Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fa...Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.展开更多
Visual object tracking plays a crucial role in computer vision.In recent years,researchers have proposed various methods to achieve high-performance object tracking.Among these,methods based on Transformers have becom...Visual object tracking plays a crucial role in computer vision.In recent years,researchers have proposed various methods to achieve high-performance object tracking.Among these,methods based on Transformers have become a research hotspot due to their ability to globally model and contextualize information.However,current Transformer-based object tracking methods still face challenges such as low tracking accuracy and the presence of redundant feature information.In this paper,we introduce self-calibration multi-head self-attention Transformer(SMSTracker)as a solution to these challenges.It employs a hybrid tensor decomposition self-organizing multihead self-attention transformermechanism,which not only compresses and accelerates Transformer operations but also significantly reduces redundant data,thereby enhancing the accuracy and efficiency of tracking.Additionally,we introduce a self-calibration attention fusion block to resolve common issues of attention ambiguities and inconsistencies found in traditional trackingmethods,ensuring the stability and reliability of tracking performance across various scenarios.By integrating a hybrid tensor decomposition approach with a self-organizingmulti-head self-attentive transformer mechanism,SMSTracker enhances the efficiency and accuracy of the tracking process.Experimental results show that SMSTracker achieves competitive performance in visual object tracking,promising more robust and efficient tracking systems,demonstrating its potential to providemore robust and efficient tracking solutions in real-world applications.展开更多
The satellite-terrestrial networks possess the ability to transcend geographical constraints inherent in traditional communication networks,enabling global coverage and offering users ubiquitous computing power suppor...The satellite-terrestrial networks possess the ability to transcend geographical constraints inherent in traditional communication networks,enabling global coverage and offering users ubiquitous computing power support,which is an important development direction of future communications.In this paper,we take into account a multi-scenario network model under the coverage of low earth orbit(LEO)satellite,which can provide computing resources to users in faraway areas to improve task processing efficiency.However,LEO satellites experience limitations in computing and communication resources and the channels are time-varying and complex,which makes the extraction of state information a daunting task.Therefore,we explore the dynamic resource management issue pertaining to joint computing,communication resource allocation and power control for multi-access edge computing(MEC).In order to tackle this formidable issue,we undertake the task of transforming the issue into a Markov decision process(MDP)problem and propose the self-attention based dynamic resource management(SABDRM)algorithm,which effectively extracts state information features to enhance the training process.Simulation results show that the proposed algorithm is capable of effectively reducing the long-term average delay and energy consumption of the tasks.展开更多
The frequent missing values in radar-derived time-series tracks of aerial targets(RTT-AT)lead to significant challenges in subsequent data-driven tasks.However,the majority of imputation research focuses on random mis...The frequent missing values in radar-derived time-series tracks of aerial targets(RTT-AT)lead to significant challenges in subsequent data-driven tasks.However,the majority of imputation research focuses on random missing(RM)that differs significantly from common missing patterns of RTT-AT.The method for solving the RM may experience performance degradation or failure when applied to RTT-AT imputation.Conventional autoregressive deep learning methods are prone to error accumulation and long-term dependency loss.In this paper,a non-autoregressive imputation model that addresses the issue of missing value imputation for two common missing patterns in RTT-AT is proposed.Our model consists of two probabilistic sparse diagonal masking self-attention(PSDMSA)units and a weight fusion unit.It learns missing values by combining the representations outputted by the two units,aiming to minimize the difference between the missing values and their actual values.The PSDMSA units effectively capture temporal dependencies and attribute correlations between time steps,improving imputation quality.The weight fusion unit automatically updates the weights of the output representations from the two units to obtain a more accurate final representation.The experimental results indicate that,despite varying missing rates in the two missing patterns,our model consistently outperforms other methods in imputation performance and exhibits a low frequency of deviations in estimates for specific missing entries.Compared to the state-of-the-art autoregressive deep learning imputation model Bidirectional Recurrent Imputation for Time Series(BRITS),our proposed model reduces mean absolute error(MAE)by 31%~50%.Additionally,the model attains a training speed that is 4 to 8 times faster when compared to both BRITS and a standard Transformer model when trained on the same dataset.Finally,the findings from the ablation experiments demonstrate that the PSDMSA,the weight fusion unit,cascade network design,and imputation loss enhance imputation performance and confirm the efficacy of our design.展开更多
To predict renewable energy sources such as solar power in microgrids more accurately,a hybrid power prediction method is presented in this paper.First,the self-attention mechanism is introduced based on a bidirection...To predict renewable energy sources such as solar power in microgrids more accurately,a hybrid power prediction method is presented in this paper.First,the self-attention mechanism is introduced based on a bidirectional gated recurrent neural network(BiGRU)to explore the time-series characteristics of solar power output and consider the influence of different time nodes on the prediction results.Subsequently,an improved quantum particle swarm optimization(QPSO)algorithm is proposed to optimize the hyperparameters of the combined prediction model.The final proposed LQPSO-BiGRU-self-attention hybrid model can predict solar power more effectively.In addition,considering the coordinated utilization of various energy sources such as electricity,hydrogen,and renewable energy,a multi-objective optimization model that considers both economic and environmental costs was constructed.A two-stage adaptive multi-objective quantum particle swarm optimization algorithm aided by a Lévy flight,named MO-LQPSO,was proposed for the comprehensive optimal scheduling of a multi-energy microgrid system.This algorithm effectively balances the global and local search capabilities and enhances the solution of complex nonlinear problems.The effectiveness and superiority of the proposed scheme are verified through comparative simulations.展开更多
Aerial threat assessment is a crucial link in modern air combat, whose result counts a great deal for commanders to make decisions. With the consideration that the existing threat assessment methods have difficulties ...Aerial threat assessment is a crucial link in modern air combat, whose result counts a great deal for commanders to make decisions. With the consideration that the existing threat assessment methods have difficulties in dealing with high dimensional time series target data, a threat assessment method based on self-attention mechanism and gated recurrent unit(SAGRU) is proposed. Firstly, a threat feature system including air combat situations and capability features is established. Moreover, a data augmentation process based on fractional Fourier transform(FRFT) is applied to extract more valuable information from time series situation features. Furthermore, aiming to capture key characteristics of battlefield evolution, a bidirectional GRU and SA mechanisms are designed for enhanced features.Subsequently, after the concatenation of the processed air combat situation and capability features, the target threat level will be predicted by fully connected neural layers and the softmax classifier. Finally, in order to validate this model, an air combat dataset generated by a combat simulation system is introduced for model training and testing. The comparison experiments show the proposed model has structural rationality and can perform threat assessment faster and more accurately than the other existing models based on deep learning.展开更多
Traditional models for semantic segmentation in point clouds primarily focus on smaller scales.However,in real-world applications,point clouds often exhibit larger scales,leading to heavy computational and memory requ...Traditional models for semantic segmentation in point clouds primarily focus on smaller scales.However,in real-world applications,point clouds often exhibit larger scales,leading to heavy computational and memory requirements.The key to handling large-scale point clouds lies in leveraging random sampling,which offers higher computational efficiency and lower memory consumption compared to other sampling methods.Nevertheless,the use of random sampling can potentially result in the loss of crucial points during the encoding stage.To address these issues,this paper proposes cross-fusion self-attention network(CFSA-Net),a lightweight and efficient network architecture specifically designed for directly processing large-scale point clouds.At the core of this network is the incorporation of random sampling alongside a local feature extraction module based on cross-fusion self-attention(CFSA).This module effectively integrates long-range contextual dependencies between points by employing hierarchical position encoding(HPC).Furthermore,it enhances the interaction between each point’s coordinates and feature information through cross-fusion self-attention pooling,enabling the acquisition of more comprehensive geometric information.Finally,a residual optimization(RO)structure is introduced to extend the receptive field of individual points by stacking hierarchical position encoding and cross-fusion self-attention pooling,thereby reducing the impact of information loss caused by random sampling.Experimental results on the Stanford Large-Scale 3D Indoor Spaces(S3DIS),Semantic3D,and SemanticKITTI datasets demonstrate the superiority of this algorithm over advanced approaches such as RandLA-Net and KPConv.These findings underscore the excellent performance of CFSA-Net in large-scale 3D semantic segmentation.展开更多
Due to the lack of long-range association and spatial location information,fine details and accurate boundaries of complex clothing images cannot always be obtained by using the existing deep learning-based methods.Th...Due to the lack of long-range association and spatial location information,fine details and accurate boundaries of complex clothing images cannot always be obtained by using the existing deep learning-based methods.This paper presents a convolutional structure with multi-scale fusion to optimize the step of clothing feature extraction and a self-attention module to capture long-range association information.The structure enables the self-attention mechanism to directly participate in the process of information exchange through the down-scaling projection operation of the multi-scale framework.In addition,the improved self-attention module introduces the extraction of 2-dimensional relative position information to make up for its lack of ability to extract spatial position features from clothing images.The experimental results based on the colorful fashion parsing dataset(CFPD)show that the proposed network structure achieves 53.68%mean intersection over union(mIoU)and has better performance on the clothing parsing task.展开更多
This paper presents a method for aspect based sentiment classification tasks, named convolutional multi-head self-attention memory network(CMA-Mem Net). This is an improved model based on memory networks, and makes it...This paper presents a method for aspect based sentiment classification tasks, named convolutional multi-head self-attention memory network(CMA-Mem Net). This is an improved model based on memory networks, and makes it possible to extract more rich and complex semantic information from sequences and aspects. In order to fix the memory network’s inability to capture context-related information on a word-level,we propose utilizing convolution to capture n-gram grammatical information. We use multi-head self-attention to make up for the problem where the memory network ignores the semantic information of the sequence itself. Meanwhile, unlike most recurrent neural network(RNN) long short term memory(LSTM), gated recurrent unit(GRU) models, we retain the parallelism of the network. We experiment on the open datasets Sem Eval-2014 Task 4 and Sem Eval-2016 Task 6. Compared with some popular baseline methods, our model performs excellently.展开更多
The martensitic transformation temperature is the basis for the application of shape memory alloys(SMAs),and the ability to quickly and accurately predict the transformation temperature of SMAs has very important prac...The martensitic transformation temperature is the basis for the application of shape memory alloys(SMAs),and the ability to quickly and accurately predict the transformation temperature of SMAs has very important practical significance.In this work,machine learning(ML)methods were utilized to accelerate the search for shape memory alloys with targeted properties(phase transition temperature).A group of component data was selected to design shape memory alloys using reverse design method from numerous unexplored data.Component modeling and feature modeling were used to predict the phase transition temperature of the shape memory alloys.The experimental results of the shape memory alloys were obtained to verify the effectiveness of the support vector regression(SVR)model.The results show that the machine learning model can obtain target materials more efficiently and pertinently,and realize the accurate and rapid design of shape memory alloys with specific target phase transition temperature.On this basis,the relationship between phase transition temperature and material descriptors is analyzed,and it is proved that the key factors affecting the phase transition temperature of shape memory alloys are based on the strength of the bond energy between atoms.This work provides new ideas for the controllable design and performance optimization of Cu-based shape memory alloys.展开更多
Vascular etiology is the second most prevalent cause of cognitive impairment globally.Endothelin-1,which is produced and secreted by endothelial cells and astrocytes,is implicated in the pathogenesis of stroke.However...Vascular etiology is the second most prevalent cause of cognitive impairment globally.Endothelin-1,which is produced and secreted by endothelial cells and astrocytes,is implicated in the pathogenesis of stroke.However,the way in which changes in astrocytic endothelin-1 lead to poststroke cognitive deficits following transient middle cerebral artery occlusion is not well understood.Here,using mice in which astrocytic endothelin-1 was overexpressed,we found that the selective overexpression of endothelin-1 by astrocytic cells led to ischemic stroke-related dementia(1 hour of ischemia;7 days,28 days,or 3 months of reperfusion).We also revealed that astrocytic endothelin-1 overexpression contributed to the role of neural stem cell proliferation but impaired neurogenesis in the dentate gyrus of the hippocampus after middle cerebral artery occlusion.Comprehensive proteome profiles and western blot analysis confirmed that levels of glial fibrillary acidic protein and peroxiredoxin 6,which were differentially expressed in the brain,were significantly increased in mice with astrocytic endothelin-1 overexpression in comparison with wild-type mice 28 days after ischemic stroke.Moreover,the levels of the enriched differentially expressed proteins were closely related to lipid metabolism,as indicated by Kyoto Encyclopedia of Genes and Genomes pathway analysis.Liquid chromatography-mass spectrometry nontargeted metabolite profiling of brain tissues showed that astrocytic endothelin-1 overexpression altered lipid metabolism products such as glycerol phosphatidylcholine,sphingomyelin,and phosphatidic acid.Overall,this study demonstrates that astrocytic endothelin-1 overexpression can impair hippocampal neurogenesis and that it is correlated with lipid metabolism in poststroke cognitive dysfunction.展开更多
Memory deficit,which is often associated with aging and many psychiatric,neurological,and neurodegenerative diseases,has been a challenging issue for treatment.Up till now,all potential drug candidates have failed to ...Memory deficit,which is often associated with aging and many psychiatric,neurological,and neurodegenerative diseases,has been a challenging issue for treatment.Up till now,all potential drug candidates have failed to produce satisfa ctory effects.Therefore,in the search for a solution,we found that a treatment with the gene corresponding to the RGS14414protein in visual area V2,a brain area connected with brain circuits of the ventral stream and the medial temporal lobe,which is crucial for object recognition memory(ORM),can induce enhancement of ORM.In this study,we demonstrated that the same treatment with RGS14414in visual area V2,which is relatively unaffected in neurodegenerative diseases such as Alzheimer s disease,produced longlasting enhancement of ORM in young animals and prevent ORM deficits in rodent models of aging and Alzheimer’s disease.Furthermore,we found that the prevention of memory deficits was mediated through the upregulation of neuronal arbo rization and spine density,as well as an increase in brain-derived neurotrophic factor(BDNF).A knockdown of BDNF gene in RGS14414-treated aging rats and Alzheimer s disease model mice caused complete loss in the upregulation of neuronal structural plasticity and in the prevention of ORM deficits.These findings suggest that BDNF-mediated neuronal structural plasticity in area V2 is crucial in the prevention of memory deficits in RGS14414-treated rodent models of aging and Alzheimer’s disease.Therefore,our findings of RGS14414gene-mediated activation of neuronal circuits in visual area V2 have therapeutic relevance in the treatment of memory deficits.展开更多
Mainstream media play a crucial role in constructing the cultural memory of a city.This study used 319 short videos released by“Hi Chengdu,”a new media product of Chengdu Radio and Television,as samples.Based on the...Mainstream media play a crucial role in constructing the cultural memory of a city.This study used 319 short videos released by“Hi Chengdu,”a new media product of Chengdu Radio and Television,as samples.Based on the grounded theory,a research framework encompassing“content,technology,and discourse”was established to explore the paths through which mainstream media construct the cultural memory.Regarding content,this paper emphasized temporal and spatial contexts and urban spaces,delving deep into the themes of the cultural memory and vehicles for it.In terms of technology,this paper discussed the practice of leveraging audio/visual-mode discourse to stitch together the impressions of a city and evoke emotional resonance to create a“flow”of memory.As for discourse,this paper looked at the performance of a communication ritual to frame concepts and shape urban identity.It is essential to break free from conventional thinking and leverage local culture as the primary driving force to further boost a city’s productivity,in order to excel in cultural communication.展开更多
Background and Purpose: Opioids, used for centuries to alleviate pain, have become a double-edged sword. While effective, they come with a host of adverse effects, including memory and cognition impairment. This revie...Background and Purpose: Opioids, used for centuries to alleviate pain, have become a double-edged sword. While effective, they come with a host of adverse effects, including memory and cognition impairment. This review delves into the impact of opioid drugs on cognitive functions, explores underlying mechanisms, and investigates their prevalence in both medical care and illicit drug use. The ultimate goal is to find ways to mitigate their potential harm and address the ongoing opioid crisis. Methods: We sourced data from PubMed and Google Scholar, employing search combinations like “opioids,” “memory,” “cognition,” “amnesia,” “cognitive function,” “executive function,” and “inhibition.” Our focus was on English-language articles spanning from the inception of these databases up to the present. Results: The literature consistently reveals that opioid use, particularly at high doses, adversely affects memory and other cognitive functions. Longer deliberation times, impaired decision-making, impulsivity, and behavioral disorders are common consequences. Chronic high-dose opioid use is associated with conditions such as amnesiac syndrome (OAS), post-operative cognitive dysfunction (POCD), neonatal abstinence syndrome (NAS), depression, anxiety, sedation, and addiction. Alarming trends show increased opioid use over recent decades, amplifying the risk of these outcomes. Conclusion: Opioids cast a shadow over memory and cognitive function. These effects range from amnesiac effects, lessened cognitive function, depression, and more. Contributing factors include over-prescription, misuse, misinformation, and prohibition policies. Focusing on correct informational campaigns, removing punitive policies, and focusing on harm reduction strategies have been shown to lessen the abuse and use of opioids and thus helping to mitigate the adverse effects of these drugs. Further research into the impacts of opioids on cognitive abilities is also needed as they are well demonstrated in the literature, but the mechanism is not often completely understood.展开更多
The adoption of Docker containers has revolutionized software deployment by providing a lightweight and efficient way to isolate applications in data centers. However, securing these containers, especially when handli...The adoption of Docker containers has revolutionized software deployment by providing a lightweight and efficient way to isolate applications in data centers. However, securing these containers, especially when handling sensitive data, poses significant challenges. Traditional Linux Security Modules (LSMs) such as SELinux and AppArmor have limitations in providing fine-grained access control to files within containers. This paper presents a novel approach using eBPF (extended Berkeley Packet Filter) to implement a LSM that focuses on file-oriented access control within Docker containers. The module allows the specification of policies that determine which programs can access sensitive files, providing enhanced security without relying solely on the host operating system’s major LSM.展开更多
With the rapid development of deep learning algorithms,the computational complexity and functional diversity are increasing rapidly.However,the gap between high computational density and insufficient memory bandwidth ...With the rapid development of deep learning algorithms,the computational complexity and functional diversity are increasing rapidly.However,the gap between high computational density and insufficient memory bandwidth under the traditional von Neumann architecture is getting worse.Analyzing the algorithmic characteristics of convolutional neural network(CNN),it is found that the access characteristics of convolution(CONV)and fully connected(FC)operations are very different.Based on this feature,a dual-mode reronfigurable distributed memory architecture for CNN accelerator is designed.It can be configured in Bank mode or first input first output(FIFO)mode to accommodate the access needs of different operations.At the same time,a programmable memory control unit is designed,which can effectively control the dual-mode configurable distributed memory architecture by using customized special accessing instructions and reduce the data accessing delay.The proposed architecture is verified and tested by parallel implementation of some CNN algorithms.The experimental results show that the peak bandwidth can reach 13.44 GB·s^(-1)at an operating frequency of 120 MHz.This work can achieve 1.40,1.12,2.80 and 4.70 times the peak bandwidth compared with the existing work.展开更多
With the rapid development of machine learning,the demand for high-efficient computing becomes more and more urgent.To break the bottleneck of the traditional Von Neumann architecture,computing-in-memory(CIM)has attra...With the rapid development of machine learning,the demand for high-efficient computing becomes more and more urgent.To break the bottleneck of the traditional Von Neumann architecture,computing-in-memory(CIM)has attracted increasing attention in recent years.In this work,to provide a feasible CIM solution for the large-scale neural networks(NN)requiring continuous weight updating in online training,a flash-based computing-in-memory with high endurance(10^(9) cycles)and ultrafast programming speed is investigated.On the one hand,the proposed programming scheme of channel hot electron injection(CHEI)and hot hole injection(HHI)demonstrate high linearity,symmetric potentiation,and a depression process,which help to improve the training speed and accuracy.On the other hand,the low-damage programming scheme and memory window(MW)optimizations can suppress cell degradation effectively with improved computing accuracy.Even after 109 cycles,the leakage current(I_(off))of cells remains sub-10pA,ensuring the large-scale computing ability of memory.Further characterizations are done on read disturb to demonstrate its robust reliabilities.By processing CIFAR-10 tasks,it is evident that~90%accuracy can be achieved after 109 cycles in both ResNet50 and VGG16 NN.Our results suggest that flash-based CIM has great potential to overcome the limitations of traditional Von Neumann architectures and enable high-performance NN online training,which pave the way for further development of artificial intelligence(AI)accelerators.展开更多
Bisphenol A (BPA), a toxicant which can leach into food from plastic containers, is reported to induce neurotoxicity among others via oxidative mechanisms. However, antioxidant compounds have been suggested to mitigat...Bisphenol A (BPA), a toxicant which can leach into food from plastic containers, is reported to induce neurotoxicity among others via oxidative mechanisms. However, antioxidant compounds have been suggested to mitigate BPA-induced toxicities. Garcinia kola (GK) and its bioactive compound, kolaviron, are well-established natural antioxidants, which can exert protective effects against BPA-induced toxicities. This study was designed to investigate the likely mitigating effect of GK and kolaviron on BPA-induced memory impairment and hippocampal neuroinflammation in male Wistar rats. Thirty-five rats were equally grouped and treated as follows: I and II received distilled water and corn oil, respectively at 0.2 mL, while III - VII received BPA (50 mg/kg), BPA + GK (200 mg/kg), BPA + kolaviron (200 mg/kg), GK and kolaviron, respectively for 28 days p.o. Thereafter, behavioral studies were done using the Novel Object Recognition and Y maze tests. Subsequently under anaesthesia, the hippocampus in each animal was dissected out, homogenized and analysed for malondialdehyde, superoxide dismutase, catalase, reduced glutathione, glutathione transferase, nitrites, interleukin-6, tumour necrosis factor-α, acetylcholinesterase, glutamate acid decarboxylase, and arginase activity. Data were analyzed by ANOVA and Tukey Post-hoc test at p p Garcinia kola and Kolaviron mitigate bisphenol A-induced memory impairment and neuroinflammation via antioxidant potentiation and neurotransmitter balance.展开更多
Reducing the process variation is a significant concern for resistive random access memory(RRAM).Due to its ultrahigh integration density,RRAM arrays are prone to lithographic variation during the lithography process,...Reducing the process variation is a significant concern for resistive random access memory(RRAM).Due to its ultrahigh integration density,RRAM arrays are prone to lithographic variation during the lithography process,introducing electrical variation among different RRAM devices.In this work,an optical physical verification methodology for the RRAM array is developed,and the effects of different layout parameters on important electrical characteristics are systematically investigated.The results indicate that the RRAM devices can be categorized into three clusters according to their locations and lithography environments.The read resistance is more sensitive to the locations in the array(~30%)than SET/RESET voltage(<10%).The increase in the RRAM device length and the application of the optical proximity correction technique can help to reduce the variation to less than 10%,whereas it reduces RRAM read resistance by 4×,resulting in a higher power and area consumption.As such,we provide design guidelines to minimize the electrical variation of RRAM arrays due to the lithography process.展开更多
基金supported by the National Natural Science Foundation of China(62073140,62073141)the Shanghai Rising-Star Program(21QA1401800).
文摘Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.
基金supported by the National Natural Science Foundation of China under Grant 62177029the Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX21_0740),China.
文摘Visual object tracking plays a crucial role in computer vision.In recent years,researchers have proposed various methods to achieve high-performance object tracking.Among these,methods based on Transformers have become a research hotspot due to their ability to globally model and contextualize information.However,current Transformer-based object tracking methods still face challenges such as low tracking accuracy and the presence of redundant feature information.In this paper,we introduce self-calibration multi-head self-attention Transformer(SMSTracker)as a solution to these challenges.It employs a hybrid tensor decomposition self-organizing multihead self-attention transformermechanism,which not only compresses and accelerates Transformer operations but also significantly reduces redundant data,thereby enhancing the accuracy and efficiency of tracking.Additionally,we introduce a self-calibration attention fusion block to resolve common issues of attention ambiguities and inconsistencies found in traditional trackingmethods,ensuring the stability and reliability of tracking performance across various scenarios.By integrating a hybrid tensor decomposition approach with a self-organizingmulti-head self-attentive transformer mechanism,SMSTracker enhances the efficiency and accuracy of the tracking process.Experimental results show that SMSTracker achieves competitive performance in visual object tracking,promising more robust and efficient tracking systems,demonstrating its potential to providemore robust and efficient tracking solutions in real-world applications.
基金supported by the National Key Research and Development Plan(No.2022YFB2902701)the key Natural Science Foundation of Shenzhen(No.JCYJ20220818102209020).
文摘The satellite-terrestrial networks possess the ability to transcend geographical constraints inherent in traditional communication networks,enabling global coverage and offering users ubiquitous computing power support,which is an important development direction of future communications.In this paper,we take into account a multi-scenario network model under the coverage of low earth orbit(LEO)satellite,which can provide computing resources to users in faraway areas to improve task processing efficiency.However,LEO satellites experience limitations in computing and communication resources and the channels are time-varying and complex,which makes the extraction of state information a daunting task.Therefore,we explore the dynamic resource management issue pertaining to joint computing,communication resource allocation and power control for multi-access edge computing(MEC).In order to tackle this formidable issue,we undertake the task of transforming the issue into a Markov decision process(MDP)problem and propose the self-attention based dynamic resource management(SABDRM)algorithm,which effectively extracts state information features to enhance the training process.Simulation results show that the proposed algorithm is capable of effectively reducing the long-term average delay and energy consumption of the tasks.
基金supported by Graduate Funded Project(No.JY2022A017).
文摘The frequent missing values in radar-derived time-series tracks of aerial targets(RTT-AT)lead to significant challenges in subsequent data-driven tasks.However,the majority of imputation research focuses on random missing(RM)that differs significantly from common missing patterns of RTT-AT.The method for solving the RM may experience performance degradation or failure when applied to RTT-AT imputation.Conventional autoregressive deep learning methods are prone to error accumulation and long-term dependency loss.In this paper,a non-autoregressive imputation model that addresses the issue of missing value imputation for two common missing patterns in RTT-AT is proposed.Our model consists of two probabilistic sparse diagonal masking self-attention(PSDMSA)units and a weight fusion unit.It learns missing values by combining the representations outputted by the two units,aiming to minimize the difference between the missing values and their actual values.The PSDMSA units effectively capture temporal dependencies and attribute correlations between time steps,improving imputation quality.The weight fusion unit automatically updates the weights of the output representations from the two units to obtain a more accurate final representation.The experimental results indicate that,despite varying missing rates in the two missing patterns,our model consistently outperforms other methods in imputation performance and exhibits a low frequency of deviations in estimates for specific missing entries.Compared to the state-of-the-art autoregressive deep learning imputation model Bidirectional Recurrent Imputation for Time Series(BRITS),our proposed model reduces mean absolute error(MAE)by 31%~50%.Additionally,the model attains a training speed that is 4 to 8 times faster when compared to both BRITS and a standard Transformer model when trained on the same dataset.Finally,the findings from the ablation experiments demonstrate that the PSDMSA,the weight fusion unit,cascade network design,and imputation loss enhance imputation performance and confirm the efficacy of our design.
基金supported by the National Natural Science Foundation of China under Grant 51977004the Beijing Natural Science Foundation under Grant 4212042.
文摘To predict renewable energy sources such as solar power in microgrids more accurately,a hybrid power prediction method is presented in this paper.First,the self-attention mechanism is introduced based on a bidirectional gated recurrent neural network(BiGRU)to explore the time-series characteristics of solar power output and consider the influence of different time nodes on the prediction results.Subsequently,an improved quantum particle swarm optimization(QPSO)algorithm is proposed to optimize the hyperparameters of the combined prediction model.The final proposed LQPSO-BiGRU-self-attention hybrid model can predict solar power more effectively.In addition,considering the coordinated utilization of various energy sources such as electricity,hydrogen,and renewable energy,a multi-objective optimization model that considers both economic and environmental costs was constructed.A two-stage adaptive multi-objective quantum particle swarm optimization algorithm aided by a Lévy flight,named MO-LQPSO,was proposed for the comprehensive optimal scheduling of a multi-energy microgrid system.This algorithm effectively balances the global and local search capabilities and enhances the solution of complex nonlinear problems.The effectiveness and superiority of the proposed scheme are verified through comparative simulations.
基金supported by the National Natural Science Foundation of China (6202201562088101)+1 种基金Shanghai Municipal Science and Technology Major Project (2021SHZDZX0100)Shanghai Municip al Commission of Science and Technology Project (19511132101)。
文摘Aerial threat assessment is a crucial link in modern air combat, whose result counts a great deal for commanders to make decisions. With the consideration that the existing threat assessment methods have difficulties in dealing with high dimensional time series target data, a threat assessment method based on self-attention mechanism and gated recurrent unit(SAGRU) is proposed. Firstly, a threat feature system including air combat situations and capability features is established. Moreover, a data augmentation process based on fractional Fourier transform(FRFT) is applied to extract more valuable information from time series situation features. Furthermore, aiming to capture key characteristics of battlefield evolution, a bidirectional GRU and SA mechanisms are designed for enhanced features.Subsequently, after the concatenation of the processed air combat situation and capability features, the target threat level will be predicted by fully connected neural layers and the softmax classifier. Finally, in order to validate this model, an air combat dataset generated by a combat simulation system is introduced for model training and testing. The comparison experiments show the proposed model has structural rationality and can perform threat assessment faster and more accurately than the other existing models based on deep learning.
基金funded by the National Natural Science Foundation of China Youth Project(61603127).
文摘Traditional models for semantic segmentation in point clouds primarily focus on smaller scales.However,in real-world applications,point clouds often exhibit larger scales,leading to heavy computational and memory requirements.The key to handling large-scale point clouds lies in leveraging random sampling,which offers higher computational efficiency and lower memory consumption compared to other sampling methods.Nevertheless,the use of random sampling can potentially result in the loss of crucial points during the encoding stage.To address these issues,this paper proposes cross-fusion self-attention network(CFSA-Net),a lightweight and efficient network architecture specifically designed for directly processing large-scale point clouds.At the core of this network is the incorporation of random sampling alongside a local feature extraction module based on cross-fusion self-attention(CFSA).This module effectively integrates long-range contextual dependencies between points by employing hierarchical position encoding(HPC).Furthermore,it enhances the interaction between each point’s coordinates and feature information through cross-fusion self-attention pooling,enabling the acquisition of more comprehensive geometric information.Finally,a residual optimization(RO)structure is introduced to extend the receptive field of individual points by stacking hierarchical position encoding and cross-fusion self-attention pooling,thereby reducing the impact of information loss caused by random sampling.Experimental results on the Stanford Large-Scale 3D Indoor Spaces(S3DIS),Semantic3D,and SemanticKITTI datasets demonstrate the superiority of this algorithm over advanced approaches such as RandLA-Net and KPConv.These findings underscore the excellent performance of CFSA-Net in large-scale 3D semantic segmentation.
文摘Due to the lack of long-range association and spatial location information,fine details and accurate boundaries of complex clothing images cannot always be obtained by using the existing deep learning-based methods.This paper presents a convolutional structure with multi-scale fusion to optimize the step of clothing feature extraction and a self-attention module to capture long-range association information.The structure enables the self-attention mechanism to directly participate in the process of information exchange through the down-scaling projection operation of the multi-scale framework.In addition,the improved self-attention module introduces the extraction of 2-dimensional relative position information to make up for its lack of ability to extract spatial position features from clothing images.The experimental results based on the colorful fashion parsing dataset(CFPD)show that the proposed network structure achieves 53.68%mean intersection over union(mIoU)and has better performance on the clothing parsing task.
基金supported by the National Key Research and Development Program of China(2018YFC0830700)。
文摘This paper presents a method for aspect based sentiment classification tasks, named convolutional multi-head self-attention memory network(CMA-Mem Net). This is an improved model based on memory networks, and makes it possible to extract more rich and complex semantic information from sequences and aspects. In order to fix the memory network’s inability to capture context-related information on a word-level,we propose utilizing convolution to capture n-gram grammatical information. We use multi-head self-attention to make up for the problem where the memory network ignores the semantic information of the sequence itself. Meanwhile, unlike most recurrent neural network(RNN) long short term memory(LSTM), gated recurrent unit(GRU) models, we retain the parallelism of the network. We experiment on the open datasets Sem Eval-2014 Task 4 and Sem Eval-2016 Task 6. Compared with some popular baseline methods, our model performs excellently.
基金financially supported by the National Natural Science Foundation of China(No.51974028)。
文摘The martensitic transformation temperature is the basis for the application of shape memory alloys(SMAs),and the ability to quickly and accurately predict the transformation temperature of SMAs has very important practical significance.In this work,machine learning(ML)methods were utilized to accelerate the search for shape memory alloys with targeted properties(phase transition temperature).A group of component data was selected to design shape memory alloys using reverse design method from numerous unexplored data.Component modeling and feature modeling were used to predict the phase transition temperature of the shape memory alloys.The experimental results of the shape memory alloys were obtained to verify the effectiveness of the support vector regression(SVR)model.The results show that the machine learning model can obtain target materials more efficiently and pertinently,and realize the accurate and rapid design of shape memory alloys with specific target phase transition temperature.On this basis,the relationship between phase transition temperature and material descriptors is analyzed,and it is proved that the key factors affecting the phase transition temperature of shape memory alloys are based on the strength of the bond energy between atoms.This work provides new ideas for the controllable design and performance optimization of Cu-based shape memory alloys.
基金financially supported by the National Natural Science Foundation of China,No.81303115,81774042 (both to XC)the Pearl River S&T Nova Program of Guangzhou,No.201806010025 (to XC)+3 种基金the Specialty Program of Guangdong Province Hospital of Chinese Medicine of China,No.YN2018ZD07 (to XC)the Natural Science Foundatior of Guangdong Province of China,No.2023A1515012174 (to JL)the Science and Technology Program of Guangzhou of China,No.20210201 0268 (to XC),20210201 0339 (to JS)Guangdong Provincial Key Laboratory of Research on Emergency in TCM,Nos.2018-75,2019-140 (to JS)
文摘Vascular etiology is the second most prevalent cause of cognitive impairment globally.Endothelin-1,which is produced and secreted by endothelial cells and astrocytes,is implicated in the pathogenesis of stroke.However,the way in which changes in astrocytic endothelin-1 lead to poststroke cognitive deficits following transient middle cerebral artery occlusion is not well understood.Here,using mice in which astrocytic endothelin-1 was overexpressed,we found that the selective overexpression of endothelin-1 by astrocytic cells led to ischemic stroke-related dementia(1 hour of ischemia;7 days,28 days,or 3 months of reperfusion).We also revealed that astrocytic endothelin-1 overexpression contributed to the role of neural stem cell proliferation but impaired neurogenesis in the dentate gyrus of the hippocampus after middle cerebral artery occlusion.Comprehensive proteome profiles and western blot analysis confirmed that levels of glial fibrillary acidic protein and peroxiredoxin 6,which were differentially expressed in the brain,were significantly increased in mice with astrocytic endothelin-1 overexpression in comparison with wild-type mice 28 days after ischemic stroke.Moreover,the levels of the enriched differentially expressed proteins were closely related to lipid metabolism,as indicated by Kyoto Encyclopedia of Genes and Genomes pathway analysis.Liquid chromatography-mass spectrometry nontargeted metabolite profiling of brain tissues showed that astrocytic endothelin-1 overexpression altered lipid metabolism products such as glycerol phosphatidylcholine,sphingomyelin,and phosphatidic acid.Overall,this study demonstrates that astrocytic endothelin-1 overexpression can impair hippocampal neurogenesis and that it is correlated with lipid metabolism in poststroke cognitive dysfunction.
基金supported by grants from the Ministerio de Economia y Competitividad(BFU2013-43458-R)Junta de Andalucia(P12-CTS-1694 and Proyexcel-00422)to ZUK。
文摘Memory deficit,which is often associated with aging and many psychiatric,neurological,and neurodegenerative diseases,has been a challenging issue for treatment.Up till now,all potential drug candidates have failed to produce satisfa ctory effects.Therefore,in the search for a solution,we found that a treatment with the gene corresponding to the RGS14414protein in visual area V2,a brain area connected with brain circuits of the ventral stream and the medial temporal lobe,which is crucial for object recognition memory(ORM),can induce enhancement of ORM.In this study,we demonstrated that the same treatment with RGS14414in visual area V2,which is relatively unaffected in neurodegenerative diseases such as Alzheimer s disease,produced longlasting enhancement of ORM in young animals and prevent ORM deficits in rodent models of aging and Alzheimer’s disease.Furthermore,we found that the prevention of memory deficits was mediated through the upregulation of neuronal arbo rization and spine density,as well as an increase in brain-derived neurotrophic factor(BDNF).A knockdown of BDNF gene in RGS14414-treated aging rats and Alzheimer s disease model mice caused complete loss in the upregulation of neuronal structural plasticity and in the prevention of ORM deficits.These findings suggest that BDNF-mediated neuronal structural plasticity in area V2 is crucial in the prevention of memory deficits in RGS14414-treated rodent models of aging and Alzheimer’s disease.Therefore,our findings of RGS14414gene-mediated activation of neuronal circuits in visual area V2 have therapeutic relevance in the treatment of memory deficits.
文摘Mainstream media play a crucial role in constructing the cultural memory of a city.This study used 319 short videos released by“Hi Chengdu,”a new media product of Chengdu Radio and Television,as samples.Based on the grounded theory,a research framework encompassing“content,technology,and discourse”was established to explore the paths through which mainstream media construct the cultural memory.Regarding content,this paper emphasized temporal and spatial contexts and urban spaces,delving deep into the themes of the cultural memory and vehicles for it.In terms of technology,this paper discussed the practice of leveraging audio/visual-mode discourse to stitch together the impressions of a city and evoke emotional resonance to create a“flow”of memory.As for discourse,this paper looked at the performance of a communication ritual to frame concepts and shape urban identity.It is essential to break free from conventional thinking and leverage local culture as the primary driving force to further boost a city’s productivity,in order to excel in cultural communication.
文摘Background and Purpose: Opioids, used for centuries to alleviate pain, have become a double-edged sword. While effective, they come with a host of adverse effects, including memory and cognition impairment. This review delves into the impact of opioid drugs on cognitive functions, explores underlying mechanisms, and investigates their prevalence in both medical care and illicit drug use. The ultimate goal is to find ways to mitigate their potential harm and address the ongoing opioid crisis. Methods: We sourced data from PubMed and Google Scholar, employing search combinations like “opioids,” “memory,” “cognition,” “amnesia,” “cognitive function,” “executive function,” and “inhibition.” Our focus was on English-language articles spanning from the inception of these databases up to the present. Results: The literature consistently reveals that opioid use, particularly at high doses, adversely affects memory and other cognitive functions. Longer deliberation times, impaired decision-making, impulsivity, and behavioral disorders are common consequences. Chronic high-dose opioid use is associated with conditions such as amnesiac syndrome (OAS), post-operative cognitive dysfunction (POCD), neonatal abstinence syndrome (NAS), depression, anxiety, sedation, and addiction. Alarming trends show increased opioid use over recent decades, amplifying the risk of these outcomes. Conclusion: Opioids cast a shadow over memory and cognitive function. These effects range from amnesiac effects, lessened cognitive function, depression, and more. Contributing factors include over-prescription, misuse, misinformation, and prohibition policies. Focusing on correct informational campaigns, removing punitive policies, and focusing on harm reduction strategies have been shown to lessen the abuse and use of opioids and thus helping to mitigate the adverse effects of these drugs. Further research into the impacts of opioids on cognitive abilities is also needed as they are well demonstrated in the literature, but the mechanism is not often completely understood.
文摘The adoption of Docker containers has revolutionized software deployment by providing a lightweight and efficient way to isolate applications in data centers. However, securing these containers, especially when handling sensitive data, poses significant challenges. Traditional Linux Security Modules (LSMs) such as SELinux and AppArmor have limitations in providing fine-grained access control to files within containers. This paper presents a novel approach using eBPF (extended Berkeley Packet Filter) to implement a LSM that focuses on file-oriented access control within Docker containers. The module allows the specification of policies that determine which programs can access sensitive files, providing enhanced security without relying solely on the host operating system’s major LSM.
基金Supported by the National Key R&D Program of China(No.2022ZD0119001)the National Natural Science Foundation of China(No.61834005,61802304)+1 种基金the Education Department of Shaanxi Province(No.22JY060)the Shaanxi Provincial Key Research and Devel-opment Plan(No.2024GX-YBXM-100)。
文摘With the rapid development of deep learning algorithms,the computational complexity and functional diversity are increasing rapidly.However,the gap between high computational density and insufficient memory bandwidth under the traditional von Neumann architecture is getting worse.Analyzing the algorithmic characteristics of convolutional neural network(CNN),it is found that the access characteristics of convolution(CONV)and fully connected(FC)operations are very different.Based on this feature,a dual-mode reronfigurable distributed memory architecture for CNN accelerator is designed.It can be configured in Bank mode or first input first output(FIFO)mode to accommodate the access needs of different operations.At the same time,a programmable memory control unit is designed,which can effectively control the dual-mode configurable distributed memory architecture by using customized special accessing instructions and reduce the data accessing delay.The proposed architecture is verified and tested by parallel implementation of some CNN algorithms.The experimental results show that the peak bandwidth can reach 13.44 GB·s^(-1)at an operating frequency of 120 MHz.This work can achieve 1.40,1.12,2.80 and 4.70 times the peak bandwidth compared with the existing work.
基金This work was supported by the National Natural Science Foundation of China(Nos.62034006,92264201,and 91964105)the Natural Science Foundation of Shandong Province(Nos.ZR2020JQ28 and ZR2020KF016)the Program of Qilu Young Scholars of Shandong University.
文摘With the rapid development of machine learning,the demand for high-efficient computing becomes more and more urgent.To break the bottleneck of the traditional Von Neumann architecture,computing-in-memory(CIM)has attracted increasing attention in recent years.In this work,to provide a feasible CIM solution for the large-scale neural networks(NN)requiring continuous weight updating in online training,a flash-based computing-in-memory with high endurance(10^(9) cycles)and ultrafast programming speed is investigated.On the one hand,the proposed programming scheme of channel hot electron injection(CHEI)and hot hole injection(HHI)demonstrate high linearity,symmetric potentiation,and a depression process,which help to improve the training speed and accuracy.On the other hand,the low-damage programming scheme and memory window(MW)optimizations can suppress cell degradation effectively with improved computing accuracy.Even after 109 cycles,the leakage current(I_(off))of cells remains sub-10pA,ensuring the large-scale computing ability of memory.Further characterizations are done on read disturb to demonstrate its robust reliabilities.By processing CIFAR-10 tasks,it is evident that~90%accuracy can be achieved after 109 cycles in both ResNet50 and VGG16 NN.Our results suggest that flash-based CIM has great potential to overcome the limitations of traditional Von Neumann architectures and enable high-performance NN online training,which pave the way for further development of artificial intelligence(AI)accelerators.
文摘Bisphenol A (BPA), a toxicant which can leach into food from plastic containers, is reported to induce neurotoxicity among others via oxidative mechanisms. However, antioxidant compounds have been suggested to mitigate BPA-induced toxicities. Garcinia kola (GK) and its bioactive compound, kolaviron, are well-established natural antioxidants, which can exert protective effects against BPA-induced toxicities. This study was designed to investigate the likely mitigating effect of GK and kolaviron on BPA-induced memory impairment and hippocampal neuroinflammation in male Wistar rats. Thirty-five rats were equally grouped and treated as follows: I and II received distilled water and corn oil, respectively at 0.2 mL, while III - VII received BPA (50 mg/kg), BPA + GK (200 mg/kg), BPA + kolaviron (200 mg/kg), GK and kolaviron, respectively for 28 days p.o. Thereafter, behavioral studies were done using the Novel Object Recognition and Y maze tests. Subsequently under anaesthesia, the hippocampus in each animal was dissected out, homogenized and analysed for malondialdehyde, superoxide dismutase, catalase, reduced glutathione, glutathione transferase, nitrites, interleukin-6, tumour necrosis factor-α, acetylcholinesterase, glutamate acid decarboxylase, and arginase activity. Data were analyzed by ANOVA and Tukey Post-hoc test at p p Garcinia kola and Kolaviron mitigate bisphenol A-induced memory impairment and neuroinflammation via antioxidant potentiation and neurotransmitter balance.
基金supported in part by the Open Fund of State Key Laboratory of Integrated Chips and Systems,Fudan Universityin part by the National Science Foundation of China under Grant No.62304133 and No.62350610271.
文摘Reducing the process variation is a significant concern for resistive random access memory(RRAM).Due to its ultrahigh integration density,RRAM arrays are prone to lithographic variation during the lithography process,introducing electrical variation among different RRAM devices.In this work,an optical physical verification methodology for the RRAM array is developed,and the effects of different layout parameters on important electrical characteristics are systematically investigated.The results indicate that the RRAM devices can be categorized into three clusters according to their locations and lithography environments.The read resistance is more sensitive to the locations in the array(~30%)than SET/RESET voltage(<10%).The increase in the RRAM device length and the application of the optical proximity correction technique can help to reduce the variation to less than 10%,whereas it reduces RRAM read resistance by 4×,resulting in a higher power and area consumption.As such,we provide design guidelines to minimize the electrical variation of RRAM arrays due to the lithography process.