Trường Đại học Công nghệ Thông tin, Đại học Quốc gia Thành phố Hồ Chí Minh

In recent years, inundation, one of natural calamities, occurs frequently and fiercely. We are sustained severe losses in the floods every year. Therefore, the development of control methods to determine, analyze, model and predict the floods is indispensable and urgent. In this paper, we propose a justified semiparametric regression model for flood water levels forecasting. The new model has three components. The first one is parametric elements of the model. They are water level, precipitation, evaporation, air-humidity and groundmoisture values, etc. There is a complex connection among these parametrics. Several innovated regression models have been offered and experimented for this complicated relationship. The second one is a non-parametric ingredient of our model. We use the Arnak S. Dalalyan et al.’s effective dimension-reduction subspace algorithm and some modified algorithms in neural networks to deal with it. They are altered back-propagation method and ameliorated cascade correlation algorithm. Besides, we also propose a new idea to modify the conjugate gradient one. These actions will help us to smooth the model’s non-parametric constituent easily and quickly. The last component is the model’s error. The whole elements are essential inputs to operational flood management. This work is usually very complex owing to the uncertain and unpredictable nature of underlying phenomena. Flood-waterlevels forecasting, with a lead time of one and more days, was made using a selected sequence of past water-level values observed at a specific location. Time-series analytical method is also utilized to build the model. The results obtained indicate that, with a new semiparametric regression one and the effective dimension-reduction subspace algorithm, together with some improved algorithms in neural network, the estimation power of the modern statistical model is reliable and auspicious, especially for flood forecasting/modeling.

One of the emerging research trends in natural language understanding is machine reading comprehension (MRC) which is the task to find answers to human questions based on textual data. While many datasets have been developed for MRC research for other languages, there is a lack of such resources for the Vietnamese language. Although many datasets and methodologies have been developed for English and Chinese, many Vietnamese machine reading comprehension limitations need to be solved further. Existing Vietnamese datasets for MRC research concentrate solely on answerable questions. However, in reality, questions can be unanswerable for which the correct answer is not stated in the given textual data. To address the weakness, we provide the research community with a benchmark dataset named UIT-ViQuAD 2.0 for evaluating the MRC task and question answering systems for the Vietnamese language. We use UIT-ViQuAD 2.0 as a benchmark dataset for the shared task on Vietnamese machine reading comprehension (VLSP2021-MRC) at the Eighth Workshop on Vietnamese Language and Speech Processing (VLSP 2021). This task attracted 77 participant teams from 34 universities and other organizations. Each participant was provided with the training data, including 28,457 annotated question-answer pairs, and returned the result on a public test set of more than 3,821 questions and a private test set of 3,712 questions. In this article, we present details of the organization of the shared task, an overview of the methods employed by shared-task participants, and the results. The highest performances in this competition are 77.24% (in EM) and 67.43% (in F1-score) on the private test set. The Vietnamese MRC systems proposed by the top 3 teams use XLM-RoBERTa, a powerful pre-trained language model based on the transformer architecture that has achieved state-of-the-art results on many natural language processing tasks. We believe that releasing the UIT-ViQuAD 2.0 dataset motivates more researchers to improve Vietnamese machine reading comprehension.

Along with the explosion of user reviews on the Internet, sentiment analysis has becomeone of the trending research topics in the field of natural language processing. In the last five years,many shared tasks were organized to keep track of the progress of sentiment analysis for various lan-guages. In the Fifth International Workshop on Vietnamese Language and Speech Processing (VLSP2018), the Sentiment Analysis shared task was the first evaluation campaign for the Vietnamese lan-guage. In this paper, we describe our system for this shared task. We employ a supervised learningmethod based on the Support Vector Machine classifiers combined with a variety of features. Weobtained the F1-score of 61% for both domains, which was ranked highest in the shared task. For theaspect detection subtask, our method achieved 77% and 69% in F1-score for the restaurant domainand the hotel domain respectively.

In this paper, we propose an integrated model for discovering, classifying and labeling topics of messages based on topic modeling to analyze and understand the topics of the messages posted by users on social networks. In which, the method of labeling is executed by machine learning on the training data and ontology. The ontology is created in the field of higher education. All parts of model are integrated on a system called social network analysis system based on topic modeling. The experiment of the model on the linguistic data of Vietnamese texts collected from a student forum is transformed into a data structure of social network, including: 13,208 messages by 2,494 users.

Hermite type stochastic processes are the indespensable core resulting from the well – matched couple of Wiener stochastic process and Hermite polynomials. They will construct an orthogonal base of stochastic processses space. The paper emphatically looks at bona fide nature of Ito integral and stochastic differential equations compared with those of Hermite type stochastic processes.

In this paper, we study some properties of Itô-Hermite random process which are necessary to study Malliavin calculus. Main results are in the following theorems:

One of the most important and popular topics in optimization problems is to find its optimal solutions, especially Pareto optimal points, a well-known solution introduced in multi-objective optimization. This topic is one of the oldest challenges in many issues related to science, engineering and other fields. Many important practical-problems in science and engineering can be expressed in terms of multi-objective/ set-valued optimization problems in order to achieve the proper results/ properties. To find the Pareto solutions, a corresponding scalarization problem has been established and studied. The relationships between the primal problem and its scalarization one should be investigated for finding optimal solutions. It can be shown that, under some suitable conditions, the solutions of the corresponding scalarization problem have uniform spread and have a close relationship to Pareto optimal solutions for the primal one. Scalarization has played an essential role in studying not only numerical methods but also duality theory. It can be usefully applied to get relationships/ important results between other fields, for example optimization, convex analysis and functional analysis. In scalarization, we ussually use a kind of scalarized-functions. One of the first and the most popular scalarized-functions used in scalarization method is the Gerstewitz function. In the paper, we mention some problems in set-valued optimization. Then, we propose an application of the Gerstewitz function to these problems. In detail, we establish some optimality conditions for Pareto/ weak solutions of unconstrained/ constrained set-valued optimization problems by using the Gerstewitz function. The study includes the consideration of problems in theoretical approach. Some examples are given to illustrate the obtained results.

Drones are increasingly used in various application domains including surveillance, agriculture, delivery, search and rescue missions. Object detection in aerial images (captured by drones) gradually gains more interest in computer vision community. However, research activities are still very few in this area due to numerous challenges such as top-view angle, small-scale object, diverse directions, and data imbalance. In this paper, we investigate different data augmentation techniques. Furthermore, we propose combining data augmentation methods to further enhance the performance of the state-of-the-art object detection methods. Extensive experiments on two datasets, namely, AERIAU, and XDUAV, demonstrate that the combination of random cropped and vertical flipped data boosts the performance of object detectors on aerial images.

Bài báo nhằm xây dựng một mô hình hệ thống E-Learning dựa trên đa tác tử, bao gồm: xây dựng các thành phần cùng với các nguyên lý và quá trình làm việc của chúng, quản lý các tác tử và giao tiếp giữa các tác tử, cung cấp môi trường và cơ chế để thiết kế và truy vấn cơ sở tri thức phân tán. Chúng tôi đã áp dụng mô hình này trong lĩnh vực hình học phẳng.