A Machine Learning Approach to Predicting Satellite Receiver Compatibility with Smartphones Tablets and Computers
Keywords: Machine learning; satellite receiver compatibility; smartphones; tablets; computers; signal processing; feature engineering; model evaluation; cross-platform interoperability; on-device inference.
Abstract:
This thesis presents a machine learning framework for predicting the compatibility of satellite receivers with consumer devices (smartphones, tablets, and computers). As satellite-based services proliferate across mobile and desktop platforms, device–receiver interoperability remains a frequent source of failed installations, degraded performance, and costly support. We formulate compatibility prediction as a supervised learning problem and develop an end-to-end pipeline that: (1) collects and normalizes multi-source data including receiver hardware specs, modulation/encoding parameters, RF signal characteristics (SNR, BER, frequency bands), device OS and driver profiles, connection interfaces (USB, Wi-Fi, Bluetooth), and contextual metadata (firmware versions, environment); (2) extracts domain-informed features through signal-processing and categorical encoding; (3) trains and compares a range of models (tree-based ensembles, support vector machines, and neural networks) using stratified cross-validation; and (4) evaluates models with robust metrics (accuracy, precision, recall, F1, ROC-AUC) and calibration analysis. The study also explores feature importance, failure-mode clustering, and a lightweight on-device inference strategy for real-time compatibility checks. Results demonstrate that ML-driven prediction can substantially reduce trial-and-error deployment, guide compatibility-aware recommendations, and inform receiver and driver design. The thesis contributes a curated compatibility dataset, reproducible modeling pipeline, and practical recommendations for integrating predictive compatibility checks into consumer installation workflows.
"A Machine Learning Approach to Predicting Satellite Receiver Compatibility with Smartphones Tablets and Computers", JNRID - JOURNAL OF NOVEL RESEARCH AND INNOVATIVE DEVELOPMENT (www.JNRID.org), ISSN:2984-8687, Vol.3, Issue 9, page no.a673-a763, September-2025, Available :https://tijer.org/JNRID/papers/JNRIDTHE2010.pdf
Volume 3
Issue 9,
September-2025
Pages : a673-a763
Paper Reg. ID: JNRID_701673
Published Paper Id: JNRIDTHE2010
Downloads: 000117
Research Area: Other area not in list
Country: Gondar City , Amhara, Ethiopia
ISSN: 2984-8687 | IMPACT FACTOR: 9.57 Calculated By Google Scholar | ESTD YEAR: 2023
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.57 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: JNRID (IJ Publication) Janvi Wave
