用深度残差模块的复杂特征学习能力,从骨架信息中充分提取相对稳定的身形特征与提供显性高效运动本质表达的步态特征;设计多分支特征融合(multi-branch feature fusion,MFF)模块,进行不同通道间的尺寸对齐与权重优化,通过动态权重矩阵调节各分支贡献,把身形特征和步态特征融合为区分度更强的总体特征。结果室内数据集采用跨视角多状态CASIA-B(Institute of Automation,Chinese Academy of Sciences)数据集,本文方法在跨视角实验中表现稳健;在多状态实验中,常规组的识别准确率为94.52%,外套干扰组在同类算法中的识别性能最佳。在开放场景数据集中,模型同样体现出较高的泛化能力,相比于现有算法,本文方法的准确率提升了4.1%。结论本文设计的步态识别方法充分利用了深度残差模块的特征提取能力与多特征融合的互补优势,面向复杂识别场景仍具有较高的模型识别精度与泛化能力。
