Most Down Articles

Published in last 1 year | In last 2 years| In last 3 years| All| Most Downloaded in Recent Month | Most Downloaded in Recent Year|

Most Downloaded in Recent Year

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

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 Abstract （190）      PDF （2934KB）（98）       Knowledge map    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

Select

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 Abstract （224）      PDF （1674KB）（91）       Knowledge map    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

Select

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 Abstract （395）      PDF （2268KB）（161）       Knowledge map    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

Select

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 Abstract （167）      PDF （3845KB）（45）       Knowledge map    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

Select

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 Abstract （214）      PDF （1591KB）（41）       Knowledge map    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

Select

Travel Intention of Electric Vehicle Sharing based on Theory of Multiple Motivations BAO Lewen (鲍乐雯), MIAO Rui, ∗ (苗 瑞), CHEN Zhihua (陈志华), ZHANG Bo (张 博), GUO Peng (郭 鹏), MA Yuze (马宇泽) J Shanghai Jiaotong Univ Sci    2023, 28 (1): 1-9.   DOI: 10.1007/s12204-023-2563-5 Abstract （268）      PDF （467KB）（107）       Knowledge map    Determining the travel intention of residents with shared electric vehicles (EVs) is significant for promoting the development of low-carbon transportation, considering that common problems such as high idle rate and lack of attractiveness still exist. To this end, a structural equation model (SEM) based on the theory of multiple motivations is proposed in this paper. First, the influencing motivations for EV sharing are divided into three categories: consumer-driven, program-driven, and enterprise-driven motivations. Then, the intentions of residents in Shanghai to travel with shared EVs are obtained through a survey questionnaire. Finally, an SEM is constructed to analyze quantitatively the impact of different motivations on the travel intention. The results show that consumer-driven motivations with impact weights from 0.14 to 0.63 have the overwhelming impact on travel intention, compared to program-driven motivations with impact weights from ?0.14 to 0.15 and enterprise-driven motivations with impact weights from 0.02 to 0.06. In terms of consumer-driven motivations, the weight of green travel awareness is the highest. The implications of these results on the policy to enable large-scale implementation of shared EVs are discussed from the perspectives of the resident, enterprise, and government. Reference | Related Articles | Metrics

Select

Further Result on the Observer Design for One-Sided Lipschitz Systems YANG Ming1 (杨 明), HUANG Jun1∗ (黄 俊), ZHANG Wei2 (章 伟) J Shanghai Jiaotong Univ Sci    2022, 27 (6): 817-822.   DOI: 10.1007/s12204-020-2252-6 Abstract （142）      PDF （328KB）（80）       Knowledge map    This paper investigates the problem of observer design for a class of control systems. Different from current works, the nonlinear functions in the system only satisfy the property of the one-sided Lipschitz (OSL) condition but not quadratic inner-boundedness (QIB). Moreover, the case where the OSL constant is negative is specially investigated. Firstly, a full-order observer is constructed for the original system. Then, a reduced-order observer is also designed by using the decomposition method. The advantage and effectiveness of the proposed design scheme are shown in a numerical simulation. Reference | Related Articles | Metrics

Select

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 Abstract （176）      PDF （2619KB）（115）       Knowledge map    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

Select

Physical Characterization of Ionic Liquid-Modified Polyvinyl Alcohol and Sodium Thiocyanate Polymer Electrolytes for Electrochemical Double-Layer Capacitor Application AZEMTSOP Manfo Theodore , MEHRA Ram Mohan , KUMAR Yogesh , GUPTA Meenal J Shanghai Jiaotong Univ Sci    2023, 28 (2): 161-171.   DOI: 10.1007/s12204-021-2397-y Abstract （235）      PDF （1140KB）（94）       Knowledge map    Novel gel polymer electrolytes (GPEs) composed of polyvinyl alcohol (PVA) and sodium thiocyanate were developed via a solution casting technique. An ionic liquid (IL), 1-ethyl-3-methyl-imidazolium tricyanomethanide ([EMIM][TCM]), was doped into a polymer–salt complex system (PVA + NaSCN) to further enhance the conductivity. IL-doped polymer electrolyte (ILDPE) films were characterized using X-ray diffraction (XRD), polarized optical microscopy (POM), Fourier-transform infrared (FTIR) spectroscopy, and conductivity measurements. XRD was performed to check the degree of crystallinity and amorphicity of the ILDPE films, and the amorphicity of GPEs increased with the increase of the IL content. POM was employed to evaluate the changes in the surface morphology due to the inclusion of salt and IL in the PVA. The compositional nature of the GPE films was examined via FTIR studies. The electrical and electrochemical properties were characterized by cyclic voltammetry and electrochemical impedance spectroscopy. The maximum conductivity for the GPE film was estimated to be 1.10 × 10-5 S/cm for 6% (mass fraction) of IL in the polymer–salt complex. The ionic transference number was approximately 0.97. An electrochemical double-layer capacitor (EDLC) was built from optimized GPE films and reduced graphene oxide-based electrodes. The specific capacitance calculated from the cyclic voltammograms of the EDLC cells was 3 F/g. Reference | Related Articles | Metrics

Select

Deformable Registration Algorithm via Non-subsampled Contourlet Transform and Saliency Map CHANG Qing∗ (常 青), YANG Wenyou (杨文友), CHEN Lanlan (陈兰岚) J Shanghai Jiaotong Univ Sci    2022, 27 (4): 452-462.   DOI: 10.1007/s12204-022-2428-3 Abstract （113）      PDF （4867KB）（31）       Knowledge map    Medical image registration is widely used in image-guided therapy and image-guided surgery to esti- mate spatial correspondence between planning and treatment images. However, most methods based on intensity have the problems of matching ambiguity and ignoring the influence of weak correspondence areas on the overall registration. In this study, we propose a novel general-purpose registration algorithm based on free-form defor- mation by non-subsampled contourlet transform and saliency map, which can reduce the matching ambiguities and maintain the topological structure of weak correspondence areas. An optimization method based on Markov random fields is used to optimize the registration process. Experiments on four public datasets from brain, car- diac, and lung have demonstrated the general applicability and the accuracy of our algorithm compared with two state-of-the-art methods. Reference | Related Articles | Metrics

Select

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 Abstract （158）      PDF （1049KB）（30）       Knowledge map    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

Select

Prediction of COVID-19 Outbreak in China and Optimal Return Date for University Students Based on Propagation Dynamics HUANG Ganyu (黄甘雨), PAN Qiaoyi (潘荍仪), ZHAO Shuangying (赵双楹), GAO Yucen (高宇岑), GAO Xiaofeng (高晓沨) J Shanghai Jiaotong Univ Sci    2020, 25 (2): 140-146.   DOI: 10.1007/s12204-020-2167-2 Abstract （546）      PDF （550KB）（328）       Knowledge map    On 12 December 2019, a novel coronavirus disease, named COVID-19, began to spread around the world from Wuhan, China. It is useful and urgent to consider the future trend of this outbreak. We establish the 4+1 penta-group model to predict the development of the COVID-19 outbreak. In this model, we use the collected data to calibrate the parameters, and let the recovery rate and mortality change according to the actual situation. Furthermore, we propose the BAT model, which is composed of three parts: simulation of the return rush (Back), analytic hierarchy process (AHP) method, and technique for order preference by similarity to an ideal solution (TOPSIS) method, to figure out the best return date for university students. We also discuss the impacts of some factors that may occur in the future, such as secondary infection, emergence of effective drugs, and population flow from Korea to China. Reference | Related Articles | Metrics

Select

CIRD-F: Spread and Influence of COVID-19 in China ZHOU Lingyun (周凌云), WU Kaiwei (吴凯伟), LIU Hanzhi (刘涵之), GAO Yuanning (高远宁), GAO Xiaofeng (高晓沨) J Shanghai Jiaotong Univ Sci    2020, 25 (2): 147-156.   DOI: 10.1007/s12204-020-2168-1 Abstract （821）      PDF （887KB）（366）       Knowledge map    The outbreak of coronavirus disease 2019 (COVID-19) has been spreading rapidly in China and the Chinese government took a series of policies to control the epidemic. Therefore, it will be helpful to predict the tendency of the epidemic and analyze the influence of official policies. Existing models for prediction, such as cabin models and individual-based models, are either oversimplified or too meticulous, and the influence of the epidemic was studied much more than that of official policies. To predict the epidemic tendency, we consider four groups of people, and establish a propagation dynamics model. We also create a negative feedback to quantify the public vigilance to the epidemic. We evaluate the tendency of epidemic in Hubei and China except Hubei separately to predict the situation of the whole country. Experiments show that the epidemic will terminate around 17 March 2020 and the final number of cumulative infections will be about 78 191 (prediction interval, 74 872 to 82 474). By changing the parameters of the model accordingly, we demonstrate the control effect of the policies of the government on the epidemic situation, which can reduce about 68% possible infections. At the same time, we use the capital asset pricing model with dummy variable to evaluate the effects of the epidemic and official policies on the revenue of multiple industries. Reference | Related Articles | Metrics

Select

Demand Analysis and Management Suggestion: Sharing Epidemiological Data Among Medical Institutions in Megacities for Epidemic Prevention and Control CAI Qinyi (蔡沁怡), MI Yiqun (宓轶群), CHU Zhaowu (储昭武), ZHENG Yuanyi (郑元义), CHEN Fang (陈方), LIU Yicheng (刘义成) J Shanghai Jiaotong Univ Sci    2020, 25 (2): 137-139.   DOI: 10.1007/s12204-020-2166-3 Abstract （491）      PDF （105KB）（303）       Knowledge map    During the prevention of coronavirus disease 2019 (COVID-19), epidemiological data is essential for controlling the source of infection, cutting off the route of transmission, and protecting vulnerable populations. Following Law of the People’s Republic of China on Prevention and Treatment of Infectious Diseases and other related regulations, medical institutions have been authorized to collect the detailed information of patients, while it is still a formidable task in megacities because of the significant patient mobility and the existing information sharing barrier. As a smart city which strengthens precise epidemic prevention and control, Shanghai has established a multi-department platform named “one-net management” on dynamic information monitoring. By sharing epidemiological data with medical institutions under a safe environment, we believe that the ability to prevent and control epidemics among medical institutions will be effectively and comprehensively improved. Reference | Related Articles | Metrics

Select

Airframe Damage Region Division Method Based on Structure Tensor Dynamic Operator CAI Shuyu∗ (蔡舒妤), SHI Lizhong (师利中) J Shanghai Jiaotong Univ Sci    2022, 27 (6): 757-767.   DOI: 10.1007/s12204-022-2498-2 Abstract （191）      PDF （1607KB）（76）       Knowledge map    In order to improve the accuracy of damage region division and eliminate the interference of damage adjacent region, the airframe damage region division method based on the structure tensor dynamic operator is proposed in this paper. The structure tensor feature space is established to represent the local features of damage images. It makes different damage images have the same feature distribution, and transform varied damage region division into consistent process of feature space division. On this basis, the structure tensor dynamic operator generation method is designed. It integrates with bacteria foraging optimization algorithm improved by defining double fitness function and chemotaxis rules, in order to calculate the parameters of dynamic operator generation method and realize the structure tensor feature space division. And then the airframe damage region division is realized. The experimental results on different airframe structure damage images show that compared with traditional threshold division method, the proposed method can improve the division quality. The interference of damage adjacent region is eliminated. The information loss caused by over-segmentation is avoided. And it is efficient in operation, and consistent in process. It also has the applicability to different types of structural damage. Reference | Related Articles | Metrics

Select

Time-Varying Delay and Quantization Error LI Bin (李 斌), WAN Yi-ming (万一鸣), YE Hao (叶 昊) Journal of shanghai Jiaotong University (Science)    2011, 16 (5): 513-518.   DOI: 10.1007/s12204-011-1181-9 Abstract （1806）      PDF （303KB）（3043）       Knowledge map    Abstract:  Problems related to fault detection of networked control systems (NCSs) with both uncertain time-varying delay and quantization error are studied in this paper. A novel model with the form of polytopic uncertainty is given to represent the influences of both the time-varying delay and the quantization error, and then the reference model based method is used to design the residual generator that is robust to both unknown network-induced delay and unknown inputs. A numerical example is also given to illustrate the merits of the presented method. The proposed method can be regarded as an extension of the authors' former work, which can only deal with time-varying delay. Reference | Related Articles | Metrics

Select

Ant Colony Algorithm Path Planning Based on Grid Feature Point Extraction LI Erchao∗ (李二超), QI Kuankuan (齐款款) J Shanghai Jiaotong Univ Sci    2023, 28 (1): 86-99.   DOI: 10.1007/s12204-023-2572-4 Abstract （134）      PDF （1196KB）（77）       Knowledge map    Aimed at the problems of a traditional ant colony algorithm, such as the path search direction and field of view, an inability to find the shortest path, a propensity toward deadlock and an unsmooth path, an ant colony algorithm for use in a new environment is proposed. First, the feature points of an obstacle are extracted to preprocess the grid map environment, which can avoid entering a trap and solve the deadlock problem. Second, these feature points are used as pathfinding access nodes to reduce the node access, with more moving directions to be selected, and the locations of the feature points to be selected determine the range of the pathfinding field of view. Then, based on the feature points, an unequal distribution of pheromones and a two-way parallel path search are used to improve the construction efficiency of the solution, an improved heuristic function is used to enhance the guiding role of the path search, and the pheromone volatilization coefficient is dynamically adjusted to avoid a premature convergence of the algorithm. Third, a Bezier curve is used to smooth the shortest path obtained. Finally, using grid maps with a different complexity and different scales, a simulation comparing the results of the proposed algorithm with those of traditional and other improved ant colony algorithms verifies its feasibility and superiority. Reference | Related Articles | Metrics

Select

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 Abstract （169）      PDF （1855KB）（74）       Knowledge map    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

Select

Real-Time Trajectory Planning for On-road Autonomous Tractor-Trailer Vehicles SHEN Qiyue (沈琦越), WANG Bing (王 冰), WANG Chunxiang∗ (王春香) J Shanghai Jiaotong Univ Sci    2021, 26 (5): 722-730.   DOI: 10.1007/s12204-021-2362-9 Abstract （300）      PDF （1546KB）（126）       Knowledge map    Tractor-trailer vehicles, which are composed of a car-like tractor towing a passive trailer, have been widely deployed in the transportation industry, and trajectory planning is a critical step in enabling such a system to drive autonomously. Owing to the properties of being highly nonlinear and nonholonomic with complex dynamics, the tractor-trailer system poses great challenges to the development of motion-planning algorithms. In this study, an indirect trajectory planning framework for a tractor-trailer vehicle under on-road driving is presented to deal with the problem that the traditional planning framework cannot consider the feasibility and quality simultaneously in real-time trajectory generation of the tractor-trailer vehicle. The indirect planning framework can easily handle complicated tractor-trailer dynamics and generate high-quality, obstacle-free trajectory using quintic polynomial spline, speed pro?le optimization, forward simulation, and properly designed cost functions. Simulations under di?erent driving scenarios and trajectories with di?erent driving requirements are conducted to validate the performance of the proposed framework. Reference | Related Articles | Metrics

Select

Camera-Radar Fusion Sensing System Based on Multi-Layer Perceptron YAO Tong (姚 彤), WANG Chunxiang(王春香), QIAN Yeqiang(钱烨强) J Shanghai Jiaotong Univ Sci    2021, 26 (5): 561-568.   DOI: 10.1007/s12204-021-2345-x Abstract （288）      PDF （1189KB）（182）       Knowledge map    Environmental perception is a key technology for autonomous driving. Owing to the limitations of a single sensor, multiple sensors are often used in practical applications. However, multi-sensor fusion faces some problems, such as the choice of sensors and fusion methods. To solve these issues, we proposed a machine learning-based fusion sensing system that uses a camera and radar, and that can be used in intelligent vehicles. First, the object detection algorithm is used to detect the image obtained by the camera; in sequence, the radar data is preprocessed, coordinate transformation is performed, and a multi-layer perceptron model for correlating the camera detection results with the radar data is proposed. The proposed fusion sensing system was verified by comparative experiments in a real-world environment. The experimental results show that the system can effectively integrate camera and radar data results, and obtain accurate and comprehensive object information in front of intelligent vehicles. Reference | Related Articles | Metrics

Select

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 Abstract （185）      PDF （5084KB）（59）       Knowledge map    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

Select

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 Abstract （233）      PDF （2503KB）（82）       Knowledge map    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

Select

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 Abstract （249）      PDF （156KB）（102）       Knowledge map    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

Select

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 Abstract （214）      PDF （345KB）（70）       Knowledge map    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

Select

Construction on Aerodynamic Surrogate Model of Stratospheric Airship QIN Pengfei (秦鹏飞), WANG Xiaoliang∗ (王晓亮) J Shanghai Jiaotong Univ Sci    2022, 27 (6): 768-779.   DOI: 10.1007/s12204-022-2494-6 Abstract （167）      PDF （3866KB）（54）       Knowledge map    Stratospheric airship can stay at an altitude of 20 km for a long time and carry various loads to achieve long-term stable applications. Conventional stratospheric airship configuration mainly includes a low-resistance streamline hull and inflatable “X”-layout fins that realize the self-stabilization. A fast aerodynamic predictive method is needed in the optimization design of airship configuration and the flight performance analysis. In this paper, a predictive surrogate model of aerodynamic parameters is constructed for the stratospheric airship with “X” fins based on the neural network. First, a geometric shape parameterized model, and a flow field parameterized model were established, and the aerodynamic coefficients of airships with different shapes used as the training and test samples were calculated based on computational fluid dynamics (SA turbulence model). The improved Bayesian regularized neural network was used as the surrogate model, and 20 types of airships with different shapes were used to test the effectiveness of network. It showed that the correlation coefficients of Cx, Cy, Cz, CM,x, CM,y, CM,z were 0.928 7, 0.991 7, 0.991 9, 0.958 2, 0.986 1, 0.984 2, respectively. The aerodynamic coefficient distribution contour at different angles of attack and sideslip angles is used to verify the reliability of the method. The method can provide an effective way for a rapid estimation of aerodynamic coefficients in the airship design. Reference | Related Articles | Metrics

Select

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 Abstract （146）      PDF （2406KB）（72）       Knowledge map    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

Select

D2EA: Depict the Epidemic Picture of COVID-19 LIU Chenzhengyi (刘陈正轶), ZHAO Jingwei (赵经纬), LIU Guohang (刘国航), GAO Yuanning (高远宁), GAO Xiaofeng (高晓沨) J Shanghai Jiaotong Univ Sci    2020, 25 (2): 165-176.   DOI: 10.1007/s12204-020-2170-7 Abstract （429）      PDF （748KB）（332）       Knowledge map    The outbreak of coronavirus disease 2019 (COVID-19) has aroused a global alert. To release social panic and guide future schedules, this article proposes a novel mathematical model, the Delay Differential Epidemic Analyzer (D2EA), to analyze the dynamics of epidemic and forecast its future trends. Based on the traditional Susceptible-Exposed-Infectious-Recovered (SEIR) model, the D2EA model innovatively introduces a set of quarantine states and applies both ordinary differential equations and delay differential equations to describe the transition between two states. Potential variations of practical factors are further considered to reveal the true epidemic picture. In the experiment part, we use the D2EA model to simulate the epidemic in Hubei Province. Fitting to the collected real data as non-linear optimization, the D2EA model forecasts that the accumulated confirmed infected cases in Hubei Province will reach the peak at the end of February and then steady down. We also evaluate the effectiveness of the quarantine measures and schedule the date to reopen Hubei Province. Reference | Related Articles | Metrics

Select

Effect of Deflectors on the Flow Characteristics of a Square Pipe with a 90° Bend JIANG Chenqi (江晨琦), GONG Zhaoxin (宫兆新) J Shanghai Jiaotong Univ Sci    2021, 26 (2): 163-169.   DOI: 10.1007/s12204-021-2278-4 Abstract （326）      PDF （2608KB）（85）       Knowledge map    Pipe flow is a classic hydrodynamic issue. Most pipelines contain bends, and bends cause energy loss and distort the flow because of secondary flow. Deflectors are often used to adjust the flow quality in a bend. In this study, a numerical simulation using ANSYS Fluent 19.0 is used to analyze the effects of the deflector number, location and angle on the flow characteristics of a square pipe with a 90° bend. The velocity non-uniformity and the head loss are analyzed quantitatively. The secondary flow is presented visually, and its evolution characteristics are assessed. An optimized installation scheme for the deflectors is discussed, and a reference is provided for controlling the flow quality in bends via deflectors. Reference | Related Articles | Metrics

Select

Shipping Economics Development: A Review from the Perspective of the Shipping Industry Chain for the Past Four Decades XIA Qiliang (夏启亮), CHEN Feier ∗ (陈飞儿) J Shanghai Jiaotong Univ Sci    2022, 27 (3): 424-436.   DOI: 10.1007/s12204-022-2449-y Abstract （105）      PDF （622KB）（47）       Knowledge map    To know the development of shipping economics, it is meaningful to overview shipping economics systemically from the perspective of markets and the shipping industry chain. To stimulate future research, this article presents an introduction to the evolution of research models including static models, dynamic models and networks theory, the characteristics of shipping markets including volatility, seasonal and market cycle, and a comprehensive review of the development of shipping economics in the past four decades. We review shipping economics in the following steps: single market’s research is generalized including the freight market, financial market including FFA market and investment market, shipbuilding market, and secondhand market; two markets’ correlation, information transmission, spillover effects, and other rules in shipping markets are surveyed; the correlation and risk of multi-markets are also investigated. Then, we summarize relationships of the shipping industry chain. Finally, we figure out issues in this field that need further study. Reference | Related Articles | Metrics

Select

Reliability Evaluation of Two-Phase Degradation Process with a Fuzzy Change-Point LIU Kai1 (刘 凯), DANG Wei1 (党 炜), ZOU Tianji1,2∗ (邹田骥), LÜ Congmin1 (吕从民), LI Peng1,2 (李 鹏), ZHANG Haitao1 (张海涛) J Shanghai Jiaotong Univ Sci    2022, 27 (6): 867-872.   DOI: 10.1007/s12204-021-2323-3 Abstract （139）      PDF （484KB）（47）       Knowledge map    For some products, degradation mechanisms change during testing, and therefore, their degradation patterns vary at different points in time; these points are called change-points. Owing to the limitation of measurement costs, time intervals for degradation measurements are usually very long, and thus, the value of change-points cannot be determined. Conventionally, a certain degradation measurement is selected as the change-point in a two-phase degradation process. According to the tendency of the two-phase degradation process, the change-point is probably located in the interval between two neighboring degradation measurements, and it is a fuzzy variable. The imprecision of the change-point may lead to the incorrect product’s reliability evaluation results. In this paper, based on the fuzzy theory, a two-phase degradation model with a fuzzy change-point and a statistical analysis method are proposed. First, a two-phase Wiener degradation model is developed according to the membership function of the change-point. Second, the reliability evaluation is carried out using maximum likelihood estimation and a fuzzy simulation approach. Finally, the proposed methodology is verified via a case study. The results of the study show that the proposed methodology can achieve more believable reliability evaluation results compared with those of the conventional approach. Reference | Related Articles | Metrics

Select

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 Abstract （146）      PDF （1368KB）（47）       Knowledge map    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

Select

Multi-UAV Route Re-Generation Method Based on Trajectory Data YUAN Dongdong (袁冬冬), WANG Yankai∗ (王彦恺), BAI Jiaqi (白嘉琪) J Shanghai Jiaotong Univ Sci    2022, 27 (6): 806-816.   DOI: 10.1007/s12204-021-2332-2 Abstract （116）      PDF （1409KB）（47）       Knowledge map    A large quantity of unmanned aerial vehicle (UAV) trajectory data related to air traffic information has important value in engineering fields. However, the cost of data and trajectory processing limits the applications, and as the number of UAVs increases rapidly, future UAVs’ path data will be very large. Therefore, this paper designs a multi-UAV route re-generation method based on trajectory data, which can realize the UAVs’ path data compression, de-aggregation, and regeneration tasks. Based on the trajectory data, the three-dimensional Douglas-Peucker algorithm is used to compress the trajectory data to reduce the storage space. The improved B-spline path smoothing algorithm based on the reversing control point is used to depolymerize and smooth the path. Simulation experiments show that the above multi-UAV route re-generation algorithm can obtain a more optimized path while maintaining the important characteristics of the original path. Reference | Related Articles | Metrics

Select

UAV Task Allocation for Hierarchical Multiobjective Optimization in Complex Conditions Using Modified NSGA-III with Segmented Encoding JIN Yudong (靳宇栋), FENG Jiabo (冯家波), ZHANG Weijun (张伟军) J Shanghai Jiaotong Univ Sci    2021, 26 (4): 431-445.   DOI: 10.1007/s12204-021-2269-5 Abstract （348）      PDF （2668KB）（292）       Knowledge map    With the recent boom in unmanned aerial vehicle (UAV) technology, many UAV applications involving complex and risky tasks in military and civilian fields have emerged, such as military strikes and disaster monitoring. Task allocation for UAVs is the process of planning the division of work among UAVs, controlled from ground stations by human operators. This study formulates the UAV task-allocation problem as an extended traveling salesman problem and presents a novel UAV task-allocation model for complex air concentration monitoring tasks. Then, an optimized non-dominated sorting genetic algorithm III (NSGA-III) based on a twin-exclusion mechanism, hierarchical objective-domination operator, and segmented gene encoding (i.e., NSGA-III-TEHOD) is developed to solve complex task-allocation problems involving multiple UAVs, hierarchical objectives, obstacles, and ambient wind. The algorithm is tested in several simulations, and the results demonstrate that the new algorithm outperforms NSGA-III, non-dominated sorting genetic algorithm II (NSGA-II), and genetic algorithm (GA) in terms of efficiency of global convergence and early maturation prevention and is available for the hierarchical objective-optimization problems. Reference | Related Articles | Metrics

Select

Two Generative Design Methods of Hospital Operating Department Layouts Based on Healthcare Systematic Layout Planning and Generative Adversarial Network ZHAO Chaowang (赵朝望), YANG Jian (杨健), XIONG Wuyue (熊吴越), LI Jiatong (李佳潼) J Shanghai Jiaotong Univ Sci    2021, 26 (1): 103-115.   DOI: 10.1007/s12204-021-2265-9 Abstract （420）      PDF （1551KB）（121）       Knowledge map    With the increasing demands of health care, the design of hospital buildings has become increasingly demanding and complicated. However, the traditional layout design method for hospital is labor intensive, time consuming and prone to errors. With the development of artificial intelligence (AI), the intelligent design method has become possible and is considered to be suitable for the layout design of hospital buildings. Two intelligent design processes based on healthcare systematic layout planning (HSLP) and generative adversarial network (GAN) are proposed in this paper, which aim to solve the generation problem of the plane functional layout of the operating departments (ODs) of general hospitals. The first design method that is more like a mathematical model with traditional optimization algorithm concerns the following two steps: developing the HSLP model based on the conventional systematic layout planning (SLP) theory, identifying the relationship and flows amongst various departments/units, and arriving at the preliminary plane layout design; establishing mathematical model to optimize the building layout by using the genetic algorithm (GA) to obtain the optimized scheme. The specific process of the second intelligent design based on more than 100 sets of collected OD drawings includes: labelling the corresponding functional layouts of each OD plan; building image-to-image translation with conditional adversarial network (pix2pix) for training OD plane layouts, which is one of the most representative GAN models. Finally, the functions and features of the results generated by the two methods are analyzed and compared from an architectural and algorithmic perspective. Comparison of the two design methods shows that the HSLP and GAN models can autonomously generate new OD plane functional layouts. The HSLP layouts have clear functional area adjacencies and optimization goals, but the layouts are relatively rigid and not specific enough. The GAN outputs are the most innovative layouts with strong applicability, but the dataset has strict constraints. The goal of this paper is to help release the heavy load of architects in the early design stage and present the effectiveness of these intelligent design methods in the field of medical architecture. Reference | Related Articles | Metrics

Select

Low Voltage Indium-Oxide-Zinc Thin Film Transistor Gated by KH550 Solid Electrolyte DONG Qian (董 钱), GUO Liqiang(郭立强), WANG Weilin (王伟琳), CHENG Guanggui (程广贵) J Shanghai Jiaotong Univ Sci    2023, 28 (2): 186-191.   DOI: 10.1007/s12204-022-2421-x Abstract （93）      PDF （763KB）（46）       Knowledge map    With the development of integrate circuit and artificial intelligence, many kinds of transistors have been invented. In recent years, wide attention has been paid to the oxide thin film transistors due to its ease preparation, low cost, and suitability for mass production. Traditionally used gate dielectric film (such as silicon dioxide film) in oxide thin film transistor owns low dielectric constant, which leads to weak capacitive coupling between the gate dielectric layer and the channel layer. As a result, high voltage (10 V or more) needs to be applied on the gate electrode in order to achieve the purpose of regulating the current of channel layer. Therefore, new oxide thin film needs to be developed. In this work, silane coupling agents (3-triethoxysilypropyla-mine) KH550 solid electrolyte film was obtained by spin coating-process. The KH550 solid electrolyte was used as gate dielectric layer to fabricate low-voltage indium zinc oxide thin film transistor. The surface topography and thickness of KH550 solid electrolyte film were characterized by atomic force microscope and field emission scanning electron microscope, respectively. The capacitance-frequency curve of the sample was measured by impedance analyzer (Soloartron 1260A), and the electrical characteristics of the sample were analyzed by a semiconductor parameter analyzer (Keithley 4200 SCS). A maximum specific capacitance of about 7.3 μF/cm2 is obtained at 1 Hz. The transistor shows a good stability of pulse operation and negative bias voltage, the operation voltage is only 2 V, the current on/off ratio is about 1.24 × 106, and the subthreshold swing is 169.2 mV/dec. The development of KH550 solid electrolyte gate dielectric provides a novel way for the research of oxide thin film transistor. Reference | Related Articles | Metrics

Select

Action-aware Encoder-Decoder Network for Pedestrian Trajectory Prediction FU Jiawei∗ (傅家威), ZHAO Xu (赵 旭) J Shanghai Jiaotong Univ Sci    2023, 28 (1): 20-27.   DOI: 10.1007/s12204-023-2565-3 Abstract （150）      PDF （775KB）（46）       Knowledge map    Accurate pedestrian trajectory predictions are critical in self-driving systems, as they are fundamental to the response- and decision-making of ego vehicles. In this study, we focus on the problem of predicting the future trajectory of pedestrians from a first-person perspective. Most existing trajectory prediction methods from the first-person view copy the bird’s-eye view, neglecting the differences between the two. To this end, we clarify the differences between the two views and highlight the importance of action-aware trajectory prediction in the first-person view. We propose a new action-aware network based on an encoder-decoder framework with an action prediction and a goal estimation branch at the end of the encoder. In the decoder part, bidirectional long short-term memory (Bi-LSTM) blocks are adopted to generate the ultimate prediction of pedestrians’ future trajectories. Our method was evaluated on a public dataset and achieved a competitive performance, compared with other approaches. An ablation study demonstrates the effectiveness of the action prediction branch. Reference | Related Articles | Metrics

Select

Strength-Toughness Improvement of 15-5PH Stainless Steel by Double Aging Treatment TE Rigele (特日格乐), ZHANG Yutuo, ∗ (张玉妥) J Shanghai Jiaotong Univ Sci    2023, 28 (2): 270-279.   DOI: 10.1007/s12204-021-2390-5 Abstract （149）      PDF （3166KB）（46）       Knowledge map    To obtain better strength-toughness balance of 15-5PH stainless steel, a double aging treatment is proposed to investigate the mechanical properties and microstructure evolution. In this study, Cu precipitates and reversed austenite played a determining role to improve strength-toughness combination. The microstructure was observed using electron backscattered diffraction, transmission electron microscopy and scanning transmission electron microscopy. The volume fractions of Cu precipitates and reversed austenite were calculated with Thermo-Calc software and measured by X-ray diffraction. The results showed that the reversed austenite is formed at the martensitic lath boundaries and its volume fraction also increases with the increase of the aging temperature. At the same time, the size of the Cu precipitates gradually increases. Compared with the traditional single aging and double aging treatment, double aging treatment of 15-5PH stainless steel can increase the toughness while retaining the necessary strength. During double aging of 550 ℃ × 4 h + 580 ℃ × 1 h, 15-5PH stainless steel has the best strength and low-temperature (- 40 ℃) toughness match. Its yield strength, ultimate tensile strength and the Charpy impact energy are 1.037 GPa, 1.086 GPa and 179 J, respectively. Reference | Related Articles | Metrics

Select

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 Abstract （173）      PDF （3921KB）（57）       Knowledge map    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

Select

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 Abstract （213）      PDF （185KB）（85）       Knowledge map    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

Select

Fabrication and Characterization of Graphene-Enhanced Hollow Microlattice Materials BAO Haisheng (鲍海生), LIU Longquan∗ (刘龙权) J Shanghai Jiaotong Univ Sci    2023, 28 (2): 192-196.   DOI: 10.1007/s12204-021-2339-8 Abstract （83）      PDF （662KB）（44）       Knowledge map    A method was developed and proposed to fabricate graphene-enhanced hollow microlattice materials, which include the three-dimensional (3D) printing, nanocomposite electroless plating, and polymer etching technologies. The surface morphology and uniformity of as-deposited coatings were systematically characterized and analyzed. Moreover, the mechanical properties of the microlattices were investigated through quasi-static compression tests. The results demonstrated that a uniform Nickel-phossphorous-graphene (Ni-P-G) coating was obtained successfully, and the specific modulus and strength were increased by adding graphene into the microlattice materials. The optimal mass concentration of graphene nanoplatelets was obtained after comparing the specific modulus and strength of the materials with different densities of graphene, and the strength mechanism was discussed. Reference | Related Articles | Metrics