Poor eating habits in children and teenagers can lead to obesity, eating disorders, or life-threatening health problems. Although researchers have studied children’s eating behavior for decades, the research community has had limited technology to support the observation and measurement of fine-grained details of a child’s eating behavior. In this paper, we present the feasibility of adapting the Auracle, an existing research-grade earpiece designed to automatically and unobtrusively recognize eating behavior in adults, for measuring children’s eating behavior. We identified and addressed several challenges pertaining to monitoring eating behavior in children, paying particular attention to device fit and comfort. We also improved the accuracy and robustness of the eating-activity detection algorithms. We used this improved prototype in a lab study with a sample of 10 children for 60 total sessions and collected 22.3 hours of data in both meal and snack scenarios. Overall, we achieved an accuracy exceeding 85.0% and an F1 score exceeding 84.2% for eating detection with a 3-second resolution, and a 95.5% accuracy and a 95.7% F1 score for eating detection with a 1-minute resolution.
more »
« less
Proximity-based active learning for eating moment recognition in wearable systems
Detecting when eating occurs is an essential step toward automatic dietary monitoring, medication adherence assessment, and diet-related health interventions. Wearable technologies play a central role in designing unobtrusive diet monitoring solutions by leveraging machine learning algorithms that work on time-series sensor data to detect eating moments. While much research has been done on developing activity recognition and eating moment detection algorithms, the performance of the detection algorithms drops substantially when the model is utilized by a new user. To facilitate the development of personalized models, we propose PALS, Proximity-based Active Learning on Streaming data, a novel proximity-based model for recognizing eating gestures to significantly decrease the need for labeled data with new users. Our extensive analysis in both controlled and uncontrolled settings indicates F-score of PALS ranges from 22% to 39% for a budget that varies from 10 to 60 queries. Furthermore, compared to the state-of-the-art approaches, off-line PALS achieves up to 40% higher recall and 12% higher F-score in detecting eating gestures.
more »
« less
- Award ID(s):
- 1932346
- PAR ID:
- 10209064
- Date Published:
- Journal Name:
- WearSys '20: Proceedings of the 6th ACM Workshop on Wearable Systems and Applications
- Page Range / eLocation ID:
- 7 to 12
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Meyendorf, Norbert G. ; Farhangdoust, Saman (Ed.)Network intrusion detection systems (NIDS) for Internet-of-Things (IoT) infrastructure are among the most critical tools to ensure the protection and security of networks against malicious cyberattacks. This paper employs four machine learning algorithms and evaluates their performance in NIDS considering the accuracy, precision, recall, and F-score. The comparative analysis conducted using the CICIDS2017 dataset reveals that the Boosted machine learning techniques perform better than the other algorithms reaching the predicted accuracy of above 99% in detecting cyberattacks. Such ML-based attack detectors also have the largest weighted metrics of F1-score, precision, and recall. The results assist the network engineers in choosing the most effective machine learning-based NIDS to ensure network security for today’s growing IoT network traffic.more » « less
-
more » « less
Abstract Human–machine interface requires various sensors for communication, manufacturing and environmental control, and health and safety monitoring. Capacitive sensors have been used to detect touch, distance, geometry, electric property, and environmental parameters. However, highly sensitive proximity detection with a small form factor has always been a challenge. This paper presents a capacitive sensor composed of a nanostructured electrode array for contact and noncontact detection. In the sensor configuration, the nanostructured electrode is made of high aspect ratio cellulose fibers embedded with carbon nanotubes. The complementary electrode is designed to be smaller in surface area for high sensitivity. Based on the analysis, the unique sensing mechanism is shown to enhance the proximity sensitivity for target detection. A pair of asymmetrically designed electrodes are characterized and compared with the traditional symmetric electrodes for proximity and contact detection of human hands. The sensor performance is also characterized for detecting water mass in glass and metal cups. In the end, a smart pad that can recognize human gestures, gait, and water mass with unprecedented sensitivity is demonstrated.
-
Modern scientific workflows are data-driven and are often executed on distributed, heterogeneous, high-performance computing infrastructures. Anomalies and failures in the work- flow execution cause loss of scientific productivity and inefficient use of the infrastructure. Hence, detecting, diagnosing, and mitigating these anomalies are immensely important for reliable and performant scientific workflows. Since these workflows rely heavily on high-performance network transfers that require strict QoS constraints, accurately detecting anomalous network perfor- mance is crucial to ensure reliable and efficient workflow execu- tion. To address this challenge, we have developed X-FLASH, a network anomaly detection tool for faulty TCP workflow transfers. X-FLASH incorporates novel hyperparameter tuning and data mining approaches for improving the performance of the machine learning algorithms to accurately classify the anoma- lous TCP packets. X-FLASH leverages XGBoost as an ensemble model and couples XGBoost with a sequential optimizer, FLASH, borrowed from search-based Software Engineering to learn the optimal model parameters. X-FLASH found configurations that outperformed the existing approach up to 28%, 29%, and 40% relatively for F-measure, G-score, and recall in less than 30 evaluations. From (1) large improvement and (2) simple tuning, we recommend future research to have additional tuning study as a new standard, at least in the area of scientific workflow anomaly detection.more » « less
-
With rapid growth in unhealthy diet behaviors, implementing strategies that improve healthy eating is becoming increasingly important. One approach to improving diet behavior is to continuously monitor dietary intake (e.g., calorie intake) and provide educational, motivational, and dietary recommendation feedback. Although technologies based on wearable sensors, mobile applications, and light-weight cameras exist to gather diet-related information such as food type and eating time, there remains a gap in research on how to use such information to close the loop and provide feedback to the user to improve healthy diet. We address this knowledge gap by introducing a diet behavior change framework that generates real-time diet recommendations based on a user’s food intake and considering user’s deviation from the suggested diet routine. We formulate the problem of optimal diet recommendation as a sequential decision making problem and design a greedy algorithm that provides diet recommendations such that the amount of change in user’s dietary habits is minimized while ensuring that the user’s diet goal is achieved within a given time-frame. This novel approach is inspired by the Social Cognitive Theory, which emphasizes behavioral monitoring and small incremental goals as being important to behavior change. Our optimization algorithm integrates data from a user’s past dietary intake as well as the USDA nutrition dataset to identify optimal diet changes. We demonstrate the feasibility of our optimization algorithms for diet behavior change using real-data collected in two study cohorts with a combined N=10 healthy participants who recorded their diet for up to 21 days.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3396870.3400011
