Human Action Recognition Using Smartphone Sensors

Saha, Ashim; Sharma, Teenu; Batra, Harshika; Jain, Anupreksha; Pal, Vabna

doi:10.1109/compe49325.2020.9200169

Cited by 11 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tri-axial accelerometry was measured using a smartphone (OPPO A92, Guangdong Oppo Mobile Telecommunications Corp., Ltd., Dongguan, China). The Physics Toolbox Sensor Suite application (version 2022.09.11), found on the Google Android platform, was used to collect and export the acceleration data at a sampling rate of 200 Hz generated by the smartphone accelerometer [32]. The center of the smartphone was horizontally placed on the lumbar region (L5) using a waist-mounted pouch close to the body's COM [25,28].…”

Section: Equipmentmentioning

confidence: 99%

Leg Dominance—Surface Stability Interaction: Effects on Postural Control Assessed by Smartphone-Based Accelerometry

Promsri

Bangkomdet

Jindatham

et al. 2023

Sports

View full text Add to dashboard Cite

The preferential use of one leg over another in performing lower-limb motor tasks (i.e., leg dominance) is considered to be one of the internal risk factors for sports-related lower-limb injuries. The current study aimed to investigate the effects of leg dominance on postural control during unipedal balancing on three different support surfaces with increasing levels of instability: a firm surface, a foam pad, and a multiaxial balance board. In addition, the interaction effect between leg dominance and surface stability was also tested. To this end, a tri-axial accelerometer-based smartphone sensor was placed over the lumbar spine (L5) of 22 young adults (21.5 ± 0.6 years) to record postural accelerations. Sample entropy (SampEn) was applied to acceleration data as a measure of postural sway regularity (i.e., postural control complexity). The results show that leg dominance (p < 0.001) and interaction (p < 0.001) effects emerge in all acceleration directions. Specifically, balancing on the dominant (kicking) leg shows more irregular postural acceleration fluctuations (high SampEn), reflecting a higher postural control efficiency or automaticity than balancing on the non-dominant leg. However, the interaction effects suggest that unipedal balancing training on unstable surfaces is recommended to reduce interlimb differences in neuromuscular control for injury prevention and rehabilitation.

show abstract

Section: Equipmentmentioning

confidence: 99%

Leg Dominance—Surface Stability Interaction: Effects on Postural Control Assessed by Smartphone-Based Accelerometry

Promsri

Bangkomdet

Jindatham

et al. 2023

Sports

View full text Add to dashboard Cite

show abstract

“…The smartphone was securely positioned using a waist-mounted pouch in the lumbar region (L5), which was close to the body’s center of mass [ 30 , 31 ]. The accelerometer functioned using the Physics Toolbox Sensor Suite application (version 2023.01.07) on the Google Android platform [ 32 , 33 ], enabling the collection and export of acceleration data at a sampling rate of 200 Hz. All participants wore their running shoes for all study runs.…”

Section: Methodsmentioning

confidence: 99%

Effects of Different Wearable Resistance Placements on Running Stability

Promsri,

Deedphimai,

Promthep

et al. 2024

Sports

View full text Add to dashboard Cite

Stability during running has been recognized as a crucial factor contributing to running performance. This study aimed to investigate the effects of wearable equipment containing external loads on different body parts on running stability. Fifteen recreational male runners (20.27 ± 1.23 years, age range 19–22 years) participated in five treadmill running conditions, including running without loads and running with loads equivalent to 10% of individual body weight placed on four different body positions: forearms, lower legs, trunk, and a combination of all three (forearms, lower legs, and trunk). A tri-axial accelerometer-based smartphone sensor was attached to the participants’ lumbar spine (L5) to record body accelerations. The largest Lyapunov exponent (LyE) was applied to individual acceleration data as a measure of local dynamic stability, where higher LyE values suggest lower stability. The effects of load distribution appear in the mediolateral (ML) direction. Specifically, running with loads on the lower legs resulted in a lower LyE_ML value compared to running without loads (p = 0.001) and running with loads on the forearms (p < 0.001), trunk (p = 0.001), and combined segments (p = 0.005). These findings suggest that running with loads on the lower legs enhances side-to-side local dynamic stability, providing valuable insights for training.

show abstract

“…In addition, ML algorithms can recognize patterns in data as well as learn from them to make their predictions. ML methods were utilized for a while for addressing the HAR problem, such as K-Nearest Neighbors [22], random forest (RF) [23], Naive Bayes [24,25], and SVM [26,27]. ML models and algorithms learn via experience.…”

Section: Machine Learning (Ml)mentioning

confidence: 99%

Human Activity Recognition Using Inertial Sensors in a Smartphone: Technical Background(Review)

Khalaf,

Riyadh

2024

ANJS

View full text Add to dashboard Cite

Human Activity Recognition (HAR) stands at the intersection of machine learning, deep learning, and sensor technology, primarily focusing on leveraging inertial sensors in smartphones and wearable devices. This paper presents a comprehensive technical overview of HAR, examining the amalgamation of machine learning and deep learning systems while considering the data inputs from mobile and wearable inertial sensors. The review encompasses a broad spectrum of methodologies applied to HAR, ranging from classical machine learning algorithms to cutting-edge deep learning architectures. Emphasis is placed on the nuanced challenges and opportunities posed using inertial sensors in smartphones and wearables. This includes discussions on data preprocessing strategies, feature extraction methods, and model architectures, accounting for the unique characteristics of sensor data, such as noise, variability, and power consumption. The paper explores recent advancements, scrutinizing state-of-the-art approaches, innovative model architectures, and emerging trends in HAR. Through a comparative evaluation of various machine learning and deep learning techniques, the review aims to guide researchers and practitioners in selecting the most appropriate methods for HAR applications across diverse scenarios. In conclusion, this paper serves as an inclusive guide to the technical landscape of HAR, incorporating insights from both mobile and wearable inertial sensors. By synthesizing existing knowledge and addressing future research directions, it aims to propel advancements in developing robust and efficient systems for recognizing human activities, accommodating the evolving landscape of sensor technologies in mobile and wearable devices.

show abstract

Human Action Recognition Using Smartphone Sensors

Cited by 11 publications

References 17 publications

Leg Dominance—Surface Stability Interaction: Effects on Postural Control Assessed by Smartphone-Based Accelerometry

Leg Dominance—Surface Stability Interaction: Effects on Postural Control Assessed by Smartphone-Based Accelerometry

Effects of Different Wearable Resistance Placements on Running Stability

Human Activity Recognition Using Inertial Sensors in a Smartphone: Technical Background(Review)

Contact Info

Product

Resources

About