Walk Algorithm Research Articles

A spam worker detection approach based on heterogeneous network embedding in crowdsourcing platforms

Due to the popularity of crowdsourcing, more crowds are participating in crowdsourcing tasks. However, the proportion of spam workers is continuously increasing due to the openness of crowdsourcing platforms and their incentive mechanisms. To defend against threats from spam workers, researchers have proposed reputation-based and verification-based detection methods, but they either cannot address various collusion patterns or are costly when facing a large number of spam workers with "good" reputations due to collusion. Therefore, we propose a spam worker detection approach based on heterogeneous network embedding. We first model three collusion patterns and analyze the characteristics of spam workers to provide a theoretical basis for detecting spam workers. We then transform the problem of spam worker detection into a node classification problem in a crowdsourcing heterogeneous network in which the vectors of worker nodes are learned using network embedding. To improve the efficiency of network embedding, we propose an improved variable-length random walk algorithm based on node centrality. Finally, based on the obtained vectors of worker nodes, a one-class SVM is used to detect spam workers. The experiments demonstrate that our proposed approach can effectively detect spam workers in different collusion patterns and that the proposed random walk algorithm can reduce the time spent on model training while improving the efficiency of network embedding.

Goal‐oriented design of optimal degree distribution for LT codes

Goal-oriented Luby transform (LT) codes are required in different scenarios. Based on the random walk model, analysis of ripple size evolution provides an effective method to design LT codes. However, the ripple addition in each step depends on both the number of symbols released in the current step and the ripple size in the last step, leading to distortion. Therefore, the authors propose a random walk algorithm with barrier (RWA-B) to model the ripple addition directly. To evaluate the performance of ripple size evolution, they utilise generalised degree distribution algorithm to generate corresponding degree distribution. Through analysing the relationship between the performance of generated ripple size evolution and the parameters of RWA-B, they design an iterator greedy algorithm to search the optimal ripple size evolution for desired goals. As a result, they compare three goal-oriented degree distributions with others through numerical simulations. In binary erasure channel, both the memory usage oriented and block error rate (BER) oriented degree distributions outperform others with lowest average overhead, and the overhead oriented degree distribution outperforms others in terms of average overhead and average degree. In additive white Gaussian noise channel, the BER-oriented degree distribution outperforms others in terms of BER and average overhead.

A Method of Directional Signs Location Selection and Content Generation in Scenic Areas

The Tourist Oriented Directional Signs (TODS) system is an essential and important project in constructing and planning scenic areas. At present, the placement of directional signs generally depends on the personal experience of the tour manager to identify important positions and display the name of critical scenic spots on a signboard. Few studies have focused on how to generate the location and display the content of directional signs automatically. This article proposes a method for directional sign location selection and automatic generation of content in a scenic area based on the tourist spatial behavior theory and network analysis algorithm. Junction nodes of the road in a scenic area are used as the candidate locations of the directional signs to be placed. The main steps of the method in this paper include tourist route simulation, betweenness centrality calculation, location selection, and content generation. The Ming Tomb in Nanjing, China, is selected as the experimental area. The evaluation indexes of the traveled distance and the number of errors were adopted. The random walk algorithm is applied to compare the generated scheme with the existing scheme in the experimental scenic area. The generated scheme is also verified through questionnaires and interviews. The results show that the method proposed in this paper can select relevant and appropriate junction nodes where to deploy directional signs and automatically generate displayed content more prominently. The comparison shows that the generated scheme in this method is significantly better than the actual placement scheme. It can optimize the actual placement scheme in the experimental area, and it also can reduce the traveled distance and number of errors.

Organ Contouring for Lung Cancer Patients with a Seed Generation Scheme and Random Walks.

In this study, we proposed a semi-automated and interactive scheme for organ contouring in radiotherapy planning for patients with non-small cell lung cancers. Several organs were contoured, including the lungs, airway, heart, spinal cord, body, and gross tumor volume (GTV). We proposed some schemes to automatically generate and vanish the seeds of the random walks (RW) algorithm. We considered 25 lung cancer patients, whose computed tomography (CT) images were obtained from the China Medical University Hospital (CMUH) in Taichung, Taiwan. The manual contours made by clinical oncologists were taken as the gold standard for comparison to evaluate the performance of our proposed method. The Dice coefficient between two contours of the same organ was computed to evaluate the similarity. The average Dice coefficients for the lungs, airway, heart, spinal cord, and body and GTV segmentation were 0.92, 0.84, 0.83, 0.73, 0.85 and 0.66, respectively. The computation time was between 2 to 4 min for a whole CT sequence segmentation. The results showed that our method has the potential to assist oncologists in the process of radiotherapy treatment in the CMUH, and hopefully in other hospitals as well, by saving a tremendous amount of time in contouring.

The identification of six risk genes for ovarian cancer platinum response based on global network algorithm and verification analysis.

Ovarian cancer is the most lethal gynaecological cancer, and resistance of platinum‐based chemotherapy is the main reason for treatment failure. The aim of the present study was to identify candidate genes involved in ovarian cancer platinum response by analysing genes from homologous recombination and Fanconi anaemia pathways. Associations between these two functional genes were explored in the study, and we performed a random walk algorithm based on reconstructed gene‐gene network, including protein‐protein interaction and co‐expression relations. Following the random walk, all genes were ranked and GSEA analysis showed that the biological functions focused primarily on autophagy, histone modification and gluconeogenesis. Based on three types of seed nodes, the top two genes were utilized as examples. We selected a total of six candidate genes (FANCA, FANCG, POLD1, KDM1A, BLM and BRCA1) for subsequent verification. The validation results of the six candidate genes have significance in three independent ovarian cancer data sets with platinum‐resistant and platinum‐sensitive information. To explore the correlation between biomarkers and clinical prognostic factors, we performed differential analysis and multivariate clinical subgroup analysis for six candidate genes at both mRNA and protein levels. And each of the six candidate genes and their neighbouring genes with a mutation rate greater than 10% were also analysed by network construction and functional enrichment analysis. In the meanwhile, the survival analysis for platinum‐treated patients was performed in the current study. Finally, the RT‐qPCR assay was used to determine the performance of candidate genes in ovarian cancer platinum response. Taken together, this research demonstrated that comprehensive bioinformatics methods could help to understand the molecular mechanism of platinum response and provide new strategies for overcoming platinum resistance in ovarian cancer treatment.

Coupling network vertex representation learning based on network embedding method

Network representation learning is a basic problem in network data analysis. By learning network representation vectors, network vertices can be represented more accurately. With the development of deep learning, embedding methods have been widely used for network vertex representation learning. Providing that network data have changed in terms of their scale and modality, the research focus gradually shifted from single network mining to coupling network mining. This paper first analyzes the research status of embedding methods for single networks and then compares their advantages and disadvantages. Furthermore, the paper presents a model called CWCNE for coupling network embedding. The random walk and training algorithms of the proposed model are improved to adapt to coupling network features. The validity of the proposed model was verified using social, academic, film, poetry, and work coupling network data. Good results were obtained on community detection, entity recognition, and label classification tasks.

Fair and trustworthy: Lock-free enhanced tendermint blockchain algorithm

Blockchain Technology is exclusively used to make online transactions secure by maintaining a distributed and decentralized ledger of records across multiple computers. Tendermint is a general-purpose blockchain engine that is composed of two parts; Tendermint Core and the blockchain application interface. The application interface makes Tendermint suitable for a wide range of applications. In this paper, we analyze and improve Practical Byzantine Fault Tolerant (PBFT), a consensus-based Tendermint blockchain algorithm. In order to avoid negative issues of locks, we first propose a lock-free algorithm for blockchain in which the proposal and voting phases are concurrent whereas the commit phase is sequential. This consideration in the algorithm allows parallelism. Secondly, a new methodology is used to decide the size of the voter set which is a subset of blockchain nodes, further investigating the block sensitivity and trustworthiness of nodes. Thirdly, to fairly select the voter set nodes, we employ the random walk algorithm. Fourthly, we imply the wait-freedom property by using a timeout due to which all blocks are eventually committed or aborted. In addition, we have discussed voting conflicts and consensuses issues that are used as a correctness property, and provide some supportive techniques.

Salient Object Detection Based on Weighted Hypergraph and Random Walk

Recently, salient object detection based on the graph model has attracted extensive research interest in computer vision because the graph model can represent the relationship between two regions better. However, it is difficult to capture the high-level relationship between multiple regions. In this algorithm, the input image is segmented into superpixels first. Then, a weighted hypergraph model is established using fuzzy C-means clustering algorithm and a new weighting strategy. Finally, the random walk algorithm is used to sort all superpixels on the weighted hypergraph model to obtain the salient object. The experimental results on three benchmark datasets demonstrate that the proposed method performs better than some other state-of-the-art methods.

Adversarial Attack: A New Threat to Smart Devices and How to Defend It

This article introduces adversarial attack, a recently-unveiled security threat to consumer electronics, especially those utilizing machine learning techniques. We start with the fundamental knowledge including what are adversarial examples, how to realize such attacks, and common defense methods. Adversarial training enhances models' resilience to adversarial attacks by taking both regular and adversarial examples for training. However, applying adversarial examples under a single adversarial strength provide defense in a very limited effective range. We propose a multiple-strength adversarial training method. A random walk algorithm is adopted to optimize the selection of adversarial strengths, which is closely related to the design cost and training time. We also analyze the hardware cost and quantization loss to guide future consumer electronics designs.

Investigation of Hybrid Locomotive Robot for Anti-Personnel Mine Detection

Most of landmine detection robots proposed so far have been strongly restricted from locomotion inside the mine field because they cannot cross over the mine. So we have proposed a mine detection robot with hybrid locomotion, which can enter inside the minefield with low ground surface contact, which can cross over the mine instead of changing its path and scan landmines directly using Electro Magnetic Induction sensor. The hybrid locomotion proposed in the robot uses the frame walking technique and the conventional wheeled locomotion. The robot switches over the locomotion mechanism from wheeled to leg when mine is detected and vice versa with a lead screw mechanism. The leg locomotion is achieved by frame walking technique where the two frames translate with the help of lead screw mechanism. A purpose of adopting this combination is to evade anti-personnel landmines which are relatively smaller in comparison to their anti-tank landmine counterparts. The robot initially starts in wheeled mode and upon detection of metal, pulls in the frame walking algorithm. The robot also deploys an obstacle avoidance algorithm when working in wheel mode.

A Novel Drug Repositioning Approach Based on Integrative Multiple Similarity Measures.

Drug repositioning refers to discovering new indications for the existing drugs, which can improve the efficiency of drug research and development. In this work, a novel drug repositioning approach based on integrative multiple similarity measure, called DR_IMSM, is proposed. The process of integrative similarity measure contains three steps. First, a heterogeneous network can be constructed based on known drug-disease association, shared entities information for drug pairwise and diseases pairwise. Second, a deep learning method, DeepWalk, is used to capture the topology similarity for drug and disease. Third, a similarity integration and adjusting process is further conducted to obtain more comprehensive drug and disease similarity measure, respectively. On this basis, a Bi-random walk algorithm is implemented in the constructed heterogeneous network to rank diseases for each drug. Compared with other approaches, the proposed DR_IMSM can achieve superior performance in terms of AUC on the gold standard datasets. Case studies further confirm the practical significance of DR_IMSM.

A Nodes-Based Non-Structural Model Considering a Series Structure for Heat Exchanger Network Synthesis

The aim of heat exchanger network synthesis is to design a cost-effective network configuration with the maximum energy recovery. Therefore, a nodes-based non-structural model considering a series structure (NNM) is proposed. The proposed model utilizes a simple principle based on setting the nodes on streams such that to achieve optimization of a heat exchanger network synthesis (HENS) problem. The proposed model uses several nodes to quantify the possible positions of heat exchangers so that the matching between hot and cold streams is random and free. Besides the stream splits, heat exchangers with series structures are introduced in the proposed model. The heuristic algorithm used to solve NNM model is a random walk algorithm with compulsive evolution. The proposed model is used to solve four scale cases of a HENS problem, the results show that the costs obtained by NNM model can be respectively lower 3226 $/a(Case 1), 11,056 $/a(Case 2), 2463 $/a(Case 3), 527 $/a(Case 4) than the best costs listed in literature.

Dynamic locomotion for passive-ankle biped robots and humanoids using whole-body locomotion control

Whole-body control (WBC) is a generic task-oriented control method for feedback control of loco-manipulation behaviors in humanoid robots. The combination of WBC and model-based walking controllers has been widely utilized in various humanoid robots. However, to date, the WBC method has not been employed for unsupported passive-ankle dynamic locomotion. As such, in this article, we devise a new WBC, dubbed the whole-body locomotion controller (WBLC), that can achieve experimental dynamic walking on unsupported passive-ankle biped robots. A key aspect of WBLC is the relaxation of contact constraints such that the control commands produce reduced jerk when switching foot contacts. To achieve robust dynamic locomotion, we conduct an in-depth analysis of uncertainty for our dynamic walking algorithm called the time-to-velocity-reversal (TVR) planner. The uncertainty study is fundamental as it allows us to improve the control algorithms and mechanical structure of our robot to fulfill the tolerated uncertainty. In addition, we conduct extensive experimentation for: (1) unsupported dynamic balancing (i.e., in-place stepping) with a six-degree-of-freedom biped, Mercury; (2) unsupported directional walking with Mercury; (3) walking over an irregular and slippery terrain with Mercury; and 4) in-place walking with our newly designed ten-DoF viscoelastic liquid-cooled biped, DRACO. Overall, the main contributions of this work are on: (a) achieving various modalities of unsupported dynamic locomotion of passive-ankle bipeds using a WBLC controller and a TVR planner; (b) conducting an uncertainty analysis to improve the mechanical structure and the controllers of Mercury; and (c) devising a whole-body control strategy that reduces movement jerk during walking.

Stochastic simulation algorithms for solving a nonlinear system of drift–diffusion-Poisson equations of semiconductors

Stochastic simulation algorithms for solving transient nonlinear drift diffusion recombination transport equations are developed. The governing system of equations includes two drift–diffusion equations coupled with a Poisson equation for the potential whose gradient forms the drift velocity. A stochastic algorithm for solving nonlinear drift–diffusion equations is proposed here for the first time. In each time step, the method calculates the solution on a cloud of points using a new global Monte Carlo random walk and Cellular Automata algorithms. The Poisson equation is solved by a global version of the Random Walk on Spheres method which calculates both the solutions and the derivatives without using finite difference approximations. The method is also able to calculate fluxes to any desired part of the boundary, from arbitrary sources. For transient drift–diffusion equations we suggest a stochastic expansion from cell to cell algorithm for calculating the whole solution field. All new global random walk algorithms developed in this paper are validated by comparing the simulation results with exact solutions. Application of the developed method to solve a system of 2D transport equations for electrons and holes in a semiconductor is given.

Tensorial graph learning for link prediction in generalized heterogeneous networks

Tensorial graph learning frameworks are proposed for link predictions in heterogeneous, homogeneous and generalized heterogeneous networks. In these frameworks, tensorial graphs are used to represent different networks by incorporating node and edge tensors into the graphs. A tensorial graph kernel method is developed for link predictions in these networks using four types of, i.e., structural, behavioral, content and node/edge characteristics, data. In this method, a n-strand iterated algorithm and a tensorial graph based random walk algorithm are proposed to measure node similarities in different networks within the generalized heterogeneous networks, and a tensorial graph multi-kernel learning method is developed to integrate the results. Experimental results on two real-world social media databases show that the tensorial graph kernel method has better performance using all types of data than using one type of data alone or combinations of some types of data. The tensorial graph kernel method also performs considerably better than existing competitive methods.

Quantum fast hitting on glued trees mapped on a photonic chip

Quantum walks on graphs play an important role in the field of quantum algorithms. Fast hitting is one of the properties that quantum walk algorithms can utilize to outperform classical random walk algorithms. Fast hitting refers to a particle starting from the entrance node on a graph and trying to hit the exit node quickly. Especially, continuous-time quantum walks on random glued binary trees have been investigated in theories extensively for their exponentially faster hitting speed over classical random walks. Here, using heralded single photons to represent quantum walkers and laser-written waveguide arrays to simulate the theoretical graph, we are able to demonstrate the hitting efficiency of quantum walks with tree depth as high as 16 layers for the first time. Furthermore, we expand the graph’s branching rate from 2 to 5, revealing that quantum walks can exhibit more superiority over classical random walks as the branching rate increases. Our results may shed light on the physical implementation of quantum walk algorithms as well as quantum computation and quantum simulation.

Attentional multi-level representation encoding based on convolutional and variance autoencoders for lncRNA-disease association prediction.

As the abnormalities of long non-coding RNAs (lncRNAs) are closely related to various human diseases, identifying disease-related lncRNAs is important for understanding the pathogenesis of complex diseases. Most of current data-driven methods for disease-related lncRNA candidate prediction are based on diseases and lncRNAs. Those methods, however, fail to consider the deeply embedded node attributes of lncRNA-disease pairs, which contain multiple relations and representations across lncRNAs, diseases and miRNAs. Moreover, the low-dimensional feature distribution at the pairwise level has not been taken into account. We propose a prediction model, VADLP, to extract, encode and adaptively integrate multi-level representations. Firstly, a triple-layer heterogeneous graph is constructed with weighted inter-layer and intra-layer edges to integrate the similarities and correlations among lncRNAs, diseases and miRNAs. We then define three representations including node attributes, pairwise topology and feature distribution. Node attributes are derived from the graph by an embedding strategy to represent the lncRNA-disease associations, which are inferred via their common lncRNAs, diseases and miRNAs. Pairwise topology is formulated by random walk algorithm and encoded by a convolutional autoencoder to represent the hidden topological structural relations between a pair of lncRNA and disease. The new feature distribution is modeled by a variance autoencoder to reveal the underlying lncRNA-disease relationship. Finally, an attentional representation-level integration module is constructed to adaptively fuse the three representations for lncRNA-disease association prediction. The proposed model is tested over a public dataset with a comprehensive list of evaluations. Our model outperforms six state-of-the-art lncRNA-disease prediction models with statistical significance. The ablation study showed the important contributions of three representations. In particular, the improved recall rates under different top $k$ values demonstrate that our model is powerful in discovering true disease-related lncRNAs in the top-ranked candidates. Case studies of three cancers further proved the capacity of our model to discover potential disease-related lncRNAs.

Identification of prognostic biomarkers and drug target prediction for colon cancer according to a competitive endogenous RNA network.

Colorectal cancer is one of the commoner digestive tract malignant tumor types, and its incidence and mortality rate are high. Accumulating evidence indicates that long-chain non-coding RNAs (lncRNAs) and protein-coding RNAs interact with each other by competing with the same micro(mi)RNA response element (MREs) and serve an important role in the regulation of gene expression in a variety of tumor types. However, the regulatory mechanism and prognostic role of lncRNA-mediated competing endogenous (ce)RNA networks in colon cancer have yet to be elucidated. The expression profiles of mRNAs, lncRNAs and miRNAs from 471 colon cancer and 41 paracancerous tissue samples were downloaded from The Cancer Genome Atlas database. A lncRNA-miRNA-mRNA ceRNA network in colon cancer was constructed and comprised 17 hub lncRNAs, 87 hub miRNA and 144 hub mRNAs. The topological properties of the network were analyzed, and the random walk algorithm was used to identify the nodes significantly associated with colon cancer. Survival analysis using the UALCAN database indicated that 2/17 lncRNAs identified [metastasis-associated lung adenocarcinoma transcript (MALAT1) and maternally expressed gene 3 (MEG3)] and 5/144 mRNAs [FES upstream region (FURIN), nuclear factor of activated T-cells 5 (NFAT5), RNA Binding Motif Protein 12B (RBM12B), Ras related GTP binding A (RRAGA) and WD repeat domain phosphoinositide-interacting protein 2 (WIPI2)] were significantly associated with the overall survival of patients with colon cancer, and may therefore be used as potential prognostic biomarkers of colon cancer. According to extracted lncRNA-miRNA-mRNA interaction pairs, the GSE26334 dataset was used to confirm that the lncRNA MALAT1/miR-129-5p/NFAT5 axis may represent a novel regulatory mechanism concerning the progression of colon cancer. The clusterProfiler package was used to analyze Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways in colon cancer. Finally, drugs that significantly interact with the core genes identified in colon cancer were predicted using a hypergeometric test. Of these, fostamatinib was identified to be a targeted drug for colon cancer therapy. The present findings provide a novel perspective for improved understanding of the lncRNA-associated ceRNA network and may facilitate the development of novel targeted therapeutics in colon cancer.

Developing An Intelligent Logistics and Distribution System For A Large Number of Retail Outlets: A Big Data Analytics Approach

The logistics and distribution system in the retail industry in Indonesia has its own complexity. The growth and productivity of the retail outlets in Indonesia have been increasing from year to year. Distribution activities in this study are related to the formation of salesman visit routes involving around 38,900 customer base retail outlets, which are quite numerous in number, calling for a challenging approach to find the optimized solution. Therefore, the case study in this research will be discussed on the concept of the Traveling Salesman Problem (TSP) and the Vehicle Routing Problem (VRP), considering the work balance and visit pattern constraints. The methods used in this research are the balanced K-means and the Minimum Span Tree – Kruskal’s Walk algorithm, which are proven to solve the problem with a shorter computation time and a more balanced daily route than the current conditions as the results.

Prediction of Specific Subtypes and Common Markers of Non-Small Cell Lung Cancer Based on Competing Endogenous RNA Network.

BackgroundThere are various pathological types of lung cancer, including squamous cell carcinoma and adenocarcinoma. Although both of them are lung cancers, there are significant differences in diagnosis, pathogenesis, location, imaging, metastasis, and treatment. According to the competing endogenous RNA (ceRNA) theory, long non-coding RNAs (lncRNAs) compete with encoding protein genes (mRNAs) to connect with miRNAs, thus affecting the level of mRNA.Material/MethodsFirst, using the t test, we identified mRNAs and lncRNAs that have different expressions (fold change >2, P<0.01) in normal samples and in tumor samples. We calculated the significance of the shared miRNAs for mRNAs and lncRNAs by hypergeometric test (P<0.01). Further, mRNA and lncRNA pairs with co-expression relationships in cancer samples were used to establish ceRNA networks. Then, the random walk algorithm was used to optimize the specific ceRNA networks and identify potential prognostic markers of survival. Finally, we built a common ceRNA network to find markers of non-small-cell lung cancer.ResultsWe identified some potential key markers, such as PVT1, LINC00472, CDKN2A, and FAM83B, in LUSC and HOXA11-AS, HNF1A-AS1, LINC00511, and HOTAIR in LUAD by analyzing the ceRNA networks. Moreover, a number of common ceRNA pairs, such as CDC25C/CDK1/RRM2-LINC00355, have been found, and they are also significant markers for tumor survival and prognosis.ConclusionsIn summary, the present study provides a comparative analysis in 2 kinds of lung cancer ceRNA networks. Some specific and common markers we predicted that may be of great importance for clinical diagnosis and treatment.