Recognizing Subtle User Activities and Person Identity with Cheap Resistive Pressure Sensing Carpet

Cheng, Jingyuan; Sundholm, Mathias; Zhou, Bo; Kreil, Matthias; Lukowicz, Paul

doi:10.1109/ie.2014.29

Cited by 13 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Likewise, authors in Ref. [43] used floor-embedded sensors to identify the subjects. Not only this approach appears to be cumbersome unlike VID which is dependent upon depth camera that can easily be embedded in smart devices such as smart TV or refrigerator, it is only evaluated of 11 subjects and has an accuracy of around 88% (unlike VID whose accuracy is around 99% for much bigger enrolled set -i.e.…”

Section: Comparison With Other Human Identification Approachesmentioning

confidence: 99%

VID: Human identification through vein patterns captured from commodity depth cameras

et al. 2021

View full text Add to dashboard Cite

Herein, a human identification system for smart spaces called Vein-ID (referred to as VID) is presented, which leverage the uniqueness of vein patterns embedded in dorsum of an individual's hand. VID extracts vein patterns using the depth information and infrared (IR) images, both obtained from a commodity depth camera. Two deep learning models (CNN and Stacked-Autoencoders) are presented for precisely identifying a target individual from a set of N enrolled users. VID also incorporates a strategy for identifying an intruder-that is a person whose vein patterns are not included in the set of enrolled individuals. The performance of VID by collecting a comprehensive data set of approximately 17,500 images from 35 subjects is evaluated. The tests reveal that VID can identify an individual with an average accuracy of over 99% from a group of up to 35 individuals. It is demonstrated that VID can detect intruders with an average accuracy of about 96%. The execution time for training and testing the two deep learning models on different hardware platforms is also investigated and the differences are reported. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Comparison With Other Human Identification Approachesmentioning

confidence: 99%

VID: Human identification through vein patterns captured from commodity depth cameras

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Activity recognition using technology is not a new topic for researchers [41], and amongst recent literature, more common methods used in this endeavour have ranged from mobile devices, such as smartphones and wearables, [42][43][44][45][46][47] as well as more unique methods such as the analysis of eye movement [48]. However, fixed implementations such as those that are surface based or use cameras [43,[49][50][51][52] 4 literature, especially when analysing whole body or limb movement to recognise activity. Additionally, there are few solutions that embrace the principles of the IoT to allow the smart floor to potentially interact with other objects.…”

Section: Background and Related Workmentioning

confidence: 99%

Activity recognition evaluation via machine learning

Rameka¹,

Connor²,

Kruse³

2019

ICST Transactions on Ambient Systems

View full text Add to dashboard Cite

With the proliferation of relatively cheap Internet of Things (IoT) devices, smart environments have been highlighted as an example of how the IoT can make our lives easier. Each of these 'things' produces data which can work in unison to react to its users. Machine learning makes use of this data to make inferences about our habits and activities, such as our buying preferences or likely commute destinations. However, this level of human inclusion within the IoT relies on indirect inferences from the usage of these devices or services. Activity recognition is already a widely researched area and could provide a more direct way of including humans within this system. This research explores the feasibility of using a cost effective, unobtrusive, single modality ground-based sensor matrix to track subtle pressure changes to predict user activity, in an effort to assess its ability to act as an intermediary interface between humans and digital systems such as the IoT.

show abstract

“…In the context of smart home applications, pressure sensing mats are an important type of sensor [5][6][7]. Pressure mats are used for elderly care [5][6][7], health monitoring [7,8], security [8,9], daily activity monitoring [5,[9][10][11][12][13][14], analyzing walking gait in ASD children [15], and recognizing sleep postures to optimize sleep positions for improved sleep quality and overall health [16].…”

Section: Introductionmentioning

confidence: 99%

Enhanced Noise-Resilient Pressure Mat System Based on Hyperdimensional Computing

Asgarinejad,

Yu,

Jiang

et al. 2024

Sensors

View full text Add to dashboard Cite

Traditional systems for indoor pressure sensing and human activity recognition (HAR) rely on costly, high-resolution mats and computationally intensive neural network-based (NN-based) models that are prone to noise. In contrast, we design a cost-effective and noise-resilient pressure mat system for HAR, leveraging Velostat for intelligent pressure sensing and a novel hyperdimensional computing (HDC) classifier that is lightweight and highly noise resilient. To measure the performance of our system, we collected two datasets, capturing the static and continuous nature of human movements. Our HDC-based classification algorithm shows an accuracy of 93.19%, improving the accuracy by 9.47% over state-of-the-art CNNs, along with an 85% reduction in energy consumption. We propose a new HDC noise-resilient algorithm and analyze the performance of our proposed method in the presence of three different kinds of noise, including memory and communication, input, and sensor noise. Our system is more resilient across all three noise types. Specifically, in the presence of Gaussian noise, we achieve an accuracy of 92.15% (97.51% for static data), representing a 13.19% (8.77%) improvement compared to state-of-the-art CNNs.

show abstract

Recognizing Subtle User Activities and Person Identity with Cheap Resistive Pressure Sensing Carpet

Cited by 13 publications

References 23 publications

VID: Human identification through vein patterns captured from commodity depth cameras

VID: Human identification through vein patterns captured from commodity depth cameras

Activity recognition evaluation via machine learning

Enhanced Noise-Resilient Pressure Mat System Based on Hyperdimensional Computing

Contact Info

Product

Resources

About