The existing image aesthetic quality evaluation methods widely use Convolution Neural Network （CNN） to extract image features. Limited by the local receptive field mechanism， it is difficult for CNN to extract global features from a given image， thereby resulting in the absence of aesthetic attributes like global composition relations， global color matching and so on. In order to solve this problem， an image aesthetic quality evaluation method based on SSViT （Self-Supervised Vision Transformer） model was proposed. Self-attention mechanism was utilized to establish long-distance dependencies among local patches of the image and to adaptively learn their correlations， and extracted the global features so as to characterize the aesthetic attributes. Meanwhile， three tasks of perceiving the aesthetic quality， namely classifying image degradation， ranking image aesthetic quality， and reconstructing image semantics， were designed to pre-train the vision Transformer in a self-supervised manner using unlabeled image data， so as to enhance the representation of global features. The experimental results on AVA （Aesthetic Visual Assessment） dataset show that the SSViT model achieves 83.28%， 0.763 4， 0.746 2 on the metrics including evaluation accuracy， Pearson Linear Correlation Coefficient （PLCC） and SRCC （Spearman Rank-order Correlation Coefficient）， respectively. These experimental results demonstrate that the SSViT model achieves higher accuracy in image aesthetic quality evaluation.
For the problem of gait stability control for continuous linear walking of a biped robot， a Soft Actor-Critic （SAC） gait control algorithm based on maximum entropy Deep Reinforcement Learning （DRL） was proposed. Firstly， without accurate robot dynamic model built in advance， all parameters were derived from joint angles without additional sensors. Secondly， the cosine similarity method was used to classify experience samples and optimize the experience replay mechanism. Finally， reward functions were designed based on knowledge and experience to enable the biped robot continuously adjust its attitude during the linear walking training process， and the reward functions ensured the robustness of straight walking. The proposed method was compared with other DRL methods such as PPO （Proximal Policy Optimization） and TRPO （Trust Region Policy Optimization） in Roboschool simulation environment. The results show that the proposed method not only achieves fast and stable linear walking of the biped robot， but also has better algorithmic robustness.
In edge computing， computing resources are deployed at edge computing nodes closer to end users， and selecting the appropriate edge computing node deployment location from the candidate locations can enhance the node capacity and user Quality of Service （QoS） of edge computing services. However， there is less research on how to place edge computing nodes to reduce the cost of edge computing. In addition， there is no edge computing node deployment algorithm that can maximize the robustness of edge services while minimizing the deployment cost of edge computing nodes under the constraints of QoS factors such as the delay of edge services. To address the above issues， firstly， the edge computing node placement problem was transformed into a minimum dominating set problem with constraints by building a model about computing nodes， user transmission delay， and robustness. Then， the concept of overlapping domination was proposed， so that the network robustness was measured on the basis of overlapping domination， and an edge computing node placement algorithm based on overlapping domination was designed， namely CHAIN （edge server plaCement algoritHm based on overlAp domINation）. Simulation results show that CHAIN can reduce the system latency by 50.54% and 50.13% compared to the coverage oriented approximate algorithm and base station oriented random algorithm， respectively.
How to allocate spectra to users efficiently and improve the revenue of providers are popular research topics recently. To address the problem of low revenue of providers in spectrum combinatorial auctions， Random Walk for Spectrum Combinatorial Auctions （RWSCA） mechanism was designed to maximize the revenue of spectrum providers by combining the characteristics of asymmetric distribution of user valuations. First， the idea of virtual valuation was introduced， the random walk algorithm was used to search for a set of optimal parameters in the parameter space， and the valuations of buyers were linearly mapped according to the parameters. Then， VCG （Vickrey-Clarke-Groves） mechanism based on virtual valuation was run to determine the users who won the auction and calculate the corresponding payments. Theoretical analysis proves that the proposed mechanism is incentive compatible and individually rational. In spectrum combinatorial auction simulation experiments， the RWSCA mechanism increases the provider’s revenue by at least 16.84%.
There are many Dynamic Multiobjective Optimization Problems （DMOPs） in real life. For such problems， when the environment changes， Dynamic Multi-Objective Evolutionary Algorithm （DMOEA） is required to track the Pareto Front （PF） or Pareto Set （PS） quickly and accurately under the new environment. Aiming at the problem of poor performance of the existing algorithms on population prediction， a dynamic multi-objective optimization algorithm based on Weight Vector Clustering Prediction （WVCP） was proposed. Firstly， the uniform weight vectors were generated in the target space， and the individuals in the population were clustered. According to the clustering results， the distribution of the population was analyzed. Secondly， a time series was established for the center points of clustered individuals. For the same weight vector， the corresponding coping strategies were adopted to supplement individuals according to different clustering situations. If there were cluster centers at all adjacent moments， the difference model was used to predict individuals in the new environment. If there was no cluster center at a certain moment， the centroid of the cluster centers of adjacent weight vectors was used as the cluster center at that moment， and then the difference model was used to predict individuals. In this way， the problem of poor population distribution was solved effectively， and the accuracy of prediction was improved at the same time. Finally， the introduction of individual supplement strategy was beneficial to make full use of historical information. In order to verify the performance of the proposed algorithm， simulation comparison of this algorithm and four representative algorithms was carried out. Experimental results show that the proposed algorithm can solve DMOPs well.
Unsupervised relation extraction aims to extract the semantic relations between entities from unlabeled natural language text. Currently， unsupervised relation extraction models based on Variational Auto-Encoder （VAE） architecture provide supervised signals to train model through reconstruction loss， which offers a new idea to complete unsupervised relation extraction tasks. Focusing on the issue that this kind of models cannot understand contextual information effectively and relies on dataset inductive biases， a Prompt-based learning based Unsupervised Relation Extraction （PURE） model was proposed， including a relation extraction module and a link prediction module. In the relation extraction module， a context-aware Prompt template function was designed to fuse the contextual information， and the unsupervised relation extraction task was converted into a mask prediction task， so as to make full use of the knowledge obtained during pre-training phase to extract relations. In the link prediction module， supervised signals were provided for the relation extraction module by predicting the missing entities in the triples to assist model training. Extensive experiments on two public real-world relation extraction datasets were carried out. The results show that PURE model can use contextual information effectively and does not rely on dataset inductive biases， and has the evaluation index B-cubed F1 improved by 3.3 percentage points on NYT dataset compared with the state-of-the-art VAE architecture-based model UREVA （Variational Autoencoder-based Unsupervised Relation Extraction model）.
Ride-hailing has become a popular choice for people to travel due to its convenience and speed， how to efficiently dispatch the appropriate orders to deliver passengers to the destination is a research hotspot today. Many researches focus on training a single agent， which then uniformly distributies orders， without the vehicle itself being involved in the decision making. To solve the above problem， a multi-agent reinforcement learning algorithm based on shared attention， named SARL （Shared Attention Reinforcement Learning）， was proposed. In the algorithm， the order dispatching problem was modeled as a Markov decision process， and multi-agent reinforcement learning was used to make each agent become a decision-maker through centralized training and decentralized execution. Meanwhile， the shared attention mechanism was added to make the agents share information and cooperate with each other. Comparison experiments with Random matching （Random）， Greedy algorithm （Greedy）， Individual Deep-Q-Network （IDQN） and Q-learning MIXing network （QMIX） were conducted under different map scales， different number of passengers and different number of vehicles. Experimental results show that the SARL algorithm achieves optimal time efficiency in three different scale maps （100×100， 10×10 and 500×500） for fixed and variable vehicle and passenger combinations， which verifies the generalization performance and stable performance of the SARL algorithm. The SARL algorithm can optimize the matching of vehicles and passengers， reduce the waiting time of passengers and improve the satisfaction of passengers.
Moving object detection aims to separate the background and foreground of the video， however， the commonly used low-rank factorization methods are often difficult to comprehensively deal with the problems of dynamic background and intermittent motion. Considering that the skewed noise distribution after background subtraction has potential background correction effect， a moving object detection model based on the reliability low-rank factorization and generalized diversity difference was proposed. There were three steps in the model. Firstly， the peak position and the nature of skewed distribution of the pixel distribution in the time dimension were used to select a sub-sequence without outlier pixels， and the median of this sub-sequence was calculated to form the static background. Secondly， the noise after static background subtraction was modeled by asymmetric Laplace distribution， and the modeling results based on spatial smoothing were used as reliability weights to participate in low-rank factorization to model comprehensive background （including dynamic background）. Finally， the temporal and spatial continuous constraints were adopted in proper order to extract the foreground. Among them， for the temporal continuity， the generalized diversity difference constraint was proposed， and the expansion of the foreground edge was suppressed by the difference information of adjacent video frames. Experimental results show that， compared with six models such as PCP（Principal Component Pursuit）， DECOLOR（DEtecting Contiguous Outliers in the Low-Rank Representation）， LSD（Low-rank and structured Sparse Decomposition）， TVRPCA（Total Variation regularized Robust Principal Component Analysis）， E-LSD（Extended LSD） and GSTO（Generalized Shrinkage Thresholding Operator）， the proposed model has the highest F-measure. It can be seen that this model can effectively improve the detection accuracy of foreground in complex scenes such as dynamic background and intermittent motion.
Abductive reasoning is an important task in Natural Language Inference （NLI）， which aims to infer reasonable process events （hypotheses） between the given initial observation event and final observation event. Earlier studies independently trained the inference model from each training sample； recently， mainstream studies have considered the semantic correlation between similar training samples and fitted the reasonableness of the hypotheses with the frequency of these hypotheses in the training set， so as to describe the reasonableness of the hypotheses in different environments more accurately. On this basis， while describing the reasonableness of the hypotheses， the difference and relativity constraints between reasonable hypotheses and unreasonable hypotheses were added， thereby achieving the purpose of two-way characterization of the reasonableness and unreasonableness of the hypotheses， and the overall relativity was modeled through many-to-many training. In addition， considering the difference of the word importance in the process of event expression， an attention module was constructed for different words in the samples. Finally， an abductive reasoning model based on attention balance list was formed. Experimental results show that compared with the L2R2 （Learning to Rank for Reasoning） model， the proposed model has the accuracy and AUC improved by about 0.46 and 1.36 percentage points respectively on the mainstream abductive inference dataset Abductive Reasoning in narrative Text （ART） ， which prove the effectiveness of the proposed model.
The performance of the recommendation systems is restricted by data sparsity， and the accuracy of prediction can be effectively improved by reasonably filling the missing values in the rating matrix. Therefore， a new algorithm named Recommendation Rating Prediction based on Concept Lattice Reduction （RRP-CLR） was proposed. RRP-CLR algorithm was composed of nearest neighbor selection module and rating prediction module， which were respectively responsible for generating reduced nearest neighbor set and realizing rating prediction and recommendation. In the nearest neighbor selection module， the user rating matrix was transformed into a binary matrix， which was regarded as the user interest formal background. Then the formal background reduction rules and concept lattice redundancy concept deletion rules were proposed to improve the efficiency of generating reduced nearest neighbors. In the rating prediction module， a new user similarity calculation method was proposed to eliminate the impact of rating deviations caused by user’s subjective factors on similarity calculation. When the number of common rating items of two users was less than a specific threshold， the similarity was scaled appropriately to make the similarity between users more consistent with the real situation. Experimental results show that compared with PC?UCF （User-based Collaborative Filtering recommendation algorithm based on Pearson Coefficient） and RRP-UICL （Recommendation Rating Prediction method based on User Interest Concept Lattice）， RRP-CLR algorithm has smaller Mean Absolute Error （MAE） and Root Mean Squared Error （RMSE）， and better rating prediction accuracy and stability.
Most of the Multi-objective Optimization Problems （MOP） in real life are Dynamic Multi-objective Optimization Problems （DMOP）， and the objective function， constraint conditions and decision variables of such problems may change with time， which requires the algorithm to quickly adapt to the new environment after the environment changes， and guarantee the diversity of Pareto solution sets while converging to the new Pareto frontier quickly. To solve the problem， an Adaptive Prediction Dynamic Multi-objective Optimization Algorithm based on New Evaluation Index （NEI-APDMOA） was proposed. Firstly， a new evaluation index better than crowding was proposed in the process of population non-dominated sorting， and the convergence speed and population diversity were balanced in different stages， so as to make the convergence process of population more reasonable. Secondly， a factor that can judge the strength of environmental changes was proposed， thereby providing valuable information for the prediction stage and guiding the population to better adapt to environmental changes. Finally， three more reasonable prediction strategies were matched according to environmental change factor， so that the population was able to respond to environmental changes quickly. NEI-APDMOA， DNSGA-Ⅱ-A （Dynamic Non-dominated Sorting Genetic Algorithm-Ⅱ-A）， DNSGA-Ⅱ-B （Dynamic Non-dominated Sorting Genetic Algorithm-Ⅱ-B） and PPS （Population Prediction Strategy） algorithms were compared on nine standard dynamic test functions. Experimental results show that NEI-APDMOA achieves the best average Inverted Generational Distance （IGD） value， average SPacing （SP） value and average Generational Distance （GD） value on nine， four and eight test functions respectively， and can respond to environmental changes faster.
The detection precision is low when the diatom training sample size is small， so a Multi-scale Multi-head Self-attention （MMS） and Online Hard Example Mining （OHEM） based few-shot diatom detection model， namely MMSOFDD was proposed based on the few-shot object detection model Two-stage Fine-tuning Approach （TFA）. Firstly， a Transformer-based feature extraction network Bottleneck Transformer Network-101 （BoTNet-101） was constructed by combining ResNet-101 with a multi-head self-attention mechanism to make full use of the local and global information of diatom images. Then， multi-head self-attention was improved to MMS， which eliminated the limitation of processing single object scale of the original multi-head self-attention. Finally， OHEM was introduced to the model predictor， and the diatoms were identified and localized. Ablation and comparison experiments between the proposed model and other few-shot object detection models were conducted on a self-constructed diatom dataset. Experiment results show that the mean Average Precision （mAP） of MMSOFDD is 69.60%， which is improved by 5.89 percentage points compared with 63.71% of TFA； and compared with 61.60% and 60.90% the few-shot object detection models Meta R-CNN and Few-Shot In Wild （FSIW）， the proposed model has the mAP improved by 8.00 percentage points and 8.70 percentage points respectively. Moreover， MMSOFDD can effectively improve the detection precision of the detection model for diatoms with small size of diatom training samples.
Relation extraction aims to extract the semantic relationships between entities from the text. As the upper-level task of relation extraction， entity recognition will generate errors and spread them to relation extraction， resulting in cascading errors. Compared with entities， entity boundaries have small granularity and ambiguity， making them easier to recognize. Therefore， a relationship extraction method based on entity boundary combination was proposed to realize relation extraction by skipping the entity and combining the entity boundaries in pairs. Since the boundary performance is higher than the entity performance， the problem of error propagation was alleviated； in addition， the performance was further improved by adding the type features and location features of entities through the feature combination method， which reduced the impact caused by error propagation. Experimental results on ACE 2005 English dataset show that the proposed method outperforms the table-sequence encoders method by 8.61 percentage points on Macro average F1-score.
In order to solve the problem that static attribute reduction cannot update attribute reduction efficiently when the number of attributes in the set-valued decision information system changes continuously， an incremental attribute reduction method with knowledge granularity as heuristic information was proposed. Firstly， the related concepts of the set-valued decision information system were introduced， then the definition of knowledge granularity was introduced， and its matrix representation method was extended to this system. Secondly， the update mechanism of incremental reduction was analyzed， and an incremental attribute reduction method was designed on the basis of knowledge granularity. Finally， three different datasets were selected for the experiments. When the number of attributes of the three datasets increased from 20% to 100%， the reduction time of the traditional non-incremental method was 54.84 s， 108.01 s， and 565.93 s respectively， and the reduction time of the incremental method was 7.57 s， 4.85 s， and 50.39 s respectively. Experimental results demonstrate that the proposed incremental method is more faster than the non-incremental method under the condition that the accuracy of attribute reduction is not affected.
To solve various issues faced by Electronic Medical Record （EMR） sharing， such as centralized data provider， passive patient data management， low interoperability efficiency and malicious dissemination， a blockchain-based EMR secure sharing method was proposed. Firstly， a more secure and efficient Universal Designated Verifier Signature Proof （UDVSP） scheme based on the commercial cryptography SM2 digital signature algorithm was proposed. Then， a smart contract with functionalities of uploading， verification， retrieval and revocation was designed， and a blockchain-based EMR secure sharing system was constructed. Finally， the feasibilities of UDVSP scheme and sharing system were demonstrated through security analysis and performance analysis. The security analysis shows that the proposed UDVSP is probably secure. The performance analysis shows that compared with existing UDVSP/UDVS schemes， the proposed UDVSP scheme saves the computation cost at least 87.42% and communication overhead at least 93.75%. The prototype of blockchain smart contract further demonstrates the security and efficiency of the sharing system.
Federated Learning （FL） is a novel privacy?preserving learning paradigm that can keep users' data locally. With the progress of the research on FL， the shortcomings of FL， such as single point of failure and lack of credibility， are gradually gaining attention. In recent years， the blockchain technology originated from Bitcoin has achieved rapid development， which pioneers the construction of decentralized trust and provides a new possibility for the development of FL. The existing research works on blockchain?based FL were reviewed， the frameworks for blockchain?based FL were compared and analyzed. Then， key points of FL solved by the combination of blockchain and FL were discussed. Finally， the application prospects of blockchain?based FL were presented in various fields， such as Internet of Things （IoT）， Industrial Internet of Things （IIoT）， Internet of Vehicles （IoV） and medical services.
In the few-shot object detection task based on transfer learning， due to the lack of attention mechanism to focus on the object to be detected in the image， the ability of the existing models to suppress the surrounding background area of the object is not strong， and in the process of transfer learning， it is usually necessary to fine-tune the meta-features to achieve cross-domain sharing， which will cause meta-feature shift， and lead to the decline of the model’s ability to detect large-sample images. To solve the above problems， an improved meta-feature transfer model Up-YOLOv3 based on the attention mechanism and the meta-feature secondary reweighting mechanism was proposed. Firstly， the Convolution Block Attention Module （CBAM）-based attention mechanism was introduced in the original meta-feature transfer model Base-YOLOv2， so that the feature extraction network was able to focus on the object area in the image and pay attention to the detailed features of the image object class， thereby improving the model’s detection performance for few-shot image objects. Then， the Squeeze and Excitation-Secondary Meta-Feature Reweighting （SE-SMFR） module was introduced to reweight the meta-features of the large-sample image for the second time in order to obtain the secondary reweighted meta-features， so that the model was not only able to improve the performance of few-shot object detection， but also able to reduce the weight shift of the meta-feature information of the large-sample image. Experimental results on PASCAL VOC2007/2012 dataset show that， compared with Base-YOLOv2， Up-YOLOv3 has the detection mean Average Precision （mAP） for few-shot object images increased by 2.3 to 9.1 percentage points； compared with the original meta-feature transfer model based on YOLOv3 Base-YOLOv3， mAP for large-sample object images increased by 1.8 to 2.4 percentage points. It can be seen that the improved model has good generalization ability and robustness for both large-sample images and few-shot images of different classes.
Aiming at the problems that current valve identification methods in industry have high missed rate of overlapping targets， low detection precision， poor target encapsulation degree and inaccurate positioning of circle center， a valve identification method based on double detection was proposed. Firstly， data enhancement was used to expand the samples in a lightweight way. Then， Spatial Pyramid Pooling （SPP） and Path Aggregation Network （PAN） were added on the basis of deep convolutional network. At the same time， the anchor boxes were adjusted and the loss function was improved to extract the valve prediction boxes. Finally， the Circle Hough Transform （CHT） method was used to secondarily identify the valves in the prediction boxes to accurately identify the valve regions. The proposed method was compared with the original You Only Look Once （YOLO）v3， YOLOv4， and the traditional CHT methods， and the detection results were evaluated by jointly using precision， recall and coincidence degree. Experimental results show that the average precision and recall of the proposed method reaches 97.1% and 94.4% respectively， 2.9 percentage points and 1.8 percentage points higher than those of the original YOLOv3 method respectively. In addition， the proposed method improves the target encapsulation degree and location accuracy of target center. The proposed method has the Intersection Over Union （IOU） between the corrected frame and the real frame reached 0.95， which is 0.05 higher than that of the traditional CHT method. The proposed method improves the success rate of target capture while improving the accuracy of model identification， and has certain practical value in practical applications.
Aiming at the problem of spectrum allocation based on maximizing network benefit in cognitive radio and the fact that Manta Ray Foraging Optimization （MRFO） algorithm is difficult to solve the problem of spectrum allocation， a Discrete Manta Ray Foraging Optimization （DMRFO） algorithm was proposed.Considering the pro-1 characteristic of spectrum allocation problem in engineering， firstly， MRFO algorithm was discretely binarized based on the Sigmoid Function （SF） discrete method. Secondly， the XOR operator and velocity adjustment factor were used to guide the manta rays to adaptively adjust the position of next time to the optimal solution according to the current velocity. Then， the binary spiral foraging was carried out near the global optimal solution to avoid the algorithm from falling into the local optimum. Finally， the proposed DMRFO algorithm was applied to solve the spectrum allocation problem. Simulation results show that the convergence mean and standard deviation of the network benefit when using DMRFO algorithm to allocate spectrum are 362.60 and 4.14 respectively， which are significantly better than those of Discrete Artificial Bee Colony （DABC） algorithm， Binary Particle Swarm Optimization （BPSO） algorithm and Improved Binary Particle Swarm Optimization （IBPSO） algorithm.
In order to solve the problem that the algorithms of publication venue recommendation always consider the text topics or the author’s history of publications separately， which leads to the low accuracy of publication venue recommendation results， a contribution recommendation algorithm of academic journal based on author preferences was proposed. In this algorithm， not only the text topics and the author’s history of publications were used together， but also the potential relationship between the academic focuses of publication venues and time were explored. Firstly， the Latent Dirichlet Allocation （LDA） topic model was used to extract the topic information of the paper title. Then， the topic-journal and time-journal model diagrams were established， and the Large-scale Information Network Embedding （LINE） model was used to learn the embedding of graph nodes. Finally， the author’s subject preferences and history of publication records were fused to calculate the journal composite scores， and the publication venue recommendation for author to contribute was realized. Experimental results on two public datasets， DBLP and PubMed， show that the proposed algorithm has better recall under different list lengths of recommended publication venues compared to six algorithms such as Singular Value Decomposition （SVD）， DeepWalk and Non-negative Matrix Factorization （NMF）. The proposed algorithm maintains high accuracy while requiring less information from papers and knowledge bases， and can effectively improve the robustness of publication venue recommendation algorithm.
In view of the problems of ant colony algorithm in global path planning under static environment， such as being unable to find the shortest path， slow convergence speed， great blindness of path search and many inflection points， an improved ant colony algorithm was proposed. Taking the grid map as the running environment of the robot， the initial pheromones were distributed unevenly， so that the path search tended to be near the line between the starting point and the target point； the information of the current node， the next node and the target point was added into the heuristic function， and the dynamic adjustment factor was introduced at the same time， so as to achieve the purpose of strong guidance of the heuristic function in the early stage and strengthening the guidance of pheromone in the later stage； the pseudo-random transfer strategy was introduced to reduce the blindness of path selection and speed up finding the shortest path； the volatilization coefficient was adjusted dynamically to make the volatilization coefficient larger in the early stage and smaller in the later stage， avoiding premature convergence of the algorithm； based on the optimal solution， B-spline curve smoothing strategy was introduced to further optimize the optimal solution， resulting in shorter and smoother path. The sensitivity analysis of the main parameters of the improved algorithm was conducted， the feasibility and effectiveness of each improved step of the algorithm were tested， the simulations compared with the traditional ant colony algorithm and other improved ant colony algorithms under 20×20 and 50×50 environments were given， and the experimental results verified the feasibility， effectiveness and superiority of the improved algorithm.
The reasonable exploration of the infeasible region in constrained multi-objective evolutionary algorithms for solving optimization problems with large infeasible domains not only helps the population to converge quickly to the optimal solution in the feasible region， but also reduces the impact of unpromising infeasible region on the performance of the algorithm. Based on this， a Constrained Multi-Objective Evolutionary Algorithm based on Space Shrinking Technique （CMOEA-SST） was proposed. Firstly， an adaptive elite retention strategy was proposed to improve the initial population in the Pull phase of Push and Pull Search for solving constrained multi-objective optimization problems （PPS）， so as to increase the diversity and feasibility of the initial population in the Pull phase. Then， the space shrinking technique was used to gradually reduce the search space during the evolution process， which reduced the impact of unpromising infeasible regions on the algorithm performance. Therefore， the algorithm was able to improve the convergence accuracy while taking account of both convergence and diversity. In order to verify the performance of the proposed algorithm， it was simulated and compared with four representative algorithms including C-MOEA/D （adaptive Constraint handling approach embedded MOEA/D）， ToP （handling constrained multi-objective optimization problems with constraints in both the decision and objective spaces）， C-TAEA （Two-Archive Evolutionary Algorithm for Constrained multi-objective optimization） and PPS on the test problems of LIRCMOP series. Experimental results show that CMOEA-SST has better convergence and diversity when dealing with constrained optimization problems with large infeasible regions.
Concerning the problem of inaccurate identification of taxi shift behaviors， an accurate identification method of taxi shift behaviors based on trajectory data mining was proposed. Firstly， after analyzing the characteristics of taxi parking state data， a method for detecting taxi parking points in non-operating state was proposed. Secondly， by clustering the parking points， the potential taxi shift locations were obtained. Finally， based on the judgment indices of taxi shift event and the kernel density estimation of the taxi shift time， the locations and times of the taxi shift were identified effectively. Taking the trajectory data of 4 416 taxis in Fuzhou as the experimental samples， a total of 5 639 taxi shift locations were identified. These taxi shift locations are in the main working areas of citizens， transportation hubs， business districts and scenic spots. And the identified taxi shift time is mainly from 4：00 to 6：00 in the morning and from 16：00 to 18：00 in the evening， which is consistent with the travel patterns of Fuzhou citizens. Experimental results show that， the proposed method can effectively detect the time-space distribution of taxi shift， and provide reasonable suggestions for the planning and management of urban traffic resources. The proposed method can also help the people to take a taxi more conveniently， improve the operating efficiency of taxis， and provide references for the site selection optimization of urban gas stations， charging stations and other car related facilities.
The current mainstream neural networks cannot satisfy the full expression of sentences and the full information interaction between sentences at the same time when processing answer selection tasks. In order to solve the problems， an answer selection model based on Dynamic Attention and Multi-Perspective Matching （DAMPM） was proposed. Firstly， the pre-trained Embeddings from Language Models （ELMo） was introduced to obtain the word vectors containing simple semantic information. Secondly， the filtering mechanism was used in the attention layer to remove the noise in the sentences effectively， so that the sentence representation of question and answer sentences was obtained in a better way. Thirdly， the multiple matching strategies were introduced in the matching layer at the same time to complete the information interaction between sentence vectors. Then， the sentence vectors output from the matching layer were spliced by the Bidirectional Long Short-Term Memory （BiLSTM） network. Finally， the similarity of splicing vectors was calculated by a classifier， and the semantic correlation between question and answer sentences was acquired. The experimental results on the Text REtrieval Conference Question Answering （TRECQA） dataset show that， compared with the Dynamic-Clip Attention Network （DCAN） method， which is one of the comparison aggregation framework based baseline models， the proposed DAMPM improves the Mean Average Precision （MAP） and Mean Reciprocal Rank （MRR） both by 1.6 percentage points. The experimental results on the Wiki Question Answering （WikiQA） dataset show that， the two performance indices of DAMPM is 0.7 percentage points and 0.8 percentage points higher than those of DCAN respectively. The proposed DAMPM has better performance than the methods in the baseline models in general.
When using Immersed Boundary-Lattice Boltzmann Method （IB-LBM） to solve the flow field， in order to obtain more accurate results， a larger and denser flow field grid is often required， which results in a long time of simulation process. In order to improve the efficiency of the simulation， according to the characteristics of IB-LBM local calculation， combined with three different task scheduling methods in OpenMP， a parallel optimization method of IB-LBM was proposed. In the parallel optimization， three task scheduling modes were mixed to solve the load imbalance problem caused by single task scheduling. The structural decomposition was performed on IB-LBM， and the optimal scheduling mode of each structure part was tested. Based on the experimental results， the optimal scheduling combination mode was selected. At the same time， it could be concluded that the optimal combination is different under different thread counts. The optimization results were verified by speedup， and it could be concluded that when the number of threads is small， the speedup approaches the ideal state； when the number of threads is large， although the additional time consumption of developing and destroying threads affects the optimization of performance， the parallel performance of the model is still greatly improved. The flow field simulation results show that the accuracy of IB-LBM simulation of fluid-solid coupling problems is not affected after parallel optimization.
