Automatic correction of annotation boundaries in activity datasets by class separation maximization

Kirkham, Reuben; Khan, Aftab; Bhattacharya, Sourav; Hammerla, Nils Y.; Mellor, Sebastian; Roggen, Daniel; Ploetz, Thomas

doi:10.1145/2494091.2495988

Cited by 16 publications

(6 citation statements)

References 8 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These labels are used for training a machine learning classifier [some issues related to ground truth annotation have been addressed in Ref. ( 48 , 60 ); automated vision-based annotation systems have also been explored in Ref. ( 59 , 61 )].…”

Section: Automated Movement Recognition For Clinical Movement Assessmmentioning

confidence: 99%

Movement Recognition Technology as a Method of Assessing Spontaneous General Movements in High Risk Infants

et al. 2015

Self Cite

View full text Add to dashboard Cite

Preterm birth is associated with increased risks of neurological and motor impairments such as cerebral palsy. The risks are highest in those born at the lowest gestations. Early identification of those most at risk is challenging meaning that a critical window of opportunity to improve outcomes through therapy-based interventions may be missed. Clinically, the assessment of spontaneous general movements is an important tool, which can be used for the prediction of movement impairments in high risk infants. Movement recognition aims to capture and analyze relevant limb movements through computerized approaches focusing on continuous, objective, and quantitative assessment. Different methods of recording and analyzing infant movements have recently been explored in high risk infants. These range from camera-based solutions to body-worn miniaturized movement sensors used to record continuous time-series data that represent the dynamics of limb movements. Various machine learning methods have been developed and applied to the analysis of the recorded movement data. This analysis has focused on the detection and classification of atypical spontaneous general movements. This article aims to identify recent translational studies using movement recognition technology as a method of assessing movement in high risk infants. The application of this technology within pediatric practice represents a growing area of inter-disciplinary collaboration, which may lead to a greater understanding of the development of the nervous system in infants at high risk of motor impairment.

show abstract

Section: Automated Movement Recognition For Clinical Movement Assessmmentioning

confidence: 99%

Movement Recognition Technology as a Method of Assessing Spontaneous General Movements in High Risk Infants

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…Users are assumed to only reflect their mood in the predetermined time intervals regardless of the tolerated delay; any potential mood change during the delay period should be accounted by users for the subsequent time interval. More advanced techniques such as [22] for automatic annotation correction can also be deployed at this stage.…”

Section: B Data Pre-processing and Feature Extractionmentioning

confidence: 99%

HealthyOffice: Mood recognition at work using smartphones and wearable sensors

Zenonos

Khan

Kalogridis

et al. 2016

2016 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops)

Self Cite

View full text Add to dashboard Cite

Abstract-Stress, anxiety and depression in the workplace are detrimental to human health and productivity with significant financial implications. Recent research in this area has focused on the use of sensor technologies, including smartphones and wearables embedded with physiological and movement sensors. In this work, we explore the possibility of using such devices for mood recognition, focusing on work environments. We propose a novel mood recognition framework that is able to identify five intensity levels for eight different types of moods every two hours. We further present a smartphone app ('HealthyOffice'), designed to facilitate self-reporting in a structured manner and provide our model with the ground truth. We evaluate our system in a small-scale user study where wearable sensing data is collected in an office environment. Our experiments exhibit promising results allowing us to reliably recognize various classes of perceived moods.

show abstract

“…For example, the temporal label uncertainty problem occurs when the time stamps associated with event labels are noisy or uncertain. The segmentation boundary uncertainty problem occurs when there is noise or uncertainty associated with the start and end time stamps of activity sessions [15, 9]. Approaches to these problems are not well matched to our setting as in our case the field labels provided by utox assessment are only available at a daily resolution.…”

Section: Related Workmentioning

confidence: 99%

Domain adaptation methods for improving lab-to-field generalization of cocaine detection using wearable ECG

Natarajan

Angarita

Gaiser

et al. 2016

Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing

View full text Add to dashboard Cite

Mobile health research on illicit drug use detection typically involves a two-stage study design where data to learn detectors is first collected in lab-based trials, followed by a deployment to subjects in a free-living environment to assess detector performance. While recent work has demonstrated the feasibility of wearable sensors for illicit drug use detection in the lab setting, several key problems can limit lab-to-field generalization performance. For example, lab-based data collection often has low ecological validity, the ground-truth event labels collected in the lab may not be available at the same level of temporal granularity in the field, and there can be significant variability between subjects. In this paper, we present domain adaptation methods for assessing and mitigating potential sources of performance loss in lab-to-field generalization and apply them to the problem of cocaine use detection from wearable electrocardiogram sensor data.

show abstract

Automatic correction of annotation boundaries in activity datasets by class separation maximization

Cited by 16 publications

References 8 publications

Movement Recognition Technology as a Method of Assessing Spontaneous General Movements in High Risk Infants

Movement Recognition Technology as a Method of Assessing Spontaneous General Movements in High Risk Infants

HealthyOffice: Mood recognition at work using smartphones and wearable sensors

Domain adaptation methods for improving lab-to-field generalization of cocaine detection using wearable ECG

Contact Info

Product

Resources

About