Bài trích (Tất cả)
A two-channel model for representation learning in vietnamese sentiment classification problem / Nguyen Hoang Quan, Ly Vu, Nguyen Quang Uy Đầu mục:0 Tài liệu số:0

Sentiment classification ISC) aims to determine whether a document. conveys a positiveor negative opinion. Due to the rapid development of the digital world. SC hm, rwmme an impor-tant research topic that affects to many aspects of our life. In SC hast-d on maritim- Earning. The representation of the document strongly influences on its accuracy. Embedding 35E; swam techniques, techniques. are proved to be beneficial techniques to the SC problem. Howeve is often not. enough to represent the semantic of Vietnamese (1062235 due tothe complexity of semantics and syntactic structure. In this paper. we propose a new:sematiun learning model called a two-channel vector to learn a higher-level feature of a (locum-er: for SC. Our model uses two neural networks to learn both the semantic feature and the feature. The semantic feature is learnt using W'ord and the syntactic feature is learnt tho-.3; Parts of Speech tag (POS). Two features are then combined and input to a Softmax functic-r. 1.51 med-2:3 the final classification.

Global Dynamics Of A Computer Virus Propagation Model With Feedback Controls / Dang A Quang, Hoang Manh Tuan, Tran Hung Dinh Đầu mục:0 Tài liệu số:0

A computer virus propagation model with feedback controls is first prop-used and inves-tigated. We show that the control variables do not influence on the global Stability 0:7 31+. Original differential model, they only alter the position of the unique viral equilibrium. The :aihernmir-al analyses and numerical simulations show that this equilibrium can be completely elimig- namely. moved to the origin of coordinates if suitable values of the control variables are chose; the other words, the control variables are effective in the prevention of viruses in computer :r us. Some numerical simulations are presented to demonstrate the validity of the obtained their results.

An Effective Algorithm For Computing Re An Ef Decision Tables Ducts In Decision Tables / Do Si Truong, Lam Thanh Hien, Nguyen Thanh Tung Đầu mục:0 Tài liệu số:1

Attribute reduction is one important part researched in rough set theory. A reduct from a decision table is a minimal subset of the conditional attributes which provide the same information for classification purposes as the entire set of available attributes. The classification task for the high dimensional decision table could be solved faster if a reduct, instead of the original whole set of attributes, is used. In this paper, we propose a reduct computing algorithm using attribute clustering. The proposed algorithm works in three main stages. In the first stage, irrelevant attributes are eliminated. In the second stage relevant attributes are divided into appropriately selected number of clusters by Partitioning Around Medoids (PAM) clustering method integrated with a special metric in attribute space which is the normalized variation of information. In the third stage, the representative attribute from each cluster is selected that is the most class—related. The selected attributes form the approximate reduct. The proposed algorithm is implemented and experimented. The experimental results show that the proposed algorithm is capable of computing approximate reduct with small size and high classification accuracy, when the number of clusters used to group the attributes is appropriately selected

A hybrid pso-sa scheme for improving the. Accuracy of fuzzy time series forecasting models / Pham Dinh Phong, Nguyen Duc Du, Pham Hoang Hiep..[and others] Đầu mục:0 Tài liệu số:1

Forecasting methods based on fuzzy time series have been examined intersh'aly during the last few years. Three main factors which affect the accuracy of those forecasts-.3 Ethan‘s are the length of intervals, the way of establishing fuzzy logical relationship groups. and olefizziicazion techniques. Many researchers focus on studying the methods of optimizing the length of intervals to improve forecasting accuracies by utilizing various optimization techniques. In line 77:72: that re-msearch trend, this paper proposes a hybrid algorithm combining particle swarm optimitazior. aim the simulated annealing technique (PSO-SA) to optimize the length of intervals to improne forecasting accuracies. The experimental results on the datasets of the “enrolments of the L‘niiezsiry of Al- abama,” “killed in car road accidents in Belgium,” and the “spot gold in Turkey" have shown that the proposed forecasting model is more effective than their counterparts.

Joint power cost and latency minimization for Secure collaborative learning systems / Nguyen Thi Thanh Van, Vu Van Quang, Nguyen Cong Luong Đầu mục:0 Tài liệu số:1

This work investigates the update security model in a collaborative learning or federatedlearning network by using the covert communication. The covert communication (CC) uses the jamming signal and multiple friendly jammers (FJS) are deployed that can offer jamming services to the model owner, i.e., a base station (BS). To enable the BS to select the best FJ, i.e., the lowest cost FJ, a truthful auction is adopted. Then, we formulate an optimization problem that aims to optimize the transmission power, jamming power, and local accuracy. The objective is to minimize the training latency, subject to the security performance requirement and budget of the BS. To solve the non-convex problem, we adopt a Successive Convex Approximation algorithm. The numerical results reveal some interesting things. For example, the trustful auction reduces the jamming cost of the BS as the number of FJs increases.

A data-centric deep learning method for Pulmonary nodule detection / Nguyen Chi Cuong, Nguyen Long Giang, Tran Hang Son Đầu mục:0 Tài liệu số:1

Lung cancer is one of the most serious cancer-related diseases in Vietnam 9;.“ all over the world. Early detection of lung nodules can help to increase the survival rate 1:3; cancer patients. Computer-aided diagnosis (CAD) systems are proposed in the literature for: 93:36 detection of lung nodules. However, most of the current CAD systems are based on the building ' List—quality machine learning models for a fixed dataset rather than taking into account the dataset properties which are very important for the lung cancer diagnosis. In this paper, we follow the arse-5:2 of data- ccntric approach for lung nodule detection by proposing a data-centric method to in;rares— detection performance of lung nodules on CT scans. Our method takes into account the dataset-span: features (nodule sizes and aspect ratios) to train detection models as well as add more trainizg 141:; from local Vietnamese hospital. We experiment our method on the three widely used object detection networks (Faster R-CNN, YOLOVQ, and RetinaNet). The experimental results show that our prop-used method improves detection sensitivity of these object detection models up to 4.24%.

Revisiting Some Fuzzy Algebraic Structures Rabal-I Kellil / Rabal-I Kellil Đầu mục:0 Tài liệu số:1

Following our investigations on particular fuzzy algebraic structures. we reaisit fuzzysubgroups and fuzzy ideals and introduce some numerical examples. As usual. we associated relationsto fuzzy subgroup and fuzzy ideal. Consequently, right and left cosets modulo a fuzzy relation were introduced. This work and the our previous works can be considered as a continuation of irrestigaiions initiated by Abu Osman and Antony in the 19805. Toward our investigation, we have in mind that by introducing these new definitions, the results that we can get should represent a real generalization of classical and commonly known concepts of algebra

Intuition and managerial decision-making / Veronika Gigalova Đầu mục:0 Tài liệu số:1

The study examines new possibilities for recognising and understanding intuitive managerial decision-making, which is increasingly discussed in relation to the theory of management. Managers make decisions in organisations which have been undergoing transformation related to societal changes. Managerial decision-making is still understood as a purely rational action. Let us suppose that managers are able to entirely rationally calculate inputs and outputs, or the consequences, of their actions, and always do so to achieve set goals. Managers are expected to decide quickly, and this increases the probability of errors occurring. Therefore, intuition derived from knowledge, experience and emotions is now taking precedence over rationality.

Incoterms® 2020 and missed opportunities for the next version / Jonathan Davis, John Vogt Đầu mục:0 Tài liệu số:1

Incoterms ® define obligations, risks and costs that each of the seller and buyer must incur in the movement of the goods for a trade. New versions are issued when deemed necessary by the International Chamber of Commerce (ICC) and are aimed at including new trade realities and fostering trade. A new version Incoterms® 2020 is now available to replace the previous version, namely Incoterms®2010.

Decision-Making on Incoterms 2020 of Automotive Parts Manufacturers in Thailand / Juthathip Suraraksa, Chompoonut Amchang, Nutcharin Sawatwong Đầu mục:0 Tài liệu số:1

The objective of this research is to examine the factors affecting the decision-making of International Commercial Terms (Incoterms) of automotive parts manufacturers in Thailand. This mixed method study applied qualitative and quantitative research methods and utilized the analytical hierarchy process (AHP) to prioritize the significance of the factors. By an in-depth literature review and expert interview, four main criteria were identified. These criteria include Operating costs, Cooperation and bargaining power, Knowledge and understanding and Operation duration then main criteria divided into fifteen sub-criteria. The common Incoterms, Ex Works (EXW), Free On Board (FOB), Free Carrier (FCA).