The COVID-19 pandemic, since its beginning in December 2019, has altered every aspect of human life. In Vietnam, the pandemic is in its fourth peak and is the most serious so far, putting Vietnam in the list of top 30 countries with the highest daily cases. In this paper, we wish to identify the magnitude of its impact on college students in Vietnam. As far as we’re concerned, college students belong to the most affected groups in the population, especially in big cities that have been hitting hard by the virus. We conducted an online survey from 31 May 2021 to 9 June 2021, asking students from four representative regions in Vietnam to describe how the pandemic has changed their lifestyle and studying environment, as well as their awareness, compliance, and psychological state. The collected answers were processed to eliminate unreliable ones then prepared for sentiment analysis. To analyze the relationship among the variables, we performed a variety of statistical tests, including Shapiro–Wilk, Mc Nemar, Mann–Whitney–Wilcoxon, Kruskal–Wallis, and Pearson’s Chi-square tests. Among 1875 students who participated, many did not embrace online education. A total of 64.53% of them refused to think that online education would be the upcoming trend. During the pandemic, nearly one quarter of students were in a negative mood. About the same number showed signs of depression. We also observed that there were increasing patterns in sleeping time, body weight, and sedentary lifestyle. However, they maintained a positive attitude toward health protection and compliance with government regulations (65.81%). As far as we know, this is the first project to conduct such a large-scale survey analysis on students in Vietnam. The findings of the paper help us take notice of financial and mental needs and perspective issues for indigent students, which contributes to reducing the pandemic’s negative effects and going forwards to a better and more sustainable life.

No abstract

While people have many ideas about how a smart home should react to particular behaviours from their inhabitant, there seems to have been relatively little attempt to organise this systematically. In this paper, we attempt to rectify this in consideration of context awareness and novelty detection for a smart home that monitors its inhabitant for illness and unexpected behaviour. We do this through the concept of the Use Case, which is used in software engineering to specify the behaviour of a system. We describe a set of scenarios and the possible outputs that the smart home could give and introduce the SHMUC Repository of Smart Home Use Cases. Based on this, we can consider how probabilistic and logic-based reasoning systems would produce different capabilities.

Automated audio captioning (AAC) is a novel task, where a method takes as an input an audio sample and outputs a textual description (i.e. a caption) of its contents. Most AAC methods are adapted from image captioning or machine translation fields. In this work, we present a novel AAC method, explicitly focused on the exploitation of the temporal and timefrequency patterns in audio. We employ three learnable processes for audio encoding, two for extracting the temporal and timefrequency information, and one to merge the output of the previous two processes. To generate the caption, we employ the widely used Transformer decoder. We assess our method utilizing the freely available splits of the Clotho dataset. Our results increase previously reported highest SPIDEr to 17.3, from 16.2 (higher is better).

Road network and building footprint extraction is essential for many applications such as updating maps, traffic regulations, city planning, ride-hailing, disaster response etc. Mapping road networks is currently both expensive and labor-intensive. Recently, improvements in image segmentation through the application of deep neural networks has shown promising results in extracting road segments from large scale, high resolution satellite imagery. However, significant challenges remain due to lack of enough labeled training data needed to build models for industry grade applications. In this paper, we propose a two-stage transfer learning technique to improve robustness of semantic segmentation for satellite images that leverages noisy pseudo ground truth masks obtained automatically (without human labor) from crowd-sourced OpenStreetMap (OSM) data. We further propose Pyramid Pooling-LinkNet (PP-LinkNet), an improved deep neural network for segmentation that uses focal loss, poly learning rate, and context module. We demonstrate the strengths of our approach through evaluations done on three popular datasets over two tasks, namely, road extraction and building footprint detection. Specifically, we obtain 78.19% meanIoU on SpaceNet building footprint dataset, 67.03% and 77.11% on the road topology metric on SpaceNet and DeepGlobe road extraction dataset, respectively. CCS CONCEPTS • Computing methodologies → Computer vision; Neural networks; • Information systems → Data mining.

No abstract

No abstract

No abstract