Machine translation is an ongoing field of research from the last decades. The main aim of machine translation is to remove the language barrier. Earlier research in this field started with the direct word-to-word replacement of source language by the target language. Later on, with the advancement in computer and communication technology, there was a paradigm shift to data-driven models like statistical and neural machine translation approaches. In this paper, we have used a neural network-based deep learning technique for English to Urdu languages. Parallel corpus sizes of around 30923 sentences are used. The corpus contains sentences from English-Urdu parallel corpus, news, and sentences which are frequently used in day-to-day life. The corpus contains 542810 English tokens and 540924 Urdu tokens, and the proposed system is trained and tested using 70 : 30 criteria. In order to evaluate the efficiency of the proposed system, several automatic evaluation metrics are used, and the model output is also compared with the output from Google Translator. The proposed model has an average BLEU score of 45.83.
Purpose
The purpose of this paper is to identify the different sequence generation techniques for learning, which are applied to a broad category of personalized learning experiences. The papers have been classified using different attributes, such as the techniques used for sequence generation, attributes used for sequence generation; whether the learner is profiled automatically or manually; and whether the path generated is dynamic or static.
Design/methodology/approach
The search for terms learning sequence generation and E-learning produced thousands of results. The results were filtered, and a few questions were answered before including them in the review. Papers published only after 2005 were included in the review.
Findings
The findings of the paper were: most of the systems generated non-adaptive paths. Systems asked the learners to manually enter their attributes. The systems used one or a maximum of two learner attributes for path generation.
Originality/value
The review pointed out the importance and benefits of learning sequence generation systems. The problems in existing systems and future areas of research were identified which will help future researchers to pursue research in this area.
Mobile applications affect our everyday activities and have become more and more information centric. Effort estimation for mobile application is an essential factor to consider in the development cycle. Due to feature complexities and size, effort estimation of mobile applications poses a continued challenge for developers. This paper attempts to adapt COSMIC Function Point and Unified Modeling Language (UML) techniques to estimate the size of a given mobile application. The COSMIC concepts capture data movements of the functional processes whereas the UML class analyzes them. We utilize the Use Case Diagrams, sequence diagrams and class diagrams for mapping the Function user requirements for sizing mobile applications. We further present a new size measurement technique; Unadjusted Mobile COSMIC Function points (UMCFP) to get the functional size of mobile application using Mobile Complex Factors as an input. In this study eight mobile applications were analyzed using UMCFP, Function Point Analysis and COSMIC Function Point. The results were compared with the actual size of previous Mobile application projects.
A cloud management platform allows users to run a multitenant atmosphere exploiting the resources from the virtual infrastructure. Although, clouds area unit is engineered with SaaS, PaaS and IaaS service layers. Infrastructure services area unit is the first and foremost typical non-public cloud services. For efficiency and high-performance in the cloud management platform, we propose the parallel virtualization in the cloud computing environment. Data centers are created which can be used by multiple users at the same time by apportioning capabilities as the need arises had made this possible. Elasticity can be effectively achieved via parallel virtualization in IaaS to community cloud.
Rapid connectivity and exchange of information across the globe with extension of computer networks during the past decade has led to security threats in network communication and has become a critical concern for network management. It is necessary to retain high security measures to ensure safe and trusted communication across the network. Diverse soft-computing-based methods have been devised in the past for the perfection of intrusion detection systems on host-based and host-independent systems. This chapter discusses the flow-based anomaly detector for intrusion in network by self-learning process with characteristics of bacterial forging approach. This approach handles the network-flow and attack on network traffic in an automated fashion. This approach works on host-independent systems and on stream of network rather than payload length where data behavior of flow in network is analyzed. This model provides a cataloging of attacks and resistance mechanism techniques to avoid intrusion.
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.