Nurse care activity recognition based on machine learning techniques using accelerometer data

Irbaz, Mohammad Sabik; Azad, Abir; Sathi, Tanjila Alam; Lota, Lutfun Nahar

doi:10.1145/3410530.3414339

Cited by 3 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Irbaz et. al [10] achieved a validation accuracy of 75% and test accuracy of 22.35%. They used both a high pass and a low pass filter to shape the data in the spatial domain during preprocessing and used the kNN classifier instead of a deep learning algorithm.…”

Section: Related Workmentioning

confidence: 98%

Predicting User-specific Future Activities using LSTM-based Multi-label Classification

Irbaz¹,

Ahsan²,

Lota³

2022

Preprint

View full text Add to dashboard Cite

User-specific future activity prediction in the healthcare domain based on previous activities can drastically improve the services provided by the nurses. It is challenging because, unlike other domains, activities in healthcare involve both nurses and patients, and they also vary from hour to hour. In this paper, we employ various data processing techniques to organize and modify the data structure and an LSTM-based multi-label classifier for a novel 2-stage training approach (user-agnostic pre-training and user-specific fine-tuning). Our experiment achieves a validation accuracy of 31.58%, precision 57.94%, recall 68.31%, and F1 score 60.38%. We concluded that proper data pre-processing and a 2-stage training process resulted in better performance. This experiment is a part of the "Fourth Nurse Care Activity Recognition Challenge" by our team "Not A Fan of Local Minima".

show abstract

Section: Related Workmentioning

confidence: 98%

Predicting User-specific Future Activities using LSTM-based Multi-label Classification

Irbaz¹,

Ahsan²,

Lota³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The authors of [9] achieved 57% leave-one-out cross-validation accuracy using Spatio-Temporal Graph Convolutional Network (STGCN). The authors of [15] extracted different features and compared several machine learning techniques for recognizing 12 activities in the second challenge. They claimed to have attained the greatest accuracy by employing KNN.…”

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

Accelerometer based Complex Nurse Care Activity Recognition using Machine Learning Approach

Tusar

Islam

Sharmin

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

Researchers have been working for a long time to recognize human activities based on sensor-based data. Despite the ongoing advancements in this field, it remains challenging to recognize complex human activities for a specific domain. To bring attention to this issue, the "Third Nurse Care Activity Recognition Challenge" gathered accelerometer data from smartphones to estimate daily nurse care activities. The main challenge was handling the noisy and inconsistent dataset, which is a persistent issue in any real-life data. Also, each activity depends on both the subject and the receiver, making its recognition more complex. Our team, Team Alkaline, used high pass and low pass filters to reduce noise, adopting an overlapping windowing technique. Then we extracted features in multiple domains to derive the necessary information required for classifying the human activities more accurately. Later on, we used a feature selection method to select the most significant features. We applied Random Forest (RF) classifier for training and achieved 99.0% accuracy on the validation set.

show abstract

Nurse care activity recognition based on machine learning techniques using accelerometer data

Cited by 3 publications

References 16 publications

Predicting User-specific Future Activities using LSTM-based Multi-label Classification

Predicting User-specific Future Activities using LSTM-based Multi-label Classification

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

Accelerometer based Complex Nurse Care Activity Recognition using Machine Learning Approach

Contact Info

Product

Resources

About