Integrating Activity Recognition and Nursing Care Records

Inoue, Sozo; Lago, Paula; Hossain, Tahera; Mairittha, Tittaya; Mairittha, Nattaya

doi:10.1145/3351244

Cited by 40 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the action that a user wants to input is out of the predefined list, it cannot be correctly predicted. Following prior work [15], the customizable activity class function developed is designed to be performed on the cloud and dynamically customized depending on the site server (e.g., an experimental group/facility) rather than individual users. The weak support of personalization can have a significant impact on model performance.…”

Section: Discussion and Future Directionsmentioning

confidence: 99%

“…First, either data labeling was done by online [11,12] or by offline [13]; they must achieve highly accurate timestamps and overcome extended memorization. Second, either data labeling was done by self-labeling or by an observer; they impose several challenges such as missing labels, inaccurate timestamps, and high cost [12,14,15]. Third, either data labeling was done in a laboratory scenario or a realistic scenario; they present specific challenges.…”

mentioning

confidence: 99%

“…For example, the models produced in laboratory settings lose accuracy when applied in real circumstances due to the variety of users' behavior. In comparison, the models produced in practical environments tend to be more generic but complicated [15][16][17][18][19]. Finally, there are many challenges to all data labeling mechanisms undertaken.…”

mentioning

confidence: 99%

See 2 more Smart Citations

On-Device Deep Personalization for Robust Activity Data Collection

Mairittha

Inoue

2020

Sensors

Self Cite

View full text Add to dashboard Cite

One of the biggest challenges of activity data collection is the need to rely on users and keep them engaged to continually provide labels. Recent breakthroughs in mobile platforms have proven effective in bringing deep neural networks powered intelligence into mobile devices. This study proposes a novel on-device personalization for data labeling for an activity recognition system using mobile sensing. The key idea behind this system is that estimated activities personalized for a specific individual user can be used as feedback to motivate user contribution and improve data labeling quality. First, we exploited fine-tuning using a Deep Recurrent Neural Network to address the lack of sufficient training data and minimize the need for training deep learning on mobile devices from scratch. Second, we utilized a model pruning technique to reduce the computation cost of on-device personalization without affecting the accuracy. Finally, we built a robust activity data labeling system by integrating the two techniques outlined above, allowing the mobile application to create a personalized experience for the user. To demonstrate the proposed model’s capability and feasibility, we developed and deployed the proposed system to realistic settings. For our experimental setup, we gathered more than 16,800 activity windows from 12 activity classes using smartphone sensors. We empirically evaluated the proposed quality by comparing it with a baseline using machine learning. Our results indicate that the proposed system effectively improved activity accuracy recognition for individual users and reduced cost and latency for inference for mobile devices. Based on our findings, we highlight critical and promising future research directions regarding the design of efficient activity data collection with on-device personalization.

show abstract

Section: Discussion and Future Directionsmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

On-Device Deep Personalization for Robust Activity Data Collection

Mairittha

Inoue

2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…This also resulted in a less overfitted model. The data was gathered from a nursing care facility in the real-world environment [3], [28]. Data were obtained from 12 subjects (2, 3, 4, 5, 6, 7, 9, 12, 17, 19, 21, and 22), all of whom are facility caregivers and nurses.…”

Section: Related Workmentioning

confidence: 99%

Nurse Care Activity Recognition: A Cost-Sensitive Ensemble Approach to Handle Imbalanced Class Problem in the Wild

Rahman

Hassan

Ahad

2021

Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of The

View full text Add to dashboard Cite

Nurse care activity recognition is a recent but demanding study topic in human activity recognition (HAR) since it has high class imbalance and intra-class variability problem depending on both the patient and the receiver. Although traditional imbalance learning approaches are offered to address this issue, they have several limitations: 1) important information is lost while using undersampling approaches, and 2) oversampling methods shifts the class distribution, exposing the model to overfitting and over-optimism. To tackle this problem, we present a framework for a cost-sensitive hybrid optimum ensemble classifier. Our technique modified the class weights to impose higher misclassification costs on minority classes. Then we combined different weighted base classifier outputs with a stacked generalization method. This technique allowed us to leverage the skills of a varied collection of high-performing base learners while balancing each other's limitations and strengths. By utilizing our hybrid technique, we achieved 70.8% average cross-validation balanced accuracy in classifying 28 activities conducted by nurses in real-life settings. We developed this algorithmic pipeline for "The 3rd Nurse Care Activity Recognition Challenge" at ACM UbiComp 2021.

show abstract

“…One of the primary goal of HAR is to better understand people's everyday actions by interpreting data from various sensors gathered from individuals and their living situations [14]. The long-term objective of this field of research is to remotely monitor the daily activities of elderly people, pregnant women, and patients in order to provide them with ongoing health and well-being supervision [1,11,12]. The fast growth of smart wearable and portable electronics, as well as the high quality embedded sensors within smartphones, is providing a significant boost to the research field of ubiquitous, pervasive, and wearable computing [3,7].…”

Section: Introductionmentioning

confidence: 99%