Seeking Optimum System Settings for Physical Activity Recognition on Smartwatches

Khan, Adil; Mazzara, Manuel; Distefano, Salvatore

doi:10.1007/978-3-030-17798-0_19

Cited by 7 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ese sensors support similar capabilities and applications of smartphones such as healthcare applications that require physical activity recognition (PAR). e accelerometer, linear accelerometer, magnetometer, and gyroscope sensors are ideal for PAR and gaitbased legitimate user identification over SPs [4][5][6][7]. is work will show that SWs are equally capable of performing PAR and gait-based legitimate user identification.…”

Section: Introductionmentioning

confidence: 94%

“…is technique permits the use of traditional machine learning classification approaches to handling the time series data. Our proposed study also utilizes the same sliding window approach employed in the prior work [2,[5][6][7]. e discussed windowing process initially partitions the time series raw signal into 30 seconds non-overlapping windows.…”

Section: Data Collectionmentioning

confidence: 99%

See 1 more Smart Citation

Smartwatch-Based Legitimate User Identification for Cloud-Based Secure Services

Alqarni

Khan

et al. 2018

Mobile Information Systems

Self Cite

View full text Add to dashboard Cite

Smartphones are ubiquitously integrated into our home and work environment and users frequently use them as the portal to cloud-based secure services. Since smartphones can easily be stolen or coopted, the advent of smartwatches provides an intriguing platform legitimate user identification for applications like online banking and many other cloud-based services. However, to access security-critical online services, it is highly desirable to accurately identifying the legitimate user accessing such services and data whether coming from the cloud or any other source. Such identification must be done in an automatic and non-bypassable way. For such applications, this work proposes a two-fold feasibility study; (1) activity recognition and (2) gait-based legitimate user identification based on individual activity. To achieve the above-said goals, the first aim of this work was to propose a semicontrolled environment system which overcomes the limitations of users’ age, gender, and smartwatch wearing style. The second aim of this work was to investigate the ambulatory activity performed by any user. Thus, this paper proposes a novel system for implicit and continuous legitimate user identification based on their behavioral characteristics by leveraging the sensors already ubiquitously built into smartwatches. The design system gives legitimate user identification using machine learning techniques and multiple sensory data with 98.68% accuracy.

show abstract

Section: Introductionmentioning

confidence: 94%

Section: Data Collectionmentioning

confidence: 99%

Smartwatch-Based Legitimate User Identification for Cloud-Based Secure Services

Alqarni

Khan

et al. 2018

Mobile Information Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…ARIMA model is a widely used timeseries forecasting model introduced by Box and Jenkins in 1970 [12]. ARIMA model is a general linear stochastic model which is the combination of autoregressive and movingaverage models [13][14][15]. An autoregressive model uses a linear combination of past values to predict the variable of interest.…”

Section: Arima Modelmentioning

confidence: 99%

Employing Deep Learning and Time Series Analysis to Tackle the Accuracy and Robustness of the Forecasting Problem

Tariq

Hanif

Sarwar

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

Crime is a bone of contention that can create a societal disturbance. Crime forecasting using time series is an efficient statistical tool for predicting rates of crime in many countries around the world. Crime data can be useful to determine the efficacy of crime prevention steps and the safety of cities and societies. However, it is a difficult task to predict the crime accurately because the number of crimes is increasing day by day. The objective of this study is to apply time series to predict the crime rate to facilitate practical crime prevention solutions. Machine learning can play an important role to better understand and analyze the future trend of violations. Different time-series forecasting models have been used to predict the crime. These forecasting models are trained to predict future violent crimes. The proposed approach outperforms other forecasting techniques for daily and monthly forecast.

show abstract

“…Wearable systems are particularly suitable to sport-specific needs (van der Kruk and Reijne, 2018 ), since: (1) sport usually takes place in uncontrolled and unstructured settings, with environmental conditions difficult to be predicted a priori (e.g., weather, interaction with equipment and other people) and many possible measurement interferences (e.g., electromagnetic noise); (2) the size of the acquisition volume inherently depends on the type of practiced sport (e.g., team vs. individual, indoor vs. outdoor); (3) sensors used to capture sports movements should be both robust and non-obtrusive for the athlete (i.e., ecologically transparent). Systems based on wearable devices, including low-cost activity trackers, smartwatches and smartphones (Ahmad et al, 2017 ), have kept evolving and are widely available for the consumer market, including clinical uses and sports applications (Ghazali et al, 2018 ; Hsu et al, 2018 ). Wearable technologies for motion analysis are predominantly inertial measurement units (IMUs) (Davila et al, 2017 ), which, thanks to their low cost and minimal obtrusiveness, represent an optimal solution for tracking and assessing sports movement on-field (Hsu et al, 2018 ; van der Kruk and Reijne, 2018 ; Adesida et al, 2019 ).…”

Section: Introductionmentioning

confidence: 99%

Supervised Machine Learning Applied to Wearable Sensor Data Can Accurately Classify Functional Fitness Exercises Within a Continuous Workout

Preatoni

Nodari

Lopomo

2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Observing, classifying and assessing human movements is important in many applied fields, including human-computer interface, clinical assessment, activity monitoring and sports performance. The redundancy of options in planning and implementing motor programmes, the inter-and intra-individual variability in movement execution, and the time-continuous, high-dimensional nature of motion data make segmenting sequential movements into a smaller set of discrete classes of actions non-trivial. We aimed to develop and validate a method for the automatic classification of four popular functional fitness drills, which are commonly performed in current circuit training routines. Five inertial measurement units were located on the upper and lower limb, and on the trunk of fourteen participants. Positions were chosen by keeping into account the dynamics of the movement and the positions where commercially-available smart technologies are typically secured. Accelerations and angular velocities were acquired continuously from the units and used to train and test different supervised learning models, including k-Nearest Neighbors (kNN) and support-vector machine (SVM) algorithms. The use of different kernel functions, as well as different strategies to segment continuous inertial data were explored. Classification performance was assessed from both the training dataset (k-fold cross-validation), and a test dataset (leave-one-subject-out validation). Classification from different subsets of the measurement units was also evaluated (1-sensor and 2-sensor data). SVM with a cubic kernel and fed with data from 600 ms windows with a 10% overlap gave the best classification performances, yielding to an overall accuracy of 97.8%. This approach did not misclassify any functional fitness movement for another, but confused relatively frequently (2.8-18.9%) a fitness movement phase with the transition between subsequent repetitions of the same task or different drills. Among 1-sensor configurations, the upper arm achieved the best classification performance (96.4% accuracy), whereas combining the upper arm and the thigh sensors obtained the highest level of accuracy (97.6%) from 2-sensors movement tracking. Preatoni et al. Gesture Classification in Functional Training We found that supervised learning can successfully classify complex sequential movements such as those of functional fitness workouts. Our approach, which could exploit technologies currently available in the consumer market, demonstrated exciting potential for future on-field applications including unstructured training.

show abstract

Seeking Optimum System Settings for Physical Activity Recognition on Smartwatches

Cited by 7 publications

References 29 publications

Smartwatch-Based Legitimate User Identification for Cloud-Based Secure Services

Smartwatch-Based Legitimate User Identification for Cloud-Based Secure Services

Employing Deep Learning and Time Series Analysis to Tackle the Accuracy and Robustness of the Forecasting Problem

Supervised Machine Learning Applied to Wearable Sensor Data Can Accurately Classify Functional Fitness Exercises Within a Continuous Workout

Contact Info

Product

Resources

About