Electrical and Computer Engineering
North Carolina A&T State University
Email: mmoradik AT aggies.ncat.edu
Control Systems, Machine Learning , Bioinformatics, Fault/Event Detection in Wireless Sensor Networks
PhD: 2013-now, North Carolina A&T State University, Electrical Engineering
MSc: 2011, Isfahan University of Technology, Iran, Control Engineering
BSc:2008, Imam Khomeini International University, Iran, Control Engineering
My Google Scholar webpage: (publications)
- M. Moradi, M.Gorji Sefidmazgi,A. Homaifar, "Delayed and Hidden Variables Interactions in Gene Regulatory Networks", IEEE 14th International Conference on Bioinformatics and Bioengineering (BIBE), 2014
- M. Moradi, M. Gorji, A. Homaifar and D. KC, "A Novel Evolutionary Artificial Neural Network with the Application to Chaotic Time-Series Forecasting,” Genetic and Evolutionary Computation Conference, GECCO 2014, July 12-16, 2014, Vancouver, BC, Canada.
- M. Gorji, M. Moradi, A. Homaifar, "a Finite Element Based Method for Identification of Switched Linear Systems, American Control Conference, Oregon, 2014
- M. Moradi, A. Homaifar, D. B KC, "Hierarchical Multi-Label Gene Function Prediction using Adaptive Mutation in Crowding Niching", 13th IEEE International Conference on BioInformatics and BioEngineering (BIBE 2013), Chania, Greece, 2013
Computational prediction of protein function is an important field in functional genomics. Gene function prediction is a Hierarchical multi label classification (HMC) problem where each gene can belong to more than one functional class simultaneously, while classes are structured in the form of hierarchy. HMC is becoming a necessity in many domains of applications as well.
Currently, we propose Crowding niching-Adaptive Mutation (CAM) as a new method for solving Hierarchical multi-label gene function prediction problem. The classification in CAM-HMC is structured in three different phases. In the first phase, a full cyclic evolutionary crowding algorithm based on new definition of distance between two individuals, and adaptive mutation is applied in order to find classification rules. In the second phase, all the examples which are covered by these rules are removed from the training data. A sequential procedure between these two phases helps us to find all the CAM-HMC rules for covering training examples. In the third phase, consequent of rules (probability of coverage of each rule for each hierarchical class) are used for classification of new set of data.
Gene Regulatory Networks: See my weblog @ BEACON