RECORD
Multi Agent System for Machine Learning Under Uncertainty in Cyber Physical Manufacturing System
Multiagent Systems · Submitted 28 Jul 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experimentally, we implement Bayesian Neural Networks for multi-tasks classification on a public dataset for the real-time condition monitoring of a hydraulic system and demonstrate the usefulness of the system by evaluating the probability of a prediction being accurate given its uncertainty.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Recent advancements in predictive machine learning has led to its application in various use cases in manufacturing. Most research focused on maximising predictive accuracy without addressing the uncertainty associated with it. While accuracy is important, focusing primarily on it poses an overfitting danger, exposing manufacturers to risk, ultimately hindering the adoption of these techniques. In this paper, we determine the sources of uncertainty in machine learning and establish the success criteria of a machine learning system to function well under uncertainty in a cyber-physical manufacturing system (CPMS) scenario. Then, we propose a multi-agent system architecture which leverages probabilistic machine learning as a means of achieving such criteria. We propose possible scenarios for which our proposed architecture is useful and discuss future work. Experimentally, we implement Bayesian Neural Networks for multi-tasks classification on a public dataset for the real-time condition monitoring of a hydraulic system and demonstrate the usefulness of the system by evaluating the probability of a prediction being accurate given its uncertainty. We deploy these models using our proposed agent-based framework and integrate web visualisation to demonstrate its real-time feasibility.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Recent advancements in predictive machine learning has led to its application in various use cases in manufacturing. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | Most research focused on maximising predictive accuracy without addressing the uncertainty associated with it. | gap 0.90 | 0.04 | 0.03 | asserted 1.00 |
| s2 | While accuracy is important, focusing primarily on it poses an overfitting danger, exposing manufacturers to risk, ultimately hindering the adoption of these techniques. | gap 0.64 | 0.06 | 0.06 | asserted 0.90 |
| s3 | In this paper, we determine the sources of uncertainty in machine learning and establish the success criteria of a machine learning system to function well under uncertainty in a cyber-physical manufacturing system (CPMS) scenario. | contribution 1.00 | 0.94 | 0.12 | asserted 0.99 |
| s4 | Then, we propose a multi-agent system architecture which leverages probabilistic machine learning as a means of achieving such criteria. | contribution 0.53 | 0.92 | 0.14 | asserted 0.98 |
| s5 | We propose possible scenarios for which our proposed architecture is useful and discuss future work. | future work 0.78 | 0.76 | 0.06 | hedged possibility 0.76 |
| s6 | Experimentally, we implement Bayesian Neural Networks for multi-tasks classification on a public dataset for the real-time condition monitoring of a hydraulic system and demonstrate the usefulness of the system by evaluating the probability of a prediction being accurate given its uncertainty. | method 0.71 | 0.97 | 0.20 | asserted 1.00 |
| s7 | We deploy these models using our proposed agent-based framework and integrate web visualisation to demonstrate its real-time feasibility. | method 0.66 | 0.95 | 0.10 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Recent advancements in predictive machine learning has led to its application in various use cases in manufacturing. Most research focused on maximising predictive accuracy without addressing the uncertainty associated with it. While accuracy is important, focusing primarily on it poses an overfitting danger, exposing manufacturers to risk, ultimately hindering the adoption of these techniques. In this paper, we determine the sources of uncertainty in machine learning and establish the success criteria of a machine learning system to function well under uncertainty in a cyber-physical manufacturing system (CPMS) scenario. Then, we propose a multi-agent system architecture which leverages probabilistic machine learning as a means of achieving such criteria. We propose possible scenarios for which our proposed architecture is useful and discuss future work. Experimentally, we implement Bayesian Neural Networks for multi-tasks classification on a public dataset for the real-time condition monitoring of a hydraulic system and demonstrate the usefulness of the system by evaluating the probability of a prediction being accurate given its uncertainty. We deploy these models using our proposed agent-based framework and integrate web visualisation to demonstrate its real-time feasibility.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 2 sentences without a confident label
Uses the method or tool of 2 papers
-
Each node's weight is represented by a probability distribution initialised as uniform distribution and trained using Bayes by Backprop [ref] .
Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference · EXPERIMENTAL SETUP · 1.00
-
The model is trained for 300 epochs, with learning rate of 0.005 and Adam optimiser [ref] .
Adam: A Method for Stochastic Optimization · EXPERIMENTAL SETUP · 1.00
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.