{"title":"Start-of-Packet Detection Using Machine Learning","authors":"Simrandeep Kaur;Arhum Ahmad;Satyam Agarwal","doi":"10.1109/TCOMM.2026.3669492","DOIUrl":null,"url":null,"abstract":"With the rapid proliferation of wireless communication systems, accurate Start-of-Packet (SOP) detection is essential for efficient packet reception and decoding. Conventional correlation-based techniques struggle under low signal-to-noise ratio (SNR) and phase/frequency offsets. This paper proposes a Proximity-based Support Vector Machine (P-SVM), a novel SVM-based approach that incorporates Proximity-based weighting and a Distance adjustment function to enhance robustness under such impairments. Evaluated using both simulations and SDR-based experiments, P-SVM consistently outperforms conventional and state-of-the-art methods in Probability of detection, Mean Absolute Error, and Probability of false alarm. Moreover, P-SVM offers reduced implementation complexity, making it suitable for practical deployment.","PeriodicalId":13041,"journal":{"name":"IEEE Transactions on Communications","volume":"74 ","pages":"5867-5878"},"PeriodicalIF":8.4000,"publicationDate":"2026-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Communications","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/11418617/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
With the rapid proliferation of wireless communication systems, accurate Start-of-Packet (SOP) detection is essential for efficient packet reception and decoding. Conventional correlation-based techniques struggle under low signal-to-noise ratio (SNR) and phase/frequency offsets. This paper proposes a Proximity-based Support Vector Machine (P-SVM), a novel SVM-based approach that incorporates Proximity-based weighting and a Distance adjustment function to enhance robustness under such impairments. Evaluated using both simulations and SDR-based experiments, P-SVM consistently outperforms conventional and state-of-the-art methods in Probability of detection, Mean Absolute Error, and Probability of false alarm. Moreover, P-SVM offers reduced implementation complexity, making it suitable for practical deployment.
期刊介绍:
The IEEE Transactions on Communications is dedicated to publishing high-quality manuscripts that showcase advancements in the state-of-the-art of telecommunications. Our scope encompasses all aspects of telecommunications, including telephone, telegraphy, facsimile, and television, facilitated by electromagnetic propagation methods such as radio, wire, aerial, underground, coaxial, and submarine cables, as well as waveguides, communication satellites, and lasers. We cover telecommunications in various settings, including marine, aeronautical, space, and fixed station services, addressing topics such as repeaters, radio relaying, signal storage, regeneration, error detection and correction, multiplexing, carrier techniques, communication switching systems, data communications, and communication theory. Join us in advancing the field of telecommunications through groundbreaking research and innovation.