Route planning is very important for the task execution of Unmanned Aerial Vehicle (UAV) swarm, and the computation is usually complex in high dimensional scenarios. Swarm intelligence has provided a good solution for this problem. Particle Swarm Optimization (PSO) algorithm is especially suitable for route planning problem because of its advantages such as few parameters, fast convergence and simple operation. However, PSO algorithm has poor global search ability and is easy to fall into local optimum when applied to route planning. In order to solve the problems above and improve the effect of UAV swarm route planning, a Dynamic Cluster Particle Swarm Optimization (DCPSO) algorithm was proposed. Firstly, artificial potential field method and receding horizon control principle were used to model the task scenario of route planning problem of UAV swarm. Secondly, Tent chaotic map and dynamic cluster mechanism were introduced to further improve the global search ability and search accuracy. Finally, DCPSO algorithm was used to optimize the objective function of the model to obtain each trajectory point selection of UAV swarm. On 10 benchmark functions with different combinations of unimodal/multimodal and low-dimension/high-dimension, simulation experiments were carried out. The results show that compared with PSO algorithm, Pigeon-Inspired Optimization (PIO), Sparrow Search Algorithm (SSA) and Chaotic Disturbance Pigeon-Inspired Optimization (CDPIO) algorithm, DCPSO algorithm has better optimal value, mean value and variance, better search accuracy and stronger stability. Besides, the performance and effect of DCPSO algorithm were demonstrated in the route planning application instances of UAV swarm simulation experiments.
Prompt paradigm is widely used to zero-shot Natural Language Processing (NLP) tasks. However, the existing zero-shot Relation Extraction (RE) model based on Prompt paradigm suffers from the difficulty of constructing answer space mappings and dependence on manual template selection, which leads to suboptimal performance. To address these issues, a zero-shot RE model via multi-template fusion in Prompt was proposed. Firstly, the zero-shot RE task was defined as the Masked Language Model (MLM) task, where the construction of answer space mapping was abandoned. Instead, the words output by the template were compared with the relation description text in the word embedding space to determine the relation class. Then, the part of speech of the relation description text was introduced as a feature, and the weight between this feature and each template was learned. Finally, this weight was utilized to fuse the results output by multiple templates, thereby reducing the performance loss caused by the manual selection of Prompt templates. Experimental results on FewRel (Few-shot Relation extraction dataset) and TACRED (Text Analysis Conference Relation Extraction Dataset) show that, the proposed model significantly outperforms the current state-of-the-art model, RelationPrompt, in terms of F1 score under different data resource settings, with an increase of 1.48 to 19.84 percentage points and 15.27 to 15.75 percentage points, respectively. These results convincingly demonstrate the effectiveness of the proposed model for zero-shot RE tasks.
A pixel classification-based multiscale Unmanned Aerial Vehicle (UAV) aerial object rotational tracking algorithm was proposed for the UAV tracking process, in which the vertical tracking box limited the tracking accuracy when dealing with scale changes, similar objects and aspect ratio changes. Firstly, MS-ResNet (MultiScale ResNet-50) was designed to extract multiscale features of the object. Then, a pixel binary classification module was designed on the multi-channel response map with orthogonal characteristics to further refine the results of classification and regression branches accurately. Meanwhile, to improve the pixel classification accuracy, the concurrent spatial and channel “Squeeze & Excitation” (scSE) module was used to filter the object features in the spatial and channel domains. Finally, a rotational tracking box fitting the actual size of the object was generated based on pixel classification to avoid the contamination of positive samples. Experimental results show that the proposed algorithm has the success rate and precision on the UAV tracking dataset UAV123 of 60.7% and 79.5% respectively, which are 5 percentage points and 2.7 percentage points higher than those of Siamese Region Proposal Network (SiamRPN) respectively, and has the speed reached 67.5 FPS, meeting the real-time requirements. The proposed algorithm has good scale adaptation, discrimination ability and robustness, and can effectively cope with UAV tracking tasks.
To solve severe performance degradation problem of person re-identification task during cross-domain migration, a new cross-domain person re-identification method based on attention mechanism with learning intra-domain variance was proposed. Firstly, ResNet50 was used as the backbone network and some modifications were made to it, so that it was more suitable for person re-identification task. And Instance-Batch Normalization Network (IBN-Net) was introduced to improve the generalization ability of model. At the same time, for the purpose of learning more discriminative features, a region attention branch was added to the backbone network. For the training of source domain, it was treated as a classification task. Cross-entropy loss was utilized for supervised learning of source domain, and triplet loss was introduced to mine the details of source domain samples and improve the classification performance of source domain. For the training of target domain, intra-domain variance was considered to adapt the difference in data distribution between the source domain and the target domain. In the test phase, the output of ResNet50 pool-5 layer was used as image features, and Euclidean distance between query image and candidate image was calculated to measure the similarity of them. In the experiments on two large-scale public datasets of Market-1501 and DukeMTMC-reID, the Rank-1 accuracy of the proposed method is 80.1% and 67.7% respectively, and its mean Average Precision (mAP) is 49.5% and 44.2% respectively. Experimental results show that, the proposed method has better performance in improving generalization ability of model.
Focused on the traditional methods of feature selection for brain functional connectivity matrix derived from Resting-state functional Magnetic Resonance Imaging (R-fMRI) have feature redundancy, cannot determine the final feature dimension and other problems, a new feature selection algorithm was proposed. The algorithm combined Random Forest (RF) algorithm in statistical method, and applied it in the identification experiment of schizophrenic and normal patients, according to the features are obtained by the classification results of out of bag data. The experimental results show that compared to the traditional Principal Component Analysis (PCA), the proposed algorithm can effectively retain important features to improve recognition accuracy, which have good medical explanation.
The traditional classification algorithms are mostly based on balanced datasets. But when the sample is not balanced, the performance of these learning algorithms are often significantly decreased. For the classification of imbalanced data, a optimized Support Vector Machine (SVM) ensemble classifier model was proposed. Firstly, the model used KSMOTE and Bootstrap to preprocess the imbalanced data and paralleled to generate the corresponding SVM models. And then these SVM models' parameters were optimized by using complex method. At last the optimized SVM ensemble classifier model was generated by the above parameters and produce the final result by voting mechanism. Through the experiment on 5 groups of UCI standard data set, the experimental results show that the optimized SVM ensemble classifier model has higher classification accuracy than SVM model, optimized SVM model and so on. And the results also verify the effect of different bootNum values on the optimized SVM ensemble classifier.
It is necessary to pre-define a cluster number in classical Fuzzy C-means (FCM) algorithm. Otherwise, FCM algorithm can not work normally, which limits the applications of this algorithm. Aiming at the problem of pre-assigning cluster number for FCM algorithm, a new fuzzy cluster validity index was presented. Firstly, the membership matrix was got by running the FCM algorithm. Secondly, the intra class compactness and the inter class overlap were computed by the membership matrix. Finally, a new cluster validity index was defined by using the intra class compactness and the inter class overlap. The proposal overcomes the shortcomings of FCM that the cluster number must be pre-assigned. The optimal cluster number can be effectively found by the proposed index. The experimental results on artificial and real data sets show the validity of the proposed index. It also can be seen that the optimal cluster number are obtained for three different fuzzy factor values of 1.8, 2.0 and 2.2 which are general used in FCM algorithm.
According to the characteristics of traditional multivariate linear regression method for long processing time and limited memory, a parallel multivariate linear regression forecasting model was designed based on MapReduce for the time-series sample data. The model was composed of three MapReduce processes which were used to solve the eigenvector and standard orthogonal vector of cross product matrix composed by historical data, to forecast the future parameter of the eigenvalues and eigenvectors matrix, and to estimate the regression parameters in the next moment respectively. Experiments were designed and implemented to the validity effectiveness of the proposed parallel multivariate linear regression forecasting model. The experimental results show multivariate linear regression prediction model based on MapReduce has good speedup and scaleup, and suits for analysis and forecasting of large data.