16 research outputs found

    Recommender System for the Efficient Treatment of COVID-19 Using a Convolutional Neural Network Model and Image Similarity

    Get PDF
    Background: Hospitals face a significant problem meeting patients’ medical needs during epidemics, especially when the number of patients increases rapidly, as seen during the recent COVID-19 pandemic. This study designs a treatment recommender system (RS) for the efficient management of human capital and resources such as doctors, medicines, and resources in hospitals. We hypothesize that a deep learning framework, when combined with search paradigms in an image framework, can make the RS very efficient. Methodology: This study uses a Convolutional neural network (CNN) model for the feature extraction of the images and discovers the most similar patients. The input queries patients from the hospital database with similar chest X-ray images. It uses a similarity metric for the similarity computation of the images. Results: This methodology recommends the doctors, medicines, and resources associated with similar patients to a COVID-19 patients being admitted to the hospital. The performance of the proposed RS is verified with five different feature extraction CNN models and four similarity measures. The proposed RS with a ResNet-50 CNN feature extraction model and Maxwell–Boltzmann similarity is found to be a proper framework for treatment recommendation with a mean average precision of more than 0.90 for threshold similarities in the range of 0.7 to 0.9 and an average highest cosine similarity of more than 0.95. Conclusions: Overall, an RS with a CNN model and image similarity is proven as an efficient tool for the proper management of resources during the peak period of pandemics and can be adopted in clinical settings

    (Re)imagining Peace: Exploring Mediatized Everyday Peace in Israel/Palestine

    No full text
    Peace is usually studied through nation-states operating in the international system, but recently, peace scholars have underscored the need to research peace as a part of everyday life. I argue that communication scholars should join the new conversation about everyday peace. I discuss major peace theories in broadcast and digital media that either replicate the state-centered approach or struggle to find ways to reach reconciliation. Nevertheless, I argue that communication scholars are well equipped to study everyday peace by focusing on mediatized manifestations of everyday life in popular culture and digital platforms. I demonstrate my claim by analyzing visual and sonic manifestations of everyday peace in Israel/Palestine. I investigate two Israeli television shows, Fauda and Arab Labor, focusing on Jewish and Palestinian men who try to pass members of the other community. Their identity work proves that national and ethnic identities are not stable but remain in flux, undermining Zionism which strives to silo Jews and Palestinians into separate categories. Nevertheless, Fauda and Arab Labor do not prescribe easy solutions to the conflict in their plots. Instead, they allow characters to work through the hardships of the conflict and its implications in their everyday lives. I study the texts of both television shows, illuminating the power of fiction to discuss taboo subjects at the core of the conflict. Moreover, I analyze the production of both shows. Based on interviews with creative workers, I contend that making quality TV is in itself a form of peacemaking because it brings Jews and Palestinian together, galvanizing them to process trauma and explore possible connections between the two communities. I study the sonic expression of everyday peace through a second case study — Border Gone, a digital activist project publishing stories of ordinary Palestinians from Gaza in Hebrew online. I trace the project’s evolution, which initially centered around translating stories written by young adults with the help of hundreds of Israeli volunteers. The stories reveal the humanity of Palestinians, undermining the Zionist perception that all Palestinians are terrorists. Ultimately, Border Gone transformed into an independent news outlet; the managing team was resolved to provide the appropriate political context to Palestinian stories, showcasing how the Israeli occupation of Gaza affects everyday lives. I conducted interviews with Border Gone’s managing team, and with members of its volunteers’ community. I analyze posts appearing on the project’s Facebook page and investigate the various comments uploaded to the page between December 2019-May 2021. May 2021 marked the peak of the project’s operation during a devastating war in Gaza. During the war, I joined the project’s managing team, conducting a participant observation on its news reporting process using the transcripts of a WhatsApp group where we communicated with each other. I conclude that Border Gone affords nonreciprocal listening to Palestinian stories, wherein Jews educate themselves about the reality of Palestinian life without expecting the other side to do the same. The stories captivate Israeli listeners and encourage them to engage in meaningful solidarity by insisting on lively descriptions of Palestinian experiences. Border Gone, as well as Fauda and Arab Labor, prove that peace is possible between Jews and Palestinians who use media to write and tell stories of everyday peace; moreover, media making draws members of these communities close, helping them process the horrors of violent conflict together.PhDCommunicationUniversity of Michigan, Horace H. Rackham School of Graduate Studieshttp://deepblue.lib.umich.edu/bitstream/2027.42/174371/1/yuvalkz_1.pd

    PocketPlant3D: Analysing canopy structure using a smartphone

    No full text
    Leaf angle and curvature are considered important by breeders for increasing plant productivity. We developed a smartphone app (PocketPlant3D) that makes use of the device accelerometer and magnetometer to measure leaf insertion angle and the leaf angles from the insertion to the tip, in turn used to reconstruct the 3D distribution of the angles of photosynthetic tissues. Starting from these angles, PocketPlant3D derives the mean leaf tilt angle (MTA) and the parameters of the Campbell and Î2 leaf angle distributions (LAD), as well as a new leaf curvature indicator. The app was compared with other methods for quantifying precision in measuring leaf insertion angle on maize and sweetcorn (4320 leaf insertion angle measurements) via a ring test. Both precision metrics (repeatability and reproducibility) were similar for the different methods, with the exception of the digital inclinometer, which was the less precise. Concerning the analysis of canopy structure (a total of more than 72,000 angles were measured), PocketPlant3D allowed two genotypes to be discriminated for MTA and, especially, for the parameters of the two LADs and for the curvature indicator, whereas the two genotypes presented similar leaf insertion angles. The completeness of the information collected and the time effectiveness make PocketPlant3D a useful tool for phenotyping activities and ecophysiological studies

    Mobilità 4.0

    No full text
    corecore