For the problems that the performance of the nearest neighbor classification algorithm is greatly affected by the adopted similarity or distance measuring method, and it is difficult to select the optimal similarity or distance measuring method, with multi-similarity method adopted, a K-Nearest Neighbor algorithm with Ordered Pairs of Normalized real numbers (OPNs-KNN) was proposed. Firstly, the new mathematical theory of Ordered Pair of Normalized real numbers (OPN) was introduced in machine learning. And all the samples in the training and test sets were converted into OPNs by multiple similarity or distance measuring methods, so that different similarity information was included in each OPN. Then, the improved nearest neighbor algorithm was used to classify the OPNs, so that different similarity or distance measuring methods were able to be mixed and complemented to improve the classification performance. Experimental results show that compared with 6 improved nearest neighbor classification algorithms, such as distance-Weighted K-Nearest-Neighbor rule (WKNN) rule on Iris, seeds, and other datasets, OPNs-KNN has the classification accuracy improved by 0.29 to 15.28 percentage points, which proves that the performance of classification can be improved greatly by the proposed algorithm.
Achieving seal segmentation precisely, it is benefit to intelligent application of the Republican archives. Concerning the problems of serious printing invasion and excessive noise, a network for seal segmentation was proposed, namely U-Net for Seal (UNet-S). Based on the encoder-decoder framework and skip connections of U-Net, this proposed network was improved from three aspects. Firstly, multi-scale residual module was employed to replace the original convolution layer of U-Net. In this way, the problems such as network degradation and gradient explosion were avoided, while multi-scale features were extracted effectively by UNet-S. Next improvement was using Depthwise Separable Convolution (DSConv) to replace the ordinary convolution in the multi-scale residual module, thereby greatly reducing the number of network parameters. Thirdly, Binary Cross Entropy Dice Loss (BCEDiceLoss) was used and weight factors were determined by experimental results to solve the data imbalance problem of archives of the Republic of China. Experimental results show that compared with U-Net, DeepLab v2 and other networks, the Dice Similarity Coefficient (DSC), mean Intersection over Union (mIoU) and Mean Pixel Accuracy (MPA) of UNet-S have achieved the best results, which have increased by 17.38%, 32.68% and 0.6% at most, and the number of parameters have decreased by 76.64% at most. It can be seen that UNet-S has good segmentation effect in the dataset of Republican archives.
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.
In order to solve the problems of low detection efficiency and poor detection precision caused by various surface defects and numerous small defects of section steel, a detection algorithm for surface defects of section steel, namely Steel-YOLOv3, was proposed on the basis of the deformable convolution and multi-scale dense feature pyramid. Firstly, the deformable convolution was used to replace the convolutional layers of part of the residual units in Darknet53 network, which strengthened the feature learning ability of feature extraction network for multi-type defects on the surface of section steel. Secondly, a multi-scale dense feature pyramid module was designed, which means that a shallower prediction scale was added to the 3 prediction scales of the original YOLOv3 algorithm and the multi-scale feature maps were connected across layers, thereby enhancing the ability to characterize dense small defects. Finally, according to the defect size distribution characteristics of section steel, the K-means dimension clustering method was used to optimize the scales of anchor boxes, and the anchor boxes were evenly distributed to 4 corresponding prediction scales. Experimental results show that Steel-YOLOv3 algorithm has a detection mean Average Precision (mAP) of 89.24%, which is improved by 3.51%, 26.46%, 12.63% and 5.71% compared with those of Faster Region-based Convolutional Neural Network (Faster R-CNN), Single Shot multibox Detector (SSD), YOLOv3 and YOLOv5 algorithms respectively. And the detection rate of tiny spalling defects is significantly improved by the proposed algorithm. Moreover, the proposed algorithm can detect 25.62 images per second, which means the requirement of real-time detection can be met and the algorithm can be applied to the online detection for the surface defects of section steel.
In machine learning, data quality has a far-reaching impact on the accuracy of system prediction. Due to the difficulty of obtaining information and the subjective and limited cognition of human, experts cannot accurately mark all samples. And some probability sampling methods proposed in resent years fail to avoid the problem of unreasonable and subjective sample division by human. To solve this problem, a label noise filtering method based on Dynamic Probability Sampling (DPS) was proposed, which fully considered the differences between samples of each dataset. By counting the frequency of built-in confidence distribution in each interval and analyzing the trend of information entropy of built-in confidence distribution in each interval, the reasonable threshold was determined. Fourteen datasets were selected from UCI classic datasets, and the proposed algorithm was compared with Random Forest (RF), High Agreement Random Forest Filter (HARF), Majority Vote Filter (MVF) and Local Probability Sampling (LPS) methods. Experimental results show that the proposed method shows high ability on both label noise recognition and classification generalization.
Traditional methods of generating digital camouflages cannot generate digital camouflages based on the background information in real time. In order to cope with this problem, a digital camouflage generation method based on cycle-consistent adversarial network was proposed. Firstly, the image features were extracted by using densely connected convolutional network, and the learned digital camouflage features were mapped into the background image. Secondly, the color retention loss was added to improve the quality of generated digital camouflages, ensuring that the generated digital camouflages were consistent with the surrounding background colors. Finally, a self-normalized neural network was added to the discriminator to improve the robustness of the model against noise. For the lack of objective evaluation criteria for digital camouflages, the edge detection algorithm and the Structural SIMilarity (SSIM) algorithm were used to evaluate the camouflage effects of the generated digital camouflages. Experimental results show that the SSIM score of the digital camouflage generated by the proposed method on the self-made datasets is reduced by more than 30% compared with the existing algorithms, verifying the effectiveness of the proposed method in the digital camouflage generation task.
Tumor in brain Magnetic Resonance Imaging (MRI) images is often difficult to be segmented accurately due to noise, gray inhomogeneity, complex structrue, fuzzy and discontinuous boundaries. For the purpose of getting precise segmentation with less position bias, a new method based on Fuzzy C-Means (FCM) clustering and morphological multi-scale modification was proposed. Firstly, a control parameter was introduced to distinguish noise points, edge points and regional interior points in neighborhood, and the function relationship between pixels and the sizes of structure elements was established by combining with spatial information. Then, different pixels were modified with different-sized structure elements using morphological closing operation. Thus most local minimums caused by irregular details and noises were removed, while region contours positions corresponding to the target area were largely unchanged. Finally, FCM clustering algorithm was employed to implement segmentation on the basis of multi-scale modified image, which avoids the local optimization, misclassification and region contours position bias, while remaining accurate positioning of contour area. Compared with the standard FCM, Kernel FCM (KFCM), Genetic FCM (GFCM), Fuzzy Local Information C-Means (FLICM) and expert hand sketch, the experimental results show that the suggested method can achieve more accurate segmentation result, owing to its lower over-segmentation and under-segmentation, as well as higher similarity index compared with the standard segmentation.
In order to reduce the time complexity of biological networks alignment, an implementation for large scale biological networks alignment based on Scalable Protein Interaction Network Alignment (SPINAL) in Message Passing Interface (MPI) program was proposed. Based on MPI, the SPINAL algorithm combined with parallelization method was applied into this approach. Instead of serial algorithm, parallel sorting algorithm was used in multi-core environment. Load balancing strategy was chosen to assign tasks reasonably. In the processing of large scale biological networks alignment, the experiment shows that, compared with the algorithm without parallelization and load balancing strategy, this proposed algorithm can reduce the runtime and improve computation efficiency effectively.