Real-time Feedback System Research Articles

Real-time closed-loop tissue-specific laser osteotomy using deep-learning-assisted optical coherence tomography.

This article presents a real-time noninvasive method for detecting bone and bone marrow in laser osteotomy. This is the first optical coherence tomography (OCT) implementation as an online feedback system for laser osteotomy. A deep-learning model has been trained to identify tissue types during laser ablation with a test accuracy of 96.28 %. For the hole ablation experiments, the average maximum depth of perforation and volume loss was 0.216 mm and 0.077 mm3, respectively. The contactless nature of OCT with the reported performance shows that it is becoming more feasible to utilize it as a real-time feedback system for laser osteotomy.

Individualized closed-loop TMS synchronized with exoskeleton for modulation of cortical-excitability in patients with stroke: a proof-of-concept study.

Repetitive TMS is used in stroke rehabilitation with predefined passive low and high-frequency stimulation. Brain State-Dependent Stimulation (BSDS)/Activity-Dependent Stimulation (ADS) using bio-signal has been observed to strengthen synaptic connections. Without the personalization of brain-stimulation protocols, we risk a one-size-fits-all approach. We attempted to close the ADS loop via intrinsic-proprioceptive (via exoskeleton-movement) and extrinsic-visual-feedback to the brain. We developed a patient-specific brain stimulation platform with a two-way feedback system, to synchronize single-pulse TMS with exoskeleton along with adaptive performance visual feedback, in real-time, for a focused neurorehabilitation strategy to voluntarily engage the patient in the brain stimulation process. The novel TMS Synchronized Exoskeleton Feedback (TSEF) platform, controlled by the patient's residual Electromyogram, simultaneously triggered exoskeleton movement and single-pulse TMS, once in 10 s, implying 0.1 Hz frequency. The TSEF platform was tested for a demonstration on three patients (n = 3) with different spasticity on the Modified Ashworth Scale (MAS = 1, 1+, 2) for one session each. Three patients completed their session in their own timing; patients with (more) spasticity tend to take (more) inter-trial intervals. A proof-of-concept study on two groups-TSEF-group and a physiotherapy control-group was performed for 45 min/day for 20-sessions. Dose-matched Physiotherapy was given to control-group. Post 20 sessions, an increase in ipsilesional cortical-excitability was observed; Motor Evoked Potential increased by ~48.5 μV at a decreased Resting Motor Threshold by ~15.6%, with improvement in clinical scales relevant to the Fugl-Mayer Wrist/Hand joint (involved in training) by 2.6 units, an effect not found in control-group. This strategy could voluntarily engage the patient. A brain stimulation platform with a real-time two-way feedback system was developed to voluntarily engage the patients during the brain stimulation process and a proof-of-concept study on three patients indicates clinical gains with increased cortical excitability, an effect not observed in the control-group; and the encouraging results nudge for further investigations on a larger cohort.

Identifying the engagement of a brain network during a targeted tDCS-fMRI experiment using a machine learning approach.

Transcranial direct current stimulation (tDCS) can noninvasively modulate behavior, cognition, and physiologic brain functions depending on polarity and dose of stimulation as well as montage of electrodes. Concurrent tDCS-fMRI presents a novel way to explore the parameter space of non-invasive brain stimulation and to inform the experimenter as well as the participant if a targeted brain region or a network of spatially separate brain regions has been engaged and modulated. We compared a multi-electrode (ME) with a single electrode (SE) montage and both active conditions with a no-stimulation (NS) control condition to assess the engagement of a brain network and the ability of different electrode montages to modulate network activity. The multi-electrode montage targeted nodal regions of the right Arcuate Fasciculus Network (AFN) with anodal electrodes placed over the skull position of the posterior superior temporal/middle temporal gyrus (STG/MTG), supramarginal gyrus (SMG), posterior inferior frontal gyrus (IFG) and a return cathodal electrode over the left supraorbital region. In comparison, the single electrode montage used only one anodal electrode over a nodal brain region of the AFN, but varied the location between STG/MTG, SMG, and posterior IFG for different participants. Whole-brain rs-fMRI was obtained approximately every three seconds. The tDCS-stimulator was turned on at 3 minutes after the scanning started. A 4D rs-fMRI data set was converted to dynamic functional connectivity (DFC) matrices using a set of ROI pairs belonging to the AFN as well as other unrelated brain networks. In this study, we evaluated the performance of five algorithms to classify the DFC matrices from the three conditions (ME, SE, NS) into three different categories. The highest accuracy of 0.92 was obtained for the classification of the ME condition using the K Nearest Neighbor (KNN) algorithm. In other words, applying the classification algorithm allowed us to identify the engagement of the AFN and the ME condition was the best montage to achieve such an engagement. The top 5 ROI pairs that made a major contribution to the classification of participant's rs-fMRI data were identified using model performance parameters; ROI pairs were mainly located within the right AFN. This proof-of-concept study using a classification algorithm approach can be expanded to create a near real-time feedback system at a participant level to detect the engagement and modulation of a brain network that spans multiple brain lobes.

Model-based feed rate optimization for cycle time reduction in milling

Feed rate is an important determinant of the cutting force and cycle time. Selection of an appropriate feed rate can increase the processing quality and production efficiency. To determine an optimized feed rate, many methods have been developed to maintain a constant cutting force by applying a real-time feedback system constructed with data such as the tool condition, temperature, and cutting load of the spindle. However, these methods have low reliability because of difficulty in accurately measuring the spindle load. Moreover, real-time changes in the feed rate alter the cycle time. This study optimized the feed rate to a value that maintains the cutting force based on a cutting force prediction model and an algorithm to extract the cutting conditions from each line of the G-code. The feed rate optimization was applied to a flat end mill and ball end mill. An interpreter for the G-code was configured to calculate the tool center point and cutting condition. A real-time spindle power measurement system was constructed to measure the cutting force in each line of the G-code by identifying the parameters of the cutting force prediction model. The cutting force criterion was selected as the highest value among the predicted cutting forces. The optimized feed rate that maintains the cutting force was extracted based on the cutting conditions in other lines and the cutting force prediction model. The extracted feed rate was applied to the G-code by modifying only the feed rate command. Experimental results obtained with a commercial machining tool show that the proposed feed rate optimization significantly reduces the overall cycle time and effectively maintains the cutting force.

A real-time feedback system stabilises the regulation of worker reproduction under various colony sizes.

Social insects demonstrate adaptive behaviour for a given colony size. Remarkably, most species do this even without visual information in a dark environment. However, how they achieve this is yet unknown. Based on individual trait expression, an agent-based simulation was used to identify an explicit mechanism for understanding colony size dependent behaviour. Through repeated physical contact between the queen and individual workers, individual colony members monitor the physiological states of others, reflecting such contact information in their physiology and behaviour. Feedback between the sensing of physiological states and the corresponding behaviour patterns leads to self-organisation with colonies shifting according to their size. We showed (1) the queen can exhibit adaptive behaviour patterns for the increase in colony size while density per space remains unchanged, and (2) such physical constraints can underlie the adaptive switching of colony stages from successful patrol behaviour to unsuccessful patrol behaviour, which leads to constant ovary development (production of reproductive castes). The feedback loops embedded in the queen between the perception of internal states of the workers and behavioural patterns can explain the adaptive behaviour as a function of colony size.

Real-time vibrotactile feedback system for reducing trunk flexion exposure during construction tasks

Workplaces are increasingly evaluating the use of wearables for ergonomic assessment and providing biofeedback as a real-time postural intervention to improve workers’ posture. However, the effectiveness of such intervention systems has yet to be thoroughly investigated in different types of industrial tasks. This study tested the immediate effects of using vibrotactile feedback in simulated construction work tasks including lifting-lowering, shoveling, and tying rebar, to investigate the potential for such an intervention as a way to instruct workers in reducing excessive trunk flexion exposures. Fourteen male participants completed simulated work tasks with three different feedback locations, namely, no feedback, back, and wrist. The results demonstrate that the 95th, 90th, and 50th percentiles of trunk flexion angles are significantly lower for lifting-lowering and shoveling tasks when the feedback system is used. No significant postural changes were observed for the rebar tying task at any combination of percentile and feedback location. The rating of perceived exertion (RPE) for each task did not differ significantly between feedback conditions. Productivity remained the same with the feedback for lifting-lowering and rebar tying, while it was significantly reduced (4.5% of working rate reduction) in shoveling. Participants rated the wrist as the most preferred feedback location. The results of this study suggest that vibrotactile feedback has potential as an effective postural intervention for ergonomic risk factors in selected construction work tasks. Implications for the future design of real-time wearable, sensor-based vibrotactile feedback systems for postural control intervention during dynamic work tasks are discussed.

COST EFFICIENT FIVE WAY HOME AUTOMATION WITH FEEDBACK SYSTEM

This paper presents the concept of home automation with feedback system using Google assistant, IR remote, Blynk app, Alexa and Manual switches. Automating of any thing has a very large scope for the coming generation and now. These days, technology follows the user wherever they go, and the automation industry is greatly influenced by mobile technology. This work is primarily based on low-cost, effective home automation systems for mobile Android device remote control of appliances with this technology, we can create a smart house at a minimal cost while also raising the standard of living there and saving time and human effort. And also, the concept of smart home is very helpful for providing support to physically disabled people to fulfil their needs in home so they can lead a life like a normal person. This system's components include an Android phone, an ESP32 controller controlled by the Blynk app, an IR remote, manual relay controls, Google Assistant, Alexa, and a real-time feedback system Wi-Fi is being used in this case to monitor the home automation system because of it has high precision, long range and immediate connectivity. This automation module is very simple to install and easy to use, and it regulates the home appliances. Keywords – ESP32 board, IR remote, Relay module, Google assistant, Alexa, Realtime feedback.

UAV Cluster Behavior Modeling Based on Spatial-Temporal Hybrid Petri Net

Currently, we are facing an increasing trend in the use of unmanned aerial vehicles (UAV) in various activities, both civilian and military. The application of UAVs in the battlefield has received extensive attention amid a global new military revolution. A UAV cluster is a large and complex real-time feedback system that integrates a communication and sensor network, control system, calculation, and physical process. The heterogeneous UAVs conduct complex behaviors, which requires a comprehensive description and analysis of UAV cluster modeling. The integrated modeling of the heterogeneous UAV cluster is of great significance and value to test and verify the new combat mode. In this paper, we present a novel representation framework based on the Petri nets. We used a spatial-temporal hybrid Petri net to illustrate the discrete state and continuous process of a heterogeneous UAV cluster system, and effectively achieved the fusion of a physical and computational process and interaction event modeling in the cluster system. Finally, the formal verification of UAV cluster attack mission modeling was carried out by UPPAAL, suggesting the proposed modeling method is feasible and effective.

Electromyography as a surrogate for estimating metabolic energy expenditure during locomotion.

Minimizing metabolic energy expenditure (MEE) plays an important role in increasing mobility in people with locomotor disabilities, as movements that require high energy lead to less activity. Rehabilitation programs and devices use MEE to determine how effective they are, but using indirect calorimetry is limiting due to time delays and non-real-world conditions. Electromyography (EMG) offers insight into how muscles activate; thus, the purpose of this study was to develop a real-time MEE feedback system through the utilization of EMG signals. Participants completed five walking conditions at different stride frequencies (preferred, +/- 15%, +/- 30%), while breath-by-breath gas exchange, ground reaction forces and EMG signals were collected. The live EMG signal was numerically integrated and separated into strides, then scaled by a cost of force (COF) coefficient. MEE had the expected quadratic relationship seen in previous literature (R²=0.967), along with COF data (R²=0.701). The EMG method stabilized between 75.1% - 133.1%, which is not within a close range (90% - 110%) of MEE; thus, future studies must investigate other mathematical methods. Our results indicate a qualitative association between MEE and EMG activity, which could be used to increase mobility and quality of life for populations with disability.

Identifying Antibiotic Use Targets for the Management of Antibiotic Resistance Using an Extended-Spectrum β-Lactamase-Producing Escherichia coli Case: A Threshold Logistic Modeling Approach.

The aim of this study was to develop a logistic modeling concept to improve understanding of the relationship between antibiotic use thresholds and the incidence of resistant pathogens. A combined approach of nonlinear modeling and logistic regression, named threshold logistic, was used to identify thresholds and risk scores in hospital-level antibiotic use associated with hospital-level incidence rates of extended-spectrum β-lactamase (ESBL)-producing Escherichia coli (E. coli). Threshold logistic models identified thresholds for fluoroquinolones (61.1 DDD/1000 occupied bed days (OBD)) and third-generation cephalosporins (9.2 DDD/1000 OBD) to control hospital ESBL-producing E. coli incidence. The 60th percentile of ESBL-producing E. coli was determined as the cutoff for defining high incidence rates. Threshold logistic analysis showed that for every one-unit increase in fluoroquinolones and third-generation cephalosporins above 61.1 and 9.2 DDD/1000 OBD levels, the average odds of the ESBL-producing E. coli incidence rate being ≥60th percentile of historical levels increased by 4.5% and 12%, respectively. Threshold logistic models estimated the risk scores of exceeding the 60th percentile of a historical ESBL-producing E. coli incidence rate. Threshold logistic models can help hospitals in defining critical levels of antibiotic use and resistant pathogen incidence and provide targets for antibiotic consumption and a near real-time performance monitoring feedback system.

A Portable Device for Hand Rehabilitation With Force Cognition: Design, Interaction, and Experiment

Introducing interactive system into portable robots for hand rehabilitation has always been a crucial topic. Moreover, hand rehabilitation with force cognition can make patients participate actively and improve rehabilitation effect. In this paper, we design a portable robotic device with interactive system for patients to rehabilitate with force cognition. Firstly, an exoskeleton glove is designed with a compact mechanical structure which is controlled by a real-time feedback system. The portable device allows patients to rehabilitate not only in hospital. Next, an interactive system including virtual environment and force cognition is introduced to detect the hand motion and collision. At last, clinical tests of our portable device is carried out with 9 subjects after tendon injury to show the effective assistance with our device.

Real-time train regulation method for metro lines with substation peak power reduction

In high-frequency metro lines, train delays and substation peak power often occur, affecting safe and efficient train operation. In this paper, we propose real-time train regulation methods considering substation peak power reduction, in which runtimes and dwelltimes are adjusted to minimize the timetable and headway deviations and avoid multiple train accelerating. Firstly, we proposed two indirect indicators, i.e. overlapping time between accelerating phases and overlapping quantity between accelerating phases, which are minimized to suppress substation peak power in joint optimal train regulation models. The joint optimal train regulation models are based on the traditional real-time train regulation model considering the train traffic dynamics and control constraints. For the real-time requirement of train regulation, model predictive control (MPC) algorithms are designed to solve the formulated joint optimal control models, which generate the optimal train regulation strategies at each control cycle based on the real-time updated feedback system states. Finally, numerical examples based on one of the Guangzhou metro lines are implemented to verify the effectiveness and robustness of the proposed methods. The results show that the train regulation strategy with minimizing the overlapping quantity can not only suppress train delays and substation peak power, but also meet the real-time computation requirement.

Real-Time, Nondestructive Optical Feedback Systems for Infrared Laser Sealing of Blood Vessels.

High-power infrared (IR) diode lasers are capable of sealing blood vessels during surgery. This study characterizes an optical feedback system for real-time, nondestructive identification of vessel seals. A low power, red aiming beam (635 nm) was used for diagnostics, co-aligned with a therapeutic high-power IR beam (1470 nm). The IR laser delivered either 30 W for 5 s for successful seals or 5 W for 5 s for unsuccessful seals (control). All studies used a linear beam measuring 8.4 × 2.0 mm. Optical signals for successful and failed seals were correlated with vessel burst pressures (BP) using destructive testing via a standard BP setup. Light scattering increased significantly as vessels were coagulated. Successful seals correlated with a percent decrease in optical transmission signal of 59 ± 11 % and seal failures to a transmission decrease of 23 ± 8% (p < 0.01). With further development, the real-time optical feedback system may be integrated into a laparoscopic device to de-activate the laser upon successful vessel sealing.

Investigating the Effect of Real-Time Center of Pressure Feedback Training on the Swing Phase of Lower Limb Kinematics in Transfemoral Prostheses With SACH Foot.

Transfemoral amputee often encounters reduced toe clearance resulting in trip-related falls. Swing-phase joint angles have been shown to influence the toe clearance; therefore, training intervention that targets shaping the swing phase joint angles can potentially enhance toe clearance. The focus of this study was to investigate the effect of the shift in the location of the center of pressure (CoP) during heel strike on modulation of the swing-phase joint angles in able-bodied participants (n = 6) and transfemoral amputees (n = 3). We first developed a real-time CoP-based visual feedback system such that participants could shift the CoP during treadmill walking. Next, the kinematic data were collected during two different walking sessions-baseline (without feedback) and feedback (shifting the CoP anteriorly/posteriorly at heel strike to match the target CoP location). Primary swing-phase joint angle adaptations were observed with feedback such that during the midswing phase, posterior CoP shift feedback significantly increases (p < 0.05) the average hip and knee flexion angle by 11.55 deg and 11.86 deg, respectively, in amputees, whereas a significant increase (p < 0.05) in ankle dorsiflexion, hip and knee flexion angle by 3.60 deg, 3.22 deg, and 1.27 deg, respectively, compared to baseline was observed in able-bodied participants. Moreover, an opposite kinematic adaptation was seen during anterior CoP shift feedback. Overall, results confirm a direct correlation between the CoP shift and the modulation in the swing-phase lower limb joint angles.

Prediction of Health Care Data Using Efficient Machine Learning Algorithms

Every clinical decision relies on the doctor's expertise and comprehension.This standard procedure may, despite appearances, lead to errors, biases, and increased costs that compromise the patients' Quality of Service (QoS).There is a pressing need for adaptable equipment for critical patient care in developing nations like India.The majority of Indian hospitals are unable to provide their patients with adequate medical care due to a lack of suitable, simple, and expandable intelligent systems.The development of a comprehensive system that will enable hospitals to provide vital patients with a real-time feedback system is the objective of this project.Using IBM cloud computing as a service platform and machine learning, we propose a standard architecture, language, and classification scheme for analyzing vital patient health data (PaaS).The development of a machine learning (ML) method for predicting a patient's fitness is the primary goal of this study.Our models and data are stored and managed by IBM Watson Studio and IBM Cloud.The Base Predictors for our ml models are Nave Bayes, Logistic Regression, the KNeighbors Classifier, the Decision Tree Classifier, the Random Forest Classifier, the Gradient Boosting Classifier, and the MLP Classifier.The precision of the model has been increased by employing the ensemble learning bagging strategy.We use a variety of machine learning algorithms for ensemble learning.The Critical Patient Management System, or CPMS, is a mobile application we developed that allows for real-time data and record viewing.Data that is relevant to ML model training and deployment can be fetched in real time from IBM Cloud and made available through CPMS because of the way the system is built.Doctors can use Ml tendencies to predict a patient's health status.The CPMS will send an SMS notification to the duty physician and nurse to provide immediate care if the situation worsens as anticipated.Hospitals might get a smart healthcare solution if the mission, milliliter models, and mobile application are combined.

Real-time video and force analysis feedback system for learning strength skills on rings in men’s artistic gymnastics

ABSTRACT The importance of objective evaluations has gathered more attention than before for a fairer and better performance judgment in gymnastics. The purpose of this report was to disseminate information about our system and provide an example of data utilisation in high-level competitive training from a practical standpoint. The system combined video and force data, measured with two force transducers at the top of the ring cables, wirelessly transmitted to a computer. The force data synchronised with the video were available in real time or immediately after trials, making it possible to objectively quantify the amount of spotting that a gymnast received as external physical assistances. The simplicity of the setup and several special functions of the system led athletes and coaches spontaneously to use it in their regular training to quantify their skill level. Based on the regular utilisation of the system, the general correspondence between objectively measured values and the subjective perception of spotters was determined. In addition, the data suggested the possibility of technical evaluation of a certain type of strength skill based on force data. The data that are shared in this report should be beneficial in facilitating activities to integrate science into practice in gymnastics.

Shape Sensing of Hyper-Redundant Robots Using an AHRS IMU Sensor Network.

The paper proposes a novel approach for shape sensing of hyper-redundant robots based on an AHRS IMU sensor network embedded into the structure of the robot. The proposed approach uses the data from the sensor network to directly calculate the kinematic parameters of the robot in modules operational space reducing thus the computational time and facilitating implementation of advanced real-time feedback system for shape sensing. In the paper the method is applied for shape sensing and pose estimation of an articulated joint-based hyper-redundant robot with identical 2-DoF modules serially connected. Using a testing method based on HIL techniques the authors validate the computed kinematic model and the computed shape of the robot prototype. A second testing method is used to validate the end effector pose using an external sensory system. The experimental results obtained demonstrate the feasibility of using this type of sensor network and the effectiveness of the proposed shape sensing approach for hyper-redundant robots.

Haptic Feedback to Assist Blind People in Indoor Environment Using Vibration Patterns.

Feedback is one of the significant factors for the mental mapping of an environment. It is the communication of spatial information to blind people to perceive the surroundings. The assistive smartphone technologies deliver feedback for different activities using several feedback mediums, including voice, sonification and vibration. Researchers 0have proposed various solutions for conveying feedback messages to blind people using these mediums. Voice and sonification feedback are effective solutions to convey information. However, these solutions are not applicable in a noisy environment and may occupy the most important auditory sense. The privacy of a blind user can also be compromised with speech feedback. The vibration feedback could effectively be used as an alternative approach to these mediums. This paper proposes a real-time feedback system specifically designed for blind people to convey information to them based on vibration patterns. The proposed solution has been evaluated through an empirical study by collecting data from 24 blind people through a mixed-mode survey using a questionnaire. Results show the average recognition accuracy for 10 different vibration patterns are 90%, 82%, 75%, 87%, 65%, and 70%.

Keep Me in the Loop: Real-Time Feedback with Multimodal Data

This paper describes the CPR Tutor, a real-time multimodal feedback system for cardiopulmonary resuscitation (CPR) training. The CPR Tutor detects training mistakes using recurrent neural networks. The CPR Tutor automatically recognises and assesses the quality of the chest compressions according to five CPR performance indicators. It detects training mistakes in real-time by analysing a multimodal data stream consisting of kinematic and electromyographic data. Based on this assessment, the CPR Tutor provides audio feedback to correct the most critical mistakes and improve the CPR performance. The mistake detection models of the CPR Tutor were trained using a dataset from 10 experts. Hence, we tested the validity of the CPR Tutor and the impact of its feedback functionality in a user study involving additional 10 participants. The CPR Tutor pushes forward the current state of the art of real-time multimodal tutors by providing: (1) an architecture design, (2) a methodological approach for delivering real-time feedback using multimodal data and (3) a field study on real-time feedback for CPR training. This paper details the results of a field study by quantitatively measuring the impact of the CPR Tutor feedback on the performance indicators and qualitatively analysing the participants’ questionnaire answers.

Effect of 6-Week Balance Exercise by Real-Time Postural Feedback System on Walking Ability for Patients with Chronic Stroke: A Pilot Single-Blind Randomized Controlled Trial.

Stroke causes balance dysfunction, leading to decreased physical activity and increased falls. Thus, effective balance exercises are needed to improve balance dysfunction. This single-blind, single-center randomized controlled trial evaluated the long-term and continuous effects of balance exercise using a real-time postural feedback system to improve balancing ability safely. Thirty participants were randomized into intervention (n = 15) and control (n = 15) groups; 11 in each group completed the final evaluation. The effect of the intervention was evaluated by muscle strength of knee extension, physical performance (short physical performance battery, the center of pressure trajectory length per second, and Timed Up and Go test [TUG]), and self-reported questionnaires (modified Gait Efficacy Scale [mGES] and the Fall Efficacy Scale) at pre (0 week), post (6-week), and at follow-up (10-week) visits. The TUG and mGES showed a significant interactive (group * time) effect (p = 0.007 and p = 0.038, respectively). The intervention group showed significant decreasing time to perform TUG from pre- to post-intervention (p = 0.015) and pre-intervention to follow-up (p = 0.016); mGES showed a significant change from pre-intervention to follow-up (p = 0.036). Thus, balance exercise using a real-time postural feedback system can confer a positive effect on the walking ability in patients with chronic stroke and increase their self-confidence in gait performance.