Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K)

Kumar, Santosh; Abowd, Gregory D.; Abraham, William T.; Al’Absi, Mustafa; Chau, Duen Horng; Ertin, Emre; Estrin, Deborah; Ganesan, Deepak; Hnat, Timothy W.; Hossain, Syed Monowar; Ives, Zachary G.; Kerr, Jacqueline; Marlin, Benjamin M.; Murphy, Susan L.; Rehg, James M.; Nahum‐Shani, Inbal; Shetty, Vivek; Sim, Ida; Spring, Bonnie; Srivastava, Mani; Dave, Wetter

doi:10.1109/mprv.2017.29

Cited by 22 publications

(24 citation statements)

References 2 publications

(2 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A marker of the maturing of this field is recent NIH investment into major collaborative initiatives such as the MD2K initiative [7], which supports the acceleration of translating motion sensor data into validated biomarkers of behavior. While the need for privacy and security around sensor data is well recognized, innovative solutions around secure data storage and transfer will be crucial to this approach gaining widespread acceptance and use [4].…”

Section: Referencesmentioning

confidence: 99%

“…), it is possible to elicit gait speed, gait patterns and spatial location. Using clinical correlation, we have established that these data can serve as markers of apathy, pacing, and disrupted circadian rhythms in patients with dementia [5].A marker of the maturing of this field is recent NIH investment into major collaborative initiatives such as the MD2K initiative [7], which supports the acceleration of translating motion sensor data into validated biomarkers of behavior. While the need for privacy and security around sensor data is well recognized, innovative solutions around secure data storage and transfer will be crucial to this approach gaining widespread acceptance and use [4].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Motion mapping in humans as a biomarker for psychiatric disorders

Vahia

Forester

2018

Neuropsychopharmacol

View full text Add to dashboard Cite

Publisher's note: Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. REFERENCES1. Christopoulos A, Changeux JP, Catterall WA, Fabbro D, Burris TP, Cidlowski JA, et al. International Union of Basic and Clinical Pharmacology. XC. Multisite pharmacology: recommendations for the nomenclature of receptor allosterism and allosteric ligands. Pharmacol Rev. 2014;66:918-47. 2. Huidobro-Toro JP, Valenzuela CF, Harris RA. Modulation of GABA A receptor function by G protein-coupled 5-HT 2C receptors. Neuropharmacology. 1996;35:1355-63. 3. Im WB, Chio CL, Alberts GL, Dinh DM. Positive-allosteric modulator of the human 5-HT 2C receptor. Mol Pharmacol. 2003;64:78-84. 4. Ding C, Bremer NM, Smith TD, Seitz PK, Anastasio NC, Cunningham KA, et al. Exploration of synthetic approaches and pharmacological evaluation of PNU-69176E and its stereoisomer as 5-HT 2C receptor allosteric modulators. ACS Chem Neurosci. 2012;3:538-45. 5. Wild CT, Miszkiel JM, Wold EA, Soto CA, Ding C, Hartley RM, et al. Design, synthesis, and characterization of 4-undecylpiperidine-2-carboxamides as positive-allosteric modulators of the serotonin (5-HT) 5-HT 2C receptor. J Med Chem. 2018 https://doi. org/10.1021/acs.jmedchem.8b00401 6. Garcia-Carceles J, Decara JM, Vazquez-Villa H, Rodriguez R, Codesido E, Cruces J, et al. A positive-allosteric modulator of the serotonin 5-HT 2C receptor for obesity. J Med Chem. 2017;60:9575-84.Measuring movement has been a cornerstone of studying behavior in animals in controlled studies. Movement data have served as a primary window into behavior, and by proxy, social function, mood, and cognition [1]. In humans, variations in locomotor activity have served as markers of a range of psychiatric syndromes including major depression, bipolar disorder, anxiety, catatonia, and substance use disorders [2]. Reports of sensor-based motion measurement in humans date back to the 1950s [2], and motion-based models of human psychopathology have been key to developing animal models of psychopathology [1]. A vast literature has documented how these animal models have facilitated development of motion-based signatures of antidepressant, anxiolytic, and other drug effects and guided drug development [3]. However, the limitations of technology thus far have meant that motion-mapping in humans has remained largely restricted to experimental settings.Phenotyping of naturalistic human behavior continues to depend on self-report or observer-report measures, with sampling often at intervals of hours to days. Newer technologies, supported by advances in wireless connectivity, more compact and reliable sensors and devices, and higher computing power can now sample movement at intervals of seconds, and can facilitate measurement of human motion in the natural living environment in ways previously not possible [4]. Such technologies are setting the stage for movement to become a major new phenotypic biomarker in neuropsychiatry.A wide array of validated technologies can quantify moti...

show abstract

Section: Referencesmentioning

confidence: 99%

mentioning

confidence: 99%

Motion mapping in humans as a biomarker for psychiatric disorders

Vahia

Forester

2018

Neuropsychopharmacol

View full text Add to dashboard Cite

show abstract

“…In this research, we investigated what types of visualizations can aid JITASI design, which is the first step towards realizing the vision of mHealth and Precision Medicine [16]. To support our goal, we evaluated the usability and usefulness of these visualizations with expert stress researchers.…”

Section: Conclusion Limitations and Future Directionsmentioning

confidence: 99%

Visualization of time-series sensor data to inform the design of just-in-time adaptive stress interventions

Sharmin

Raij

Epstien³

et al. 2015

Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing

Self Cite

View full text Add to dashboard Cite

We investigate needs, challenges, and opportunities in visualizing time-series sensor data on stress to inform the design of just-in-time adaptive interventions (JITAIs). We identify seven key challenges: massive volume and variety of data, complexity in identifying stressors, scalability of space, multifaceted relationship between stress and time, a need for representation at multiple granularities, interperson variability, and limited understanding of JITAI design requirements due to its novelty. We propose four new visualizations based on one million minutes of sensor data (n=70). We evaluate our visualizations with stress researchers (n=6) to gain first insights into its usability and usefulness in JITAI design. Our results indicate that spatio-temporal visualizations help identify and explain between-and within-person variability in stress patterns and contextual visualizations enable decisions regarding the timing, content, and modality of intervention. Interestingly, a granular representation is considered informative but noise-prone; an abstract representation is the preferred starting point for designing JITAIs.

show abstract

“…For example, respiration measurements are now routinely collected in field studies for smoking cessation [51] and stress regulation [26]. Conversation plays an important role in these and other health outcomes (e.g., depression) as well as in everyday work performance.…”

Section: Introductionmentioning

confidence: 99%

rConverse

Bari

Adams

Rahman

et al. 2018

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

Self Cite

View full text Add to dashboard Cite

Monitoring of in-person conversations has largely been done using acoustic sensors. In this paper, we propose a new method to detect moment-by-moment conversation episodes by analyzing breathing patterns captured by a mobile respiration sensor. Since breathing is affected by physical and cognitive activities, we develop a comprehensive method for cleaning, screening, and analyzing noisy respiration data captured in the field environment at individual breath cycle level. Using training data collected from a speech dynamics lab study with 12 participants, we show that our algorithm can identify each respiration cycle with 96.34% accuracy even in presence of walking. We present a Conditional Random Field, Context-Free Grammar (CRF-CFG) based conversation model, called rConverse, to classify respiration cycles into speech or non-speech, and subsequently infer conversation episodes. Our model achieves 82.7% accuracy for speech/non-speech classification and it identifies conversation episodes with 95.9% accuracy on lab data using a leave-one-subject-out cross-validation. Finally, the system is validated against audio ground-truth in a field study with 32 participants. rConverse identifies conversation episodes with 71.7% accuracy on 254 hours of field data. For comparison, the accuracy from a high-quality audio-recorder on the same data is 71.9%.

show abstract

Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K)

Cited by 22 publications

References 2 publications

Motion mapping in humans as a biomarker for psychiatric disorders

Motion mapping in humans as a biomarker for psychiatric disorders

Visualization of time-series sensor data to inform the design of just-in-time adaptive stress interventions

rConverse

Contact Info

Product

Resources

About