Distributed Triangle Approximately Counting Algorithms in Simple Graph Stream

Recently, the counting algorithm of local topology structures, such as triangles, has been widely used in social network analysis, recommendation systems, user portraits and other fields. At present, the problem of counting global and local triangles in a graph stream has been widely studied, and numerous triangle counting steaming algorithms have emerged. To improve the throughput and scalability of streaming algorithms, many researches of distributed streaming algorithms on multiple machines are studied. In this article, we first propose a framework of distributed streaming algorithm based on the Master-Worker-Aggregator architecture. The two core parts of this framework are an edge distribution strategy, which plays a key role to affect the performance, including the communication overhead and workload balance, and aggregation method, which is critical to obtain the unbiased estimations of the global and local triangle counts in a graph stream. Then, we extend the state-of-the-art centralized algorithm TRIÈST into four distributed algorithms under our framework. Compared to their competitors, experimental results show that DVHT-i is excellent in accuracy and speed, performing better than the best existing distributed streaming algorithm. DEHT-b is the fastest algorithm and has the least communication overhead. What’s more, it almost achieves absolute workload balance.

Attentively Learning Edge Distributions for Semantic Segmentation of Remote Sensing Imagery

Semantic segmentation has been a fundamental task in interpreting remote sensing imagery (RSI) for various downstream applications. Due to the high intra-class variants and inter-class similarities, inflexibly transferring natural image-specific networks to RSI is inadvisable. To enhance the distinguishability of learnt representations, attention modules were developed and applied to RSI, resulting in satisfactory improvements. However, these designs capture contextual information by equally handling all the pixels regardless of whether they around edges. Therefore, blurry boundaries are generated, rising high uncertainties in classifying vast adjacent pixels. Hereby, we propose an edge distribution attention module (EDA) to highlight the edge distributions of leant feature maps in a self-attentive fashion. In this module, we first formulate and model column-wise and row-wise edge attention maps based on covariance matrix analysis. Furthermore, a hybrid attention module (HAM) that emphasizes the edge distributions and position-wise dependencies is devised combing with non-local block. Consequently, a conceptually end-to-end neural network, termed as EDENet, is proposed to integrate HAM hierarchically for the detailed strengthening of multi-level representations. EDENet implicitly learns representative and discriminative features, providing available and reasonable cues for dense prediction. The experimental results evaluated on ISPRS Vaihingen, Potsdam and DeepGlobe datasets show the efficacy and superiority to the state-of-the-art methods on overall accuracy (OA) and mean intersection over union (mIoU). In addition, the ablation study further validates the effects of EDA.

A Novel Active Rehabilitation Model for Stroke Patients Using Electroencephalography Signals and Deep Learning Technology

The main clinical manifestations of stroke are motor, language, sensory, and mental disorders. After treatment, in addition to being conscious, other symptoms will still remain in varying degrees. This is the sequelae of stroke, including numbness, facial paralysis, central paralysis, and central paralysis. If the sequelae of stroke are not treated effectively, they can easily develop into permanent sequelae. Most of the affected people have sequelae, and most of them have symptoms of upper limb paralysis. Therefore, it is of great significance to study how to carry out effective rehabilitation training for stroke patients to reduce the disease and even restore their motor function. Based on this background, this research aims to use deep learning technology to design a stroke rehabilitation model based on electroencephalography (EEG) signals. First, the patient’s EEG signal will be preprocessed. Then, an improved deep neural network model (IDNN) is used to get the EEG classification results. The traditional DNN model construction process is simple and suitable for scenarios where there is no special requirement for the data format, but the generalization of a single DNN model is usually poor. Large margin support vector machine (LM_SVM) is an extension method of support vector machine (SVM), suitable for any occasion. By optimizing the edge distribution, better generalization performance can be obtained. Taking into account the advantages of DNN and LM_SVM and the high aliasing characteristics of stroke data, an improved DNN model is proposed. Finally, based on the EEG recognition result of the model, the rehabilitation equipment is controlled to assist the patient in rehabilitation treatment. The experimental results verify the superiority of the EEG classification model used, and further prove that this research has good practical value.

Copula-Based Method for Estimating the Minimum Void Ratio Parameters of Tailings Deposits

The pore ratio is an important parameter affecting the stability and safety of tailings reservoirs; however, the relationship between the pore ratio and physical properties of tailings sand has not been researched in-depth. In this paper, using the tailings from a tungsten mine in southern Shaanxi as a case study, the correlation between the minimum void ratio and related parameters is analyzed, based on laboratory test data, and the optimal marginal distribution function of the parameters is determined. The Gumbel-Hougard copula function that best describes the correlation between parameters is identified, and it is used to establish the joint probability distribution model of the three parameters, and the guarantee rate α is introduced to estimate and analyze the minimum void ratio. The results show that the optimal edge distribution of the fine particle content and specific gravity follows a truncated normal distribution, and the optimal edge distribution of the minimum void ratio follows a logarithmic normal distribution. According to AIC criterion, the Gumbel-Hougard copula is the best three-dimensional copula function to fit the minimum void ratio and related parameters. When the guarantee rate α is 0.485, the joint probability distribution model achieves optimal performance in terms of estimating the minimum void ratio. The maximum error of the estimation is 1.99%, which is verified through data, and the estimation meets the requirements for practical engineering. The method proposed in this paper uses the existing measured data to establish a joint probability distribution model and combines the collected fine particle content and specific gravity data with the guarantee rate to estimate the minimum void ratio, providing a novel basis for the study of the physical properties of tailings.

Evaluation of Tourism Development Potential on Provinces along the Belt and Road in China: Generation of a Comprehensive Index System

The evaluation of tourism development potential (TDP) is the crucial foundation and critical step for sustainable regional tourism development. Prior studies mainly evaluate TDP through the univariate potential model and the multi-indicator descriptive evaluation. However, these two methods have only limited effectiveness for the destination’s TDP in the context of the mesoscale level. Thus, this study aims to develop an effective multi-dimensional mesoscale to evaluate the destination’s TDP and construct a potential index model. Based on the literature review, this study develops four rule layers (tourism supply and consumption (X1), the demand and purchasing power of tourist source (X2), development value of destination resources (X3), and the contribution of the destination’s tourism industry (X4)) and 31 factor layers. All the factor layers are then assigned values based on the provincial statistics in China in 2019. Through SPSS 24.0, the current study uses the principal component analysis (PCA) to construct a provincial TDP index model for the research area: Y=0.2573X1+0.1305X2+0.3177X3+0.2945X4. The results show significant regional differences in the TDP index of the provinces along the Belt and Road (study area) in China. Among them, Guangdong has the most extensive TDP index, Qinghai has the smallest TDP index. The study also uses ArcGIS 10.2 for the function of kernel density analysis to visualize provincial TDP and finds significant spatial differences and a central-edge distribution pattern across provinces.

Emergence of spatial transitions in urban congestion dynamics

The quantitative study of traffic dynamics is crucial to ensure the efficiency of urban transportation networks. The current work investigates the spatial properties of congestion, that is, we aim to characterize the city areas where traffic bottlenecks occur. The analysis of a large amount of real road networks in previous works showed that congestion points experience spatial abrupt transitions, namely they shift away from the city center as larger urban areas are incorporated. The fundamental ingredient behind this effect is the entanglement of central and arterial roads, embedded in separated geographical regions. In this paper we extend the analysis of the conditions yielding abrupt transitions of congestion location. First, we look into the more realistic situation in which arterial and central roads, rather than lying on sharply separated regions, present spatial overlap. It results that this affects the position of bottlenecks and introduces new possible congestion areas. Secondly, we pay particular attention to the role played by the edge distribution, proving that it allows to smooth the transitions profile, and so to control the congestion displacement. Finally, we show that the aforementioned phenomenology may be recovered also as a consequence of a discontinuity in the node’s density, in a domain with uniform connectivity. Our results provide useful insights for the design and optimization of urban road networks, and the management of the daily traffic.

An adaptive node embedding framework for multiplex networks

Network Embedding (NE) has emerged as a powerful tool in many applications. Many real-world networks have multiple types of relations between the same entities, which are appropriate to be modeled as multiplex networks. However, at random walk-based embedding study for multiplex networks, very little attention has been paid to the problems of sampling bias and imbalanced relation types. In this paper, we propose an Adaptive Node Embedding Framework (ANEF) based on cross-layer sampling strategies of nodes for multiplex networks. ANEF is the first framework to focus on the bias issue of sampling strategies. Through metropolis hastings random walk (MHRW) and forest fire sampling (FFS), ANEF is less likely to be trapped in local structure with high degree nodes. We utilize a fixed-length queue to record previously visited layers, which can balance the edge distribution over different layers in sampled node sequence processes. In addition, to adaptively sample the cross-layer context of nodes, we also propose a node metric called Neighbors Partition Coefficient (NPC). Experiments on real-world networks in diverse fields show that our framework outperforms the state-of-the-art methods in application tasks such as cross-domain link prediction and mutual community detection.

Lemp: a Robust Image Feature Descriptor for Retrieval Applications

line edge magnitude pattern (lemp) is proposed in this paper. Line edge distribution is used to denote local region of an image. Popular texture descriptors such as lbp deal with a comparison of centre pixel with neighbors and thus encode the information. In lemp ,pixel at the centre is replaced by edge values of neighbors. Discriminating information provided by line edges makes this method different from many of the existing methods. Magnitude is also added to the line edge information in order to make the feature descriptor more effective and robust. Performance of lemp method is estimated with corel database. Standard metrics such as recall, precision and average retrieval rate are determined for comparison purpose. Experimental values exhibit a notable improvement in the performance.