Comparison of four machine learning algorithms for a pre-impact fall detection system.

In recent years, real-time health monitoring using wearable sensors has been an active area of research. This paper presents an efficient and low-cost fall detection system based on a pair of shoes equipped with inertial sensors and plantar pressure sensors. In addition, four machine learning algorithms (KNN, SVM, RF, and BP neural network) are compared in terms of their detection performance and suitability for pre-impact fall detection. The results show that KNN and BP neural network outperformed the other two algorithms, where KNN had 98.8% sensitivity, 99.8% specificity, and 99.7% accuracy, and BP neural network had 100% sensitivity, 99.8% specificity, and 99.9% accuracy. KNN outperformed BP neural network in terms of fitting ability, and their lead times were both 460.95 ms. The system can provide sufficient intervention time for the wearer in the pre-impact phase and together with the touchdown fall protection device can effectively prevent fall injuries.

Identifying the changes in the cortical activity of various brain regions for different balance tasks: A review.

BACKGROUND: Balance support is critical to a person's overall function and health. Previous neuroimaging studies have shown that cortical structures play an essential role in postural control. OBJECTIVE: This review aims to identify differences in the pattern of neural activity induced by balance tasks with different balance control requirements. METHODS: Seventy-four articles were selected from the field of balance training and were examined based on four brain function detection technologies. RESULTS: In general, most studies focused on the activity changes of various cortical areas during training at different difficulty levels, but more and more attention has also begun to focus on the functional changes of other cortical and deep subcortical structures. Our analysis also revealed the neglect of certain task types. CONCLUSION: Based on these results, we identify and discuss future research directions that may contribute to a clear understanding of neural functional plasticity under different tasks.

Sensors and algorithms for locomotion intention detection of lower limb exoskeletons.

In recent years, lower limb exoskeletons (LLEs) have received much attention due to the potential to help people with paraplegia regain the ability of upright-legged locomotion. However, one major hindrance to converting prototypes into actual products is the lack of a balance recovery function. Locomotion intentions can be the first step for balance assistance. Therefore, its significance continues to grow. Many researchers focus on this topic, but there is a lack of a general discussion on the research phenomenon. Therefore, the purpose of this work is to systematize these data and benefit future research. This review is divided into two parts, the location of sensors/devices and the evaluation criteria of algorithms, which are the main components of locomotion intentions. We found that sensor/device placement is still concentrated in the lower limbs, but most researchers have found the importance of the chest. The peak power of the signal collected from the chest may be overestimated because it undergoes higher vertical velocity and acceleration during a rotation. However, despite the differences in peak power between the upper and lower back, high correlations were found for the tasks, especially from sitting to standing. Since peak power is based on vertical acceleration and velocity, it can be considered a metric that is more robust to changes in sensor location. Therefore, data acquisition from the chest is effective. In this paper, it is pointed out that sensors placed on the chest may have a tendency to change, as some researchers have realized in the field of locomotion intention recognition. In the evaluation criteria, we also found that deep learning algorithm (such as Back Propagation Artificial Neural Network (BPANN)) is outstanding, and Support Vector Machine (SVM) is the most cost-effective algorithm. In terms of accuracy, sensitivity, and specificity, BPANN achieved nearly 100%. SVM has different types; the best one achieves 98% accuracy, 100% sensitivity, and 100% specificity. But it also has 87.8% accuracy, which is not stable. Convolutional Neural Networks (CNN) can be used for image classification and have an accuracy of around 87%. Compared to the above two algorithms, CNN may have lower performance. Other algorithms also have higher accuracy, sensitivity, and specificity. These evaluation criteria, however, were not all ideal at the same time. Based on these results, we also point out the existing problems. In general, the application of these algorithms to LLE can contribute to its intention recognition, which can be helpful in balancing research. Finally, this can help make LLE more suitable for daily use.

The identification of interacting brain networks during robot-assisted training with multimodal stimulation.

Objective.Robot-assisted rehabilitation training is an effective way to assist rehabilitation therapy. So far, various robotic devices have been developed for automatic training of central nervous system following injury. Multimodal stimulation such as visual and auditory stimulus and even virtual reality technology were usually introduced in these robotic devices to improve the effect of rehabilitation training. This may need to be explained from a neurological perspective, but there are few relevant studies.Approach.In this study, ten participants performed right arm rehabilitation training tasks using an upper limb rehabilitation robotic device. The tasks were completed under four different feedback conditions including multiple combinations of visual and auditory components: auditory feedback; visual feedback; visual and auditory feedback (VAF); non-feedback. The functional near-infrared spectroscopy devices record blood oxygen signals in bilateral motor, visual and auditory areas. Using hemoglobin concentration as an indicator of cortical activation, the effective connectivity of these regions was then calculated through Granger causality.Main results.We found that overall stronger activation and effective connectivity between related brain regions were associated with VAF. When participants completed the training task without VAF, the trends in activation and connectivity were diminished.Significance.This study revealed cerebral cortex activation and interacting networks of brain regions in robot-assisted rehabilitation training with multimodal stimulation, which is expected to provide indicators for further evaluation of the effect of rehabilitation training, and promote further exploration of the interaction network in the brain during a variety of external stimuli, and to explore the best sensory combination.

A Center of Mass Estimation and Control Strategy for Body-Weight-Support Treadmill Training.

Walking disorders are common in post-stroke. Body weight support (BWS) systems have been proposed and proven to enhance gait training systems for recovering in individuals with hemiplegia. However, the fixed weight support and walking speed increase the risk of falling and decrease the active participation of the subjects. This paper proposes a strategy to enhance the efficiency of BWS treadmill training. It consists in regulating the height of the BWS system to track the height of the subject's center of mass (CoM), whereby the CoM is estimated through a long-short term memory (LSTM) network and a locomotion recognition system. The LSTM network takes the walking speed, body-height to leg-length ratio, hip and knee joint angles of the hemiplegic subjects' non-paretic side from the locomotion recognition system as input signals and outputs the CoM height to a BWS treadmill training robot. Besides, the hip and knee joints' ranges of motion are increased by 34.54% and 25.64% under the CoM height regulation compared to the constant weight support, respectively. With the CoM height regulation strategy, the stance phase duration of the paretic side is significantly increased by 14.6% of the gait cycle, and the symmetry of the gait is also promoted. The CoM height kinematics by adjustment strategy is in good agreement with the mean values of the 14 non-disabled subjects, which demonstrated that the adjustment strategy improves the stability of CoM height during the training.

Design and Preliminary Validation of a Lightweight Powered Exoskeleton During Level Walking for Persons With Paraplegia.

Upright-legged locomotion is a desirable ability for people with paraplegia. This paper introduces a newly developed lightweight powered exoskeleton (LIPE) for level walking and posture transfer of people with paraplegia using a user-centered design concept, which integrates the requirements of practical use, mechanical structure, and control system. The LIPE was evaluated with two subjects through several experimental tasks including kinematics and dynamics analysis in a local hospital. Results of functional evaluation showed that these subjects received the exoskeleton intervention well and the LIPE could provide appropriate gait assistance to the wearer during level walking, it could also help the wearer achieve the posture transfer from sitting to standing or from standing to sitting independently. Moreover, an endurance test also indicated that LIPE allows wearers to use it continuously for a long time. It is lightweight, cost effective, easy to use, and practical for people with paraplegia in their daily lives.

Dynamic Causal Modeling on the Identification of Interacting Networks in the Brain: A Systematic Review.

Dynamic causal modeling (DCM) has long been used to characterize effective connectivity within networks of distributed neuronal responses. Previous reviews have highlighted the understanding of the conceptual basis behind DCM and its variants from different aspects. However, no detailed summary or classification research on the task-related effective connectivity of various brain regions has been made formally available so far, and there is also a lack of application analysis of DCM for hemodynamic and electrophysiological measurements. This review aims to analyze the effective connectivity of different brain regions using DCM for different measurement data. We found that, in general, most studies focused on the networks between different cortical regions, and the research on the networks between other deep subcortical nuclei or between them and the cerebral cortex are receiving increasing attention, but far from the same scale. Our analysis also reveals a clear bias towards some task types. Based on these results, we identify and discuss several promising research directions that may help the community to attain a clear understanding of the brain network interactions under different tasks.

Design and Preliminary Validation of Individual Customized Insole for Adults with Flexible Flatfeet Based on the Plantar Pressure Redistribution.

Flatfoot is a common musculoskeletal deformity. One of the most effective treatments is to wear individually customized plantar pressure-based insoles to help users change the abnormally distributed pressure on the pelma. However, most previous studies were divided only into several plantar areas without detailed plantar characteristic analysis. In this study, a new insole is designed which redistributes pressure following the analysis of characteristic points of plantar pressure, and practical evaluation during walking of subjects while wearing the insole. In total, 10 subjects with flexible flatfeet have participated in the performance of gait experiments by wearing flat insoles, orthotic insoles, and plantar pressure redistribution insoles (PPRI). The results showed that the stance time of PPRI was significantly lower than that of the flat insoles under slow gait. PPRI in the second to third metatarsal and medial heel area showed better unloading capabilities than orthotic insoles. In the metatarsal and heel area, the PPRI also had its advantage in percentage of contact area compared to flat insole and orthotic insole. The results prove that PPRI improves the plantar pressure distribution and gait efficiency of adults with flexible flatfeet, and can be applied into clinical application.

Purchase and use of home healthcare devices for the elderly: a pilot study in Shanghai, China.

BACKGROUND: In China, home-based healthcare/rehabilitation has always been advocated by the government and is the most prevalent healthcare pattern. However, there is currently no data on how many each product has been purchased, and it is not clear what factors are associated with their use. The research aims to clarify the current practices and attitudes of the elderly on such matters, and further analyze their influence factors. METHODS: This pilot study consisted of two-round regional survey, conducted from July 25 to August 3, 2015 and July 20 to August 10, 2018 respectively. Both surveys released on-site paper questionnaires and collected after filling out in different communities. RESULTS: Two hundred forty-four valid questionnaires from 52 communities were collected. Compared with 2015 (30.8%), the number of people who did not purchase home healthcare devices in the same area decreased in 2018 (28.2%). Hemopiezometer (44.3%), glucometer (18.4%), massager (21.3%) and walking devices (19.3%) are the four main types of products that urbanites are most willing to buy. In addition, users' age group, education level, and income level were significantly correlated with the purchase of certain products. CONCLUSIONS: The types of home healthcare devices purchased by respondents are consistent with the distribution of chronic diseases of urban residents in China. The analysis of product brands also revealed the existing problems and huge growth space of the industry market, which also requires the government to introduce relevant policies and measures to regulate the market and accelerate the development of the industry.

Reprocessing and reuse of single-use medical devices in China: a pilot survey.

BACKGROUND: In China, reprocessing and reuse of single-use medical devices (SUDs) are banned. However, the actual situation has not been reported so far. The study aims to clarify the perceptions and concerns of various sectors of the community on the reuse of SUDs, and whether such practice exists. In addition, we are also wondering how acceptable the respondents are on this matter. METHODS: A cross-sectional study based on a national survey which was conducted on the professional online questionnaire survey platform ( www.wjx.cn ) from July 26 to August 4, 2015. We analyzed the data according to the work fields, sex, age, education level, professional background and participants' answers to 49 other questions. RESULTS: Five hundred forty-four nationwide respondents belong to nine different work fields. In general, participants had positive attitudes towards the reprocessing and reuse of SUDs. However, many respondents doubted the hygienic and functional safety of the reprocessed SUDs. They also tended to think that the reuse of SUDs should have lower prices and more technical training as well as patient advocacy. Further analysis demonstrated the work fields, education level and professional background of respondents were statistically associated with their responses to certain questions. CONCLUSIONS: The research indicated that although the reuse of SUDs is prohibited legally in China, there were extensive reprocessing and reuse in hospitals. Most responses tended to accept reprocessed SUDs if safety and low prices were guaranteed. These existing contradictions and the lack of relevant research led to policy makers in China will confront numerous challenges in building and improving this use system of medical devices to meet escalating demands of social sectors.

Facility Layout Planning with SHELL and Fuzzy AHP Method Based on Human Reliability for Operating Theatre.

A well-design facility layout planning refers to the reduction of the operation cost in the manufacturing and service industry. This work consists of reliability analysis of facility layout for an operating theatre; it aims at proposing a new evaluation approach, which integrated the fuzzy analytic hierarchy process and human reliability tool, for optimization of facility layout design with safety and human factors in an operating theatre. Firstly, the systematic layout planning is used to design the layout schemes on the basis of field investigations. Then, the criteria system is proposed based on human reliability analysis from four perspectives: software, hardware, environment, and liveware. Finally, the fuzzy analytic hierarchy process, a fuzzy extension of the multicriteria decision-making technique analytic hierarchy process, is used to compare these layout schemes based on the criteria system. The results that are obtained reveal interesting properties of facility layout planning in hospitals. It reveals that decision in selecting a suitable layout must meet not only the strategies and goals of the system but also meet the safety, security, and reliability of the system.

Design and Development of a Portable Exoskeleton for Hand Rehabilitation.

Improvement in hand function to promote functional recovery is one of the major goals of stroke rehabilitation. This paper introduces a newly developed exoskeleton for hand rehabilitation with a user-centered design concept, which integrates the requirements of practical use, mechanical structure, and control system. The paper also evaluated the function with two prototypes in a local hospital. Results of functional evaluation showed that significant improvements were found in ARAT (P = 0.014), WMFT (P = 0.020), and FMA_WH (P = 0.021). Increase in the mean values of FMA_SE was observed but without significant difference (P = 0.071). The improvement in ARAT score reflects the motor recovery in hand and finger functions. The increased FMA scores suggest there is a motor improvement in the whole upper limb, and especially in the hand after the training. The product met patients' requirements and has practical significance. It is portable, cost-effective, easy to use and supports multiple control modes to adapt to different rehabilitation phases.

[Study on the center-driven multiple degrees of freedom upper limb rehabilitation training robot].

With the aging of the society, the number of stroke patients has been increasing year by year. Compared with the traditional rehabilitation therapy, the application of upper limb rehabilitation robot has higher efficiency and better rehabilitation effect, and has become an important development direction in the field of rehabilitation. In view of the current development status and the deficiency of upper limb rehabilitation robot system, combined with the development trend of all kinds of products of the upper limb rehabilitation robot, this paper designed a center-driven upper limb rehabilitation training robot for cable transmission which can help the patients complete 6 degrees of freedom (3 are driven, 3 are underactuated) training. Combined the structure of robot with more joints rehabilitation training, the paper choosed a cubic polynomial trajectory planning method in the joint space planning to design two trajectories of eating and lifting arm. According to the trajectory equation, the movement trajectory of each joint of the robot was drawn in MATLAB. It laid a foundation for scientific and effective rehabilitation training. Finally, the experimental prototype is built, and the mechanical structure and design trajectories are verified.

A novel method for designing and optimizing the layout of facilities in bathroom for the elderly in home-based rehabilitation.

PURPOSE: The home-based rehabilitation of elderly patients improves their autonomy, independence and reintegration into society. Hence, a suitable environment plays an important role in rehabilitation, as do different assistance technologies. The majority of accidents at home involving elderly people occur in the bathroom. Therefore, the planning of the layout of facilities is important in this potentially dangerous area. This paper proposes an approach towards designing and optimizing the layout of facilities in the bathroom, based on logistical and nonlogistical relationships. METHODOLOGY: A fuzzy-based analytical hierarchical process (fuzzy-AHP) is then proposed for a comprehensive evaluation of the alternatives for this layout plan. This approach was applied to the home of a 71 years old female patient, who was experiencing home-based rehabilitation. After the initial designing and optimizing of the layout of the facilities in her bathroom, a plan could then be created for her particular needs. FINDINGS: The results of this research could then enable the home-based rehabilitation of elderly patients to be more effective. Value: This paper develops a new approach to design and optimize the layout of facilities in bathroom for the elderly. Implications for Rehabilitation Develop a new approach to design and optimize the layout of facilities in bathroom. Provide a mathematical and more scientific approach to home layout design for home-based rehabilitation. Provide new opportunities for research, for both the therapist and the patient to analyse the home facility layout.