Air combat target maneuver trajectory prediction based on robust regularized Volterra series and adaptive ensemble online transfer learning

Target maneuver trajectory prediction is an important prerequisite for air combat situation awareness and maneuver decision-making.However,how to use a large amount of trajectory data generated by air combat confrontation training to achieve real-time and accurate prediction of target maneuver trajectory is an urgent problem to be solved.To solve this problem,in this paper,a hybrid algorithm based on transfer learning,online learning,ensemble learning,regularization technology,target maneuvering segmentation point recognition algorithm,and Volterra series,abbreviated as AERTrOS-Volterra is proposed.Firstly,the model makes full use of a large number of trajectory sample data generated by air combat confrontation training,and constructs a Tr-Volterra algorithm framework suitable for air combat target maneuver trajectory prediction,which realizes the extraction of effective information from the historical trajectory data.Secondly,in order to improve the real-time online prediction accuracy and robustness of the prediction model in complex electromagnetic environments,on the basis of the TrVolterra algorithm framework,a robust regularized online Sequential Volterra prediction model is proposed by integrating online learning method,regularization technology and inverse weighting calculation method based on the priori error.Finally,inspired by the preferable performance of models ensemble,ensemble learning scheme is also incorporated into our proposed algorithm,which adaptively updates the ensemble prediction model according to the performance of the model on real-time samples and the recognition results of target maneuvering segmentation points,including the adaptation of model weights;adaptation of parameters;and dynamic inclusion and removal of models.Compared with many existing time series prediction methods,the newly proposed target maneuver trajectory prediction algorithm can fully mine the prior knowledge contained in the historical data to assist the current prediction.The rationality and effectiveness of the proposed algorithm are verified by simulation on three sets of chaotic time series data sets and a set of real target maneuver trajectory data sets.

Malicious Activities Prediction Over Online Social Networking Using Ensemble Model

With the vast advancements in Information Technology,the emergence of Online Social Networking(OSN)has also hit its peak and captured the atten-tion of the young generation people.The clone intends to replicate the users and inject massive malicious activities that pose a crucial security threat to the original user.However,the attackers also target this height of OSN utilization,explicitly creating the clones of the user’s account.Various clone detection mechanisms are designed based on social-network activities.For instance,monitoring the occur-rence of clone edges is done to restrict the generation of clone activities.However,this assumption is unsuitable for a real-time environment and works optimally during the simulation process.This research concentrates on modeling and effi-cient clone prediction and avoidance methods to help the social network activists and the victims enhance the clone prediction accuracy.This model does not rely on assumptions.Here,an ensemble Adaptive Random Subspace is used for clas-sifying the clone victims with k-Nearest Neighbour(k-NN)as a base classifier.The weighted clone nodes are analysed using the weighted graph theory concept based on the classified results.When the weighted node’s threshold value is high-er,the trust establishment is terminated,and the clones are ranked and sorted in the higher place for termination.Thus,the victims are alert to the clone propaga-tion over the online social networking end,and the validation is done using the MATLAB 2020a simulation environment.The model shows a better trade-off than existing approaches like Random Forest(RF),Naïve Bayes(NB),and the standard graph model.Various performance metrics like True Positive Rate(TPR),False Alarm Rate(FAR),Recall,Precision,F-measure,and ROC and run time analysis are evaluated to show the significance of the model.

基于Online-GRU信道预测的星上自适应功率控制方法

针对传统卫星功率控制方法存在资源浪费、时延长的问题,提出一种基于在线-门控循环单元(Online-GRU)信道预测的星上自适应功率控制方法,通过在线训练更新网络参数来解决离线预测算法存在的累积误差的问题。仿真结果表明,提出的在线训练算法比离线算法预测精确度提升了38.30%,相比在线-长短期记忆网络(Online-LSTM)节约了63.21%的训练时间;提出的自适应功率控制方法比固定发射功率的方法节约了55.74%的发射功率;同时,相比基于地面定时反馈信道状态的自适应功率控制方法具备更好的鲁棒性。

Residual subsidence time series model in mountain area caused by underground mining based on GNSS online monitoring

The residual subsidence caused by underground mining in mountain area has a long subsidence duration time and great potential harm,which seriously threatens the safety of people's production and life in the mining area.Therefore,it is necessary to use appropriate monitoring methods and mathematical models to effectively monitor and predict the residual subsidence caused by underground mining.Compared with traditional level survey and InSAR(Interferometric Synthetic Aperture Radar)technology,GNSS(Global Navigation Satellite System)online monitoring technology has the advantages of long-term monitoring,high precision and more flexible monitoring methods.The empirical equation method of residual subsidence in mining subsidence is effectively combined with the rock creep equation,which can not only describe the residual subsidence process from the mechanism,but also predict the residual subsidence.Therefore,based on GNSS online monitoring technology,combined with the mining subsidence model of mountain area and adding the correlation coefficient of the compaction degree of caving broken rock and the Kelvin model of rock mechanics,this paper constructs the residual subsidence time series model of arbitrary point on the ground in mountain area.Through the example,the predicted results of the model in the inversion parameter phase and the dynamic prediction phase are compared with the measured data sequence.The results show that the model can carry out effective numerical calculation according to the GNSS monitoring data of any point on the ground,and the model prediction effect is good,which provides a new method for the prediction of residual subsidence in mountain mining.

Analysis and Prediction of Content Popularity for Online Video Service:A Youku Case Study

Understanding the characteristics and predicting the popularity of the newly published online videos can provide direct implications in various contexts such as service design, advertisement planning, network management and etc. In this paper, we collect a real-world large-scale dataset from a leading online video service provider in China, namely Youku. We first analyze the dynamics of content publication and content popularity for the online video service. Then, we propose a rich set of features and exploit various effective classification methods to estimate the future popularity level of an individual video in various scenarios. We show that the future popularity level of a video can be predicted even before the video's release, and by introducing the historical popularity information the prediction performance can be improved dramatically. In addition, we investigate the importance of each feature group and each feature in the popularity prediction, and further reveal the factors that may impact the video popularity. We also discuss how the early monitoring period influences the popularity level prediction. Our work provides an insight into the popularity of the newly published online videos, and demonstrates promising practical applications for content publishers,service providers, online advisers and network operators.

Online Predictive Monitoring and Prediction Model for a Periodic Process Through Multiway Non-Gaussian Modeling

A new on-line predictive monitoring and prediction model for periodic biological processes is proposed using the multiway non-Gaussian modeling. The basic idea of this approach is to use multiway non-Gaussian modeling to extract some dominant key components from daily normal operation data in a periodic process, and subsequently combining these components with predictive statistical process monitoring techniques. The proposed predictive monitoring method has been applied to fault detection and diagnosis in the biological wastewater-treatment process, which is based on strong diurnal characteristics. The results show the power and advantages of the proposed predictive monitoring of a continuous process using the multiway predictive monitoring concept, which is thus able to give very useful conceptual results for a daily monitoring process and also enables a more rapid detection of the process fault than other traditional monitoring methods.

Online prediction for contamination of chlortetracycline fermentation based on Dezert–Smarandache theory

Fermentative production of chlortetracycline is a complex fed-batch bioprocess. It generally takes over 90 h for cultivation and is often contaminated by undesired microorganisms. Once the fermentation system is contaminated to certain extent, the product quality and yield will be seriously affected, leading to a substantial economic loss. Using information fusion based on the Dezer–Smarandache theory, self-recursive wavelet neural network and unscented kalman filter, a novel method for online prediction of contamination is developed. All state variables of culture process involving easy-to-measure and difficult-to-measure variables commonly obtained with soft-sensors present their contamination symptoms. By extracting and fusing latent information from the changing trend of each variable, integral and accurate prediction results for contamination can be achieved. This makes preventive and corrective measures be taken promptly. The field experimental results show that the method can be used to detect the contamination in time, reducing production loss and enhancing economic efficiency.

Prediction of Online Judge Practice Passing Rate Based on Knowledge Tracing

Programming ability has become one of the most practical basic skills,and it is also the foundation of software development.However,in the daily training experiment,it is difficult for students to find suitable exercises from a large number of topics provided by numerous online judge(OJ)systems.Recommending high passing rate topics with an effective prediction algorithm can effectively solve the problem.Directly applying some common prediction algorithms based on knowledge tracing could bring some problems,such as the lack of the relationship among programming exercises and dimension disaster of input data.In this paper,those problems were analyzed,and a new prediction algorithm was proposed.Additional information,which represented the relationship between exercises,was added in the input data.And the input vector was also compressed to solve the problem of dimension disaster.The experimental results show that deep knowledge tracing(DKT)with side information and compression(SC)model has an area under the curve(AUC)of 0.7761,which is better than other models based on knowledge tracing and runs faster.

Online prediction of EEG based on KRLST algorithm

Kernel adaptive algorithm is an extension of adaptive algorithm in nonlinear,and widely used in the field of non-stationary signal processing.But the distribution of classic data sets seems relatively regular and simple in time series.The distribution of the electroencephalograph(EEG)signal is more randomness and non-stationarity,so online prediction of EEG signal can further verify the robustness and applicability of kernel adaptive algorithms.What’s more,the purpose of modeling and analyzing the time series of EEG signals is to discover and extract valuable information,and to reveal the internal relations of EEG signals.The time series prediction of EEG plays an important role in EEG time series analysis.In this paper,kernel RLS tracker(KRLST)is presented to online predict the EEG signals of motor imagery and compared with other 13 kernel adaptive algorithms.The experimental results show that KRLST algorithm has the best effect on the brain computer interface(BCI)dataset.

Online Fault Prediction Based on Combined AOSVR and ARMA Models

Accurate fault prediction can obviously reduce cost and decrease the probability of accidents so as to improve the performance of the system testing and maintenance. Traditional fault prediction methods are always offline that are not suitable for online and real-time processing. For the complicated nonlinear and non-stationary time series, it is hard to achieve exact predicting result with single models such as support vector regression （SVR）, artifieial neural network （ANN）, and autoregressive moving average （ARMA）. Combined with the accurate online support vector regression （AOSVR） algorithm and ARMA model, a new online approach is presented to forecast fault with time series prediction. The fault trend feature can be extracted by the AOSVR with global kernel for general fault modes. Moreover, its prediction residual that represents the local high-frequency components is synchronously revised and compensated by the sliding time window ARMA model. Fault prediction with combined AOSVR and ARMA can be realized better than with the single one. Experiments on Tennessee Eastman process fault data show the new method is practical and effective.

Machine learning-based prediction models for patients no-show in online outpatient appointments

With the development of information and communication technologies,all public tertiary hospitals in China began to use online outpatient appointment systems.However,the phenomenon of patient no-shows in online outpatient appointments is becoming more serious.The objective of this study is to design a prediction model for patient no-shows,thereby assisting hospitals in making relevant decisions,and reducing the probability of patient no-show behavior.We used 382,004 original online outpatient appointment records,and divided the data set into a training set(N_(1)=286,503),and a validation set(N_(2)=95,501).We used machine learning algorithms such as logistic regression,k-nearest neighbor(KNN),boosting,decision tree(DT),random forest(RF)and bagging to design prediction models for patient no-show in online outpatient appointments.The patient no-show rate of online outpatient appointment was 11.1%(N=42,224).From the validation set,bagging had the highest area under the ROC curve and AUC value,which was 0.990,followed by random forest and boosting models,which were 0.987 and 0.976,respectively.In contrast,compared with the previous prediction models,the area under ROC and AUC values of the logistic regression,decision tree,and k-nearest neighbors were lower at 0.597,0.499 and 0.843,respectively.This study demonstrates the possibility of using data from multiple sources to predict patient no-shows.The prediction model results can provide decision basis for hospitals to reduce medical resource waste,develop effective outpatient appointment policies,and optimize operations.

Impact point prediction guidance of ballistic missile in high maneuver penetration condition

An impact point prediction(IPP) guidance based on supervised learning is proposed to address the problem of precise guidance for the ballistic missile in high maneuver penetration condition.An accurate ballistic trajectory model is applied to generate training samples,and ablation experiments are conducted to determine the mapping relationship between the flight state and the impact point.At the same time,the impact point coordinates are decoupled to improve the prediction accuracy,and the sigmoid activation function is improved to ameliorate the prediction efficiency.Therefore,an IPP neural network model,which solves the contradiction between the accuracy and the speed of the IPP,is established.In view of the performance deviation of the divert control system,the mapping relationship between the guidance parameters and the impact deviation is analysed based on the variational principle.In addition,a fast iterative model of guidance parameters is designed for reference to the Newton iteration method,which solves the nonlinear strong coupling problem of the guidance parameter solution.Monte Carlo simulation results show that the prediction accuracy of the impact point is high,with a 3 σ prediction error of 4.5 m,and the guidance method is robust,with a 3 σ error of 7.5 m.On the STM32F407 singlechip microcomputer,a single IPP takes about 2.374 ms,and a single guidance solution takes about9.936 ms,which has a good real-time performance and a certain engineering application value.

Non-Minimum Phase Nonlinear System Predictive Control Based on Local Recurrent Neural Networks

After a recursive multi-step-ahead predictor for nonlinear systems based on local recurrent neural networks is introduced, an intelligent FID controller is adopted to correct the errors including identified model errors and accumulated errors produced in the recursive process. Characterized by predictive control, this method can achieve a good control accuracy and has good robustness. A simulation study shows that this control algorithm is very effective.

An Ensemble Learning Model for Early Dropout Prediction of MOOC Courses

Massive open online courses(MOOCs)have become a way of online learning across the world in the past few years.However,the extremely high dropout rate has brought many challenges to the development of online learning.Most of the current methods have low accuracy and poor generalization ability when dealing with high-dimensional dropout features.They focus on the analysis of the learning score and check result of online course,but neglect the phased student behaviors.Besides,the status of student participation at a given moment is necessarily impacted by the prior status of learning.To address these issues,this paper has proposed an ensemble learning model for early dropout prediction(ELM-EDP)that integrates attention-based document representation as a vector(A-Doc2vec),feature learning of course difficulty,and weighted soft voting ensemble with heterogeneous classifiers(WSV-HC).First,A-Doc2vec is proposed to learn sequence features of student behaviors of watching lecture videos and completing course assignments.It also captures the relationship between courses and videos.Then,a feature learning method is proposed to reduce the interference caused by the differences of course difficulty on the dropout prediction.Finally,WSV-HC is proposed to highlight the benefits of integration strategies of boosting and bagging.Experiments on the MOOCCube2020 dataset show that the high accuracy of our ELM-EDP has better results on Accuracy,Precision,Recall,and F1.

Generalized Predictive Control with Online Least Squares Support Vector Machines

这份报纸基于能有效地处理非线性的系统的联机最少的广场支持向量机器(LS-SVM ) 建议一个实际概括预兆的控制(GPC ) 算法。在每个采样时期，算法递归地由增加新数据对并且在实时性质上从考虑删除最不重要的修改模型。删除的数据对被 lagrange 的绝对值从最后一个采样时期更多样地决定。当增加新数据对并且删除存在的时，纸给模型参数的递归的算法分别地，一个大矩阵的倒置被避免，存储器能被算法完全控制。非线性的 LS-SVM 模型在每个采样时期在 GPC 算法被使用。抵销过程的 pH 上的概括预兆的控制的实验显示出建议算法的有效性和实物。

Efficient and robust CNN-LSTM prediction of flame temperature aided light field online tomography

Light field tomography,an optical combustion diagnostic technology,has recently attracted extensive attention due to its easy implementation and non-intrusion.However,the conventional iterative methods are high data throughput,low efficiency and time-consuming,and the existing machine learning models use the radiation spectrum information of the flame to realize the parameter field measurement at the current time.It is still an offline measurement and cannot realize the online prediction of the instantaneous structure of the actual turbulent combustion field.In this work,a novel online prediction model of flame temperature instantaneous structure based on deep convolutional neural network and long short-term memory(CNN-LSTM)is proposed.The method uses the characteristics of local perception,shared weight,and pooling of CNN to extract the threedimensional(3D)features of flame temperature and outgoing radiation images.Moreover,the LSTM is used to comprehensively utilize the ten historical time series information of high dynamic combustion flame to accurately predict 3D temperature at three future moments.A chaotic time-series dataset based on the flame radiation forward model is built to train and validate the performance of the proposed CNN-LSTM model.It is proven that the CNN-LSTM prediction model can successfully learn the evolution pattern of combustion flame and make accurate predictions.

Online learning method for predicting air environmental information used in agricultural robots

Air environmental information plays an important role during plant growth and reproduction, prompt and accurate prediction of atmospheric environmental data is helpful for agricultural robots to make a timely decision. For efficiency, an online learning method for predicting air environmental information was presented in this work. This method combines the advantages of convolutional neural network (CNN) and experience replay technique: CNN is used to extract features from raw data and predict atmospheric environmental information, experience replay technique can store environmental data over some time and update the hyperparameters of CNN. To validate the effects of this method, this online method was compared with three different predictive methods (including random forest, multi-layer perceptron, and support vector regression) using a public dataset (Jena). According to results, a suitable sample sequence size (e.g., 16) has a smaller number of training sessions and stable results, a larger replay memory size (e.g., 200) can provide enough samples to capture useful features, and 6 d of historical information is the best setting for training predictor. Compared with traditional methods, the method proposed in this study is the only method applied for various conditions.

A generalizable, data-driven online approach to forecast capacity degradation trajectory of lithium batteries

Estimating battery degradation is vital not only to monitor battery’s state-of-health but also to accelerate research on new battery chemistries. Herein, we present a data-driven approach to forecast the capacity fading trajectory of lab-assembled lithium batteries. Features with physical meanings in addition to predictive abilities are extracted from discharge voltage curves, enabling online prediction for a single cell with only its historical data. The robustness and generalizability allow for the demonstration on a compromised quality dataset consisting of batteries varying in battery architectures and cycling conditions,with superior accuracy for end of life and degradation trajectory prediction with average errors of 8.2%and 2.8%, respectively. Apart from the impressive prediction accuracy, the as-extracted features also provide physical insights, the incorporation of which into material design or battery operation conditions further enlightens the development of better batteries. We highlight the effectiveness of time-seriesbased techniques in forecasting battery cycling performance, as well as the huge potential of datadriven methods in unveiling hidden correlations in complicated energy chemistries such as lithium metal batteries.

Online machine learning for stream wastewater influent flow rate prediction under unprecedented emergencies

Accurate influent flow rate prediction is important for operators and managers at wastewater treatment plants(WWTPs),as it is closely related to wastewater characteristics such as biochemical oxygen demand(BOD),total suspend solids(TSS),and pH.Previous studies have been conducted to predict influent flow rate,and it was proved that data-driven models are effective tools.However,most of these studies have focused on batch learning,which is inadequate for wastewater prediction in the era of COVID-19 as the influent pattern changed significantly.Online learning,which has distinct advantages of dealing with stream data,large data set,and changing data pattern,has a potential to address this issue.In this study,the performance of conventional batch learning models Random Forest(RF),K-Nearest Neighbors(KNN),and Multi-Layer Perceptron(MLP),and their respective online learning models Adaptive Random Forest(aRF),Adaptive K-Nearest Neighbors(aKNN),and Adaptive Multi-Layer Perceptron(aMLP),were compared for predicting influent flow rate at two Canadian WWTPs.Online learning models achieved the highest R2,the lowest MAPE,and the lowest RMSE compared to conventional batch learning models in all scenarios.The R2 values on testing data set for 24-h ahead prediction of the aRF,aKNN,and aMLP at Plant A were 0.90,0.73,and 0.87,respectively;these values at Plant B were 0.75,0.78,and 0.56,respectively.The proposed online learning models are effective in making reliable predictions under changing data patterns,and they are efficient in dealing with continuous and large influent data streams.They can be used to provide robust decision support for wastewater treatment and management in the changing era of COVID-19 and also under other unprecedented emergencies that could change influent patterns.

Evolution-Based Performance Prediction of Star Cricketers

Cricket databases contain rich and useful information to examine and forecasting patterns and trends.This paper predicts Star Cricketers(SCs)from batting and bowling domains by employing supervised machine learning models.With this aim,each player’s performance evolution is retrieved by using effective features that incorporate the standard performance measures of each player and their peers.Prediction is performed by applying Bayesianrule,function and decision-tree-based models.Experimental evaluations are performed to validate the applicability of the proposed approach.In particular,the impact of the individual features on the prediction of SCs are analyzed.Moreover,the category and model-wise feature evaluations are also conducted.A cross-validation mechanism is applied to validate the performance of our proposed approach which further confirms that the incorporated features are statistically significant.Finally,leading SCs are extracted based on their performance evolution scores and their standings are cross-checked with those provided by the International Cricket Council.