Aiming at the mechanical system related to multi-component failure， a reliability evaluation method of multi-component system based on time-varying Copula function was proposed. Firstly， the nonlinear Wiener process was introduced to characterize the performance degradation process， and the Copula function was used to characterize the correlation between multiple component failures. Secondly， based on the evolutionary equation of the Copula function approximation of the Fourier series， the fitting effects of the Fourier series on common time-varying forms were verified by Monte Carlo （MC） simulation. In addition， the likelihood ratio statistic was used to test the existence of time-varying correlation， indicating the necessity of time-varying correlation research. The example analysis shows that compared with the static correlation model， the time-varying correlation model has the log-likelihood function value increased by 4.36%， and the Akaike Information Criterion （AIC） decreased by 3.81%， achieving more accurate reliability evaluation results.
To solve the competitive facility location problem of new energy vehicle battery recycling outlets considering queuing theory， an Improved Human Learning Optimization （IHLO） algorithm was proposed. First， the competitive facility location model of new energy vehicle battery recycling outlets was constructed， which included queuing time constraints， capacity constraints， threshold constraints and other constraints. Then， considering that this problem belongs to NP-hard problem， in view of the shortcomings of Human Learning Optimization （HLO） algorithm， such as low convergence speed，optimization accuracy and solving stability in the early stage， IHLO algorithm was proposed by adopting elite population reverse learning strategy， group mutual learning operator and adaptive strategy of harmonic parameter. Finally， taking Shanghai and the Yangtze River Delta as examples for numerical experiments， IHLO was compared with Improved Binary Grey Wolf Optimization （IBGWO） algorithm， Improved Binary Particle Swarm Optimization （IBPSO） algorithm， HLO and Human Learning Optimization based on Learning Psychology （LPHLO） algorithm. For large， medium and small scales， the experimental results show that IHLO algorithm has the best performance in 14 of the 15 indicators； compared with IBGWO algorithm， the solution accuracy of IHLO algorithm is improved by at least 0.13%， the solution stability is improved by at least 10.05%， and the solution speed is improved by at least 17.48%. The results show that the proposed algorithm has high computational accuracy and fast optimization speed， which can effectively solve the competitive facility location problem.
To handle the problem of variable coupling in Unmanned Aerial Vehicle （UAV） three-axis gimbal stabilization control， an UAV gimbal system control algorithm based on Extended State Observer （ESO） was proposed. Firstly， an attitude solution algorithm model for the desired angle of the UAV gimbal was developed. Secondly， serial PID （Proportional-Integral-Derivative） control loops of position and velocity were constructed. Finally， an ESO was introduced to estimate the angular velocity term online in real-time， which solves the problem that the angular velocity term is difficult to measure directly due to high coupling and multiple external disturbances， and the control input of each channel was compensated. The experimental results show that in scenarios including without command， with command， and composite tasks， the root mean square errors of the proposed algorithm for angle measurement are 0.235 7°， 0.631 7°， and 0.946 3°， respectively. Compared to the traditional PID algorithm， the proposed algorithm achieves angle error reduction rates of 69.43%， 53.29%， and 50.43%， respectively. The proposed algorithm exhibits greater resistance to disturbances and higher control accuracy.
The existing industry-university-research performance evaluation systems and methods have problems such as single coverage of evaluation indicators， insufficient expression of evaluation sample features， and self-optimization ability of evaluation models to be improved， the system and method of subjective and objective intelligent evaluation of industry-university-research comprehensive performance were proposed. Firstly， for the three-party cooperation subjects， the factors and the connections between these factors that affect performance in the process of industry-university-research cooperation were excavated， and the three-level subjective and objective performance evaluation system of industry-university-research was self-constructed. Secondly， the features expression of discrete samples was enhanced by mapping the collected discrete sequence evaluation samples to different high-dimensional spatial domains， such as polar coordinate space and Markov transfer matrix. Then， through the chaotic optimization strategy design based on elite reverse somersault foraging， the depth model redundancy compression and hyperparameter global optimization efficiency were improved， and the ParNet （Parallel Network） classification model with lightweight compression and high-dimensional superparameter Adaptive optimization （AParNet） was constructed. Finally， the model was applied to industry-university-research performance evaluation to achieve high-performance intelligent performance evaluation. The experimental results show that this method fits well with the applications of discrete sequence non-linear classification and improves the classification performance while reducing the computational load when an optimization strategy is added to the model. Specifically， compared to ParNet， AParNet reduces the number of parameters by 10.8%， effectively achieving model compression， and its classification accuracy in performance evaluation of industry-university-research cooperation can reach 98.6%. Therefore， in the applications of intelligent performance evaluation of industry-university-research cooperation， the proposed method improves the adaptive ability of evaluation model and achieves accurate and efficient industry-university-research performance evaluation.
Aiming at the correlation problem between sleep stages and sleep apnea hypopnea， a sleep physiological time series classification method based on adaptive multi-task learning was proposed. Single-channel electroencephalogram and electrocardiogram were used for sleep staging and Sleep Apnea Hypopnea Syndrome （SAHS） detection. A two-stream time dependence learning module was utilized to extract shared features under joint supervision of the two tasks. The correlation between sleep stages and sleep apnea hypopnea was modeled by the adaptive inter-task correlation learning module with channel attention mechanism. The experimental results on two public datasets indicate that the proposed method can complete sleep staging and SAHS detection simultaneously. On UCD dataset， the accuracy， MF1（Macro F1-score）， and Area Under the receiver characteristic Curve （AUC） for sleep staging of the proposed method were 1.21 percentage points， 1.22 percentage points， and 0.008 3 higher than those of TinySleepNet； its MF2 （Macro F2-score）， AUC， and recall of SAHS detection were 11.08 percentage points， 0.053 7， and 15.75 percentage points higher than those of the 6-layer CNN model， which meant more disease segments could be detected. The proposed method could be applied to home sleep monitoring or mobile medical to achieve efficient and convenient sleep quality assessment， assisting doctors in preliminary diagnosis of SAHS.
Drug-target prediction method can effectively reduce costs and accelerate research process compared with traditional drug discovery. However， there are various challenges such as low balance of datasets and low precision of prediction in practical applications. Therefore， a drug-target interaction prediction method based on self-adaptive spherical evolution was proposed， namely ASE-KELM （self-Adaptive Spherical Evolution based on Kernel Extreme Learning Machine）. By the method， negative samples with high confidence were selected based on the principle that drugs with similar structures are likely to interact with targets. And to solve the problem that spherical evolution algorithm tends to fall into local optima， the feedback mechanism of historical memory of search factors and Linear Population Size Reduction （LPSR） were used to balance global and local search， which improved the optimization ability of the algorithm. Then the parameters of Kernel Extreme Learning Machine （KELM） were optimized by the self-adaptive spherical evolution algorithm. ASE-KELM was compared with algorithms such as NetLapRLS （Network Laplacian Regularized Least Square） and BLM-NII （Bipartite Local Model with Neighbor-based Interaction profile Inferring） on gold standard based datasets to verify the performance of the algorithms. Experimental results show that ASE-KELM outperforms comparison algorithms in AUC （Area Under the receiver operating Characteristic curve） and AUPR （Area Under the Precision-Recall curve） for the Enzyme （E）， G-Protein-Coupled Receptor （GPCR）， Ion Channel （IC）， and Nuclear Receptor （NR） datasets. And the effectiveness of ASE-KELM in predicting new drug-target pairs was validated on databases such as DrugBank.
For problems such as low accuracy and poor real-time detection of existing radar non-contact vital signs detection， a human vital signs detection algorithm based on Frequency Modulated Continuous Wave （FMCW） radar was proposed. Firstly，the vital signs signal was obtained through the millimeter wave radar. Then， the adaptive decomposition and reconstruction of the vital signs signal were achieved using the improved Empirical Wavelet Transformation （EWT） algorithm. The best value of the spectrum division line was found by introducing Sparrow Search Algorithm （SSA） and Fuzzy Entropy （FE）. Finally，the heart rate and respiratory rate were calculated using the estimation algorithm with improved frequency interpolation. The superiority and robustness of the proposed algorithm were verified through comparative experiments with a medical critical care monitor. The experimental results showed that compared with Wavelet Transform （WT） algorithm， Complementary Ensemble Empirical Mode Decomposition （CEEMD） algorithm and Variational Mode Decomposition （VMD） algorithm， the Mean Square Error （MSE） was reduced by 77.65， 27.25 and 21.05， the Mean Absolute Percentage （MAPE） was reduced by 7.33， 4.33 and 3.42 percentage points， and the real-time performance was improved by 0.72 s， 16.74 s and 1.87 s. At the same time， the proposed algorithm also achieves the detection of Heart Rate Variability （HRV）.
To help the autonomous vehicle plan a safe， comfortable and efficient driving trajectory， a trajectory planning approach based on model predictive control was proposed. First， to simplify the planning environment， a safe and feasible “three-circle” expansion of the safety zone was introduced， which also eliminates the collision issues caused by the idealized model of the vehicle. Then， the trajectory planning was decoupled in lateral and longitudinal space. A model prediction method was applied for lateral planning to generate a series of candidate trajectories that met the driving requirements， and a dynamic planning approach was utilized for longitudinal planning， which improved the efficiency of the planning process. Eventually， the factors affecting the selection of optimal trajectories were considered comprehensively， and an optimal trajectory evaluation function was proposed for path planning and speed planning more compatible with the driving requirements. The effectiveness of the proposed algorithm was verified by joint simulation with Matlab/Simulink， Prescan and Carsim software. Experimental results indicate that the vehicle achieves the expected effects in terms of comfort metrics， steering wheel angle variation and localization accuracy， and the planning curve also perfectly matches the tracking curve， which validates the advantage of the proposed algorithm.
Aiming at the problem that gait recognition is easily affected by changes in shooting angle and appearance， a gait recognition method based on a two-branch convolutional network was proposed. Firstly， a data augmentation method of random cropping and random occlusion， named RRDA（Restricted Random Data Augmentation）， was proposed to expand the data samples of appearance changes and improve the robustness of model occlusion. Secondly， the attention mechanism was used to form a two-branch Composite-Convolutional （C-Conv） layer to extract gait features. One branch network extracted the global and most recognizable information of pedestrian appearance through Horizontal Pyramid Mapping （HPM）； the other branch used multiple parallel Micro-Motion Capture Modules （MCMs） to extract short-term gait spatio-temporal information. Finally， the feature information of the two branches was added and fused， and then the gait recognition was achieved through a fully connected layer. A joint loss function was constructed based on the discriminative ability of balanced sample features and the convergence of the model to accelerate the convergence of the model. Experiments were conducted on the gait recognition dataset CASIA-B， the recognition accuracies of the proposed method in three states of walking are 97.40%， 93.67% and 81.19%， which are higher than those of GaitSet method， CapsNet method， two-stream gait method and GaitPart method； compared to GaitSet method， the recognition accuracy of the proposed method is 1.30 percentage points higher in the state of normal walking， 2.87 percentage points higher on carrying backpack， and 10.89 percentage points higher on wearing jacket. Experimental results show that the proposed method is feasible and effective.
Aiming at the problems that the detection accuracy of small objects such as cyclists and pedestrians in Three-Dimensional （3D） object detection is low， and it is difficult to adapt to complex urban road conditions， a 3D object detection network based on self-attention mechanism and graph convolution was proposed. Firstly， in order to obtain more discriminative small object features， self-attention mechanism was introduced into the backbone network to make the network more sensitive to small object features and improve the ability to extract network features. Secondly， a feature fusion module was constructed based on the self-attention mechanism to further enrich the information of shallow network and enhance the feature expression ability of deep network. Finally， dynamic graph convolution was used to predict the boundary box of the object， improving the accuracy of object prediction. The proposed network was tested on KITTI dataset， and compared to eight major networks such as TANet （Triple Attention Network） and IA-SSD （Instance-Aware Single-Stage Detector）. The experimental results show that the pedestrian detection accuracy of the proposed network is increased by 12.12， 13.82 and 11.03 percentage points compared with TANet， which has the suboptimal pedestrian detection accuracy， under three difficulty levels of simple， medium，and difficult degrees； the cyclist detection accuracy of the proposed network is 3.06 and 5.34 percentage points higher than that of IA-SSD under medium and difficult degrees. In summary， the network proposed in this paper can be better applied to small object detection tasks.
Object detection in autonomous driving scenes is one of the important research directions in computer vision. The researches focus on ensuring real-time and accurate object detection of objects by autonomous vehicles. Recently， a rapid development in deep learning technology had been witnessed， and its wide application in the field of autonomous driving had prompted substantial progress in this field. An analysis was conducted on the research status of object detection by YOLO （You Only Look Once） algorithms in the field of autonomous driving from the following four aspects. Firstly， the ideas and improvement methods of the single-stage YOLO series of detection algorithms were summarized， and the advantages and disadvantages of the YOLO series of algorithms were analyzed. Secondly， the YOLO algorithm-based object detection applications in autonomous driving scenes were introduced， the research status and applications for the detection and recognition of traffic vehicles， pedestrians， and traffic signals were expounded and summarized respectively. Additionally， the commonly used evaluation indicators in object detection， as well as the object detection datasets and automatic driving scene datasets， were summarized. Lastly， the problems and future development directions of object detection were discussed.
A new Maximum Power Point Tracking （MPPT） method， based on Self-Adaptive Particle Swarm Optimization （SAPSO）， was proposed to address the energy storage challenge in engine tandem composite turbine power generation systems. A Hybrid Energy Storage System （HESS） was introduced to augment the power capture capability of the generation system and replace single battery storage， achieving efficient and stable electrical energy storage. A control simulation model of energy storage optimization based on tandem composite turbine power generation was established using Matlab/Simulink software. The power tracking performance for various control methods and the energy storage characteristics of hybrid energy storage systems were compared and analyzed under predetermined operating conditions. Simulation results reveal that the proposed SAPSO-MPPT method outperforms the conventional P&O （Perturbation and Observation） control method， increasing power generation by 190 W and reducing response time by 0.15 s. Additionally， HESS could effectively track the demand power on the busbar， achieving power recovery efficiency of 95.3% . Finally， a test platform for the tandem composite turbine power generation system was developed using a modified Y24 engine bench to validate the fuel-saving potential of the proposed energy storage optimized control strategy. The test findings indicate that the suggested SAPSO-MPPT+HESS energy storage optimization strategy improves energy recovery efficiency by 0.53 percentage points compared to the original engine.
To address the issue of existing information diffusion models overlooking user subjectivity and social network dynamics， an SCBRD （Susceptible-Commented-Believed-Recovered-Defensed） opinion propagation model that considers user initiative and mobility in heterogeneous networks was proposed.Firstly， the basic reproduction number was determined using the next-generation matrix method， and the system’s dynamics and optimal control were investigated by applying Lyapunov’s stability theorem and Pontryagin’s principle. Then， a simulation analysis was performed based on BA （Barabási-Albert） scale-free network to identify the significant factors affecting the opinion propagation. The results reveal that users’ curiosity， forwarding behavior， and admission rate play dominant roles in information diffusion and the system has an optimal control solution. Finally， the model’s rationality was validated based on actual data. Compared to the SCIR （Susceptible-inCubation-Infective-Refractory） model， the SCBRD model improves fitting accuracy by 27.40% and reduces the Root Mean Square Error （RMSE） of prediction by 39.02%. Therefore， the proposed model can adapt to the complex and changing circumstances of information diffusion and provide better guidance for official public opinion regulation.
The problem of event-triggered fixed-time consistency based on event triggering was studied for multi-agent systems with unknown disturbances and nonlinear dynamics. Based on the traditional static event-triggered strategy， a fixed-time consensus protocol based on dynamic event-triggered strategy was proposed by introducing an adjustable dynamic variable. A dynamic event-triggered function based on state information and dynamic variables was given for each agent， and the event was triggered only when the measurement error of each agent satisfied the given triggering function. The introduced dynamic variables were adjustable threshold parameters that could further reduce the number of event triggers and use the limited resources of the system more efficiently. By using graph theory， fixed-time consensus theory and Lyapunov stability theory， the conditions that the parameters in the consensus protocol and trigger functions needed to satisfy when the system reaching fixed-time consensus were obtained， meanwhile Zeno behavior was shown not to exist. Finally， the numerical simulation results were applied to verify the correctness and validity of the theoretical analysis.
In order to address the low accuracy and speed of detection by manual and traditional automation methods for the weld seam surface of traction seat， a lightweight weld seam quality detection algorithm YOLOv5s-G2CW was proposed for the weld seam surface of traction seat. Firstly， the GhostBottleneckV2 module was applied as a replacement for the C3 module in YOLOv5s to reduce the number of parameters used in the model. Then， the CBAM （Convolutional Block Attention Module） was introduced into the Neck of the YOLOv5s model for integration of the weld features in two dimensions： channel and space. Also， the positioning loss function of the YOLOv5s model was improved into Wise-IoU， focusing on the predictive regression of ordinary quality anchor frames. Finally， the 13 × 13 feature layer used for the detection of large-sized objects in the YOLOv5s model was removed to further reduce the number of parameters used in the model. Experimental results show that， compared with the YOLOv5s model， the size of YOLOv5s-G2CW model reduces by 53.9%， the number of frames transmitted per second increases by 8.0%， and the mAP （mean Average Precision） value increases by 0.8 percentage points. It can be seen that the model is applicable to meet the requirements for real-time and accurate detection of the weld seam surface for traction seat.
With the advancement of technologies such as sensor networks and global positioning systems， the volume of meteorological data with both temporal and spatial characteristics has exploded， and the research on deep learning models for Spatiotemporal Sequence Forecasting （STSF） has developed rapidly. However， the traditional machine learning methods applied to weather forecasting for a long time have unsatisfactory effects in extracting the temporal correlations and spatial dependences of data， while the deep learning methods can extract features automatically through artificial neural networks to improve the accuracy of weather forecasting effectively， and have a very good effect in encoding long-term spatial information modeling. At the same time， the deep learning models driven by observational data and Numerical Weather Prediction （NWP） models based on physical theories are combined to build hybrid models with higher prediction accuracy and longer prediction time. Based on these， the application analysis and research progress of deep learning in the field of weather forecasting were reviewed. Firstly， the deep learning problems in the field of weather forecasting and the classical deep learning problems were compared and studied from three aspects： data format， problem model and evaluation metrics. Then， the development history and application status of deep learning in the field of weather forecasting were looked back， and the latest progress in combining deep learning technologies with NWP was summarized and analyzed. Finally， the future development directions and research focuses were prospected to provide a certain reference for future deep learning research in the field of weather forecasting.
To meet the needs of data sharing in the context of digitalization currently， and take into account the necessity of protecting private data security at the same time， a blockchain smart contract private data authorization method based on TrustZone was proposed. The blockchain system is able to realize data sharing in different application scenarios and meet regulatory requirements， and a secure isolation environment was provided by TrustZone Trusted Execution Environment （TEE） technology for private computing. In the integrated system， the uploading of private data was completed by the regulatory agency， the plaintext information of the private data was obtained by other business nodes only after obtaining the authorization of the user. In this way， the privacy and security of the user were able to be protected. Aiming at the problem of limited memory space in the TrustZone architecture during technology fusion， a privacy set intersection algorithm for small memory conditions was proposed. In the proposed algorithm， the intersection operation for large-scale datasets was completed on the basis of the ??grouping computing idea. The proposed algorithm was tested with datasets of different orders of magnitude. The results show that the time and space consumption of the proposed algorithm fluctuates in a very small range and is relatively stable. The variances are 1.0 s2 and 0.01 MB2 respectively. When the order of magnitudes of the dataset is increased， the time consumption is predictable. Furthermore， using a pre-sorted dataset can greatly improve the algorithm performance.
Aiming at the problems of the existing power load forecasting models such as heavy modeling workload， insufficient spatiotemporal joint representation， and low forecasting accuracy， a Short-Term power Load Forecasting model based on Graph Convolutional Network （GCN） combining Long Short-Term Memory （LSTM） network and Self-attention mechanism （GCNLS-STLF） was proposed. Firstly， original multi-dimensional time series data was transformed into a power load graph containing the correlation between series by using LSTM and self-attention mechanism. Then， the features were extracted from the power load graph by GCN， LSTM and Graph Fourier Transform （GFT）. Finally， a full connection layer was used to reconstruct features， and the residual was used to forecast the power load for multiple times to enhance the expression ability of the original power load data. The short-term power load forecasting experimental results on real historical power load data of power stations in Morocco and Panama showed that compared with Support Vector Machine （SVM）， LSTM， mixed model CNN-LSTM and CNN-LSTM based on attention （CNN-LSTM-attention）， the Mean Absolute Percentage Error （MAPE） of GCNLS-STLF was reduced by 1.94， 0.90， 0.49 and 0.37 percentage points， respectively， on the entire Morocco power load test set； the MAPE of GCNLS-STLF on the Panama power load test dataset decreased by 1.39， 0.94， 0.38 and 0.29 percentage points respectively in March and 1.40， 0.99， 0.35 and 0.28 percentage points respectively in June. Experimental results show that GCNLS-STLF can effectively extract key features of power load， and forecasting effects are satisfactory.
Aiming at the problem that most trajectory similarity measurement algorithms cannot distinguish the trajectories with opposite directions， a three-dimensional Triangulation Division （3TD） algorithm based on three-dimensional space area division was proposed. Firstly， the absolute time series of the trajectory set was transformed into the relative time series according to the time conversion rules of the 3TD algorithm. Then， in the three-dimensional space coordinate system composed of three elements of longitude， latitude， and time， the area between trajectories were divided into several non-overlapping triangles by partitioning rules， and the areas of the triangles were accumulated and the trajectory similarity was calculated. Finally， the proposed algorithm was compared with the Longest Common SubSequence （LCSS） algorithm and Triangle Division （TD） algorithm on the randomly sampled trajectory dataset collected from the ship Automatic Identification System （AIS）. Experimental results show that the accuracy of the 3TD algorithm reaches 100%. At the same time， the proposed algorithm can also maintain accurate measurement results and high operation efficiency on massive datasets and datasets with partial missing trajectory points， which can better adapt to the similarity measurement of divergent trajectories.
The operating cost of the port can be greatly reduced and economic benefits can be greatly improved by the automatic ship loading system， which is an important part of the smart port construction. Hatch recognition is the primary link in the automatic ship loading task， and its success rate and recognition accuracy are important guarantees for the smooth progress of subsequent tasks. Collected ship point cloud data is often missing due to issues such as the number and angle of the port lidars. In addition， the geometric information of the hatch cannot be expressed accurately by the collected point cloud data because there is often a large amount of material accumulation near the hatch. The recognition success rate of the existing algorithm is significantly reduced due to the frequent problems in the actual ship loading operation of the port mentioned above， which has a negative impact on the automatic ship loading operation. Therefore， it is urgent to improve the success rate of hatch recognition in the case of material interference or incomplete hatch data in the ship point cloud. A hatch recognition algorithm of bulk cargo ship based on incomplete point cloud normal filtering and compensation was proposed， by analyzing the ship structural features and point cloud data collected during the automatic ship loading process. Experiments were carried out to verify that the recognition success rate and recognition accuracy are improved compared with Miao’s and Li’s hatch recognition algorithms. The experimental results show that the proposed algorithm can not only filter out the material noise in the hatch， but also compensate for the missing data， which can effectively improve the hatch recognition effect.
The portfolio problem is a hot issue in the field of quantitative trading. An Integrated Deep Reinforcement Learning Portfolio Model （IDRLPM） was proposed to address the shortcomings of existing deep reinforcement learning-based portfolio models that cannot achieve adaptive trading strategies and effectively utilize supervised information. Firstly， multi-agent method was used to construct multiple base agents and design reward functions with different trading styles to represent different trading strategies. Secondly， integrated learning method was used to fuse the features of strategy network of the base agents to obtain the integrated agent adaptive to market environment. Then， a trend prediction network based on Convolutional Block Attention Module （CBAM） was embedded in the integrated agent， and the output of the trend prediction network guided integrated strategy network to adaptively select the proportion of trades. Finally， under the alternating iterative training of supervised deep learning and reinforcement learning， IDRLPM effectively utilized supervised information from training data to enhance model profitability. The Sharpe Ratio （SR） of IDRLPM reaches 1.87 and 1.88， and the Cumulative Return （CR） reaches 2.02 and 1.34 in Shanghai Stock Exchange （SSE） 50 constituent stocks and China Securities Index （CSI） 500 constituent stocks； compared with the Ensemble Deep Reinforcement Learning （EDRL） trading model， the SR improves by 105% and 55%， and the CR improves by 124% and 79%. The experimental results show that IDRLPM can effectively solve the portfolio problem.
Decoding motor imagery EEG （ElectroEncephaloGraphy） signal is one of the crucial techniques for building Brain Computer Interface （BCI） system. Due to EEG signal’s high cost of acquisition， large inter-subject discrepancy， and characteristics of strong time variability and low signal-to-noise ratio， constructing cross-subject pattern recognition methods become the key problem of such study. To solve the existing problem， a cross-subject dynamic multi-domain adversarial learning method was proposed. Firstly， the covariance matrix alignment method was used to align the given EEG samples. Then， a global discriminator was adapted for marginal distribution of different domains， and multiple class-wise local discriminators were adapted to conditional distribution for each class. The self-adaptive adversarial factor for multi-domain discriminator was automatically learned during training iterations. Based on dynamic multi-domain adversarial learning strategy， the Dynamic Multi-Domain Adversarial Network （DMDAN） model could learn deep features with generalization ability between cross-subject domains. Experimental results on public BCI Competition IV 2A and 2B datasets show that， DMDAN model improves the ability of learning domain-invariant features， achieving 1.80 and 2.52 percentage points higher average classification accuracy on dataset 2A and dataset 2B compared with the existing adversarial learning method Deep Representation Domain Adaptation （DRDA）. It can be seen that DMDAN model improves the decoding performance of cross-subject motor imagery EEG signals， and has generalization ability on different datasets.
To address the problems of limited information expression， imbalance， and dynamic spatio-temporal characteristics of accident data， an accident prediction model fusing heterogeneous traffic situations was proposed. In which， the semantic enhancement was completed by the spatio-temporal state aggregation module through traffic events and weather features representing dynamic traffic situations， and the historical multi-period spatio-temporal states of four types of regions （single region， adjacent region， similar region， and global region） were aggregated； the dynamic local and global spatio-temporal characteristics of accident data were captured by the spatio-temporal relation capture module from both micro- and macro-perspectives； and the multi-region and multi-angle spatio-temporal states were further fused by the spatio-temporal data fusion module， and the accident prediction task in the next period was realized. Experimental results on five city datasets of US-Accident demonstrate that the average F1-scores of the proposed model for accident， non-accident， and weighted average samples are 85.6%， 86.4%， and 86.6% respectively， which are improved by 14.4%， 5.6%， and 9.3% in the three metrics compared to the traditional Feedforward Neural Network （FNN）， indicating that the proposed model can effectively suppresses the influence of accident data imbalance on experimental results. Constructing an efficient accident prediction model helps to analyze the safety situation of road traffic， reduce the occurrence of traffic accidents and improve the traffic safety.
When the Unmanned Aerial Vehicle （UAV） cluster attacks ground targets， it will be divided into two formations： a strike UAV cluster that attacks the targets and a auxiliary UAV cluster that pins down the enemy. When auxiliary UAVs choose the action strategy of aggressive attack or saving strength， the mission scenario is similar to a public goods game where the benefits to the cooperator are less than those to the betrayer. Based on this， a decision method for cooperative combat of UAV clusters based on deep reinforcement learning was proposed. First， by building a public goods game based UAV cluster combat model， the interest conflict problem between individual and group in cooperation of intelligent UAV clusters was simulated. Then， Muti-Agent Deep Deterministic Policy Gradient （MADDPG） algorithm was used to solve the most reasonable combat decision of the auxiliary UAV cluster to achieve cluster victory with minimum loss cost. Training and experiments were performed under conditions of different numbers of UAV. The results show that compared to the training effects of two algorithms — IDQN （Independent Deep Q-Network） and ID3QN （Imitative Dueling Double Deep Q-Network）， the proposed algorithm has the best convergence， its winning rate can reach 100% with four auxiliary UAVs， and it also significantly outperforms the comparison algorithms with other UAV numbers.
To address the issues of difficult prediction of landslide displacement and difficulty in selecting influencing factors， a model combining Double Moving Average （DMA）， Variational Modal Decomposition （VMD）， Improved Gray Wolf Optimizer （IGWO） algorithm and Support Vector Regression （SVR） was proposed for landslide displacement prediction. Firstly， DMA was used to extract the trend and periodic terms of landslide displacement， and polynomial fitting was used to predict the trend term. Secondly， the influencing factors of the landslide periodic term were classified， and VMD was used to decompose the original factor sequence to obtain the optimal sequence. Then， a grey wolf optimizer algorithm combining SVR with an improved Circle-based multi-tactic， called CTGWO-SVR （Circle Tactics Grey Wolf Optimizer with SVR）， was proposed to predict the landslide periodic term. Finally， the cumulative displacement prediction sequence was obtained using a time series additive model， and the model was evaluated using post validation difference verification and small probability error in grey prediction. Experimental results show that compared with GA （Genetic Algorithm）-SVR and GWO-SVR models， CTGWO-SVR has higher prediction accuracy with a fitting degree of 0.979， and the Root Mean Square Error （RMSE） reduces by 51.47% and 59.25%， respectively. The model evaluation accuracy is level one， which can meet the real-time and accuracy requirements of landslide prediction.
In order to better meet the accuracy and timeliness requirements of Chinese food dish recognition， a new type of dish recognition network was designed. The original YOLOv5 model was pruned by combining Supermask method and structured channel pruning method， and lightweighted finally by Int8 quantization technology. This ensured that the proposed model could balance accuracy and speed in dish recognition， achieving a good trade-off while improving the model portability. Experimental results show that the proposed model achieves a mean Average Precision （mAP） of 99.00% and an average recognition speed of 59.54 ms /frame at an Intersection over Union （IoU） of 0.5， which is 20 ms/frame faster than that of the original YOLOv5 model while maintaining the same level of accuracy. In addition， the new dish recognition network was ported to the Renesas RZ/G2L board by Qt. Based on this， an intelligent service system was constructed to realize the whole process of ordering， generating orders， and automatic meal distribution. A theoretical and practical foundation was provided for the future construction and application of truly intelligent service systems in restaurants.
Automatic inspection of concrete bridge health based on wall-climbing robot is an effective way to promote intelligent bridge management and maintenance， moreover reasonable path planning is particularly important for the robot to obtain comprehensive detection data. Aiming at the engineering practical problem of weight limitation of the wall-climbing robot power supply and the difficulty of energy supplement during inspection， the inspection scenarios of bridge components such as main beams and high piers were fully considered， the energy consumption index was taken as the objective function of performance evaluation optimization and corresponding constraint conditions were established， and a full coverage path planning evaluation model was proposed. An Improved Grey Wolf Optimization （IGWO） algorithm was proposed to solve the problem that traditional Grey Wolf Optimization （GWO） algorithm is prone to fall into local optimum. The IGWO algorithm improved the characteristics of initial gray wolf population which was difficult to maintain relatively uniform distribution in the search space by K-Means clustering. The nonlinear convergence factor was used to improve the local development ability and global search performance of the algorithm. Combining with the idea of individual superiority of particle swarm optimization， the position updating formula was improved to enhance the model solving ability of the algorithm. Algorithm simulation and comparison experiment results show that IGWO has better stability compared with GWO， Different Evolution （DE） and Genetic Algorithm （GA）， IGWO reduces energy consumption by 10.2% - 16.7%， decreases iterations by 19.3% - 36.9% and solving time by 12.8% - 32.3%， reduces path repetition rate by 0.23 - 1.91 percentage points， and reduces path length by 1.6% - 11.0%.
Early detection and timely intervention of cognitive impairment are crucial to slow down the progress of the disease. The ElectroEncephaloGraphy （EEG） signal has become an important tool for the investigation of biomarkers of cognitive diseases due to its high temporal resolution and easy acquisition. Compared with the traditional biomarker recognition method， the machine learning method has higher accuracy and better stability for the recognition and classification of cognitive impairment based on EEG signals. Aiming at the relevant research literature on the recognition and classification of cognitive impairment based on EEG signals in the past three years， firstly， from the perspectives of five categories of EEG features commonly used in the recognition and classification of cognitive impairment， including time domain， frequency domain， combination of time and frequency domains， nonlinear dynamics， functional connectivity and brain network， more representative EEG features were found. Then， the currently commonly used classification methods based on machine learning and deep learning， such as Support Vector Machine （SVM）， Linear Discriminant Analysis （LDA）， K-Nearest Neighbor （KNN） and Artificial Neural Network （ANN）， as well as their performance were summarized. Finally， the current problems in different kinds of studies were analyzed， and the future research directions in this field were prospected， thereby providing reference for the follow-up research on the recognition and classification of cognitive impairment based on EEG signals.
Concerning the periodicity and time-varying characteristics of air traffic system operation， a flight conflict network situation prediction method based on Optimal Training Set Online Fuzzy-Least Squares Support Vector Machine （OTSOF-LSSVM） was proposed by combining complex network theory and fuzzy Least Squares Support Vector Machine （LSSVM）. Firstly， a flight conflict network model was constructed based on the three-dimensional velocity obstacle method， and conflicts were judged according to the positions， headings and velocities of the aircrafts. Then， the evolution time series of topology indicators of flight conflict network were analyzed to obtain the optimal training set which consisted of samples related to the predicted moment in time and distance. Finally， a prediction model was obtained by online fuzzy LSSVM training， and the idea of block matrix was used to simplify the updating process and improve the efficiency of the algorithm. Experimental results show that the proposed method can quickly and accurately predict the air situation， provide reference for controllers to master the development of air traffic， and assist the pre-deployment of conflicts.
The task of spatio-temporal sequence prediction has a wide range of applications in the fields such as transportation， meteorology and smart city. It is necessary to learn the spatio-temporal characteristics of different data with the combination of external factors such as precipitation and temperature when making station wind speed predictions， which is one of the main tasks in meteorological forecasting. The irregular distribution of meteorological stations and the inherent intermittency of the wind itself bring the challenge of achieving wind speed prediction with high accuracy. In order to consider the influence of multi-site spatial distribution on wind speed to obtain accurate and reliable prediction results， a Graph-based Dynamic Switch-Attention Network （Graph-DSAN） wind speed prediction model was proposed. Firstly， the distances between different sites were used to reconstruct the connection of them. Secondly， the process of local sampling was used to model adjacency matrices of different sampling sizes to achieve the aggregation and transmission of the information between neighbor nodes during the graph convolution process. Thirdly， the results of the graph convolution processed by Spatio-Temporal Position Encoding （STPE） were fed into the Dynamic Attention Encoder （DAE） and Switch-Attention Decoder （SAD） for dynamic attention computation to extract the spatio-temporal correlations. Finally， a multi-step prediction was formed by using autoregression. In experiments on wind speed prediction on 15 sites data in New York State， the designed model was compared with ConvLSTM， Graph Multi-Attention Network （GMAN）， Spatio-Temporal Graph Convolutional Network （STGCN）， Dynamic Switch-Attention Network （DSAN） and Spatial-Temporal Dynamic Network （STDN）. The results show that the Root Mean Square Error （RMSE） of 12 h prediction of Graph-DSAN model is reduced by 28.2%， 6.9%， 27.7%， 14.4% and 8.9% respectively， verifying the accuracy of Graph-DSAN in wind speed prediction.
