Random Walk Procedure Research Articles

AE-RW: Predicting miRNA-disease associations by using autoencoder and random walk on miRNA-gene-disease heterogeneous network

Since scientific investigations have demonstrated that aberrant expression of miRNAs brings about the incidence of numerous intricate diseases, precise determination of miRNA-disease relationships greatly contributes to the advancement of human medical progress. To tackle the issue of inefficient conventional experimental approaches, numerous computational methods have been proposed to predict miRNA-disease association with enhanced accuracy. However, constructing miRNA-gene-disease heterogeneous network by incorporating gene information has been relatively under-explored in existing computational techniques. Accordingly, this paper puts forward a technique to predict miRNA-disease association by applying autoencoder and implementing random walk on miRNA-gene-disease heterogeneous network(AE-RW). Firstly, we integrate association information and similarities between miRNAs, genes, and diseases to construct a miRNA-gene-disease heterogeneous network. Subsequently, we consolidate two network feature representations extracted independently via an autoencoder and a random walk procedure. Finally, deep neural network(DNN) are utilized to conduct association prediction. The experimental results demonstrate that the AE-RW model achieved an AUC of 0.9478 through 5-fold CV on the HMDD v3.2 dataset, outperforming the five most advanced existing models. Additionally, case studies were implemented for breast and lung cancer, further validated the superior predictive capabilities of our model.

Filtering and Parallel Diffusive Fractal Characterization of 2-Dimensional Images

The article presents a complete solution for filtering and diffusive fractal characterization of 2-dimensional images. This includes preparing the sample by subtracting background, application of random walk procedure and its parallelization using two different approaches. For each technique the processing time is measured to compare speedups with regard to a sequential implementation. To prove the correctness of the results, a black square is used as the reference sample, for which diffusive fractal dimension is known and equls 2. Finally the results for a complex image are elaborated.

Improving Network Representation Learning via Dynamic Random Walk, Self-Attention and Vertex Attributes-Driven Laplacian Space Optimization.

Network data analysis is a crucial method for mining complicated object interactions. In recent years, random walk and neural-language-model-based network representation learning (NRL) approaches have been widely used for network data analysis. However, these NRL approaches suffer from the following deficiencies: firstly, because the random walk procedure is based on symmetric node similarity and fixed probability distribution, the sampled vertices’ sequences may lose local community structure information; secondly, because the feature extraction capacity of the shallow neural language model is limited, they can only extract the local structural features of networks; and thirdly, these approaches require specially designed mechanisms for different downstream tasks to integrate vertex attributes of various types. We conducted an in-depth investigation to address the aforementioned issues and propose a novel general NRL framework called dynamic structure and vertex attribute fusion network embedding, which firstly defines an asymmetric similarity and h-hop dynamic random walk strategy to guide the random walk process to preserve the network’s local community structure in walked vertex sequences. Next, we train a self-attention-based sequence prediction model on the walked vertex sequences to simultaneously learn the vertices’ local and global structural features. Finally, we introduce an attributes-driven Laplacian space optimization to converge the process of structural feature extraction and attribute feature extraction. The proposed approach is exhaustively evaluated by means of node visualization and classification on multiple benchmark datasets, and achieves superior results compared to baseline approaches.

Global random walk solvers for reactive transport and biodegradation processes in heterogeneous porous media

Flow and multicomponent reactive transport in saturated/unsaturated porous media are modeled by ensembles of computational particles moving on regular lattices according to specific random walk rules. The occupation number of the lattice sites is updated with a global random walk (GRW) procedure which spreads the particles from a lattice site with computational costs comparable to those for a single random walk step in sequential procedures. To cope with the nonlinearity and the degeneracy of the Richards equation the GRW flow solver uses linearization techniques similar to the L-scheme developed in finite element/volume approaches. Numerical schemes for reactive transport, coupled with the flow solver via numerical solutions for saturation and water flux, are implemented in splitting procedures. Diffusion–advection steps are solved by GRW algorithms using either biased or unbiased random walk probabilities. Since the number of particles in GRW simulations can be as large as the number of molecules involved in chemical reactions, one avoids the cumbersome problem of rescaling particle densities to approximate concentrations. Reaction steps are therefore formulated in terms of concentrations, as in deterministic approaches. The numerical convergence of the new schemes is demonstrated by comparisons with manufactured analytical solutions. Coupled flow and reactive transport problems of contaminant biodegradation described by the Monod model are further solved and the influence of flow nonlinearity/degeneracy and of the spatial heterogeneity of the medium is investigated numerically.

Fieldwork opportunities and challenges in Palestinian refugee camps in the West Bank, occupied Palestinian territory, and in Jordan: lessons learned from a Palestinian adolescent reproductive health cross-sectional study

BackgroundPalestinian refugee camps have lasted for more than 70 years. Generally the residents are poor and the camps are crowded and politically unstable, with a range of social, cultural, and economic constraints. Studying the adolescent reproductive health of girls in refugee camps is crucial yet challenging, primarily because of its sensitive nature. We use experiences from a cross-sectional study of Palestinian adolescent reproductive health to discuss methodological challenges and opportunities for researching this subject in the context of refugee camps. MethodsWe completed a household survey in Palestinian refugee camps in the West Bank (19 camps) and Jordan (ten camps) from June to September, 2019. Data from 2949 adolescent girls aged 15–18 years (1443 from the West Bank and 1506 from Jordan) were collected in relation to menarche and menstruation, mental health, and nutrition. A fingerprick haemoglobin test for anaemia was conducted among participating girls. Data were collected by women fieldworkers using electronic tablets. Written consent was obtained from girls and their mothers or a female caregiver for both the survey and the blood tests. Consent to enter the household was obtained first, then consent from girls. FindingsResponse rates at the household level were 3573 (87%) of 4103 and 3210 (74%) of 4314 for the West Bank and Jordan, respectively, and for girls were 1443 (95%) of 1522 and 1506 (99%) of 1526 for the West Bank and Jordan, respectively. This seemed to suggest a higher level of trust and willingness to participate in the West Bank compared with Jordan at the household level, although this seemed almost no problem for the girls as long as their caregivers had agreed. During data collection, we encountered fieldwork challenges at political, social, cultural, and structural levels. When recruiting participants, fieldworkers used a random-walk procedure, as it was hard for them to track their route in the narrow, unstructured, and unidentified camp roads and alleyways, which caused delays and disruption to the process. Crowded households posed an ethical challenge in securing girls’ privacy, particularly in more conservative Jordan. Furthermore, we encountered resistance to fingerprick blood tests owing to fear of contamination, particularly in the more politically unstable camps in the West Bank. The political situation also affected fieldwork in the West Bank by limiting working hours owing to road closures and Israeli army incursions. Despite this, fieldworkers were able to develop a good rapport with participants, especially when the fieldworkers themselves were camp dwellers. Engagement and involvement with local organisations was essential for research teams to gain the trust of families and girls, enabling valuable and credible data collection. InterpretationWhen conducting studies in Palestinian refugee camps, especially on sensitive issues, it is crucial to know the camp well, obtain assistance from local organisations to acquaint and familiarise the population with the research, and to use trained fieldworkers from the local community. Finally, and most importantly, it is essential to be flexible and to have contingency plans that include extra time, personnel, and resources that may be needed to overcome unforeseen circumstances. FundingInternational Development Research Centre (IDRC), Ottawa, Canada.

Network structural perturbation against interlayer link prediction

Interlayer link prediction aims at matching the same entities across different layers of the multiplex network. Existing studies attempt to predict more accurately, efficiently, or generically from the aspects of network structure, attribute characteristics, and their combination. Few of them analyze the effects of intralayer links. Namely, few works study the backbone structures which can effectively preserve the predictive accuracy while dealing with a smaller number of intralayer links. It can be used to investigate what types of intralayer links are most important for correct prediction. Are there any intralayer links whose presence leads to worse predictive performance than their absence, and how to attack the prediction algorithms at the minimum cost? To this end, two kinds of network structural perturbation methods are proposed. For the scenario where the structural information of the whole network is completely known, we offer a global perturbation strategy that gives different perturbation weights to different types of intralayer links and then selects a predetermined proportion of intralayer links to remove according to the weights. In contrast, if these information cannot be obtained at one time, we design a biased random walk procedure, local perturbation strategy, to execute perturbation. Four kinds of interlayer link prediction algorithms are carried out on different real-world and artificial perturbed multiplex networks. We find out that the intralayer links connected with small degree nodes have the most significant impact on the prediction accuracy. The intralayer links connected with large degree nodes may have side effects on the interlayer link prediction.

Use of and barriers to maternal health services in southeast Chad: results of a population-based survey 2019

ObjectivesChad reports the second highest maternal mortality worldwide. We conducted a survey in Sila region in southeast Chad to estimate the use of maternal health services (MHS) and to identify...

Surrogate modeling of the CLIC final-focus system using artificial neural networks

Artificial neural networks can be used for creating surrogate models that can replace computationally expensive simulations. In this paper, a surrogate model was created for a subset of the Compact Linear Collider (CLIC) final-focus system. By training on simulation data, we created a model that maps sextupole offsets to luminosity and beam sizes, thus replacing computationally intensive tracking and beam-beam simulations. This model was then used for optimizing the parameters of a random walk procedure for sextupole alignment.

Clustering of graphs using pseudo-guided random walk

Clustering is an unsupervised learning task that models data as coherent groups. Multiple approaches have been proposed in the past to cluster large volumes of data. Graphs provide a logical mapping of many real-world datasets rich enough to reflect various peculiarities of numerous domains. Apart from k-means, k-medoid, and other well-known clustering algorithms, utilization of random walk-based approaches to cluster data is a prominent area of data mining research. Markov clustering algorithm and limited random walk-based clustering are the prominent techniques that utilize the concept of random walk. The main goal of this work is to address the task of clustering graphs using an efficient random walk-based method. A novel walk approach in a graph is presented here that determines the weight of the edges and the degree of the nodes. This information is utilized by the pseudo-guidance model to guide the random walk procedure. This work introduces the friends-of-friends concept during the random walk process so that the edges’ weights are determined utilizing an inclusive criterion. This concept enables a random walk to be initiated from the highest degree node. The random walk continues until the walking agent cannot find any unvisited neighbor(s). The agent walks to its neighbors if it finds a weight of one or more, otherwise the agent’s stopping criteria is met. The nodes visited in this walk form a cluster. Once a walk comes to halt, the visited nodes are removed from the original graph and the next walk starts in the remaining graph. This process continues until all nodes of the graph are traversed. The focus of this work remains random walk-based clustering of graphs. The proposed approach is evaluated using 18 real-world benchmark datasets utilizing six cluster validity indices, namely Davies-Bouldin index (DBI), Dunn index (DI), Silhouette coefficient (SC), Calinski-Harabasz index (CHI), modularity index, and normalized cut. This proposal is compared with seven closely related approaches from the same domain, namely, limited random walk, pairwise clustering, personalized page rank clustering, GAKH (genetic algorithm krill herd) graph clustering, mixing time of random walks, density-based clustering of large probabilistic graphs, and Walktrap. Experiments suggest better performance of this work based on the evaluation metrics.

Extending Voronoi-diagram based modeling of oil slick spreading to surface tension-viscous spreading regime

An earlier paper demonstrated a methodology for modeling the spreading process with a Gaussian random walk procedure, but was limited to the gravity-viscous spreading regime. Here we extend the methodology of representing spread and transport of oil slicks on calm sea surface by updated Voronoi diagrams to account for the surface tension-viscous spreading regime as well. We have utilized the analogy between diffusion and spreading processes by defining a step length for the particle-based random walk scheme. In this study, calculation of the diffusive length is improved by including the surface tension term in the numerical solution method. The results from the numerical simulation of the spreading oil slick agree very well with the analytical solutions. The solution is robust in that good agreement is achieved for a large range of model and numerical solution parameters. This modeling procedure remains valid only for passive, quiescent spreading. The inclusion of spreading due to important horizontal and vertical turbulent shear processes in the Voronoi diagram paradigm remains a challenge for future work.

Things2Vec: Semantic Modeling in the Internet of Things With Graph Representation Learning

The advent of fifth generation (5G) enables the Internet of Things (IoT) to connect a massive number of things. The interaction and communication among these things generate an enormous amount of context-aware data that is semantically diverse. Traditional data representation approaches, such as semantic annotation, ontology, and semantic Web technology are rule based, which lack flexibility and adaptability when applied to IoT. To address the challenge, this article mainly focuses on the problem of semantic representation, which is essential for processing and fusion of IoT data. To serve as a bridge, we propose a high-level framework, namely, Things2Vec, which aims to produce the latent semantic representations from the interaction of things through the graph embedding technique. These semantic representations benefit various IoT semantic analysis tasks, such as the IoT service recommendation and automation of things. In Things2Vec, we utilize the graph to model the function sequence relationships that are generated by the interaction of things, which is called the IoT context graph. Since these function sequence relationships are heterogeneous in terms of semantics, it causes general graph embeddings to fail to learn complete information. Thus, we propose a biased random walk procedure, which is tailored to capture the neighborhoods of nodes with different types of semantic relationships. Extensive experiments are carried out, and our results show that the proposed method can effectively capture the semantic relationships among context-aware data in IoT.

SPWalk: Similar Property Oriented Feature Learning for Phishing Detection

Detecting phishing webpages is an essential task that protects legitimate websites and their users from various malicious activities. To classify the suspect webpage as phishing or legitimate, robust and effective features used for classification are in demand. However, recent phishing attacks usually make phishing webpages resemble the legitimate webpages in visual and functional aspects. This poses a greater difficulty for feature extraction. We herein propose SPWalk , an unsupervised feature learning algorithm for phishing detection. In SPWalk , similar property nodes refer to a collection of phishing webpages or legitimate webpages. We first construct a weblink network with nodes representing webpages. The edges between nodes represent the reference relationships that connect webpages through hyperlinks or similar textual content. Then, SPWalk applies the network embedding technique to mapping nodes into a low-dimensional vector space. A biased random walk procedure efficiently integrates both structural information between nodes and URL information of each node. The effectiveness and robustness of SPWalk come from three points. (1). Phishing attackers do not have full control over reference relationships . (2). The structural regularities generated by diverse reference relationships can be exploited to discriminate between phishing and legitimate webpages. (3). Node URL information makes the learned node representations more suited for phishing detection. Using node as numeric features, we conduct experiments to classify webpages as legitimate or phishing. We demonstrate the superiority of SPWalk over state-of-the-art techniques on phishing detection, especially in terms of precision (over 95%). Even in the case that phishing webpages are well camouflaged by attackers for evading detection, SPwalk exhibits better classification efficacy consistently.

Community-oriented attributed network embedding

Network embedding aims to map vertices in a complex network into a continuous low-dimensional vector space. Meanwhile, the original network structure and inherent properties must be preserved. Most of the existing methods merely focus on preserving local structural features of vertices, whereas they largely ignore the community patterns and rich attribute information. For example, the title of papers in an academic citation network could imply their research directions, which are potentially valuable in seeking more meaningful representations of these papers. In this paper, we propose a Community-oriented Attributed Network Embedding (COANE) framework, which can smoothly incorporate the community information and text contents of vertices into network embedding. We design a margin-based random walk procedure on the network coupled with flexible margins among communities, which limit the scope of random walks. Inspired by the analogy between vertex sequences and documents, the statistical topic model is adopted to extract community features in the network. Furthermore, COANE integrates textual semantics into representations through the topic model while preserving their structural correlations. Experiments on real-world networks indicate that our proposed method outperforms six state-of-the-art network embedding approaches on network visualization, vertex classification and link prediction.

Mortality and health survey, Walikale, Democratic Republic of the Congo, 2017: an example of the use of survey data for humanitarian program planning

BackgroundDuring humanitarian crises, health information systems are often lacking and surveys are a valuable tool to assess the health needs of affected populations. In 2013, a mortality and health survey undertaken by Médecins Sans Frontières (MSF) in the conflict affected Walikale territory of North Kivu, Democratic Republic of the Congo (DRC), indicated mortality rates exceeding humanitarian crisis thresholds and a high burden of mortality and morbidity due to malaria. In late 2017, after a period of relative stability, MSF reassessed the health status of the population through a second survey to guide ongoing operations.MethodsA two-stage cluster survey, selecting villages using probability proportional to size and households using random walk procedures, was conducted. Household members were interviewed on morbidity and mortality, healthcare use, vaccination status, and bednet availability.ResultsThe sample included 5711 persons in 794 households. The crude mortality rate (CMR) and under-five mortality rate (U5MR) were 0.98 per 10,000 persons/day (95% confidence interval (CI) 0.78–1.2) and 1.3 per 10,000 persons/day (95% CI): 0.82–2.0), respectively. The most frequently reported causes of death were fever/malaria (31%), diarrhoea (15%) and respiratory infections (8%). In 89% of households at least one person was reported as falling ill in the previous 2 weeks, and 58% sought healthcare. Cost was the main barrier amongst 58% of those who did not seek healthcare. Coverage of measles-containing-vaccine was 62% in under-fives. Sufficient bednet coverage (1 bednet/2 people) was reported from 17% of households.ConclusionThe second survey illustrates that although mortality is now just below crisis thresholds, the area still experiences excess mortality and has substantial health needs. The study results have supported the further expansion of integrated community case management to improve access to care for malaria, diarrhoea and respiratory infections. Such surveys are important to orient operations to the health needs of the population being served and also highlight the ongoing vulnerability of populations after humanitarian crises.

Drug Side-Effect Prediction Via Random Walk on the Signed Heterogeneous Drug Network.

Drug side-effects have become a major public health concern as they are the underlying cause of over a million serious injuries and deaths each year. Therefore, it is of critical importance to detect side-effects as early as possible. Existing computational methods mainly utilize the drug chemical profile and the drug biological profile to predict the side-effects of a drug. In the utilized drug biological profile information, they only focus on drug–target interactions and neglect the modes of action of drugs on target proteins. In this paper, we develop a new method for predicting potential side-effects of drugs based on more comprehensive drug information in which the modes of action of drugs on target proteins are integrated. Drug information of multiple types is modeled as a signed heterogeneous information network. We propose a signed heterogeneous information network embedding framework for learning drug embeddings and predicting side-effects of drugs. We use two bias random walk procedures to obtain drug sequences and train a Skip-gram model to learn drug embeddings. We experimentally demonstrate the performance of the proposed method by comparison with state-of-the-art methods. Furthermore, the results of a case study support our hypothesis that modes of action of drugs on target proteins are meaningful in side-effect prediction.

DISL: Deep Isomorphic Substructure Learning for network representations

The analysis of complex networks based on deep learning has drawn much attention recently. Generally, due to the scale and complexity of modern networks, traditional methods are gradually losing the analytic efficiency and effectiveness. Therefore, it is imperative to design a network analysis model which caters to the massive amount of data and learns more comprehensive information from networks. In this paper, we propose a novel model, namely Deep Isomorphic Substructure Learning (DISL) model, which aims to learn network representations from patterns with isomorphic substructures. Specifically, in DISL, deep learning techniques are used to learn a better network representation for each vertex (node). We provide the method that makes the isomorphic units self-embed into vertex-based subgraphs whose explicit topologies are extracted from raw graph-structured data, and design a Probability-guided Random Walk (PRW) procedure to explore the set of substructures. Sequential samples yielded by PRW provide the information of relational similarity, which integrates the information of correlation and co-occurrence of vertices and the information of substructural isomorphism of subgraphs. We maximize the likelihood of the preserved relationships for learning the implicit similarity knowledge. The architecture of the Convolutional Neural Networks (CNNs) is redesigned for simultaneously processing the explicit and implicit features to learn a more comprehensive representation for networks. The DISL model is applied to several vertex classification tasks for social networks. Our results show that DISL outperforms the challenging state-of-the-art Network Representation Learning (NRL) baselines by a significant margin on accuracy and weighted-F1 scores over the experimental datasets.

Citation recommendation based on citation tendency

Due to the development of academic, more and more attentions are paid to citation recommendation. To solve the citation recommendation problem, researchers begin to focus on the network representation, because it fuses semantic information and structural information well. It is a big challenge that how to map articles in a heterogeneous information network into a low-dimensional space while preserving the potential associations between articles. We propose a novel citation recommendation algorithm based on citation tendency, named CIRec which learns more about the potential relationship of articles in the process of network embedding. Citation tendency means if an article can be selected as a reference, it probability satisfies some kinds of conditions. In our algorithm, five weight matrices which represent the probability of entity-to-entity migration based on citation tendency are defined to build weighted heterogeneous network first. Second, we design a biased random walk procedure which efficiently explores articles’ characteristics and citations information. Finally, the skip-gram model is used to learn the neighborhood relationship of the nodes in the walk sequence and map the nodes to the vector space. Comparing with existing state-of-the-art technique, experiment results show that our algorithm CIRec has better recall, precision, NDCG on AAN and DBLP dataset.

Weighted superposition attraction algorithm for combinatorial optimization

Weighted Superposition Attraction (WSA) is a swarm based metaheuristic algorithm that is lately proposed for solving continuous optimization problems. Performance of the WSA was comprehensively tested with numerous unconstrained/constrained optimization problems. Due to its reasonable performance on continuous optimization problems we were motivated to develop a combinatorial version of WSA. A new method is devised to handle combinatorial problems without requiring an indirect representation mechanism like random keys. A random walk procedure is integrated into the combinatoric WSA (cWSA) so as to improve its diversification capability. Additionally, opposition based learning is also integrated into cWSA to increase its performance further. Performance of cWSA is tested on two well-known combinatorial optimization problems, namely the Resource Constrained Project Scheduling Problem (RCPSP) and the Permutation Flow Shop Scheduling Problem (PFSP). The results of the extensive computational study point out the efficiency of the proposed cWSA.

HYBRID IMPROVED BACTERIAL SWARM OPTIMIZATION ALGORITHM FOR HAND-BASED MULTIMODAL BIOMETRIC AUTHENTICATION SYSTEM

This paper proposes a Hybrid Improved Bacterial Swarm (HIBS) optimization algorithm for the minimization of Equal Error Rate (EER) as a performance measure in a hand-based multimodal biometric authentication system. The hybridization of the algorithm was conducted by incorporating Bacterial Foraging Optimization (BFO) and Particle Swarm Optimization (PSO) algorithm to mitigate weaknesses in slow and premature convergence. In the proposed HIBS algorithm, the slow convergence of BFO algorithm was mitigated by using the random walk procedure of Firefly algorithm as an adaptive varying step size instead of using fixed step size. Concurrently, the local optima trap (i.e. premature convergence) of PSO algorithm was averted by using mutation operator. The HIBS algorithm was tested using benchmark functions and compared against classical BFO, PSO and other hybrid algorithms like Genetic Algorithm-Bacterial Foraging Optimization (GA-BFO), Genetic Algorithm-Particle Swarm Optimization (GA-PSO) and other BFO-PSO algorithms to prove its exploration and exploitation ability. It was observed from the experimental results that the EER values, after the influence of the proposed HIBS algorithm, dropped to 0.0070% and 0.0049% from 1.56% and 0.86% for the right and left hand images of the Bosphorus database, respectively. The results indicated the ability of the proposed HIBS in optimization problem where it optimized relevant weights in an authentication system.

A Nonasymptotic Approach to Analyzing Kidney Exchange Graphs

We propose a novel methodology to study kidney exchange. Using a random graph model of kidney exchange, we propose a nonasymptotic approach to quantifying the effectiveness of transplant chains in reducing the number of unmatched highly sensitized patients. Our approach is based on a two-phase random walk procedure where random walks are used to allocate chains, followed by allocation in cycles. The benefit of random walks is that they preserve the probabilistic structure of residual graphs, greatly facilitating analysis. Our approach allows us to analytically show the benefit of chains, as opposed to transplantation in cycles only, in nonasymptotic (medium-sized) graphs. We also derive useful analytical bounds that illustrate the performance of our proposed allocation procedure and more general kidney allocation procedures. Our results complement previous findings from analytical results in large (limit) graphs and empirical results based on data from fielded kidney exchanges demonstrating the benefits of chains. Moreover, our analysis sheds light on the relative importance of chains versus cycles in kidney allocation. In particular, our results show prioritizing chains over easy-to-transplant cycles, as opposed to prioritizing those cycles over chains, improves performance and provides analytical bounds on the associated benefits. A detailed simulation study numerically verifies our main results and provides additional insights. The online appendix is available at https://doi.org/10.1287/opre.2017.1717 .