The move from boxed products to services and the widespread adoption of cloud computing has had a huge impact on the software development life cycle and DevOps processes. Particularly, incident management has become critical for developing and operating large-scale services. Prior work on incident management has heavily focused on the challenges with incident triaging and de-duplication. In this work, we address the fundamental problem of structured knowledge extraction from service incidents. We have built SoftNER, a framework for unsupervised knowledge extraction from service incidents. We frame the knowledge extraction problem as a Named-Entity Recognition task for extracting factual information. SoftNER leverages structural patterns like key-value pairs and tables for bootstrapping the training data. Further, we build a novel multitask learning based BiLSTM-CRF model which leverages not just the semantic context but also the data-types for named-entity extraction. We have deployed SoftNER at Microsoft, a major cloud service provider and have evaluated it on more than 2 months of cloud incidents. We show that the unsupervised machine learning pipeline has a high precision of 0.96. Our multi-task learning based deep learning model also outperforms the state of the art NER models. Lastly, using the knowledge extracted by SoftNER we are able to build significantly more accurate models for important downstream tasks like incident triaging.
Burn wounds are a devastating type of skin injury leading to severe impacts on both patients and the healthcare system. Current treatment methods are far from ideal, driving the need for tissue engineered solutions. Among various approaches, stem cell-based strategies are promising candidates for improving the treatment of burn wounds. A thorough search of the Embase, Medline, Scopus, and Web of Science databases was conducted to retrieve original research studies on stem cell-based tissue engineering treatments tested in preclinical models of burn wounds, published between January 2009 and June 2021. Of the 347 articles retrieved from the initial database search, 33 were eligible for inclusion in this review. The majority of studies used murine models with a xenogeneic graft, while a few used the porcine model. Thermal burn was the most commonly induced injury type, followed by surgical wound, and less commonly radiation burn. Most studies applied stem cell treatment immediately post-burn, with final endpoints ranging from 7 to 90 days. Mesenchymal stromal cells (MSCs) were the most common stem cell type used in the included studies. Stem cells from a variety of sources were used, most commonly from adipose tissue, bone marrow or umbilical cord, in conjunction with an extensive range of biomaterial scaffolds to treat the skin wounds. Overall, the studies showed favourable results of skin wound repair in animal models when stem cell-based tissue engineering treatments were applied, suggesting that such strategies hold promise as an improved therapy for burn wounds.
Graphical abstract
Cyber attacks are increasingly becoming prevalent and causing significant damage to individuals, businesses and even countries. In particular, ransomware attacks have grown significantly over the last decade. We do the first study on mining insights about ransomware attacks by analyzing query logs from Bing web search engine. We first extract ransomware related queries and then build a machine learning model to identify queries where users are seeking support for ransomware attacks. We show that user search behavior and characteristics are correlated with ransomware attacks. We also analyse trends in the temporal and geographical space and validate our findings against publicly available information. Lastly, we do a case study on 'Nemty', a popular ransomware, to show that it is possible to derive accurate insights about cyber attacks by query log analysis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.