A5027533682- Artificial Intelligence in Healthcare
- Human Mobility and Location-Based Analysis
- Advanced Sensor and Control Systems
- Data Mining Algorithms and Applications
- Machine Learning in Healthcare
- Traffic Prediction and Management Techniques
- Risk and Safety Analysis
- Advanced Clustering Algorithms Research
- Statistical Distribution Estimation and Applications
- Sensor Technology and Measurement Systems
- Air Quality Monitoring and Forecasting
- Cerebral Palsy and Movement Disorders
- Neurogenetic and Muscular Disorders Research
- Urban and Freight Transport Logistics
- Neuroblastoma Research and Treatments
- Fault Detection and Control Systems
- Neonatal Respiratory Health Research
- Transportation Planning and Optimization
- Rough Sets and Fuzzy Logic
- Software Reliability and Analysis Research
- Retinal Imaging and Analysis
- Radiation Dose and Imaging
- Advanced Computing and Algorithms
- Real-time simulation and control systems
- Vehicle Routing Optimization Methods
Sichuan University
2025
Hainan General Hospital
2024
Beihang University
2020-2021
BaiCheng Normal University
2019
Wuhan Prevention and Treatment Center for Occupational Diseases
2018
With the development of big data technology, creating ‘Digital Campus’ is a hot issue. For an increasing amount data, traditional mining algorithms are not suitable. The clustering algorithm becoming more and important in field mining, but does take efficiency effect into consideration. In this paper, based on K-Means by fast search find density peaks (K-CFSFDP) proposed, which improves distance points. This method used to cluster students from four universities. experiment shows that...
Abstract Complications caused by hypertension include heart failure, stroke, arteriosclerosis, etc. The prediction of complications is a hot issue, and it difficult to predict from medical perspective. In this study, we aim establish model based on machine learning data mining. We first proposed GBDT-based feature selection method, which can screen out indicators that affect the complications. On basis, established LightGBM. results show after 10-fold cross-validation comparison analysis,...
In the process of aircraft maintenance and support, a large amount fault description text data is recorded. However, most existing diagnosis models are based on structured data, which means they not suitable for unstructured such as text. Therefore, text-driven model proposed in this paper Word to Vector (Word2vec) prior-knowledge Convolutional Neural Network (CNN). The first enters Word2vec perform feature extraction, extracted vectors then input into CNN train classifier. introduces expert...
Ventilatory pump failure is a common cause of death for patients with neuromuscular diseases. The vital capacity plateau value (VCPLAT) an important indicator to judge the status ventilatory congenital myopathy, Duchenne muscular dystrophy and spinal atrophy. Due complex relationship between VCPLAT patient’s own condition, it difficult predict pediatric disease from medical perspective. We established prediction model based on data mining machine learning. first performed correlation...
For patients with hypertension, serious complications, such as myocardial infarction, a common cause of heart failure, occurs in the late stage hypertension. Hypertension outcomes can lead to including death. threaten patients’ lives and need be predicted. In our research, we reviewed hypertension medical data from tertiary-grade A class hospital Beijing, established outcome prediction model machine learning theory. We first proposed gain sequence forward tabu search feature selection...
Smart transportation is an important part of smart urban areas, and travel characteristics analysis traffic prediction modeling are the two key technical measures building systems. Although online car-hailing has developed rapidly a large number users, most studies on do not focus car-hailing, but instead taxis, buses, metros, other traditional means transportation. The univariate variable hybrid time series model based autoregressive integrated moving average (ARIMA) ignores explanatory...
Abstract The paper proposed a prediction model of online car-hailing demand based on K-means and support vector regression (SVR) methods. In the past few years, market has grown rapidly, rapid growth become hot topic. This study takes initial longitude latitude orders as eigenvalues for clustering. clustering results are taken result area division. number size potential areas could be determined automatically. method division solves shortcomings traditional artificial meshing existing...
The traditional sequential pattern mining method is carried out considering the whole time period and often ignores patterns that only occur in local windows, as well possible periodicity. Therefore, order to overcome limitations of methods, this paper proposes status set with windows (SSPMTW). In contrast item considered, minimum confidence, coverage, factor ratios other constraints are added mine more valuable rules windows. periodicity these also analyzed. According proposed method,...
To analyze the short-term clinical efficacy and safety of arsenic trioxide (ATO) combined with a modified N7 induction regimen in treatment children high-risk neuroblastoma (NB).
Abstract In order to cope with the challenges of high cargo load and timeliness distribution in logistics industry, as well alleviate current situation oil resource depletion air pollution, this study established a mathematical model two-echelon electric vehicle routing problem (2E-EVRP) design heuristic algorithm. The 2E-EVRP can be divided into multiple depot (MDEVRP) split delivery (SDVRP). proposed genetic algorithm is used solve MDEVRP, actual case company Beijing taken calculation...
The Type-I censoring test has the advantage of time control which makes it widely used in engineering practice. outputs current statistical algorithm are total and receiving number failures. However, already been settled by profile under many circumstances. Furthermore, is unable to evaluate system reliability when failure zero during test. Aiming at problems above, a new was proposed calculate failures receive results considering fixed time. And an evaluation method for zero-failure...
Objective: To understand the healthy status of radiation workers on staff in Nanjing, and to analysis relationship between abnormal crystalline lens its influencing factors. Methods: We described physical indicators including blood pressure (BP) 、blood sugar (BG) 、thyroid B ultrasound、crystalline lens、chromosome so among 3 349 year 2016 from Jan 1 Dec 31, results were analyzed statistically. Results: The rate BP、BG、WBC、Thyroid was 19.0%、2.2%、5.8%、30.0%、3.6% respectively; chromosome...