An official website of the United States government
Bipolar Disorder is a chronic psychiatric illness characterized by pathological mood swings associated with severe disruptions in emotion regulation. Clinical monitoring of mood is key to the care of these dynamic and incapacitating mood states. Frequent and detailed monitoring improves clinical sensitivity to detect mood state changes, but typically requires costly and limited resources. Speech characteristics change during both depressed and manic states, suggesting automatic methods applied to the speech signal can be effectively used to monitor mood state changes. However, speech is modulated by many factors, which renders mood state prediction challenging. We hypothesize that emotion can be used as an intermediary step to improve mood state prediction. This paper presents critical steps in developing this pipeline, including (1) a new in the wild emotion dataset, the PRIORI Emotion Dataset, collected from everyday smartphone conversational speech recordings, (2) activation/valence emotion recognition baselines on this dataset (PCC of 0.71 and 0.41, respectively), and (3) significant correlation between predicted emotion and mood state for individuals with bipolar disorder. This provides evidence and a working baseline for the use of emotion as a meta-feature for mood state monitoring.
more »
« less
HADD: High-Accuracy Detection of Depressed Mood
Depression is a serious mood disorder that is under-recognized and under-treated. Recent advances in mobile/wearable technology and ML (machine learning) have provided opportunities to detect the depressed moods of participants in their daily lives with their consent. To support high-accuracy, ubiquitous detection of depressed mood, we propose HADD, which provides new capabilities. First, HADD supports multimodal data analysis in order to enhance the accuracy of ubiquitous depressed mood detection by analyzing not only objective sensor data, but also subjective EMA (ecological momentary assessment) data collected by using mobile devices. In addition, HADD improves upon the accuracy of state-of-the-art ML algorithms for depressed mood detection via effective feature selection, data augmentation, and two-stage outlier detection. In our evaluation, HADD significantly enhanced the accuracy of a comprehensive set of ML models for depressed mood detection.
more »
« less
- Award ID(s):
- 2007854
- PAR ID:
- 10435823
- Date Published:
- Journal Name:
- Technologies
- Volume:
- 10
- Issue:
- 6
- ISSN:
- 2227-7080
- Page Range / eLocation ID:
- 123
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We built and compared several machine learning models to predict future self-reported wellbeing labels (of mood, health, and stress) for next day and for up to 7 days in the future, using multi-modal data. The data are from surveys, wearables, mobile phones and weather information collected in a study from college students, each providing daily data for 30 or 90 days. We compared the performance of multiple models, including personalized multi-task models and deep learning models. The best personalized multi-task linear model showed mean absolute errors of 12.8, 11.9, and 13.7 on a continuous-100 pt scale for estimating next days mood, health, and stress value, while the best multi-task neural network model, applied to 3-way high/med/low classification of the wellbeing values showed F1 scores of 0.71, 0.74, and 0.66 on mood, health, and stress metrics, respectively. We found that features related to weather, and morning academic activities are strongly associated with wellbeing labels. We further found greater prediction accuracy among participants with the least fluctuations in their wellbeing labels.more » « less
-
Background Supporting mental health and wellness is of increasing interest due to a growing recognition of the prevalence and burden of mental health issues. Mood is a central aspect of mental health, and several technologies, especially mobile apps, have helped people track and understand it. However, despite formative work on and dissemination of mood-tracking apps, it is not well understood how mood-tracking apps used in real-world contexts might benefit people and what people hope to gain from them. Objective To address this gap, the purpose of this study was to understand motivations for and experiences in using mood-tracking apps from people who used them in real-world contexts. Methods We interviewed 22 participants who had used mood-tracking apps using a semistructured interview and card sorting task. The interview focused on their experiences using a mood-tracking app. We then conducted a card sorting task using screenshots of various data entry and data review features from mood-tracking apps. We used thematic analysis to identify themes around why people use mood-tracking apps, what they found useful about them, and where people felt these apps fell short. Results Users of mood-tracking apps were primarily motivated by negative life events or shifts in their own mental health that prompted them to engage in tracking and improve their situation. In general, participants felt that using a mood-tracking app facilitated self-awareness and helped them to look back on a previous emotion or mood experience to understand what was happening. Interestingly, some users reported less inclination to document their negative mood states and preferred to document their positive moods. There was a range of preferences for personalization and simplicity of tracking. Overall, users also liked features in which their previous tracked emotions and moods were visualized in figures or calendar form to understand trends. One gap in available mood-tracking apps was the lack of app-facilitated recommendations or suggestions for how to interpret their own data or improve their mood. Conclusions Although people find various features of mood-tracking apps helpful, the way people use mood-tracking apps, such as avoiding entering negative moods, tracking infrequently, or wanting support to understand or change their moods, demonstrate opportunities for improvement. Understanding why and how people are using current technologies can provide insights to guide future designs and implementations.more » « less
-
Machine learning model and strategy for fast and accurate detection of leaks in water supply networkAbstract The water supply network (WSN) is subjected to leaks that compromise its service to the communities, which, however, is challenging to identify with conventional approaches before the consequences surface. This study developed Machine Learning (ML) models to detect leaks in the WDN. Water pressure data under leaking versus non-leaking conditions were generated with holistic WSN simulation code EPANET considering factors such as the fluctuating user demands, data noise, and the extent of leaks, etc. The results indicate that Artificial Neural Network (ANN), a supervised ML model, can accurately classify leaking versus non-leaking conditions; it, however, requires balanced dataset under both leaking and non-leaking conditions, which is difficult for a real WSN that mostly operate under normal service condition. Autoencoder neural network (AE), an unsupervised ML model, is further developed to detect leak with unbalanced data. The results show AE ML model achieved high accuracy when leaks occur in pipes inside the sensor monitoring area, while the accuracy is compromised otherwise. This observation will provide guidelines to deploy monitoring sensors to cover the desired monitoring area. A novel strategy is proposed based on multiple independent detection attempts to further increase the reliability of leak detection by the AE and is found to significantly reduce the probability of false alarm. The trained AE model and leak detection strategy is further tested on a testbed WSN and achieved promising results. The ML model and leak detection strategy can be readily deployed for in-service WSNs using data obtained with internet-of-things (IoTs) technologies such as smart meters.more » « less
-
Indoor localization plays a vital role in applications such as emergency response, warehouse management, and augmented reality experiences. By deploying machine learning (ML) based indoor localization frameworks on their mobile devices, users can localize themselves in a variety of indoor and subterranean environments. However, achieving accurate indoor localization can be challenging due to heterogeneity in the hardware and software stacks of mobile devices, which can result in inconsistent and inaccurate location estimates. Traditional ML models also heavily rely on initial training data, making them vulnerable to degradation in performance with dynamic changes across indoor environments. To address the challenges due to device heterogeneity and lack of adaptivity, we propose a novel embedded ML framework calledFedHIL. Our framework combines indoor localization and federated learning (FL) to improve indoor localization accuracy in device-heterogeneous environments while also preserving user data privacy.FedHILintegrates a domain-specific selective weight adjustment approach to preserve the ML model's performance for indoor localization during FL, even in the presence of extremely noisy data. Experimental evaluations in diverse real-world indoor environments and with heterogeneous mobile devices show thatFedHILoutperforms state-of-the-art FL and non-FL indoor localization frameworks.FedHILis able to achieve 1.62 × better localization accuracy on average than the best performing FL-based indoor localization framework from prior work.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/technologies10060123
