Department of Communication and Media

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 5 of 14
  • Item
    Compressed feature vector-based effective object recognition model in detection of COVID-19
    (Elsevier B.V., 2022-02) Chen, Chao; Mao, Jinhong; Liu, Xinzhi; Tan, Yi; Abaido, Ghada M; Alsayed, Hamdy
    To better understand the structure of the COVID-19, and to improve the recognition speed, an effective recognition model based on compressed feature vector is proposed. Object recognition plays an important role in computer vison aera. To improve the recognition accuracy, most recent approaches always adopt a set of complicated hand-craft feature vectors and build the complex classifiers. Although such approaches achieve the favourable performance on recognition accuracy, they are inefficient. To raise the recognition speed without decreasing the accuracy loss, this paper proposed an efficient recognition modeltrained witha kind of compressed feature vectors. Firstly, we propose a kind of compressed feature vector based on the theory of compressive sensing. A sparse matrix is adopted to compress feature vector from very high dimensions to very low dimensions, which reduces the computation complexity and saves enough information for model training and predicting. Moreover, to improve the inference efficiency during the classification stage, an efficient recognition model is built by a novel optimization approach, which reduces the support vectors of kernel-support vector machine (kernel SVM). The SVM model is established with whether the subject is infected with the COVID-19 as the dependent variable, and the age, gender, nationality, and other factors as independent variables. The proposed approach iteratively builds a compact set of the support vectors from the original kernel SVM, and then the new generated model achieves approximate recognition accuracy with the original kernel SVM. Additionally, with the reduction of support vectors, the recognition time of new generated is greatly improved. Finally, the COVID-19 patients have specific epidemiological characteristics, and the SVM recognition model has strong fitting ability. From the extensive experimental results conducted on two datasets, the proposed object recognition model achieves favourable performance not only on recognition accuracy but also on recognition speed. © 2021
  • Item
    Government failure or irresponsible residents? Framing Detroit’s water shutoffs before and during the COVID-19 pandemic
    (SAGE Publications Ltd, 2022-03) Mesmer, Kelsey; Frazier, Darryl; Burgess, Scott
    This content analysis of news stories about the Detroit water shutoffs sought to understand how the ongoing water crisis is framed in local Detroit newspapers—as a human rights issue, or in relation to the city’s financial burden. Using a deductive framing approach, we paid special attention to the frames used within stories and whether articles contained context related to the water shutoffs, specifically about health implications. We paid particular attention to how the focus on health implications changed in response to the COVID-19 pandemic in 2020. Results showed that stories about the water shutoffs often included an economic consequences and responsibility frame which put the blame for the water shutoffs on the city’s government and simultaneously called for the city to step up and fix the problem. Very few news articles focused on the human element of the story, with only a small fraction of the stories including the voices of residents living with no water or focusing on the health implications for those without running water in their homes. These findings led us to make strategic recommendations for reporters covering the water shutoffs in Detroit and similar areas. © 2022 NOND of AEJMC.
  • Item
    Research on a reference signal optimisation algorithm for indoor Bluetooth positioning
    (Sciendo, 2021) Luo, Heng; Hu, Xinyu; Zou, Youmin; Jing, Xinglei; Song, Chengyi; Ni, Qidong
    GPS has a sharp performance decline in terms of accuracy indoors due to the complex building structure. A combined algorithm, targeting at received signal strength indication (RSSI) calibration optimisation, depending on deep neural network training via input vector Γ and the target output vector ψ, termed reference signal optimisation algorithm (RSOA) is proposed to improve the positioning accuracy in the indoor Bluetooth positioning networks. Experimental results show that the relative error of the proposed RSOA between the estimated results and the measured ones can reach as low as 0.2%, and the absolute errors can be reduced to 0.13 m at most within 10 m. © 2021 Heng Luo et al., published by Sciendo 2021.
  • Item
    Twitter’s impact in building reputed hospital brands in USA
    (Obercom, 2020) Aguerrebere, Pablo Medina
    Social media have become a strategic tool for hospitals interested in boosting their corporate communication and achieving several organizational objectives such as improving patient's engagement or reinforcing their own corporate reputation. These platforms help hospitals adapt their communication strategies to a new context (new patients' demands, increasing competition between health organizations, development of health technologies, etc.). This paper aims to analyse Twitter's impact in branding initiatives led by hospitals. To do that, we carried out a literature review about corporate communication, branding and social media; and then, we analysed Twitter's corporate profiles of the best US hospitals in the treatment of oncological diseases. This paper concludes that hospitals interested in effectively using Twitter as a corporate communication tool for branding initiatives need to carry out a strategic reflection before launching any initiative on this platform, improve Twitter's integration with other social media platforms and mobile applications, and facilitate better collaborations between health professionals and communication experts. © 2020 Obercom. All rights reserved.
  • Item
    Branding hospitals on social media through health professionals
    (Equinox Publishing Ltd, 2019) Aguerrebere, Pablo Medina
    Hospitals are facing a constantly changing context in which patients are becoming more demanding, public health education initiatives are regarded as increasingly important and hospital business models have to take account of constantly developing medical technologies. In order to better interact with internal and external stakeholders, hospitals try to reinforce their corporate communication strategies as well as their brand reputation by means that include using social media platforms. This literature review paper aims to better understand why health professionals have the potential to play a key role in hospitals’ branding initiatives through social media. First, I report the findings from studies of concepts related to corporate communication, branding and the connection between social media and personal branding; and, second, I propose a communication model – what I call the PMA branding model – to help hospitals build a brand reputation based on health professionals’ participation in corporate communication initiatives led by hospitals on social media. The paper concludes by showing that the PMA branding model consists of organisational tools based on a rigorous methodology that will help health professionals participate in branding initiatives led by the hospital through these platforms. Copyright © 2020 Equinox Publishing Ltd.