Bảng thống kê danh sách bài báo đăng trên tạp chí Quốc tế năm 2012

Stt Tên bài mã số, thời gian thực hiện Tác giả Tóm tắt nội dung Tạp chí đăng tải
Tạp chí cấp Quốc tế
1 An enhancement of landmarc using descriptive statistical concepts Nguyễn Thị Mai Phương, Hsu Yang Kung, Sumalee Chaisit The Landmarc algorithm is the most common scheme to achieve the object location. However, Landmarc has been found with estimation errors due to the type of  RSSI radio property. In the present study, we introdure an enhanced statistical approach in order to process RSSI data and estimate the tracking tag position in a room. We pro-posed herein two location estimate scheme, namely, the ESL_Average and ESL_Median schemes. Both schemes periodically collect RSSI data within a fixed time period and calculate final values ta estimate location by using the Landmarc algorithm. For the ESL_Average acheme, the final RSSI value is the average of all RSSI values mea-sured in the given time period. The ESL_Median scheme uses the median of RSSI values to estimate the tracking tag location. We also estimate the estimation accuracy of the two propose schemes by experiment and comparison with the Landmarc algorithm. The result from performance evaluations reveals that the proposed schemes yield performed higher accuracy than the traditional Landmarc scheme. ICIC express letters; Volume 6, number 2, February 2012, Pg 353-358 
2 An Effective and Secure Cipher Based on SDDO Đỗ Thị Bắc , Nguyễn Hiểu Minh, Hồ Ngọc Duy To improve the efficiency of security of the information secure mechanism, an algorithm BMD-128 is proposed. This algorithm is built on the SDDO. Using this operator decreases significanthy the cost of hardware implementation. Besides, it also ensures both the high applicability in the transaction needing the change of session keys with high frequency and the ability against slide attack. Concurrently, this algorithm also eliminates the weak keys without the complex round key proceduce. The algorithm is evaluated regards to the standard NESSIE and the ability against the differential cryptanalysis. Concurrently, it is also compared the performance with the other famous ciphers when implementing on hardware FPGA. I. J. Computer Network and Information Security; Volume 4, Number 11, October 2012, Pg 01-10
3 Iterative method for a biharmonic problem with crack Trương Hà Hải, Đặng Quang Á, Vũ Vinh Quang For numerical solution of the latter problems, we ues a domain decompsition method developed by ourselves in recent years. The fast convergence of the iterative method is established theoretically and illustrated on many numerical experiments Applied Mathematical Sciences; Vol. 6, No. 62, 3095 - 3108, 2012
Kỷ yếu cấp Quốc tế
1 A fast iterrative learning strategy for Bi-directional Associative Memory. Nông Thị Hoa, Bùi Thế Duy Artificial neural networks, characterized by massive parallelism, robustness, and learning capability, have many applications in various fields. Being one kind of neural networks, Bidirectional Associative Memory (BAM) was extended from Hopfiled networks to make a two-way associative search for a pattern pair. Learning strategies for BAMs can be divided into two categories: none-iterative learning and iterative learning. Learning strategies without iteration allow the BAM to recall perfectly and do not need any condition for stability. However, the resulting BAM's noise tolerance is low. Iterative learning can let the BAM recall better from noisy inputs but it needs more time for learning process. In this paper, a new iterative learning strategy of Bi-directional Associative Memory (BAM) is derived to guarantee the recall of all training pairs. Our novel learning strategy flexibly modify pair weights in interactive learning algorithm. Consequently, learning process is faster and the ability of recall is larger or equal to than other BAMs. Simulations show that our novel model greatly improves both learning process and increases noise tolerance. Proceedings international conference; IST 2012; Shanghai China, April 2012, Part 1, Pg 182-184
2 A new learning Strategy of general BAMs Nông Thị Hoa,Bùi Thế Duy Bi-directional Associative Memory (BAM) is an artificial neural network that consists of two Hopfield networks. The most important advantage of BAM is the ability to recall a stored pattern from a noisy input, which depends on learning process. Between two learning types of iterative learning and non-iterative learning, the former allows better noise tolerance than the latter. However, interactive learning BAMs take longer to learn. In this paper, we propose a new learning strategy that assures our BAM converges in all states, which means that our BAM recalls perfectly all learning pairs. Moreover, our BAM learns faster, more flexibility and tolerates noise better. In order to prove the effectiveness of the model, we have compared our model to existing ones by theory and by experiments. Machine Learning and data mining in Pattern recognition; 8th International Conference, MLDM 2012 Berlin, Germany, July 2012 Proceedings, Pg 213 - 221
3 A new effective learning rule of Fuzzy ART Nông Thị Hoa,Bùi Thế Duy Unsupervised neural networks are known for their ability to cluster inputs into categories based on the similarity among inputs. Fuzzy Adaptive Resonance Theory (Fuzzy ART) is a kind of unsupervised neural networks that learns training data until satisfying a given need. In the learning process, weights of categories are changed to adapt to noisy inputs. In other words, learning process decides the quality of clustering. Thus, updating weights of categories is an important step of learning process. We propose a new effective learning rule for Fuzzy ART to improve clustering. Our learning rule modifies weights of categories based on the ratio of the input to the weight of chosen category and a learning rate. The learning rate presents the speed of increasing/decreasing the weight of chosen category. It is changed by the following rule: the number of inputs is larger, value is smaller. We have conducted experiments on ten typical datasets to prove the effectiveness of our novel model. Result from experiments shows that our novel model clusters better than existing models, including Original Fuzzy ART, Complement Fuzzy ART, K-mean algorithm, Euclidean ART. 2012 Conference on Technologies and Applications of Artificial Intelligence; Taiwan, November 16-18, 2012,         Pg 224 -231, 
4 Intelligent personalized food recommendation system based on a semantic sensor web Nguyễn Thị Mai Phương, Hsu Yang Kung, Sumalee Chaisit With changes in eating habits and lifestyles in Taiwan, the number of patients with a chronic disease is increasing, especially the number of those wuth hypertension, hyperglycemia and hyperlipidemia. However, a Food Service Rec-ommendation (FSR) system based on user clinical data and health records has not been investigated. This word proposes a novel Intelligent Personalized Food Ser-vice Recommendation System (IPESRS), which contains a Vital Sensor Web Layer (VSWL), Sematic Medical Web Layer (SMWL), and Medical Service Presentation Layer (MSPL). The vital sensors in the VSML can transfer user clinical data based on Sensor Web Enablement (SWE). The SMWL uses Rule-Based Reasoning (RBR) and Domain Ontologies (DOs) based on the Sematic Web (SW) to determine a user's health status according to that user's data from the VSWL. Furthermore, Bayesian Classification (BC) can be utilized to predict future health states of users. Finally, the FSR determines health states according to the current and future health states of users in the MSPL. 2011 International Conference in Electrics, Communication and Automatic control Proceedings; 2012, Pg 61 -68