RLRuichen Liu

Ruichen Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ruichen Liu has a total of 31 co-authors. Here are the top co-authors by number of shared publications:

  • Xin Shi

    Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian, China

    7 shared publications
  • Zhelong Wang

    Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian, China

    7 shared publications
  • Hongyu Zhao

    Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian, China

    6 shared publications
  • Sen Qiu

    School of Control Science and Engineering, Dalian University of Technology, Dalian, China

    6 shared publications
  • Fang Lin

    Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of the Ministry of Education and the School of Control Science and Engineering, Dalian University of Technology, Dalian, China

    4 shared publications
  • Cui Wang

    Department of Neurology, Dalian Municipal Central Hospital, Dalian University of Technology, Dalian, Liaoning, China

    3 shared publications

Latest Publications

  • Perioperative Gait Analysis of Patients With Cervical Spondylotic Myelopathy Using Inertial Sensors

    by Xin Shi, Zhelong Wang, Cui Qin, Hongyu Zhao, Ruichen Liu, Fang Lin, Kai Tang

    Cervical spondylotic myelopathy (CSM) is a progressive spinal disorder often associated with subtle yet clinically relevant gait impairments. Accurate gait evaluation during the perioperative period remains challenging due to the limitations of coarse clinical rating scales. This study employs a wearable gait analysis framework using foot-mounted inertial measurement units (IMUs) to extract spatiotemporal gait parameters with high precision, validated in an optical lab with relative errors of 2.4% for stride length (SL) and 5.5% for maximum foot clearance (MFC). A dataset of healthy controls and CSM patients was collected, and bilateral gait features were analyzed across pre- and postoperative stages. To enhance evaluation sensitivity, we introduce a Robust Gait Normalcy Index (RINI) based on the extracted gait features and robust principal component analysis (RPCA). RINI demonstrated a greater mean change in the Nurick improvement group with 1.72 and a stable change in the unchanged group with 0.36, outperforming other indices. These results suggest that RINI enables fine-grained and robust gait evaluation for CSM patients in the perioperative period.

  • Fine-Grained Assessment of Upper-Limb Bradykinesia Through Multimodal Feature Enhancement and Deep Learning

    by Fang Lin, Zhelong Wang, Zhenglin Li, Hongyu Zhao, Xin Shi, Ruichen Liu, Jiaxi Li, Daoyong Peng, Bo Ru

    Bradykinesia is a hallmark symptom of Parkinson’s disease (PD) that significantly affects patients’ functional abilities and quality of life. This study proposed a fine-grained classification method for evaluating the level of bradykinesia in PD patients. Based on inertial signals, surface electromyographic (sEMG) signals, and videos obtained from 40 PD patients and 13 healthy subjects, the proposed data preprocessing method extracts 69-D features from inertial and sEMG (IE) signals, and 7-D skeleton features from videos. A two-stream network, including IE stream, skeleton stream, and decision fusion module, was developed using long short-term memory, full convolutional neural networks, and fully connected neural networks. In addition, the IE stream incorporated a feature shrinking module to process high-dimensional features to reduce redundant features. Furthermore, an LSTM-variational autoencoders method was proposed for data augmentation of categories with fewer samples. The proposed method achieved higher recognition rates (pro/supination movements of hands: 85.51%, finger tapping: 88.06%, hand movements: 90.00%) compared to other methods. With low-cost, compact and lightweight methods, bradykinesia in PD patients can be intelligently assessed, which will enhance patient management and treatment efficiency.


  • Open Access

    Result Prediction of Wordle Word Guessing Game Based on SVM And BP Neural Network Multi-Input-Multi-Output Regression Prediction Model

    by Ruichen Liu, Yinxi Li, Mengdan Li

    Wordle is a popular daily puzzle game in which players can guess a five-letter word in six or fewer attempts. In order to predict the distribution column of user participation and guessing results, this paper established a support vector machine (SVM) regression model based on the historical data set of game results to predict the number of reports on March 1, 2023. Then, by extracting attribute features such as word frequency from words, the relationship between word attribute and report quantity under difficult mode is studied through multiple regression analysis and correlation coefficient analysis. Finally, a BP neural network multi-input-multi-output regression prediction model was established. The goodness of fit (R) of the model was 0.93671, and the distribution of correct guesses of the word "EERIE" was predicted. Through this regulation, the popularity of the game can be maintained to some extent, so that the number of people playing the game can maintain stability or growth.

  • Hand Movement Recognition and Salient Tremor Feature Extraction With Wearable Devices in Parkinson’s Patients

    by Fang Lin, Zhelong Wang, Hongyu Zhao, Sen Qiu, Ruichen Liu, Xin Shi, Cui Wang, Wenchao Yin

    Tremor is one of the earliest signs of Parkinson’s disease (PD), which seriously disrupts patients’ daily lives. It is important to study upper limb tremors quantitatively to control PD progression. In this study, surface electromyography (sEMG) signals from wearable devices are used to recognize rest, posture, and kinetic tremor action from 6 upper-limb clinical actions and to quantify features of tremors. A multivariable time series classification model (MTSCM) based on fully convolutional networks and a long short-term memory network is proposed to recognize tremor actions. MTSCM achieves a high degree of accuracy both on the left-hand and right-hand data sets for tremor actions. An improved Hilbert-Huang transform (HHT) method is proposed to decompose the inertial signals of tremor actions to obtain tremor components. Using the improved HHT, tremor and motion components can be decomposed effectively. In addition, 53 features are extracted from inertial and sEMG signals, and a canonical correlation analysis is used to determine the correlation between features and MDS-UPDRS scores. Several of the relevant characteristics are related to MDS-UPDRS scores, notably the dominant frequency and amplitude of the tremor component are significantly correlated (p < 0.01) with tremor scores. Detecting upper-limb clinical tremors in PD patients using wearable sensors is feasible according to our findings.


  • Threshold-Free Phase Segmentation and Zero Velocity Detection for Gait Analysis Using Foot-Mounted Inertial Sensors

    by Xin Shi, Zhelong Wang, Hongyu Zhao, Sen Qiu, Ruichen Liu, Fang Lin, Kai Tang

    Gait analysis is a prosperous tool for the clinical evaluation and diagnosis. In this article, a portable gait analysis system based on foot-mounted inertial sensors is established. A threshold-free method using a long short-term memory recurrent neural network is constructed to segment four typical gait phases in a gait sequence for the temporal parameters analysis. Segmentation accuracy reaches over 95% across recruited subjects with distinct gait patterns, which is significantly superior when compared with traditional machine learning methods. The zero-velocity indicator is generated successively according to the segmented sequence to accomplish zero velocity update for the spatial parameter calculation. The accuracy of the proposed system is also validated through the OptiTrack in the lab. The comparison result of the stride length shows that the error between the two systems is less than 2%, which demonstrates that our system can satisfy the demand in the clinical.


  • Open Access

    Advances in traditional Chinese medicine as adjuvant therapy for diabetic foot

    by Fa-Shun Liu, Yue Li, Xian-Shan Guo, Rui-Chen Liu, Hong-Ya Zhang, Zhen Li

    Advances in traditional Chinese medicine as adjuvant therapy for diabetic foot


  • Quantitative Analysis of Lower Limb Motion in Parkinson’s Disease Based on Inertial Sensors

    by Ruichen Liu, Zhelong Wang, Hongyu Zhao, Sen Qiu, Cui Wang, Xin Shi, Fang Lin

    This study proposed a wearable inertial motion capture method for Parkinson’s lower limb motion reconstruction and analysis. To eliminate the error accumulation caused by sensor noise, the error state Kalman filter is used for attitude estimation. The inertial motion capture method proposed in this study is compared with OptiTrack system to verify the motion tracking effect. The accuracy of different phase detection methods is compared, and the highest recognition accuracy is 99.11% using long short-term memory method. In addition, this study collected subjects in healthy control, Parkinson’s disease and freezing of gait groups for comparative analysis. The experimental results revealed differences in motion characteristics and kinematics between Parkinson’s disease and healthy subjects. Thus, the quantitative analysis results can be used as an important reference for the clinical application of Parkinson’s disease.


  • A Wearable Gait Analysis and Recognition Method for Parkinson’s Disease Based on Error State Kalman Filter

    by Ruichen Liu, Zhelong Wang, Sen Qiu, Hongyu Zhao, Cui Wang, Xin Shi, Fang Lin

    For the purpose of quantitative analysis, this paper proposes a wearable gait analysis method for Parkinson’s disease (PD) to evaluates the motor ability. The error state Kalman filter (ESKF) is used for attitude estimation, and the gait parameters are modified by phase segmentation and zero velocity update (ZUPT) algorithm. In addition, this study uses gait parameters as classifier features to recognize abnormal gait, and compares the recognition effect with statistical features. The effect of our gait system is verified by comparison with the OptiTrack system, and the mean absolute error (MAE) of step length and foot clearance are 2.52 $\pm$ 3.61 cm and 0.96 $\pm$ 1.24 cm respectively. Forty Parkinson’s patients and forty age-matched healthy people are recruited for gait comparison, the analysis results showed significant differences between the two groups. The abnormal gait recognition results show that gait features have stronger generalization ability than statistical features in leave-one-subject-out (LOSO) validation. The method proposed in this study can be applied to the gait analysis and objective evaluation of PD.


  • Top Cited Papers

    Multi-sensor information fusion based on machine learning for real applications in human activity recognition: State-of-the-art and research challenges

    by Sen Qiu, Hongkai Zhao, Nan Jiang, Zhelong Wang, Long Liu, Yi An, Hongyu Zhao, Xin Miao, Ruichen Liu, Giancarlo Fortino


  • Motion Analysis of Deadlift for Trainers With Different Levels Based on Body Sensor Network

    by Zhelong Wang, Ruichen Liu, Hongyu Zhao, Sen Qiu, Xin Shi, Jiaxin Wang, Jie Li

    Deadlift is one of the most common weight training exercises that can help build waist muscles. However, many trainers with less experience may not receive the expected effect or even damage themselves. To exercise in a healthier way, a portable and quantifiable deadlift evaluation system is proposed in this article. The system employs a body sensor network (BSN), including the inertial and surface electromyography (sEMG) information, to reconstruct the human motion and segment the deadlift into certain phases to realize the detailed analysis. A two-step extended Kalman filter (EKF) that can reduce the magnetic interference is presented to estimate the attitude and the accuracy of the method is validated by the OptiTrack system. We also carry out the kinematic and sEMG analysis among trainers with different levels. The experiment results reveal that our system can significantly discriminate the technical differences for those trainers, which demonstrated that the system can provide valuable information for the deadlift training.