Activity Segmentation and Identification based on Eye Gaze Features

Amrouche, Sabrina; Gollan, Benedikt; Ferscha, Alois; Heftberger, Josef

doi:10.1145/3197768.3197775

Cited by 6 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So far, for example, it has been demonstrated that the temporal demand (changing the task load by changing the speed of the stimulation) leads to a spreaded out distribution of fixations, whereas the visuospatial demand (changing the task load by increasing the visuospatial request) lead to a clustered distribution of fixations. Many laboratory and simulation studies have been conducted by the team who introduced this approach (Di Nocera, Camilli, Nacchia, Terenzi & Di Nocera, 2008; Gollan, Ferscha & Heftberger, 2018;Coyne, Sibley, Sherwood, Foroughi, Olson & Vorm, 2017;Davies, Vigo, Harper & Jay, 2016;Latorella & Harden, 2015;Moacdieh & Sarter, 2015;Moacdieh & Sarter, 2017;Wolf, Martinez, Roitberg, Stiefelhagen & Deml, 2018). Until now, no studies were run for testing the technique in the real world.…”

Section: Discussionmentioning

confidence: 99%

Scanpath analysis into the wild: the spatiotemporal distribution of fixations as an indicator of driver’s mental workload

Nocera¹,

Ricciardi

Mastrangelo³

et al. 2020

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

Past studies using the distribution of eye fixations as an indicator of mental workload are limited to simulations and laboratory tasks. Hence, this assessment strategy has not yet been proven useful in real- world settings. In order to bridge this gap, in this study eye movements of a group of individuals were recorded while driving a car in a suburban road. Drivers’ scanpaths during driving and during driving while performing mundane secondary tasks were compared in this study. A more grouped pattern of fixations was expected in the dual-task condition than in the driving-only condition. As expected, results showed the effectiveness the spatiotemporal distribution of fixations in correctly discriminating between task load conditions, therefore indicating its usefulness for assessing mental workload also in complex real-world tasks.

show abstract

Section: Discussionmentioning

confidence: 99%

Scanpath analysis into the wild: the spatiotemporal distribution of fixations as an indicator of driver’s mental workload

Nocera¹,

Ricciardi

Mastrangelo³

et al. 2020

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

show abstract

“…Amrouche et al [31] proposed a application-independent approach toward the segmentation of task executions in a semi-manual industrial assembly setup by exploiting the expressive features of the distribution-based gaze feature Nearest Neighbor Index (NNI) to build a Dynamic Activity Segmentation Algorithm (DASA). The proposed approach is enriched with a ML model acting as a feedback loop to classify segment qualities.…”

Section: Figure 2: Life Cycle Of Contexts In Iotmentioning

confidence: 99%

IoT-Based Patient Health Data Using Improved Context-Aware Data Fusion and Enhanced Recursive Feature Elimination Model

Saranya

Fatima

2022

IEEE Access

View full text Add to dashboard Cite

The Internet of Things (IoT) in the healthcare market is propelled forward by the implementation of digital systems for monitoring and analysing health problems. IoT and smart devices can contribute to a highly smart environment. Smart medical devices interconnected with smartphone apps can collect medical and other required health data. "Data Fusion (DF)" refers to integrating data and knowledge from multiple sources. However, these techniques are also applied to other domains, including text processing. Using data from multiple distributed sources, the objective of DF in multisensory contexts is to reduce the chance of detection errors and increase their reliability. The objective is to increase scalability, performance efficiency, and identification. A medical device's ability to scale up or down demonstrates its capacity to respond to environmental factors. A more scalable system performs as expected, with no interruptions, and makes the best available use of the resource management it has. To ensure that these tracking devices all work the same way, it is essential to form a specialised group to develop uniformity in areas such as communication channels, aggregation of data, and smart interfaces. The main contribution of this research is pre-processing, DF using the Improved Context-aware Data Fusion (ICDF) algorithm, feature extraction via Improved Principal Component Analysis (IPCA), feature selection through the Enhanced Recursive Feature Elimination (ERFE) algorithm, and a classifier using an ensemble-based Machine Learning (ML) model. The Improved Dynamic Bayesian Network (IDBN) is a good trade-off for tractability, becoming a tool for ICDF operations. The simulation results show that the proposed ICDF model achieves higher performance in terms of 97% accuracy, 96% precision, 97% recall, and 97% F1 score in the healthcare system.

show abstract

Towards Industrial Assistance Systems: Experiences of Applying Multi-sensor Fusion in Harsh Environments

Haslgrübler

Gollan

Ferscha

2019

Physiological Computing Systems

View full text Add to dashboard Cite

Activity Segmentation and Identification based on Eye Gaze Features

Cited by 6 publications

References 16 publications

Scanpath analysis into the wild: the spatiotemporal distribution of fixations as an indicator of driver’s mental workload

Scanpath analysis into the wild: the spatiotemporal distribution of fixations as an indicator of driver’s mental workload

IoT-Based Patient Health Data Using Improved Context-Aware Data Fusion and Enhanced Recursive Feature Elimination Model

Towards Industrial Assistance Systems: Experiences of Applying Multi-sensor Fusion in Harsh Environments

Contact Info

Product

Resources

About