Detecting Walking in Synchrony Through Smartphone Accelerometer and Wi-Fi Traces

Garcia-Ceja, Enrique; Osmani, Venet; Maxhuni, Alban; Mayora, Oscar

doi:10.1007/978-3-319-14112-1_3

Cited by 5 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a more advanced research, Kjaergaard et al [7] used sensor fusion techniques of accelerometer, magnetometer and WiFi sensors to recognize pedestrian flocks using smartphone devices with an accuracy of up to 87 percent. Finally, Garcia-Ceja et al [5] have used low-frequency accelerometer (5Hz) and WiFi data to detect when two individual are walking at the same time.…”

Section: Related Workmentioning

confidence: 99%

Walking in Sync

Katevas

Haddadi

Tokarchuk

et al. 2015

Proceedings of the 2nd Workshop on Workshop on Physical Analytics

View full text Add to dashboard Cite

Eventual gait synchronization between two individuals while walking and talking with each other has been shown to be an indicator of agreeableness and companionship. The inferred physical signal from this subconscious phenomenon can potentially be an indicator of cooperation or relation between two individuals. In this paper we investigate this effect, and whether having a third person actively engaging in the same act or conversation can reduce this synchronization level. Using high frequency accelerometer data from a dedicated smartphone app, we perform a number of controlled experiments on a number of individuals in different group configuration. Our results bring an interesting insight: it is the non-verbal social signals such as the gaze, head orientation and gestures that is the key factor in synchronization, not necessarily the number or configuration of the walkers. These early results can lead us on detecting relationships between individuals or detecting the group formation and numbers for crowd-sensing applications when only partial data is available.

show abstract

Section: Related Workmentioning

confidence: 99%

Walking in Sync

Katevas

Haddadi

Tokarchuk

et al. 2015

Proceedings of the 2nd Workshop on Workshop on Physical Analytics

View full text Add to dashboard Cite

show abstract

“…Such sensors are increasingly embedded in many wearable devices such as smartphones, smart-watches, fitness bracelets, actigraphy devices and so on. These sensors have been used to monitor physical activities [14], sport activities [16], mental health [10], social interactions [8], to name a few. Recently, the use of inertial units has been explored for user identification and user authentication applications [1,15].…”

Section: Introductionmentioning

confidence: 99%

User Recognition Based on Daily Actigraphy Patterns

Garcia-Ceja

Morin

2019

IFIP Advances in Information and Communication Technology

Self Cite

View full text Add to dashboard Cite

The use of inertial sensors such as accelerometers and gyroscopes, which are now often embedded in many wearable devices, has gained attention for their applicability in user authentication applications as an alternative to PINs, passwords, biometric signatures, etc. Previous works have shown that it is possible to authenticate users based on fine-grained kinematic behavior profiles like gait, hand gestures and physical activities. In this work we explore the use of actigraphy data for user recognition based on daily patterns as opposed to fine-grained motion. One of the advantages of the former, is that it does not require to perform specific movements, thus, easing the training and calibration stages. In this work we extracted daily patterns from an actigraphy device and used a random forest classifier and a majority voting approach to perform the user classification. We used a public available dataset collected by 55 participants and we achived a true positive rate of 0.64, a true negative rate of 0.99 and a balanced accuracy of 0.81.

show abstract

“…In literature, several technological approaches have been proposed to recognize human activities [ 1 , 2 , 3 , 4 ]. These activities can be divided into two types: simple activities (i.e., walking, running, climbing stairs, moving arms) and complex (or long-term) activities (which include several simple activities—for example, cooking—that could be comprised of walking and moving one’s arms [ 5 , 6 ]). Most of the approaches that have been proposed are characterized by sensors involved that must be carried by subjects (accelerometers, microphones, gyroscopes, biosensors, plantar pressure sensors, Radio Frequency Identification (RFID) tags, among others [ 7 , 8 , 9 , 10 , 11 ]), as well as devices embedded in their environment such as camcorders [ 12 , 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

A Similarity Analysis of Audio Signal to Develop a Human Activity Recognition Using Similarity Networks

García-Hernández

Galván-Tejada

et al. 2017

Sensors

View full text Add to dashboard Cite

Human Activity Recognition (HAR) is one of the main subjects of study in the areas of computer vision and machine learning due to the great benefits that can be achieved. Examples of the study areas are: health prevention, security and surveillance, automotive research, and many others. The proposed approaches are carried out using machine learning techniques and present good results. However, it is difficult to observe how the descriptors of human activities are grouped. In order to obtain a better understanding of the the behavior of descriptors, it is important to improve the abilities to recognize the human activities. This paper proposes a novel approach for the HAR based on acoustic data and similarity networks. In this approach, we were able to characterize the sound of the activities and identify those activities looking for similarity in the sound pattern. We evaluated the similarity of the sounds considering mainly two features: the sound location and the materials that were used. As a result, the materials are a good reference classifying the human activities compared with the location.

show abstract

Detecting Walking in Synchrony Through Smartphone Accelerometer and Wi-Fi Traces

Cited by 5 publications

References 31 publications

Walking in Sync

Walking in Sync

User Recognition Based on Daily Actigraphy Patterns

A Similarity Analysis of Audio Signal to Develop a Human Activity Recognition Using Similarity Networks

Contact Info

Product

Resources

About