add zenodo ref
This commit is contained in:
Arthur Grisel-Davy
parent
6c413308a1
commit
87f17c2564
2 changed files with 52 additions and 12 deletions
|
|
@ -473,6 +473,12 @@ title={Evaluation Dataset for the Machine State Detector, https://zenodo.org/rec
|
|||
year={2023},
|
||||
}
|
||||
|
||||
@misc{name_hidden_for_peer_review_2023_8192914,
|
||||
title = {{160 Hours of Labeled Power Consumption Dataset of
|
||||
Computer, https://doi.org/10.5281/zenodo.8192914}},
|
||||
year = 2023,
|
||||
}
|
||||
|
||||
@article{gupta2021novel,
|
||||
title={A novel failure mode effect and criticality analysis (FMECA) using fuzzy rule-based method: A case study of industrial centrifugal pump},
|
||||
author={Gupta, Gajanand and Ghasemian, Hamed and Janvekar, Ayub Ahmed},
|
||||
|
|
@ -667,3 +673,41 @@ howpublished = {https://github.com/fchollet/keras},
|
|||
pages={2825--2830},
|
||||
year={2011}
|
||||
}
|
||||
|
||||
@INPROCEEDINGS{1253591,
|
||||
|
||||
author={Saputra, H. and Vijaykrishnan, N. and Kandemir, M. and Irwin, M.J. and Brooks, R. and Kim, S. and Zhang, W.},
|
||||
|
||||
booktitle={2003 Design, Automation and Test in Europe Conference and Exhibition},
|
||||
|
||||
title={Masking the energy behavior of DES encryption [smart cards]},
|
||||
|
||||
year={2003},
|
||||
|
||||
volume={},
|
||||
|
||||
number={},
|
||||
|
||||
pages={84-89},
|
||||
|
||||
doi={10.1109/DATE.2003.1253591}
|
||||
}
|
||||
|
||||
@ARTICLE{6918465,
|
||||
|
||||
author={Khedkar, Ganesh and Kudithipudi, Dhireesha and Rose, Garrett S.},
|
||||
|
||||
journal={IEEE Transactions on Nanotechnology},
|
||||
|
||||
title={Power Profile Obfuscation Using Nanoscale Memristive Devices to Counter DPA Attacks},
|
||||
|
||||
year={2015},
|
||||
|
||||
volume={14},
|
||||
|
||||
number={1},
|
||||
|
||||
pages={26-35},
|
||||
|
||||
doi={10.1109/TNANO.2014.2362416}}
|
||||
|
||||
|
|
|
|||
|
|
@ -343,7 +343,6 @@ Algorithm~\ref{alg:code} presents the implementation's pseudo-code.
|
|||
\subsection{Analysis}
|
||||
|
||||
\textbf{Time-Efficiency:}
|
||||
\agd{Better time efficiency analysis and comparison with the efficiency of \gls{1nn}}
|
||||
The time efficiency of the algorithm is expressed as a function of the number of normalized distance computations and the number of comparison operations.
|
||||
Each part of the algorithm has its own time-efficiency expression, with Algorithm~\ref{alg:code} showing each of the three parts.
|
||||
The first part, dedicated to the threshold computation, is polynomial in the number of patterns and linear in the length of each pattern.
|
||||
|
|
@ -401,7 +400,6 @@ Figure~\ref{fig:areas} illustrate the areas of capture around the patterns for d
|
|||
\caption{2D visualization of the areas of capture around each pattern as $\alpha$ changes. When $\alpha \ggg 2$, the areas of capture tend to equal these of a classic \gls{1nn}.}
|
||||
\label{fig:areas}
|
||||
\end{figure}
|
||||
\agd{Increase font size}
|
||||
|
||||
|
||||
The influence of the $\alpha$ coefficient on the classification is monotonic and predictable.
|
||||
|
|
@ -487,7 +485,6 @@ It is important to notice that zero represents the best Levenshtein distance and
|
|||
|
||||
|
||||
\subsection{Dataset}\label{sec:dataset}
|
||||
\agd{include more datasets from REFIT. One per house would be perfect but simply more is already good. Add in annexe why other are rejected.}
|
||||
We evaluate the performances of \gls{mad} against eight time series.
|
||||
One is a simulated signal composed of sine waves of varying frequency and average.
|
||||
Four were captured in a lab environment on consumer-available machines (two NUC PCs and two wireless routers).
|
||||
|
|
@ -496,6 +493,7 @@ Table~\ref{tab:dataset} presents the times series and their characteristics.
|
|||
|
||||
\begin{table}
|
||||
\centering
|
||||
\caption{Characteristics of the machines in the evaluation dataset.}
|
||||
\begin{tabular}{lcc}
|
||||
Name & length & Number of states\\
|
||||
\toprule
|
||||
|
|
@ -508,7 +506,6 @@ Table~\ref{tab:dataset} presents the times series and their characteristics.
|
|||
REFIT-H4A1 & 100000 & 142\\
|
||||
\bottomrule
|
||||
\end{tabular}
|
||||
\caption{Characteristics of the machines in the evaluation dataset.}
|
||||
\label{tab:dataset}
|
||||
\end{table}
|
||||
|
||||
|
|
@ -546,7 +543,6 @@ The no-consumption sections are not challenging --- i.e., all detectors perform
|
|||
For this reason, we removed large sections of inactivity between active segments to make the time series more challenging without tempering with the order of detector performances.
|
||||
|
||||
\subsection{Alternative Methods}
|
||||
\agd{explain how the svm and mlp are trained.}
|
||||
We implemented three alternative methods to compare with \gls{mad}.
|
||||
The alternative methods are chosen to be well-established and of comparable complexity.
|
||||
The methods are: a \gls{1nn} detector, an \gls{svm} classifier, and an \gls{mlp} classifier.
|
||||
|
|
@ -623,8 +619,9 @@ The final sampling rate of 20 samples per second was selected empirically to be
|
|||
For each compressed day of the experiment (four hours segment, thereafter referred to as days), the \gls{mad} performs state detection and returns a label vector.
|
||||
This label vector associates a label to each sample of the power trace following the mapping: -~1 is UNKNOWN, 0 is SLEEP, 1 is IDLE, 2 is HIGH and 3 is REBOOT.
|
||||
The training dataset comprises one sample per state, captured during the run of a benchmark script that interactively places the machine in each state to detect.
|
||||
\agd{make dataset available}
|
||||
The script on the machine generates logs that serve as ground truth to verify the results of rule checking.
|
||||
The traces and ground truth for each day of the experiment are available online \cite{name_hidden_for_peer_review_2023_8192914}.
|
||||
Please note that day 1 was removed due to a scheduling issue that affected to scenario.
|
||||
Figure~\ref{fig:preds} present an illustration of the results.
|
||||
The main graph line in the middle is the power consumption over time.
|
||||
The line's colour represents the machine's predicted state based on the power consumption pattern.
|
||||
|
|
@ -670,7 +667,7 @@ The performance measure represents the ability of the complete pipeline (\gls{ma
|
|||
The main metrics are the micro and macro $F_1$ score of the rule violation detection.
|
||||
The macro-$F_1$ score is defined as the arithmetic mean over individual $F_1$ scores for a more robust evaluation of the global performance as described in \cite{opitz2021macro}.
|
||||
Table~\ref{tab:rules-results} presents the performance for the detection of each rule.
|
||||
The performances are perfect for this scenario without any false positive or false negative over XX\agd{updates} runs.
|
||||
The performances are perfect for this scenario without any false positive or false negative over 40 runs.
|
||||
|
||||
The perfect detection of more complex patterns like REBOOT illustrates the need for a system capable of matching arbitrary states.
|
||||
Flat lines at varying average levels represent many common states from embedded systems.
|
||||
|
|
@ -686,16 +683,15 @@ This illustrates that \gls{mad} balances the tradeoff between simple, explainabl
|
|||
\begin{tabular}{lccc}
|
||||
Rule & Violation Ratio & Micro-$F_1$ & Macro-$F_1$\\
|
||||
\toprule
|
||||
Night Sleep & 0.273 & 1.0 & \multirow{4}*{1.0} \\
|
||||
Work Hours & 0.227 & 1.0 & \\
|
||||
Reboot & 0.445 & 1.0 & \\
|
||||
No Long High & 0.773 & 1.0 & \\
|
||||
Night Sleep & 0.33 & 1.0 & \multirow{4}*{1.0} \\
|
||||
Work Hours & 0.3 & 1.0 & \\
|
||||
Reboot & 0.48 & 1.0 & \\
|
||||
No Long High & 0.75 & 1.0 & \\
|
||||
\bottomrule
|
||||
\end{tabular}
|
||||
\label{tab:rules-results}
|
||||
\end{table}
|
||||
|
||||
|
||||
\section{Discussion}\label{sec:discussion}
|
||||
In this section, we highlight specific aspects of the proposed solution.
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue