ABSTRACT
It is hard to find an empirical study that examines the online learning or blended learning's effect on school pupils' regular exam performance during the COVID-19 epidemic and afterwards. This study attempts to fill in this research gap. An intelligent tutoring system (ITS) was utilised in mathematics online instruction in many elementary and middle schools in China. It supports individualised teaching and learning and has positive effect on students' learning. Two case studies are introduced to illustrate the system's functions and effects on students' mathematics learning performance. In the first case, a mathematics teacher in a junior high school provided the students with differentiated assignments during the epidemic. In the second case, a teacher in a primary school utilised the ITS to implement blended learning after the epidemic. Quasi-experiments were conducted and the regular examination's data analysis result shows that the treatment group outperformed the control group.
ABSTRACT
Visible-infrared cross-modality person re-identification (VI-ReID) is currently a prevalent but challenging research topic in computer vision, since it can remedy the poor performance of existing single-modality ReID models under insufficient illumination, thus enabling the 24/7 surveillance systems. Although extensive research efforts have been dedicated to VI-ReID, a systematic and comprehensive literature review is still missing. Considering that, in this paper, a comprehensive review of VI-ReID approaches is provided. First, we clarify the importance, definition and challenges of VI-ReID. Secondly and most importantly, we elaborately analyze the motivations and the methodologies of existing VI-ReID methods. Accordingly, we will provide a comprehensive taxonomy, including 4 categories with 8 sub-items, for those state-of-the-art (SOTA) VI-ReID models. After that, we elaborate on some widely used datasets and evaluation metrics. Next, comprehensive comparisons of SOTA methods are made on the benchmark datasets. Based on the results, we point out the limitations of current methods. At last, we outline the challenges in this field and future research trends.
ABSTRACT
Currently, urban crises are spreading, even tending to be magnified along the urban networks. Improving urban network resilience can effectively reduce the loss and cope with sudden disasters. Based on the dimensions of regional resilience and the framework of urban network, a new evaluation system of network resilience, including economic, social, and engineering networks, was established to assess the network resilience of the Guangdong-Hong Kong-Macao Greater Bay Area (GBA) from a structural perspective. We analyzed the spatial characteristics and influencing factors of network resilience using social network analysis and quadratic assignment procedure. The results were as follows: (1) regional difference was biggest in GBA's economic network strength while smallest in its transportation network strength, and the east bank of the Pearl River represented an extremely resilient connection axis;(2) the structures of network resilience and its subsystems were heterogeneous, and the connection paths of network resilience were more heterogeneous and diversified than those of the subsystems;(3) network resilience presented an obvious core-edge structure, and the spatial correlation and spillover effect between blocks were substantial;and (4) geographical proximity, as well as differences in economic development, urban agglomeration, and market development, had a significant impact on network resilience. This study provides a more systematic approach to evaluate the regional network resilience, and the results provide references for the construction of bay areas in developing countries.
ABSTRACT
As one of the manifestations of virtual reality (VR) in education, virtual classroom allows students to enjoy a near-real classroom experience. VR class creates much better engagement and helps to stimulate interest and motivation in learning, making it an ideal solution to online teaching and learning activities, especially during the COVID-19 pandemic. Distraction is an unavoidable problem in immersive virtual classes, which has a great detrimental impact on learning. However, how to intervene in students' distraction behaviors in immersive virtual environments has not been thoroughly investigated up to now. In this paper, inspired by teachers' instructional techniques in real-life classes, we propose three intervention strategies, namely eye contact, verbal warning and text warning, and explore the intervening effects of these strategies on the inattention of students seated at the front or back of a virtual classroom via eye tracking. Our results show that all of the proposed intervention strategies have positive impacts on the attention of students. This research gives evidence that teachers' instructional techniques in the real world can be transferred to the virtual class, which provides a new insight for the future design of educational VR. © 2022 ACM.
ABSTRACT
This paper examines the investor reaction of firm-specific pessimistic sentiment extracted from Twitter messages during the pandemic period due to the Covid-19. We find that Twitter sentiment predicts stock returns without subsequent reversals. This finding is consistent with the view that tweets provide information not already reflected in stock prices during the pandemic period. We investigate possible sources of return predictability with a Twitter sentiment. The results show that Twitter's pessimistic sentiment towards the Covid-19 provides new information about the investor. This information explains about one-third of the predictive ability of Twitter sentiment for stock returns. Our findings shed new light on the predictive value of social media content for stock returns. © 2021 International Consortium for Electronic Business. All rights reserved.
ABSTRACT
Acquiring the spatial distribution of users in mobile crowdsensing (MCS) brings many benefits to users (e.g., avoiding crowded areas during the COVID-19 pandemic). Although the leakage of users’location privacy has received a lot of research attention, existing works still ignore the rationality of users, resulting that users may not obtain satisfactory spatial distribution even if they provide true location information. To solve the problem, we employ game theory with incomplete information to model the interactions among users and seek an equilibrium state through learning approaches of the game. Specifically, we first model the service as a game in the satisfaction form and define the equilibrium for this service. Then, we design a LEFS algorithm for the privacy strategy learning of users when their satisfaction expectations are fixed, and further design LSRE that allows users to have dynamic satisfaction expectations. We theoretically analyze the convergence conditions and characteristics of the proposed algorithms, along with the privacy protection level obtained by our solution. We conduct extensive experiments to show the superiority and various performances of our proposal, which illustrates that our proposal can get more than 85% advantage in terms of the sensing distribution availability compared to the well-known differential privacy based solutions. IEEE
ABSTRACT
To cope with the covid-19 epidemic challenge for school education, many researchers have conducted studies from different point of views. However, it is hard to find empirical study to examine the online learning’s effect on school pupils’ performance represented by regular exams. This study attempts to fill in this research gap. An intelligent tutoring system, Lexue 100 was utilized in mathematics online instruction during the COVID-19 epidemic outbreak time in a junior high school in Shandong Province China. Supported by this system, the teacher provided the students with differentiated assignments including class assignment, group assignment and individual assignment, as well as error sets. Those assignments could be completed before the class, in the class or after the class. A quasi-experiment was conducted to compare the effect of this online learning supported by the individualized assignment with that of uniform assignment to all students. The treatment group and control group had the statistically not significant difference in the regular school exams before the experiment as the pretest. At the end of the experiment, the treatment group performed better than the control group in the mid-term test as the posttest, reaching a statistically significant advantage 6.83% (p < 0.01) and an effect size 0.381. The individualized homework contributed to the performance improvement. Implications for online learning design and limitations are discussed. © 2021, Springer Nature Switzerland AG.
ABSTRACT
Developing an intelligent application to assist the detection and study of the COVID-19 infection is crucial and urgent during this pandemic, given the scarcity of available data and the rapidly changing virus. This paper presents a study of transfer learning in image classification to efficiently develop deep learning models following a three-stage procedure to take advantage of pre-trained models from one area and effectively modify the model for application in a relatively new area. The case study in this work is the classification of COVID-19 X-ray images. The experiment evaluations show that the proposed method and developed models achieve satisfactory results in a timely manner. © 2020 IEEE.
ABSTRACT
Primary healthcare settings are the control and prevention network basis of COVID-19 epidemic.So improving COVID-19 control and prevention,service delivery and response levels of these institutions is crucial to the national epidemic control and prevention.Based on the analysis of related field survey results as well as information from national and local official websites,we summed up the important role of primary healthcare in dealing with the epidemic.Moreover,we proposed the following priorities for primary healthcare settings in combating the complex epidemic and delivering daily healthcare services:strengthening community-based control and prevention of COVID-19,providing assistance for other institutions in combating COVID-19,implementing daily healthcare and essential public health services,ensuring medical safety and strengthening the control and prevention of nosocomial infections,and adequately playing the role in county-based healthcare network.Furthermore,developing strategies targeting the weaknesses in combating the epidemic and inadequacies in delivering daily healthcare services of primary healthcare were also put forward:strengthening the development of general practitioner system and hierarchical medical system;improving early warning sensitivity,awareness of timely report of major epidemic,and emergency response level in primary healthcare workers;enhancing the informatization construction and application in primary care using artificial intelligence and cutting-edge technologies;promoting the development of regional medical consortiums and local healthcare networks,and exploring patterns for efficiently integrating medical and prevention services;vigorously carrying out patriotic public health campaigns,strengthening the mechanism of group-based control and prevention of communicable diseases,and facilitating the construction of healthy communities and villages. Copyright © 2020 by the Chinese General Practice.