Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and so...Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and solving the data isolation problem faced by centralized GNNs in data-sensitive scenarios. Despite the plethora of prior work on inference attacks against centralized GNNs, the vulnerability of FedGNNs to inference attacks has not yet been widely explored. It is still unclear whether the privacy leakage risks of centralized GNNs will also be introduced in FedGNNs. To bridge this gap, we present PIAFGNN, the first property inference attack (PIA) against FedGNNs. Compared with prior works on centralized GNNs, in PIAFGNN, the attacker can only obtain the global embedding gradient distributed by the central server. The attacker converts the task of stealing the target user’s local embeddings into a regression problem, using a regression model to generate the target graph node embeddings. By training shadow models and property classifiers, the attacker can infer the basic property information within the target graph that is of interest. Experiments on three benchmark graph datasets demonstrate that PIAFGNN achieves attack accuracy of over 70% in most cases, even approaching the attack accuracy of inference attacks against centralized GNNs in some instances, which is much higher than the attack accuracy of the random guessing method. Furthermore, we observe that common defense mechanisms cannot mitigate our attack without affecting the model’s performance on mainly classification tasks.展开更多
Developing efficient neural network(NN)computing systems is crucial in the era of artificial intelligence(AI).Traditional von Neumann architectures have both the issues of"memory wall"and"power wall&quo...Developing efficient neural network(NN)computing systems is crucial in the era of artificial intelligence(AI).Traditional von Neumann architectures have both the issues of"memory wall"and"power wall",limiting the data transfer between memory and processing units[1,2].Compute-in-memory(CIM)technologies,particularly analogue CIM with memristor crossbars,are promising because of their high energy efficiency,computational parallelism,and integration density for NN computations[3].In practical applications,analogue CIM excels in tasks like speech recognition and image classification,revealing its unique advantages.For instance,it efficiently processes vast amounts of audio data in speech recognition,achieving high accuracy with minimal power consumption.In image classification,the high parallelism of analogue CIM significantly speeds up feature extraction and reduces processing time.With the boosting development of AI applications,the demands for computational accuracy and task complexity are rising continually.However,analogue CIM systems are limited in handling complex regression tasks with needs of precise floating-point(FP)calculations.They are primarily suited for the classification tasks with low data precision and a limited dynamic range[4].展开更多
Network attack graphs are originally used to evaluate what the worst security state is when a concerned net-work is under attack. Combined with intrusion evidence such like IDS alerts, attack graphs can be further use...Network attack graphs are originally used to evaluate what the worst security state is when a concerned net-work is under attack. Combined with intrusion evidence such like IDS alerts, attack graphs can be further used to perform security state posterior inference (i.e. inference based on observation experience). In this area, Bayesian network is an ideal mathematic tool, however it can not be directly applied for the following three reasons: 1) in a network attack graph, there may exist directed cycles which are never permitted in a Bayesian network, 2) there may exist temporal partial ordering relations among intrusion evidence that can-not be easily modeled in a Bayesian network, and 3) just one Bayesian network cannot be used to infer both the current and the future security state of a network. In this work, we improve an approximate Bayesian posterior inference algorithm–the likelihood-weighting algorithm to resolve the above obstacles. We give out all the pseudocodes of the algorithm and use several examples to demonstrate its benefit. Based on this, we further propose a network security assessment and enhancement method along with a small network scenario to exemplify its usage.展开更多
Flatness pattern recognition is the key of the flatness control. The accuracy of the present flatness pattern recognition is limited and the shape defects cannot be reflected intuitively. In order to improve it, a nov...Flatness pattern recognition is the key of the flatness control. The accuracy of the present flatness pattern recognition is limited and the shape defects cannot be reflected intuitively. In order to improve it, a novel method via T-S cloud inference network optimized by genetic algorithm(GA) is proposed. T-S cloud inference network is constructed with T-S fuzzy neural network and the cloud model. So, the rapid of fuzzy logic and the uncertainty of cloud model for processing data are both taken into account. What's more, GA possesses good parallel design structure and global optimization characteristics. Compared with the simulation recognition results of traditional BP Algorithm, GA is more accurate and effective. Moreover, virtual reality technology is introduced into the field of shape control by Lab VIEW, MATLAB mixed programming. And virtual flatness pattern recognition interface is designed.Therefore, the data of engineering analysis and the actual model are combined with each other, and the shape defects could be seen more lively and intuitively.展开更多
There are two distinct types of domains,design-and cross-classes domains,with the former extensively studied under the topic of small-area estimation.In natural resource inventory,however,most classes listed in the co...There are two distinct types of domains,design-and cross-classes domains,with the former extensively studied under the topic of small-area estimation.In natural resource inventory,however,most classes listed in the condition tables of national inventory programs are characterized as cross-classes domains,such as vegetation type,productivity class,and age class.To date,challenges remain active for inventorying cross-classes domains because these domains are usually of unknown sampling frame and spatial distribution with the result that inference relies on population-level as opposed to domain-level sampling.Multiple challenges are noteworthy:(1)efficient sampling strategies are difficult to develop because of little priori information about the target domain;(2)domain inference relies on a sample designed for the population,so within-domain sample sizes could be too small to support a precise estimation;and(3)increasing sample size for the population does not ensure an increase to the domain,so actual sample size for a target domain remains highly uncertain,particularly for small domains.In this paper,we introduce a design-based generalized systematic adaptive cluster sampling(GSACS)for inventorying cross-classes domains.Design-unbiased Hansen-Hurwitz and Horvitz-Thompson estimators are derived for domain totals and compared within GSACS and with systematic sampling(SYS).Comprehensive Monte Carlo simulations show that(1)GSACS Hansen-Hurwitz and Horvitz-Thompson estimators are unbiased and equally efficient,whereas thelatter outperforms the former for supporting a sample of size one;(2)SYS is a special case of GSACS while the latter outperforms the former in terms of increased efficiency and reduced intensity;(3)GSACS Horvitz-Thompson variance estimator is design-unbiased for a single SYS sample;and(4)rules-ofthumb summarized with respect to sampling design and spatial effect improve precision.Because inventorying a mini domain is analogous to inventorying a rare variable,alternative network sampling procedures are also readily available for inventorying cross-classes domains.展开更多
Prediction intervals(PIs)for industrial time series can provide useful guidance for workers.Given that the failure of industrial sensors may cause the missing point in inputs,the existing kernel dynamic Bayesian netwo...Prediction intervals(PIs)for industrial time series can provide useful guidance for workers.Given that the failure of industrial sensors may cause the missing point in inputs,the existing kernel dynamic Bayesian networks(KDBN),serving as an effective method for PIs construction,suffer from high computational load using the stochastic algorithm for inference.This study proposes a variational inference method for the KDBN for the purpose of fast inference,which avoids the timeconsuming stochastic sampling.The proposed algorithm contains two stages.The first stage involves the inference of the missing inputs by using a local linearization based variational inference,and based on the computed posterior distributions over the missing inputs the second stage sees a Gaussian approximation for probability over the nodes in future time slices.To verify the effectiveness of the proposed method,a synthetic dataset and a practical dataset of generation flow of blast furnace gas(BFG)are employed with different ratios of missing inputs.The experimental results indicate that the proposed method can provide reliable PIs for the generation flow of BFG and it exhibits shorter computing time than the stochastic based one.展开更多
An efficient and accurate prediction of a precise tidal level in estuaries and coastal areas is indispensable for the management and decision-making of human activity in the field wok of marine engineering. The variat...An efficient and accurate prediction of a precise tidal level in estuaries and coastal areas is indispensable for the management and decision-making of human activity in the field wok of marine engineering. The variation of the tidal level is a time-varying process. The time-varying factors including interference from the external environment that cause the change of tides are fairly complicated. Furthermore, tidal variations are affected not only by periodic movement of celestial bodies but also by time-varying interference from the external environment. Consequently, for the efficient and precise tidal level prediction, a neuro-fuzzy hybrid technology based on the combination of harmonic analysis and adaptive network-based fuzzy inference system（ANFIS）model is utilized to construct a precise tidal level prediction system, which takes both advantages of the harmonic analysis method and the ANFIS network. The proposed prediction model is composed of two modules： the astronomical tide module caused by celestial bodies’ movement and the non-astronomical tide module caused by various meteorological and other environmental factors. To generate a fuzzy inference system（FIS） structure,three approaches which include grid partition（GP）, fuzzy c-means（FCM） and sub-clustering（SC） are used in the ANFIS network constructing process. Furthermore, to obtain the optimal ANFIS based prediction model, large numbers of simulation experiments are implemented for each FIS generating approach. In this tidal prediction study, the optimal ANFIS model is used to predict the non-astronomical tide module, while the conventional harmonic analysis model is used to predict the astronomical tide module. The final prediction result is performed by combining the estimation outputs of the harmonious analysis model and the optimal ANFIS model. To demonstrate the applicability and capability of the proposed novel prediction model, measured tidal level samples of Fort Pulaski tidal station are selected as the testing database. Simulation and experimental results confirm that the proposed prediction approach can achieve precise predictions for the tidal level with high accuracy, satisfactory convergence and stability.展开更多
The goal of point cloud completion is to reconstruct raw scanned point clouds acquired from incomplete observations due to occlusion and restricted viewpoints.Numerous methods use a partial-to-complete framework,direc...The goal of point cloud completion is to reconstruct raw scanned point clouds acquired from incomplete observations due to occlusion and restricted viewpoints.Numerous methods use a partial-to-complete framework,directly predicting missing components via global characteristics extracted from incomplete inputs.However,this makes detail re-covery challenging,as global characteristics fail to provide complete missing component specifics.A new point cloud completion method named Point-PC is proposed.A memory network and a causal inference model are separately designed to introduce shape priors and select absent shape information as supplementary geometric factors for aiding completion.Concretely,a memory mechanism is proposed to store complete shape features and their associated shapes in a key-value format.The authors design a pre-training strategy that uses contrastive learning to map incomplete shape features into the complete shape feature domain,enabling retrieval of analogous shapes from incomplete inputs.In addition,the authors employ backdoor adjustment to eliminate confounders,which are shape prior components sharing identical semantic structures with incomplete inputs.Experiments conducted on three datasets show that our method achieves superior performance compared to state-of-the-art approaches.The code for Point-PC can be accessed by https://github.com/bizbard/Point-PC.git.展开更多
Network topology inference is one of the important applications of network tomography.Traditional network topology inference may impact network normal operation due to its generation of huge data traffic.A unicast net...Network topology inference is one of the important applications of network tomography.Traditional network topology inference may impact network normal operation due to its generation of huge data traffic.A unicast network topology inference is proposed to use time to live(TTL)for layering and classify nodes layer by layer based on the similarity of node pairs.Finally,the method infers logical network topology effectively with self-adaptive combination of previous results.Simulation results show that the proposed method holds a high accuracy of topology inference while decreasing network measuring flow,thus improves measurement efficiency.展开更多
Complex breast cancer network constructed from experimentally verified seventy genes, by coordinating standard seven human protein and genome databases, follows hierarchical scale free features. Centrality based metho...Complex breast cancer network constructed from experimentally verified seventy genes, by coordinating standard seven human protein and genome databases, follows hierarchical scale free features. Centrality based method of identification of inferred genes is implemented to this network and has predicted forty nine breast cancer genes, and nineteen non-breast cancer genes. As predicting good candidate genes before experimental analysis will save time and effort both. Fourteen genes out of nineteen are found to involve in various types of cancer and diseases, and five genes are engaged in non-cancer diseases. Some of the inferred genes need proper experimental investigation to understand fundamental roles of these genes in regulating breast cancer network.展开更多
Fire detection has held stringent importance in computer vision for over half a century.The development of early fire detection strategies is pivotal to the realization of safe and smart cities,inhabitable in the futu...Fire detection has held stringent importance in computer vision for over half a century.The development of early fire detection strategies is pivotal to the realization of safe and smart cities,inhabitable in the future.However,the development of optimal fire and smoke detection models is hindered by limitations like publicly available datasets,lack of diversity,and class imbalance.In this work,we explore the possible ways forward to overcome these challenges posed by available datasets.We study the impact of a class-balanced dataset to improve the fire detection capability of state-of-the-art(SOTA)vision-based models and propose the use of generative models for data augmentation,as a future work direction.First,a comparative analysis of two prominent object detection architectures,You Only Look Once version 7(YOLOv7)and YOLOv8 has been carried out using a balanced dataset,where both models have been evaluated across various evaluation metrics including precision,recall,and mean Average Precision(mAP).The results are compared to other recent fire detection models,highlighting the superior performance and efficiency of the proposed YOLOv8 architecture as trained on our balanced dataset.Next,a fractal dimension analysis gives a deeper insight into the repetition of patterns in fire,and the effectiveness of the results has been demonstrated by a windowing-based inference approach.The proposed Slicing-Aided Hyper Inference(SAHI)improves the fire and smoke detection capability of YOLOv8 for real-life applications with a significantly improved mAP performance over a strict confidence threshold.YOLOv8 with SAHI inference gives a mAP:50-95 improvement of more than 25%compared to the base YOLOv8 model.The study also provides insights into future work direction by exploring the potential of generative models like deep convolutional generative adversarial network(DCGAN)and diffusion models like stable diffusion,for data augmentation.展开更多
In this paper, a modeling algorithm developed by transferring the adaptive fuzzy inference neural network into an on-line real time algorithm, combining the algorithm with conventional system identification method and...In this paper, a modeling algorithm developed by transferring the adaptive fuzzy inference neural network into an on-line real time algorithm, combining the algorithm with conventional system identification method and applying them to separate identification of nonlinear multi-variable systems is introduced and discussed.展开更多
Increases in the treatment of water to meet the growing water demand ultimately result in unmanageable quantities of residuals,the handling,and disposal of which is a major environmental issue.Consequently,research in...Increases in the treatment of water to meet the growing water demand ultimately result in unmanageable quantities of residuals,the handling,and disposal of which is a major environmental issue.Consequently,research into beneficial reuse of water treatment residuals continues unabated.This study investigated the applicability of lime-iron sludge for phosphate adsorption by fixed-bed column adsorption.Laboratory-scale experiments were conducted at varying flow rates and bed depths.Fundamental and empirical models(Thomas,Yan,Bohart-Adams,Yoon-Nelson,and Wolboroska)as well as artificial intelligence techniques(Artificial neural network(ANN)and Adaptive neuro-fuzzy inference system(ANFIS))were used to simulate experimental breakthrough curves and predict column dynamics.Increase in flow rate resulted in reduced adsorption capacity.However,adsorption capacity was not affected by bed depth.ANN was superior in predicting breakthrough curves and predicted breakthrough times with high accuracy(R^2>0.9962).Na OH(0.5 mol·L^-1)was successfully used to regenerate the adsorption bed.After nine cyclic adsorption/desorption runs,only a marginal decrease in adsorption and desorption efficiencies of 10%and 8%respectively was observed.The same regenerate Na OH solution was reused for all desorption cycles.After nine cycles the eluent desorbed a total of 1550 mg phosphate exhibiting potential for further reuse.展开更多
The fully connected Hopfield network is inferred based on observed magnetizations and pairwise correlations.We present the system in the glassy phase with low temperature and high memory load.We find that the inferenc...The fully connected Hopfield network is inferred based on observed magnetizations and pairwise correlations.We present the system in the glassy phase with low temperature and high memory load.We find that the inference error is very sensitive to the form of state sampling.When a single state is sampled to compute magnetizations and correlations,the inference error is almost indistinguishable irrespective of the sampled state.However,the error can be greatly reduced if the data is collected with state transitions.Our result holds for different disorder samples and accounts for the previously observed large fluctuations of inference error at low temperatures.展开更多
The Stokes production coefficient(E_(6))constitutes a critical parameter within the Mellor-Yamada type(MY-type)Langmuir turbulence(LT)parameterization schemes,significantly affecting the simulation of turbulent kineti...The Stokes production coefficient(E_(6))constitutes a critical parameter within the Mellor-Yamada type(MY-type)Langmuir turbulence(LT)parameterization schemes,significantly affecting the simulation of turbulent kinetic energy,turbulent length scale,and vertical diffusivity coefficient for turbulent kinetic energy in the upper ocean.However,the accurate determination of its value remains a pressing scientific challenge.This study adopted an innovative approach by leveraging deep learning technology to address this challenge of inferring the E_(6).Through the integration of the information of the turbulent length scale equation into a physical-informed neural network(PINN),we achieved an accurate and physically meaningful inference of E_(6).Multiple cases were examined to assess the feasibility of PINN in this task,revealing that under optimal settings,the average mean squared error of the E_(6) inference was only 0.01,attesting to the effectiveness of PINN.The optimal hyperparameter combination was identified using the Tanh activation function,along with a spatiotemporal sampling interval of 1 s and 0.1 m.This resulted in a substantial reduction in the average bias of the E_(6) inference,ranging from O(10^(1))to O(10^(2))times compared with other combinations.This study underscores the potential application of PINN in intricate marine environments,offering a novel and efficient method for optimizing MY-type LT parameterization schemes.展开更多
Deep learning has now been widely used in intelligent apps of mobile devices.In pursuit of ultra-low power and latency,integrating neural network accelerators(NNA)to mobile phones has become a trend.However,convention...Deep learning has now been widely used in intelligent apps of mobile devices.In pursuit of ultra-low power and latency,integrating neural network accelerators(NNA)to mobile phones has become a trend.However,conventional deep learning programming frameworks are not well-developed to support such devices,leading to low computing efficiency and high memory-occupation.To address this problem,a 2-stage pipeline is proposed for optimizing deep learning model inference on mobile devices with NNAs in terms of both speed and memory-footprint.The 1 st stage reduces computation workload via graph optimization,including splitting and merging nodes.The 2 nd stage goes further by optimizing at compilation level,including kernel fusion and in-advance compilation.The proposed optimizations on a commercial mobile phone with an NNA is evaluated.The experimental results show that the proposed approaches achieve 2.8×to 26×speed up,and reduce the memory-footprint by up to 75%.展开更多
Discovering genetic basis of diseases is an important goal and a challenging problem in bioinformatics research. Inspired by network-based global inference approach, Semi-global inference method is proposed to capture...Discovering genetic basis of diseases is an important goal and a challenging problem in bioinformatics research. Inspired by network-based global inference approach, Semi-global inference method is proposed to capture the complex associations between phenotypes and genes. The proposed method integrates phenotype similarities and protein-protein interactions, and it establishes the profile vectors of phenotypes and proteins. Then the relevance between each candidate gene and the target phenotype is evaluated. Candidate genes are then ranked according to relevance mark and genes that are potentially associated with target disease are identified based on this ranking. The model selects nodes in integrated phenotype-protein network for inference, by exploiting Phenotype Similarity Threshold (PST), which throws lights on selection of similar phenotypes for gene prediction problem. Different vector relevance metrics for computing the relevance marks of candidate genes are discussed. The performance of the model is evaluated on Online Mendelian Inheritance in Man (OMIM) data sets and experimental evaluation shows high performance of proposed Semi-global method outperforms existing global inference methods.展开更多
This paper applies both the neural network and adaptive neuro-fuzzy inference system for forecasting short-term chaotic traffic volumes and compares the results. The architecture of the neural network consists of the ...This paper applies both the neural network and adaptive neuro-fuzzy inference system for forecasting short-term chaotic traffic volumes and compares the results. The architecture of the neural network consists of the input vector, one hidden layer and output layer. Bayesian regularization is employed to obtain the effective number of neurons in the hidden layer. The input variables and target of the adaptive neuro-fuzzy inference system are the same as those of the neural network. The data clustering technique is used to group data points so that the membership functions will be more tailored to the input data, which in turn greatly reduces the number of fuzzy rules. Numerical results indicate that these two models have almost the same accuracy, while the adaptive neuro-fuzzy inference system takes more time to train. It is also shown that although the effective number of neurons in the hidden layer is less than half the number of the input elements, the neural network can have satisfactory performance.展开更多
At present,knowledge embedding methods are widely used in the field of knowledge graph(KG)reasoning,and have been successfully applied to those with large entities and relationships.However,in research and production ...At present,knowledge embedding methods are widely used in the field of knowledge graph(KG)reasoning,and have been successfully applied to those with large entities and relationships.However,in research and production environments,there are a large number of KGs with a small number of entities and relations,which are called sparse KGs.Limited by the performance of knowledge extraction methods or some other reasons(some common-sense information does not appear in the natural corpus),the relation between entities is often incomplete.To solve this problem,a method of the graph neural network and information enhancement is proposed.The improved method increases the mean reciprocal rank(MRR)and Hit@3 by 1.6%and 1.7%,respectively,when the sparsity of the FB15K-237 dataset is 10%.When the sparsity is 50%,the evaluation indexes MRR and Hit@10 are increased by 0.8%and 1.8%,respectively.展开更多
In the field of engineering,LabVIEW and MATLAB are the languages most commonly used by program developers.Howev-er,they have their respective advantages and disadvantages.The combination of the two will undoubtedly fa...In the field of engineering,LabVIEW and MATLAB are the languages most commonly used by program developers.Howev-er,they have their respective advantages and disadvantages.The combination of the two will undoubtedly facilitate program develop-ment.Design of inference engine is the key point and difficulty in the design of fault diagnosis expert system.This paper combinesLabVIEW and MATLAB to design the inference engine of fault diagnosis expert system based on the advantages of the graphical pro-gramming environment and signal analysis toolkit of LabVIEW without the defect of neural network toolkit.In addition,it introducesthe implementation methods and precautions for combination of LabVIEW and BP network so as to make LabVIWE amd BP benefitfrom each other,which is of great pragmatic value.展开更多
基金supported by the National Natural Science Foundation of China(Nos.62176122 and 62061146002).
文摘Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and solving the data isolation problem faced by centralized GNNs in data-sensitive scenarios. Despite the plethora of prior work on inference attacks against centralized GNNs, the vulnerability of FedGNNs to inference attacks has not yet been widely explored. It is still unclear whether the privacy leakage risks of centralized GNNs will also be introduced in FedGNNs. To bridge this gap, we present PIAFGNN, the first property inference attack (PIA) against FedGNNs. Compared with prior works on centralized GNNs, in PIAFGNN, the attacker can only obtain the global embedding gradient distributed by the central server. The attacker converts the task of stealing the target user’s local embeddings into a regression problem, using a regression model to generate the target graph node embeddings. By training shadow models and property classifiers, the attacker can infer the basic property information within the target graph that is of interest. Experiments on three benchmark graph datasets demonstrate that PIAFGNN achieves attack accuracy of over 70% in most cases, even approaching the attack accuracy of inference attacks against centralized GNNs in some instances, which is much higher than the attack accuracy of the random guessing method. Furthermore, we observe that common defense mechanisms cannot mitigate our attack without affecting the model’s performance on mainly classification tasks.
文摘Developing efficient neural network(NN)computing systems is crucial in the era of artificial intelligence(AI).Traditional von Neumann architectures have both the issues of"memory wall"and"power wall",limiting the data transfer between memory and processing units[1,2].Compute-in-memory(CIM)technologies,particularly analogue CIM with memristor crossbars,are promising because of their high energy efficiency,computational parallelism,and integration density for NN computations[3].In practical applications,analogue CIM excels in tasks like speech recognition and image classification,revealing its unique advantages.For instance,it efficiently processes vast amounts of audio data in speech recognition,achieving high accuracy with minimal power consumption.In image classification,the high parallelism of analogue CIM significantly speeds up feature extraction and reduces processing time.With the boosting development of AI applications,the demands for computational accuracy and task complexity are rising continually.However,analogue CIM systems are limited in handling complex regression tasks with needs of precise floating-point(FP)calculations.They are primarily suited for the classification tasks with low data precision and a limited dynamic range[4].
文摘Network attack graphs are originally used to evaluate what the worst security state is when a concerned net-work is under attack. Combined with intrusion evidence such like IDS alerts, attack graphs can be further used to perform security state posterior inference (i.e. inference based on observation experience). In this area, Bayesian network is an ideal mathematic tool, however it can not be directly applied for the following three reasons: 1) in a network attack graph, there may exist directed cycles which are never permitted in a Bayesian network, 2) there may exist temporal partial ordering relations among intrusion evidence that can-not be easily modeled in a Bayesian network, and 3) just one Bayesian network cannot be used to infer both the current and the future security state of a network. In this work, we improve an approximate Bayesian posterior inference algorithm–the likelihood-weighting algorithm to resolve the above obstacles. We give out all the pseudocodes of the algorithm and use several examples to demonstrate its benefit. Based on this, we further propose a network security assessment and enhancement method along with a small network scenario to exemplify its usage.
基金Project(LJRC013)supported by the University Innovation Team of Hebei Province Leading Talent Cultivation,China
文摘Flatness pattern recognition is the key of the flatness control. The accuracy of the present flatness pattern recognition is limited and the shape defects cannot be reflected intuitively. In order to improve it, a novel method via T-S cloud inference network optimized by genetic algorithm(GA) is proposed. T-S cloud inference network is constructed with T-S fuzzy neural network and the cloud model. So, the rapid of fuzzy logic and the uncertainty of cloud model for processing data are both taken into account. What's more, GA possesses good parallel design structure and global optimization characteristics. Compared with the simulation recognition results of traditional BP Algorithm, GA is more accurate and effective. Moreover, virtual reality technology is introduced into the field of shape control by Lab VIEW, MATLAB mixed programming. And virtual flatness pattern recognition interface is designed.Therefore, the data of engineering analysis and the actual model are combined with each other, and the shape defects could be seen more lively and intuitively.
基金supported by the Fundamental Research Funds for the Central Universities (Grant No. 2021ZY04)the National Natural Science Foundation of China (Grant No. 32001252)the International Center for Bamboo and Rattan (Grant No. 1632020029)
文摘There are two distinct types of domains,design-and cross-classes domains,with the former extensively studied under the topic of small-area estimation.In natural resource inventory,however,most classes listed in the condition tables of national inventory programs are characterized as cross-classes domains,such as vegetation type,productivity class,and age class.To date,challenges remain active for inventorying cross-classes domains because these domains are usually of unknown sampling frame and spatial distribution with the result that inference relies on population-level as opposed to domain-level sampling.Multiple challenges are noteworthy:(1)efficient sampling strategies are difficult to develop because of little priori information about the target domain;(2)domain inference relies on a sample designed for the population,so within-domain sample sizes could be too small to support a precise estimation;and(3)increasing sample size for the population does not ensure an increase to the domain,so actual sample size for a target domain remains highly uncertain,particularly for small domains.In this paper,we introduce a design-based generalized systematic adaptive cluster sampling(GSACS)for inventorying cross-classes domains.Design-unbiased Hansen-Hurwitz and Horvitz-Thompson estimators are derived for domain totals and compared within GSACS and with systematic sampling(SYS).Comprehensive Monte Carlo simulations show that(1)GSACS Hansen-Hurwitz and Horvitz-Thompson estimators are unbiased and equally efficient,whereas thelatter outperforms the former for supporting a sample of size one;(2)SYS is a special case of GSACS while the latter outperforms the former in terms of increased efficiency and reduced intensity;(3)GSACS Horvitz-Thompson variance estimator is design-unbiased for a single SYS sample;and(4)rules-ofthumb summarized with respect to sampling design and spatial effect improve precision.Because inventorying a mini domain is analogous to inventorying a rare variable,alternative network sampling procedures are also readily available for inventorying cross-classes domains.
基金supported by the National Key Research andDevelopment Program of China(2017YFA0700300)the National Natural Sciences Foundation of China(61533005,61703071,61603069)。
文摘Prediction intervals(PIs)for industrial time series can provide useful guidance for workers.Given that the failure of industrial sensors may cause the missing point in inputs,the existing kernel dynamic Bayesian networks(KDBN),serving as an effective method for PIs construction,suffer from high computational load using the stochastic algorithm for inference.This study proposes a variational inference method for the KDBN for the purpose of fast inference,which avoids the timeconsuming stochastic sampling.The proposed algorithm contains two stages.The first stage involves the inference of the missing inputs by using a local linearization based variational inference,and based on the computed posterior distributions over the missing inputs the second stage sees a Gaussian approximation for probability over the nodes in future time slices.To verify the effectiveness of the proposed method,a synthetic dataset and a practical dataset of generation flow of blast furnace gas(BFG)are employed with different ratios of missing inputs.The experimental results indicate that the proposed method can provide reliable PIs for the generation flow of BFG and it exhibits shorter computing time than the stochastic based one.
基金The National Natural Science Foundation of China under contract No.51379002the Fundamental Research Funds for the Central Universities of China under contract Nos 3132016322 and 3132016314the Applied Basic Research Project Fund of the Chinese Ministry of Transport of China under contract No.2014329225010
文摘An efficient and accurate prediction of a precise tidal level in estuaries and coastal areas is indispensable for the management and decision-making of human activity in the field wok of marine engineering. The variation of the tidal level is a time-varying process. The time-varying factors including interference from the external environment that cause the change of tides are fairly complicated. Furthermore, tidal variations are affected not only by periodic movement of celestial bodies but also by time-varying interference from the external environment. Consequently, for the efficient and precise tidal level prediction, a neuro-fuzzy hybrid technology based on the combination of harmonic analysis and adaptive network-based fuzzy inference system（ANFIS）model is utilized to construct a precise tidal level prediction system, which takes both advantages of the harmonic analysis method and the ANFIS network. The proposed prediction model is composed of two modules： the astronomical tide module caused by celestial bodies’ movement and the non-astronomical tide module caused by various meteorological and other environmental factors. To generate a fuzzy inference system（FIS） structure,three approaches which include grid partition（GP）, fuzzy c-means（FCM） and sub-clustering（SC） are used in the ANFIS network constructing process. Furthermore, to obtain the optimal ANFIS based prediction model, large numbers of simulation experiments are implemented for each FIS generating approach. In this tidal prediction study, the optimal ANFIS model is used to predict the non-astronomical tide module, while the conventional harmonic analysis model is used to predict the astronomical tide module. The final prediction result is performed by combining the estimation outputs of the harmonious analysis model and the optimal ANFIS model. To demonstrate the applicability and capability of the proposed novel prediction model, measured tidal level samples of Fort Pulaski tidal station are selected as the testing database. Simulation and experimental results confirm that the proposed prediction approach can achieve precise predictions for the tidal level with high accuracy, satisfactory convergence and stability.
基金National Key Research and Development Program of China,Grant/Award Number:2020YFB1711704。
文摘The goal of point cloud completion is to reconstruct raw scanned point clouds acquired from incomplete observations due to occlusion and restricted viewpoints.Numerous methods use a partial-to-complete framework,directly predicting missing components via global characteristics extracted from incomplete inputs.However,this makes detail re-covery challenging,as global characteristics fail to provide complete missing component specifics.A new point cloud completion method named Point-PC is proposed.A memory network and a causal inference model are separately designed to introduce shape priors and select absent shape information as supplementary geometric factors for aiding completion.Concretely,a memory mechanism is proposed to store complete shape features and their associated shapes in a key-value format.The authors design a pre-training strategy that uses contrastive learning to map incomplete shape features into the complete shape feature domain,enabling retrieval of analogous shapes from incomplete inputs.In addition,the authors employ backdoor adjustment to eliminate confounders,which are shape prior components sharing identical semantic structures with incomplete inputs.Experiments conducted on three datasets show that our method achieves superior performance compared to state-of-the-art approaches.The code for Point-PC can be accessed by https://github.com/bizbard/Point-PC.git.
基金supported by the National Natural Science Foundation of China (Nos.61373137,61373017, 61373139)the Major Program of Jiangsu Higher Education Institutions (No.14KJA520002)+1 种基金the Six Industries Talent Peaks Plan of Jiangsu(No.2013-DZXX-014)the Jiangsu Qinglan Project
文摘Network topology inference is one of the important applications of network tomography.Traditional network topology inference may impact network normal operation due to its generation of huge data traffic.A unicast network topology inference is proposed to use time to live(TTL)for layering and classify nodes layer by layer based on the similarity of node pairs.Finally,the method infers logical network topology effectively with self-adaptive combination of previous results.Simulation results show that the proposed method holds a high accuracy of topology inference while decreasing network measuring flow,thus improves measurement efficiency.
文摘Complex breast cancer network constructed from experimentally verified seventy genes, by coordinating standard seven human protein and genome databases, follows hierarchical scale free features. Centrality based method of identification of inferred genes is implemented to this network and has predicted forty nine breast cancer genes, and nineteen non-breast cancer genes. As predicting good candidate genes before experimental analysis will save time and effort both. Fourteen genes out of nineteen are found to involve in various types of cancer and diseases, and five genes are engaged in non-cancer diseases. Some of the inferred genes need proper experimental investigation to understand fundamental roles of these genes in regulating breast cancer network.
基金supported by a grant from R&D Program Development of Rail-Specific Digital Resource Technology Based on an AI-Enabled Rail Support Platform,grant number PK2401C1,of the Korea Railroad Research Institute.
文摘Fire detection has held stringent importance in computer vision for over half a century.The development of early fire detection strategies is pivotal to the realization of safe and smart cities,inhabitable in the future.However,the development of optimal fire and smoke detection models is hindered by limitations like publicly available datasets,lack of diversity,and class imbalance.In this work,we explore the possible ways forward to overcome these challenges posed by available datasets.We study the impact of a class-balanced dataset to improve the fire detection capability of state-of-the-art(SOTA)vision-based models and propose the use of generative models for data augmentation,as a future work direction.First,a comparative analysis of two prominent object detection architectures,You Only Look Once version 7(YOLOv7)and YOLOv8 has been carried out using a balanced dataset,where both models have been evaluated across various evaluation metrics including precision,recall,and mean Average Precision(mAP).The results are compared to other recent fire detection models,highlighting the superior performance and efficiency of the proposed YOLOv8 architecture as trained on our balanced dataset.Next,a fractal dimension analysis gives a deeper insight into the repetition of patterns in fire,and the effectiveness of the results has been demonstrated by a windowing-based inference approach.The proposed Slicing-Aided Hyper Inference(SAHI)improves the fire and smoke detection capability of YOLOv8 for real-life applications with a significantly improved mAP performance over a strict confidence threshold.YOLOv8 with SAHI inference gives a mAP:50-95 improvement of more than 25%compared to the base YOLOv8 model.The study also provides insights into future work direction by exploring the potential of generative models like deep convolutional generative adversarial network(DCGAN)and diffusion models like stable diffusion,for data augmentation.
文摘In this paper, a modeling algorithm developed by transferring the adaptive fuzzy inference neural network into an on-line real time algorithm, combining the algorithm with conventional system identification method and applying them to separate identification of nonlinear multi-variable systems is introduced and discussed.
文摘Increases in the treatment of water to meet the growing water demand ultimately result in unmanageable quantities of residuals,the handling,and disposal of which is a major environmental issue.Consequently,research into beneficial reuse of water treatment residuals continues unabated.This study investigated the applicability of lime-iron sludge for phosphate adsorption by fixed-bed column adsorption.Laboratory-scale experiments were conducted at varying flow rates and bed depths.Fundamental and empirical models(Thomas,Yan,Bohart-Adams,Yoon-Nelson,and Wolboroska)as well as artificial intelligence techniques(Artificial neural network(ANN)and Adaptive neuro-fuzzy inference system(ANFIS))were used to simulate experimental breakthrough curves and predict column dynamics.Increase in flow rate resulted in reduced adsorption capacity.However,adsorption capacity was not affected by bed depth.ANN was superior in predicting breakthrough curves and predicted breakthrough times with high accuracy(R^2>0.9962).Na OH(0.5 mol·L^-1)was successfully used to regenerate the adsorption bed.After nine cyclic adsorption/desorption runs,only a marginal decrease in adsorption and desorption efficiencies of 10%and 8%respectively was observed.The same regenerate Na OH solution was reused for all desorption cycles.After nine cycles the eluent desorbed a total of 1550 mg phosphate exhibiting potential for further reuse.
基金Supported by the National Science Foundation of China under Grant Nos. 10774150,10834014the China 973-Program under Grant Nos. 2007CB935903 and HKUST605010
文摘The fully connected Hopfield network is inferred based on observed magnetizations and pairwise correlations.We present the system in the glassy phase with low temperature and high memory load.We find that the inference error is very sensitive to the form of state sampling.When a single state is sampled to compute magnetizations and correlations,the inference error is almost indistinguishable irrespective of the sampled state.However,the error can be greatly reduced if the data is collected with state transitions.Our result holds for different disorder samples and accounts for the previously observed large fluctuations of inference error at low temperatures.
基金The National Key Research and Development Program of China under contract No.2022YFC3105002the National Natural Science Foundation of China under contract No.42176020the project from the Key Laboratory of Marine Environmental Information Technology,Ministry of Natural Resources,under contract No.2023GFW-1047.
文摘The Stokes production coefficient(E_(6))constitutes a critical parameter within the Mellor-Yamada type(MY-type)Langmuir turbulence(LT)parameterization schemes,significantly affecting the simulation of turbulent kinetic energy,turbulent length scale,and vertical diffusivity coefficient for turbulent kinetic energy in the upper ocean.However,the accurate determination of its value remains a pressing scientific challenge.This study adopted an innovative approach by leveraging deep learning technology to address this challenge of inferring the E_(6).Through the integration of the information of the turbulent length scale equation into a physical-informed neural network(PINN),we achieved an accurate and physically meaningful inference of E_(6).Multiple cases were examined to assess the feasibility of PINN in this task,revealing that under optimal settings,the average mean squared error of the E_(6) inference was only 0.01,attesting to the effectiveness of PINN.The optimal hyperparameter combination was identified using the Tanh activation function,along with a spatiotemporal sampling interval of 1 s and 0.1 m.This resulted in a substantial reduction in the average bias of the E_(6) inference,ranging from O(10^(1))to O(10^(2))times compared with other combinations.This study underscores the potential application of PINN in intricate marine environments,offering a novel and efficient method for optimizing MY-type LT parameterization schemes.
基金Supported by the National Key Research and Development Program of China(No.2017YFB1003101,2018AAA0103300,2017YFA0700900)the National Natural Science Foundation of China(No.61702478,61732007,61906179)+2 种基金the Beijing Natural Science Foundation(No.JQ18013)the National Science and Technology Major Project(No.2018ZX01031102)the Beijing Academy of Artificial Intelligence
文摘Deep learning has now been widely used in intelligent apps of mobile devices.In pursuit of ultra-low power and latency,integrating neural network accelerators(NNA)to mobile phones has become a trend.However,conventional deep learning programming frameworks are not well-developed to support such devices,leading to low computing efficiency and high memory-occupation.To address this problem,a 2-stage pipeline is proposed for optimizing deep learning model inference on mobile devices with NNAs in terms of both speed and memory-footprint.The 1 st stage reduces computation workload via graph optimization,including splitting and merging nodes.The 2 nd stage goes further by optimizing at compilation level,including kernel fusion and in-advance compilation.The proposed optimizations on a commercial mobile phone with an NNA is evaluated.The experimental results show that the proposed approaches achieve 2.8×to 26×speed up,and reduce the memory-footprint by up to 75%.
文摘Discovering genetic basis of diseases is an important goal and a challenging problem in bioinformatics research. Inspired by network-based global inference approach, Semi-global inference method is proposed to capture the complex associations between phenotypes and genes. The proposed method integrates phenotype similarities and protein-protein interactions, and it establishes the profile vectors of phenotypes and proteins. Then the relevance between each candidate gene and the target phenotype is evaluated. Candidate genes are then ranked according to relevance mark and genes that are potentially associated with target disease are identified based on this ranking. The model selects nodes in integrated phenotype-protein network for inference, by exploiting Phenotype Similarity Threshold (PST), which throws lights on selection of similar phenotypes for gene prediction problem. Different vector relevance metrics for computing the relevance marks of candidate genes are discussed. The performance of the model is evaluated on Online Mendelian Inheritance in Man (OMIM) data sets and experimental evaluation shows high performance of proposed Semi-global method outperforms existing global inference methods.
文摘This paper applies both the neural network and adaptive neuro-fuzzy inference system for forecasting short-term chaotic traffic volumes and compares the results. The architecture of the neural network consists of the input vector, one hidden layer and output layer. Bayesian regularization is employed to obtain the effective number of neurons in the hidden layer. The input variables and target of the adaptive neuro-fuzzy inference system are the same as those of the neural network. The data clustering technique is used to group data points so that the membership functions will be more tailored to the input data, which in turn greatly reduces the number of fuzzy rules. Numerical results indicate that these two models have almost the same accuracy, while the adaptive neuro-fuzzy inference system takes more time to train. It is also shown that although the effective number of neurons in the hidden layer is less than half the number of the input elements, the neural network can have satisfactory performance.
基金supported by the Sichuan Science and Technology Program under Grants No.2022YFQ0052 and No.2021YFQ0009.
文摘At present,knowledge embedding methods are widely used in the field of knowledge graph(KG)reasoning,and have been successfully applied to those with large entities and relationships.However,in research and production environments,there are a large number of KGs with a small number of entities and relations,which are called sparse KGs.Limited by the performance of knowledge extraction methods or some other reasons(some common-sense information does not appear in the natural corpus),the relation between entities is often incomplete.To solve this problem,a method of the graph neural network and information enhancement is proposed.The improved method increases the mean reciprocal rank(MRR)and Hit@3 by 1.6%and 1.7%,respectively,when the sparsity of the FB15K-237 dataset is 10%.When the sparsity is 50%,the evaluation indexes MRR and Hit@10 are increased by 0.8%and 1.8%,respectively.
文摘In the field of engineering,LabVIEW and MATLAB are the languages most commonly used by program developers.Howev-er,they have their respective advantages and disadvantages.The combination of the two will undoubtedly facilitate program develop-ment.Design of inference engine is the key point and difficulty in the design of fault diagnosis expert system.This paper combinesLabVIEW and MATLAB to design the inference engine of fault diagnosis expert system based on the advantages of the graphical pro-gramming environment and signal analysis toolkit of LabVIEW without the defect of neural network toolkit.In addition,it introducesthe implementation methods and precautions for combination of LabVIEW and BP network so as to make LabVIWE amd BP benefitfrom each other,which is of great pragmatic value.
