Search

Distribution mismatch can be easily found in multi-sensor systems, which may be caused by different shoot angles, weather conditions and so on. Domain adaptation aims to build robust classifiers using the knowledge from a well-labeled source domain, while applied on a related but different target domain. Pseudo labeling is a prevalent technique for class-wise distribution alignment. Therefore, numerous efforts have been spent on alleviating the issue of mislabeling. In this paper, unlike existing selective hard labeling works, we propose a fuzzy labeling based graph learning framework for matching conditional distribution. Specifically, we construct the cross-domain affinity graph by considering the fuzzy label matrix of target samples. In order to solve the problem of representation shrinkage, the paradigm of sparse filtering is introduced. Finally, a unified optimization method based on gradient descent is proposed. Extensive experiments show that our method achieves comparable or superior performance when compared to state-of-the-art works.

With the advantages of uniform stress transfer and weight reduction, adhesive joints are widely used in engineering. The propagation of non-linear Lamb waves in an adhesive joint with micro-cracks distributing in a random way is systematically investigated by using the numerical simulation method in this paper. A finite element model of the tri-layer adhesive structure with micro-cracks distributing randomly is established, and the Lamb wave mode pair with a matching condition of the phase velocity is chosen to examine the interaction of the micro-cracks with Lamb waves. The results show that the micro-cracks within the adhesive layer will lead to the generation of second harmonics. We also find that the Acoustic Non-linearity Parameters (ANP) increase with the propagation distance in the micro-crack damage zone and the density of the micro-cracks. However, ANPs are less concerned with the friction coefficients of the surface of micro-cracks. This numerical research reveals that non-linear Lamb waves can be employed to effectively characterize the micro-cracks related damages within an adhesive joint.

The sensor-weapon−target assignment (S-WTA) problem is a crucial decision issue in C4ISR. The cooperative engagement capability (CEC) of sensors and weapons depends on the S-WTA schemes, which can greatly affect the operational effectiveness. In this paper, a mathematical model based on the synthetical framework of the S-WTA problem is established, combining the dependent and independent cooperative engagement modes of sensors and weapons. As this problem is a complex combinatorial optimization problem, a novel genetic algorithm is proposed to improve the solution of this formulated S-WTA model. Based on the prior knowledge of this problem, a problem-specific population initialization method and two novel repair operators are introduced. The performances of the proposed algorithm have been validated on the known benchmarks. Extensive experimental studies compared with three state-of-the-art approaches demonstrate that the proposed algorithm can generate better assignment schemes for the most of the benchmarks.

From the aspect of human circulation system structure, a complete hemodynamic model requires consideration of the influence of microcirculation load effect. This paper selected the seepage in porous media as the simulant of microcirculation load. On the basis of a bi-directional liquid-solid coupling tube model, we built a liquid-solid-porous media seepage coupling model. The simulation parameters accorded with the physiological reality. Inlet condition was set as transient single-pulse velocity, and outlet as free outlet. The pressure in the tube was kept at the state of dynamic stability in the range of 80–120 mmHg. The model was able to simulate the entire propagating process of pulse wave. The pulse wave velocity simulated was 6.25 m/s, which accorded with the physiological reality. The complex pressure wave shape produced by reflections of pressure wave was also observed. After the model changed the cardiac cycle length, the pressure change according with actual human physiology was simulated successfully. The model in this paper is well-developed and reliable. It demonstrates the importance of microcirculation load in hemodynamic model. Moreover the properties of the model provide a possibility for the simulation of dynamic adjustment process of human circulation system, which indicates a promising prospect in clinical application.

Artificial intelligence (AI) in complex networks has made revolutionary breakthroughs in this century, and AI-driven methods are being increasingly integrated into different scientific research [...]

In numerical analysis, the pile equivalent calculation method plays a key role in foundation pit calculation results. However, the effect and mechanism of different pile equivalent calculation methods in the foundation pit has remained unclear. To solve this question, based on FLAC3D, four pile equivalent calculation methods were introduced into a typical pile–anchor pit. This research was carried out from the perspective of soil displacement and stress, special points’ stress paths, and the plastic zone. The results revealed that there was a remarkable influence on the calculation results for different pile equivalent calculation methods. Specifically, compared with structural pile elements, displacements near the pile were smaller in solid pile element mode. Moreover, with the increase in excavation depth, stress concentration appeared in the solid pile element mode. The solid support pile with the interface, compared to that without the interface, had less displacement but more stress concentration around the pile, which led the special points’ stress paths around the solid pile to become irregular. Regarding the structural pile elements, it is suggested that both modeling approaches had a similar effect. These findings could help to provide a deeper insight into pile–anchor foundation pit numerical analysis.

Membrane computing is a natural computing branch inspired by the structure of biological cells. The mathematical abstract model of a membrane computing system is called a P System, which is one of the main topics in membrane computing research for the design and verification of a P System. Integer factorization is still a world-class problem and a very important research direction. If a fast method can be found to solve the integer factorization problem, several important cryptographic systems including the RSA public key algorithm will be broken. The aim of this paper is to design a P System capable of implementing integer decomposition, taking advantage of the characteristics of parallelism of P Systems. We construct a process with a main goal to study the modal exponential function f(x) = ax mod N and explore the possible periodic behavior for different values of a. We attempt to compute nontrivial prime factors by the period found and constrain the operation of the P System in polynomial time.

The accurate identification of forest tree species is important for forest resource management and investigation. Using single remote sensing data for tree species identification cannot quantify both vertical and horizontal structural characteristics of tree species, so the classification accuracy is limited. Therefore, this study explores the application value of combining airborne high-resolution multispectral imagery and LiDAR data to classify tree species in study areas of different altitudes. Three study areas with different altitudes in Muyu Town, Shennongjia Forest Area were selected. Based on the object-oriented method for image segmentation, multi-source remote sensing feature extraction was performed. The recursive feature elimination algorithm was used to filter out the feature variables that were optimal for classifying tree species in each altitude study area. Four machine learning algorithms, SVM, KNN, RF, and XGBoost, were combined to classify tree species at each altitude and evaluate the accuracy. The results show that the diversity of tree layers decreased with the altitude in the different study areas. The texture features and height features extracted from LiDAR data responded better to the forest community structure in the different study areas. Coniferous species showed better classification than broad-leaved species within the same study areas. The XGBoost classification algorithm showed the highest accuracy of 87.63% (kappa coefficient of 0.85), 88.24% (kappa coefficient of 0.86), and 84.03% (kappa coefficient of 0.81) for the three altitude study areas, respectively. The combination of multi-source remote sensing numbers with the feature filtering algorithm and the XGBoost algorithm enabled accurate forest tree species classification.

Infrared point-target detection is one of the key technologies in infrared guidance systems. Due to the long observation distance, the point target is often submerged in the background clutter and large noise in the process of atmospheric transmission and scattering, and the signal-to-noise ratio is low. On the other hand, the target in the image appears in the form of fuzzy points, so that the target has no obvious features and texture information. Therefore, scholars have proposed many object detection methods for dimming infrared images, which has become a hot research topic on account of the flow-rank model based on the image patch. However, the result has a high false alarm rate because the most low-rank models based on the image patch do not consider the spatial-temporal characteristics of the infrared sequences. Therefore, we introduce 3D total variation (3D-TV) to regularize the foreground on account of the non-convex rank approximation minimization method, so as to consider the spatial-temporal continuity of the target and effectively suppress the interference caused by dynamic background and target movement on the foreground extraction. Finally, this paper proposes the minimization of the non-convex spatial-temporal tensor low-rank approximation algorithm (MNSTLA) by studying the related algorithms of the point infrared target detection, and the experimental results show strong robustness and a low false alarm rate for the proposed method compared with other advanced algorithms, such as NARM, RIPT, and WSNMSTIPT.

Traditional collaborative filtering recommendation algorithms only consider the interaction between users and items leading to low recommendation accuracy. Aiming to solve this problem, a graph convolution collaborative filtering recommendation method integrating social relations is proposed. Firstly, a social recommendation model based on graph convolution representation learning and general collaborative filtering (SRGCF) is constructed; then, based on this model, a social relationship recommendation algorithm (SRRA) is proposed; secondly, the algorithm learns the representations of users and items by linear propagation on the user–item bipartite graph; then the user representations are updated by learning the representations with social information through the neighbor aggregation operation in the social network to form the final user representations. Finally, the prediction scores are calculated, and the recommendation list is generated. The comparative experimental results on four real-world datasets show that: the proposed SRRA algorithm performs the best over existing baselines on Recall@10 and NDCG@10; specifically, SRRA improved by an average of 4.40% and 9.62% compared to DICER and GraphRec, respectively, which validates that the proposed SRGCF model and SRRA algorithm are reasonable and effective.

As most of the community discovery methods are researched by static thought, some community discovery algorithms cannot represent the whole dynamic network change process efficiently. This paper proposes a novel dynamic community discovery method (Phylogenetic Planted Partition Model, PPPM) for phylogenetic evolution. Firstly, the time dimension is introduced into the typical migration partition model, and all states are treated as variables, and the observation equation is constructed. Secondly, this paper takes the observation equation of the whole dynamic social network as the constraint between variables and the error function. Then, the quadratic form of the error function is minimized. Thirdly, the Levenberg–Marquardt (L–M) method is used to calculate the gradient of the error function, and the iteration is carried out. Finally, simulation experiments are carried out under the experimental environment of artificial networks and real networks. The experimental results show that: compared with FaceNet, SBM + MLE, CLBM, and PisCES, the proposed PPPM model improves accuracy by 5% and 3%, respectively. It is proven that the proposed PPPM method is robust, reasonable, and effective. This method can also be applied to the general social networking community discovery field.