Resource-aware Feature Extraction in Mobile Edge Computing


Mobile image recognition services are revolutionizing our everyday lives by providing people with image recognition services that they can access through the cameras on their mobile devices. However, the majority of currently available cloud- and edge-based approaches are plagued by two major drawbacks: I low recognition accuracy and high network bandwidth pressure, and (ii) it is not simple to extract features based on the resources that are currently available on mobile devices. In this article, we present a framework for resource-aware feature extraction that is intended for use in mobile image recognition services. The discriminative feature extraction (DFE) and NestDFE algorithms make up the aforementioned framework that has been proposed. The DFE algorithm is able to generate an extractor E, which can then be used to extract discriminative features from image data sets stored on the edge server as well as images stored on mobile devices. As a result, the proposed framework has the potential to achieve a higher recognition accuracy while simultaneously requiring mobile devices to upload fewer feature data sets to the edge server. The NestDFE algorithm is responsible for the generation of a single multi-capacity extractor that functions as a series of sub-extractors and enables mobile devices to select sub-extractors in a manner that is dynamic. The results of the experiments show that the proposed framework increases recognition accuracy by approximately 23 percent and reduces network traffic by approximately 76 percent in comparison to the existing methods.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Biomedical Relation Extraction With Knowledge Graph-Based Recommendations ABSTRACT: Biomedical Relation Extraction (RE) systems search for and categorize relations between biomedical entities in order to improve
PROJECT TITLE : A Natural Language Process-Based Framework for Automatic Association Word Extraction ABSTRACT: In psychology, word association has been extensively explored for exposing mental representations and relationships
PROJECT TITLE : Automatic Keyword Extraction for Text Summarization A Survey ABSTRACT: Data has been quickly rising in recent years in every sphere, including journalism, social media, banking, education, and so on. Due to the
PROJECT TITLE : Financial Latent Dirichlet Allocation (FinLDA) Feature Extraction in Text and Data Mining for Financial Time Series Prediction ABSTRACT: Many financial time series predictions based on fundamental analysis have
PROJECT TITLE : Automatic Land Cover Reconstruction From Historical Aerial Images An Evaluation of Features Extraction and Classification Algorithms ABSTRACT: As large-scale epidemiological studies including retrospective study

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry