VNU-UET Repository: No conditions. Results ordered -Date Deposited. 2024-03-28T20:53:57ZEPrintshttp://eprints.uet.vnu.edu.vn/images/sitelogo.pnghttps://eprints.uet.vnu.edu.vn/eprints/2022-08-22T04:06:27Z2022-08-22T04:06:27Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4776This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/47762022-08-22T04:06:27ZDynamic-GTN: Learning an Node Efficient Embedding in Dynamic Graph with TransformerGraph Transformer Networks (GTN) use attention mechanism to learn the node representation in a static graph and can achieve state-of-the-art results on several graph learning tasks. However, due to the computation complexity of the attention operation, these models are not applicable to dynamic graphs. In this paper, we propose the Dynamic-GTN model which is designed to learn the node embedding in a continous-time dynamic graph. The Dynamic-GTN extends the attention mechanism in a standard GTN to include temporal information of recent node interaction.
Based on temporal patterns interaction between nodes, an node sampling step is added to reduce the number of attention connections in the dynamic graph.
We evaluate our model on three benchmark datasets for learning node embedding in dynamic graphs.
The results show that the Dynamic-GTN has better accuracy than the state-of-the-art of graph neural networks on both transductive and inductive graph learning tasks.Thi Linh Hoanghoanglinh@vnu.edu.vnViet Cuong Ta2022-08-22T03:58:02Z2022-08-22T03:58:02Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4751This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/47512022-08-22T03:58:02ZA multi-label classification framework using the covering based decision tableMulti-label classification (MLC) has recently drawn much attention thanks to its usefulness and omnipresence in real-world applications, in which objects may be characterized by more than one labels. One of the challenges in MLC is to deter-mine the relationship between the labels due to the fact that there is not any as-sumptions of the independence between labels, and there is not any information and knowledge about these relationships in a training dataset. Recently, many re-searches have focused on exploiting these label relationships to enhance the per-formance of the classification, however there have not many of them using the covering rough set. This paper propose a multi-label classification algorithm named CDTML, based on ML-KNN algorithm, using covering based decision table which exploits the relationship between labels to enhance the performance of the multi-label classifier. The experimental results on serveral dataset of Enron, Medical and a Vietnamese dataset of hotel reviews shown the effectiveness of the proposed algorithm.Thanh-Huyen Phamphamthanhhuyen@daihochalong.edu.vnPhan Van-Tuanblanctuan@gmail.comPham Thi-Nganptngan2012@gmail.comVuong Thi-Honghongvtn@vnu.edu.vnNguyen Tri-Thanhntthanh@vnu.edu.vnHa Quang-Thuythuyhq@vnu.edu.vn2022-08-22T03:57:47Z2022-08-22T03:57:47Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4749This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/47492022-08-22T03:57:47ZA model to detect student’s learning styles in the blended learning courseRecently, personalized learning is becoming more and more popular, especially in blended learning courses. The student learning
style is one of several factors to personalize content and appropriate learning activities for each learner. This article proposes a
model to detect learning styles in blended learning courses to classify learners for personalization. The proposed model focuses
on two phases: the online and face-to-face learning phases of the learning process. Besides, we also present several parameters
to map resources and activities in a blended-learning course to a learning style model. Based on the identified criteria, the
experimental results with 205 students' data when classifying learning styles by the Support Vector Machine method give an
accuracy of 76.7% - 83.2% in the 04 dimensions of the Felder and Silverman model. Experimental results when applying two
approaches: literature-based and driven-based, show that learners' styles are similar up to 83%. Findings show that the student's
learning style does not change much in the learning process. As for course design implications, we also propose suggestions for
developing content and designing learning activities.Viet Anh Nguyenvietanh@vnu.edu.vn2021-12-13T03:56:42Z2021-12-13T03:56:42Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4690This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/46902021-12-13T03:56:42ZEfficient Incremental Instance-based Learning Algorithms for Open World Malware ClassificationMalware is growing rapidly in number and become more and more sophisticated. To prevent them we need to collect samples continuously and update them to the classifier. In this paper, we will propose a method to update new labeled samples of malware to the classifier easily without re-training everything. The classifier can be updated by both labeled malware samples of an existing class or a new class. Our method also has the ability to detect samples of unknown families. Experiments are performed over the traditional computer malware dataset and the IoT malware dataset. The results have shown that our method can reach the macro F1-score almost the same re-train everything but take significantly less time.Dang Kien Hoangkienhd1@vnu.edu.vnDai Tho Nguyennguyendaitho@vnu.edu.vnThi Thu Trang Nguyentrangngtt@vnu.edu.vn2021-10-15T02:48:25Z2021-10-15T02:48:25Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4619This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/46192021-10-15T02:48:25ZA Variability Fault Localization Approach for Software Product LinesSoftware fault localization is one of the most expensive, tedious, and time-consuming activities in program debugging. This activity becomes even much more challenging in Software Product Line (SPL) systems due to variability of failures. These unexpected behaviors are induced by variability faults which can only be exposed under some combinations of system features. The interaction among these features causes the failures of the system. Although localizing bugs in single-system engineering has been studied in-depth, variability fault localization in SPL systems still remains mostly unexplored. In this article, we present VarCop, a novel and effective variability fault localization approach. For an SPL system failed by variability bugs, VarCop isolates suspicious code statements by analyzing the overall test results of the sampled products and their source code. The isolated suspicious statements are the statements related to the interaction among the features which are necessary for the visibility of the bugs in the system. In VarCop, the suspiciousness of each isolated statement is assessed based on both the overall test results of the products containing the statement as well as the detailed results of the test cases executed by the statement in these products. On a large public dataset of buggy SPL systems, our empirical evaluation shows that VarCop significantly improves two state-of-the-art fault localization techniques by 33% and 50% in ranking the incorrect statements in the systems containing a single bug each. In about two-thirds of the cases, VarCop correctly ranks the buggy statements at the top-3 positions in the resulting lists. Moreover, for the cases containing multiple bugs, VarCop outperforms the state-of-the-art approaches 2 times and 10 times in the proportion of bugs localized at the top-1 positions. Especially, in 22% and 65% of the buggy versions, VarCop correctly ranks at least one bug in a system at the top-1 and top-5 positions.Thu Trang Nguyentrang.nguyen@vnu.edu.vnKien Tuan NgoVan Son Nguyensonnguyen@vnu.edu.vnDinh Hieu Vohieuvd@vnu.edu.vn2021-09-15T02:51:09Z2021-09-15T02:51:09Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4608This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/46082021-09-15T02:51:09ZEstimate the memory bounds required by shared variables in software transactional memory programs", ID 280.Ngoc Khai NguyenAnh Hoang TruongDuc Hanh Dang2021-07-15T02:04:52Z2021-07-15T02:04:52Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4566This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/45662021-07-15T02:04:52ZFormal specification and model checking of a recoverable wait-free version of MCSMCS is widely known as one of the most efficient and influential spinning lock mutual exclusion protocols. The protocol, however, only works under the assumption that processes do not crash while acquiring/releasing the lock or being in the critical section. Furthermore, the exit segment pseudo-code of MCS’s algorithm is not wait-free since a process releasing the lock needs to wait for the next process in the virtual queue to perform some steps. A new version of MCS has been proposed by S. Dhoked and N. Mittal such that the new version is wait-free and recoverable (i.e., if some processes crash, the protocol can recover and work normally). In this paper, we formally specify the recoverable wait-free version of MCS and conduct model checking to check whether the protocol enjoys the mutual exclusion property. Our experiments say that: (1) the property is not satisfied if crashes are allowed to occur without any restriction, (2) the protocol enjoys the property if crashes never happen at all, or (3) if crashes have not occurred recently. We also describe the challenge of how to formally specify dynamic memory allocation and present our solution to solve that problem.Duong Tran Dinhduongtd@vnu.edu.vnKentaro Wakikentaro.waki@jaist.ac.jpKazuhiro Ogataogata@jaist.ac.jp2021-07-15T02:04:40Z2021-07-15T02:04:40Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4565This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/45652021-07-15T02:04:40ZSimulation-based invariant verification technique for the OTS/CafeOBJ methodWe demonstrate the power of the simulation-based invariant verification technique through two case studies in which it is formally verified that two mutual exclusion protocols, MCS protocol and Anderson protocol, enjoy the mutual exclusion property by the simulation-based invariant verification technique. We initially attempted formally verifying that the two protocols enjoy the property by the induction-based invariant verification technique. We successfully completed the formal proof for MCS protocol by the simulation-based invariant verification technique earlier than the one by the induction- based invariant verification technique even though we started the latter earlier than the former. We did not successfully complete the formal proof for Anderson protocol by the induction-based invariant verification technique as of the time of this paper submission. We define a variant of simulation, "observably equivalent simulations," and prove some theorems on them to conduct the MCS case study. Given a state machine M, another state machine M' constructed by introducing auxiliary variables into M observably equivalently simulates M. In this sense, M' can be regarded as an abstract version of M.Duong Tran Dinhduongtd@vnu.edu.vnDang Bui Duybddang@jaist.ac.jpKazuhiro Ogataogata@jaist.ac.jp2021-06-28T02:28:35Z2021-06-28T02:28:35Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4523This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/45232021-06-28T02:28:35ZVariability Fault Localization: A BenchmarkSoftware fault localization is one of the most expensive, tedious, and time-consuming activities in program debugging. This activity becomes even much more challenging in Software Product Line (SPL) systems due to the variability of failures in SPL systems. These unexpected behaviors are caused by variability faults which can only be exposed under some combinations of system features. Although localizing bugs in non-configurable code has been investigated in-depth, variability fault localization in SPL systems still remains mostly unexplored. To approach this challenge, we propose a benchmark for variability fault localization with a large set of 1,773 buggy versions of six SPL systems and baseline variability fault localization performance results. Our hope is to engage the community to propose new and better approaches to the problem of variability fault localization in SPL systems.Kien Tuan NgoThu Trang Nguyentrang.nguyen@vnu.edu.vnVan Son Nguyensonnguyen@vnu.edu.vnDinh Hieu Vohieuvd@vnu.edu.vn2021-06-28T02:04:56Z2021-06-28T02:04:56Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4549This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/45492021-06-28T02:04:56ZSolving reduction problems in cover lattice based decision tablesCovering based rough set is an important extension of Paw-lak's traditional rough set. Reduction is a typical application of rough sets, including traditional, cover-ing based and other rough set extensions. Although this task has several pro-posals, it is still an open problem to decision systems (tables) in covering based rough set. This paper focuses on the reduction problem for the condition lattice, and fitting problem for the decision lattice in the decision table based on cover lat-tice. A corresponding algorithm is proposed for each problem. Two examples to illustrate a covering based decision table and two related problems show the ap-plications of these concepts and problemsThanh Huyen Phamphamthanhhuyen@daihochalong.edu.vnThi Ngan Phamnganpt.di12@vnu.edu.vnThuan Hohothuan@vast.ac.vnThi Hong Vuonghongvt_57@vnu.edu.vnTri Thanh Nguyenntthanh@vnu.edu.vnQuang Thuy Hathuyhq@vnu.edu.vn2021-06-28T02:04:40Z2021-06-28T02:04:40Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4550This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/45502021-06-28T02:04:40ZExploiting Social Networks as a Live Mass Media Channel
During Disasters for ReactionsMinh Tien Nguyentiennm@jaist.ac.jpTri Thanh Nguyenntthanh@vnu.edu.vnKitamoto AsanobuVan-Hau Nguyen2020-12-18T09:08:09Z2020-12-18T09:08:09Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4290This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/42902020-12-18T09:08:09ZN-tier machine learning-based architecture for DDoS attack detectionDistributed Denial of Service (DDoS) attack is a menace to network security that aims at exhausting the target networks with malicious traffic. With simple but powerful attack mechanisms, it introduces an immense threat to the current Internet community. In this paper, we propose a novel multi-tier architecture intrusion detection model based on a machine learning method that possibly detects DDoS attacks.
We evaluate our model using the newly released dataset CICDDoS2019, which contains a comprehensive variety of DDoS attacks and address the gaps of the existing current datasets. Experimental results indicated that the proposed method is more efficient than other existing ones. The experiments demonstrated that the proposed model accurately recognize DDoS attacks outperforming the state-of-the-art by F1-score.Thi Hong Vuonghongvt_57@vnu.edu.vnThi Cam Van Nguyenvanntc@vnu.edu.vnQuang Thuy Hathuyhq@vnu.edu.vn2020-12-18T09:07:40Z2020-12-18T09:07:40Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4288This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/42882020-12-18T09:07:40ZA model for building probabilistic knowledge-based systems using divergence distancesThe knowledge-based systems (KBSs) in general and solving the knowledge merging problem in particular have seen a great surge of research activity in recent years. However, there still exist two main shortcomings that need to be addressed in the probabilistic framework. Firstly, the current methods only deal with the problems in which original probabilistic knowledge bases (PKBs) are required to be consistent and formed in the same structure. It is a very strong requirement and difficult to apply in practice. Secondly, only a few measures of distance between probability distributions have been studied to apply in existing models. To overcome these disadvantages, in this paper, we introduce a novel framework for merging PKBs. To this end, a theoretical model is introduced and several experiments are implemented. In theoretical model, some theorems are pointed out and proved to provide mathematical background to construct the merging model. Moreover, a deep survey on how to employ divergence distance functions (DDFs) between probability distributions to carry out the merging process are performed. In experimental aspect, a consistency recovery algorithm and some merging algorithms based on DDFs are proposed. Through the results of conducted experiments, issues about the time cost of merging process, the number of iterations, and CPU Time Elapsed parameter to solve the class of optimization problems in the merging process are analyzed, compared, and evaluated.Van Tham Nguyenthamnv.nute@gmail.comNgoc Thanh Nguyenngoc-thanh.nguyen@pwr.wroc.plTrong Hieu Tranhieutt@vnu.edu.vn2020-12-17T08:27:42Z2020-12-17T08:27:42Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/4286This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/42862020-12-17T08:27:42ZDesign of architecture for carpooling based on flexible pickup and delivery locationsVan Manh TranThi Hong Nhan Vuvthnhan@vnu.edu.vn2018-04-18T03:35:50Z2018-04-18T03:35:50Zhttp://eprints.uet.vnu.edu.vn/eprints/id/eprint/2938This item is in the repository with the URL: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/29382018-04-18T03:35:50ZModern Approaches for Intelligent Information and Database SystemsIntroduction
This book offers a unique blend of reports on both theoretical models and their applications in the area of Intelligent Information and Database Systems. The reports cover a broad range of research topics, including advanced learning techniques, knowledge engineering, Natural Language Processing (NLP), decision support systems, Internet of things (IoT), computer vision, and tools and techniques for Intelligent Information Systems. They are extended versions of papers presented at the ACIIDS 2018 conference (10th Asian Conference on Intelligent Information and Database Systems), which was held in Dong Hoi City, Vietnam on 19–21 March 2018. What all researchers and students of computer science need is a state-of-the-art report on the latest trends in their respective areas of interest. Over the years, researchers have proposed increasingly complex theoretical models, which provide the theoretical basis for numerous applications. The applications, in turn, have a profound influence on virtually every aspect of human activities, while also allowing us to validate the underlying theoretical concepts.