Article
Engineering, Electrical & Electronic
Yu Ling, Xiang Chen, Yuwen Ruan, Xu Zhang, Xun Chen
Summary: This study compares hand gesture recognition using ACC and PPG sensors, finding that PPG signals are more suitable for implementing gesture interactions on wearable devices. The research shows that PPG signals are less affected by motion noise and perform better in recognizing finger-related gestures.
IEEE SENSORS JOURNAL
(2021)
Article
Mathematical & Computational Biology
Pierre Drouin, Aymeric Stamm, Laurent Chevreuil, Vincent Graillot, Laetitia Barbin, Pierre-Antoine Gourraud, David-Axel Laplaud, Lise Bellanger
Summary: Recent approaches in gait analysis using wearable motion sensors can provide valuable tools for assessing gait impairment in the medical community. However, the complexity of motion sensor data requires the development of statistical methods to analyze and extract clinically relevant information. This study measures gait through hip rotation and presents a statistical method using time series of unit quaternions. By applying semi-supervised clustering, groups of patients with similar walking deficiencies can be formed while considering their overall disability. The study also demonstrates the effectiveness of compromise-based clustering in this context.
STATISTICS IN MEDICINE
(2023)
Article
Engineering, Electrical & Electronic
Zewei Pan, Huigang Gao, Yan Chen, Zekun Xie, Longhan Xie
Summary: Using inertial measurement units (IMUs) and plantar pressure insole sensors for gait quantitative assessment allows for objective evaluation, reduced difficulty, and decreased reliance on doctors in rehabilitation plans. Experimental results show that the wearable device has good accuracy and data repeatability for gait assessment. The linear correlation between the extracted distance score and the Mini-BES test score is -0.94. Therefore, it is feasible to use wearable devices to evaluate lower limb rehabilitation through a walking test, potentially replacing the complex Mini-BES test.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Biomedical
Jonathan Camargo, Will Flanagan, Noel Csomay-Shanklin, Bharat Kanwar, Aaron Young
Summary: This study develops and optimizes a combined locomotion mode classifier and environmental parameter estimator using machine learning and wearable sensors. The system accurately classifies ambulation modes, estimates ramp incline, stair height, and walking speed with high accuracy. Mechanical sensors play a significant role in classification, with goniometers dominating incline and height estimation, and speed estimation primarily relying on inertial measurement units.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2021)
Article
Computer Science, Information Systems
Will Carroll, Alana Turner, Purva Talegaonkar, Erin Parker, J. Carver Middleton, Preston Peranich, David Saucier, Reuben F. Burch, John E. Ball, Brian K. Smith, Harish Chander, Adam C. Knight, Charles E. Freeman
Summary: Soft robotic sensors are suitable for wearable technology, and this research evaluated the accuracy and repeatability of a newly-developed wearable prototype, demonstrating accurate joint angle estimation during complex, dynamic movements with minimal performance degradation even when wearing shoes over the sock prototype.
Article
Computer Science, Information Systems
Jia-Yan Li, Jaden Chao-Ho Lin, Kun-Ru Wu, Yu-Chee Tseng
Summary: Video prediction is improved by using wearable inertial sensors to overcome limitations in existing solutions, including ambiguity and degradation in lengthy predictions. The study creates a data set called Pedestrians with IMU (Ped-IMU) to collect the relationship between IMU and video data and proposes the SensePred model, which utilizes wearable sensor information and partial video information to predict missing video information. Simulation results confirm the effectiveness of the model.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Biomedical
Ho Chit Siu, Jennifer Sloboda, Ryan J. McKindles, Leia A. Stirling
Summary: This study presents a method of mapping joint torque estimates and sequences of torque predictions to wearable sensor data using modern neural networks. Long short-term memory neural networks outperform other types of networks in predicting future ankle torques, showing strong positive correlations with actual torques. The proposed approach relies on learning from motion capture data but can be implemented with wearable sensors for torque estimation without the need for motion capture data.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2021)
Article
Automation & Control Systems
Ashish Gupta, Hari Prabhat Gupta, Bhaskar Biswas, Tanima Dutta
Summary: Real-time information about the operational behavior of industrial or domestic appliances can be easily obtained with the availability of sensors. Sensors generate multivariate time series measurements corresponding to appliance operations, helping in identifying faults and understanding appliance behavior.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Robotics
Vishnu Dev Amara, Jorn Malzahn, Wesley Roozing, Nikos Tsagarakis
Summary: This study explores and validates two methods for enhancing the explosive motion capabilities of series elastic actuated robots during standing jumps. By combining field weakening control and energy-efficient parallel elastic actuators, a significant performance increase of up to 54% in jump height is achieved, demonstrating the effectiveness of the approach in improving the explosive capabilities of these robots.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Engineering, Mechanical
Brokoslaw Laschowski, John McPhee
Summary: Robotic leg prostheses and exoskeletons often use motor-transmission systems that do not fully utilize the passive dynamics of human locomotion, resulting in inefficient actuators. Two energy-efficient actuator design principles, series elasticity and backdrivability, are reviewed. Series elastic actuators can improve shock tolerance and reduce power consumption, but have limitations. Quasi-direct drives provide backdrivability and safe human-robot interactions, but have their own drawbacks. Designers should consider energy efficiency in daily locomotor activities beyond level-ground walking.
JOURNAL OF COMPUTATIONAL AND NONLINEAR DYNAMICS
(2023)
Article
Engineering, Biomedical
Shihao Cheng, Edgar Bolivar-Nieto, Robert D. Gregg
Summary: This research introduces an activity recognition system using signals from a thigh-mounted IMU and a force sensitive resistor to classify transitions between sitting, walking, stair ascending, and stair descending. Through real-time and offline evaluations, it was found that using Instantaneous Characteristic Features (ICFs) for activity recognition can achieve high accuracy. The study also demonstrates that simplified classification rules create a new paradigm where humans can understand machines and vice versa.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2021)
Article
Engineering, Electrical & Electronic
Luis Almeida, Vitor Santos, Joao P. Ferreira
Summary: This study presents a technique for real-time classification of floor types based on contact force data and robot inertial sensor information, achieving a classification accuracy of over 92%. Through testing different learning models and tuning parameters, a good mapping between inputs and targets is achieved, demonstrating the suitability of the proposed approach for the multi-classification problem addressed.
IEEE SENSORS JOURNAL
(2021)
Article
Mathematics
Kevin Fauvel, Tao Lin, Veronique Masson, Elisa Fromont, Alexandre Termier
Summary: This paper introduces XCM, a new compact convolutional neural network for MTS classification, which not only achieves good generalization performance on both large and small datasets, but also provides faithful explanations by precisely identifying important input data variables and timestamps.
Article
Chemistry, Analytical
Kim S. Sczuka, Marc Schneider, Alan K. Bourke, Sabato Mellone, Ngaire Kerse, Jorunn L. Helbostad, Clemens Becker, Jochen Klenk
Summary: A two-layer locomotion recognition method using inertial sensor data was proposed to identify walking, ascending and descending stairs. The results showed high sensitivity in recognizing walking but lower sensitivity in recognizing stair climbing.
Article
Engineering, Electrical & Electronic
Md Rejwanul Haque, Md Rafi Islam, Zahra Bassiri, Edward Sazonov, Dario Martelli, Xiangrong Shen
Summary: The Smart Lacelock is a shoe-mounted sensor that provides valuable information about human locomotion through reliable motion measurement and force sensing.
IEEE SENSORS JOURNAL
(2022)
Article
Orthopedics
Jordan S. Broberg, Edward M. Vasarhelyi, Brent A. Lanting, James L. Howard, Matthew G. Teeter, Douglas D. R. Naudie
Summary: The study found no significant differences in implant migration or inducible displacement between the gap balancing and measured resection surgical techniques for bicruciate-stabilized total knee arthroplasty. This indicates that both surgical techniques are safe and effective options for implanting this specific implant design.
JOURNAL OF ARTHROPLASTY
(2022)
Article
Orthopedics
Jordan S. Broberg, Douglas D. R. Naudie, Brent A. Lanting, James L. Howard, Edward M. Vasarhelyi, Matthew G. Teeter
Summary: This study compared satisfied and dissatisfied total knee arthroplasty (TKA) patients and found no differences in implant migration and objectively measured function between the two groups. However, there were kinematic differences and differences in patient-reported outcome measures (PROMs). These findings suggest that improving the functional satisfaction of TKA requires restoration of kinematics in early flexion and management of patient's pain and expectations.
JOURNAL OF ARTHROPLASTY
(2022)
Article
Orthopedics
Michael E. Neufeld, Brent A. Lanting, Michael Shehata, Douglas D. R. Naudie, Richard W. McCalden, Matthew G. Teeter, Edward M. Vasarhelyi
Summary: The prevalence of unexpected positive intraoperative cultures (UPC) in presumed aseptic revision total knee arthroplasty (TKA) was found to be 9.8%, with excellent infection-free implant survival. The infection-free survivorship from prosthetic joint infection (PJI) caused by the same UPC microorganism is outstanding.
JOURNAL OF ARTHROPLASTY
(2022)
Article
Orthopedics
Madeleine L. Van de Kleut, Xunhua Yuan, Matthew G. Teeter, George S. Athwal
Summary: This study compared BIO-RSA and metal-augmented glenoid baseplates in reverse shoulder arthroplasty in terms of clinical outcomes and baseplate migration. Results indicated that both methods provide stable initial fixation, maintained at 2 years' follow-up, with no substantial differences in clinical outcomes.
JOURNAL OF SHOULDER AND ELBOW SURGERY
(2022)
Article
Orthopedics
Madeleine L. Van de Kleut, Xunhua Yuan, George S. Athwal, Matthew G. Teeter
Summary: A study was conducted comparing clinical outcomes and implant migration between cemented standard-length and press-fit short humeral stems in reverse shoulder arthroplasty. Results showed that press-fit short stems migrated significantly more than cemented stems at 6 months, 1 year, and 2 years postoperatively, but there were no significant differences in clinical outcomes between the cohorts at 2 years.
JOURNAL OF SHOULDER AND ELBOW SURGERY
(2022)
Article
Surgery
Jennifer S. Polus, Maxwell E. Perelgut, Edward M. Vasarhelyi, Matthew G. Teeter, Brent A. Lanting
Summary: This study compared the stability and migration of different femoral stem designs in direct lateral and direct anterior total hip arthroplasty. The results showed that the direct lateral group had less femoral stem migration compared to the direct anterior group. Migration was not correlated with function or activity.
CANADIAN JOURNAL OF SURGERY
(2022)
Article
Orthopedics
Andrew Salipas, Andrew S. Poole, Matthew G. Teeter, Lyndsay E. Somerville, Douglas D. Naudie, Richard W. McCalden
Summary: This study compared the 10-year polyethylene wear rates between OxZi/XLPE and CoCr/XLPE articulations using radiostereometric analysis. The results showed no significant difference in steady-state wear rates between OxZi and CoCr, and both were below the threshold for osteolysis. The OxZi cohort demonstrated higher scores in the Harris Hip Score.
JOURNAL OF ARTHROPLASTY
(2022)
Article
Orthopedics
Jordan S. S. Broberg, Joanna Chen, Andrew Jensen, Scott A. A. Banks, Matthew G. G. Teeter
Summary: Recently, an automatic single-plane fluoroscopic method utilizing machine learning has been developed to measure the kinematics of total knee replacements (TKR) quickly and easily. The results of this study have shown that the automated technique has small errors and high reproducibility compared to the gold standard biplanar radiostereometric analysis (RSA). The advantages of this automated technique will facilitate kinematic analyses of TKR and improve efficiency in research and clinical practice.
JOURNAL OF ORTHOPAEDIC RESEARCH
(2023)
Article
Orthopedics
Jordan Kump, Matthew G. Teeter, John Matheson, Robert Klassen, Brent A. Lanting, Michael M. Decker
Summary: This study aims to determine if there is evidence of subsurface microhardness changes in retrieved HXLPE liner at the rim and articular subsurface after extended in vivo time that could be associated with oxidation and its effects on mechanical properties and implant integrity.
JOURNAL OF ORTHOPAEDIC RESEARCH
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Caleigh E. Bourdon, Zachary J. Koudys, Brent A. Lanting, C. Thomas Appleton, Jonathan D. Thiessen, Matthew G. Teeter
Summary: The segmentation-based attenuation correction (AC) approach significantly reduces the measurement error caused by PET signal attenuation from metal TKA implants.
EUROPEAN JOURNAL OF HYBRID IMAGING
(2022)
Article
Orthopedics
Jennifer S. Polus, Edward M. Vasarhelyi, Brent A. Lanting, Matthew G. Teeter
Summary: The use of screws for cup fixation in total hip arthroplasty was found to have a significant effect on cup migration. Cups fixed with only 1 screw showed greater migration compared to those with no screws or 2 screws, although the mean magnitude was still below the threshold for unacceptable migration.
Article
Orthopedics
Matthew G. Teeter, Jordan S. Broberg, James L. Howard, Brent A. Lanting
Summary: The study aimed to investigate the displacement pattern of a cementless tibial baseplate under loading one year after surgery. The results showed similar inducible displacement patterns for both stable and continuously migrating baseplates, with the greatest displacement in the anterior-posterior and lateral-medial axes. The discussion highlighted that the predominant displacement pattern for the cementless tibial baseplate during the transition from supine to standing position was axial rotation, with some subjects also displaying an anterior-posterior tilt.
JOURNAL OF ARTHROPLASTY
(2023)
Article
Engineering, Biomedical
Anastasia M. Codirenzi, Brent A. Lanting, Matthew G. Teeter
Summary: Corrosion at the modular head-neck taper interface is a concern in hip implants. The Goldberg scoring method is widely used but time-consuming. This study developed a convolutional neural network to accurately identify different corrosion levels, which can assist observers in reducing their workload.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART H-JOURNAL OF ENGINEERING IN MEDICINE
(2023)
Article
Orthopedics
Jordan S. S. Broberg, Matthew F. F. Koff, James L. L. Howard, Brent A. A. Lanting, Hollis G. G. Potter, Matthew G. G. Teeter
Summary: This study used radiography, radiostereometric analysis (RSA), and magnetic resonance imaging (MRI) to investigate the fixation of cementless total knee arthroplasty. It found that early micromotion was associated with the presence of fibrous membranes at the component-bone interface, providing important clinical significance for understanding the fixation of modern cementless TKA.
JOURNAL OF ORTHOPAEDIC RESEARCH
(2023)
Article
Orthopedics
Paul Kooner, Taran Schubert, James L. Howard, Brent A. Lanting, Matthew G. Teeter, Edward M. Vasarhelyi
Summary: The study suggests that wearable step counters have poor reliability when used with various gait aids, especially walkers. This finding should be taken into consideration in research and clinical environments when using step counters.
ORTHOPEDIC RESEARCH AND REVIEWS
(2021)