MétaCan
Menu
Back to cohort

Towards Reliable IoT: Fog-Based AI Sensor Validation

2019· article· en· W3014030278 on OpenAlex
Luke Russell, Felix Kwamena, Rafik Goubran

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
FieldEnvironmental Science
TopicAir Quality Monitoring and Forecasting
Canadian institutionsCarleton University
Fundersnot available
KeywordsComputer scienceDependabilityFalse positive paradoxData validationCloud computingRobustness (evolution)Edge computingReliability (semiconductor)Cyber-physical systemWireless sensor networkProfiling (computer programming)Enhanced Data Rates for GSM EvolutionResilience (materials science)Real-time computingDistributed computingArtificial intelligencePower (physics)Computer networkDatabase

Abstract

fetched live from OpenAlex

Trust, reliability, and validation of data collected in distributed edge sensor systems is an increasingly relevant issue. Though the obvious solution of deploying redundant identical systems can provide validation, real-world modification constraints can sometimes make this difficult, or even prevent this. However, many distributed sensors exist for other purposes, that may be available to be used. Introducing validation with existing sensors may impose too high a requirement for bandwidth to use cloud-based validation, while edge-based validation may require too much computing power. A fog-based validation layer using sensory substitution is presented. With the rise of cyber-physical attacks on cloud, fog, and edge computing systems, validation is important, and lack of correct validation has been seen in some high impact cases where incorrect sensor data can be thought of as as true. A playback cyber-attack is discussed, and an algorithm for increasing reliability of IoT systems in the case of typical sensor errors or more serious incidents like cyber-physical attacks is presented. Given the need for dependable autonomy and reliability in IoT systems, this paper presents a method of sensor validation to increase robustness, resilience and dependability of sensed data by detecting false positives and negatives, and corroboration of true positives and negatives, using sensory substitution. Perhaps sometimes sensor data is trusted without ongoing validation. Using the example of cameras and artificial intelligence-based human presence detection, as well as using ambient distributed magnetometers and luminosity sensors, examples of a fog-based corroboration and validation methodology for human detection is presented. Results show the technique is an effective vector for sensor validation using available sensors, and scenarios where sensory substitution corrects false positives and false negatives from an artificial intelligence visual model are shown.

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 categoriesInsufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.659
Threshold uncertainty score0.997

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 communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0050.004

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 head0.019
GPT teacher head0.259
Teacher spread0.240 · 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

Citations10
Published2019
Admission routes1
Has abstractyes

Explore more

Same topicAir Quality Monitoring and ForecastingFrench-language works237,207