A Clustering - Based Attribute Selection Approach for High Dimensional Data

Volume 6 Issue 3 June - August 2017

Research Paper

A Clustering - Based Attribute Selection Approach for High Dimensional Data

Ravi P. Patki*

Assistant Professor, Department of Information Technology, International Institute of Information Technology, Pune, India.

Patki, R. P. (2017). A Clustering - Based Attribute Selection Approach for High Dimensional Data. i-manager’s Journal on Information Technology, 6(3), 8-14. https://doi.org/10.26634/jit.6.3.13775

Abstract

Attribute selection is the procedure of selecting a subset of important attributes for utilization in model development. The central supposition when utilizing as attribute selection method is that the information contains numerous redundant or irrelevant attributes. Repetitive attributes are those which give no more data than the right now chosen attributes, and irrelevant attributes give no helpful data in any setting. Attribute selection is a process in which subset of important attribute is selected which produce good results. Attribute selection algorithm is used for that purpose which achieve efficiency, i.e. less time and correctness of subset. Existing system proposed clustering based attribute selection algorithm based on efficiency and effectiveness criteria. In this algorithm, attributes are first separated into different clusters using graph theoretic clustering method and then those attributes are selected from each clusters, which is most related to target class. Because of large attributes minimal in graph many nodes are generated and in such situations working of prims algorithm is better. In this paper, the system uses Kruskals algorithm instead of Prims algorithm for better efficiency and accuracy. The Kruskals algorithm perform sorting according to the weight and starts from the smallest one which will take less time to iterate. This is the only method which uses sorting technique which will increase the efficiency.

Role of Recognizing Patterns with Neural Network Approach

Volume 6 Issue 3 June - August 2017

Article

Role of Recognizing Patterns with Neural Network Approach

Sunny Thukral*

Assistant Professor, PG Department of Computer Science and Information Technology, DAV College, Amritsar, India.

Thukral. S. (2017). Role of Recognizing Patterns with Neural Network Approach. i-manager’s Journal on Information Technology, 6(3), 1-7. https://doi.org/10.26634/jit.6.3.13774

Abstract

This paper is based upon the recognition of either characters or digits by using Neocognitron algorithm, which can be used for detecting multiple patterns. A large pattern can be divided into multiple parts until it becomes a single cell for each and every block for its representation. Neural Network can be implemented with the concept of fuzzy logic which deals with ambiguous problems. The integration of Neural Network and Fuzzy Logic will generate such type of intelligent systems for mankind in optimum real life problems. It also describes various types of architects that can be constructed with neural network. In Neocognitron approach, a type of hierarchal network where two types of cells can be used like simple and complex cells, which can be trained by using different neural network algorithm approaches. It also describes various types of applications that can be used in real life through Neocognitron. The objective of the paper is to describe various architectures of Neural Network approach, so that it can be implemented with different algorithms for better outcomes in real life complex problems.

Study on the Attitude towards Internet Applications

Volume 6 Issue 2 March - May 2017

Survey Paper

Study on the Attitude towards Internet Applications

Devika R*

Assistant Professor, NSS Training College, Ottapalam, Palghat District, Kerala, India.

Devika, R. (2017). Study on the Attitude towards Internet Applications. i-manager’s Journal on Information Technology, 6(2), 33-40. https://doi.org/10.26634/jit.6.2.13575

Abstract

The present study aims to determine the attitude of teachers towards internet applications. Survey method was employed for the study. The sample consisted of 50 school teachers. An attitude scale towards internet applications was developed and standardized by the investigator. t-test and ANOVA were used to analyse the data. It was concluded from the study that a majority of the teachers maintained a positive attitude towards internet applications. In addition to this it was concluded that gender, teacher qualification, and teaching experience of teachers have no role on the attitude towards internet application of teachers.

An Intelligent System based on Back-propagation Neural Network and Particle Swarm optimization Based Neural Network for Diagnosing Anemia in Pregnant Ladies

Volume 6 Issue 2 March - May 2017

Research Paper

An Intelligent System based on Back-propagation Neural Network and Particle Swarm optimization Based Neural Network for Diagnosing Anemia in Pregnant Ladies

Neha Sharma*, Vikas Khullar**, Ashish Luhach***

* PG Scholar, Department of Computer Science & Engineering, CT Institute of Engineering Management and Technology, Jalandhar, India.

** Assistant Professor, Department of Computer Science & Engineering, CT Institute of Engineering Management and Technology, Jalandhar, India.

*** Vice Principal & Associate Professor, Department of Computer Science, and Engineering, CT Institute of Engineering Management and Technology, Jalandhar, India.

Sharma, N., Khullar, V., and Luhach, A. (2017). An Intelligent System based on Back-propagation Neural Network and Particle Swarm optimization Based Neural Network for Diagnosing Anemia in Pregnant Ladies. i-manager’s Journal on Information Technology, 6(2), 27-32. https://doi.org/10.26634/jit.6.2.13574

Abstract

According to WHO According to World Health Organization (WHO) survey, anemia is one of the most commonly encountered medical deficiencies during pregnancy [5]. BP network has been successfully used for anemia diagnosing in pregnant ladies, however BP network's drawbacks, such as long execution time and its easy fall into local optima have restricted its wider applications. Recently proposed stochastic optimization method Particle Swarm Optimization (PSO) is also been discussed. Also the way BP network's initial weights and bias are optimized; Particle swarm optimization is also carefully discussed. In this paper, firstly BP is used to initially train and test the BP network, then the Particle Swarm Optimization Based Back-Propagation (PSO-BP) networks is used to train and diagnose the anemia in pregnant ladies. While concluding the experimental results, it shows variation in the taken parameters, execution time, and accuracy [10, 11], [16].

Robust Reed Solomon code Analysis for use in Deep Space and Mobile Communication Applications

Volume 6 Issue 2 March - May 2017

Research Paper

Robust Reed Solomon code Analysis for use in Deep Space and Mobile Communication Applications

P. Ratna Kamala*, R. V. S. Satyanarayana**

* Professor, Department of Electronics and Communication Engineering, Siddharth Institute of Engineering and Technology, Puttur, AP, India.

** Professor and Head, Department of Electronics and Communication Engineering, Sri Venkateswara University, Tirupati, AP, India.

Kamala, P. R., and Satyanarayana, R. V. S. (2017). Robust Reed Solomon code Analysis for use in Deep Space and Mobile Communication Applications. i-manager’s Journal on Information Technology, 6(2), 22-26. https://doi.org/10.26634/jit.6.2.13573

Abstract

For the past few years, there is an increasing demand for reliable data transmission and storage media. During transmission of data, noisy channels often introduce errors in received information bits. Froward error correction, FEC is one of the methods used to enhance reliability of data transmission. The basic idea of FEC is to systematically add redundancy at the end of the messages so as to enable the correct retrieval of messages despite errors in the received sequences. This eliminates the need for retransmission. Reed Solomon codes are a type of algebraic Forward Error Correction code which is found to be an optimal code for maintaining data integrity during wireless transmission. Modulation techniques used in Wireless communication applications must be robust and at the same time should be bandwidth efficient. Thus, there is a need for the analysis of coding schemes to evaluate the optimal code for use in wireless communication applications. From the analysis of linear block codes, Reed Solomon code with n=255 and k=223 is observed to offer optimal performance. Detailed analysis of this code is done to ensure its use in Deep Space and Mobile communication applications.

Neuro-Fuzzy Approach as Data Predictor Using WEKA Tool

Volume 6 Issue 2 March - May 2017

Research Paper

Neuro-Fuzzy Approach as Data Predictor Using WEKA Tool

Sunny Thukral*

Assistant Professor, PG Department of Computer Science and Information Technology, DAV College, Amritsar, India.

Thukral, S. (2017). Neuro-Fuzzy Approach as Data Predictor Using WEKA Tool. i-manager’s Journal on Information Technology, 6(2), 16-21. https://doi.org/10.26634/jit.6.2.13572

Abstract

This paper presents the role of neuro-fuzzy logic in real world problems. An Artificial Neural network will process the data set using different algorithms like Perceptron, Adaline, and back propagation algorithms such that the weight should be trained for better performance. To do this, different types of activation functions are required to meet the optimum result of the data set. Due to adaptable characteristic of neural network; it can adjust their weights for new data set predictors through learning phase. With respect from fuzzy logic, which produces uncertain values that can be mapped from zero to one along with all the intermediate values that lies in-between them through fuzzy sets. So, neural network can work on maximum implementation with learning and training while fuzzy logic deals with imprecise information. But Neural Networks when combined with Fuzzy Logic generate intelligent systems that can resolve a number of complex problems in no time with less mean error. We can apply fuzzy rules with neural data set that can integrate to resolve specific problems. The concept of Adaptive Neuro Fuzzy Inference System was introduced under the concept of adaptability of bias and weight values of the neuron with the processing power of fuzzy inference system. Various types of real world problems and new directions might be achieved for neuro-fuzzy with multiple applications. The goal of this paper is to explain the role of neuro-fuzzy systems; and to implement one of the sample instances of weather prediction by using WEKA Tool. This tool clearly represents that multilayer perceptron algorithm that is common in neural networks when related with fuzzy logic would produce better results as prescribed in data set.

Implementation of Robust Search Algorithm to Mine Data from e-Literature Databases

Volume 6 Issue 2 March - May 2017

Research Paper

Implementation of Robust Search Algorithm to Mine Data from e-Literature Databases

S. Govinda Rao*

Associate Professor, Department of Computer Science and Engineering, Gokaraju Rangaraju Institute of Engineering and Technology, Telangana, India.

Rao, S. G. (2017). Implementation of Robust Search Algorithm to Mine Data from e-Literature Databases. i-manager’s Journal on Information Technology, 6(2), 11-15. https://doi.org/10.26634/jit.6.2.13571

Abstract

Mining data from databases have seen many upgrades since few decades considering the development of huge data repositories with the advent of internet revolution worldwide. Inherently, the importance of search algorithms to mine data has gained prominence over a period of time. Many programming languages have been used to retrieve relevant information from databases. In this paper, the author presents the E-Literature database created in MySQL with all possible entries, such as ISSN, Publisher name, publication type, etc. Authors from different geographical regions can also be searched from the database. The search algorithm code implemented in the work is used to search the database with varied options, such as 'Abstract', 'keywords', 'affiliation', 'country', 'ISSN', etc. Each search option and the relevant code were written in PHP. Binary search algorithm has been implemented in the work to perform search routine. Apart from general search option, a robust search method which combines various search combinations called 'combination search' can be used to efficiently mine data.