EDITORIAL BOARD
Editor-In-Chief
Bui Thu Lam, Le Quy Don Technical University
Deputy Editor-In-Chief
Tran Xuan Nam, Le Quy Don Technical University
Advisory Member
Pham The Long, Le Quy Don Technical University
Editors
Nguyen Binh, Posts and Telecommunications Institute of Technology
Dinh The Cuong, Directorate of Information Technology
Luong Chi Mai, Vietnam Academy of Science and Technology
Huynh Quyet Thang, Hanoi University of Science and Technology
Nguyen Huu Thanh, Hanoi University of Science and Technology
Vu Duc Thi, Vietnam National University, Hanoi
Nguyen Thanh Thuy, Vietnam National University, Hanoi
Dao Thanh Tinh, Le Quy Don Technical University
Scientific Secretary
Nguyen Van Giang, Le Quy Don Technical University
Table: Issue 7
ID Paper
Title
Author
Page
Abstract
[Pdf link]
12.01
Sampling method for evolving multiple subpopulations in genetic programming.
Chu Thi Huong, Nguyen Quang Uy
5-16
Sampling techniques are the techniques that use a subset of the training data instead of the full data. These approaches have recently used in Genetic Programing (GP) to speed up the evolving process and to improve its performance. In this paper, we propose a new sampling technique that evolves multiple subpopulations on the sampled datasets. A number of subdatasets are sampled from the training data and a subpopulation is evolved on each of these datasets for a predefined generations. The subpopulations are then combined to form a full population that is evolved on the full training dataset for the rest generations. We tested this sampling technique (shorted as SEMS-GP) on seventeen regression problems and compared its performance to standard GP and two recently proposed sampling techniques (Interleaved Sampling and Random Interleaved). The experimental results show that SEMS-GP achieved better performance compared to other tested methods. Particularly, the training error and the size of the solutions found by SEMS-GP are often significantly better than those found by others.
12.02
Application of Nash Equilibrium based approach in solving the risk responses conflicts.
Trinh Bao Ngoc, Huynh Quyet Thang, Nguyen Xuan Thang, Ngo Van Quyen, Vu Thanh Trung.
17-31
The responses to a given risk reflect the risk assessment and the organization’s attitude to risk, response method to risk can cause a problem to the response method of another risk. Therefore, the project manager cannot decide which risk response will be used in case of conflicts happen. Until now, the amount of research which deals with risk responses is count-on-finger. This paper proposes a model and the algorithm to resolve this conflict. The problem-solving model introduced below will base on Project Network and Game Theory, in which players of the game are risks, and the solution of this game is a Nash Equilibrium. The input information of the game will be described in the Project Network model, which can be used later in a Genetic Algorithm. The chromosome model of Genetic Algorithm is a Nash Equilibrium of the game whereas providing the balance in selecting a response method to each risk.
12.03
Combining transfer learning and case-based reasoning for an educational decision making support model.
Pham Thanh Tri, Vo Thi Ngoc Chau, Nguyen Hua Phung.
32-47
In the educational domain, study extension is considered for in-trouble students. If a decision is proper, it can advance the success of the students. To provide decision making support for this problem, a materialization of an educational decision making support model is proposed with our transfer learning-based algorithm, named CombinedTL, by integrating transfer learning into the case-based reasoning framework. All the processes of the model (case base construction, problem solving, and case base maintenance) can be well supported and enhanced by CombinedTL. In an empirical study, CombinedTL is evaluated in each process of the materialized model on real data sets. Experimental results have confirmed that CombinedTL is more effective than the others with higher Accuracy and F-measure values. This also implies that to some extent, the feasibility and applicability of our model can be taken into consideration in practice to provide appropriate information for decision making support on in-trouble students.
12.04
A hybrid approach of fuzzy clustering and particle swarm optimization method for land-cover classification.
Mai Dinh Sinh, Ngo Thanh Long, Trinh Le Hung
48-63
In remote sensing image analysis, semi-supervised fuzzy clustering techniques improves the accuracy of unsupervised fuzzy clustering due to the supplement of some labelled data. However, these algorithms are often difficult to choose for the fuzzy parameter and the initial centroids, which may affect the results of the algorithm. In this research, a hybrid approach of fuzzy clustering and particle swarm optimization method based on semi-supervised method for remote sensing imagery analysis (SFCM-PSO) is proposed to overcome the above disadvantages. This method consists of two main parts: using labelled data in a new objective function for clustering, and optimizing fuzzy parameters and cluster centroids by PSO. In this research, Landsat-8 OLI satellite imagery data of Hanoi and Spot-5 image of Chu Prong (Gia Lai) have been classified into 6 types of land-cover. Test results were evaluated by some indicators including S index, XB index, PC index, CE index, D index, $\tau$ index, CS index and compared on labeled data sets, it has been shown that classification results are improved compared to some other algorithms.
12.05
A general coordinate formula for designing phased array antennas in cylindrical shape with triangular grid.
Nguyen Dinh Tinh, Nguyen Tuan Hung, Trinh Dang Khanh, Nguyen Manh Cuong, Duong Huy Binh.
64-74
This paper proposes a mathematical model of coordinate combination in a particular shape of phased array antennas, namely, the cylindrical arrays with triangular grid (CATG), which are used in sonar applications. With the proposed solution, phase distribution in the CATG can be synthesized mathematically to calculate the radiation patterns when the main beam needs to be steered to any desirable direction. The results are calculated in both cases of with and without mutual coupling. The validity of the solution is evaluated by comparing the derived radiation patterns with that resulted by the tool Sensor Array Analyzer of MATLAB. However, the tool does not provide the information of phase distribution of all elements, radiation pattern formula of the CATG and requires users to enter coordinates of all elements in the array. The formulas of phase distribution and radiation patterns in this paper are the basis to design any CATG.