TCAS-PINN:Physics-informed neural networks with a novel temporal causality-based adaptive sampling method

Physics-informed neural networks(PINNs)have become an attractive machine learning framework for obtaining solutions to partial differential equations(PDEs).PINNs embed initial,boundary,and PDE constraints into the loss function.The performance of PINNs is generally affected by both training and sampling.Specifically,training methods focus on how to overcome the training difficulties caused by the special PDE residual loss of PINNs,and sampling methods are concerned with the location and distribution of the sampling points upon which evaluations of PDE residual loss are accomplished.However,a common problem among these original PINNs is that they omit special temporal information utilization during the training or sampling stages when dealing with an important PDE category,namely,time-dependent PDEs,where temporal information plays a key role in the algorithms used.There is one method,called Causal PINN,that considers temporal causality at the training level but not special temporal utilization at the sampling level.Incorporating temporal knowledge into sampling remains to be studied.To fill this gap,we propose a novel temporal causality-based adaptive sampling method that dynamically determines the sampling ratio according to both PDE residual and temporal causality.By designing a sampling ratio determined by both residual loss and temporal causality to control the number and location of sampled points in each temporal sub-domain,we provide a practical solution by incorporating temporal information into sampling.Numerical experiments of several nonlinear time-dependent PDEs,including the Cahn–Hilliard,Korteweg–de Vries,Allen–Cahn and wave equations,show that our proposed sampling method can improve the performance.We demonstrate that using such a relatively simple sampling method can improve prediction performance by up to two orders of magnitude compared with the results from other methods,especially when points are limited.

Failure-Informed Adaptive Sampling for PINNs,Part II:Combining with Re-sampling and Subset Simulation

This is the second part of our series works on failure-informed adaptive sampling for physic-informed neural networks(PINNs).In our previous work(SIAM J.Sci.Comput.45:A1971–A1994),we have presented an adaptive sampling framework by using the failure probability as the posterior error indicator,where the truncated Gaussian model has been adopted for estimating the indicator.Here,we present two extensions of that work.The first extension consists in combining with a re-sampling technique,so that the new algorithm can maintain a constant training size.This is achieved through a cosine-annealing,which gradually transforms the sampling of collocation points from uniform to adaptive via the training progress.The second extension is to present the subset simulation(SS)algorithm as the posterior model(instead of the truncated Gaussian model)for estimating the error indicator,which can more effectively estimate the failure probability and generate new effective training points in the failure region.We investigate the performance of the new approach using several challenging problems,and numerical experiments demonstrate a significant improvement over the original algorithm.

Scientific Elegance in NIDS: Unveiling Cardinality Reduction, Box-Cox Transformation, and ADASYN for Enhanced Intrusion Detection

The emergence of digital networks and the wide adoption of information on internet platforms have given rise to threats against users’private information.Many intruders actively seek such private data either for sale or other inappropriate purposes.Similarly,national and international organizations have country-level and company-level private information that could be accessed by different network attacks.Therefore,the need for a Network Intruder Detection System(NIDS)becomes essential for protecting these networks and organizations.In the evolution of NIDS,Artificial Intelligence(AI)assisted tools and methods have been widely adopted to provide effective solutions.However,the development of NIDS still faces challenges at the dataset and machine learning levels,such as large deviations in numeric features,the presence of numerous irrelevant categorical features resulting in reduced cardinality,and class imbalance in multiclass-level data.To address these challenges and offer a unified solution to NIDS development,this study proposes a novel framework that preprocesses datasets and applies a box-cox transformation to linearly transform the numeric features and bring them into closer alignment.Cardinality reduction was applied to categorical features through the binning method.Subsequently,the class imbalance dataset was addressed using the adaptive synthetic sampling data generation method.Finally,the preprocessed,refined,and oversampled feature set was divided into training and test sets with an 80–20 ratio,and two experiments were conducted.In Experiment 1,the binary classification was executed using four machine learning classifiers,with the extra trees classifier achieving the highest accuracy of 97.23%and an AUC of 0.9961.In Experiment 2,multiclass classification was performed,and the extra trees classifier emerged as the most effective,achieving an accuracy of 81.27%and an AUC of 0.97.The results were evaluated based on training,testing,and total time,and a comparative analysis with state-of-the-art studies proved the robustness and significance of the applied methods in developing a timely and precision-efficient solution to NIDS.

Research on Adaptive Cluster Sampling Method Based on PPS

This paper introduces the principle of PPS-based adaptive cluster sampling method and its modified HH estimator and HT estimator calculation method. It compares PPS-based adaptive cluster sampling method with SRS sampling and SRS-based adaptive group. The difference between the group sampling and the advantages and scope of the PPS adaptive cluster sampling method are analyzed. According to the case analysis, the relevant conclusions are drawn: 1) The adaptive cluster sampling method is more accurate than the SRS sampling;2) SRS adaptive The HT estimator of the cluster sampling is more stable than the HH estimator;3) The two estimators of the PPS adaptive cluster sampling method have little difference in the estimation of the population mean, but the HT estimator variance is smaller and more suitable;4) PPS The HH estimator of adaptive cluster sampling is the same as the HH estimator of SRS adaptive cluster sampling, but the variance is larger and unstable.

Cascaded projection of Gaussian mixture model for emotion recognition in speech and ECG signals

A cascaded projection of the Gaussian mixture model algorithm is proposed.First,the marginal distribution of the Gaussian mixture model is computed for different feature dimensions, and a number of sub-classifiers are generated using the marginal distribution model.Each sub-classifier is based on different feature sets.The cascaded structure is adopted to fuse the sub-classifiers dynamically to achieve sample adaptation ability.Secondly,the effectiveness of the proposed algorithm is verified on electrocardiogram emotional signal and speech emotional signal.Emotional data including fidgetiness,happiness and sadness is collected by induction experiments.Finally,the emotion feature extraction method is discussed,including heart rate variability, the chaotic electrocardiogram feature and utterance level static feature.The emotional feature reduction methods are studied, including principle component analysis,sequential forward selection, the Fisher discriminant ratio and maximal information coefficient.The experimental results show that the proposed classification algorithm can effectively improve recognition accuracy in two different scenarios.

Multiple-target tracking with adaptive sampling intervals for phased-array radar

A novel adaptive sampling interval algorithm for multitarget tracking is presented. This algorithm which is based on interacting multiple models incorporates the grey relational grade （GRG） into the particle swarm optimization （PSO）. Firstly, the desired tracking accuracy is set for each target. Secondly, sampling intervals are selected as particles, and then the advantage of the GRG is taken as the measurement function for resource management. Meanwhile, the fitness value of the PSO is used to measure the difference between desired tracking accuracy and estimated tracking accuracy. Finally, it is suggested that the radar should track the target whose prediction value of the next sampling interval is the smallest. Simulations show that the proposed method improves both the tracking accuracy and tracking efficiency of the phased-array radar.

Physics-informed neural networks with residual/gradient-based adaptive sampling methods for solving partial differential equations with sharp solutions

We consider solving the forward and inverse partial differential equations(PDEs)which have sharp solutions with physics-informed neural networks(PINNs)in this work.In particular,to better capture the sharpness of the solution,we propose the adaptive sampling methods(ASMs)based on the residual and the gradient of the solution.We first present a residual only-based ASM denoted by ASMⅠ.In this approach,we first train the neural network using a small number of residual points and divide the computational domain into a certain number of sub-domains,then we add new residual points in the sub-domain which has the largest mean absolute value of the residual,and those points which have the largest absolute values of the residual in this sub-domain as new residual points.We further develop a second type of ASM(denoted by ASMⅡ)based on both the residual and the gradient of the solution due to the fact that only the residual may not be able to efficiently capture the sharpness of the solution.The procedure of ASMⅡis almost the same as that of ASMⅠ,and we add new residual points which have not only large residuals but also large gradients.To demonstrate the effectiveness of the present methods,we use both ASMⅠand ASMⅡto solve a number of PDEs,including the Burger equation,the compressible Euler equation,the Poisson equation over an Lshape domain as well as the high-dimensional Poisson equation.It has been shown from the numerical results that the sharp solutions can be well approximated by using either ASMⅠor ASMⅡ,and both methods deliver much more accurate solutions than the original PINNs with the same number of residual points.Moreover,the ASMⅡalgorithm has better performance in terms of accuracy,efficiency,and stability compared with the ASMⅠalgorithm.This means that the gradient of the solution improves the stability and efficiency of the adaptive sampling procedure as well as the accuracy of the solution.Furthermore,we also employ the similar adaptive sampling technique for the data points of boundary conditions(BCs)if the sharpness of the solution is near the boundary.The result of the L-shape Poisson problem indicates that the present method can significantly improve the efficiency,stability,and accuracy.

ADAPTIVE MEASUREMENT METHOD BASED ON CHANGING-CURVATURE FOR UNKNOWN FREE-FORM SURFACE

Current measurement method for unknown free-form surface has low efficiency.To acquire given precision, a lot of null points are measured. Based on change surface curvature, anew measurement planning is put forward. Sample step is evaluated from the change curvature and thelocally-bounded character of extrapolating curve. Two coefficients, maximum error coefficient andlocal camber coefficient, are used to optimize sampling step. The first coefficient is computed toavoid sampling-point exceeding the measurement range and the second control sampling precision.Compared with the other methods, the proposed planning method can reduce the number of themeasuring-point efficiently for the given precision. Measuring point distributes adaptively by thechange surface curvature. The method can be applied to improve measurement efficiency and accuracy.

SMC-PHD based multi-target track-before-detect with nonstandard point observations model

Detection and tracking of multi-target with unknown and varying number is a challenging issue, especially under the condition of low signal-to-noise ratio(SNR). A modified multi-target track-before-detect(TBD) method was proposed to tackle this issue using a nonstandard point observation model. The method was developed from sequential Monte Carlo(SMC)-based probability hypothesis density(PHD) filter, and it was implemented by modifying the original calculation in update weights of the particles and by adopting an adaptive particle sampling strategy. To efficiently execute the SMC-PHD based TBD method, a fast implementation approach was also presented by partitioning the particles into multiple subsets according to their position coordinates in 2D resolution cells of the sensor. Simulation results show the effectiveness of the proposed method for time-varying multi-target tracking using raw observation data.

A Novel Multiple Dependent State Sampling Plan Based on Time Truncated Life Tests Using Mean Lifetime

The design of a new adaptive version of the multiple dependent state(AMDS)sampling plan is presented based on the time truncated life test under the Weibull distribution.We achieved the proposed sampling plan by applying the concept of the double sampling plan and existing multiple dependent state sampling plans.A warning sign for acceptance number was proposed to increase the probability of current lot acceptance.The optimal plan parameters were determined simultaneously with nonlinear optimization problems under the producer’s risk and consumer’s risk.A simulation study was presented to support the proposed sampling plan.A comparison between the proposed and existing sampling plans,namely multiple dependent state(MDS)sampling plans and a modified multiple dependent state(MMDS)sampling plan,was considered under the average sampling number and operating characteristic curve values.In addition,the use of two real datasets demonstrated the practicality and usefulness of the proposed sampling plan.The results indicated that the proposed plan is more flexible and efficient in terms of the average sample number compared to the existing MDS and MMDS sampling plans.

Processing of 3D meshed surfaces using spherical wavelets

This paper presents an efficient technique for processing of 3D meshed surfaces via spherical wavelets. More specifically, an input 3D mesh is firstly transformed into a spherical vector signal by a fast low distortion spherical parameterization approach based on symmetry analysis of 3D meshes. This signal is then sampled on the sphere with the help of an adaptive sampling scheme. Finally, the sampled signal is transformed into the wavelet domain according to spherical wavelet transform where many 3D mesh processing operations can be implemented such as smoothing, enhancement, compression, and so on. Our main contribution lies in incorporating a fast low distortion spherical parameterization approach and an adaptive sampling scheme into the frame for pro- cessing 3D meshed surfaces by spherical wavelets, which can handle surfaces with complex shapes. A number of experimental ex- amples demonstrate that our algorithm is robust and efficient.

Designing Adaptive Multiple Dependent State Sampling Plan for Accelerated Life Tests

A novel adaptive multiple dependent state sampling plan(AMDSSP)was designed to inspect products from a continuous manufacturing process under the accelerated life test(ALT)using both double sampling plan(DSP)and multiple dependent state sampling plan(MDSSP)concepts.Under accelerated conditions,the lifetime of a product follows the Weibull distribution with a known shape parameter,while the scale parameter can be determined using the acceleration factor(AF).The Arrhenius model is used to estimate AF when the damaging process is temperature-sensitive.An economic design of the proposed sampling plan was also considered for the ALT.A genetic algorithm with nonlinear optimization was used to estimate optimal plan parameters to minimize the average sample number(ASN)and total cost of inspection(TC)under both producer’s and consumer’s risks.Numerical results are presented to support the AMDSSP for the ALT,while performance comparisons between the AMDSSP,the MDSSP and a single sampling plan(SSP)for the ALT are discussed.Results indicated that the AMDSSP was more flexible and efficient for ASN and TC than the MDSSP and SSP plans under accelerated conditions.The AMDSSP also had a higher operating characteristic(OC)curve than both the existing sampling plans.Two real datasets of electronic devices for the ALT at high temperatures demonstrated the practicality and usefulness of the proposed sampling plan.

Distributed model predictive control based on adaptive sampling mechanism

In this work,an adaptive sampling control strategy for distributed predictive control is proposed.According to the proposed method,the sampling rate of each subsystem of the accused object is determined based on the periodic detection of its dynamic behavior and calculations made using a correlation function.Then,the optimal sampling interval within the period is obtained and sent to the corresponding sub-prediction controller,and the sampling interval of the controller is changed accordingly before the next sampling period begins.In the next control period,the adaptive sampling mechanism recalculates the sampling rate of each subsystem’s measurable output variable according to both the abovementioned method and the change in the dynamic behavior of the entire system,and this process is repeated.Such an adaptive sampling interval selection based on an autocorrelation function that measures dynamic behavior can dynamically optimize the selection of sampling rate according to the real-time change in the dynamic behavior of the controlled object.It can also accurately capture dynamic changes,meaning that each sub-prediction controller can more accurately calculate the optimal control quantity at the next moment,significantly improving the performance of distributed model predictive control(DMPC).A comparison demonstrates that the proposed adaptive sampling DMPC algorithm has better tracking performance than the traditional DMPC algorithm.

ALGORITHMS FOR TRACKING MANEUVERING TARGET WITH PHASED ARRAY RADAR

Several typical algorithms for tracking maneuvering target with phased array radar are studied in this paper. The constant gain filter with multiple models is analyzed. A typical method for adaptively controlling the sampling interval is modified. The performance of the single model and multiple model estimator with uniform and variable sampling interval are evaluated and compared. It is shown by the simulation results that it is necessary to apply the adaptive sampling policy based on the multiple model method when the maneuvering targets are tracked by the phased array radar since saving radar resources is more important. The adaptive algorithms of variable sampling interval are better than the algorithms of variable model. The adaptive policy to determine the sampling interval based on multiple model are superior than those based on the single model filter, because IMM estimator can adapt to the maneuver more quickly and the prediction covariance of IMM is the more sensitive and more reliable index than residual to determine the sampling interval. With IMM based method, lower sampling interval is required for a certain accuracy.

Adaptive sampling for mesh spectrum editing

A mesh editing framework is presented in this paper, which integrates Free-Form Deformation (FFD) and geometry signal processing. By using simplified model from original mesh, the editing task can be accomplished with a few operations. We take the deformation of the proxy and the position coordinates of the mesh models as geometry signal. Wavelet analysis is em- ployed to separate local detail information gracefully. The crucial innovation of this paper is a new adaptive regular sampling approach for our signal analysis based editing framework. In our approach, an original mesh is resampled and then refined itera- tively which reflects optimization of our proposed spectrum preserving energy. As an extension of our spectrum editing scheme, the editing principle is applied to geometry details transferring, which brings satisfying results.

A new method of searching for concealed Au deposits by using the spectrum of arid desert plant species

With the increase of exploration depth,it is more and more difficult to find Au deposits.Due to the limitation of time and cost,traditional geological exploration methods are becoming increasingly difficult to be effectively applied.Thus,new methods and ideas are urgently needed.This study assessed the feasibility and effectiveness of using hyperspectral technology to prospect for hidden Au deposits.For this purpose,48 plant(Seriphidium terrae-albae)and soil(aeolian gravel desert soil)samples were first collected along a sampling line that traverses an Au mineralization alteration zone(Aketasi mining region in an arid region of China)and were used to obtain soil Au contents by a chemical analysis method and the reflectance spectra of plants obtained with an Analytical Spectral Device(ASD)FieldSpec3 spectrometer.Then,the corresponding relationship between the soil Au content anomaly and concealed Au deposits was investigated.Additionally,the characteristic bands were selected from plant spectra using four different methods,namely,genetic algorithm(GA),stepwise regression analysis(STE),competitive adaptive reweighted sampling(CARS),and correlation coefficient method(CC),and were then input into the partial least squares(PLS)method to construct a model for estimating the soil Au content.Finally,the quantitative relationship between the soil Au content and the 15 different plant transformation spectra was established using the PLS method.The results were compared with those of a model based on the full spectrum.The results obtained in this study indicate that the location of concealed Au deposits can be predicted based on soil geochemical anomaly information,and it is feasible and effective to use the full plant spectrum and PLS method to estimate the Au content in the soil.The cross-validated coefficient of determination(R2)and the ratio of the performance to deviation(RPD)between the predicted value and the measured value reached the maximum of 0.8218 and 2.37,respectively,with a minimum value of 6.56μg/kg for the root-mean-squared error(RMSE)in the full spectrum model.However,in the process of modeling,it is crucial to select the appropriate transformation spectrum as the input parameter for the PLS method.Compared with the GA,STE,and CC methods,CARS was the superior characteristic band screening method based on the accuracy and complexity of the model.When modeling with characteristic bands,the highest accuracy,R2 of 0.8016,RMSE of 7.07μg/kg,and RPD of 2.20 were obtained when 56 characteristic bands were selected from the transformed spectra(1/lnR)'(where it represents the first derivative of the reciprocal of the logarithmic spectrum)of sampled plants using the CARS method and were input into the PLS method to construct an inversion model of the Au content in the soil.Thus,characteristic bands can replace the full spectrum when constructing a model for estimating the soil Au content.Finally,this study proposes a method of using plant spectra to find concealed Au deposits,which may have promising application prospects because of its simplicity and rapidity.

Adaptive Sampling for Near Space Hypersonic Gliding Target Tracking

For modern phased array radar systems,the adaptive control of the target revisiting time is important for efficient radar resource allocation,especially in maneuvering target tracking applications.This paper presents a novel interactive multiple model(IMM)algorithm optimized for tracking maneuvering near space hypersonic gliding vehicles(NSHGV)with a fast adaptive sam-pling control logic.The algorithm utilizes the model probabilities to dynamically adjust the revisit time corresponding to NSHGV maneuvers,thus achieving a balance between tracking accuracy and resource consumption.Simulation results on typical NSHGV targets show that the proposed algo-rithm improves tracking accuracy and resource allocation efficiency compared to other conventional multiple model algorithms.

ADAPTIVE UPDATE RATE FOR PHASED ARRAY RADAR BASED ON IMMK-PF

Interacting Multiple Model Kalman-Particle Filter (IMMK-PF) has the advantages of particle filter and Kalman filter and good computation efficiency compared with Interacting Multiple Model Particle Filter (IMMPF). Based on IMMK-PF, an adaptive sampling target tracking algorithm for Phased Array Radar (PAR) is proposed. This algorithm first predicts Posterior Cramer-Rao Bound Matrix (PCRBM) of the target state, then updates the sample interval in accordance with change of the target dynamics by comparing the trace of the predicted PCRBM with a certain threshold. Simulation results demonstrate that this algorithm could solve the nonlinear motion and the nonlinear relationship between radar measurement and target motion state and decrease computation load.

Application of Hyperspectral Imaging Technology in Rapid Detection of Preservative in Milk

To ensure the quality and safety of pure milk,detection method of typical preservative-potassium sorbate in milk was researched in this paper.Hyperspectral imaging technology was applied to realize rapid detection.Influence factors for hyperspectral data collection for milk samples were firstly researched,including height of sample,bottom color and sample filled up container or not.Pretreatment methods and variable selection algorithms were applied into original spectral data.Rapid detection models were built based on support vector machine method(SVM).Finally,standard normalized variable(SNV)-competitive adaptive reweighted sampling(CARS)and SVM model was chosen in this paper.The accuracies of calibration set and testing set were 0.97 and 0.97,respectively.Kappa coefficient of the model was 0.93.It could be seen that hyperspectral imaging technology could be used to detect for potassium sorbate in milk.Meanwhile,it also provided methodological supports for the rapid detection of other preservatives in milk.

Nanopore ultra-long sequencing and adaptive sampling spur plant complete telomere-totelomere genome assembly

The pursuit of complete telomere-to-telomere(T2T)genome assembly in plants,challenged by genomic complexity,has been advanced by Oxford Nanopore Technologies(ONT),which offers ultra-long,realtime sequencing.Despite its promise,sequencing length and gap filling remain significant challenges.This study optimized DNA extraction and library preparation,achieving DNA lengths exceeding 485 kb;average N50 read lengths of 80.57 kb,reaching up to 440 kb;and maximum reads of 5.83 Mb.Importantly,we demonstrated that combining ultra-long sequencing and adaptive sampling can effectively fill gaps during assembly,evidenced by successfully filling the remaining gaps of a near-complete Arabidopsis genome assembly and resolving the sequence of an unknown telomeric region in watermelon genome.Collectively,our strategies improve the feasibility of complete T2T genomic assemblies across various plant species,enhancing genome-based research in diverse fields.