Multi-Task Learning U-Net for Functional Shoulder Sub-Task Segmentation.

The assessment of a frozen shoulder (FS) is critical for evaluating outcomes and medical treatment. Analysis of functional shoulder sub-tasks provides more crucial information, but current manual labeling methods are time-consuming and prone to errors. To address this challenge, we propose a deep multi-task learning (MTL) U-Net to provide an automatic and reliable functional shoulder sub-task segmentation (STS) tool for clinical evaluation in FS. The proposed approach contains the main task of STS and the auxiliary task of transition point detection (TPD). For the main STS task, a U-Net architecture including an encoder-decoder with skip connection is presented to perform shoulder sub-task classification for each time point. The auxiliary TPD task uses lightweight convolutional neural networks architecture to detect the boundary between shoulder sub-tasks. A shared structure is implemented between two tasks and their objective functions of them are optimized jointly. The fine-grained transition-related information from the auxiliary TPD task is expected to help the main STS task better detect boundaries between functional shoulder sub-tasks. We conduct the experiments using wearable inertial measurement units to record 815 shoulder task sequences collected from 20 healthy subjects and 43 patients with FS. The experimental results present that the deep MTL U-Net can achieve superior performance compared to using single-task models. It shows the effectiveness of the proposed method for functional shoulder STS. The code has been made publicly available at https://github.com/RobinChu9890/MTL-U-Net-for-Functional-Shoulder-STS.Clinical Relevance- This work provides an automatic and reliable functional shoulder sub-task segmentation tool for clinical evaluation in frozen shoulder.

An Analysis of Fluid Intake Assessment Approaches for Fluid Intake Monitoring System.

Monitoring fluid intake is essential to help people manage their individual fluid intake behaviors and achieve adequate hydration. Previous studies of fluid intake assessment approaches based on inertial sensors can be categorized into wrist-worn-based and smart-container-based approaches. This study aims to analyze wrist-worn-based and smart-container-based fluid intake assessment approaches using inertial sensors. The comparison of these two approaches should be analyzed according to gesture recognition and volume estimation. In addition, the influence of the fill level and sip size information on the performance is explored in this study. The accuracy of gesture recognition with postprocessing is 92.89% and 91.8% for the wrist-worn-based approach and smart-container-based approach, respectively. For volume estimation, sip-size-dependent models can achieve better performance than general SVR models for both wrist-worn-based and smart-container-based approaches. The improvement of MAPE, MAD, and RMSE can reach over 50% except MAPE for small sip sizes. The results demonstrate that the sip size information and recognition performance are important for fluid intake assessment approaches.

Multiphase Identification Algorithm for Fall Recording Systems Using a Single Wearable Inertial Sensor.

Fall-related information can help clinical professionals make diagnoses and plan fall prevention strategies. The information includes various characteristics of different fall phases, such as falling time and landing responses. To provide the information of different phases, this pilot study proposes an automatic multiphase identification algorithm for phase-aware fall recording systems. Seven young adults are recruited to perform the fall experiment. One inertial sensor is worn on the waist to collect the data of body movement, and a total of 525 trials are collected. The proposed multiphase identification algorithm combines machine learning techniques and fragment modification algorithm to identify pre-fall, free-fall, impact, resting and recovery phases in a fall process. Five machine learning techniques, including support vector machine, k-nearest neighbor (kNN), naïve Bayesian, decision tree and adaptive boosting, are applied to identify five phases. Fragment modification algorithm uses the rules to detect the fragment whose results are different from the neighbors. The proposed multiphase identification algorithm using the kNN technique achieves the best performance in 82.17% sensitivity, 85.74% precision, 73.51% Jaccard coefficient, and 90.28% accuracy. The results show that the proposed algorithm has the potential to provide automatic fine-grained fall information for clinical measurement and assessment.

Domain-Adaptive Fall Detection Using Deep Adversarial Training.

Fall detection (FD) systems are important assistive technologies for healthcare that can detect emergency fall events and alert caregivers. However, it is not easy to obtain large-scale annotated fall events with various specifications of sensors or sensor positions during the implementation of accurate FD systems. Moreover, the knowledge obtained through machine learning has been restricted to tasks in the same domain. The mismatch between different domains might hinder the performance of FD systems. Cross-domain knowledge transfer is very beneficial for machine-learning based FD systems to train a reliable FD model with well-labeled data in new environments. In this study, we propose domain-adaptive fall detection (DAFD) using deep adversarial training (DAT) to tackle cross-domain problems, such as cross-position and cross-configuration. The proposed DAFD can transfer knowledge from the source domain to the target domain by minimizing the domain discrepancy to avoid mismatch problems. The experimental results show that the average F1-score improvement when using DAFD ranges from 1.5% to 7% in the cross-position scenario, and from 3.5% to 12% in the cross-configuration scenario, compared to using the conventional FD model without domain adaptation training. The results demonstrate that the proposed DAFD successfully helps to deal with cross-domain problems and to achieve better detection performance.

Automatic Functional Shoulder Task Identification and Sub-task Segmentation Using Wearable Inertial Measurement Units for Frozen Shoulder Assessment.

Advanced sensor technologies have been applied to support frozen shoulder assessment. Sensor-based assessment tools provide objective, continuous and quantitative information for evaluation and diagnosis. However, the current tools for assessment of functional shoulder tasks mainly rely on manual operation. It may cause several technical issues to the reliability and usability of the assessment tool, including manual bias during the recording and additional efforts for data labeling. To tackle these issues, this pilot study aims to propose an automatic functional shoulder task identification and sub-task segmentation system using inertial measurement units to provide reliable shoulder task labeling and sub-task information for clinical professionals. The proposed method combines machine learning models and rule-based modification to identify shoulder tasks and segment sub-tasks accurately. A hierarchical design is applied to enhance the efficiency and performance of the proposed approach. Nine healthy subjects and nine frozen shoulder patients are invited to perform five common shoulder tasks in the lab-based and clinical environments, respectively. The experimental results show that the proposed method can achieve 87.11% F-score for shoulder task identification, and 83.23% F-score and 427 mean absolute time errors (milliseconds) for sub-task segmentation. The proposed approach demonstrates the feasibility of the proposed method to support reliable evaluation for clinical assessment.

Fluid Intake Monitoring System Using a Wearable Inertial Sensor for Fluid Intake Management.

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.

Subtask Segmentation of Timed Up and Go Test for Mobility Assessment of Perioperative Total Knee Arthroplasty.

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.

Multi-Sensor Fusion Approach for Improving Map-Based Indoor Pedestrian Localization.

The interior space of large-scale buildings, such as hospitals, with a variety of departments, is so complicated that people may easily lose their way while visiting. Difficulties in wayfinding can cause stress, anxiety, frustration and safety issues to patients and families. An indoor navigation system including route planning and localization is utilized to guide people from one place to another. The localization of moving subjects is a critical-function component in an indoor navigation system. Pedestrian dead reckoning (PDR) is a technology that is widely employed for localization due to the advantage of being independent of infrastructure. To improve the accuracy of the localization system, combining different technologies is one of the solutions. In this study, a multi-sensor fusion approach is proposed to improve the accuracy of the PDR system by utilizing a light sensor, Bluetooth and map information. These simple mechanisms are applied to deal with the issue of accumulative error by identifying edge and sub-edge information from both Bluetooth and the light sensor. Overall, the accumulative error of the proposed multi-sensor fusion approach is below 65 cm in different cases of light arrangement. Compared to inertial sensor-based PDR system, the proposed multi-sensor fusion approach can improve 90% of the localization accuracy in an environment with an appropriate density of ceiling-mounted lamps. The results demonstrate that the proposed approach can improve the localization accuracy by utilizing multi-sensor data and fulfill the feasibility requirements of localization in an indoor navigation system.

Novel Hierarchical Fall Detection Algorithm Using a Multiphase Fall Model.

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.