MétaCan
Menu
Back to cohort

Radio Frequency Interference Detection using Deep Learning

2020· article· en· W3038428551 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicWireless Signal Modulation Classification
Canadian institutionsUniversité du Québec à Montréal
Fundersnot available
KeywordsAutoencoderComputer scienceDeep learningObject detectionElectromagnetic interferenceArtificial intelligenceInterference (communication)Supervised learningObject (grammar)Process (computing)Pattern recognition (psychology)Artificial neural networkMachine learningTelecommunications

Abstract

fetched live from OpenAlex

Radio frequency interference (RFI) is considered as anomalous disruptive parasite signal due to its harmful impact in wireless communication. That is why, RFI mitigation is indispensable to avoid this impact. Detecting and localizing the RFI are the first steps in RFI mitigation process. In this paper, we propose two approaches to detect and localize RFI using the supervised and unsupervised techniques of deep learning. First, our research investigates an object detection algorithm based on convolutionnal neural network as a supervised approach. This proposition is based on the object detection algorithm You Only Look Once v3 (YOLO-v3) trained on real-world data contaminated by multiples sources of RFI. Second, we propose the utilisation of Convolutionnal Autoencoder (CAE) as an unsupervised approach. Experimental results show that the RFI detection by YOLO-v3 is relatively fast and it has an excellent accurate detection rate of 94% and show that the average precision of the YOLO-V3 algorithm can achieve 89%. For CAE, the average precision achieves 78% and outperforms the supervised approach in certain cases.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.945
Threshold uncertainty score0.322

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.053
GPT teacher head0.251
Teacher spread0.197 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations23
Published2020
Admission routes1
Has abstractyes

Explore more

Same topicWireless Signal Modulation ClassificationFrench-language works237,207