posted by user: kmusial || 5550 views || tracked by 13 users: [display]

ITSS 2011 : Special Session on Intelligent Techniques for Soft Sensors

FacebookTwitterLinkedInGoogle

Link: http://www.lcs.syr.edu/iea-aie2011/special.html
 
When Jun 28, 2011 - Jul 1, 2011
Where Syracuse, NY, USA
Submission Deadline Nov 12, 2010
Notification Due Feb 1, 2011
Final Version Due Feb 28, 2011
Categories    soft sensors   machine learning   computational intelligence   artificial intelligence
 

Call For Papers

There is a very strong demand for adaptive predictive systems in the process industries. Predictive models, also known as soft sensors in the process industries, can be developed to fulfil a broad range of tasks. The most widespread application area is online prediction of important process variables, which usually can be performed either at low sampling rates or through off-line analysis. Such process variables are very important for control and management, as they are often related to the critical aspects of the process. Other important application areas of soft sensors are process monitoring and fault detection. The role of process monitoring soft sensors is to build multivariate features based on historic data, which are relevant for description of the process state. By providing the predicted process state or multivariate features, the soft sensor can support the process operators and allow them to make faster and more objective decisions.

Currently, a shift from traditional statistical PCA- / PLS-based techniques to more advanced approaches, like Artificial Neural Networks, kernel-based methods, Gaussian processes, Neuro-Fuzzy Systems can currently be observed in the field of soft sensor development. Some recent publications also demonstrate the increasing popularity of computational intelligence and machine learning concepts like ensemble methods, local learning and meta-learning in soft sensors.

It has also been recognised by many researchers that in order to develop practically relevant soft sensors, the models must be able to adapt to the changing environment, which resulted in the application of adaptive, incremental and evolving techniques to soft sensing and other applications.

In real-life industrial applications it is often inevitable to incorporate expert and prior knowledge into the models in order to achieve acceptable performance level. Although there were some first attempts to use, for example, the evidence theory for this task, in a vast majority of cases this is done in a sub-optimal ad-hoc way.


Special Session Aim
-------------------

Although soft sensors have been developed for at least two decades and their importance has been constantly reiterated, they have not made a breakthrough as commercial products in the process industry. This is mainly due to the issues discussed above and the lack of suitable tools on the market.

The aim of the special session on Intelligent Techniques for Soft Sensors is to bring together researchers and practitioners in the area of soft sensors to share their visions, research achievements and solutions, and to establish worldwide cooperative research and developmental environment. At the same time, we want to provide a platform for discussing research topics underlying the concepts of soft sensors by inviting members of different communities and people with different research and industrial background. This will give an opportunity to further push the discussion upon the potential of soft sensors and challenges within this area.

---------------------------------------------------------------------------------------
TOPICS OF INTEREST
---------------------------------------------------------------------------------------
1) Soft sensors based on:
- Artificial Neural Network
- Fuzzy / Neuro-Fuzzy Systems
- Kernel-based methods
- Statistical learning methods (PCA/PLS)
- Knowledge-based systems
- Expert systems
- Model-driven approaches
- (Extended) Kalman filter
- Adaptive observer
- First principle models
- Combination of model and data-driven methods, etc.
2) Advanced machine learning concepts in soft sensing including:
- Ensemble methods
- Local learning
- Meta-learning
3) Advanced data pre-processing for data de-noising, outlier detection, and
missing value treatment in a soft sensing context
4) Adaptive, incremental and evolving techniques for soft sensing
5) Exploitation of expert and prior knowledge
6) Real life soft sensor applications for:
- On-line prediction of critical process variables
- Process monitoring and fault detection
- Sensor fault detection
- Inferential and model-based process control, etc.
7) Case studies:
- Process industry
- Chemical industry
- Fermentation and other biochemical processes
- Refineries
- Energy generation
- Robotics
- Integrated Vehicle Health Management, etc.

---------------------------------------------------------------------------------------
PAPER SUBMISSION
---------------------------------------------------------------------------------------
Paper Preparation: Authors are invited to electronically submit their paper,
written in English, of up to 10 single spaced pages, presenting the results of
original research or innovative practical applications relevant to the special
session.

Shorter works, up to 6 pages, to be presented in 10 minutes, may be submitted
as SHORT PAPERS representing work in progress or suggesting possible research
directions.

Paper Format: Submitted papers should be conformed to the Lecture Notes
in Artificial Intelligence (LNAI) format.
For the format go to http://www.springer.de/comp/lncs/authors.html. For
other related information visit the Springer-Verlag website and look for their
íLecture Notes in Artificial Intelligence (LNAI) series, which is a sub-series
Lecture Notes in Computer Science (LNCS).

For the submission details go to: http://www.lcs.syr.edu/iea-aie2011/paper_submission.html

---------------------------------------------------------------------------------------
ORGANISATION COMMITTEE
---------------------------------------------------------------------------------------
Petr Kadlec - Email: pkadlec@bournemouth.ac.uk
Marcin Budka - Email: mbudka@bournemouth.ac.uk
Bogdan Gabrys - Email: bgabrys@bournemouth.ac.uk
Christiane Lemke - Email: clemke@bournemouth.ac.uk
Katarzyna Musial - Email: kmusial@bournemouth.ac.uk

Mailing address: Bournemouth University, Poole House, Talbot Campus,
Fern Barrow, Poole, Dorset, BH12 5BB, UK

---------------------------------------------------------------------------------------
Acknowledgement
---------------------------------------------------------------------------------------
This Special Session is organised as one of the Transfer of Knowledge activities
within the Computational Intelligence Platform for Evolving and Robust Predictive
Systems (INFER) project that has received funding from the European Union
Seventh Framework Programme (FP7/2007-2013) under grant agreement no
251617.

More information about INFER project can be found at www.infer.eu

Related Resources

SS MLSP4EV 2020   Special Session on Machine-Learning and Signal Processing Techniques for Electric Vehicles Interaction and Management
FAIML 2020-Ei Compendex & Scopus 2020   2020 2nd International Conference on Frontiers of Artificial Intelligence and Machine Learning (FAIML 2020)
PACT 2020   International Conference on Parallel Architectures and Compilation Techniques
SCAI 2020   9th International Conference on Soft Computing, Artificial Intelligence and Applications
AICA 2020   O'Reilly AI Conference San Jose
IDA 2020   The 18th International Symposium on Intelligent Data Analysis (IDA 2020)
JSE 2020   9th International Conference on Software Engineering and Applications
MLIOB 2020   International Conference on Machine Learning, IOT and Blockchain
COMIT 2020   4th International Conference on Computer Science and Information Technology
Fintech 2020   Sustainaility (Q2): Fintech: Recent Advancements in Modern Techniques, Methods and Real-World Solutions