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

Elia, Rafaella; Plastiras, George; Theocharides, Theocharis

doi:10.1109/vlsi-soc.2019.8920298

Cited by 3 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

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%

“…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%

“…Moreover, monitoring the movements of different body parts, according to the mission, may be beneficial for detecting stress and fatigue. In our previous work [11], we suggested that the sEMG from the operator's right hand, in addition to the IMU sensor data from the UAV, can be fused to construct a small; yet an effective dataset that can be classified by a classifier executed on a low-power processor [11]. Furthermore, since HR yields promising results in detecting stress and fatigue during a mission, it was also included in the proposed approach.…”

Section: Human Monitoringmentioning

confidence: 99%

“…We utilise these sensors since most of the commercial devices are employed with these types of sensors; hence, we eliminated the need of external sensors or devices. We utilise altitude and relative height given from the barometer, additionally to the data used in our previous approach [11]. A description of the sensors of a UAV is provided in Table 1.…”

Section: Proposed Dataset Collection Frameworkmentioning

confidence: 99%

See 3 more Smart Citations

A real‐world data collection framework for a fused dataset creation for joint human and remotely operated vehicle monitoring and anomalous command detection

Elia

Plastiras

Pettemeridou

et al. 2022

CAAI Trans on Intel Tech

Self Cite

View full text Add to dashboard Cite

Unmanned Remotely Operated Vehicles (ROVs) are widely used in safety‐critical missions, spanning across monitoring, surveillance, and search and rescue missions. In most cases, the human operator controls the ROV under stressful conditions and in harsh environments. The physical and mental states of the operator are vital as they may cause involuntary movements, issuing unintentional commands due to fatigue or stress. Consequently, a joint monitoring mechanism that will assess the operator's commands can be beneficial in preventing potentially catastrophic events, such as accidents. To this end, in this study, we propose a data collection framework for creating a fused dataset, consisting of data obtained from both the human operator and the ROV, and we integrate stress induction to stimulate stress and fatigue that may affect operators during missions. We optimise the dataset, which includes the operator's physiological signals and inertial measurement unit (IMU) sensor data from the ROV, using data fusion approaches and feature extraction. We evaluate the dataset through the statistical analysis, illustrating a statistical difference between data characterising normal and involuntary commands. Finally, we evaluate the optimised and original datasets over a variety of classifiers, demonstrating an accuracy of 94% and 95%, respectively.

show abstract

Section: Framework Evaluationsupporting

confidence: 51%

Section: Introductionmentioning

confidence: 66%

Section: Human Monitoringmentioning

confidence: 99%

Section: Proposed Dataset Collection Frameworkmentioning

confidence: 99%

See 2 more Smart Citations

A real‐world data collection framework for a fused dataset creation for joint human and remotely operated vehicle monitoring and anomalous command detection

Elia

Plastiras

Pettemeridou

et al. 2022

CAAI Trans on Intel Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…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%

An Analysis of Machine Learning Classifiers for Joint Operator-UAV Monitoring and Abnormal Command Detection

Elia

Savva

Pettemeridou

et al. 2022

2022 International Conference on Unmanned Aircraft Systems (ICUAS)

Self Cite

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAVs) are widely used in search and rescue missions, which mostly involve stressful conditions for first responders and especially UAV operators, who have to control the UAVs under dynamically changing conditions and harsh environments. Operations under these conditions lead to increased stress and fatigue for the operators and may result in unwanted commands, which in turn may endanger the UAV's mission and result in accidents and delays, something often critical in search and rescue. However, jointly monitoring both the UAV and the operator's mental and physical status, we can potentially prevent such abnormal movements to be executed by the UAV. Wearable, non-invasive sensors and UAV's inertial measurement unit (IMU) sensor data, can be used in real-time to provide a holistic contextual awareness of the UAV and the operator. Through the use of machine learning and classification algorithms, we can identify such unwanted commands, enabling the UAV to ignore them. To this end, this paper presents an analysis and evaluation of the performance of a variety of machine learning classifiers using data from the IMU which is integrated in the UAV, and operator's biomarker data, collected and constructed in a realistic environment with a stress-induction technique. For each classifier, we analyze its performance in terms of accuracy, processing time and energy consumption, since the aim is to be deployed directly on the UAV. Our analysis suggests that a range of classifiers can be used in these situations and we also critically discuss trade-offs between accuracy, processing time and energy consumption.

show abstract

An Energy Aware VLSI Framework for ECG Features Extraction for Wearable Devices in Healthcare

Kundra

2023

2023 7th International Conference on I-Smac (IoT in Social, Mobile, Analytics and Cloud) (I-Smac)

View full text Add to dashboard Cite

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

Cited by 3 publications

References 10 publications

A real‐world data collection framework for a fused dataset creation for joint human and remotely operated vehicle monitoring and anomalous command detection

A real‐world data collection framework for a fused dataset creation for joint human and remotely operated vehicle monitoring and anomalous command detection

An Analysis of Machine Learning Classifiers for Joint Operator-UAV Monitoring and Abnormal Command Detection

An Energy Aware VLSI Framework for ECG Features Extraction for Wearable Devices in Healthcare

Contact Info

Product

Resources

About