Due to the characteristics of COVID-19, the epidemic develops rapidly and overwhelms health service systems worldwide. Many patients suffer from life-threatening systemic problems and need to be carefully monitored in ICUs. An intelligent prognosis can help physicians take an early intervention, prevent adverse outcomes, and optimize the medical resource allocation, which is urgently needed, especially in this ongoing global pandemic crisis. However, in the early stage of the epidemic outbreak, the data available for analysis is limited due to the lack of effective diagnostic mechanisms, the rarity of the cases, and privacy concerns. In this paper, we propose a distilled transfer learning framework, DistCare, which leverages the existing publicly available online Electronic Medical Records to enhance the prognosis for inpatients with emerging infectious diseases. It learns to embed the COVID-19related medical features based on massive existing EMR data. The transferred parameters are further trained to imitate the teacher model's representation based on distillation, which embeds the health status more comprehensively on the source dataset. We conduct Length-of-Stay prediction experiments for patients in ICUs on real-world COVID-19 datasets. The experiment results indicate that our proposed model consistently outperforms competitive baseline methods. In order to further verify the scalability of DistCare to deal with different clinical tasks on different EMR datasets, we conduct an additional mortality prediction experiment on End-Stage Renal Disease datasets. The extensive experiments demonstrate that DistCare can benefit the prognosis for emerging pandemics and other diseases with limited EMR.

Purpose Security is the most important issue in Internet of Things (IoT)-based smart cities and blockchain (BC). So, the present paper aims to detect and organize the literature regarding security in the IoT-based smart cities and BC context. It also proposes an agenda for future research. Therefore, the authors did a statistical review of security in IoT and BC in smart cities. The present investigation aims to determine the principal challenges and disturbances in IoT because of the BC adoption, the central BC applications in IoT-based smart cities and the BC future in IoT-based smart cities. Design/methodology/approach IoT) has a notable influence on modernizing and transforming the society and industry for knowledge digitizing. Therefore, it may be perceived and operated in real time. The IoT is undergoing exponential development in industry and investigation. Still, it contains some security and privacy susceptibilities. Naturally, the research community pays attention to the security and privacy of the IoT. Also, the academic community has put a significant focus on BC as a new security project. In the present paper, the significant mechanisms and investigations in BC ground have been checked out systematically because of the significance of security in the IoT and BC in smart cities. Electronic databases were used to search for keywords. Totally, based on different filters, 131 papers have been gained, and 17 related articles have been obtained and analyzed. The security mechanisms of BC in IoT-based smart cities have been ranked into three main categories as follows, smart health care, smart home and smart agriculture. Findings The findings showed that BC’s distinctive technical aspects might impressively find a solution for privacy and security problems encountering the IoT-based smart cities development. They also supply distributed storage, transparency, trust and other IoT support to form a valid, impressive and secure distributed IoT network and provide a beneficial guarantee for IoT-based smart city users’ security and privacy. Research limitations/implications The present investigation aims to be comprehensive, but some restrictions were also observed. Owing to the use of some filters for selecting the original papers, some complete works may be excluded. Besides, inspecting the total investigations on the security topic in BC and the IoT-based smart cities is infeasible. Albeit, the authors attempt to introduce a complete inspection of the security challenges in BC and the IoT-based smart cities. BC includes significant progress and innovation in the IoT-based smart cities’ security domain as new technology. Still, it contains some deficiencies as well. Investigators actively encounter the challenges and bring up persistent innovation and inspection of related technologies in the vision of the issues available in diverse application scenarios. Practical implications The use of BC technology in finding a solution for the security issues of the IoT-based smart cities is a research hotspot. There is numerable literature with data and theoretical support despite the suggestion of numerous relevant opinions. Therefore, this paper offers insights into how findings may guide practitioners and researchers in developing appropriate security systems dependent upon the features of IoT-based smart city systems and BC. This paper may also stimulate further investigation on the challenge of security in BC and IoT-based smart cities. The outcomes will be of great value for scholars and may supply sights into future investigation grounds in the present field. Originality/value As the authors state according to their knowledge, it is the first work using security challenges on BC and IoT-based smart cities. The literature review shows that few papers discuss how solving security issues in the IoT-based smart cities can benefit from the BC. The investigation suggests a literature review on the topic, recommending some thoughts on using security tools in the IoT-based smart cities. The present investigation helps organizations plan to integrate IoT and BC to detect the areas to focus. It also assists in better resource planning for the successful execution of smart technologies in their supply chains.

Phrase grounding aims to localize the objects described by phrases in a natural language specification. Previous works model the interaction of inputs from text modality and visual modality only in the intra-modal global level and consequently lacks the ability to capture the precise and complete context information. In this paper, we propose a novel Cross-Modal Omni Interaction network (COI Net) composed of a neighboring interaction module, a global interaction module, a cross-modal interaction module and a multilevel alignment module. Our approach formulates the complex spatial and semantic relationship among image regions and phrases through multi-level multi-modal interaction. We capture the local relationship using the interaction among neighboring regions and then collect the global context through the interaction among all regions using a transformer encoder. We further use a co-attention module to apply the interaction between two modalities to gather the crossmodal context for all image regions and phrases. In addition to the omni interaction modeling, we also leverage a straightforward yet effective multilevel alignment regularization to formulate the dependencies among all grounding decisions. We extensively validate the effectiveness of our model. Experiments show that our approach outperforms existing state-of-the-art methods by large margins on two popular datasets in terms of accuracy: 6.15% on Flickr30K Entities (71.36% increased to 77.51%) and 21.25% on ReferItGame (44.91% * Equal contribution.