Journal Articles - Computer and Information Technology - 2021

Permanent URI for this collection

http://repository.vlu.edu.vn:443/handle/123456789/102

Browse

Browsing Journal Articles - Computer and Information Technology - 2021 by Title

  • Publication
    Automatic clustering algorithm for interval data based on overlap distance
    ( 2021)
    Ngoc Lethikim
    ;
    Tuan Lehoang
    ;
    Tai Vovan
    In this study, the improved overlap distance is used as a criterion in order to build clusters for interval data. This distance has shown the suitability, and given an outstanding advantage in evaluating the similarity for intervals with a lot of the considered data sets. Based on the overlap distance, we propose the Automatic Clustering Algorithm for Interval data (ACAI). One of the best advantages of the proposed algorithm is that ACAI figure out simultaneously the appropriate number of groups, and factors in every group. The proposed algorithm can be effectively performed through a Matlab procedure. Based on the extracted intervals from texture of images, we have applied ACAI to recognize the images, an interesting and challenging issue at present. Experimental data sets including the differences of the characteristics as well as the number of elements has shown the reasonableness of the proposed algorithm, and its advantages in comparing to the surviving ones. From the image recognition problem, this research has shown prospect in practical applications for many fields.
  • Publication
    D2D Multi-hop Multi-path Communications in B5G Networks: A Survey on Models, Techniques, and Applications
    ( 2021)
    Quang-Nhat Tran
    ;
    Nguyen-Son Vo
    ;
    Quynh-Anh Nguyen
    ;
    Minh-Phung Bui
    ;
    Thanh-Minh Phan
    ;
    Van-Viet Lam
    ;
    Antonino Masaracchia
    In 5G networks, device-to-device (D2D) communications have played an important role in enlarging the coverage, relaxing the workload of backhaul links of both macro base stations (MBSs) and small-cell base stations (SBSs), and serving the mobile users (MUs) local applications and services at high capacity. However, beyond 5G (B5G or 6G) networks will require disruptive solutions that can assist D2D communications to meet numerous advanced applications and services requested by dense MUs. One of the most efficient solutions for D2D communications is multi-hop multi-path (MHMP). In this paper, we present a detailed survey of the so called D2D MHMP communications in terms of models, techniques, and applications for B5G networks. We discuss and propose the future research directions of D2D MHMP communications. All the models, techniques, and applications as well as future research directions of D2D MHMP communications provide the useful insights into B5G networks design and optimisation.
  • Publication
    Fuzzy clustering algorithm for outlier-interval data based on the robust exponent distance
    ( 2021)
    Dinh Phamtoan
    ;
    Khanh Nguyenhuu
    ;
    Tai Vovan
    The outlier elements of a data are ones that differs significantly from others. For many reasons, we have to face with outlier elements in data analysis for the different fields. Because an outlier element can cause the serious problems in statistical analyses, studying about it is interested in many researchers. This article proposes the fuzzy clustering algorithm for outlier - interval data based on the robust exponent distance to overcome the drawback of traditional clustering algorithm which to clean the outliers before performing. The outstanding advantage of this algorithm is to find the suitable number of clusters, to cluster for the interval data with outlier elements, and to determine the probability belonging to clusters for the intervals at the same time. The proposed algorithm is described step by step via numerical examples, and can be performed effectively by the Matlab procedure. In addition, it also applied in reality with the air pollution, mushroom, and image data sets. These real applications demonstrate the robustness of the proposed algorithm in comparison with the existing ones.
  • Publication
    Image Recognition Using Unsupervised Learning Based Automatic Fuzzy Clustering Algorithm
    ( 2021)
    Lê Thị Kim Ngọc
    This article proposes a novel techniques for unsupervised learning in image recognition using automatic fuzzy clustering algorithm (AFCA) for discrete data. There are two main stages in order to recognize images in this study. First of all, new technique is shown to extract sixty four textural features from n images represented by a matrix n × 64. Afterwards, we use the proposed method based on Hausdorff distance to simultaneously determine the appropriate number of clusters. At the end of the unsupervised clustering process, discrete data belonging to the same cluster converge to the same position, which represents the cluster’s center. After determining number of cluster, we have probability of assigning objects to the established clusters. The simulation result built by Matlab program shows the effectiveness of the proposed method using the corrected rand, the partition entropy, and the partition coefficients index. The experimental outcomes illustrate that the proposed method is better than the existing ones as Fuzzy C-mean. As a result, we believe that the proposed method is filled with a potential possibility which can be applied in practical realization.
  • Publication
    New Betweenness Centrality Node Attack Strategies for Real-World Complex Weighted Networks
    ( 2021)
    Quang Nguyen
    ;
    Ngoc-Kim-Khanh Nguyen
    ;
    Davide Cassi
    ;
    Michele Bellingeri
    ;
    Giacomo Fiumara
    In this work, we introduce a new node attack strategy removing nodes with the highest conditional weighted betweenness centrality (CondWBet), which combines the weighted structure of the network and the node’s conditional betweenness. We compare its efficacy with well-known attack strategies from literature over five real-world complex weighted networks. We use the network weighted efficiency (WEFF) like a measure encompassing the weighted structure of the network, in addition to the commonly used binary-topological measure, i.e., the largest connected cluster (LCC). We find that if the measure is WEFF, the CondWBet strategy is the best to decrease WEFF in 3 out of 5 cases. Further, CondWBet is the most effective strategy to reduce WEFF at the beginning of the removal process, whereas the Strength that removes nodes with the highest sum of the link weights first shows the highest efficacy in the final phase of the removal process when the network is broken into many small clusters. These last outcomes would suggest that a better attacking in weighted networks strategy could be a combination of the CondWBet and Strength strategies.
  • Publication
    Nonparametric estimation of cumulative distribution function from noisy data in the presence of Berkson and classical errors
    ( 2021)
    Cao Xuan Phuong
    ;
    Le Thi Hong Thuy
    ;
    Vo Nguyen Tuyet Doan
    Let X, Y ,W, δ and ε be continuous univariate random variables defined on a probability space such that Y = X + ε and W = X + δ. Herein X, δ and ε are assumed to be mutually independent. The variables ε and δ are called classical and Berkson errors, respectively. Their distributions are known exactly. Supposewe only observe a random sample Y1, . . . , Yn from the distribution of Y . This paper is devoted to a nonparametric estimation of the unknown cumulative distribution function FW of W based on the observations as well as on the distributions of ε, δ. An estimator for FW depending on a smoothing parameter is suggested. It is shown to be consistent with respect to the mean squared error. Under certain regularity assumptions on the densities of X, δ and ε, we establish some upper and lower bounds on the convergence rate of the proposed estimator. Finally, we perform some numerical examples to illustrate our theoretical results.
  • Publication
    Periodic Time Series Forecasting with Bidirectional Long Short-Term Memory
    ( 2021)
    Dung Quoc Nguyen
    ;
    Minh Nguyet Phan
    ;
    Ivan Zelinka
    Deep learning methods such as recurrent neural network and long short-term memory have recently drawn a lot of attentions in many fields such as computer vision, natural language processing and finance. Long short-term memory is a type of recurrent neural network capable of predicting future values of sequential data by learning observed data over time. Many real-world time series in business, finance, weather forecasting and engineering science have periodic property like daily, monthly, quarterly or yearly period and need efficient tools to forecast their future events and values. The forecasting study and tools in these fields are therefore essential and important. In this paper, we present a deep learning technique, called bidirectional long short-term memory, in forecasting time series data. The bidirectional long short-term memory model is evaluated based on the benchmark periodic time series dataset. The model performs well on the macro and industry categories and achieves average mean absolute percentage errors less than 9%. It is shown that the bidirectional architecture obtains the better results than the baseline models. We also test the model by tuning the time step parameter to evaluate how the time step length impacts on forecasting performance of the model.
  • Publication
    Replication of a nonlinear dynamical system’s trajectory using the ANFIS technique
    ( 2021)
    Tri Quoc Truong
    Machine Learning technique demonstrates various successes in the analysis of the nonlinear dynamical system. However, the limitation of previous research is that it is difficult to predict the trajectory solution for a long-time evolution. To overcome this problem, we consider a novelty approach in the Machine Learning field, named Adaptive Neuro-Fuzzy Inference System (ANFIS). By applying this method, we replicate the system’s chaotic solution based only on data collected along with time evolution. We numerically confirm the effectiveness of the ANFIS method in time series prediction.