A5100337072- Transportation Planning and Optimization
- Transportation and Mobility Innovations
- BIM and Construction Integration
- Urban Transport and Accessibility
- Product Development and Customization
- Emergency and Acute Care Studies
- Traffic Prediction and Management Techniques
- Occupational Health and Safety Research
- Sepsis Diagnosis and Treatment
- Data Management and Algorithms
- Advanced Materials and Mechanics
- Human Mobility and Location-Based Analysis
- Manufacturing Process and Optimization
- Evaluation and Optimization Models
- Remote Sensing and Land Use
- Chronic Disease Management Strategies
- Medical Imaging and Analysis
- Outsourcing and Supply Chain Management
- COVID-19 Clinical Research Studies
- Radiology practices and education
- Library Science and Information Literacy
- Healthcare Systems and Public Health
- Trauma, Hemostasis, Coagulopathy, Resuscitation
- Vehicle Dynamics and Control Systems
- Blockchain Technology Applications and Security
Beijing Jiaotong University
2011-2025
Harbin Institute of Technology
2024
Nanjing University of Science and Technology
2023
Wuchang University of Technology
2021
Chinese PLA General Hospital
2021
Qilu Hospital of Shandong University
2019
Beijing Institute of Technology
2018
Zhengzhou University of Light Industry
2012
Arizona State University
2010
Beijing University of Technology
2010
Most conventional active frequency selective surfaces (AFSSs) are designed with a dc biasing circuit to allow the application of voltage across any component. An innovative method designing AFSS is here described. It involves using an induced surface loading components. This serves as sign and facilitates control FSS's transmission properties. The simulated results prove that passband exists on FSS at 3.3 GHz when it exposed less intense electric field; field intensity (EFI) higher than 70...
Traumatic pneumothorax is a complex condition that challenging to diagnose, particularly in hospitals, underdeveloped areas, and during mass casualty events. This study aimed evaluate the potential of machine learning (ML) for diagnosing assessing traumatic pneumothorax. We extracted 33 vital signs blood gas parameters from MIMIC-IV database, selecting 12 clinically significant features as inputs four ML algorithms: extreme gradient boosting (XGBoost), artificial neural network (ANN),...
Financial Technology (FinTech) employs technological advancements and sharing economy models to improve financing services. The emergence of the Internet-of-Things (IoT) has changed way humans interact with surrounding world. In this paper, we present a proactive FinTech model that uses IoT intelligence deliver positive InsurTech feedback. We propose an system three main components: monitoring feedback device, fog analytics engine, cloud server. driving use sensor-recorded data calculate in...
To alleviate traffic congestion and traffic-related environmental pollution caused by the increasing numbers of private cars, public transport (PT) is highly recommended to travelers. However, there an obvious contradiction between diversification travel demands simplification PT service. Customized bus (CB), as innovative supplementary mode service, aims provide demand-responsive direct transit service travelers with similar demands. But how obtain accurate demands? It passive limited...
With the development of big data and deep learning, bus passenger flow prediction considering real-time becomes possible. Real-time traffic helps to grasp dynamics, provide early warning for a sudden support plan changes, improve stability urban transportation systems. To solve problem data, this paper proposes novel network model based on long short-term memory (LSTM) networks. The includes four parts: feature extraction Xgboost model, information coding historical decoding multi-layer...
Early warning prediction of traumatic hemorrhagic shock (THS) can greatly reduce patient mortality and morbidity. We aimed to develop validate models with different stepped feature sets predict THS in advance. From the PLA General Hospital Emergency Rescue Database Medical Information Mart for Intensive Care III, we identified 604 1,614 patients, respectively. Two popular machine learning algorithms (i.e., extreme gradient boosting [XGBoost] logistic regression) were applied. The area under...
The customized bus (CB) is an innovative and environmental supplementary mode of public transport, providing demand-responsive user-oriented service to specific passenger groups with similar travel demands, especially commuters, based on online reservations. However, sufficient demand essential for the successful operation CB. purpose this study analyze factors influencing attraction CB which tied ordered shift decisions, do no transfer CB, remain undecided, A combination revealed preference...
Abstract A high-performing interpretable model is proposed to predict the risk of deterioration in coronavirus disease 2019 (COVID-19) patients. The was developed using a cohort 3028 patients diagnosed with COVID-19 and exhibiting common clinical symptoms that were internally verified (AUC 0.8517, 95% CI 0.8433, 0.8601). total 15 high factors for their approximate warning ranges identified. This included prothrombin time (PT), activity, lactate dehydrogenase, international normalized ratio,...
在遥感、地理信息系统和全球定位系统技术综合应用于山区土地资源动态监测领域的研究工作中 ,探讨采用以图像差值法为主 ,分类后比较法为辅提取土地利用变化信息的基本思路和方法 ,提出采用定量统计分析的方法来选择合适的差值计算波段和相应的变化阈值。在数据分析过程中 ,GPS测量数据发挥了重要作用。
The pricing of ride-hailing platforms (e.g., Didi Rider and Uber) is heavily simultaneously influenced by the cross-group network effect congestion effect. To analyze bilateral under influence these two effects, in this paper we construct a game-theoretic model four different scenarios equilibrium outcomes. results show that: (1) when both passengers drivers are sensitive to hassle costs, if on passenger side higher than that driver side, then platform’s sides increases with increase effect,...
Field failure data often exhibit extra heterogeneity as early may have quite different distribution characteristics from later data. These infant failures come a defective subpopulation instead of the normal product population. Many exiting methods for field analyses focus only on estimation hypothesized mixture model, while model identification is ignored. This paper aims to develop efficient, accurate both detecting heterogeneity, and estimating parameters. Mixture detection achieved by...
Affordability is a key factor in today's manufacturing industry. Therefore, cost estimation at the design stage necessary to optimise product design. This paper presents model for and of composite structures. The model, known as Fuzzy Multi-attribute Utility, combines Utility Theory Logic. implemented assign utility values drivers according expert opinions, calculate index using fuzzy logic methods. method can be used early phase where information normally incomplete or uncertain.
The chattering is inevitable in using Variable Structure Controller (VSC) to control two-wheeled unstable vehicle. Although the traditional methods which are improved reaching law and switching surface effectively impair chattering, they anti-interfering of VSC at same time. To solve this problem, dynamic pseudo sliding mode with disturbance compensation term designed paper, not only impairs but also improve ability.
Construction technology safety management under the background of BIM and information system modeling is studied in this paper. Fuzzy comprehensive evaluation method widely used risk assessment, prediction effect very significant, but determination membership function, degree weight object subjective, lacks ability to adapt environment, cannot dynamically adjust with problems such as adjustment still exist. Hence, data modelling are combined for better performance. The proposed model...
To propose a method of prediction for fatal gastrointestinal bleeding recurrence in hospital and feature selection via machine learning models.728 digestive tract hemorrhage samples were extracted from the first aid database PLA General Hospital, 343 patients among them diagnosed as hospital. A total 64 physiological or laboratory indicators screened. Based on ten-fold cross-validation, Logistic regression, AdaBoost XGBoost used classification comparison. was to search sequence features, key...
The one-way running time of the bus has been paid a lot attention especially for passengers to decide their travels and companies make schedules. Recent research provide some machine learning algorithms prediction similar topics, however without satisfactory results. In order improve predictive accuracy time, four including LSTM, MLR, KNN, XGBoost are selected integrated through linear regression model as an effectively model. More specifically, dynamic static factors public transportation...
In this paper, we introduce the concept of software-focused chain. A software focused product consists hardware component and component, where is either higher value part product. We study a service supply chain based on case Beijing UniStrong Company. discuss common unique issues that has compared with traditional Issues challenges management have also been studied in paper.
The project management is activities accompanied with demanding and high risks, so it necessary to evaluate its risks. Currently methods of risk assessment more, which the application fuzzy mathematics method most widely, but this in determining weight factor exists some limitations. evaluation model based on entropy has been built by analyzing introduction "ertropy weight" concept text, thus overcomes identified limitations weight, when applied process construction assessment, proves be...
With the development and maturation of mining information technology, computer networks communication digital mine has become a new trend. In this article, author makes research on key technology algorithm entity modeling in three-dimensional visualization system coalmine, particularly relation to laneway industry square. On basis, establish database which we put basic data model cross-section. By modeling, physical situation is displayed more clearly, can facilitate people understand...
To explore a method of screening the core indicators in emergency database that can be used to evaluate in-hospital fatal gastrointestinal rebleeding by using big data algorithm.Based on Chinese PLA General Hospital, through retrieval technology, all 647 patients diagnosed as bleeding were enrolled, except those who admitted hospital for first time and whose hemoglobin (Hb) was less than 90 g/L or did not undergo Hb test. Among them, there 313 group (fatal hospital) 334 non-rebleeding (no...
On the premise of fully studying disaster medical rescue monitoring mechanism in emergencies at home and abroad, functional requirements domestic system was analyzed this paper, logical framework data structure with privacy protection designed by department emergency Chinese PLA General Hospital, information management School Economics Management Beijing Jiaotong University, Information Nanjing University. Three major modules were realized system: reporter management, upload, search. Android...
Objective To provide the basis for popularization and application of QCC,we investigate operation status nursing quality control circle (QCC) in Shandong Province, analyze existing problems. Methods A self-designed questionnaire which Cronbach’s α=0.905, was used to attendees annual meeting Nursing Committee Hospital Quality Management Alliance by convenience sampling. The filled out online mobile phone scanning. SPSS 23.0 software data. Results Among 224 respondents,score GSES...