Classification of Escherichia Coli Bacteria using Meta-Cognitive Neural Network
Journal Title: International Journal of Computer Science & Engineering Technology - Year 2014, Vol 5, Issue 2
Abstract
The classification of data using machine learning involves different challenging tasks which depend on the learning method, selection of neurons, selection of dataset, selection of algorithm etc. This paper deals with classifying Escherichia Coli bacteria proteins from the amino acid sequence using Meta-cognitive learning. Different machine learning techniques are implied on the imbalanced dataset of E-Coli with 10 cross-fold validations to prove the performance of Meta-cognitive Neural Network (McNN) .McNN is capable of learning what –to-learn, when-to-learn and how-to-learn. Extreme Learning Machine (ELM) a batch learning algorithm, Self – adaptive Resource Allocation Network (SRAN) a sequential learning algorithm and Meta- cognitive Neural Network (McNN) which employs meta-cognition in sequential learning are applied for experimental study. This paper shows that classification of McNN performs well with respect to other machine learning algorithms.
Authors and Affiliations
Padma. S , Arun Kumar. M
Keywords
Related Articles
- EP ID EP141761
- DOI -
- Views 97
- Downloads 0
Human Computer Interaction based on Psychology and Interactive system design
Human - computer interaction (HCI) is the area of intersection between psychology and the social sciences, on the one hand, and computer science and technology, on the other.HCI researchers analyze and design-specific us...
VOICE ENABLED ONTOLOGY BASED SEARCH ENGINE ON SEMANTIC WEB FOR BLIND
With the development of web services, the retrieval of relevant services has become a challenge. Keyword based discovery mechanism is insufficient, due to retrieval of large amount of irrelevant information. Here we prop...
AN ENHANCED PRIVACY RULE BASED MODEL FOR FILTERING UNPREFERRED MESSAGES
The online social networks (OSN) offers proficient message controls that are posted on their private space in order to avoid un-preferred content displayed to users. But, OSN provides a low supportive and flexibility to...
Analysis of Trust in Wireless Sensor Networks
Trust is an important factor in Wireless Sensor Network (WSN) that enables the sensor node to cooperate each other for their application. It makes the nodes in the wireless sensor networks to cope with uncertainty caused...
Applicability of Soft computing technique for Crime Forecasting: A Preliminary Investigation
Soft Computing is a multidisciplinary field originally proposed by Dr. Lotfi Zadeh. It is the fusion of methodologies designed to model solution to real world problems that are otherwise difficult to model mathematically...