Yinlai Jiang

ORCID: 0000-0002-0825-6444
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Muscle activation and electromyography studies
  • Neuroscience and Neural Engineering
  • EEG and Brain-Computer Interfaces
  • Robot Manipulation and Learning
  • Prosthetics and Rehabilitation Robotics
  • Advanced Sensor and Energy Harvesting Materials
  • Hand Gesture Recognition Systems
  • Soft Robotics and Applications
  • Tactile and Sensory Interactions
  • Motor Control and Adaptation
  • Gaze Tracking and Assistive Technology
  • Robotic Locomotion and Control
  • Gait Recognition and Analysis
  • Stroke Rehabilitation and Recovery
  • Human Pose and Action Recognition
  • Balance, Gait, and Falls Prevention
  • Teleoperation and Haptic Systems
  • Optical Imaging and Spectroscopy Techniques
  • Visual perception and processing mechanisms
  • Robotic Mechanisms and Dynamics
  • Assistive Technology in Communication and Mobility
  • Robotics and Sensor-Based Localization
  • Evacuation and Crowd Dynamics
  • Advanced Memory and Neural Computing
  • Time Series Analysis and Forecasting

University of Electro-Communications
2016-2025

Zhengzhou University
2024

Beijing Advanced Sciences and Innovation Center
2018-2022

Beijing Institute of Technology
2020-2021

Facing Our Risk of Cancer Empowered
2021

Inspire
2015-2019

Shenyang Institute of Automation
2018

Chinese Academy of Sciences
2018

Children's Hospital of Zhejiang University
2017

Kochi University of Technology
2006-2014

In this paper, we develop a prosthetic bionic hand system to realize adaptive gripping with two closed-loop control loops by using linear discriminant analysis algorithm (LDA). The contains five fingers and each finger is driven servo motor. When grasping objects, four except the thumb would adjust automatically bend an appropriate gesture, while stretched bent Since change of surface electromechanical signal (sEMG) occurs before human movement, recognition sEMG LDA can help obtain people’s...

10.3390/mi13020219 article EN cc-by Micromachines 2022-01-29

The activities of muscles in the forearm have been widely investigated to develop human interfaces involving hand motions, especially fields prosthetic hands and teleoperation. Although surface electromyography (sEMG) is considered as an effective biological signal from which motions can be recognized, availability quality sEMG data limit usability intuitiveness interfaces. This article introduces force myography (FMG) a supplementary proposes layered sEMG–FMG hybrid sensor that measure both...

10.1109/thms.2023.3287594 article EN cc-by IEEE Transactions on Human-Machine Systems 2023-07-10

Crack Segmentation in industrial concrete surfaces is a challenging task because cracks usually exhibit intricate morphology with slender appearances. Traditional segmentation methods often struggle to accurately locate such cracks, leading inefficiencies maintenance and repair processes. In this paper, we propose novel diffusion-based model cross-conditional encoder-decoder, named CrossDiff, which the first introduce diffusion probabilistic for crack task. Specifically, CrossDiff integrates...

10.48550/arxiv.2501.12860 preprint EN arXiv (Cornell University) 2025-01-22

One of the greatest challenges using a myoelectric prosthetic hand in daily life is to conveniently measure stable signals. This study proposes novel surface electromyography (sEMG) sensor polypyrrole-coated nonwoven fabric sheet as electrodes (PPy electrodes) allow people with disabilities control limbs. The PPy are sewn on an elastic band guarantee close contact skin and thus reduce electrical impedance between skin. highly customizable fit size shape stump so that can attach by...

10.3389/fnins.2017.00033 article EN cc-by Frontiers in Neuroscience 2017-02-06

Faced with the increasingly severe global aging population fewer children, research, development, and application of elderly-care robots are expected to provide some technical means solve problems elderly care, disability semi-disability nursing, rehabilitation. Elderly-care involve biomechanics, computer science, automatic control, ethics, other fields knowledge, which is one most challenging concerned research robotics. Unlike robots, work for frail elderly. There information exchange...

10.3389/fnins.2023.1291682 article EN cc-by Frontiers in Neuroscience 2023-11-30

The usability of a prosthetic hand differs significantly from that real hand. Moreover, the complexity manipulation increases as number degrees freedom to be controlled increases, making with biological signals extremely difficult. To overcome this problem, users need select grasping posture is adaptive object and stable method prevents falling. In previous studies, these have been left operating skills user, which difficult achieve. study, we demonstrate how can achieved according...

10.34133/2022/9861875 article EN cc-by Cyborg and Bionic Systems 2022-01-01

The electromyography(EMG) signal is the biocurrent associated with muscle contraction and can be used as input to a myoelectric intelligent bionic hand control different gestures of hand. Increasing number myoelectric-signal channels yield richer information motion intention improve accuracy gesture recognition. However, acquisition increases, its effect on improvement recognition gradually diminishes, resulting in reaching plateau. To address these problems, this paper presents proposed...

10.34133/cbsystems.0066 article EN cc-by Cyborg and Bionic Systems 2023-10-09

Millions of physical disabilities, who have lost a hand or both hands, are in need prosthetic hands not only for decoration but also the functions to help them with basic daily activities. Although EMG being extensively studied satisfy this need, most too expensive be economically available, difficult operate and maintain by user him/herself, over heavy longtime wearing. The aim study is therefore develop simplified (sim-EMGPH) solve these problems. sim-EMGPH consists five parts: lightweight...

10.1109/robio.2014.7090524 article EN 2021 IEEE International Conference on Robotics and Biomimetics (ROBIO) 2014-12-01

The knowledge remembered by the human body and reflected dexterity of motion is called embodied knowledge. In this paper, we propose a new method using singular value decomposition for extracting from time-series data motion. We compose matrix use left vectors as patterns values scalar, which each corresponding vector affects matrix. Two experiments were conducted to validate method. One gesture recognition experiment in categorize motions two kinds models with indexes similarity estimation...

10.1109/tkde.2014.2316521 article EN other-oa IEEE Transactions on Knowledge and Data Engineering 2014-04-10

This article proposes coupled tendon-driven joint modules for anthropomorphic robots. Fully actuated 2-degree-of-freedom (DoF) and 3-DoF are classified analyzed based on the motor-joint routing matrix that describes tendon structure between motors joints. Two-motor 2-DoF (2M2D) modules, which share same form of matrix, into four types: externally actuated, internally coaxially separately hybrid-actuated according to location motors. Three-motor (3M3D) forms possible matrix: fully routed...

10.1109/tro.2020.3038687 article EN publisher-specific-oa IEEE Transactions on Robotics 2020-12-05

Abstract To achieve robust sEMG measurements in an EMG prosthetic system, this study proposes a surface electromyogram (sEMG) sensor with novel electrode structure composed of two-layered conductive silicone different carbon concentrations. We hypothesized there is optimal concentration for achieving large amplitude robustness to external perturbation, and we empirically determined concentration. produced fourteen sets electrodes, the weight ratio ranging from 1.7% 4.0%. Using these user...

10.1038/s41598-019-50112-4 article EN cc-by Scientific Reports 2019-09-30

Most prosthetic hands adopt an under-actuated mechanism to achieve dexterous motion performance with a lightweight and anthropomorphic design. Many have been verified in laboratories, some already commercialized. However, trade-off exists between the dexterity light weight of such hands. In general, current commercially available usually consider one aspect at expense other, as obtaining diversiform hand motions but increased weight, or achieving design limited functions. This study attempts...

10.3390/app9204203 article EN cc-by Applied Sciences 2019-10-09

Estimating muscle force by surface electromyography(sEMG) is a noninvasive and flexible way of diagnosing biomechanical diseases controlling assistive devices, e.g. prosthetic hands. To estimate sEMG, supervised method usually adopted, which requires the simultaneous recording sEMG measured extra devices to tune variables. However, lost limbs amputees challenging, limits application method. Though unsupervised does not need record force, it suffers from low accuracy due lack recorded as...

10.3389/fnbot.2018.00020 article EN cc-by Frontiers in Neurorobotics 2018-05-04

A newly brain computer interaction (BCI) system which combined electrooculography (EOG) with electroencephalography (EEG) was designed and realized to make prosthesis control multicontrol commands come true. Based on two different imaginary tasks, time-frequency spectrum topographic mapping were used analyze validate event related synchronization/desychronization (ERS/ERD). Obviously frequency band of EEG is chosen based common spatial pattern (CSP) algorithm, then support vector machine...

10.1109/icinfa.2016.7832013 article EN 2016-08-01

Abstract The authors propose a multifunctional intelligent bed (MIB) that integrates multiple modes of interaction to improve the welfare mobility‐impaired users and reduce workload medical personnel. MIB features independent autonomous omnidirectional movement, position adjustment, multi‐degree‐of‐freedom (DOF) movement regulation posture memory functions facilitate comfortable convenient for users. In particular, an integrated “MIB‐state perception‐interaction interfaces” system is...

10.1049/csy2.12097 article EN cc-by IET Cyber-Systems and Robotics 2023-09-01

Myoelectric prosthesis has become an important aid to disabled people. Although it can help people recover a nearly normal life, whether they adapt severe working conditions is subject that yet be studied. Generally speaking, the environment dominated by vibration. This paper takes gripping action as its research object, and focuses on identification of grasping intentions under different vibration frequencies in conditions. In this way, possibility who wear myoelectric work various paper,...

10.3390/s21186234 article EN cc-by Sensors 2021-09-17

EMG prosthetic hands are being extensively studied to meet with the need of millions physical disabilities who have lost a hand or both hands. But for most existing multi-degree freedom hands, shortcomings such as low intensity, high price, et al., blocked them from practical realization. Low-degree performance is therefore desired solve these problems. The aim this study optimize low-freedom degree based on utilization rate human hand's joints in daily life. We used two motors realize...

10.1109/bmei.2014.7002838 article EN 2014-10-01

Deep learning gesture recognition based on surface electromyography (sEMG) is playing an increasingly important role in prosthetic hand control. In order to improve the rate of multi-modal EMG signals, this paper proposes a feature model construction and optimization method multi-channel signal amplification unit. And through CNN LSTM (CNN+LSTM) deep model, acquisition window are trained. Use established time series image construct solve problem signal. The experimental results show that...

10.1109/isr50024.2021.9419532 article EN 2021-03-04

There are millions of people who have lost a hand or both hands due to acquired amputation congenital limb deficiencies. In order improve their quality life, electromyogram (EMG) prosthetic been developed compensate for some daily activities which cosmetic glove cannot do. However, most EMG pursue the ability motions by multi-degree freedom mechanisms that lead shortcomings, such as low intensity, high cost, overweight, and maintenance difficulties at same time. The development low-degree...

10.1109/bmei.2014.7002837 article EN 2014-10-01

Mixed reality device sensing capabilities are valuable for robots, example, the inertial measurement unit (IMU) sensor and time-of-flight (TOF) depth can support robot in navigating its environment. This paper demonstrates a deep learning (YOLO model) background, realtime object detection system implemented on mixed device. The goal of is to create real-time communication between HoloLens Ubuntu systems enable using YOLO model. experimental results show that proposed method has fast speed...

10.1109/lifetech52111.2021.9391811 article EN 2021 IEEE 3rd Global Conference on Life Sciences and Technologies (LifeTech) 2021-03-09
Coming Soon ...