Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM64629
Volume:
10 |
6 |
Jun 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of computer application
Nehru Institute of Information Technology and Management
Department of computer application
Nehru Institute of Information Technology and Management
Radio frequency communication systems generate massive amounts of signal data continuously through satellite communication, radar systems, wireless transmission, and astronomical observations. Monitoring these signals manually is difficult because of environmental noise, interference, and rapidly changing signal patterns. Traditional monitoring systems mainly rely on threshold-based methods that fail to detect complex anomalies accurately in real time. The proposed system, “CosmicPulse AI: Intelligent Detection and Visualization of Radio Signal,” introduces an Artificial Intelligence based approach for intelligent signal monitoring and anomaly detection. The system processes pulsar signal datasets using advanced signal preprocessing techniques such as Butterworth Low-Pass Filtering and Savitzky-Golay smoothing. After preprocessing, Long Short-Term Memory (LSTM) neural networks and Isolation Forest algorithms are used to identify abnormal signal behavior and unexpected frequency variations. The system is developed using Python and Streamlit to provide an interactive real-time monitoring dashboard. Features such as signal overview graphs, anomaly analysis, live noise filtering, 3D radio wave visualization, burst tracking maps, and automated system alerts improve signal interpretation and monitoring efficiency. The proposed system can be effectively applied in radio astronomy, satellite communication monitoring, wireless spectrum sensing, and intelligent signal security analysis.
KEYWORDS
The project "CosmicPulse AI: Intelligent Detection and Visualization of Radio Signal" has been successfully designed and developed as a robust, real-time solution for the automated monitoring of radio frequency signals. In an era where the RF spectrum is becoming increasingly crowded, this system provides a critical bridge between complex signal data and actionable intelligence. By integrating advanced mathematical filters like Butterworth and Savitzky-Golay, the system effectively handles environmental noise, ensuring that signal integrity is maintained for analysis. The core intelligence, powered by a hybrid AI approach using LSTM Networks and Isolation Forest, demonstrates high efficiency in learning sequential signal patterns and accurately flagging unauthorized or anomalous transmissions that could signify security threats or scientific discoveries. The implementation of an interactive Streamlit dashboard equipped with 3D Wave Surface and Heatmap visualizations ensures that complex technical data is accessible to both expert researchers and non-technical security officers. Furthermore, the automated SMTP Alert Module and JSON Logging system ensure that no critical event goes unnoticed, providing a secure audit trail for future forensic analysis. Overall, CosmicPulse AI stands as a scalable, open-source, and efficient tool that addresses the modern challenges of satellite security, radio astronomy, and wireless interference monitoring. The project successfully meets all its initial objectives, delivering a high-performance application that is ready for deployment in real-world signal monitoring environments.
1. Marc Lichtman, PySDR: A Guide to SDR and DSP using Python, Software Defined Radio and Digital Signal Processing Tutorial. Available: [https://pysdr.org/] 2. Matthew Hall, Alex Betts, Donna Cox, David Pointer, and Volodymyr Kindratenko, The Visible Radio: Process Visualization of a Software-Defined Radio, IEEE Visualization Conference, 2005. Available: [https://ieeexplore.ieee.org/document/1532790] 3. Zeghdoud Sabrina, Teguig Djamel, Tanougast Camel, Mesloub Ammar, Sadoudi Said, and Nesraoui Okba, SDR Implementation of Spectrum Sensing using Deep Learning, International Journal of Sensors Wireless Communications and Control, 2023. Available: [https://www.eurekaselect.com/article/131705] 4. Stefan Brennsteiner, Towards Real-Time, Machine Learning Enhanced Signal Detection in 5G-NR, University of Edinburgh Research Archive, 2023. Available: [https://era.ed.ac.uk/handle/1842/42067] 5. Quoc Viet Pham, Nhan Thanh Nguyen, Thien Huynh-The, Long Bao Le, Kyungchun Lee, and Won Joo Hwang, Intelligent Radio Signal Processing: A Survey, IEEE Access, 2021. Available: [https://ieeexplore.ieee.org/document/9444812]
Publication Date
6/8/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
7
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...