Article
Chemistry, Analytical
Bridget Schabron, Jaydip Desai, Yimesker Yihun
Summary: The study presents an adaptive controller mechanism trained by an artificial neural network using sEMG signals from the forearm to detect hand gestures and navigate an upper limb robotic exoskeleton mounted on a wheelchair based on user's intent. The trained network achieved high accuracy, allowing participants without prior experience to successfully perform tasks using the proposed mechanism.
Article
Computer Science, Artificial Intelligence
Oluwarotimi Williams Samuel, Mojisola Grace Asogbon, Yanjuan Geng, Naifu Jiang, Deogratias Mzurikwao, Yue Zheng, Kelvin K. L. Wong, Luca Vollero, Guanglin Li
Summary: A new approach utilizing spatiotemporal neuromuscular descriptor and adaptive filtering technique is proposed for optimally characterizing multiple patterns of upper extremity movements in post-stroke patients, providing inputs for intelligently driven motor training in robotic systems targeted towards stroke rehabilitation.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Kewen Li, Yongming Li
Summary: This article introduces a finite-time neural network adaptive dynamic surface control design for single-input single-output nonlinear systems. The control algorithm utilizes a novel nonlinear filter and finite-time Lyapunov stable theory to ensure tracking error convergence within a small neighborhood of origin in finite time. Simulation examples demonstrate the superiority and effectiveness of the proposed control algorithm.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Thermodynamics
Muhammed A. Hassan, Omar Abdelaziz
Summary: This study proposes an offline adaptive predictive control strategy for hybrid radiant-air systems, which improves indoor thermal environment and reduces peak electricity consumption.
APPLIED THERMAL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Shuai Ding, Jinzhu Peng, Hui Zhang, Yaonan Wang
Summary: This article proposes an event-triggered adaptive neural impedance control (ETANIC) scheme that combines impedance control (IC) and event-triggered mechanism to reduce computational burden and communication cost while ensuring stability and tracking performance of robotic systems. IC is used to achieve compliant behavior of robotic systems in response to the environment. Uncertainties of the systems are estimated using radial basis function neural network (RBFNN) and update laws are derived from a designed Lyapunov function. Stability of the closed-loop system is analyzed using Lyapunov theory and event-triggered conditions are designed to avoid Zeno behavior. Numerical and experimental results demonstrate the efficiency of the proposed ETANIC scheme in controlling robotic systems for interaction tasks with the environment compared to adaptive neural IC (ANIC).
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Naser Cheraghi, Mahmoud Miri, Mohsen Rashki
Summary: This study combines Monte Carlo simulation, artificial neural networks, and control variate techniques to improve the efficiency and accuracy of reliability analyses in engineering systems. The results show that the improved artificial neural network model using control variate techniques is superior in reducing function calls and is not sensitive to the number of hidden layer neurons.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Shixian Wen, Amanda Rios, Yunhao Ge, Laurent Itti
Summary: The human brain is a model of adaptive learning, being able to adapt to new situations and learn from experiences. A new biologically plausible deep neural network with task-dependent biasing units has been proposed to address catastrophic forgetting in continual learning of multiple tasks, achieving state-of-the-art performance across different tasks and domains.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Materials Science, Multidisciplinary
Wojciech Rzadkowski, Mikhail Lemeshko, Johan H. Mentink
Summary: This study introduces a variant of neural network states called neural coherent states, which shows excellent performance in learning the ground state of nonadditive systems. The approach is generic and has wide applications without requiring specific details of the system.
Article
Computer Science, Artificial Intelligence
Pablo P. e Silva, Wyctor F. da Rocha, Luiza E. V. N. Mazzoni, Rafhael M. de Andrade, Antonio Bento, Mariana Rampinelli, Douglas Almonfrey
Summary: This article proposes a VR system for diagnosing and rehabilitating lower limb amputees. The system utilizes a virtual environment and intelligent space to visualize and analyze gait parameters. Physiotherapists and doctors can explore the virtual environment and manage features using a head-mounted display and hand controllers. The system includes an automatic classifier to assist in assessing abnormalities in human gait.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Rohollah Moghadam, Pappa Natarajan, Sarangapani Jagannathan
Summary: This article presents an online optimal adaptive regulation method based on multilayer neural networks, which can effectively handle partially uncertain dynamics in nonlinear discrete-time systems. The actor-critic framework is used to estimate control inputs and value functions, with weights of the networks adjusted using instantaneous control input error and temporal difference. The proposed approach does not require selecting basis functions or their derivatives, and the Lyapunov method proves that the state vector, critic, and actor NN weights are bounded.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Optics
Yiheng Zhao, Peng Zou, Zhixue He, Ziwei Li, Nan Chi
Summary: This paper presents a feasible and low spatial complexity adaptive artificial neural network (AANN) post-equalization algorithm for MIMO visible light communication (VLC) systems. By reducing the spatial complexity of the post-ANN equalization algorithm to less than 10% and maintaining BER performance, a data rate of 2.1Gbps was successfully achieved in the AANN equalized 16QAM superposition coding modulation (SCM) and carrier-less amplitude-phase (CAP) single-receiver MIMO (SR-MIMO) VLC system.
Article
Computer Science, Artificial Intelligence
Wei Sun, Shuzhen Diao, Shun-Feng Su, Zong-Yao Sun
Summary: This study proposes a fixed-time tracking control scheme to address the control problem for nonlinear systems subject to actuator saturation. The scheme improves the controller performance by approximating the saturation function and introducing an auxiliary system. The effectiveness of the proposed method is demonstrated through theoretical analysis and numerical examples.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Huiyan Li, Yihao Liang, Han Gao, Li Liu, You Wang, Daqi Chen, Zhiyuan Luo, Guang Li
Summary: This article proposes a Mandarin-based Silent Speech Interface (SSI) that converts articulatory neuromuscular signals of silent speakers into audio using a hybrid framework of CNNs and Transformer. Experimental results show that the proposed method achieves an average objective CER of 10.69% in converting sEMG into audio with vocal speaker assistance.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Information Systems
Yifei Xing, Yantao Wang
Summary: This article proposes a finite-time adaptive dynamic surface control (DSC) approach for nonstrict fractional-order nonlinear systems (FONSs) with input delay. An auxiliary compensation function is used to handle the input delay problem. To address the computational complexity, a fractional-order filter is utilized to approximate the virtual controller and its fractional-order derivative in each step of the backstepping procedure. The developed finite-time adaptive DSC approach incorporates backstepping technology and neural network (NN), and introduces finite-time stability criteria based on fractional-order Lyapunov method to ensure the convergence of the tracking error within a small region around the origin. The effectiveness of the proposed control scheme is demonstrated through two examples.
Article
Computer Science, Artificial Intelligence
Xinglan Liu, Bin Xu, Yingxin Shou, Quan-Yong Fan, Yingxue Chen
Summary: This article focuses on event-based collaborative design for strict-feedback systems with uncertain nonlinearities, proposing a controller design method based on neural network weight adaptive law and updating the controller and NN weights adaptive law at triggering instants determined by a novel composite triggering threshold. By integrating state-model error, the requirements of system information and allowable range of event-triggering error are relaxed, reducing the number of triggering instants significantly while maintaining system performance. The stability of the closed-loop system is proven using the Lyapunov method at time intervals and sampling instants, with simulation results demonstrating the effectiveness of the proposed scheme.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Orthopedics
Eytan M. Debbi, Benjamin Bernfeld, Amir Herman, Moshe Salai, Yocheved Laufer, Alon Wolf
JOURNAL OF ARTHROPLASTY
(2019)
Article
Biophysics
Deborah Solomonow-Avnon, Amir Herman, Alon Wolf
JOURNAL OF BIOMECHANICS
(2019)
Article
Neurosciences
Mona Khoury-Mireb, Deborah Solomonow-Avnon, Nimrod Rozen, Alon Wolf
Article
Biophysics
Deborah Solomonow-Avnon, Amir Herman, Uriel Giwnewer, Nimrod Rozen, Avi Elbaz, Amit Mor, Alon Wolf
JOURNAL OF BIOMECHANICS
(2019)
Article
Robotics
Evgenia Virozub, Oren Wiezel, Alon Wolf, Yizhar Or
Article
Neurosciences
Arkadeb Dutta, Tidhar Lev-Ari, Ouriel Barzilay, Rotem Mairon, Alon Wolf, Ohad Ben-Shahar, Yoram Gutfreund
JOURNAL OF NEUROPHYSIOLOGY
(2020)
Article
Engineering, Biomedical
Tomer Bercovitz, Amir Herman, Deborah Solomonow-Avnon, Alon Wolf, Einat Kodesh
Summary: Running-induced fatigue alters foot strike pattern and may increase stress on joints and tissues, leading to overload injuries.
SPORTS BIOMECHANICS
(2022)
Article
Multidisciplinary Sciences
Yair Herbst, Lihi Zelnik-Manor, Alon Wolf
Article
Biology
Hadar Shaulian, Amit Gefen, Deborah Solomonow-Avnon, Alon Wolf
Summary: This study developed a novel method to analyze the mechanical loading on the human heel under different offloading footwear configurations, identifying two effective combinations of offloading parameters. The method has the potential to optimize the development of offloading solutions and revolutionize prevention and treatment of diabetic ulcers.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Clinical Neurology
Benjamin N. Groisser, Howard J. Hillstrom, Ankush Thakur, Kyle W. Morse, Matthew Cunningham, M. Timothy Hresko, Ron Kimmel, Alon Wolf, Roger F. Widmann
Summary: This study introduces a novel surface-topographic scanning system capable of automatically generating objective measurements to characterize torso shape. The system shows high reliability in measuring trunk alignment parameters and offers an objective description of torso shape.
Article
Biophysics
Hadar Shaulian, Amit Gefen, Deborah Solomonow-Avnon, Alon Wolf
Summary: This study proposes a novel graded-stiffness offloading method for preventing and treating diabetic heel ulcers. The method involves using heel support with multi-increasing levels of stiffness materials. The study shows that this offloading solution is more effective than existing solutions in reducing heel internal loads.
BIOMECHANICS AND MODELING IN MECHANOBIOLOGY
(2022)
Article
Neurosciences
Hadar Shaulian, Amit Gefen, Hen Biton, Alon Wolf
Summary: This study investigates a novel graded-stiffness offloading method for diabetic heel ulcers, which can effectively redistribute heel pressure and reduce focal stress concentration areas. The results show that the graded-stiffness offloading solution is more effective in reducing and redistributing peak pressure and pressure dose compared to existing solutions.
Article
Clinical Neurology
Ankush Thakur, Benjamin Groisser, Howard J. Hillstrom, Matthew E. Cunningham, M. Timothy Hresko, Hila Otremski, Kyle W. Morse, Kira Page, Caroline Gmelich, Ron Kimmel, Alon Wolf, Roger F. Widmann, Jessica H. Heyer
Summary: The purpose of this study was to investigate the relationship between objective surface topographic measurements of the torso and subjective patient self-perception. The results showed that back surface rotation, waist crease vertical asymmetry, and rib prominence volume were the most predictive factors for TAPS. Back surface rotation, silhouette centroid deviation, and shoulder normal asymmetry were the most predictive factors for SRS-22r self-image.
Proceedings Paper
Engineering, Biomedical
Yair Herbst, Derick Sivakumaran, Yoav Medan, Alon Wolf
Summary: This paper introduces a low-cost, 3D printed, motorized prosthetic hand design with a sensory feedback interface, which can improve the quality of life for children without an upper limb.
2022 9TH IEEE RAS/EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL ROBOTICS AND BIOMECHATRONICS (BIOROB 2022)
(2022)
Article
Rheumatology
Aviv Kramer, Raviv Allon, Alon Wolf, Tal Kalaiman, Idit Lavi, Ronit Wollstein
CURRENT RHEUMATOLOGY REVIEWS
(2019)