Search

Search Results

##search.searchResults.foundPlural##

Evaluation of Feature Selection Methods for Gene Expression Data Classifcation

Phan Thi Thu Hong, Nguyen Thi Thuy

Received: 11-08-2015 / Accepted: 08-03-2016
Selection of relevant genes that have effects in some diseases is a challenging task in gene expression studies. Most gene selection studies focused on assessing the association between individual gene and the disease. In fact, diseases are thought to involve a complex etiology including complicated interactions between many genes and the disease. Random Forest (RF) method has recently been successfully used for identifying genetic factors that have effects in some complex diseases. In spite of performing well in some data sets with moderate size, RF still suffers from working for selecting informative genes and building accurate prediction models. In this paper, we investigatedsome methods in learning advanced random forests that allow one to select a sub-set of informative genes (most relevant to disease). The method can therefore reduce the dimensionality and can perform well in prediction high-dimensional data sets. The performance of these methods has been analyzed for finding the robust one for each interest objective (the accuracy of the prediction model or the smallest possible set of relevant genes) based on experiments results on 8 available public data sets of gene expression from the repository of biomedical data sets (Kent Ridge) and bioinformatics data sets(Bioinformatics).
Assessment and Prediction of Productivity of wild macrofungal species in the Central Highlands of Vietnam

Dang Thi Thu Huong, Nguyen Van Sinh, Nguyen Hung Manh, Bui Thi Tuyet Xuan, Nguyen Tien Dung

Received: 18-08-2023 / Accepted: 25-12-2023
The assessment of productivity of some important wild macrofungi helps us to predict the mushroom supply in different natural conditions and make recommendations on development of empirical models for achieving highest productivity. This study aimed to evaluate productivity of seven important macrofungi in the forest from 90 plots in 03 National Parks belongings to the Central Hiaghlands for nearly 3 years (from 2021 to 2023). The macrofungi included 6 edible species: Boletus edulisBull., Agaricus bisporus(J.E.Lange Imbach), Ramaria botrytoides(Pk.) Comb., Amanita caesarea(Scop.) Pers., Termitomyces eurrhizus(Berk.) R. Heim. and Auricularia nigricans(Sw.) Birkebak, Looney & Sánchez- García and 01 medicinal species: Ganoderma lucidum(Curtis) P. Karst. to build the predicted models for them. The method of collecting and determining the fresh weight of edible mushrooms in the field was carried out weekly from May to November every year. The average yield of Ganoderma lucidumwas the highest at 19.22 ± 2.95 kg-1ha-1year and the lowest of Ramaria botrytoides: 2.42 ± 0.54 kg-1ha-1year. Using the quadratic polynomial function to build predicting models, 07 prediction models were built for each mushroom species and 04 predicting models for each National Park and in the Central Highlands with sufficient reliability as shown by high determination coefficient (R2 = 0.7518-0.9909).
Prediction of Land Use Changes in Don Duong District, Lam Dong Province Using Integrated Model of GIS, Markov Chain, and Logistic Regression

Nguyen Huu Cuong, Nguyen Van Cuong

Received: 14-10-2021 / Accepted: 01-03-2022
Land use changes are recognized as one of the most significant driving forces of environmental changes. This study aimed to predict land-use change in Don Duong district, Lam Dong provinceby applying the integration of GIS, Markov chain and logistic regression. The land-use maps of 2010 and 2015 were employed to predict the land-use scenario for 2020. The predicted results were compared with the observed land-use map of 2020 to validate the method using kappa index statistics. Based on the proposed model, the future land-use change prediction for 2025 and 2030 was performed. The forecast results show that Don Duong district had a significant change in land use. Converting the forest land into other land uses, especially to built-up land and annual agricultural land, is the main land-use change in the future.The resultof this study providesuseful information as the foundation for planning local land-use policies to ensure sustainable development goals.
Study Method Base on Biological Networks for Disease Candidate Gene Prediction

Vu Thi Luu, Tran Thi Thu Huyen, Nguyen Van Hoang, Nguyen Thi Huyen, Le Duc Hau

Received: 21-12-2016 / Accepted: 23-02-2017
Predicting genes which may associate with disease is one of the important goals of biomedical research. There have been many computational methods developed to rank genes involved in a particular disease. However, due to the complex relationship between genes and the diseases, many genes that cause genetic diseases have not yet been discovered. The problem of ranking genes to identify the disease-associated gene has drawn attention of many researchers. To find a good method to predict target genes that cause diseases with high performance, we have conducted a survey of prediction methods based on biological network. We then proposed a new method using a Boolean network model. In biological network, defects by mutations on genes/proteins may cause a disease to occurin a person. Also, these mutations may affect other genes/proteins through structures of the biological networks. In this study, we proposed to use Boolean network model to assess the relevance of candidate genes to a disease of interest by measuring the degree of mutational effect from known disease-associated genes to candidate genes. Particularly, we mutated known disease-associated genes and measured the effect of this mutation on candidate genes based on Boolean dynamics of biological networks. Based on this measured value, candidate genes can be prioritized and finally top-ranked candidate genes can be selected as novel promising disease genes. Simulation results on a set of diseases showed that the proposed method is superior to a state-of-the-art one, which is based on a random walk with a restart algorithm. Using the proposed method, we have identified 27 genes associated with breast cancer with evidences from literature.
A New Feature Sampling Method in Learning Random Forest for SNP Data Analysis

Nguyen Van Hoang, Phan Thi Thu Hong, Nguyen Thanh Tung, Nguyen Thi Thuy

Received: 22-10-2014 / Accepted: 20-12-2014
Recently, Genome-wide association studies (GWAS) have been successful in the identification of genetic variants that have effects in some complex diseases. Most GWA studies used single SNP (single-nucleotide polymorphism) approaches that mainly focused on assessing the association between each individual SNP and the disease. However, in fact, complex diseases are thought to involve complex etiologies including complicated interactions between many SNPs. Thus, different approaches are necessary to identify SNPs that influence disease risk jointly or in complex interactions. Random Forest (RF) method recently has been successfully used in GWAS for identifying genetic factors that have effects in some complex diseases. In spite of performing well in terms of prediction accuracy in some data sets with moderate size, RF still suffers from working in GWAS for selecting informative SNPs and building accurate prediction models. In this paper, we propose a new two-stage sampling method in learning random forests. The proposed method allows to select a sub-set of informative SNPs which are most relevant to disease. Therefore, it reduces the dimensionality and can perform well with high-dimensional data sets. We conducted experiments on two genome-wide SNP data sets to demonstrate the effectiveness of the proposed method.
Modelling for Growth of Mould

Dao Thien, Tran Thanh Hoa, Nguyen Thi Bich Thuy, Tran Thi Lan Huong

Received: 29-05-2012 / Accepted: 12-08-2012
Predictive mycology aims at predicting fungal development in foods and raw products. For many years, most of the studies concerned food pathogenic bacteria. Recently, there is a growing concern about food contamination by moulds, especially strains responsible for mycotoxins production. This paper advocates the use of specific models for describing germination and growth of mould.
Ứng dụng ngôn ngữ lập trình hướng đối tượng python cho bài toán mô phỏng sự truyền neutron trong lò hạt nhân trong điều kiện tới hạn với cấu trúc hình học phẳng

Luong Minh Quan, Nguyen Thi Thanh

Received: 22-07-2015 / Accepted: 03-09-2015
Sử dụng phương pháp lặp theo hàm mũ để giải phương trình truyền neutron trong lò phản ứng hạt nhân với cấu trúc hình học phẳng, một chiều bằng phương pháp mô phỏng Monte Carlo để xác định trị riêng và hàm riêng (tương ứng với sự phân bố của nguồn phân hạch) tồn tại hai vấn đề chính là: (1) sự hội tụ chậm của nguồn phân hạch dự đoán ban đầu về phân bố thực; (2) mối liên hệ giữa các chu kỳ trong mỗi mô phỏng sẽ dẫn đến sai số khi đánh giá độ tin cậy của kết quả thu được. Do đó, nghiên cứu này đã đề cập tới một phương pháp mới, Wielandt, với mục đích tăng tốc quá trình hội tụ của nguồn ban đầu và đưa ra phương án mới để đánh giá mối liên hệ giữa các chu kì liên tiếp trong một mô phỏng độc lập. Ngôn ngữ lập trình hướng đối tượng có tên gọi Python đã được sử dụng để mô tả sự truyền của hạt neutron đơn năng, đồng thời so sánh kết quả thu được bằng hai phương pháp khác nhau. Kết quả cho thấy, phương pháp mới đã giải quyết thành công các vấn đề đặt ra của bài toán Monte Carlo. Tuy nhiên, bài toán về hệ số phẩm chất vẫn cần tiếp tục nghiên cứu thêm.
SOIL ORGANIC MATTER DETERMINATION USING WIRELESS SENSOR NETWORKS

Nguyen Van Linh

Received: 10-11-2015 / Accepted: 08-03-2016
The paper addresses the problem of predicting soil organic matter content in an agricultural field using information collected by a low-cost network of mobile, wireless and noisy sensors that can take discrete measurements in the environment. In this context, it is proposed that the spatial phenomenon of organic matter in soil to be monitored is modeled using Gaussian processes. The proposed model then enables the wireless sensor network to estimate the soil organic matter at all unobserved locations of interest. The estimated values at predicted locations are highly comparable to those at corresponding points on a realistic image that is aerially taken by a very expensive and complex remote sensing system.
PREDICTION MODELS FOR COLOUR CHANGES IN ORANGE FLESHED SWEET POTATO (Ipomoea batatas L. Lam.) DURING HOT AIR DRYING

Hoang Quoc Tuan, Le Canh Toan

Received: 27-06-2015 / Accepted: 11-03-2016
The main objective of this study was to investigate the effect of different temperatures of hot air drying on the quality attributes of orange fleshed sweet potato including colour parameters and colour sensory quality. The drying experiments were carried out at five air temperature of 40, 50, 60, 70 and 80oC. The colour parameters, L(whiteness/darkness), a(redness/greenness) and b(yellowness/blueness) for colour change of the materials were quantified by the Hunter Lab system. These values were also used for calculation of total change (E), hue angle, chroma and browning index. A consumer preference test was conducted with 80 consumers to assess the colour quality of five dried orange fleshed sweet potato samples. Relationship between colour sensory scores of consumer’s taste and quantification of three Hunter parameters using least square regression indicated that all colour values significantly affect colour quality ranking of dried orange fleshed sweet potato. The zero-order model appeared best suited to explain the colour change kinetics during hot drying orange fleshed sweet potato slices at 70oC.
Application of DifferentNonlinear Functionsto Describe the Egg Production Rate of D310 Chicken

Ha Xuan Bo, Le Viet Phuong, Do Duc Luc

Received: 18-11-2021 / Accepted: 01-03-2022
Egg production is an important economic trait in poultry production in general and egg-laying hens in particular. Prediction of eggs performance at early stage could improve livestock efficiency by setting up a early production plan. This study was conducted to describe the egg production rate and determine the best models to estimate egg production at the peak of egg-laying of D310 chickens raised at experimental farm, Faculty of Animal Science of Vietnam National University of Agriculture from December 2020 to May 2021. Five functional nonlinear models (Logistic, Compartmental I, McNally, Compartmental II and Yang) were used to estimate egg production rate at the peak of egg-laying from 19 to 49 weeks of age. Egg production rate was collected from 360 hens from 19 weeks of age (fisrt egglaying week) to 49 weeks of age (26 weeks of egglaying period). The egg production rate at the peak of egg-laying (a) estimated by Logistic model was 0.839. The mean egg production week at egg production peak estimated by Logistic model was 5.265 eggs. The Logistic function appeared most appropriate to describe egg production rate of D310 chickens with the highest coefficient of determination (99.58 %) and the lowest values of AIC (-1862,53) and BIC (-1843,82).
Application of the Different Non-linear Functions to Describe Growth Curve of Beef Cattle Crossbreds between Lai Sind and Belgian Blue

Nguyen Thi Vinh, Duong Thu Huong, Tran Bich Phuong, Ha Xuan Bo, Do Duc Luc, Nguyen Thi Nguyet

Received: 19-08-2020 / Accepted: 10-09-2020
This study aimed to determine the best model to explain the growth curve of F1(BBB x Lai Sind) bulls using non-linear function models such as Logistic, von Bertalanffy, Gompertz, Brody, and Negative Exponential. For this purpose, live weight records of a total 60 F1(BBB x Lai Sind) consisted of 30 bulls and 30 heifers, reared in Ba Vi district, Hanoi city were used. In order to select the best model, the coefficient of determination (R2) and parameters of ME, MSE, MAE, MPE, MAPE were utilized. Results showed that, in both bulls and heifers, von Bertalanffy and Brody functions had the highest R2 and lowest ME, MSE, MAE, MPE, MAPE; followed by Gompertz function. Logistic and Negative Exponential functions had lower values of the above parameters. Age and body weight at the inflection point ranged from 15.47 to 20.41 months; and 400.13 to 415.44kg for bulls; 10.05-14.29 months and 255-276.27kg for heifers, respectively. Therefore, von Bertalanffy function is recommended to use for prediction of live weight on the age of F1(BBB x Lai Sind).
Prediction ofWater Requirementsfor Land Use Types in Srepok River Basinin the Context of Climate Change

Nguyen Thi Ngoc Quyen

Received: 30-11-2018 / Accepted: 11-04-2019
In agricultural production, irrigation water is at the forefront, especially in the context of climate change. The objective of this study wasto predictthe irrigation waterrequirementsfor the major land use types in the Srepok basin and to propose agricultural land-use planning to support decision makers in integrated river basin management towards sustainable development. The modeling approach under thesupport ofCROPWAT 8.0and assessment of natural land adaptation process were applied in the study. Irrigation demand for coffee, pepper, cashew, rubber, tea, rice, maize and cassava were calculated in 2015with highest value of 7.746 m3.ha-1.crop-1forwinter-spring rice. Theirrigation water wasforecast for the future (2045) with decreasing trend in three scenarios (11.7% for low scenario, 18.59% for average scenario and 4.25% in the high scenario) compared to the presentperiod. Furthermore, three maps for agricultural land-use thatdefine suitable areasand spatial allocation of land use plans, were proposed with climatechange scenarios as a response solution.
Evaluating the Potential of Digital Soil Mapping Method to Map Soil Typesin BacNinh Province

Doan Thanh Thuy, Le Thi Giang

Received: 08-01-2016 / Accepted: 29-04-2016
The multinomial logistic regression (MLR) model has been being widely used for soil mapping because it could help save time and costs for collecting and analyzing soil data points compared to conventional methods. This research aimed to assess the potential of mapping soil types in Bac Ninh by assessing the performance of Multinomial Logistic Regression (MLR) model in predicting soil types. Nine predictive variables were derived from the ancillary data including land use, altitude, slope, NDVI, PVI, RVI, Topographic Wetness Index and SAGA Wetness Index. MLR model was constructed to predict soil classes at 2 levels: WRB-Reference Soil Group and intermediate level of Soil Group between Reference Soil Group and the full WRB soil name. The map quality was evaluated by the soil map purity estimated with an independent validation dataset. The diversity indices were calculated to assess the information content of the resultant maps. Assessment of the model’s prediction was based on the soil map purity, the Shannon’s entropy and a combined index. MLR yielded high map purity at the level of Reference Soil Group. When the taxonomic level changed from Reference Soil Group level to intermediate level, the map purity decreased while the value of the diversity indices increased. Therefore, soil mapping using MLR in predicting Reference Soil Group might be more efficient. However, at intermediate level, the model predicted higher diversity of soil map and thus the informative value estimated by the combined index was higher.
NguycơlởđấttạihuyệnMai Châu, tỉnhHòaBình, ViệtNam

Do Van Nha, Do Nguyen Hai

Received: 04-11-2014 / Accepted: 18-04-2015
Trong những thảm hoạ tự nhiên, lở đất xảy ra thường xuyên và ảnh hưởng rất lớn đến người dân và môi trường tại các vùng đất dốc. Mục tiêu nghiên cứu là xác định nguy cơ lở đất gây ra bởi các yếu tố khác nhau tại vùng có độ dốc cao. Phương pháp phân tích đa mục tiêu (AHP) và hệ thống thông tin địa lý (GIS) được áp dụng để xác định nguy cơ lở đất trên địa bàn huyện Mai Châu. Ba mức đánh giá nguy cơ lở đất được xác định là nguy cơ thấp, nguy cơ trung bình và nguy cơ cao. Trong đó, nguy cơ cao được đánh giá là rất quan trọng giúp người sử dụng đất và các nhà hoạch định chính sách trong vùng điều chỉnh các loại hình sử dụng đất không thích hợp. Kết quả cũng sẽ được kiểm định bởi điều tra thực tế lở đất đã xảy ra tại địa phương để từ đó đánh giá được độ chính xác của dự báo về nguy cơ lở đất.
The Impact of 2008 Global Financial and Economic Crisis on Foreign Trade of Vietnam

Hoang Chi Cuong, Bui Thi Thanh Nhan

Received: 27-06-2013 / Accepted: 22-08-2013
The global financial and economic crisis, which was triggered by the Lehman Brothers shock in September 2008, has had enormous negative impacts on the global economy and Vietnam. In this paper, some gravity models were constructed using the Hausman–Taylor (1981) estimator, Fixed-effects (FE), Random-effects (RE) estimations, and applied to recent panel data that includes 18 of Vietnam’s major trade partners during the period from 1995 to 2011. This purpose was to examine the possible impacts of the 2008 global financial and economic crisis on the export and import of Vietnam. The authors found evidence broadly consistent with the prediction that the crisis strongly reduced the country’s import. By contrast, there was no evidence that demonstrated convincingly that this crisis decreased the country’s export. In addition, the authors modeled and found the reciprocal relationship between the export and import of Vietnam.
TRADE LIBERALIZATION AND FOREIGN DIRECT INVESTMENT IN VIETNAM: A GRAVITY MODEL USING HAUSMAN - TAYLORESTIMATOR APPROACH

Hoang Chi Cuong , Do Thi Bich Ngoc, Dang Huyen Linh, Bui Thi Phuong Mai

Received: 07-01-2013 / Accepted: 19-02-2013
Foreigndirect investment (FDI) plays a crucial role in the process of development for Vietnam. Over the two decades of Renovation, a large number of FDI capital flowed into the country, especially after joining the WTO in 2007, an amount reaching up to approximatelyUSD 229,913.7 million. Agravity model constructed using the Hausman – Taylor(1981) estimatorwasapplied to 1995 to 2011panel data that included18 of Vietnam’s major country partnersandprovided by Vietnam’s authorities and international organizations. Thepurposewasto reexamine the possible effect of trade liberalization under the WTO regime and various FTAs on FDI flows. The estimates wereconsistent in line with the prediction that the WTO exerted great impact onFDI flows to Vietnam. By contrast, there is no evidence that demonstrates convincingly that the various FTAs in which Vietnamhas signed/joined recently, increased FDI capital into the country. The paper also proposes recommendations for attracting FDI and using FDI capital more effectively.

1 - 16 of 16 items

Search

Advanced filters

Search Results