A5027281226- Data Visualization and Analytics
- Data Analysis with R
- Time Series Analysis and Forecasting
- Smart Grid Energy Management
- Energy Load and Power Forecasting
- Genomics and Rare Diseases
- Research Data Management Practices
- Hearing Loss and Rehabilitation
- Pancreatic and Hepatic Oncology Research
- E-Learning and COVID-19
- Biometric Identification and Security
- Scientific Computing and Data Management
- Nursing Diagnosis and Documentation
- Advanced Database Systems and Queries
- Big Data and Business Intelligence
- Noise Effects and Management
- Epigenetics and DNA Methylation
- Statistics Education and Methodologies
- Meteorological Phenomena and Simulations
- Distributed and Parallel Computing Systems
- Electric Vehicles and Infrastructure
- Building Energy and Comfort Optimization
- Advanced Aircraft Design and Technologies
- Health Education and Validation
- Radiomics and Machine Learning in Medical Imaging
Renji Hospital
2024
Shanghai Jiao Tong University
2024
University of Nebraska at Omaha
2015-2023
Nanjing Tech University
2019
Iowa State University
2014-2015
Missing values are common in data, and usually require attention order to conduct the statistical analysis. One of first steps is explore structure missing values, how missingness relates other collected variables. This article describes an R package, that provides a graphical user interface (GUI) designed help data examine results different imputation methods. The GUI numerical summaries conditional on missingness, includes imputations using fixed multiple nearest neighbors.
Radiomics is a rapidly growing field that quantitatively extracts image features in high-throughput manner from medical imaging. In this study, we analyzed the radiomics of whole pancreas between healthy individuals and pancreatic cancer patients, established predictive model can distinguish patients based on these features. Methods: We retrospectively collected venous-phase scans contrast-enhanced computed tomography (CT) images 181 control subjects 85 case for analysis modeling. An...
Hospital noise can be problematic for both patients and staff consistently is rated poorly on national patient satisfaction surveys. A surge of research in the last two decades highlights challenges healthcare acoustic environments. However, existing commonly relies conventional metrics such as equivalent sound pressure level, which may insufficient to fully characterize fluctuating complex nature hospital environments experienced by occupants. In this study, unsupervised machine learning...
One of the big challenges developing interactive statistical applications is management data pipeline, which controls transformations from to plot. The user's interactions needs be propagated through these modules and reflected in output representation at a fast pace. Each individual module may easy develop manage, but dependency structure can quite challenging. MVC (Model/View/Controller) pattern an attempt solve problem by separating interaction data. In this paper we discuss paradigm...
Temporal data are information measured in the context of time. This contextual structure provides components that need to be explored understand and can form basis interactions applied plots. In multivariate time series, we expect see temporal dependence, long term seasonal trends, cross-correlations. longitudinal data, also within between subject dependence. Time series although analyzed differently, often plotted using similar displays. We provide a taxonomy on plots enable exploring these...
The expansion of Advanced Metering Infrastructure (AMI) has provided building operators and researchers detailed information on energy consumption. majority AMI systems, however, record data at relatively low resolutions 15, 30, or 60 minutes, due to cost, storage bandwidth limitations. Emerging applications in power flow analysis, Quasi-Static Time-Series Simulation (QSTS), smart grid integration load matching, require higher resolutions. Short-term demand can deviate significantly from...
While the increase in EV use is a positive step towards embracing green technology, heightened energy demands resulting from this rapid growth present major challenges to local grid load management. For context, new EVs being deployed store approximately 100 kWh, about four times daily electricity of average household U.S. Current distribution grids do not have capacity accommodate these massively increased loads. reason, it important that utilities full understanding charging demand within...
Donoho's article "50 Years of Data Science" is a well-thought explanation newly developed discipline called "data science." In this article, we examine his explanations and suggestions about data science, follow-up on some the issues he mentioned, share our experiences in developing science curriculum teaching related courses.
This paper identifies structural and relational factors for the performance of cyberinfrastructure as a class cyber-physical systems, filling gap in our knowledge about social technical factors, well their coupling, performance. study draws from literature on virtual organizations, network governance, coupling socio-technical systems to develop conceptual framework The empirical investigation focuses NSF-funded program United States, arguably one largest most comprehensive programs country....
Temporal data is information measured in the context of time. This contextual structure provides components that need to be explored understand and can form basis interactions applied plots. In multivariate time series we expect see temporal dependence, long term seasonal trends cross-correlations. longitudinal also within between subject dependence. Time data, although analyzed differently, are often plotted using similar displays. We provide a taxonomy on plots enable exploring these...
In order to solve the problem of insufficient feature extraction and slow convergence in face recognition, a convolutional neural network recognition algorithm based on multi-channel fusion dynamic sample weights is designed. Firstly, theoretical analysis shortcomings traditional CNN carried out. Then weight theory are The structure determined through multiple experiments. addition, above used identify partial occlusion rotation test set. end, method designed this paper compared with other...