scholarly journals A Telepresence System for Therapist-in-the-Loop Training for Elbow Joint Rehabilitation

2019 ◽  
Vol 9 (8) ◽  
pp. 1710 ◽  
Author(s):  
Songyuan Zhang ◽  
Qiang Fu ◽  
Shuxiang Guo ◽  
Yili Fu
Keyword(s):  
Real Time ◽  
Force Feedback ◽  
Interaction Force ◽  
Patient Specific ◽  
Light Weight ◽  
Haptic Interaction ◽  
Robotic Rehabilitation ◽  
Training Strategy ◽  
Specific Manner ◽  
Exoskeleton Device

This paper proposes a new robotic rehabilitation training platform that is motivated by the requirement for adjusting the training strategy and intensity in a patient-specific manner. The platform is implemented for tele-rehabilitation and is comprised of a haptic device operated by therapists, a lightweight exoskeleton worn by patients and a visually shared model. Through the visually shared model, the motion of the therapist and patient are measured and mapped to the motion of the corresponding object. Thus, the force generated by the therapist can be transferred to the patient for delivering training, while real-time force feedback with high transparency can be provided to the therapist so they know the amount of force being applied to patients in real time. In particular, both assistive therapy in the early stages and resistive therapy in the later stages of stroke can be performed. The home-use exoskeleton device is specifically designed to be light-weight and compliant for safety. The patient-exoskeleton and therapist-haptic interaction performance is evaluated by observing the muscle activities and interaction force. Two volunteers were requested to imitate the process of the therapist-in-the-loop training to evaluate the proposed platform.

GPU-Based Haptic Simulator for Dental Bone Drilling

2011 ◽  
Author(s):  
Fei Zheng ◽  
WenFeng Lu ◽  
Yoke San Wong ◽  
Kelvin Weng Chiong Foong
Keyword(s):  
Real Time ◽  
Graphics Processing Units ◽  
Force Feedback ◽  
Mandibular Canal ◽  
Structure Design ◽  
Patient Specific ◽  
Force Model ◽  
Bone Drilling ◽  
The Real ◽  
Drill Bits

Dental bone drilling is an inexact and often a blind art. Dentist risks damaging the invisible tooth roots, nerves and critical dental structures like mandibular canal and maxillary sinus. This paper presents a haptics-based jawbone drilling simulator for novice surgeons. Through the real-time training of tactile sensations based on patient-specific data, improved outcomes and faster procedures can be provided. Previously developed drilling simulators usually adopt penalty-based contact force models and often consider only spherical-shaped drill bits for simplicity and computational efficiency. In contrast, our simulator is equipped with a more precise force model, adapted from the Voxmap-PointShell (VPS) method to capture the essential features of the drilling procedure. In addition, the proposed force model can accommodate various shapes of drill bits. To achieve better anatomical accuracy, our oral model has been reconstructed from Cone Beam CT, using voxel-based method. To enhance the real-time response, the parallel computing power of Graphics Processing Units is exploited through extra efforts for data structure design, algorithms parallelization, and graphic memory utilization. Preliminary results show that the developed system can produce appropriate force feedback at different tissue layers.

scholarly journals Smart-YOLO: A Light-Weight Real-time Object Detection Network

2021 ◽  
Vol 1757 (1) ◽  
pp. 012096
Author(s):  
Dongyang Zhang ◽  
Xiaoyan Chen ◽  
Yumeng Ren ◽  
Nenghua Xu ◽  
Shuangwu Zheng
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Light Weight

Effect of a Real-Time Risk Score on 30-day Readmission Reduction in Singapore

2021 ◽  
Vol 12 (02) ◽  
pp. 372-382
Author(s):  
Christine Xia Wu ◽  
Ernest Suresh ◽  
Francis Wei Loong Phng ◽  
Kai Pik Tai ◽  
Janthorn Pakdeethai ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Real Time ◽  
Risk Score ◽  
Patient Specific ◽  
Learning Models ◽  
Medicine Department ◽  
High Risk Patients ◽  
Risk Patients ◽  
Machine Learning Models

Abstract Objective To develop a risk score for the real-time prediction of readmissions for patients using patient specific information captured in electronic medical records (EMR) in Singapore to enable the prospective identification of high-risk patients for enrolment in timely interventions. Methods Machine-learning models were built to estimate the probability of a patient being readmitted within 30 days of discharge. EMR of 25,472 patients discharged from the medicine department at Ng Teng Fong General Hospital between January 2016 and December 2016 were extracted retrospectively for training and internal validation of the models. We developed and implemented a real-time 30-day readmission risk score generation in the EMR system, which enabled the flagging of high-risk patients to care providers in the hospital. Based on the daily high-risk patient list, the various interfaces and flow sheets in the EMR were configured according to the information needs of the various stakeholders such as the inpatient medical, nursing, case management, emergency department, and postdischarge care teams. Results Overall, the machine-learning models achieved good performance with area under the receiver operating characteristic ranging from 0.77 to 0.81. The models were used to proactively identify and attend to patients who are at risk of readmission before an actual readmission occurs. This approach successfully reduced the 30-day readmission rate for patients admitted to the medicine department from 11.7% in 2017 to 10.1% in 2019 (p < 0.01) after risk adjustment. Conclusion Machine-learning models can be deployed in the EMR system to provide real-time forecasts for a more comprehensive outlook in the aspects of decision-making and care provision.

Towards soft real-time fault diagnosis for edge devices in industrial IoT using deep domain adaptation training strategy

2021 ◽  
Author(s):  
Dileep Kumar Soother ◽  
Sanaullah Mehran Ujjan ◽  
Kapal Dev ◽  
Sunder Ali Khowaja ◽  
Naveed Anwar Bhatti ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Real Time ◽  
Domain Adaptation ◽  
Training Strategy ◽  
Industrial Iot

Real-Time 2D Surface Profile Mapping of Biological Tissue with Force Feedback in Robot-Assisted Minimally Invasive Surgery

2015 ◽  
Vol 798 ◽  
pp. 319-323
Author(s):  
Ali Reza Hassan Beiglou ◽  
Javad Dargahi
Keyword(s):  
Minimally Invasive Surgery ◽  
Minimally Invasive ◽  
Real Time ◽  
Invasive Surgery ◽  
Strain Gauge ◽  
Force Feedback ◽  
Surface Profile ◽  
Robot Assisted ◽  
Contact Points ◽  
Force Signal

It has been more than 20 years that robot-assisted minimally invasive surgery (RMIS) has brought remarkable accuracy and dexterity for surgeons along with the decreasing trauma for the patients. In this paper a novel method of the tissue’s surface profile mapping is proposed. The tissue surface profile plays an important role for material identification during RMIS. It is shown how by integrating the force feedback into robot controller the surface profile of the tissue can be obtained with force feedback scanning. The experiment setup includes a 5 degree of freedoms (DOFs) robot which is equipped with a strain-gauge ball caster as the force feedback. Robot joint encoders signals and the captured force signal of the strain-gauge are transferred to developed surface transformation algorithm (STA). The real-time geometrical transformation process is triggered with force signal to identify contact points between the ball caster and the artificial tissue. The 2D surface profile of tissue will be mapped based on these contact points. Real-time capability of the proposed system is evaluated experimentally for the artifical tissues in a designed test rig.

scholarly journals Light-Weight, Self-Powered Sensor Based on Triboelectric Nanogenerator for Big Data Analytics in Sports

Electronics ◽  
2021 ◽  
Vol 10 (19) ◽  
pp. 2322
Author(s):  
Xiaofei Ma ◽  
Xuan Liu ◽  
Xinxing Li ◽  
Yunfei Ma
Keyword(s):  
Big Data ◽  
Real Time ◽  
Data Analytics ◽  
Mechanical Energy ◽  
Rapid Development ◽  
Big Data Analytics ◽  
Triboelectric Nanogenerator ◽  
Light Weight ◽  
Table Tennis ◽  
Self Powered

With the rapid development of the Internet of Things (IoTs), big data analytics has been widely used in the sport field. In this paper, a light-weight, self-powered sensor based on a triboelectric nanogenerator for big data analytics in sports has been demonstrated. The weight of each sensing unit is ~0.4 g. The friction material consists of polyaniline (PANI) and polytetrafluoroethylene (PTFE). Based on the triboelectric nanogenerator (TENG), the device can convert small amounts of mechanical energy into the electrical signal, which contains information about the hitting position and hitting velocity of table tennis balls. By collecting data from daily table tennis training in real time, the personalized training program can be adjusted. A practical application has been exhibited for collecting table tennis information in real time and, according to these data, coaches can develop personalized training for an amateur to enhance the ability of hand control, which can improve their table tennis skills. This work opens up a new direction in intelligent athletic facilities and big data analytics.

Sign in / Sign up

Export Citation Format

Share Document