Feng Tan

ORCID: 0000-0003-1849-4443
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Formal Methods in Verification
  • Face and Expression Recognition
  • Seismic Imaging and Inversion Techniques
  • Gene expression and cancer classification
  • Real-Time Systems Scheduling
  • Evolutionary Algorithms and Applications
  • Healthcare Technology and Patient Monitoring
  • Neural Networks and Applications
  • Distributed and Parallel Computing Systems
  • Drilling and Well Engineering
  • Algorithms and Data Compression
  • Petri Nets in System Modeling
  • Computer Graphics and Visualization Techniques
  • COVID-19 Pandemic Impacts
  • VLSI and Analog Circuit Testing
  • Geological Modeling and Analysis
  • Turbomachinery Performance and Optimization
  • Network Time Synchronization Technologies
  • Text and Document Classification Technologies
  • Higher Education and Teaching Methods
  • Neonatal and fetal brain pathology
  • Machine Learning in Bioinformatics
  • Material Properties and Applications
  • Gear and Bearing Dynamics Analysis
  • Web Data Mining and Analysis

State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation
2020-2025

Chengdu University of Technology
2020-2025

China National Petroleum Corporation (China)
2024-2025

Chinese Center For Disease Control and Prevention
2018-2024

Chongqing University of Posts and Telecommunications
2022

Beijing Academy of Artificial Intelligence
2022

Sichuan University
2018

Hong Kong Polytechnic University
2012-2014

Fairchild Semiconductor (United States)
2012

Georgia State University
2006-2007

Pipe-like formations are vertical, complex and shape-diverse subsurface structures. The accurate seismic interpretation is essential for understanding their fluid dynamics environmental impacts. However, conventional exploration techniques struggle to accurately resolve critical areas due a general decline in imaging quality. This challenge significant three-dimensional nature, as some exaggerated forms impact imaging, despite appearing similar 2D slices. limited perspective commonly used...

10.3389/feart.2024.1487605 article EN cc-by Frontiers in Earth Science 2025-01-17

Hybrid systems model checking is a great success in guaranteeing the safety of computerized control cyber-physical (CPS). However, when applying hybrid to Medical Device Plug-and-Play (MDPnP) CPS, we encounter two challenges due complexity human body: 1) there are no good offline differential equation-based models for many body parameters; 2) can result variables, complicating system model. In an attempt address challenges, propose alter traditional approach time-unbounded (i.e., infinite...

10.1109/tpds.2013.50 article EN IEEE Transactions on Parallel and Distributed Systems 2013-10-28

Microarray data usually contains a huge number of genes (features) and comparatively small samples, which make accurate classification or prediction diseases challenging. Feature selection techniques can help us identify important irrelevant (unimportant) features by applying certain criteria. However, different feature algorithms based on various theoretical arguments often produce results when applied to the same set. This makes selecting an optimal near subset for set difficult. In this...

10.1109/cec.2006.1688623 article EN IEEE International Conference on Evolutionary Computation 2006-09-22

Hybrid systems model checking is a great success in guaranteeing the safety of computerized control cyber-physical (CPS). However, when applying hybrid to Medical Device Plug-and-Play(MDPnP) CPS, we encounter two challenges due complexity human body: i) there are no good offline differential equation based models for many body parameters, ii) can result variables, complicating system model. In an attempt address challenges, propose alter traditional approach time-unbounded (i.e., long-run)...

10.1109/iccps.2012.10 article EN 2012-04-01

The difficulty of feature extraction and the small sample size are two challenges in field mechanical fault diagnosis for a long time. Here we propose an intelligent method scenario with datasets. This can not only diagnose bearing faults but also gear faults, has strong generalization performance. We use convolutional neural network to realize automatic extraction. Through sliding window scanning, one set is expanded three sub-sample sets different scales meet needs deep learning training....

10.1038/s41598-022-26316-6 article EN cc-by Scientific Reports 2022-12-20

Cyber-Physical Systems (CPS) integrate discretetime computing and continuous-time physical-world entities, which are often wirelessly interlinked.The use of wireless safety critical CPS (control, healthcare etc.) requires guarantees despite communication faults.This paper focuses on one important set such rules: Proper-Temporal-Embedding (PTE).Our solution introduces hybrid automata to formally describe analyze design patterns.We propose a novel lease based pattern, along with closed-form...

10.1109/dsn.2013.6575357 article EN 2013-06-01

Cyber-Physical Systems (CPS) integrate discrete-time computing and continuous-time physical-world entities, which are often wirelessly interlinked. The use of wireless safety-critical CPS requires safety guarantees despite communication faults. This paper focuses on one important set such rules: Proper-Temporal-Embedding (PTE), where distributed entities must enter/leave risky states according to properly nested temporal pattern certain duration spacing. Our solution introduces hybrid...

10.1109/tpds.2014.2358224 article EN IEEE Transactions on Parallel and Distributed Systems 2014-09-15

As a classical visualization tool for seismic facies analysis, the clustering process of self-organizing map (SOM) is generally divided into two stages: feature extraction and clustering. However, when horizon pickings are ambiguous waveforms chaotic, structural cannot correspond well to topological structure SOM. To improve performance classification, we propose one-stage method deep embedded SOM (DESOM) which means that extracting representation completed simultaneously. Moreover,...

10.1109/lgrs.2020.3003585 article EN publisher-specific-oa IEEE Geoscience and Remote Sensing Letters 2020-06-26

To compare the performance between compartment model and autoregressive integrated moving average (ARIMA) that were applied to prediction of new infections during coronavirus disease 2019 (COVID-19) epidemic.The ARIMA established based on daily cases infection reported in China from December 2, April 8, 2020. The goodness fit two models was compared using coefficient determination (R2).The predicts number without a cordon sanitaire, i.e., restriction mobility prevent spread disease, will...

10.46234/ccdcw2022.239 article EN PubMed 2022-12-30

The Shaximiao Formation in the Zhongjiang Gas Field of Sichuan Basin was initially a high-productivity gas field with bright spot channel as vital exploration target. With further development, wells were obtained some nonbright areas, which caused interpreters to pay great attention channels abnormal amplitudes. We have developed method delineate from complicated sand-mudstone contact relationship. First, we classified sandstone into types I, IIa, IIb, and III, depending on responses...

10.1190/int-2020-0152.1 article EN Interpretation 2021-08-24

The quality factor Q is generally used to describe seismic attenuation that leads amplitude decay (AD) and wavelet distortion. Time-frequency transforms are commonly measure on surface data. These methods capture frequency changes over time using a fixed or variable sliding window. Other adaptive also can provide localization, they often superior for estimation. In this study, we compare three time-frequency indicate how the choice of fixed- variable-time window an transform affects accuracy...

10.1190/geo2021-0210.1 article EN Geophysics 2022-03-19

Glycidyl methacrylate (GMA) is a widely used industrial polymerization material. Current occupational exposure limits (OELs) for GMA in China show significant disparities compared to those established by international regulatory bodies, including the United States, European Union, and Japan. A comprehensive revision of crucial ensuring optimal worker protection. This investigation analyzed data from 104-week inhalation carcinogenicity study mice conducted identified statistically...

10.46234/ccdcw2024.277 article EN PubMed 2024-12-27

Control Cyber-Physical Systems (CPS) is a major category of CPS. In control CPS, besides the well-studied noises within physical subsystem, we are particularly interested in better understanding cross-domain noises: those come from "physical" propagate through "cyber" computing and go back to subsystem. The focus this paper propose framework profile propagation noises.

10.1109/iccps.2014.6843737 article EN 2014-04-01

Often times IC test solutions are constrained by the capability of choice or targeted tester technology in terms parametric functional specifications. This is usually main majority platform that being used a given organization. paper will focus on methodology to extend said for higher precision measurement. It not cover enhancement capability. In this paper, use circuit designs and programming detailed create novel solution, way creative programmable-gain instrumentation amplifier board...

10.1109/iemt.2012.6521767 article EN 2012-11-01

One-dimensional convolutional neural networks have achieved great success in time series classification problems due to their ability automatically learn feature representations. Therefore, the mainstream researches focus on optimization of 1D network structure enhance accuracy. In this paper, we propose a novel considering and 2D images transformed by for classification. Furthermore, from computer vision view, influence accuracy image methods sizes are discussed. The experimental results...

10.1109/icnsc55942.2022.10004078 article EN 2021 IEEE International Conference on Networking, Sensing and Control (ICNSC) 2022-12-15

Building a system based on variants of disparate individual components/programs is usually challenging task. The are not designed to communicate with each other but the whole construction does require seamless collaboration among them. In this paper, targeting at protein structure prediction, pluggable application server framework presented. capable combining various existing programs into an efficient unit and design devoted provide model which able integrate heterogeneous quickly without...

10.1109/iembs.2006.259692 article EN International Conference of the IEEE Engineering in Medicine and Biology Society 2006-08-01
Coming Soon ...