LAUSR

The adoption of electronic patient records in hospitals will provide numerous benefits, but it will also present new issues. One of these is the creation of deadlocks, which causes delays in conducting tasks such as obtaining patient information. If the underlying system is distributed, the deadlock situation gets even more problematic. The strategy for preventing deadlock requires basic information from the transaction structure and requested resources. However, in most circumstances, this information is either unavailable or ambiguous. Because the cost of processing and storing sophisticated structures (e.g., wait-for graphs) is so high for a system in comparison to an array of structures, most discovery and resolved-deadlock protocols use them. Due to imprecise knowledge in specifying the transactions’ attributes, distributed deadlock resolution methods present a new problem in dealing with uncertainty. To address this problem, a variety of fuzzy logic-based techniques have been proposed. However, very little attention has been paid to dealing with ambiguous, vague, incomplete, and inconsistent information about transaction attributes in a single framework. In this paper, we used neutrosophic logic, a generalization of fuzzy logic, to solve the problem of uncertainty in distributed real-time deadlock-resolving systems. The proposed method is structured to reflect multiple types of knowledge and relations among all features and tripartitions the transactions’ features include validation factor degree, slackness degree, degree of deadline-missed transaction based on the degree of membership of truthiness, degree of membership of indeterminacy, and degree of membership of falsity. We developed a tool set and conducted experiments using benchmark datasets. There is an increase in detection rate and a large drop in rollback rate when this new strategy is used. Our technology resolved all database deadlocks and significantly increased database performance by up to three orders of magnitude.