A Hidden Semi-Markov Model based approach for rehabilitation exercise assessment.

In this paper, a Hidden Semi-Markov Model (HSMM) based approach is proposed to evaluate and monitor body motion during a rehabilitation training program. The approach extracts clinically relevant motion features from skeleton joint trajectories, acquired by the RGB-D camera, and provides a score for the subject's performance. The approach combines different aspects of rule and template based methods. The features have been defined by clinicians as exercise descriptors and are then assessed by a HSMM, trained upon an exemplar motion sequence. The reliability of the proposed approach is studied by evaluating its correlation with both a clinical assessment and a Dynamic Time Warping (DTW) algorithm, while healthy and neurological disabled people performed physical exercises. With respect to the discrimination between healthy and pathological conditions, the HSMM based method correlates better with the physician's score than DTW. The study supports the use of HSMMs to assess motor performance providing a quantitative feedback to physiotherapist and patients. This result is particularly appropriate and useful for a remote assessment in the home.

Predicting Motor and Cognitive Improvement Through Machine Learning Algorithm in Human Subject that Underwent a Rehabilitation Treatment in the Early Stage of Stroke.

BACKGROUND: The objective of this study was to investigate, in subject with stroke, the exact role as prognostic factor of common inflammatory biomarkers and other markers in predicting motor and/or cognitive improvement after rehabilitation treatment from early stage of stroke. METHODS: In this longitudinal cohort study on stroke patients undergoing inpatient rehabilitation, data from 55 participants were analyzed. Functional and clinical data were collected after admission to the rehabilitation unit. Biochemical and hematological parameters were obtained from peripheral venous blood samples on all individuals who participated in the study within 24hours from the admission at the rehabilitative treatment. Data regarding the health status were collected at the end of rehabilitative treatment. First, a feature selection has been performed to estimate the mutual dependence between input and output variables. More specifically, the so called Mutual Information criterion has been exploited. In the second stage of the analysis, the Support Vector Machines (SVMs), a non-probabilistic binary machine learning algorithm widely used for classification and regression, has been used to predict the output of the rehabilitation process. Performances of the linear SVM regression algorithm have been evaluated considering a different number of input features (ranging from 4 to 14). The performance evaluation of the model proposed has been investigated in terms of correlation, Root Mean Square Error (RMSE) and Mean Absolute Deviation Percentage (MADP). RESULTS: Results on the test samples show a good correlation between all the predicted and measured outputs (i.e. T1 Barthel Index (BI), T1 Motor Functional Independence Measure (FIM), T1 Cognitive FIM and T1 Total FIM) ranging from 0.75 to 0.81. While the MADP is high (i.e., 83.96%) for T1 BI, the other predicted responses (i.e., T1 Motor FIM, T1 Cognitive FIM, T1 Total FIM) disclose a smaller MADP of 30%. Accordingly, the RMSE ranges from 4.28 for T1 Cognitive FIM to 22.6 for T1 BI. CONCLUSIONS: In conclusion, the authors developed a new predictive model using SVM regression starting from common inflammatory biomarkers and other ratio markers. The main efforts of our model have been accomplished in regard to the evidence that the type of stroke has not shown itself to be a critical input variable to predict the discharge data, furthermore, among the four selected indicators, Barthel at T1 is the less predictable (MADP > 80%), while it is possible to predict T1 Cognitive FIM with an MADP less than 18%.

An Integrated Simulation Module for Cyber-Physical Automation Systems.

The integration of Wireless Sensors Networks (WSNs) into Cyber Physical Systems (CPSs) is an important research problem to solve in order to increase the performances, safety, reliability and usability of wireless automation systems. Due to the complexity of real CPSs, emulators and simulators are often used to replace the real control devices and physical connections during the development stage. The most widespread simulators are free, open source, expandable, flexible and fully integrated into mathematical modeling tools; however, the connection at a physical level and the direct interaction with the real process via the WSN are only marginally tackled; moreover, the simulated wireless sensor motes are not able to generate the analogue output typically required for control purposes. A new simulation module for the control of a wireless cyber-physical system is proposed in this paper. The module integrates the COntiki OS JAva Simulator (COOJA), a cross-level wireless sensor network simulator, and the LabVIEW system design software from National Instruments. The proposed software module has been called "GILOO" (Graphical Integration of Labview and cOOja). It allows one to develop and to debug control strategies over the WSN both using virtual or real hardware modules, such as the National Instruments Real-Time Module platform, the CompactRio, the Supervisory Control And Data Acquisition (SCADA), etc. To test the proposed solution, we decided to integrate it with one of the most popular simulators, i.e., the Contiki OS, and wireless motes, i.e., the Sky mote. As a further contribution, the Contiki Sky DAC driver and a new "Advanced Sky GUI" have been proposed and tested in the COOJA Simulator in order to provide the possibility to develop control over the WSN. To test the performances of the proposed GILOO software module, several experimental tests have been made, and interesting preliminary results are reported. The GILOO module has been applied to a smart home mock-up where a networked control has been developed for the LED lighting system.

Fractal Dimension as a discriminative feature for high accuracy classification in motor imagery EEG-based brain-computer interface.

BACKGROUND AND OBJECTIVE: The brain-computer interface (BCI) technology acquires human brain electrical signals, which can be effectively and successfully used to control external devices, potentially supporting subjects suffering from motor impairments in the interaction with the environment. To this aim, BCI systems must correctly decode and interpret neurophysiological signals reflecting the intention of the subjects to move. Therefore, the accurate classification of single events in motor tasks represents a fundamental challenge in ensuring efficient communication and control between users and BCIs. Movement-associated changes in electroencephalographic (EEG) sensorimotor rhythms, such as event-related desynchronization (ERD), are well-known features of discriminating motor tasks. Fractal dimension (FD) can be used to evaluate the complexity and self-similarity in brain signals, potentially providing complementary information to frequency-based signal features. METHODS: In the present work, we introduce FD as a novel feature for subject-independent event classification, and we test several machine learning (ML) models in behavioural tasks of motor imagery (MI) and motor execution (ME). RESULTS: Our results show that FD improves the classification accuracy of ML compared to ERD. Furthermore, unilateral hand movements have higher classification accuracy than bilateral movements in both MI and ME tasks. CONCLUSIONS: These results provide further insights into subject-independent event classification in BCI systems and demonstrate the potential of FD as a discriminative feature for EEG signals.

A human-in-the-loop approach for enhancing mobile robot navigation in presence of obstacles not detected by the sensory set.

Human-in-the-loop approaches can greatly enhance the human-robot interaction by making the user an active part of the control loop, who can provide a feedback to the robot in order to augment its capabilities. Such feedback becomes even more important in all those situations where safety is of utmost concern, such as in assistive robotics. This study aims to realize a human-in-the-loop approach, where the human can provide a feedback to a specific robot, namely, a smart wheelchair, to augment its artificial sensory set, extending and improving its capabilities to detect and avoid obstacles. The feedback is provided by both a keyboard and a brain-computer interface: with this scope, the work has also included a protocol design phase to elicit and evoke human brain event-related potentials. The whole architecture has been validated within a simulated robotic environment, with electroencephalography signals acquired from different test subjects.

Comparing between Different Sets of Preprocessing, Classifiers, and Channels Selection Techniques to Optimise Motor Imagery Pattern Classification System from EEG Pattern Recognition.

The ability to control external devices through thought is increasingly becoming a reality. Human beings can use the electrical signals of their brain to interact or change the surrounding environment and more. The development of this technology called brain-computer interface (BCI) will increasingly allow people with motor disabilities to communicate or use assistive devices to walk, manipulate objects and communicate. Using data from the PhysioNet database, this study implemented a pattern classification system for use in a BCI on 109 healthy volunteers during real movement activities and motor imagery recorded by 64-channels electroencephalography (EEG) system. Different classifiers such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Decision Trees (TREE) were applied on different combinations of EEG channels. Starting from two channels (C3, C4 and CP3 and CP4) positioned on the contralateral and ipsilateral sensorimotor cortex, the Region of Interest (RoI) centred on C3/Cp3 and C4/Cp4 and, finally, a data-driven automatic channels selection was tested to explore the best channel combination able to increase the classification accuracy. The results showed that the proposed automatic channels selection was able to significantly improve the performance of each classifier achieving 98% of accuracy for classification of real and imagined hand movement (sensitivity = 97%, specificity = 99%, AUC = 0.99) by SVM. While the accuracy of the classification between the imagery of hand and foot movements was 91% (sensitivity = 87%, specificity = 86%, AUC = 0.93) also with SVM. In the proposed approach, the data-driven automatic channels selection outperforms classical a priori channel selection models such as C3/C4, Cp3/Cp4, or RoIs around those channels with the utmost accuracy to help remove the boundaries of human communication and improve the quality of life of people with disabilities.

Neuromuscular Control Modelling of Human Perturbed Posture Through Piecewise Affine Autoregressive With Exogenous Input Models.

In this study, the neuromuscular control modeling of the perturbed human upright stance is assessed through piecewise affine autoregressive with exogenous input (PWARX) models. Ten healthy subjects underwent an experimental protocol where visual deprivation and cognitive load are applied to evaluate whether PWARX can be used for modeling the role of the central nervous system (CNS) in balance maintenance in different conditions. Balance maintenance is modeled as a single-link inverted pendulum; and kinematic, dynamic, and electromyography (EMG) data are used to fit the PWARX models of the CNS activity. Models are trained on 70% and tested on the 30% of unseen data belonging to the remaining dataset. The models are able to capture which factors the CNS is subjected to, showing a fitting accuracy higher than 90% for each experimental condition. The models present a switch between two different control dynamics, coherent with the physiological response to a sudden balance perturbation and mirrored by the data-driven lag selection for data time series. The outcomes of this study indicate that hybrid postural control policies, yet investigated for unperturbed stance, could be an appropriate motor control paradigm when balance maintenance undergoes external disruption.

Hybrid Deep Learning (hDL)-Based Brain-Computer Interface (BCI) Systems: A Systematic Review.

BACKGROUND: Brain-Computer Interface (BCI) is becoming more reliable, thanks to the advantages of Artificial Intelligence (AI). Recently, hybrid Deep Learning (hDL), which combines different DL algorithms, has gained momentum over the past five years. In this work, we proposed a review on hDL-based BCI starting from the seminal studies in 2015. OBJECTIVES: We have reviewed 47 papers that apply hDL to the BCI system published between 2015 and 2020 extracting trends and highlighting relevant aspects to the topic. METHODS: We have queried four scientific search engines (Google Scholar, PubMed, IEEE Xplore and Elsevier Science Direct) and different data items were extracted from each paper such as the database used, kind of application, online/offline training, tasks used for the BCI, pre-processing methodology adopted, type of normalization used, which kind of features were extracted, type of DL architecture used, number of layers implemented and which optimization approach were used as well. All these items were then investigated one by one to uncover trends. RESULTS: Our investigation reveals that Electroencephalography (EEG) has been the most used technique. Interestingly, despite the lower Signal-to-Noise Ratio (SNR) of the EEG data that makes pre-processing of that data mandatory, we have found that the pre-processing has only been used in 21.28% of the cases by showing that hDL seems to be able to overcome this intrinsic drawback of the EEG data. Temporal-features seem to be the most effective with 93.94% accuracy, while spatial-temporal features are the most used with 33.33% of the cases investigated. The most used architecture has been Convolutional Neural Network-Recurrent Neural Network CNN-RNN with 47% of the cases. Moreover, half of the studies have used a low number of layers to achieve a good compromise between the complexity of the network and computational efficiency. SIGNIFICANCE: To give useful information to the scientific community, we make our summary table of hDL-based BCI papers available and invite the community to published work to contribute to it directly. We have indicated a list of open challenges, emphasizing the need to use neuroimaging techniques other than EEG, such as functional Near-Infrared Spectroscopy (fNIRS), deeper investigate the advantages and disadvantages of using pre-processing and the relationship with the accuracy obtained. To implement new combinations of architectures, such as RNN-based and Deep Belief Network DBN-based, it is necessary to better explore the frequency and temporal-frequency features of the data at hand.

Functional evaluation of triceps surae during heel rise test: from EMG frequency analysis to machine learning approach.

Soleus muscle flap as coverage tissue is a possible surgical solution adopted to cover the wounds due to open fractures. Despite this procedure presents many clinical advantages, relatively poor information is available about the loss of functionality of triceps surae of the treated leg. In this study, a group of patients who underwent a soleus muscle flap surgical procedure has been analyzed through the heel rise test (HRT), in order to explore the triceps surae residual functionalities. A frequency band analysis was performed in order to assess whether the residual heads of triceps surae exhibit different characteristics with respect to both the non-treated lower limb and an age-matched control group. Then, an in-depth analysis based on a machine learning approach was proposed for discriminating between groups by generalizing across new unseen subjects. Experimental results showed the reliability of the proposed analyses for discriminating between-group at a specific time epoch and the high interpretability of the proposed machine learning algorithm allowed the temporal localization of the most discriminative frequency bands. Findings of this study highlighted that significant differences can be recognized in the myoelectric spectral characteristics between the treated and contralateral leg in patients who underwent soleus flap surgery. These experimental results may support the clinical decision-making for assessing triceps surae performance and for supporting the choice of treatment in plastic and reconstructive surgery. Graphical Abstract The Graphical abstract presents the scope of the proposed analysis of myoelectric signals of soleus and gastrocnemius muscles of patiens groups during Hell Rise Test, highlighting the applied methods and the obtained results.

A functional source separation algorithm to enhance error-related potentials monitoring in noninvasive brain-computer interface.

BACKGROUND AND OBJECTIVES: An Error related Potential (ErrP) can be noninvasively and directly measured from the scalp through electroencephalography (EEG), as response, when a person realizes they are making an error during a task (as a consequence of a cognitive error performed from the user). It has been shown that ErrPs can be automatically detected with time-discrete feedback tasks, which are widely applied in the Brain-Computer Interface (BCI) field for error correction or adaptation. In this work, a semi-supervised algorithm, namely the Functional Source Separation (FSS), is proposed to estimate a spatial filter for learning the ErrPs and to enhance the evoked potentials. METHODS: EEG data recorded on six subjects were used to evaluate the proposed method based on FFS algorithm in comparison with the xDAWN algorithm. FSS- and xDAWN-based methods were compared also to the Cz and FCz single channel. Single-trial classification was considered to evaluate the performances of the approaches. (Both the approaches were evaluated on single-trial classification of EEGs.) RESULTS: The results presented using the Bayesian Linear Discriminant Analysis (BLDA) classifier, show that FSS (accuracy 0.92, sensitivity 0.95, specificity 0.81, F1-score 0.95) overcomes the other methods (Cz - accuracy 0.72, sensitivity 0.74, specificity 0.63, F1-score 0.74; FCz - accuracy 0.72, sensitivity 0.75, specificity 0.61, F1-score 0.75; xDAWN - accuracy 0.75, sensitivity 0.79, specificity 0.61, F1-score 0.79) in terms of single-trial classification. CONCLUSIONS: The proposed FSS-based method increases the single-trial detection accuracy of ErrPs with respect to both single channel (Cz, FCz) and xDAWN spatial filter.

The KIMORE Dataset: KInematic Assessment of MOvement and Clinical Scores for Remote Monitoring of Physical REhabilitation.

This paper proposes a free dataset, available at the following link,1named KIMORE, regarding different rehabilitation exercises collected by a RGB-D sensor. Three data inputs including RGB, depth videos, and skeleton joint positions were recorded during five physical exercises, specific for low back pain and accurately selected by physicians. For each exercise, the dataset also provides a set of features, specifically defined by the physicians, and relevant to describe its scope. These features, validated with respect to a stereophotogrammetric system, can be analyzed to compute a score for the subject's performance. The dataset also contains an evaluation of the same performance provided by the clinicians, through a clinical questionnaire. The impact of KIMORE has been analyzed by comparing the output obtained by an example of rule and template-based approaches and the clinical score. The dataset presented is intended to be used as a benchmark for human movement assessment in a rehabilitation scenario in order to test the effectiveness and the reliability of different computational approaches. Unlike other existing datasets, the KIMORE merges a large heterogeneous population of 78 subjects, divided into 2 groups with 44 healthy subjects and 34 with motor dysfunctions. It provides the most clinically-relevant features and the clinical score for each exercise.1https://univpm-my.sharepoint.com/:f:/g/personal/p008099_staff_univpm_it/EiwbKIzk6N9NoJQx4J8aubIBx0o7tIa1XwclWp1NmRkA-w?e=F3jtBk.

Dynamic surface fault tolerant control for underwater remotely operated vehicles.

In this paper, we present a two stages actuator Fault Tolerant Control (FTC) strategy for the trajectory tracking of a Remotely Operated Vehicle (ROV). Dynamic Surface Control (DSC) is used to generate the moment and forces required by the vehicle to perform the desired motion. In the second stage of the control system, a fault tolerant thruster allocation policy is employed to distribute moment and forces among the thrusters. Exhaustive simulations have been carried out in order to compare the performance of the proposed solution with respect to different control techniques (i.e., PID, backstepping and sliding mode approaches). Saturations, actuator dynamics, sensor noises and time discretization are considered, in fault-free and faulty conditions. Furthermore, in order to provide a fair and exhaustive comparison of the control techniques, the same meta-heuristic approach, namely Artificial Bee Colony algorithm (ABC), has been employed to tune the controllers parameters.

An instrumental approach for monitoring physical exercises in a visual markerless scenario: A proof of concept.

This work proposes a real-time monitoring tool aimed to support clinicians for remote assessing exercise performances during home-based rehabilitation. The study relies on clinician indications to define kinematic features, that describe five motor tasks (i.e., the lateral tilt of the trunk, lifting of the arms, trunk rotation, pelvis rotation, squatting) usually adopted in the rehabilitation program for axial disorders. These features are extracted by the Kinect v2 skeleton tracking system and elaborated to return disaggregated scores, representing a measure of subjects performance. A bell-shaped function is used to rank the patient performances and to provide the scores. The proposed rehabilitation tool has been tested on 28 healthy subjects and on 29 patients suffering from different neurological and orthopedic diseases. The reliability of the study has been performed through a cross-sectional controlled design methodology, comparing algorithm scores with respect to blinded judgment provided by clinicians through filling a specific questionnaire. The use of task-specific features and the comparison between the clinical evaluation and the score provided by the instrumental approach constitute the novelty of the study. The proposed methodology is reliable for measuring subject's performance and able to discriminate between the pathological and healthy condition.