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
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: Current Issue
ID Paper
[Pdf link]
Self-adaptive crossover and mutation parameters in tree adjoining grammar guided genetic programming.
Le Hai Nam, Hoang Tuan Hao, Vu Van Canh
In some Evolutionary Computations such as Genetic Algorithms or Evolution Strategies, it is well known that the choice of genetic operator rates is important to the success of these algorithms. Researchers mainly focused on choosing genetic operator rates appropriate to specific problems. Several papers work on adapting crossover and mutation rate in evolutionary algorithms showing potential results that adaptive algorithms may out-perform non-adaptive ones. In this paper, we examine the application of adaptive operator selection rates to genetic programming and propose a new algorithm for self-adapting crossover and mutation rates in the specific genetic programming - Tree Adjoining Grammar Guided Genetic Programming (TAG3P). Experimental results showed that our proposed algorithm improved the performance of TAG3P than previous works.
A new reversible watermarking scheme using difference expansion for pixel vectors.
Do Van Tuan, Tran Dang Hien, Pham Duc Long, Pham Van At
Difference expansion (DE) is an important technique for designing reversible watermarking schemes. In this paper we propose a new reversible watermarking algorithm by using the idea of DE for vectors of image pixel values. For each vector, an element is selected as a basic element and differences are generated by subtracting the basic element from other elements. Each small difference can be used for embedding a bit by using the DE technique. In our new scheme, the position of a basic element is adjusted adaptively on each vector so that the differences have small absolute values. As a consequence, the embedding capacity and the watermarked image quality of the scheme are improved. Experimental results show that the proposed scheme has higher embedding capacity and better image quality in comparison with many existing reversible watermarking methods.
Bilateral filtering with clusters by expectation maximization.
Dao Nam Anh
Image restoration keeping sharp edges is achieved by bilateral filter. In this paper, an approach to improve edges for the filter is presented. The proposed algorithm relies on clustering by Expectation Maximization that produced clusters of intensive values. A stage is followed where standard deviation of Gaussian filters for scales of the spatial and intensity are adjusted by features of the clusters. This makes the filters have adaptive levels of smoothing for specific clusters and helps to preserve edges while remove noise. Experiments and evaluation by PSNR metrics indicated the restoration quality enhanced and the efficacy of the proposed adaptive bilateral filter algorithm.
An effective model for rating product aspects from customer reviews using neural networks.
Pham Duc Hong, Le Anh Cuong, Le Hoan
Opinion mining and sentiment analysis has been one of the attracting topics of knowledge mining and natural language processing in recent years. The problem of rating product aspects from textual customer reviews is an important task in the field of opinion mining and sentiment analysis. Previous studies have usually used rules of rating and have assumed that the rating scores are integers, that cause the time costs and low accuracy. In this paper, we propose a model based on neural networks for rating (or ranking) product aspects with rating scores are reals. The experimental results show the effectiveness of our proposal on computational times and accuracies in comparison with previous studies using model Perceptron classifier or nonlinear regression model (using Support Vector Regression). Our experiments are carried out on the hotel services extracted from the system Tripadvisor with the aspects including cleanliness, location, service, room, and value.
A high sensitivity signal acquisition method for GPS L5 receivers.
Nguyen Thi Thanh Tu, La The Vinh, Ta Hai Tung.
Currently, the U.S government is implementing the GPS modernization program with the development of various next-generation signals. Among which, the GPS L5 is dedicated for safety-of-life (SoL) applications such as aviation, marine, railways, etc. Aiming at providing better accuracy and availability, L5 signal has many advantages with respect to the widely used legacy signal L1 C/A in term of signal structures, as well as anti-jamming capability. To exploit all the advantages given by this signal as well as to meet the highly demanding requirements of SoL applications, this paper proposes a new acquisition method, which improves the sensitivity for GPS L5 receivers. The proposed method is proved that having a higher sensitivity than the other methods which are being utilized. In addition, the complexity is acceptable with respect to traditional methods even in the case of low power level signal.
Performance improvement of MIMO-SDM cooperative communication systems using lattice reduction-aided detectors.
Tran Van Canh, Nguyen Le Van, Tran Xuan Nam
Multiple-input multiple-output (MIMO) cooperative communication systems often use conventional linear detectors such as zero forcing (ZF) or minimum mean-square error (MMSE) at the destination node for the sake of reduced complexity. However, the performance of these detectors is not as good as expected. In this work, in order to improve the BER performance of the MIMO spatial division multiplexing (SDM) cooperative system, we propose to combine lattice reduction with the ZF and MMSE linear detectors at the destination. The proposed two lattice reduction aided (LRA) detectors, namely LRA-ZF and LRA-MMSE, are shown to achieve significant improvement in BER performance while requiring only small additional complexity compared with the conventional linear detectors.
Parallel and serial LDPC decoders for Wifi and Wimax receivers.
Nguyen Tung Hung, Nguyen Van Duan, Do Quoc Trinh
In this paper, we introduce new parallel and serial LDPC decoders with predefined parity check matrices and adaptive channel LDPC decoders with equivalent parity check matrices based on channel information. Simulation results show that these new decoders can improve the performance of WiFi and WiMAX receivers with acceptable complexity.