Grant: Engage Grants Program
University of New Brunswick
$25,000.00
Development of advanced data mining techniques for microbiological control
EF 2013-14
Résumé
The proposed research will solve the data analysis problem related to microbiological data for LuminUltra Technologies Ltd, and will be integrated into their data analysis system LumiCalc. The microbiological data in LumiCalc is collected through a variety of tests on different sites. The ultimate goal of data analysis is to predict the amount of biomass measured by ATP (Adenosine Triphosphate). ATP can be affected by many different variables, such as food, nutrients, temperature, pH, etc. Therefore, causal relations correlations) play an important role. With a large amount of historical data, users need a powerful tool that allows them to analyze data and discover similarities, patterns, trends, and especially causal relations. Data mining techniques have been applied to dealing with the flood of biological data. In this research project, we will investigate various data mining algorithms and models for LuminUltra data analysis, select a few suitable models, and implement and integrate them into the LumiCalc software.The proposed research is comprised of the following three projects:1. Enhancing Correlation Analysis in LumiCalcWe will extend the correlation analysis of LumiCalc to cover more complex non-linear correlations. We will replace the pre-defined ranges with dynamically determined ranges based on the probability distribution.2. Accommodating Predictive Models in LumiCalcWe will study and implement three predictive models. (1) Bayesian networks (BNs): in this research, we will use a BN for predicting the value of ATP or any other variable(s) and conducting causal analysis among variables. (2) Linear regression. (3) k-nearest neighbor (k-NN).3. Accommodating Cluster Analysis in LumiCalcClustering analysis is an important functionality for LumiCalc users to discover hidden patterns. We will study two types of clustering: (1) Clustering observations for one site; (2) Clustering sites based on observations.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
New Brunswick, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
461599-2013
Name nom
Zhang, Huajie
Department département
Computer Science, Faculty of
Organization id
75
Institution établissement
University of New Brunswick
Province en
New Brunswick
Province fr
Nouveau-Brunswick
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2013
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1551
Committee name en
Atlantic Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Atlantique
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2805
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Learning and inference theories
Research subject fr
Théories de l'apprentissage et l'inférence
Partie
1
Nb partie
1
Application title
Development of advanced data mining techniques for microbiological control
Keyword
NSERC
Application summary
The proposed research will solve the data analysis problem related to microbiological data for LuminUltra Technologies Ltd, and will be integrated into their data analysis system LumiCalc. The microbiological data in LumiCalc is collected through a variety of tests on different sites. The ultimate goal of data analysis is to predict the amount of biomass measured by ATP (Adenosine Triphosphate). ATP can be affected by many different variables, such as food, nutrients, temperature, pH, etc. Therefore, causal relations correlations) play an important role. With a large amount of historical data, users need a powerful tool that allows them to analyze data and discover similarities, patterns, trends, and especially causal relations. Data mining techniques have been applied to dealing with the flood of biological data. In this research project, we will investigate various data mining algorithms and models for LuminUltra data analysis, select a few suitable models, and implement and integrate them into the LumiCalc software.The proposed research is comprised of the following three projects:1. Enhancing Correlation Analysis in LumiCalcWe will extend the correlation analysis of LumiCalc to cover more complex non-linear correlations. We will replace the pre-defined ranges with dynamically determined ranges based on the probability distribution.2. Accommodating Predictive Models in LumiCalcWe will study and implement three predictive models. (1) Bayesian networks (BNs): in this research, we will use a BN for predicting the value of ATP or any other variable(s) and conducting causal analysis among variables. (2) Linear regression. (3) k-nearest neighbor (k-NN).3. Accommodating Cluster Analysis in LumiCalcClustering analysis is an important functionality for LumiCalc users to discover hidden patterns. We will study two types of clustering: (1) Clustering observations for one site; (2) Clustering sites based on observations.