Neighbor Strategy Research Articles

A Novel Energy-Aware Path Planning by Autonomous Underwater Vehicle in Underwater Wireless Sensor Networks

Wireless sensor networks can monitor the environment to detect anomalies and reduce the risk of maritime traffic. Energy is necessary for low-power conditions where wireless sensor networks are used. Ensuring the lifespan of energy constraints and providing continuous environmental observation, data collecting, and communication requires management. Battery replacement and energy consumption issues can be resolved with path planning and energy-efficient autonomous underwater vehicle charging for sensor nodes. The nearest neighbour technique is used in this study to solve the energy-aware path planning problem of an autonomous underwater vehicle. Path planning simulations show that the nearest neighbour strategy converges faster and produces a better result than the genetic algorithm. We develop robust and energy-efficient path-planning algorithms that efficiently acquire sensor data while consuming less energy, allowing the monitoring system to respond to anomalies more rapidly. Increased sensor connectivity lowers energy usage and increases network longevity. This study also considers the situation when it is recommended to avoid taking direct travel paths between particular node pairs for a variety of reasons. This recommendation is considered in this study. We present a strategy based on a modified Nearest Neighbour-based Approach from the Nearest Neighbour method to address this more challenging scenario. The direct pathways between such nodes are constrained within the context of this technique. The modified version of Nearest Neighbor-based approach performs well even in that particular situation.

Fabric defect detection based on feature enhancement and complementary neighboring information

Abstract Fabric defect detection is a crucial aspect of quality control in the textile industry. Given the complexities of fabric backgrounds, the high similarity between patterned backgrounds and defects, and the variety of defect scales, we propose a fabric defect detection method based on feature enhancement and complementary neighboring information . The core of this method lies in two main components: the feature enhancement module and the neighboring information complementation strategy. The feature enhancement module includes two sub-modules: similarity feature enhancement(SFE) and edge detail feature enhancement(EDFE). The SFE aims to capture the similarities between features to strengthen the distinction between defects and complex backgrounds, thereby highlighting the correlations among defects and the differences between defects and the background. The EDFE focuses on improving the network's ability to capture the edge details of fabrics, preventing edge information from becoming blurred or lost due to deeper network layers. The neighboring information complementation strategy consists of shallow-level information complementation(SLIC) and top-down information fusion complementation(TDIFC). The SLIC integrates newly introduced shallow features with neighboring features that have a smaller semantic gap, injecting richer detail information into the network. The TDIFC adaptively guides the interaction of information between adjacent feature maps, effectively aggregating multi-scale features to ensure information complementarity between features of different scales. Additionally, to further optimize model performance, we introduced partial convolution(PConv) in the backbone of the feature extraction network. PConv reduces redundant computations and decreases the model's parameter count. Experimental results show that our proposed method achieved an mAP@50 of 82.4%, which is a 6.6% improvement over the baseline model YOLOv8s. The average inference frame rate reached 61.8 FPS, meeting the real-time detection requirements for fabric defects. Moreover, the model demonstrated good generalization capabilities, effectively adapting to detecting defects in different types and colors of fabrics.

A multimodal multi-objective differential evolution with series-parallel combination and dynamic neighbor strategy

Multimodal multi-objective optimization problems (MMOPs), which aim to identify as many optimal solutions as possible and exhibit multiple equivalent Pareto optimal solution sets (PSs) that correspond to the same Pareto optimal front (PF), commonly arise in a wide range of optimization problems in the real world. However, some dominated solutions that exhibit greater diversity in the decision space may be substituted by non-dominated solutions with a higher level of decision space crowding. To tackle this issue, this paper proposes a multimodal multi-objective differential evolution with series-parallel combination and dynamic neighbor strategy (MMODE_SPDN), which can balance convergence, objective space diversity and decision space diversity. Specifically, two archives are initially updated serially followed by the overall update of the parallel structure, in which the serial-first approach can enhance population diversity and the parallel structure can greatly reduce the amount of calculation. In addition, a dynamic neighbor strategy which utilizes adaptive selection among neighbors to generate difference vectors in the decision space and objective space and then adopts the main and auxiliary parent method during the mutation process is proposed. Furthermore, the utilization of an auxiliary archive and the clustering-based special crowding distance (CSCD) method are employed to facilitate the updating of the archive, thereby enhancing diversity. MMODE_SPDN is compared with other multimodal multi-objective optimization evolutionary algorithms (MMOEAs) on numerous test problems and the experimental results demonstrate that MMODE_SPDN exhibits superior performance.

Differential graphical games of multiagent systems with nonzero leader's control input and external disturbances

AbstractIn this article, we investigate the problem of differential graphical games for multiagent systems (MASs) with external disturbances. In particular, the system considered in this article allows the leader to have an unknown bounded control input, and the communication topology between agents is allowed to be a weakly restricted structure with only containing a directed spanning tree. We propose a novel dynamic sliding mode control strategy to dispose the presence of leader's nonzero control input and external disturbances. Furthermore, a nominal controller based on the worst‐case control strategies of neighbors is designed to provide a distributed solution for differential graphics games of MASs. Finally, our algorithms are applied to solve multiple unmanned surface vessels games. Simulation studies are provided to test the effectiveness of the proposed algorithms.

Enhancing smart road safety with federated learning for Near Crash Detection to advance the development of the Internet of Vehicles

We introduce an innovative methodology for the identification of vehicular collisions within Internet of Vehicles (IoV) applications. This approach combines a knowledge base system with deep learning for model selection in an ensemble learning setting. It is designed to provide a general near-crash detection capability without relying on domain-specific knowledge, enabling the development of generic deep learning models. Our proposed methodology employs a novel deep learning approach, wherein multiple learning models are individually trained for each image. Subsequently, visual features are computed and stored for each trained image, along with the associated loss values from the training phase. This stored information is utilized to select the most suitable models for processing new image data during the testing phase. To facilitate efficient model selection, we employ a kNN (k Nearest Neighbors) strategy. To enhance both data and model security in IoV environments, we implement an intelligent federated learning (FL) strategy. Users are organized into clusters, and we employ two distinct aggregation methods, departing from conventional federated learning approaches. In the initial stage, we aggregate model data from all users to create a global model representing collective knowledge. In the subsequent stage, we aggregate models from each cluster to generate customized local models. Users are provided with both global and local models, allowing them to select the most suitable model for their specific crash detection needs. We test our approach, that we call Knowledge Guided Deep Learning for Near Crash Detection (KGDL-NCD), on well-known NCD benchmarks. The results demonstrate that KGDL-NCD surpasses baseline solutions, achieving an AUC (Area Under Curve) metric of 0.95.

Cluster-based oversampling with area extraction from representative points for class imbalance learning

Class imbalance learning is challenging in various domains where training datasets exhibit disproportionate samples in a specific class. Resampling methods have been used to adjust the class distribution, but they often have limitations for small disjunct minority subsets. This paper introduces AROSS, an adaptive cluster-based oversampling approach that addresses these limitations. AROSS utilizes an optimized agglomerative clustering algorithm with the Cophenetic Correlation Coefficient and the Bayesian Information Criterion to identify representative areas of the minority class. Safe and half-safe areas are obtained using an incremental k-Nearest Neighbor strategy, and oversampling is performed with a truncated hyperspherical Gaussian distribution. Experimental evaluations on 70 binary datasets demonstrate the effectiveness of AROSS in improving class imbalance learning performance, making it a promising solution for mitigating class imbalance challenges, especially for small disjunct minority subsets.

Multiview Spectral Clustering Based on Consensus Neighbor Strategy.

Multiview spectral clustering, renowned for its spatial learning capability, has garnered significant attention in the data mining field. However, existing methods assume that the optimal consensus adjacency matrix is confined within the space spanned by each view's adjacency matrix. This constraint restricts the feasible domain of the algorithm and hinders the exploration of the optimal consensus adjacency matrix. To address this limitation, we propose a novel and convex strategy, termed the consensus neighbor strategy, for learning the optimal consensus adjacency matrix. This approach constructs the optimal consensus adjacency matrix by capturing the consensus local structure of each sample across all views, thereby expanding the search space and facilitating the discovery of the optimal consensus adjacency matrix. Furthermore, we introduce the concept of a correlation measuring matrix to prevent trivial solution. We develop an efficient iterative algorithm to solve the resulting optimization problem, benefitting from the convex nature of our model, which ensures convergence to a global optimum. Experimental results on 16 multiview datasets demonstrate that our proposed algorithm surpasses state-of-the-art methods in terms of its robust consensus representation learning capability. The code of this article is uploaded to https://github.com/PhdJiayiTang/Consensus-Neighbor-Strategy.git.

Supervised Manifold Learning Based on Multi-Feature Information Discriminative Fusion within an Adaptive Nearest Neighbor Strategy Applied to Rolling Bearing Fault Diagnosis.

Rolling bearings are a key component for ensuring the safe and smooth operation of rotating machinery and are very prone to failure. Therefore, intelligent fault diagnosis research on rolling bearings has become a crucial task in the field of mechanical fault diagnosis. This paper proposes research on the fault diagnosis of rolling bearings based on an adaptive nearest neighbor strategy and the discriminative fusion of multi-feature information using supervised manifold learning (AN-MFIDFS-Isomap). Firstly, an adaptive nearest neighbor strategy is proposed using the Euclidean distance and cosine similarity to optimize the selection of neighboring points. Secondly, three feature space transformation and feature information extraction methods are proposed, among which an innovative exponential linear kernel function is introduced to provide new feature information descriptions for the data, enhancing feature sensitivity. Finally, under the adaptive nearest neighbor strategy, a novel AN-MFIDFS-Isomap algorithm is proposed for rolling bearing fault diagnosis by fusing various feature information and classifiers through discriminative fusion with label information. The proposed AN-MFIDFS-Isomap algorithm is validated on the CWRU open dataset and our experimental dataset. The experiments show that the proposed method outperforms other traditional manifold learning methods in terms of data clustering and fault diagnosis.

Target number influences strategy use by rats (Rattus norvegicus) in the traveling salesperson problem.

The traveling salesman problem (TSP) is an optimization problem in which the goal is to find the shortest possible route that passes through each of a set of points in space. The TSP is of interest not only in the fields of mathematics, computer science, and engineering, but also in cognitive and behavioral research to study problem-solving and spatial navigation. Humans are able to complete even complex TSPs with a high degree of efficiency, and distance minimization in TSP analogs has been observed in a variety of nonhuman species as well. Tasks based on the TSP also have the potential for translational research on cognitive and neurological disorders such as Alzheimer's disease. The current experiment was designed to examine the effects of target number on TSP performance in rats. After pretraining, rats were tested once on each of several target configurations, and their travel routes were recorded. We examined the routes for general efficiency, as well as evidence for strategy use including the nearest neighbor (NN) strategy and crossing avoidance. Our results indicate that latency and route length increase in proportion to the number of targets. Rats also showed a strong tendency to avoid path crossing, and to select NN targets, which strengthened with increasing target numbers. Taken together, our results indicate that travel efficiency decreases linearly in relation to the target number rather than the number of possible routes, which grows factorially with a target number. Additionally, spatial memory and route selection strategy are also affected by an increasing number of targets. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Active Antinoise Fuzzy Dominance Rough Feature Selection Using Adaptive K-Nearest Neighbors

Feature selection methods with anti-noise performance are effective dimensionality reduction methods for classification tasks with noise. However, there are few studies on robust feature selection methods for monotonic classification tasks. The fuzzy dominance rough set (FDRS) model is a nontrivial knowledge acquisition tool, which is widely used in feature selection of monotonic classification tasks. Nonetheless, this model has been proved in practice to be generally poorly fault-tolerance, and only one noisy sample can cause huge interference in acquiring knowledge. In view of these two issues, this paper firstly designs an adaptive <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$K$</tex-math></inline-formula> -nearest neighbors strategy to calculate the density of samples. The noisy samples are identified according to their densities, and then an active anti-noise fuzzy dominance rough set model is proposed. Then, in the active anti-noise fuzzy dominance rough approximation space, the class-separability is evaluated by the approximation operators of the proposed model, and the feature-redundancy is evaluated by the fuzzy ranking conditional mutual information. On this basis, a feature evaluation index is designed comprehensively considering class-separability and feature-redundancy. Finally, a feature selection algorithm is designed to select the feature subset with the highest classification performance. The experimental results show that the proposed algorithm has better robustness and classification performance.

An Improved Vicsek Model of Swarms Based on a New Neighbor Strategy Considering View and Distance

Collective behaviors in nature and human societies have been intensively studied in recent decades. The Vicsek model is one of the typical models that explain self-ordered particle systems well. In the original Vicsek model, the neighbor strategy takes all its neighbors’ mean directions into account when updating particles’ directions, which leads to a longer convergence time and higher computation cost due to the excess number of neighbors. In this paper, we introduce a new neighbor strategy to the Vicsek model. It defines that each particle will only select a certain number of particles with the farthest distance that fall into its vision sector as its neighbors. In addition, we classify the Vicsek model as the static model and the dynamic model according to whether the features of particles in the model are constant or not. Moreover, we design a new rule to apply the new neighbor strategy to dynamic Vicsek models. The simulation results indicate that our new neighbor strategy can significantly decrease the average number of particles’ neighbors but still be able to further enhance the Vicsek model’s convergence performance. The comparative results found that the static and dynamic model applied with the new neighbor strategy outperforms the models that only apply view restriction or remote neighbor strategy in noiseless and noisy conditions.

Adaptive Sparsity Orthogonal Least Square with Neighbor Strategy for Fluorescence Molecular Tomography.

Fluorescence molecular tomography (FMT) is a highly sensitive and noninvasive optical imaging technique which has been widely applied to disease diagnosis and drug discovery. However, FMT reconstruction is a highly ill-posed problem. In this work, L0-norm regularization is employed to construct the mathematical model of the inverse problem of FMT. And an adaptive sparsity orthogonal least square with a neighbor strategy (ASOLS-NS) is proposed to solve this model. This algorithm can provide an adaptive sparsity and can establish the candidate sets by a novel neighbor expansion strategy for the orthogonal least square (OLS) algorithm. Numerical simulation experiments have shown that the ASOLS-NS improves the reconstruction of images, especially for the double targets reconstruction.Clinical relevance- The purpose of this work is to improve the reconstruction results of FMT. Current experiments are focused on simulation experiments, and the proposed algorithm will be applied to the clinical tumor detection in the future.

Model-assisted domain estimation of postfire tree regeneration in the western US using nearest neighbor techniques

Many nations administer national forest inventory programs for unbiased estimation of forest attributes over broad spatial and temporal extents. However, management and conservation decisions often demand reliable estimates for finer spatiotemporal domains. In the western US, wildfire activity is expanding and postfire regeneration must contend with a warmer, drier climate. We evaluate the potential of K nearest neighbor (KNN) strategies for estimation of stocking across postfire measurements of Forest Inventory &amp; Analysis plots in 11 western US states, and subsequently for model-assisted (MA) estimation of stocking over domains defined by aggregations of burned areas within individual states and 4-year periods. In particular, we develop and evaluate a form of constrained KNN that allows for unbiased MA domain estimation under simple random sampling by drawing only on measurements external to a domain of interest. KNN strategies based on geographically, radiometrically, and climatically proximate measurements are found to provide more accurate estimates of stocking at the plot level than domain means. Applying the selected external KNN strategy also reduced standard errors of MA domain estimates by 16% over direct domain estimators, but bias correction introduces substantial variability over synthetic estimates. Further applications of the external constraint imposed on KNN are discussed.

Comparing the risk of serious infections in patients with and without MS: A German claims data analysis

Research suggests that serious infections (SIs), comorbidities, and advanced disability represent key drivers of early death in people with Multiple Sclerosis (pwMS). Nevertheless, further research is warranted to better characterize and quantify the risk of SI among pwMS compared to the general population. Our study consisted of a retrospective analysis of claims data provided by a German statutory health insurance fund, AOK PLUS, covering 3.4 million individuals in Saxony and Thuringia from 01/01/2015-31/12/2019. A propensity score (PS) matching method was used to compare the incidence of SIs among people with and without MS. PwMS were required to have ≥1 inpatient or ≥2 confirmed outpatient diagnoses of MS (ICD-10 G35) from a neurologist from 01/01/2016-31/12/2018, while people from the general population could not have any inpatient/outpatient codes for MS during the entire study period. The index date was defined as the first observed MS diagnosis or, in the case of the non-MS cohort, a randomly assigned date within the inclusion period. For both cohorts a PS was assigned, corresponding with their probabilistic likelihood of having MS based on observable factors including patient characteristics, comorbidities, medication use and other variables. People with and without MS were matched using a 1:1 nearest neighbor strategy. An exhaustive list of ICD-10 codes was created in association with 11 main SI categories. SIs were those recorded as the main diagnosis during an inpatient stay. ICD-10 codes from the 11 main categories were sorted into smaller classification units, used to distinguish between infections. A 60-day threshold for measuring new cases was defined to account for the potential risk of re-infection. Patients were observed until the end of the study period (31/12/2019) or death. Cumulative incidence, incidence rates (IRs) and IR ratios (IRRs) were reported during follow-up and at 1-, 2- and 3-years post-index. A total of 4250 and 2,098,626 patients were included in the unmatched cohorts of people with and without MS. Ultimately, one match was identified for all 4,250 pwMS, corresponding with a final population of 8,500 patients. On average, patients were 52.0/52.2 years in the matched MS/non-MS cohorts; the gender breakdown was 72% female. Overall, IRs of SIs per 100 patient years (PY) were higher in pwMS than in those without MS (1 year: 7.6vs. 4.3; 2 years: 7.1vs. 3.8; 3 years: 6.9vs. 3.9). During follow-up, the most common infection types in pwMS were of a bacterial/parasitic origin (2.3 per 100 PY), followed by respiratory (2.0) and genitourinary (1.9) infections. Respiratory infections were most common in patients without MS (1.5 per 100 PY). Differences in the IRs of SIs were statistically significant (p<0.01) at each measurement window, with IRRs ranging from 1.7-1.9. PwMS had a higher risk of hospitalized genitourinary infections (IRR: 3.3-3.8) and bacterial/parasitic infections (2.0-2.3). The incidence of SIs is much higher in pwMS, than comparators from the general population in Germany. Differences in hospitalized infection rates were largely driven by higher levels of bacterial/parasitic and genitourinary infections in the MS population.

Switching synthesizing-incorporated and cluster-based synthetic oversampling for imbalanced binary classification

Oversampling is a popular yet useful method to fulfill the binary classification of imbalanced data, however many existing results of oversampling are very likely to generate redundant/unsafe/noise samples due primarily to the inadequate consideration of the data distribution. To address this issue, we propose a novel oversampling approach, namely Switching Synthesizing-Incorporated and Cluster-Based Synthetic Oversampling (SSI-CBSO). The core idea of SSI-CBSO is four-fold: (1) noise samples are removed by using K nearest neighbor strategy and Fuzzy C-Means clustering is adopted for the filtered data in the minority class; (2) the number of samples that need to be synthesized is adaptively assigned to each cluster concerning the inter-class distance and the intra-cluster similarity; (3) to better reflect the data distribution, a new method in terms of the concept of the hypersphere is put forward to measure the cluster density in a high dimensional; and (4) a new principle based on the Mahalanobis distance is provided for a better selection of the target sample. Then, a switching synthesizing strategy is established to guarantee the safety of the synthesized samples. Finally, experiments on 13 binary imbalanced data sets by using five evaluation metrics with four classifiers verify that our proposed SSI-CBSO approach can obtain desirable results.

Assessing Biomaterial-Induced Stem Cell Lineage Fate by Machine Learning-Based Artificial Intelligence.

Current functional assessment of biomaterial-induced stem cell lineage fate in vitro mainly relies on biomarker-dependent methods with limited accuracy and efficiency. Here a "Mesenchymal stem cell Differentiation Prediction (MeD-P)" framework for biomaterial-induced cell lineage fate prediction is reported. MeD-P contains a cell-type-specific gene expression profile as a reference by integrating public RNA-seq data related to tri-lineage differentiation (osteogenesis, chondrogenesis, and adipogenesis) of human mesenchymal stem cells (hMSCs) and a predictive model for classifying hMSCs differentiation lineages using the k-nearest neighbors (kNN) strategy. It is shown that MeD-P exhibits an overall accuracy of 90.63% on testing datasets, which is significantly higher than the model constructed based on canonical marker genes (80.21%). Moreover, evaluations of multiple biomaterials show that MeD-P provides accurate prediction of lineage fate on different types of biomaterials as early as the first week of hMSCs culture. In summary, it is demonstrated that MeD-P is an efficient and accurate strategy for stem cell lineage fate prediction and preliminary biomaterial functional evaluation.

Prisoner’s dilemma game model Based on historical strategy information

In many dilemmas, decisions are determined not by a single factor, but by multiple ones, including memory, reputation, reward and punishment. In recent years, how to design a mechanism to promote cooperation has become a research hot-spot. However, most of the previous studies mainly consider the historical benefits of the game, and pay less attention to the stability of the strategy (the frequency of strategy changes in the length of memory) and the proportion of memory in decision-making. The decision-making process of group evolution involves the influence of memory information on cooperative evolution in multi round games. It makes up for the lack of stability factors and weights in previous studies. Based on the above factors, a new strategy update rule is proposed to study the influence of the stability of historical strategy information on the evolution of cooperation in prisoner’s dilemma game, and the influence of memory weight on cooperation is considered. The stability of the current strategy is measured by the strategy in historical memory (the number of times the strategy in memory is continuous and consistent with the current strategy), which can determine the probability of an individual learning the neighbor strategy next time. Numerical simulation shows that an appropriate increase in the length of historical memory is more conducive to the emergence of cooperation, and the greater the weight of historical strategy information is, the more conducive to promoting cooperation, which shows that historical strategy information is still the main factor in decision-making. This study will help us understand the cooperative evolution of many real systems, such as nature, biology, society and so on, and effectively design reasonable mechanisms to promote cooperation.

Bayesian Image Reconstruction Using Weighted Laplace Prior for Lung Respiratory Monitoring With Electrical Impedance Tomography

The poor spatial resolution of electrical impedance tomography (EIT) limits its use in medical devices because of its highly nonlinear and ill-posed nature. A novel hierarchical block sparse Bayesian learning (BSBL) method is designed for lung respiratory monitoring with EIT. It is its excellent modeling capability and noise robustness that allows BSBL to adaptively explore and exploit the internal conductivity distribution, e.g., block sparsity and intra-block correlation. First, the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -nearest neighbor (KNN) strategy is employed to automatically group each block based on the clustering property and incorporated to constrain the intra-block correlation matrix based on the spatial distance. Second, a three-layer hierarchical BSBL model using weighted Laplace (WL) prior is considered to enhance the recovery performance. Finally, an efficient bound optimization (BO) method is performed for Bayesian inference, avoiding the tedious parameter adjustment. This leads to improvements in recovery performance, algorithm robustness, and computational efficiency. Moreover, root mean square error (RMSE), image correlation coefficient (ICC), and relative size coverage ratio (RCR) are applied for quantitative comparisons of image quality. Numerical simulations and in vivo lung respiratory experiments showed that the proposed KNN-BSBL-WL method outperforms existing referenced methods in terms of reconstruction accuracy and computational time. On average, KNN-BSBL-WL obtains the RMSE <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$= 0.07\,\,\pm \,\,0.02$ </tex-math></inline-formula> , ICC <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$= 0.96\,\,\pm \,\,0.01$ </tex-math></inline-formula> , and RCR <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$= 0.98\,\,\pm \,\,0.05$ </tex-math></inline-formula> , which are closest to the true values of the recorded snapshots obtained in the experiments. Meanwhile, the average time of KNN-BSBL-WL is 0.16 s, achieving an acceleration ratio close to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim 3$ </tex-math></inline-formula> compared with the referenced KNN-BSBL method. Therefore, the proposed method is an efficient and robust means of imaging reconstruction, which further improves the feasibility of EIT in respiratory clinical applications.

Robust Face Recognition Algorithm Based on Multidirectional Log-Gabor Features

In order to improve the robustness to variable factors such as illumination, expression and pose, a face recognition method based on multi-directional Log-Gabor feature map sparse representation is proposed. First, conduct multi-directional and multi-scale Log-Gabor transformation on the face image, and then fuse the Log-Gabor features of different scales in the same direction to obtain a multi-directional feature map. Then, extract Gist features from the fused feature map of each direction and give them adaptive weights. Then, connect the adaptive weighted Gist features of all directional feature maps to form a feature vector of the face image, Finally, sparse representation classification method is used to realize face recognition. Face recognition experiments were carried out on WIDER FACE dataset and the MAFA occlusion face dataset, and the identification accuracy of the proposed method is compared with SRC, NMR, Gabor NLDA NN and Gabor NLDA SVM. The experimental results show that the method in this paper can effectively describe the local face information by using multi-directional Log Gabor feature map (MGFM) to establish the feature representation of the face image, and the improved cooperative representation classification algorithm using adaptive K nearest neighbor strategy can achieve higher recognition accuracy.

Complex interactions promote the frequency of cooperation in snowdrift game

The emergence and maintains of cooperation in social dilemmas is one of the most popular problem in evolutionary game theory. In this paper, we consider the influence of complex interactions in evolutionary game theory. We consider a situation that some individuals may get additional benefits in snowdrift game without the detriment of the co-player because of difference in status, like good reputation of assisting the weak. We find that the replicator dynamics of asymmetric snowdrift game have one boundary stable equilibrium, which is affected by the asymmetry of the interaction and the proportion of strong individuals. The stable equilibrium shows that strong individuals are willing to choose cooperation and weak individuals are willing to choose defection. In this case, the average frequency of cooperation is not less than the equilibrium frequency of cooperators with only symmetric interactions. In addition, complex interactions in spatially organized populations causes weak individuals to mimic the strategies of strong neighbors. Strong individuals with great benefit are willing to choose cooperation, and cooperators create a cluster with a core of strong cooperators and weak cooperators outside. For a wide range of parameters, the frequency of cooperation among weak individuals grows dramatically. Complex interactions frequently improves the frequency of cooperation while decreasing the frequency of cooperation slightly only over a narrow range of parameter. Because of the high frequency of cooperation, complex interactions can roughly solve the paradox in the snowdrift game.