2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC) 2019
DOI: 10.1109/vlsi-soc.2019.8920298
|View full text |Cite
|
Sign up to set email alerts
|

Towards an Embedded and Real-Time Joint Human-Machine Monitoring Framework: Dataset optimization Techniques for Anomaly Detection

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

2
5
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
2
1

Relationship

2
1

Authors

Journals

citations
Cited by 3 publications
(7 citation statements)
references
References 10 publications
2
5
0
Order By: Relevance
“…As mentioned above, we will examine in the future the impact of this drop in accuracy in processing time, memory footprint and energy consumption. In our previous work [11], we also observed a drop around 10%, having a significant impact on processing time and energy consumption. Specifically, an average of 10‐fold reduction in energy consumption was achieved, rendering the 10% drop in accuracy acceptable, paving the way to achieve real‐time low‐power classification.…”
Section: Framework Evaluationsupporting
confidence: 51%
See 3 more Smart Citations
“…As mentioned above, we will examine in the future the impact of this drop in accuracy in processing time, memory footprint and energy consumption. In our previous work [11], we also observed a drop around 10%, having a significant impact on processing time and energy consumption. Specifically, an average of 10‐fold reduction in energy consumption was achieved, rendering the 10% drop in accuracy acceptable, paving the way to achieve real‐time low‐power classification.…”
Section: Framework Evaluationsupporting
confidence: 51%
“…In this study, we present a framework for the creation of a dataset consisting of data from both the human operator and the ROV. In detail, the contributions of this manuscript significantly extend our initial work in [11]:…”
Section: Introductionmentioning
confidence: 66%
See 2 more Smart Citations
“…Prior to feature extraction, we apply a normalization step to the raw data using the MinMaxScaler of scikit-learn library in Python [22] to map input values to [0, 1]. Following scaling, we extracted features from the sEMG and the ROV values, similar to our previous work [23], while HR is used as a raw value. The 11 extracted features from the sEMG values are the following: mean absolute value (MAV), variance (VAR), waveform length (WL), zero crossings (ZC), willison amplitude (WAMP), root mean square (RMS), slope sign change (SSC), minimum (MIN), maximum (MAX), integrated absolute value (IAV) and simple square integral (SSI).…”
Section: B Pre-processing and Feature Extractionmentioning
confidence: 99%