Springer Science and Business Media LLC

Medical information system is a comprehensive system which integrates the application of medicine, information, management, computer and other disciplines. It has been widely used in the social medical security system. But with the rapid development of Internet plus medical technology, the risk of malicious invasion has increased dramatically, which gradually exposes the problem of inadequate medical information security. Therefore, effective detection of medical information system network intrusion and timely prevention of network threats have become the focus of attention and research in this field. Intrusion detection is a common detection method in network security, it plays a very important role in network security. Traditional intrusion detection is mostly based on rule matching, statistics and other methods. With the advent of the era of big data, traditional intrusion detection can not play a good performance, especially in the face of massive, complex and unbalanced intrusion data. The privacy data access monitoring system based on virtual computing environment can monitor the access of privacy data in two levels, namely, tracking the flow of privacy data within the host and tracking the propagation of privacy data between hosts. In the host, we can customize the taint propagation rules to achieve fine-grained capture of privacy data violations in the virtual computing environment. Hence, this paper studies the medical data intrusion detection technology based on virtual data pipeline from the assurance perspectives. The model is designed and implemented with the discussions of the performance. The experimental results have proven that the proposed model is efficient.

In the present paper, we consider the residual lifetime Type-II censored Lindley distribution model with unknown parameter θ. Maximum likelihood estimation with asymptotic confidence intervals are used to estimate the parameter and the reliability characteristics. Bootstrap-p and t confidence intervals are also developed. Bayes estimates using generalized entropy loss function (GELF) with highest posterior density (HPD) credible intervals are obtained for the parameter and the reliability characteristics. Here, the posterior distribution is not in an explicit form therefore, we use Metropolis–Hastings algorithm to estimate the posterior distribution. To perform the analysis of the estimation procedures, a Markov Chain Monte Carlo simulation study is performed. For giving illustration to our work, a real data example is also studied.

The present work is depend upon a different data structure to perform the network reliability estimation efficiently. Zero suppressed binary decision diagram (ZBDD) is an well ordered and effective method of representing not only the boolean functions but also the sets of combinations than the conventional binary decision diagrams (BDD). This paper proposes new algorithm to manipulate the ZBDDs the variant of BDD on some benchmark networks. The 2-terminal network reliability problem has been studied extensively and effective results have been obtained.

In Big data computing domains with a huge network of connected devices involved in various internet and social network concerns mainly for security, integrity, authentication and data privacy. Allocation and efficient usage of containers provided by cloud service providers has huge impact over efficient data processing and data handling. Batch processing method emphasizes huge databases by letting it into the programmable domains and segregate in accordance with their size, reliability, processing speed and required memory space. Whereas, Stream processing involves scrutinizing data promptly before entering into the stream and scrutinizing will be done accordingly. Container selection plays a major role in such processing methodologies and promptly makes the effective resource scheduling possible and efficient in cloud service providing. In our proposed method, the Guided Container Selection (GCS) process eradicates the bottle neck problem by selecting an efficient and optimal container which satisfies all requirements like required size, reliability, processing speed etc. Implementing either batch processing or stream processing to analyze solutions for multiple domain container selection which will be analyzed and resolved through Deep Neural Learning (DNL). The novel DNL method successfully ranks and handles optimal container selection according to the dynamic data involvement and provides efficient solutions for data processing.In future it also helps selecting appropriate containers for similar requirements for cloud service providers and also for its consumers.

Frauds accounted for significant losses in the financial sector and emerged as the industry’s biggest challenge. Companies invest significant amounts to prevent such fraud. It has been reported that 63.6% of the financial institutions that use Automated Fraud prevention methods successfully prevented frauds before their occurrence. Some estimations suggest that 80% of specialists are confident in cutting down fraud using Artificial Intelligence (AI)-based platforms. Several research studies have also administered AI-based techniques for fraud prevention. This study takes a systematic literature review approach to uncover the emerging areas of fraud detection using AI. The authors have analyzed 241 research articles published in the last 20 years. The Scopus database was the source of the articles in the literature review. The meta-analysis and network analysis were carried out, and the output shows the up trend of this research domain. Author-coauthor network collaboration is analyzed using the VOSviewer tool. K-means clustering was performed to identify the critical research domain, and future research areas were also identified. This research will act as a reference for future scholars who want to perform analysis on the application of AI techniques in financial fraud detection and prevention. We finally conclude the study by identifying the scope of future research and will be a value addition for financial fraud researchers.

The recently introduced Submission Decision Process problem entails deciding, out of N-1! possible journal submission schedules, which one will, if followed, give an author the maximum expected number of citations while minimizing the expected number of submissions required on one hand, or the expected time spent in review on the other hand. The unnecessarily high computational burden in the existing algorithm used for addressing this problem was observed, and propose a new discrete Multi-Objective Particle Swarm Optimization algorithm which cuts down computational time by a huge factor is proposed. An improvement in the computation of the various objectives is also suggested which further reduces computational burden, and the problem is extended beyond the usual bi-objective optimization to a 3-objective optimization which is solved with the proposed algorithm.

A key objective for e-maintenance efforts is to align maintenance processes with business- and operational processes in order to reach organizational objectives. In the context of the process- and manufacturing industry a key objective for firms is to avoid downtime and to make sure all critical production equipment is up and running. To this end, e-maintenance has become increasingly important for the process- and manufacturing industry. Successful e-maintenance is realized by the organizational use of advanced information technology-solutions which aims at moving maintenance work from being primarily reactive (e.g. to react and respond to equipment breakdowns) to predictive (e.g. to predict when equipment are in need of maintenance before it breaks down). Building on a collaborative project with industrial organizations in the pulp and paper and the mining industry this paper explores organizational opportunities and challenges associated with the design and implementation of IT-based services for remote diagnostics of industrial equipment. We observe opportunities and challenges related to organizational innovation and learning. The paper introduces a multi-contextual perspective to better understand the opportunities and challenges associated with organizational learning and innovation. We argue that in order for e-maintenance services to be successful it must not only build on leading-edge technological solutions but also be built on an explicit model for how the maintenance work is organized and how e-maintenance efforts are aligned with overall organizational objectives.