Wearable Social Sensing: Content-Based Processing Methodology and Implementation

Gu, Juping; Gao, Bin; Chen, Yuanpeng; Long, Jiang; Gao, Zhao; Ma, Xiaole; Ma, Yukun; Woo, Wai Lok; Jin, Juan

doi:10.1109/jsen.2017.2754289

Cited by 26 publications

(14 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different social models have developed to classify mental states of individuals. Gu et al [ 28 ] developed a wearable device equipped with a microphone capable of automatically identifying and analyzing paralinguistic features (e.g., Brightness_sp and MFCC5_sp) contained in the human voice during social interactions. These features were used to train the K-Means algorithm to classify the participants’ anxiety level, which obtained an accuracy of 72.73%.…”

Section: Related Workmentioning

confidence: 99%

Recognizing Context-Aware Human Sociability Patterns Using Pervasive Monitoring for Supporting Mental Health Professionals

Moura

Teles

Endler

et al. 2020

Sensors

View full text Add to dashboard Cite

Traditionally, mental health specialists monitor their patients’ social behavior by applying subjective self-report questionnaires in face-to-face meetings. Usually, the application of the self-report questionnaire is limited by cognitive biases (e.g., memory bias and social desirability). As an alternative, we present a solution to detect context-aware sociability patterns and behavioral changes based on social situations inferred from ubiquitous device data. This solution does not focus on the diagnosis of mental states, but works on identifying situations of interest to specialized professionals. The proposed solution consists of an algorithm based on frequent pattern mining and complex event processing to detect periods of the day in which the individual usually socializes. Social routine recognition is performed under different context conditions to differentiate abnormal social behaviors from the variation of usual social habits. The proposed solution also can detect abnormal behavior and routine changes. This solution uses fuzzy logic to model the knowledge of the mental health specialist necessary to identify the occurrence of behavioral change. Evaluation results show that the prediction performance of the identified context-aware sociability patterns has strong positive relation (Pearson’s correlation coefficient >70%) with individuals’ social routine. Finally, the evaluation conducted recognized that the proposed solution leading to the identification of abnormal social behaviors and social routine changes consistently.

show abstract

Section: Related Workmentioning

confidence: 99%

Recognizing Context-Aware Human Sociability Patterns Using Pervasive Monitoring for Supporting Mental Health Professionals

Moura

Teles

Endler

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The wearable device consists of an ARM-Cortex4 microcontroller with DSP function for audio feature calculation, a variety of digital sensors for collecting multi-modal data from the environment, physiological signals and behavioral activity. In addition, specific components [5] consist of a microSD card for long-term data storage, a power management unit with a 2200mAh lithium battery, OLED screen, a debug port for download and debug firmware program and a USB port. The block diagram of the wearable platform is shown in Figure 1.…”

Section: A Wearable Social-mental-health Sensing Platformmentioning

confidence: 99%

“…In order to protect personal privacy, the wearable device extracts social related audio features and deletes raw data automatically. We embed four social-related audio features into the wearable hardware platform: Energy, Entropy, Brightness [5] and Formant [12]. We use ADC (analog digital converter) sampling and filtering for the digital signal of the audio code unit WM8978.…”

Section: A Wearable Social-mental-health Sensing Platformmentioning

confidence: 99%

“…Wrist skin temperature and humidity sensing are used for body data analysis. Several features of multi-modal sensing data are calculated, namely mean, standard deviation, short-time energy, energy-entropy, correlation coefficient between axis, pitch, roll and peak value in the frequency domain [5]. In this paper, we have calculated eight features in the time domain and ten features in the frequency domain, such as Mean, STD, Mode, skewness of a FFT window shape, kurtosis of amplitude about a FFT window and so on.…”

Section: Multi-modal Sensing and Feature Extractionmentioning

confidence: 99%

“…In order to obtain objective assessment, there has been increasing interest in the interrelationships of Affective Computing (AC) [1], Social Signal Processing (SSP) [2] and Physical Mental Health (PMH) [3]. These subjects have attracted researchers from various fields such as psychology, healthcare, ambient intelligence and computer science [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations