Top Read Articles

    Published in last 1 year |  In last 2 years |  In last 3 years |  All
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Eye Robotic System for Vitreoretinal Surgery
    DAI Qianlin (代倩琳), XU Mengqiao (徐梦乔), SUN Xiaodong (孙晓东), XIE Le∗ (谢叻)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 1-6.   DOI: 10.1007/s12204-021-2369-2
    Abstract279)      PDF (1040KB)(228)      
    Micro incision vitrectomy system (MIVS) is considered to be one of the most difficult tasks of eye surgery, due to its requirements of high accuracy and delicate operation under blurred vision environment. Therefore, robot-assisted ophthalmic surgery is a potential and efficient solution. Based on that consideration, a novel master-slave system for vitreoretinal surgery is realized. A 4-DOF remote center of motion (RCM) mechanism with a novel linear stage and end-effector is designed and the master-slave control system is implemented. The forward and inverse kinematics are analyzed for the controller implementation. Then, algorithms with motion scaling are also integrated into the control architecture for the purpose to enhance the surgeon’s operation accuracy. Finally, experiments on an eye model are conducted. The results show that the eye robotic system can fulfill surgeon’s motion following and simulate operation of vitrectomy, demonstrating the feasibility of this system.
    Reference | Related Articles | Metrics
    Sealing Performance of Pressure-Adaptive Seal
    LI Yuanfeng (李元丰), WANG Yiling (王怡灵), ZHANG Wanxin∗ (张万欣), LIU Jinian (刘冀念), MA Jialu (马加炉)
    J Shanghai Jiaotong Univ Sci    2022, 27 (6): 747-756.   DOI: 10.1007/s12204-022-2510-x
    Abstract217)      PDF (2268KB)(75)      
    A pressure-adaptive seal is developed to meet the demands of quick assembling and disassembling for an individual protection equipment in aerospace. The analysis model, which reflects the main characteristics of the seal structure, is built based on the finite element method and the Roth’s theory of rubber seal, and verified by the prototype test. The influences of precompression ratio, hardness of the sealing ring rubber, and friction coefficient on the sealing performance are investigated by variable parameter method. Results show that the model can describe the essential characteristics of the pressure-adaptive seal structure, which has good follow-up to the cavity pressure to achieve the purpose of pressure self-adaptive. The leakage rate correlates negatively with the precompression ratio of the sealing ring and the hardness of the sealing ring material, while is positively related to the friction coefficient between the sealing ring and the sealing edge. The maximum contact stress on sealing surface has negative correlation with the precompression ratio of the sealing ring, and positive correlation with the hardness of the seal ring material. The damage risk of the sealing ring increases with the increases of the precompression ratio of sealing ring, hardness of sealing ring material, and friction coefficient.
    Reference | Related Articles | Metrics
    Advances in Medicine-Engineering Crossover in Automated Anesthesia
    XU Tianyi (徐天意), XIA Ming (夏明), JIANG Hong (姜虹)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 137-143.   DOI: 10.1007/s12204-021-2329-x
    Abstract203)      PDF (156KB)(83)      
    Medicine-engineering crossover refers to the cross-fertilization of multiple disciplines to meet clinical needs through various means, including engineering, which greatly promotes medical development. In the development of anesthesiology, improvements in anesthesia equipment and continuous innovation of anesthesia technology are all closely related to the integration of medicine and engineering. In recent years, the exploration and development of automated anesthesia equipment has led to closer integration of medicine, engineering, and other disciplines, including the development of robots in anesthesia, automated monitoring and alarm technology,automated perioperative management, and remote anesthesia. Herein, the current status of applications and development of medicine-engineering crossover in the field of automated anesthesia are discussed.
    Reference | Related Articles | Metrics
    Development of a Robotic Cochlear Implantation System
    CHEN Ziyun (陈子云), XIE Le (谢叻), DAI Peidong (戴培东), ZHANG Tianyu (张天宇)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 7-14.   DOI: 10.1007/s12204-021-2381-6
    Abstract195)      PDF (1384KB)(68)      
    Traditional cochlear implantation surgery has problems such as high surgical accuracy requirement and large trauma, which cause the difficulty of the operation and the high requirements for doctors, so that only a few doctors can complete the operation independently. However, there is no research on robotic cochlear implantation in China. In response to this problem, a robotic cochlear implantation system is proposed. The robot is controlled by robot operating system (ROS). A simulation environment for the overall surgery is established on the ROS based on the real surgery environment. Through the analysis of the kinematics and the motion planning algorithm of the manipulator, an appropriate motion mode is designed to control the motion of the manipulator, and perform the surgery under the simulation environment. A simple and feasible method of navigation is proposed, and through the model experiment, the feasibility of robotic cochlear implantation surgery is verified.
    Reference | Related Articles | Metrics
    Teleoperated Puncture Robot System: Preliminary Design and Workspace Analysis
    HU Bo (胡博), LIN Yanping∗ (林艳萍), CHEN Shihang (陈士行), WANG Fang (汪方), MA Xiaojun (马小军), CAO Qixin (曹其新)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 15-23.   DOI: 10.1007/s12204-021-2368-3
    Abstract168)      PDF (1455KB)(53)      
    Radiofrequency ablation (RFA) guided by X-ray images aims to relieve herniated disc pain with minimal invasiveness and fast recovery. It requires an accurate and fast positioning of the puncture needle. We propose a teleoperated robotic system for percutaneous puncture to support RFA. We report the kinematics modelling and workspace analysis of the proposed system, which comprises preliminary and accurate positioning mechanisms. Preliminary positioning mechanism automatically drives the needle to the puncture area, and accurate positioning is then achieved by teleoperation under the guidance of X-ray images. We calculate the teleoperation workspace of the robot system using a spatial search algorithm and quantitatively analyze the optimal structural parameters aiming to maximize the workspace. The workspace of the proposed robot system complies with clinical requirements to support RFA.
    Reference | Related Articles | Metrics
    Dynamic Obstacle Avoidance for Application of Human-Robot Cooperative Dispensing Medicines
    WANG Zheng (王正), XU Hui (许辉), L v Na (吕娜), TAO Wei∗ (陶卫), CHEN Guodong (陈国栋), CHI Wenzheng (迟文正), SUN Lining (孙立宁)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 24-35.   DOI: 10.1007/s12204-021-2366-5
    Abstract167)      PDF (2378KB)(44)      
    For safety reasons, in the automated dispensing medicines process, robots and humans cooperate to accomplish the task of drug sorting and distribution. In this dynamic unstructured environment, such as a humanrobot collaboration scenario, the safety of human, robot, and equipment in the environment is paramount. In this work, a practical and effective robot motion planning method is proposed for dynamic unstructured environments. To figure out the problems of blind zones of single depth sensor and dynamic obstacle avoidance, we first propose a method for establishing offline mapping and online fusion of multi-sensor depth images and 3D grids of the robot workspace, which is used to determine the occupation states of the 3D grids occluded by robots and obstacles and to conduct real-time estimation of the minimum distance between the robot and obstacles. Then, based on the reactive control method, the attractive and repulsive forces are calculated and transformed into robot joint velocities to avoid obstacles in real time. Finally, the robot’s dynamic obstacle avoidance ability is evaluated on an experimental platform with a UR5 robot and two KinectV2 RGB-D sensors, and the effectiveness of the proposed method is verified.
    Reference | Related Articles | Metrics
    COVID-19 Interpretable Diagnosis Algorithm Based on a Small Number of Chest X-Ray Samples
    BU Ran (卜冉), XIANG Wei∗ (向伟), CAO Shitong (曹世同)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 81-89.   DOI: 10.1007/s12204-021-2393-2
    Abstract164)      PDF (1470KB)(108)      
    The COVID-19 medical diagnosis method based on individual’s chest X-ray (CXR) is achieved difficultly in the initial research, owing to difficulties in identifying CXR data of COVID-19 individuals. At the beginning of the study, infected individuals’ CXRs were scarce. The combination of artificial intelligence (AI) and medical diagnosis has been advanced and popular. To solve the difficulties, the interpretability analysis of AI model was used to explore the pathological characteristics of CXR samples infected with COVID-19 and assist in medical diagnosis. The dataset was expanded by data augmentation to avoid overfitting. Transfer learning was used to test different pre-trained models and the unique output layers were designed to complete the model training with few samples. In this study, the output results of four pre-trained models in three different output layers were compared, and the results after data augmentation were compared with the results of the original dataset. The control variable method was used to conduct independent tests of 24 groups. Finally, 99.23% accuracy and 98% recall rate were obtained, and the visual results of CXR interpretability analysis were displayed. The network of COVID-19 interpretable diagnosis algorithm has the characteristics of high generalization and lightweight. It can be quickly applied to other urgent tasks with insufficient experimental data. At the same time, interpretability analysis brings new possibilities for medical diagnosis.
    Reference | Related Articles | Metrics
    Application of Digital Medicine in Addiction
    WU Xiaojun (吴萧俊), DU Jiang (杜江), JIANG Haifeng (江海峰), ZHAO Min (赵敏)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 144-152.   DOI: 10.1007/s12204-021-2391-4
    Abstract154)      PDF (185KB)(69)      
    Digital medicine plays an important role in disease assessment, psychological intervention, and relapse management in mental illnesses. Patients with substance use disorders can be easily affected by the environment and negative emotions, inducing addiction and relapse. However, due to social discrimination, stigma, or economic issues, they are unwilling to go to the hospital for treatment, making it difficult for health workers to track their health changes. Additionally, mental health resources in China are insufficient. Digital medicine aims to solve these problems. This article reviews digital medicine in the field of addiction, hoping to provide a reference for the future exploration of more individualized and effective digital medicine.
    Reference | Related Articles | Metrics
    Safety Protection Method of Rehabilitation Robot Based on fNIRS and RGB-D Information Fusion
    LI Dong (李栋), FAN Yulin (樊钰琳), L v Na (吕娜), CHEN Guodong∗ (陈国栋), WANG Zheng (王正), CHI Wenzheng (迟文政)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 45-54.   DOI: 10.1007/s12204-021-2365-6
    Abstract153)      PDF (2503KB)(35)      
    In order to improve the safety protection performance of the rehabilitation robot, an active safety protection method is proposed in the rehabilitation scene. The oxyhemoglobin concentration information and RGB-D information are combined in this method, which aims to realize the comprehensive monitoring of the invasion target, the patient’s brain function movement state, and the joint angle in the rehabilitation scene. The main focus is to study the fusion method of the oxyhemoglobin concentration information and RGB-D information in the rehabilitation scene. Frequency analysis of brain functional connectivity coefficient was used to distinguish the basic motion states. The human skeleton recognition algorithm was used to realize the angle monitoring of the upper limb joint combined with the depth information. Compared with speed and separation monitoring, the protection method of multi-information fusion is safer and more comprehensive for stroke patients. By building the active safety protection platform of the upper limb rehabilitation robot, the performance of the system in different safety states is tested, and the safety protection performance of the method in the upper limb rehabilitation scene is verified.
    Reference | Related Articles | Metrics
    Depth Camera-Based Robot-Assisted Ultrasonic Lipolysis System
    YAN Minpeng (严旻芃), CHAI Gang ∗ (柴岗), XIE Le ∗ (谢叻)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 36-44.   DOI: 10.1007/s12204-021-2343-z
    Abstract152)      PDF (1756KB)(20)      
    With many advantages such as non-invasive, safe and quick effect, focused ultrasound lipolysis stands out among many fat-removing methods. However, during the whole process, the doctor needs to hold the ultrasound transducer and press it on the patient’s skin with a large pressure for a long time; thus the probability of muscle and bone damage for doctors is greatly increased. To reduce the occurrence of doctors’ occupational diseases, a depth camera-based ultrasonic lipolysis robot system is proposed to realize robot-assisted automatic ultrasonic lipolysis operation. The system is composed of RealSense depth camera, KUKA LBR Med seven-axis robotic arm, PC host, and ultrasonic lipolysis instrument. The whole operation includes two parts: preoperative planning and intraoperative operation. In preoperative planning, the treatment area is selected in the camera image by the doctor; then the system automatically plans uniformly distributed treatment points in the treatment area. At the same time, the skin normal vector is calculated to determine the end posture of the robot, so that the ultrasound transducer can be pressed down in the normal direction of skin. During the intraoperative operation, the robot is controlled to arrive at the treatment point in turn. Meanwhile, the patient’s movement can be detected by the depth camera, and the path of robot is adjusted in real time so that the robot can track the movement of patient, thereby ensuring the accuracy of the ultrasonic lipolysis operation. Finally, the human body model experiment is conducted. The results show that the maximum error of the robot operation is within 5mm, average error is 3.1mm, and the treatment points of the robot operation are more uniform than those of manual operation. Therefore, the system can replace the doctor and achieve autonomous ultrasonic lipolysis to reduce the doctor’s labor intensity.
    Reference | Related Articles | Metrics
    Application of Deep Learning Method on Ischemic Stroke Lesion Segmentation
    ZHANG Yue (张月), LIU Shijie (刘世界), LI Chunlai (李春来), WANG Jianyu (王建宇)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 99-111.   DOI: 10.1007/s12204-021-2273-9
    Abstract147)      PDF (944KB)(38)      
    Although deep learning methods have been widely applied in medical image lesion segmentation, it is still challenging to apply them for segmenting ischemic stroke lesions, which are different from brain tumors in lesion characteristics, segmentation difficulty, algorithm maturity, and segmentation accuracy. Three main stages are used to describe the manifestations of stroke. For acute ischemic stroke, the size of the lesions is similar to that of brain tumors, and the current deep learning methods have been able to achieve a high segmentation accuracy. For sub-acute and chronic ischemic stroke, the segmentation results of mainstream deep learning algorithms are still unsatisfactory as lesions in these stages are small and diffuse. By using three scientific search engines including CNKI, Web of Science and Google Scholar, this paper aims to comprehensively understand the state-of-the-art deep learning algorithms applied to segmenting ischemic stroke lesions. For the first time, this paper discusses the current situation, challenges, and development directions of deep learning algorithms applied to ischemic stroke lesion segmentation in different stages. In the future, a system that can directly identify different stroke stages and automatically select the suitable network architecture for the stroke lesion segmentation needs to be proposed.
    Reference | Related Articles | Metrics
    Multi-Lead ECG Classification via an Information-Based Attention Convolutional Neural Network
    TUNG Hao (董昊), ZHENG Chao (郑超), MAO Xinsheng(毛新生), QIAN Dahong (钱大宏)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 55-69.   DOI: 10.1007/s12204-021-2371-8
    Abstract133)      PDF (943KB)(23)      
    A novel structure based on channel-wise attention mechanism is presented in this paper. With the proposed structure embedded, an efficient classification model that accepts multi-lead electrocardiogram (ECG) as input is constructed. One-dimensional convolutional neural networks (CNNs) have proven to be effective in pervasive classification tasks, enabling the automatic extraction of features while classifying targets. We implement the residual connection and design a structure which can learn the weights from the information contained in different channels in the input feature map during the training process. An indicator named mean square deviation is introduced to monitor the performance of a particular model segment in the classification task on the two out of five ECG classes. The data in the MIT-BIH arrhythmia database is used and a series of control experiments is conducted. Utilizing both leads of the ECG signals as input to the neural network classifier can achieve better classification results than those from using single channel inputs in different application scenarios. Models embedded with the channel-wise attention structure always achieve better scores on sensitivity and precision than the plain Resnet models. The proposed model exceeds most of the state-of-the-art models in ventricular ectopic beats (VEB) classification performance and achieves competitive scores for supraventricular ectopic beats (SVEB). Adopting more lead ECG signals as input can increase the dimensions of the input feature maps, helping to improve both the performance and generalization of the network model. Due to its end-to-end characteristics, and the extensible intrinsic for multi-lead heart diseases diagnosing, the proposed model can be used for the realtime ECG tracking of ECG waveforms for Holter or wearable devices.
    Reference | Related Articles | Metrics
    Enhancing Speech Recognition for Parkinson’s Disease Patient Using Transfer Learning Technique
    YU Qing (余青), MA Yi (马祎), LI Yongfu∗ (李永福)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 90-98.   DOI: 10.1007/s12204-021-2376-3
    Abstract129)      PDF (1087KB)(23)      
    Parkinson’s disease patients suffer from disorders of speech. The most frequently reported speech problems are weak, hoarse, nasal or monotonous voice, imprecise articulation, slow or fast speech, difficulty starting speech, impaired stress or rhythm, stuttering, and tremor. To improve the speech quality and assist the patient with speech rehabilitation therapy, we have proposed the speech recognition model for Parkinson’s disease patients using transfer learning technique (PSTL), where we have pre-trained the long short-term memory (LSTM) neural network model with our developed publicly available dataset that has been obtained from healthy people through the social media platform. Then, we applied the transfer learning technique to improve the performance of the PSTL framework. The frequency spectrogram masking data augmentation method has been used to alleviate the over-fitting problem so that the word error rate (WER) is further reduced. Even with a limited dataset, our proposed model has effectively reduced the WER from 58% to 44.5% on the original speech dataset and 53.1% to 43% on the denoised speech dataset, which demonstrated the feasibility of our framework.
    Reference | Related Articles | Metrics
    Solution to Long-Range Continuous and Precise Positioning in Deep Ocean for Autonomous Underwater Vehicles Using Acoustic Range Estimation and Inertial Sensor Measurements
    YANG Tao (杨 涛), ZHAO Jiankang∗ (赵健康)
    J Shanghai Jiaotong Univ Sci    2022, 27 (3): 281-297.   DOI: 10.1007/s12204-022-2441-6
    Abstract129)      PDF (2619KB)(101)      
    Although advances in research into autonomous underwater vehicles (AUVs) have been made to extend their working depth and endurance, underwater experiments and missions remain to be restricted by the positioning performance of AUVs. With the Global Navigation Satellite System (GNSS) precluded due to the rapid attenuation of radio signals in underwater environments, acoustic positioning methods serve as an effective substitution. A long-range continuous and precise positioning solution for AUVs in deep ocean is proposed in this study, relying on acoustic signals from beacons at the same depth and aided by onboard inertial sensors. A signal system is investigated to provide time of arrival (TOA) estimation in a resolution of milliseconds. Without pre-knowledge or local measurement of the accurate sound speed, an AUV is enabled to continuously locate its horizontal position based on rough ranges estimated by an iterative least square (ILS) based algorithm. For better accuracy and robustness, range deviations are compensated with a reference point of known position and outliers in the trajectory are eliminated by an implementation of the extended Kalman filter (EKF) coupled with the state-acceptance filter. The solution is evaluated in simulation experiments with environmental information measured on the spot, providing an average position error from ground truth below 10 m with a standard deviation below 5 m.
    Reference | Related Articles | Metrics
    Progress and Perspective of Artificial Intelligence and Machine Learning of Prediction in Anesthesiology
    XIA Ming (夏明), XU Tianyi (徐天意), JIANG Hong∗ (姜虹)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 112-120.   DOI: 10.1007/s12204-021-2331-3
    Abstract128)      PDF (409KB)(38)      
    Artificial intelligence (AI) has long been an attractive topic in medicine, especially in light of the rapid developments in digital and information technologies. AI has already provided some breakthroughs in medicine. With the assistance of AI, more precise models have been used for clinical predictions, diagnoses, and decision-making. This review defines the basic concepts of AI and machine learning (ML), and provides a simple introduction to certain frequently used algorithms in AI and ML. In addition, the review discusses the current common applications of AI and ML in the prediction of anesthesia conditions, including those for preoperative predictions of difficult airways, intraoperative predictions of adverse events and anesthetic effects, and postoperative predictions of vomiting and pain. The use of AI in anesthesiology remains in development, even without extensive promotion and clinical application; moreover, it has immense potential to maintain further development in the future. Finally, the limitations and challenges of AI development for anesthesia are also discussed, along with considerations regarding ethics and safety.
    Reference | Related Articles | Metrics
    Multi-Model Ensemble Deep Learning Method to Diagnose COVID-19 Using Chest Computed Tomography Images
    WANG Zhiming(王志明), DONG Jingjing (董静静), ZHANG Junpeng∗ (张军鹏)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 70-80.   DOI: 10.1007/s12204-021-2392-3
    Abstract127)      PDF (1418KB)(19)      
    Deep learning based analyses of computed tomography (CT) images contribute to automated diagnosis of COVID-19, and ensemble learning may commonly provide a better solution. Here, we proposed an ensemble learning method that integrates several component neural networks to jointly diagnose COVID-19. Two ensemble strategies are considered: the output scores of all component models that are combined with the weights adjusted adaptively by cost function back propagation; voting strategy. A database containing 8 347 CT slices of COVID- 19, common pneumonia and normal subjects was used as training and testing sets. Results show that the novel method can reach a high accuracy of 99.37% (recall: 0.998 1; precision: 0.989 3), with an increase of about 7% in comparison to single-component models. And the average test accuracy is 95.62% (recall: 0.958 7; precision: 0.955 9), with a corresponding increase of 5.2%. Compared with several latest deep learning models on the identical test set, our method made an accuracy improvement up to 10.88%. The proposed method may be a promising solution for the diagnosis of COVID-19.
    Reference | Related Articles | Metrics
    Panoramic and Personalised Intelligent Healthcare Mode
    LIU Quanchen (刘权宸), ZHANG Pengzhu∗ (张鹏翥)
    J Shanghai Jiaotong Univ Sci    2022, 27 (1): 121-136.   DOI: 10.1007/s12204-021-2274-8
    Abstract125)      PDF (1453KB)(25)      
    Although the development of national conditions and the increase in health risk factors undoubtedly pose a huge challenge to China’s medical health and labour security system, these simultaneously promote the elevation and transformation of national healthcare consciousness. Given that the current disease diagnosis and treatment models hardly satisfy the growing demand for medical and health care in China, based on the theory of healthcare and basic laws of human physiological activities, and combined with the characteristics of the information society, this paper presents a panoramic and personalised intelligent healthcare mode that is aimed at improving and promoting individual health. The basic definition and conceptual model are provided, and its basic characteristics and specific connotations are elaborated in detail. Subsequently, an intelligent coordination model of daily time allocation and a dynamic optimisation model for healthcare programmes are proposed. The implementation of this mode is explicitly illustrated with a practical application case. It is expected that this study will provide new ideas for further healthcare research and development.
    Reference | Related Articles | Metrics
    Automatic Removal of Multiple Artifacts for Single-Channel Electroencephalography
    ZHANG Chenbei (张晨贝), SABOR Nabil, LUO Junwen (罗竣文), PU Yu (蒲 宇), WANG Guoxing (王国兴), LIAN Yong∗ (连 勇)
    J Shanghai Jiaotong Univ Sci    2022, 27 (4): 437-451.   DOI: 10.1007/s12204-021-2374-5
    Abstract115)      PDF (2934KB)(80)      
    Removing different types of artifacts from the electroencephalography (EEG) recordings is a critical step in performing EEG signal analysis and diagnosis. Most of the existing algorithms aim for removing single type of artifacts, leading to a complex system if an EEG recording contains different types of artifacts. With the advancement in wearable technologies, it is necessary to develop an energy-efficient algorithm to deal with different types of artifacts for single-channel wearable EEG devices. In this paper, an automatic EEG artifact removal algorithm is proposed that effectively reduces three types of artifacts, i.e., ocular artifact (OA), transmission- line/harmonic-wave artifact (TA/HA), and muscle artifact (MA), from a single-channel EEG recording. The effectiveness of the proposed algorithm is verified on both simulated noisy EEG signals and real EEG from CHB- MIT dataset. The experimental results show that the proposed algorithm effectively suppresses OA, MA and TA/HA from a single-channel EEG recording as well as physical movement artifact.
    Reference | Related Articles | Metrics
    Risk Prediction Model of Gallbladder Disease in Shanghai Middle-Aged and Elderly People Based on Neural Networks
    YUAN Xiaoqi (袁筱祺), ZHU Lelan (朱乐兰), XU Qiongfan(徐琼凡), GAO Wei (高玮)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 153-159.   DOI: 10.1007/s12204-021-2386-1
    Abstract108)      PDF (345KB)(46)      
    This paper discusses the risk factors related to gallbladder disease in Shanghai, improves the accuracy of risk prediction, and provides a theoretical basis for scientific diagnosis and universality of gallbladder disease.We selected 3 462 data of middle-aged and elderly health check-up patients in a general hospital in Shanghai,and divided into gallbladder disease group according to color doppler ultrasound diagnosis results. Single-factor analysis screened out 8 important risk factors, which were used as an analysis variable of multi-layer perceptron neural network and binary logistic regression to construct the prediction model of gallbladder disease. The prediction accuracy of the multi-layer perceptron neural network risk prediction model is 76%. The area under the receiver operating characteristic curve (AUC) is 0.82, the maximum Youden index is 0.44, the sensitivity is 79.51, and the specificity is 64.23. The prediction accuracy of the multi-layer perceptron neural network model is better than that of the binary logistic regression prediction model. The overall prediction accuracy of the binary logistic regression prediction model is 75.60%, the AUC is 0.81, the maximum Youden index is 0.42, the sensitivity is 74.48, and the specificity is 57.60. In the objective risk prediction of gallbladder disease in middle-aged and elderly people in Shanghai, the risk prediction model based on the multi-layer perceptron neural network has a better prediction performance than the binary logistic regression model, which provides a theoretical basis for preventive treatment and intervention.
    Reference | Related Articles | Metrics
    SeRN: A Two-Stage Framework of Registration for Semi-Supervised Learning for Medical Images
    JIA Dengqiang* (贾灯强), LUO Xinzhe (罗鑫喆), DING Wangbin (丁王斌),HUANG Liqin (黄立勤), ZHUANG Xiahai (庄吓海)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 176-189.   DOI: 10.1007/s12204-021-2383-4
    Abstract89)      PDF (2406KB)(44)      
    Significant breakthroughs in medical image registration have been achieved using deep neural networks (DNNs). However, DNN-based end-to-end registration methods often require large quantities of data or adequate annotations for training. To leverage the intensity information of abundant unlabeled images, unsupervised registration methods commonly employ intensity-based similarity measures to optimize the network parameters.However, finding a sufficiently robust measure can be challenging for specific registration applications. Weakly supervised registration methods use anatomical labels to estimate the deformation between images. High-level structural information in label images is more reliable and practical for estimating the voxel correspondence of anatomic regions of interest between images, whereas label images are extremely difficult to collect. In this paper, we propose a two-stage semi-supervised learning framework for medical image registration, which consists of unsupervised and weakly supervised registration networks. The proposed semi-supervised learning framework is trained with intensity information from available images, label information from a relatively small number of labeled images and pseudo-label information from unlabeled images. Experimental results on two datasets (cardiac and abdominal images) demonstrate the efficacy and efficiency of this method in intra- and inter-modality medical image registrations, as well as its superior performance when a vast amount of unlabeled data and a small set of annotations are available. Our code is publicly available at https://github.com/jdq818/SeRN.
    Reference | Related Articles | Metrics
    Modification Method of Longitudinal Bow Structure for Ice-Strengthened Merchant Ship
    DING Shifeng (丁仕风), ZHOU Li∗ (周 利), GU Yingjie (顾颖杰), ZHOU Yajun (周亚军)
    J Shanghai Jiaotong Univ Sci    2022, 27 (3): 298-306.   DOI: 10.1007/s12204-022-2442-5
    Abstract87)      PDF (5084KB)(35)      
    Merchant ships, which are quite different from icebreakers, usually require the light ice-strengthened bow under the floe-ice condition. According to ice-class B, requirements of China Classification Society (CCS), intermediate frames and thick hull plates are necessary for the ice belt area to resist floe-ice impact. However, due to the limited space, it is not practical to set so many intermediate longitudinals from manufacture point of view. In this paper, a modification method is proposed to solve the problem by maintaining the frame spacing and increasing the plate thickness. The aim is to make sure that the bow owns the equivalent ice-bearing capacity with the original frame spacing. At first, a bulk carrier with ice-class B is used for case study. According to the requirements of the ice class rule, a designed ice thickness is used to calculate the ice load acting on the bow area due to the impact of ice floe. Two structural models are presented to perform the strength analysis under ice load, including the out-shell plate model and the longitudinal model. The results show that increasing the plate thickness is helpful to remove the negative effect induced by enlarging the spacing of the longitudinal. A reasonable curve is presented to modify the bow for the ice-strengthened merchant ship, which shows the relationship between the increase of plate thickness and the spacing of longitudinal. Moreover, a model test of floe-ice–ship interaction is conducted to measure the dynamic ice load, based on which nonlinear dynamic FE analysis is used to verify the presented plate-thickness–longitudinal spacing curve. The results show that the proposed method can be used to improve the ice-strengthened bow structure effectively, which provides theoretical foundation to modify the requirement of CCS’s ice class rule.
    Reference | Related Articles | Metrics
    Adaptive Human-Robot Collaboration Control Based on Optimal Admittance Parameters
    YU Xinyi (禹鑫燚), WU Jiaxin (吴加鑫), XU Chengjun (许成军), LUO Huizhen (罗惠珍), OU Linlin∗ (欧林林)
    J Shanghai Jiaotong Univ Sci    2022, 27 (5): 589-601.   DOI: 10.1007/s12204-022-2460-3
    Abstract86)      PDF (1674KB)(70)      
    In order to help the operator perform the human-robot collaboration task and optimize the task performance, an adaptive control method based on optimal admittance parameters is proposed. The overall control structure with the inner loop and outer loop is first established. The tasks of the inner loop and outer loop are robot control and task optimization, respectively. Then an inner-loop robot controller integrated with barrier Lyapunov function and radial basis function neural networks is proposed, which makes the robot with unknown dynamics securely behave like a prescribed robot admittance model sensed by the operator. Subsequently, the optimal parameters of the robot admittance model are obtained in the outer loop to minimize the task tracking error and interaction force. The optimization problem of the robot admittance model is transformed into a linear quadratic regulator problem by constructing the human-robot collaboration system model. The model includes the unknown dynamics of the operator and the task performance details. For relaxing the requirement of the system model, the integral reinforcement learning is employed to solve the linear quadratic regulator problem. Besides, an auxiliary force is designed to help the operator complete the specific task better. Compared with the traditional control scheme, the security performance and interaction performance of the human-robot collaboration system are improved. The effectiveness of the proposed method is verified through two numerical simulations. In addition, a practical human-robot collaboration experiment is carried out to demonstrate the performance of the proposed method.
    Reference | Related Articles | Metrics
    A 12-bit 80 MS/s 2 mW SAR ADC with Deliberated Digital Calibration and Redundancy Schemes for Medical Imaging
    HAN Gang* (韩刚), WU Bin (吴斌), PU Yilin (蒲钇霖)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 250-255.   DOI: 10.1007/s12204-021-2377-2
    Abstract83)      PDF (1130KB)(11)      
    In this article, we presented a 12-bit 80MS/s low power successive approximation register (SAR)analog to digital converter (ADC) design. A simplified but effective digital calibration scheme was exploited to make the ADC achieve high resolution without sacrificing more silicon area and power efficiency. A modified redundancy technique was also adopted to guarantee the feasibility of the calibration and meantime ease the burden of the reference buffer circuit. The prototype SAR ADC can work up to a sampling rate of 80MS/s with the performance of > 10.5 bit equivalent number of bits (ENOB), < ±1 least significant bit (LSB) differential nonlinearity (DNL) & integrated nonlinearity (INL), while only consuming less than 2mA current from a 1.1V power supply. The calculated figure of merit (FoM) is 17.4 fJ/conversion-step. This makes it a practical and competitive choice for the applications where high dynamic range and low power are simultaneously required,such as portable medical imaging.
    Reference | Related Articles | Metrics
    Spontaneous Language Analysis in Alzheimer’s Disease:Evaluation of Natural Language Processing Technique for Analyzing Lexical Performance
    LIU Ning (刘宁), YUAN Zhenming* (袁贞明)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 160-167.   DOI: 10.1007/s12204-021-2384-3
    Abstract79)      PDF (932KB)(20)      
    Language disorder, a common manifestation of Alzheimer’s disease (AD), has attracted widespread attention in recent years. This paper uses a novel natural language processing (NLP) method, compared with latest deep learning technology, to detect AD and explore the lexical performance. Our proposed approach is based on two stages. First, the dialogue contents are summarized into two categories with the same category. Second,term frequency - inverse document frequency (TF-IDF) algorithm is used to extract the keywords of transcripts,and the similarity of keywords between the groups was calculated separately by cosine distance. Several deep learning methods are used to compare the performance. In the meanwhile, keywords with the best performance are used to analyze AD patients’ lexical performance. In the Predictive Challenge of Alzheimer’s Disease held by iFlytek in 2019, the proposed AD diagnosis model achieves a better performance in binary classification by adjusting the number of keywords. The F1 score of the model has a considerable improvement over the baseline of 75.4%, and the training process of which is simple and efficient. We analyze the keywords of the model and find that AD patients use less noun and verb than normal controls. A computer-assisted AD diagnosis model on small Chinese dataset is proposed in this paper, which provides a potential way for assisting diagnosis of AD and analyzing lexical performance in clinical setting.
    Reference | Related Articles | Metrics
    Topology Optimization Method for Calcaneal Prosthesis
    LIU Xiaoying* (刘晓颖), YUE Yong(岳勇), WANG Chongning (王宠宁), HUANG Jiazan (黄家赞),HUANG Xianwei(黄贤伟), HAO Yanhua(郝艳华)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 240-249.   DOI: 10.1007/s12204-021-2324-2
    Abstract78)      PDF (1932KB)(19)      
    With the development of economy and the progress of medical science and technology, artificial prosthesis replacement has become an important means to improve the dysfunction caused by human bone diseases.However, there are still some loose phenomena caused by stress shielding. To solve the complications of aseptic loosening after calcaneal prosthesis replacement, an optimal design method for the prosthesis was proposed. The prosthesis was designed and optimized according to the real bone shape and the replacement requirements by the combination of computed tomography (CT) technology, computer-aided design, finite element analysis, and power flow theory. CT data were imported into MIMICS and Geomagic Studios. UG was used to obtain the geometric model of the human skeleton. Then, the 3D finite element model of the prosthesis was established by combining the finite element software Abaqus, and a series of finite element analysis was carried out. The prosthesis was topologically optimized and filled with a porous structure. The prosthesis was implanted by computer simulation.Finally, the power flow method was used to compare the dynamic performance and energy transfer before and after the prosthesis replacement to verify the rationality of the prosthesis design. In this paper, this method was used to optimize the design of the calcaneal prosthesis, and the research shows that this method can reduce the stress shielding effect of the calcaneal prosthesis. From the case of calcaneal prosthesis optimization, this method is not only a supplement to the contemporary biomechanical theory but also can guide the design of bone prosthesis in bone prosthesis replacement surgery.
    Reference | Related Articles | Metrics
    Design and Overall Strength Analysis of Multi-Functional Elastic Connections Floating Breakwater System
    HUO Fali∗ (霍发力), YANG Hongkun (杨宏坤), GUO Jianting (郭建廷), JI Chunyan (嵇春艳), NIU Jianjie (牛建杰), WANG Ke (王 珂)
    J Shanghai Jiaotong Univ Sci    2022, 27 (3): 326-338.   DOI: 10.1007/s12204-022-2413-x
    Abstract77)      PDF (3201KB)(20)      
    As a new type of marine structure, floating breakwater can provide suitable water area for coastal residents. In this paper, a multi-module floating breakwater with three cylinders was designed. According to the characteristics of each module, the elastic connector was created. The cabins with functions such as living, generating electricity and entertainment were arranged. A linear spring constrained design wave (LSCDW) method for strength analysis of floating marine structures with multi-module elastic connections was proposed. The numerical model was verified by 1 : 50 similarity ratio in the test tank. According to the analysis of design wave and extreme wave conditions, considering the mooring loads and environmental loads and connector loads, the overall strength of breakwater was analyzed by LSCDW method. These studies can provide new insights and theoretical guidance for the design of multi-module floating structures.
    Reference | Related Articles | Metrics
    Cable-Driven Flexible Exoskeleton Robot for Abnormal Gait Rehabilitation
    XU Ziwei (徐子薇), XIE Le* (谢叻)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 231-239.   DOI: 10.1007/s12204-021-2403-4
    Abstract76)      PDF (1563KB)(30)      
    The number of people with abnormal gait in China has been increasing for years. Compared with traditional methods, lower limb rehabilitation robots which address problems such as longstanding human guidance may cause fatigue, and the training is lacking scientific and intuitive monitoring data. However, typical rigid rehabilitation robots are always meeting drawbacks like the enormous weight, the limitation of joint movement,and low comfort. The purpose of this research is to design a cable-driven flexible exoskeleton robot to assist in rehabilitation training of patients who have abnormal gait due to low-level hemiplegia or senility. The system consists of a PC terminal, a Raspberry Pi, and the actuator structure. Monitoring and training are realized through remote operation and interactive interface simultaneously. We designed an integrated and miniaturized driving control box. Inside the box, two driving cables on customized pulley-blocks with different radii can retract/release by one motor after transmitting the target position to the Raspberry Pi from the PC. The force could be transferred to the flexible suit to aid hip flexion and ankle plantar flexion. Furthermore, the passive elastic structure was intended to assist ankle dorsiflexion. We also adopted the predictable admittance controller,which uses the Prophet algorithm to predict the changes in the next five gait cycles from the current ankle angular velocity and obtain the ideal force curve through a functional relationship. The admittance controller can realize the desired force following. Finally, we finished the performance test and the human-subject experiment.Experimental data indicate that the exoskeleton can meet the basic demand of multi-joint assistance and improve abnormal postures. Meanwhile, it can increase the range of joint rotation and eliminate asymmetrical during walking.
    Reference | Related Articles | Metrics
    Path Planning and Optimization of Humanoid Manipulator in Cartesian Space
    LI Shiqi (李世其), LI Xiao∗ (李肖), HAN Ke (韩可), XIONG Youjun (熊友军), XIE Zheng (谢铮), CHEN Jinliang (陈金亮)
    J Shanghai Jiaotong Univ Sci    2022, 27 (5): 614-620.   DOI: 10.1007/s12204-022-2416-7
    Abstract75)      PDF (1591KB)(27)      
    To solve the problems of low efficiency and multi-solvability of humanoid manipulator Cartesian space path planning in physical human-robot interaction, an improved bi-directional rapidly-exploring random tree algorithm based on greedy growth strategy in 3D space is proposed. The workspace of manipulator established based on Monte Carlo method is used as the sampling space of the rapidly-exploring random tree, and the opposite expanding greedy growth strategy is added in the random tree expansion process to improve the path planning efficiency. Then the generated path is reversely optimized to shorten the length of the planned path, and the optimized path is interpolated and pose searched in Cartesian space to form a collision-free optimized path suitable for humanoid manipulator motion. Finally, the validity and reliability of the algorithm are verified in an intelligent elderly care service scenario based on Walker2, a large humanoid service robot.
    Reference | Related Articles | Metrics
    Interactive Liver Segmentation Algorithm Based on Geodesic Distance and V-Net
    KANG Jie* (亢洁), DING Jumin (丁菊敏), LEI Tao (雷涛),FENG Shujie (冯树杰), LIU Gang (刘港)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 190-201.   DOI: 10.1007/s12204-021-2379-0
    Abstract74)      PDF (3921KB)(33)      
    Convolutional neural networks (CNNs) are prone to mis-segmenting image data of the liver when the background is complicated, which results in low segmentation accuracy and unsuitable results for clinical use. To address this shortcoming, an interactive liver segmentation algorithm based on geodesic distance and V-net is proposed. The three-dimensional segmentation network V-net adequately considers the characteristics of the spatial context information to segment liver medical images and obtain preliminary segmentation results. An artificial algorithm based on geodesic distance is used to form artificial hard constraints to modify the image,and the superpixel piece created by the watershed algorithm is introduced as a sample point for operation, which significantly improves the efficiency of segmentation. Results from simulation of the liver tumor segmentation challenge (LiTS) dataset show that this algorithm can effectively refine the results of automatic liver segmentation,reduce user intervention, and enable a fast, interactive liver image segmentation that is convenient for doctors.
    Reference | Related Articles | Metrics
    KDLPCCA-Based Projection for Feature Extraction in SSVEP-Based Brain-Computer Interfaces
    HUANG Jiayang (黄嘉阳), YANG Pengfei* (杨鹏飞), WAN Bo (万波), ZHANG Zhiqiang (张志强)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 168-175.   DOI: 10.1007/s12204-021-2387-0
    Abstract74)      PDF (519KB)(31)      
    An electroencephalogram (EEG) signal projection using kernel discriminative locality preserving canonical correlation analysis (KDLPCCA)-based correlation with steady-state visual evoked potential (SSVEP) templates for frequency recognition is presented in this paper. With KDLPCCA, not only a non-linear correlation but also local properties and discriminative information of each class sample are considered to extract temporal and frequency features of SSVEP signals. The new projected EEG features are classified with classical machine learning algorithms, namely, K-nearest neighbors (KNNs), naive Bayes, and random forest classifiers. To demonstrate the effectiveness of the proposed method, 16-channel SSVEP data corresponding to 4 frequencies collected from 5 subjects were used to evaluate the performance. Compared with the state of the art canonical correlation analysis (CCA), experimental results show significant improvements in classification accuracy and information transfer rate (ITR), achieving 100% and 240 bits/min with 0.5 s sample block. The superior performance demonstrates that this method holds the promising potential to achieve satisfactory performance for high-accuracy SSVEP-based brain-computer interfaces.
    Reference | Related Articles | Metrics
    Experimental Study on Hydrodynamic Response of Semisubmersible Platform-Based Bottom-Hinged Flap Wave Energy Converter
    LIN Yana∗ (林 焰), PEI Feib (裴 斐)
    J Shanghai Jiaotong Univ Sci    2022, 27 (3): 307-315.   DOI: 10.1007/s12204-022-2443-4
    Abstract71)      PDF (1368KB)(33)      
    A semisubmersible platform-based (SPB) bottom-hinged flap (BHF) wave energy converter (WEC) concept is presented in this paper, and its platform hydrodynamic response was studied experimentally. Aimed at studying the special WEC-mounted platform response problem, both regular and irregular wave experiments were conducted. The frequency domain results of regular wave experiments are described in the form of response amplitude operators. The time domain results of irregular wave experiments are treated by statistical analysis and fast Fourier transformation. Regular wave experiments and irregular wave experiments show good consistency. The mooring system strongly affects the whole system, which is a considerable factor for WEC design. The influences of BHF mounted on the platform are revealed in both statistic and frequency spectral ways. The results of experiments give a guide for SPB design aiming to support BHF-WEC.
    Reference | Related Articles | Metrics
    Improvement of Physical Fitness Test Assessment Criteria Based on fNIRS Technology: Taking Pull-Up as an Example
    GONG Bin(巩斌), YU Xianghua(禹香华), FANG Yu (方宇), WANG Zheng (王正), YANG Hao (杨皓), CHEN Guodong (陈国栋), L Ü Na (吕娜)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 219-225.   DOI: 10.1007/s12204-021-2367-4
    Abstract70)      PDF (1855KB)(26)      
    Pull-up, as an important physical fitness test event of the “National Student Physical Health Standard”, is known as a difficult physical fitness test event. To improve the assessment criteria of pull-ups, this paper uses the functional near-infrared spectroscopy (fNIRS) to monitor the changes and activation of oxyhemoglobin (HbO) signals in the brain motor cortex of people with different body mass indexes (BMIs) during the pullup assessment. Then the relationship between BMIs and evaluation criteria is discussed. After collecting and analyzing experimental data of 18 recruited college students, it is found that the number of pull-ups performed by people with different BMIs is different when they reach the peak state of brain activation. The results of the study indicate that different assessment criteria should be adopted for different BMI groups. It is suggested that the BMI should be introduced as one of the test indexes in the examination of pull-ups event in “National Student Physical Health Standard”.
    Reference | Related Articles | Metrics
    Machine Learning-Based Approach to Liner Shipping Schedule Design
    DU Jian1∗ (杜 剑), ZHAO Xu2 (赵 旭), GUO Liming2 (郭力铭), WANG Jun2 (王 军)
    J Shanghai Jiaotong Univ Sci    2022, 27 (3): 411-423.   DOI: 10.1007/s12204-021-2338-9
    Abstract69)      PDF (524KB)(25)      
    This paper studied a tactical liner shipping schedule design issue under sail and port time uncertainties, which is the determination of the planned arrival time at each port call as well as the punctuality rate and number of assigned ship on the route. A number of studies have tried to introduce the operational speed adjustment measure into this tactical schedule design issue, to alleviate the discrepancies between designed schedule and maritime practice. On the one hand, weather conditions can lead to speed loss phenomenon of ships, which may result in the failure of ships’ punctual arrivals. On the other hand, improving the ability of speed adjustment can decrease the late-arrival compensation, but increase the fuel consumption cost. Then, we formulated a machine learning-based liner shipping schedule design model aiming at above-mentioned two limitations on speed adjustment measure. And a machine learning-based approach has been designed, where the speed adjustment simulation, the neural network training and the reinforcement learning were included. Numerical experiments were conducted to validate our results and derive managerial insights, and then the applicability of machine learning method in shipping optimization issue has been confirmed.
    Reference | Related Articles | Metrics
    Gram Matrix-Based Convolutional Neural Network for Biometric Identification Using Photoplethysmography Signal
    WU Caiyu, (吴彩钰), SABOR Nabil, ZHOU Shihong, (周世鸿), WANG Min, (王 敏), YING Liang (应 亮), WANG Guoxing∗ (王国兴)
    J Shanghai Jiaotong Univ Sci    2022, 27 (4): 463-472.   DOI: 10.1007/s12204-022-2426-5
    Abstract68)      PDF (1049KB)(17)      
    As a kind of physical signals that could be easily acquired in daily life, photoplethysmography (PPG) signal becomes a promising solution to biometric identification for daily access management system (AMS). State- of-the-art PPG-based identification systems are susceptible to the form of motions and physical conditions of the subjects. In this work, to exploit the advantage of deep learning, we developed an improved deep convolutional neural network (CNN) architecture by using the Gram matrix (GM) technique to convert time-serial PPG signals to two-dimensional images with a temporal dependency to improve accuracy under different forms of motions. To ensure a fair evaluation, we have adopted cross-validation method and “training and testing” dataset splitting method on the TROIKA dataset collected in ambulatory conditions. As a result, the proposed GM-CNN method achieved accuracy improvement from 69.5% to 92.4%, which is the best result in terms of multi-class classification compared with state-of-the-art models. Based on average five-fold cross-validation, we achieved an accuracy of 99.2%, improved the accuracy by 3.3% compared with the best existing method for the binary-class.
    Reference | Related Articles | Metrics
    Improved Nonsingular Fast Terminal Sliding Mode Control of Unmanned Underwater Hovering Vehicle
    HE Chenlua (何晨璐), FENG Zhengpinga,b∗ (冯正平)
    J Shanghai Jiaotong Univ Sci    2022, 27 (3): 393-401.   DOI: 10.1007/s12204-022-2447-0
    Abstract66)      PDF (1034KB)(26)      
    An improved nonsingular fast terminal sliding mode manifold based on scaled state error is proposed in this paper. It can significantly accelerate the convergence rate of the state error which is initially far from the origin and achieve the fixed-time convergence. In addition, conventional double power term based reaching law is improved to ensure the convergence of sliding state in the presence of disturbances. The proposed approach is applied to the hovering control of an unmanned underwater vehicle. The controller exhibits both fast convergence and strong robustness to model uncertainty and external disturbances
    Reference | Related Articles | Metrics
    Dynamic Stability Analysis of Backhoe Dredger Based on Time Domain Method
    CHEN Yihua1 (陈熠画), CHEN Xinquan1∗ (陈新权), YANG Qi1,2 (杨 启), OUYANG Yiping1 (欧阳义平)
    J Shanghai Jiaotong Univ Sci    2022, 27 (3): 339-345.   DOI: 10.1007/s12204-021-2272-x
    Abstract66)      PDF (1221KB)(17)      
    When incidents happen with the positioning spud of a backhoe dredger, the hull loses stability, heels significantly, and may even capsize under extreme conditions. Coupling the hydrodynamics and spud vibrations, this paper investigates the dynamic stability of a backhoe dredger after spud failure based on the time domain method. The maximum dynamic heeling angle verifies the stability of the backhoe dredger. To identify the influences of environmental load, operating conditions, and spud-soil interactions, numerical motion simulations were conducted in the time domain. The main conclusions on dynamic stability consider the influences of relative environmental and operational factors. This study provides a powerful and efficient approach to analyze the dynamic stability of backhoe dredgers and to design flooding angles.
    Reference | Related Articles | Metrics
    Generation Approach of Human-Robot Cooperative Assembly Strategy Based on Transfer Learning
    LÜ Qibing (吕其兵), LIU Tianyuan (刘天元), ZHANG Rong (张荣), JIANG Yanan (江亚南), XIAO Lei (肖雷), BAO Jingsong∗ (鲍劲松)
    J Shanghai Jiaotong Univ Sci    2022, 27 (5): 602-613.   DOI: 10.1007/s12204-022-2493-7
    Abstract66)      PDF (3845KB)(27)      
    In current small batch and customized production mode, the products change rapidly and the personal demand increases sharply. Human-robot cooperation combining the advantages of human and robot is an effective way to solve the complex assembly. However, the poor reusability of historical assembly knowledge reduces the adaptability of assembly system to different tasks. For cross-domain strategy transfer, we propose a human-robot cooperative assembly (HRCA) framework which consists of three main modules: expression of HRCA strategy, transferring of HRCA strategy, and adaptive planning of motion path. Based on the analysis of subject capability and component properties, the HRCA strategy suitable for specific tasks is designed. Then the reinforcement learning is established to optimize the parameters of target encoder for feature extraction. After classification and segmentation, the actor-critic model is built to realize the adaptive path planning with progressive neural network. Finally, the proposed framework is verified to adapt to the multi-variety environment, for example, power lithium batteries.
    Reference | Related Articles | Metrics
    Evaluation Value of Intravoxel Incoherent Motion Diffusion-Weighted Imaging on Early Efficacy of Magnetic Resonance-Guided High-Intensity Focused Ultrasound Ablation for Uterine Adenomyoma
    TANG Na (唐纳), GU Jianjun (顾坚骏), YIN Xiaorui (尹肖睿), YU Rongjiang (虞容江),XU Yuantao (徐元涛), LI Xiang (李想), WANG Han* (王悍)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 226-230.   DOI: 10.1007/s12204-022-2405-x
    Abstract66)      PDF (549KB)(17)      
    To investigate the evaluation value of intravoxel incoherent motion diffusion-weighted imaging (IVIMDWI) on the early efficacy of magnetic resonance-guided high-intensity focused ultrasound (MRgFUS) ablation for uterine adenomyoma. The clinical and magnetic resonance imaging (MRI) data of 36 patients with uterine adenomyoma before and after MRgFUS treatment in our hospital from January 2018 to December 2018 were retrospectively analyzed. All the 36 patients underwent MRI examination one day before operation and immediately after operation using GE Discovery MR750 3.0T MRI, including conventional sequences (T1WI, T2WI,and T2 fat suppression sequences) plain scan, IVIM-DWI sequences with 9 b values, and contrast enhanced-MRI sequences. The IVIM-DWI quantitative parameters (true diffusion coefficient D, perfusion related diffusion coefficient D?, and perfusion fraction f) of double-exponential model were obtained by using GE ADW 4.7 functool,a postprocessor. SPSS 24.0 software was used to analyze the difference in parameter between the ablation and non-ablation areas of uterine adenomyoma. DWI signal in the ablation area of uterine adenomyoma was increased,and manifested as heterogeneous diffuse high signal, with low central signal and high edge signal. Values of D, D? and f in the ablation area of uterine adenomyoma were significantly lower than those in the non-ablation area,and there was statistical difference between the two (P <0.05). The areas under receiver operating characteristic (ROC) curve of D, D? and f values in the ablation area of uterine adenomyoma were 0.854, 0.898 and 0.924,respectively; the optimal thresholds for the diagnosis of ablation area of uterine adenomyoma were 0.81 × 10 ?3 mm2/s, 4.99×10 ?3 mm2/s and 0.24, respectively; the diagnostic sensitivity was 80.6%, 72.2% and 94.4%, respectively; and the specificity was 91.7%, 97.2% and 94.4%, respectively. IVIM-DWI has a certain clinical value in the evaluation on early efficacy of MRgFUS ablation of uterine adenomyosis.
    Reference | Related Articles | Metrics
    Instruction Cues Increase Brain Network Complexity During Movement Preparation
    WANG Ning (王宁), ZHANG Lipeng (张利朋), ZHANG Rui (张锐), MA Liuyang(马留洋),NIU Deyuan(牛得源), ZHANG Yankun (张彦昆), ZHAO Hui (赵辉), HU Yuxia* (胡玉霞)
    J Shanghai Jiaotong Univ Sci    2022, 27 (2): 202-210.   DOI: 10.1007/s12204-021-2342-0
    Abstract64)      PDF (992KB)(14)      
    Instruction cues are widely employed for research on neural mechanisms during movement preparation.However, their influence on brain connectivity during movement has not received much attention. Herein, 15 healthy subjects completed two experimental tasks including either instructed or voluntary movements; meanwhile electroencephalogram (EEG) data were synchronously recorded. Based on source analysis and related literature,six movement-related brain regions were selected, including the left/right supplementary motor area (SMA),left/right inferior frontal gyrus (iFg), and left/right postcentral gyrus (pCg). After assuming 10 a priori models of regional brain connectivity, we evaluated the optimal connectivity model between brain regions for the two scenarios using the dynamic causality model (DCM). During voluntary movement, the movement originated in the SMA, passed through the iFg of the prefrontal lobe, and then returned to the main sensory cortex of the pCg. In the instructed movement, the movement originated in the iFg, and then was transmitted to the pCg and the SMA, as well as from the pCg to the SMA. In contrast to the preparation process of voluntary movement,there were long-range information interactions between the iFg and pCg. Further, almost the same brain regions were active during movement preparation under both voluntary and instructed movement tasks, which evidences certain similarities in dynamic brain connectivity, that is, the brain has direct connections between the bilateral SMA, bilateral pCg, and bilateral SMA, indicating that the both brain hemispheres work together during the movement preparation phase. The results suggest that the network during the preparation process of instructed movements is more complex than voluntary movements.
    Reference | Related Articles | Metrics
    Breast Pathological Image Classification Based on VGG16 Feature Concatenation
    LIU Min (刘 敏), YI Ming (易 鸣), WU Minghu∗ (武明虎), WANG Juan (王 娟), HE Yu (何 宇)
    J Shanghai Jiaotong Univ Sci    2022, 27 (4): 473-484.   DOI: 10.1007/s12204-021-2398-x
    Abstract64)      PDF (5914KB)(11)      
    Breast cancer is one of the malignancies that endanger women’s health all over the world. Considering that there is some noise and edge blurring in breast pathological images, it is easier to extract shallow features of noise and redundant information when VGG16 network is used, which is affected by its relative shallow depth and small convolution kernel. To improve the pathological diagnosis of breast cancers, we propose a classification method for benign and malignant tumors in the breast pathological images which is based on feature concatenation of VGG16 network. First, in order to improve the problems of small dataset size and unbalanced data samples, the original BreakHis dataset is processed by data augmentation technologies, such as geometric transformation and color enhancement. Then, to reduce noise and edge blurring in breast pathological images, we perform bilateral filtering and denoising on the original dataset and sharpen the edge features by Sobel operator, which makes the extraction of shallow features by VGG16 model more accurate. Based on transfer learning, the network model trained with the expanded dataset is called VGG16-1, and another model trained with the image denoising and sharpening and mixed with the original dataset is called VGG16-2. The features extracted by VGG16-1 and VGG16-2 are concatenated, and then classified by support vector machine. The final experimental results show that the average accuracy is 98.44%, 98.89%, 98.30% and 97.47%, respectively, when the proposed method is tested with the breast pathological images of 40×, 100×, 200× and 400× on BreakHis dataset.
    Reference | Related Articles | Metrics