Falls are a leading health risk for the elderly. Various wearable-based fall detection systems based on machine learning models have been developed to provide emergency alarms and services to improve safety and health-related quality of life. To support long-term healthcare services, the appropriate sampling rate, which plays a vital role in a fall detection system, must be investigated to guarantee performance accuracy and energy efficiency. Intuitively, decreasing the sampling rate of sensor nodes can provide computing and energy savings. However, there is lack of research exploring the performance accuracy of fall detection systems in terms of sampling rate, especially for machine learning models. In this work, the effects of decreasing sampling rates (ranging from 200/128 Hz to 3 Hz) on wearable-based fall detection systems are investigated based on four machine learning models: Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Naive Bayes (NB), and Decision Tree (DT). Two emulated fall datasets, the SisFall public dataset and the proposed dataset of this study, are used to allow an objective investigation of sampling rates. The findings show that fall detection systems based on SVM modeling and a radial basis function could achieve at least 98% and 97% accuracy, with sampling rates of 11.6 Hz and 5.8 Hz, respectively. Overall, the experimental results demonstrate that a sampling rate of 22 Hz is sufficient for most machine learning models to support wearable-based fall detection systems (accuracy ≥ 97%).

Falls are the primary cause of accidents for the elderly in the living environment. Reducing hazards in the living environment and performing exercises for training balance and muscles are the common strategies for fall prevention. However, falls cannot be avoided completely; fall detection provides an alarm that can decrease injuries or death caused by the lack of rescue. The automatic fall detection system has opportunities to provide real-time emergency alarms for improving the safety and quality of home healthcare services. Two common technical challenges are also tackled in order to provide a reliable fall detection algorithm, including variability and ambiguity. We propose a novel hierarchical fall detection algorithm involving threshold-based and knowledge-based approaches to detect a fall event. The threshold-based approach efficiently supports the detection and identification of fall events from continuous sensor data. A multiphase fall model is utilized, including free fall, impact, and rest phases for the knowledge-based approach, which identifies fall events and has the potential to deal with the aforementioned technical challenges of a fall detection system. Seven kinds of falls and seven types of daily activities arranged in an experiment are used to explore the performance of the proposed fall detection algorithm. The overall performances of the sensitivity, specificity, precision, and accuracy using a knowledge-based algorithm are 99.79%, 98.74%, 99.05% and 99.33%, respectively. The results show that the proposed novel hierarchical fall detection algorithm can cope with the variability and ambiguity of the technical challenges and fulfill the reliability, adaptability, and flexibility requirements of an automatic fall detection system with respect to the individual differences.

Falls are the major risks and threats among elderly population. Various studies have developed automatic critical fall detection systems for emergency alarms and medical services. Window sizes and segmentation approaches would affect the system performance in terms of power consumption, computational speed and reliability that are essential considerations in the real-world implementation. Intuitively, employing shorter window sizes and simpler segmentation approaches leads to a faster detection speed and better power efficiency. However, few works explore the effects of windowing methods on detection performance, especially for machine learning models. This paper investigates the impact of segmentation approaches and window sizes in wearable-based critical fall detection systems with machine learning models. Two generally used segmentation approaches, including sliding windows and impact-defined windows, are explored with a range of window sizes from 0.5 s to 5.0 s and four machine learning models: Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Classification and Regression Tree (CART) and Naove Bayes (NB). The results show that sliding windows are more sensitive to the changes of window sizes compared to impact-defined windows. However, the differences between the best performance of both segmentation approaches are within 1% (99.66% in sliding windows and 99.78% in impact-defined windows). For systems with SVM and k-NN models, using 0.5 s window sizes in sliding windows and combinations of 1.5 s backward and forward windows in impact-defined windows are sufficient to achieve at least 94% accuracy and 98% accuracy.

Total knee arthroplasty (TKA) is one of the most common treatments for people with severe knee osteoarthritis (OA). The accuracy of outcome measurements and quantitative assessments for perioperative TKA is an important issue in clinical practice. Timed up and go (TUG) tests have been validated to measure basic mobility and balance capabilities. A TUG test contains a series of subtasks, including sit-to-stand, walking-out, turning, walking-in, turning around, and stand-to-sit tasks. Detailed information about subtasks is essential to aid clinical professionals and physiotherapists in making assessment decisions. The main objective of this study is to design and develop a subtask segmentation approach using machine-learning models and knowledge-based postprocessing during the TUG test for perioperative TKA. The experiment recruited 26 patients with severe knee OA (11 patients with bilateral TKA planned and 15 patients with unilateral TKA planned). A series of signal-processing mechanisms and pattern recognition approaches involving machine learning-based multi-classifiers, fragmentation modification and subtask inference are designed and developed to tackle technical challenges in typical classification algorithms, including motion variability, fragmentation and ambiguity. The experimental results reveal that the accuracy of the proposed subtask segmentation approach using the AdaBoost technique with a window size of 128 samples is 92%, which is an improvement of at least 15% compared to that of the typical subtask segmentation approach using machine-learning models only.

Fluid intake is important for people to maintain body fluid homeostasis. Inadequate fluid intake leads to negative health consequences, such as headache, dizziness and urolithiasis. However, people in busy lifestyles usually forget to drink sufficient water and neglect the importance of fluid intake. Fluid intake management is important to assist people in adopting individual drinking behaviors. This work aims to propose a fluid intake monitoring system with a wearable inertial sensor using a hierarchical approach to detect drinking activities, recognize sip gestures and estimate fluid intake amount. Additionally, container-dependent amount estimation models are developed due to the influence of containers on fluid intake amount. The proposed fluid intake monitoring system could achieve 94.42% accuracy, 90.17% sensitivity, and 40.11% mean absolute percentage error (MAPE) for drinking detection, gesture spotting and amount estimation, respectively. Particularly, MAPE of amount estimation is improved approximately 10% compared to the typical approaches. The results have demonstrated the feasibility and the effectiveness of the proposed fluid intake monitoring system.

Insufficient fluid intake is becoming an actual concern and problem of the elderly with dramatic increase of aging population. Poor fluid intake habits and Dehydration can cause long-term negative effects in mental and physical capabilities, and even death. Typical approaches to monitor individual fluid intake behavior and consumption of fluid quantities mainly rely on self-report, such as questionnaires. However, these typical approaches suffer issues in manual errors and cause additional burdens on the user. In recent years, advantages of wireless sensor networks and pervasive computing technologies have provided the opportunities to create automatic, objective and low-intrusive fluid intake monitoring systems. The aim of this work is to design a 3D-printed smart cup attached with a single accelerometer and drinking event detection algorithm that is feasible to spot fluid intake gestures, especially for detecting drinking events and recognizing complete periods of drinking. Such drinking information about timing and the frequency of fluid intake can reveal fluid intake habits and that is important for clinical assessment and intervention. The finding shows that the best system performance using k-nearest neighbors (k-NN) model with window size of 4s achieves 89.92% and 85.88% F-measure in event-defined and frame-defined evaluation approaches, respectively.