Search

Abstract This paper proposes an improved adaptive lion swarm optimization (LSO) algorithm integrating the chaotic search strategy and information entropy to address the problem that the standard LSO algorithm has slow convergence and easily falls into the local optimum in later iterations. At first, an adaptive factor is introduced to improve tent chaotic mapping and used for population position initialization to enhance population diversity and realize uniform traversal while ensuring random distribution, ultimately improving the global search ability. Second, to address the problem that the cub selection strategy is blind, resulting in insufficient traversal in the early stage, a dynamic step-size perturbation factor is established using the second-order norm and information entropy. Adaptive parameters are used to dynamically adjust the selection probability of different cub behaviors based on the number of iterations to suppress the premature convergence of the algorithm. Finally, tent chaotic search is employed to adaptively adjust the search range and improve the individuals with poor fitness through multiple neighborhood points of the local optimal solution, further improving the algorithm’s search speed and accuracy. Experimental results on 18 benchmark functions revealed that the proposed algorithm yields superior performance in terms of convergence speed, optimization accuracy, and ability to jump out of the local optimal solution compared with the standard LSO, gray wolf optimizer, and particle swarm optimization algorithms. Furthermore, the improved LSO algorithm was used to optimize the initial weights and thresholds of the BP neural network, and the effectiveness of the proposed algorithm was further verified by studying the house price prediction problem using two real-world datasets.

Abstract Efficient and accurate porosity prediction is essential for the fine description of reservoirs, for which an optimized BP neural network (BPNN) prediction model is proposed. Aiming at the problem that the BPNN is sensitive to initialization and converges to local optimum easily, an improved shuffled frog leaping algorithm (ISFLA) is proposed based on roulette and genetic coding. Firstly, a roulette mechanism is introduced to improve the selection probability of elite individuals, thus enhancing the global optimization ability. Secondly, a genetic coding method is carried out by making full use of effective information such as the global and local optimal solutions and the boundary values of subgroups. Subsequently, the ISFLA algorithm is verified on 12 benchmark functions and compared with four intelligent optimization algorithms, and experimental results show its good optimization performance. Finally, the ISFLA algorithm is applied to the optimization of initial weights and thresholds of the BPNN, and a new model named ISFLA_BP is proposed to study the porosity prediction problem. The logging data is preprocessed by grey correlation analysis and deviation normalization, and then the effective prediction of porosity is achieved by natural gamma, density and other relevant parameters. The performance of ISFLA_BP model is compared with the standard three-layer BPNN and four BPNN parameter optimization methods based on swarm intelligence algorithms. Experimental results show that the proposed model has higher training accuracy, stability and faster convergence speed, with a mean square error of 0.02, and its prediction accuracy for porosity is higher than that of the other five methods.

Abstract To solve the problems of poor stability and low modularity (Q) of community division results caused by the randomness of node selection and label update in the traditional label propagation algorithm, an improved two-stage label propagation algorithm based on LeaderRank was proposed in this study. In the first stage, the order of node updating was determined by the participation coefficient (PC). Then, a new similarity measure was defined to improve the label selection mechanism so as to solve the problem of label oscillation caused by multiple labels of the node with the most similarity to the node. Moreover, the influence of the nodes was comprehensively used to find the initial community structure. In the second stage, the rough communities obtained in the first stage were regarded as nodes, and their merging sequence was determined by the PC. Next, the non-weak community and the community with the largest number of connected edges were combined. Finally, the community structure was further optimized to improve the modularity so as to obtain the final partition result. Experiments were performed on nine classic realistic networks and 19 artificial datasets with different scales, complexities, and densities. The modularity and normalized mutual information (NMI) were used as evaluation indexes for comparing the improved algorithm with dozens of relevant classic algorithms. The results showed that the proposed algorithm yields superior performance, and the results of community partitioning obtained using the improved algorithm were stable and more accurate than those obtained using other algorithms. In addition, the proposed algorithm always performs well in nine large-scale artificial data sets with 6,000 to 50,000 nodes and three large realistic network datasets, which verifies its computational performance and utility in community detection for large-scale networks.

A complex network in reality contains a large amount of information, but some information cannot be obtained accurately or is missing due to various reasons. An uncertain complex network is an effective mathematical model to deal with this problem, but its related research is still in its infancy. In order to facilitate the research into uncertainty theory in complex network modeling, this paper summarizes and analyzes the research hotspots of set pair analysis, rough set theory and fuzzy set theory in complex network modeling. This paper firstly introduces three kinds of uncertainty theories: the basic definition of set pair analysis, rough sets and fuzzy sets, as well as their basic theory of modeling in complex networks. Secondly, we aim at the three uncertainty theories and the establishment of specific models. The latest research progress in complex networks is reviewed, and the main application fields of the three uncertainty theories are discussed, respectively: community discovery, link prediction, influence maximization and decision-making problems. Finally, the prospect of the modeling and development of uncertain complex networks is put forward.

With the increase in the number of live TV channels, audiences must spend increasing amounts of time and energy deciding which shows to watch; this problem is called information overload, and recommender systems (RSs) are effective methods for addressing such problems. Due to the high update rates and low replay rates of TV programs, the item cold-start problem is prominent, and this problem seriously affects the effectiveness of the recommender and limits the application of recommendation algorithms for live TV. To solve this problem better, RSs must consider information in addition to the time slot strategy, which relies on experience. At present, no methods make good use of viewing behavior records. Therefore, in this paper, we proposed a viewing environment model called DeepTV that considers viewing behavior records and electronic program guides and includes a feature generation process and a model construction process. In the feature generation process, we defined seven key features by clustering viewing time, distinguishing positive and negative feedback, capturing continuous viewing preference and introducing the remaining time proportion of candidate programs. We normalize the continuous features and add powers of them. In the model construction process, we regard the live TV recommendation task as a classification problem and fuse the above features by using a neural network. Finally, experiments on industrial datasets show that the proposed model significantly outperforms baseline algorithms.

The current graph-neural-network-based recommendation algorithm fully considers the interaction between users and items. It achieves better recommendation results, but due to a large amount of data, the interaction between users and items still suffers from the problem of data sparsity. To address this problem, we propose a method to alleviate the data sparsity problem by retaining user–item interactions while fully exploiting the association relationships between items and using side-information enhancement. We constructed a “twin-tower” model by combining a user–item training model and an item–item training model inspired by the knowledge distillation technique; the two sides of the structure learn from each other during the model training process. Comparative experiments were carried out on three publicly available datasets, using the recall and the normalized discounted cumulative gain as evaluation metrics; the results outperform existing related base algorithms. We also carried out extensive parameter sensitivity and ablation experiments to analyze the influence of various factors on the model. The problem of user–item interaction data sparsity is effectively addressed.

The rapid development of Virtual Environments (VEs) gives rise to its prominent performance in a myriad of multimedia applications. Accompanied by this is the increasingly massive data used for ascending user's visual experience. Recently, 3D streaming makes it viable to put VEs into real-time use through progressive transmission. Nonetheless, downloading VEs over inevitable lossy networks still remains a major bottleneck that urgently needs to be solved. In this paper, we propose a three-stage progressive transmission scheme for VEs over lossy networks, which aims to minimize distortion even when encountering poor network condition. The first stage is the Pre-coding Stage that offers the most feasible transmission scheme for subsequent transmission, in this stage we combine the advanced interest management algorithm and our proposed scene distortion estimation algorithm to bring up a scene update strategy which takes the user's visual features, quality of the scene and bandwidth estimation into account, so as to determine the download priority comprehensively. In the following Transmitting Stage, we apply Transmission Control Protocol (TCP) to make sure that we convey the essential information. More importantly, we adopt expanding window fountain (EWF) codes to provide an unequal error protection (UEP) for data with different importance. Eventually in the third After-process Stage, we employ a geometry prediction algorithm for the scenario with packet loss. The final results of our experiments show that the three-stage scheme can offer preeminent visual experience especially when it comes to a relatively inferior network condition.

In heterogeneous networks, random walks based on meta-paths require prior knowledge and lack flexibility. On the other hand, random walks based on non-meta-paths only consider the number of node types, but not the influence of schema and topology between node types in real networks. To solve these problems, this paper proposes a novel model HNE-RWTIC (Heterogeneous Network Embedding Based on Random Walks of Type and Inner Constraint). Firstly, to realize flexible walks, we design a Type strategy, which is a node type selection strategy based on the co-occurrence probability of node types. Secondly, to achieve the uniformity of node sampling, we design an Inner strategy, which is a node selection strategy based on the adjacency relationship between nodes. The Type and Inner strategy can realize the random walks based on meta-paths, the flexibility of the walks, and can sample the node types and nodes uniformly in proportion. Thirdly, based on the above strategy, a transition probability model is constructed; then, we obtain the nodes’ embedding based on the random walks and Skip-Gram. Finally, in the classification and clustering tasks, we conducted a thorough empirical evaluation of our method on three real heterogeneous networks. Experimental results show that HNE-RWTIC outperforms state-of-the-art approaches. In the classification task, in DBLP, AMiner-Top, and Yelp, the values of Micro-F1 and Macro-F1 of HNE-RWTIC are the highest: 2.25% and 2.43%, 0.85% and 0.99%, 3.77% and 5.02% higher than those of five other algorithms, respectively. In the clustering task, in DBLP, AMiner-Top, and Yelp networks, the NMI value is increased by 19.12%, 6.91%, and 0.04% at most, respectively.

With the advent of big data and the information age, the data magnitude of various complex networks is growing rapidly. Many real-life situations cannot be portrayed by ordinary networks, while hypergraphs have the ability to describe and characterize higher order relationships, which have attracted extensive attention from academia and industry in recent years. Firstly, this paper described the development process, the application areas, and the existing review research of hypergraphs; secondly, introduced the theory of hypergraphs briefly; then, compared the learning methods of ordinary graphs and hypergraphs from three aspects: matrix decomposition, random walk, and deep learning; next, introduced the structural optimization of hypergraphs from three perspectives: dynamic hypergraphs, hyperedge weight optimization, and multimodal hypergraph generation; after that, the applicability of three uncertain hypergraph models were analyzed based on three uncertainty theories: probability theory, fuzzy set, and rough set; finally, the future research directions of hypergraphs and uncertain hypergraphs were prospected.

The carbide transformation of Cr35Ni45Nb type alloy during service has been investigated in the present work. The primary carbide of the as-cast Cr35Ni45Nb type alloy is M _7 C _3 (M is mainly Cr element) and NbC, which transformed into M _23 C _6 type carbides (M is mainly Cr element) and G phase(Ni _16 Nb _6 Si _7 ) after service, respectively. The G phase and M _23 C _6 carbides mix together and grow up with each other during service. After carburization, the crystal structure of M _23 C _6 type carbide changes again and transforms into M _7 C _3 type carbide. The mechanism of M _23 C _6 → M _7 C _3 carbide reaction is an in situ transformation; the M _7 C _3 type carbide preferentially nucleates at the interface of M _23 C _6 / γ and grows toward the M _23 C _6 type carbide interior. With the diffusion of free carbon atoms into the M _23 C _6 type carbides, the M _23 C _6 type carbides are gradually surrounded by the M _7 C _3 type carbides until they are completely changed into M _7 C _3 type carbides.

Motivated by the wide application in some fields, such as viral marketing, sales promotion etc, influence maximization has been the most important and extensively studied problem in social network. However, the most classical KK-Greedy algorithm for influence maximization is inefficient. Two major sources of the algorithm’s inefficiency were analyzed in this paper. With the analysis of algorithms CELF and CELF++, all nodes in the influenced set of u would never bring any marginal gain when a new seed u was produced. Through this optimization strategy, a lot of redundant nodes will be removed from the candidate nodes. Basing on the strategy, two improved algorithms of Lv_CELF and Lv_CELF++ were proposed in this study. To evaluate the two algorithms, the two algorithms with their benchmark algorithms of CELF and CELF++ were conducted on some real world datasets. To estimate the algorithms, influence degree and running time were employed to measure the performance and efficiency respectively. Experimental results showed that, compared with benchmark algorithms of CELF and CELF++, matching effects and higher efficiency were achieved by the new algorithms Lv_CELF and Lv_CELF++. Solutions with the proposed optimization strategy can be useful for the decisionmaking problems under the scenarios related to the influence maximization problem.