7,536 Hits in 1.3 sec

Directed hypergraph neural network [article]

Loc Hoang Tran, Linh Hoang Tran
2022 arXiv   pre-print
To deal with irregular data structure, graph convolution neural networks have been developed by a lot of data scientists. However, data scientists just have concentrated primarily on developing deep neural network method for un-directed graph. In this paper, we will present the novel neural network method for directed hypergraph. In the other words, we will develop not only the novel directed hypergraph neural network method but also the novel directed hypergraph based semi-supervised learning
more » ... ethod. These methods are employed to solve the node classification task. The two datasets that are used in the experiments are the cora and the citeseer datasets. Among the classic directed graph based semi-supervised learning method, the novel directed hypergraph based semi-supervised learning method, the novel directed hypergraph neural network method that are utilized to solve this node classification task, we recognize that the novel directed hypergraph neural network achieves the highest accuracies.
arXiv:2008.03626v2 fatcat:uyk2zndaqvarbbrbldny2t7vee

Solve fraud detection problem by using graph based learning methods [article]

Loc Tran, Tuan Tran, Linh Tran, An Mai
2019 arXiv   pre-print
The credit cards' fraud transactions detection is the important problem in machine learning field. To detect the credit cards's fraud transactions help reduce the significant loss of the credit cards' holders and the banks. To detect the credit cards' fraud transactions, data scientists normally employ the unsupervised learning techniques and supervised learning techniques. In this paper, we employ the graph p-Laplacian based semi-supervised learning methods combined with the undersampling
more » ... iques such as Cluster Centroids to solve the credit cards' fraud transactions detection problem. Experimental results show that the graph p-Laplacian semi-supervised learning methods outperform the current state of the art graph Laplacian based semi-supervised learning method (p=2).
arXiv:1908.11708v1 fatcat:ptds4r6ehfae5ljaoonp43ow6u


Diem-Linh Phuong Tran
2016 Zenodo  
Lan Tran, who was the most courageous person in the world. She sent me across the ocean to the United States, the land of opportunity, so I could fulfill my potential.  ... 
doi:10.5281/zenodo.4445451 fatcat:dmu637rfmvaznhg3zdk25dn4va

The Generalized Mean Information Coefficient [article]

Alexander Luedtke, Linh Tran
2013 arXiv   pre-print
Reshef & Reshef recently published a paper in which they present a method called the Maximal Information Coefficient (MIC) that can detect all forms of statistical dependence between pairs of variables as sample size goes to infinity. While this method has been praised by some, it has also been criticized for its lack of power in finite samples. We seek to modify MIC so that it has higher power in detecting associations for limited sample sizes. Here we present the Generalized Mean Information
more » ... oefficient (GMIC), a generalization of MIC which incorporates a tuning parameter that can be used to modify the complexity of the association favored by the measure. We define GMIC and prove it maintains several key asymptotic properties of MIC. Its increased power over MIC is demonstrated using a simulation of eight different functional relationships at sixty different noise levels. The results are compared to the Pearson correlation, distance correlation, and MIC. Simulation results suggest that while generally GMIC has slightly lower power than the distance correlation measure, it achieves higher power than MIC for many forms of underlying association. For some functional relationships, GMIC surpasses all other statistics calculated. Preliminary results suggest choosing a moderate value of the tuning parameter for GMIC will yield a test that is robust across underlying relationships. GMIC is a promising new method that mitigates the power issues suffered by MIC, at the possible expense of equitability. Nonetheless, distance correlation was in our simulations more powerful for many forms of underlying relationships. At a minimum, this work motivates further consideration of maximal information-based nonparametric exploration (MINE) methods as statistical tests of independence.
arXiv:1308.5712v1 fatcat:glul66flobbnljdkl2xyksgue4


Vũ Trường Khanh, Nguyễn Quý Linh, Vũ Hải Linh, Đào Trần Tiến, Trần Vân Khánh, Trần Vân Khánh, Trần Huy Thịnh
2021 Y học Việt Nam  
Vũ Trường Khanh 1 , Nguyễn Quý Linh 2 , Vũ Hải Linh 3 , Đào Trần Tiến 1 , Trần Vân Khánh 2 , Trần Huy Thịnh 1 TÓM TẮT2 8 1 Trường Đại học Y Hà Nội 2 Bệnh viện Bạch Mai 3 Bệnh viện K Chịu trách  ...  Lời cảm ơn: Chúng tôi xin trân trọng cảm ơn Ban lãnh đạo, Phòng Kế hoạch tổng hợp, các khoa lâm sàng Bệnh viện K, Bệnh viện Đại học Y Hà Nội đã tạo mọi điều kiện giúp tôi hoàn thành nghiên cứu này. thư  ... 
doi:10.51298/vmj.v501i2.508 fatcat:mjuuekpikrfivf5gmz3kjyveim

From Implicit to Explicit feedback: A deep neural network for modeling sequential behaviours and long-short term preferences of online users [article]

Quyen Tran, Lam Tran, Linh Chu Hai, Linh Ngo Van, Khoat Than
2021 arXiv   pre-print
Tran); (L. Tran); (L.C. Hai); (L.N. Van); (K.  ... 
arXiv:2107.12325v1 fatcat:fltur2e3b5gcjavehlq3bqnn4y

Sparse random graphs: Eigenvalues and Eigenvectors [article]

Linh Tran, Van Vu, Ke Wang
2010 arXiv   pre-print
In this paper we prove the semi-circular law for the eigenvalues of regular random graph G_n,d in the case d→∞, complementing a previous result of McKay for fixed d. We also obtain a upper bound on the infinity norm of eigenvectors of Erdős-Rényi random graph G(n,p), answering a question raised by Dekel-Lee-Linial.
arXiv:1011.6646v1 fatcat:kphbunzkifao5g2edcytvfbxp4

Global optimization using Lévy flights [article]

Truyen Tran, Trung Thanh Nguyen, Hoang Linh Nguyen
2014 arXiv   pre-print
This paper studies a class of enhanced diffusion processes in which random walkers perform L\'evy flights and apply it for global optimization. L\'evy flights offer controlled balance between exploitation and exploration. We develop four optimization algorithms based on such properties. We compare new algorithms with the well-known Simulated Annealing on hard test functions and the results are very promising.
arXiv:1407.5739v1 fatcat:wuzaneerxnalrpcg3cqtvdxi5a

Factors Affecting the Quality of Financial Statements

Ngoc Linh Tran
2021 Zenodo  
In addition, Tran (2014) finds that there are concerns about various forms of transparency and accountability in Vietnam.  ...  Therefore, Tran (2014) suggested that future researchers need to re-examine the link between transparency, accountability and the performance of public administration in Vietnam.  ... 
doi:10.5281/zenodo.4764463 fatcat:dnepxknzevgrbdazx4yaycxepm

Relationship between International Trade and Circular Economy: Literature Review

Xuan Phu Pham, Thi Minh Hai Tran, Thi Thuy Linh Tran
2020 Zenodo  
In the last few years, the circular economy has received considerable attention worldwide because it offers an opportunity to optimise and promote sustainable production and consumption through new models based on continuous growth and limitless resources. This concept has been adopted in some countries such as Denmark, Netherlands, Scotland, Sweden, Japan, China, and Germany while it is being considered by others including England, Austria, and Finland. Although applications of a circular
more » ... my have been identified in many developed countries, a few of studies exist that investigate practices in developing countries. However, the implementation of each country may vary, with specific priorities. This paper aims at analyzing the concept of circular economy (CE) and some international experience of implementing CE.
doi:10.5281/zenodo.4991489 fatcat:rvdjodlrvbgu7nstl2oekzzqci

Simultaneous face detection and 360 degree headpose estimation [article]

Hoang Nguyen Viet, Linh Nguyen Viet, Tuan Nguyen Dinh, Duc Tran Minh, Long Tran Quoc
2021 arXiv   pre-print
With many practical applications in human life, including manufacturing surveillance cameras, analyzing and processing customer behavior, many researchers are noticing face detection and head pose estimation on digital images. A large number of proposed deep learning models have state-of-the-art accuracy such as YOLO, SSD, MTCNN, solving the problem of face detection or HopeNet, FSA-Net, RankPose model used for head pose estimation problem. According to many state-of-the-art methods, the
more » ... e of this task consists of two parts, from face detection to head pose estimation. These two steps are completely independent and do not share information. This makes the model clear in setup but does not leverage most of the featured resources extracted in each model. In this paper, we proposed the Multitask-Net model with the motivation to leverage the features extracted from the face detection model, sharing them with the head pose estimation branch to improve accuracy. Also, with the variety of data, the Euler angle domain representing the face is large, our model can predict with results in the 360 Euler angle domain. Applying the multitask learning method, the Multitask-Net model can simultaneously predict the position and direction of the human head. To increase the ability to predict the head direction of the model, we change there presentation of the human face from the Euler angle to vectors of the Rotation matrix.
arXiv:2111.11604v1 fatcat:7bgeay3w4jh6rkojdcejwov6ce

To Detect Irregular Trade Behaviors In Stock Market By Using Graph Based Ranking Methods [article]

Loc Tran, Linh Tran
2019 arXiv   pre-print
To detect the irregular trade behaviors in the stock market is the important problem in machine learning field. These irregular trade behaviors are obviously illegal. To detect these irregular trade behaviors in the stock market, data scientists normally employ the supervised learning techniques. In this paper, we employ the three graph Laplacian based semi-supervised ranking methods to solve the irregular trade behavior detection problem. Experimental results show that that the un-normalized
more » ... d symmetric normalized graph Laplacian based semi-supervised ranking methods outperform the random walk Laplacian based semi-supervised ranking method.
arXiv:1909.08964v1 fatcat:vndbp53msnadfmki7723vxtllm

Patterns of Urban Foot Traffic Dynamics [article]

Gregory Dobler, Jordan Vani, Trang Tran Linh Dam
2019 arXiv   pre-print
Using publicly available traffic camera data in New York City, we quantify time-dependent patterns in aggregate pedestrian foot traffic. These patterns exhibit repeatable diurnal behaviors that differ for weekdays and weekends but are broadly consistent across neighborhoods in the borough of Manhattan. Weekday patterns contain a characteristic 3-peak structure with increased foot traffic around 9:00am, 12:00-1:00pm, and 5:00pm aligned with the "9-to-5" work day in which pedestrians are on the
more » ... reet during their morning commute, during lunch hour, and then during their evening commute. Weekend days do not show a peaked structure, but rather increase steadily until sunset. Our study period of June 28, 2017 to September 11, 2017 contains two holidays, the 4th of July and Labor Day, and their foot traffic patterns are quantitatively similar to weekend days despite the fact that they fell on weekdays. Projecting all days in our study period onto the weekday/weekend phase space (by regressing against the average weekday and weekend day) we find that Friday foot traffic can be represented as a mixture of both the 3-peak weekday structure and non-peaked weekend structure. We also show that anomalies in the foot traffic patterns can be used for detection of events and network-level disruptions. Finally, we show that clustering of foot traffic time series generates associations between cameras that are spatially aligned with Manhattan neighborhood boundaries indicating that foot traffic dynamics encode information about neighborhood character.
arXiv:1910.02380v1 fatcat:fi32fqmbwve35hc3a2bwis6uwu

Overview of Arbitration and Online

Thi Thao Truong, Thuy Linh Tran, Mai Thanh Nong
2020 Zenodo  
Online arbitration is an ideal dispute resolution mechanism to solve disputes arising from B2B transactions for various reasons, among others, because it allows parties to select a specialist they both trust to solve the controversy with an award that is binding for both parties, but that respect the minimum necessary formalities of the procedure. Additionally, the use of electronic means of communication allows the procedure to be conducted in a faster pace, from any location, and allowing
more » ... ies to get access to the documents of the procedure at any place at any time.
doi:10.5281/zenodo.4991331 fatcat:kgvo6atcnnatrkfrztnrvcwcke


Thúy Trần Thị
Bài viết trên cơ sở phân tích các yếu tố tác động bản lĩnh chính trị, đề xuất một số giải pháp góp phần nâng cao bản lĩnh chính trị của thanh niên hiện nay.  ...  Rèn luyện bản lĩnh chính trị là nhiệm vụ và cũng là sứ mệnh của thanh niên trước sự vận động phức tạp của đời sống xã hội hiện nay.  ...  TẠP CHÍ KHOA HỌC ĐẠI HỌC TÂN TRÀO ISSN: 2354 -1431 RÈN LUYỆN BẢN LĨNH CHÍNH TRỊ CHO THANH NIÊN HIỆN NAY Trần Thị Thúy 1,* 1 Trường Chính trị tỉnh Nghệ An, Việt Nam *  ... 
doi:10.51453/2354-1431/2021/496 fatcat:qmra4tdymjd6ngwft6k2xwfuti
« Previous Showing results 1 — 15 out of 7,536 results