D Shanthi

Energy Efficient NoC design through Supervised Machine Learning

Journal of Physics: Conference Series

3D Network On Chip(NoC) will provide high multi-core data processing with the minimal amount of e... more 3D Network On Chip(NoC) will provide high multi-core data processing with the minimal amount of energy consumption. It is necessary to consider the architectural limits of three-dimensional NoCs. A deep reinforced framework is proposed that uses router-less NoC for evaluation in the case study. The framework uses prior approaches that may be unreliable because of the difficulties with the design and search process, and the inflexibility that results because of space restrictions. The framework has better loop placements for networking chips with various design constraints. A Monte Carlo search tree is used to develop a Deep Neural Network that searches in parallel for a NoC design.

Human Intelligence vs. Artificial Intelligence: Survey

Research in AIA neural network is an artificial representation of the human brain that tries to s... more Research in AIA neural network is an artificial representation of the human brain that tries to simulate its learning process. An artificial neural network (ANN) is often called a "Neural Network" or simply Neural Net (NN). In this paper I provide the survey which I found more interesting facts in my research. That is 1.The brief study of human brain and nervous system 2. What actually an intelligence 3.how this artificial intelligence is differing from human intellectual.

Download

Location Predicated Gregarious Networks

With the wide application of location-predicated gregarious networks (LBSNs), Point of interest g... more With the wide application of location-predicated gregarious networks (LBSNs), Point of interest guidance has become one of the major accommodations in LBSNs. The deportments of users in LBSNs are mainly checking in Point of Interests, and these checking in deportments are influenced by user’s demeanor daily habits and his/her friends. “In convivial networks, convivial influence is often used to avail businesses to magnetize more users”. Each user target utilizers have a different influence on different Point of Interest in gregarious networks. This paper culls the list of Point of Interests with the greatest influence for recommending users. Our aims are to gratify the target user’s accommodation need, and simultaneously to promote businesses’ locations Point of Interests.This Project defines a point of interest guidance quandary for location promotion. Adscititiously, we utilize sub modular properties to solve the optimization quandary. At last, this Project conducted a comprehensi...

Application of partical swarm intelligence technique to predict software reliability

2017 International Conference on Intelligent Computing and Control Systems (ICICCS)

Predict software program reliability turns into a completely huge trouble in these days. Ordinary... more Predict software program reliability turns into a completely huge trouble in these days. Ordinary many new software programs are introducing inside the marketplace and some of them dealing with failures as their usage/managing is very hard. and plenty of shrewd strategies are already used to are expecting software program reliability. In this paper we're giving a sensible knowledge and the difference among those techniques with my new method. As a result, the prediction fashions constructed on one dataset display a extensive decrease in their accuracy when they are used with new statistics. The aim of this assessment, SE issues which can be of sensible importance are software development/cost estimation, software program reliability prediction, and so forth, and also computing its broaden computational equipment with enhanced power, scalability, flexibility and that can engage more successfully with human beings.

Credit Score Prediction System using Deep Learning and K-Means Algorithms

Journal of Physics: Conference Series, 2021

In financial markets, credit rating and risk assessment tools are used to minimize potential risk... more In financial markets, credit rating and risk assessment tools are used to minimize potential risk up to some extent for credit score. Nowadays, the banking and financial industry has experienced rapid expansion. Therefore, with this growth, the numbers of credit card applications with various credit products are increasing day by day because many people want to avail these services for their personal interest. The challenge here is to identify insights on the performance of a finance industry by using deep learning algorithms as they directly affect the viability of that industry. These industries have a limited number of resources and capital, which can be used to deliver the services among the customers. In this research work, we proposed prediction of credit scoring system using deep learning and K-Means algorithm for the financial industry. The scheme contains a predictive model which uses feature selection (FS) classification and deep learning applications simultaneously to tra...

Survey of energy efficient high performance low power router for network on chip

This design and fabrication of a 66 litre batch poultry feed mixer have an efficiency of 87.4%, a... more This design and fabrication of a 66 litre batch poultry feed mixer have an efficiency of 87.4%, at a low operating cost, easy to control and maintain. A choice of 1 horse power single phase electric motor was used to power the machine such that it rotates the blade attached to the shaft for a desired speed of 50rpm. The transmission from the power source to the mixer is from a gear box. The power source is separated from the mixer for easy servicing, the other various part of the machine are the hopper, trough, flange coupling, bearing, blades attached to the solid shafts and stand. The construction materials were chosen based on the availability and cost, so as to make it affordable to the average users. This machine was designed and fabricated at the rate of N75, 900 as against N380, 000 for those imported and available in the market.

“IoT Based Medical Diagnosis Expert System Application”

Lecture Notes on Data Engineering and Communications Technologies, 2019

Medical diagnosis expert system application is mainly developed to diagnose the probable disease ... more Medical diagnosis expert system application is mainly developed to diagnose the probable disease of a user depending upon the symptoms the user has provided. This application also determines the location of the hospitals, clinics and diagnostic centers. The application also offers to deliver the medicines to the user on order to the location of the user.

The Blue Brain Technology using Machine Learning

2021 6th International Conference on Communication and Electronics Systems (ICCES)

“Blue brain” is the first virtual brain in the world. It is a computer that functions similarly t... more “Blue brain” is the first virtual brain in the world. It is a computer that functions similarly to the human brain. The Blue Brain Project began developing the neocortical pillar in July 2005 in collaboration with EPFL (Ecole Polytechnique Fdrale de Lausanne), Professor Henry Markram of the Brain Mind Institute, and IBM (International Business Machines). Scientists are currently researching the development of an artificial brain that can think, react, decide and remember something. With technology advances, people should still be retained as the ultimate source of knowledge and exploration. In other words, people don't live for thousands of years, but they could save and use knowledge in their minds for several thousand years. Blue brain is the useful technology in this operation. The key objective is to upload the human brain. It can be used for human society's growth.

Application of Machine Learning Techniques for Stastical Analysis of Software Reliability Data Sets

2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS)

Selecting a right data set for right problem became a very big issue. Most of the researches does... more Selecting a right data set for right problem became a very big issue. Most of the researches doesn't know what actually a dataset and how to select a suitable dataset for their problem. In this paper we are giving a brief explanation of datasets and applying Software reliability data sets and machine learning techniques for stastical analysis under MINITAB.

Neural Networks And Its Learning Techniques

A neural network is an artificial representation of the human brain that tries to simulate its le... more A neural network is an artificial representation of the human brain that tries to simulate its learning process. An artificial neural network (ANN) is often called a "Neural Network " or simply Neural Net (NN). This paper summarizes the some of the most important developments in neural network and its learning techniques. Learning can be done in supervised or unsupervised training. Our purpose is to provide a synthesis of the published research in this area and stimulate further research interests and efforts in the identified topics.

Neural Networks and Its Learning Techniques

International Conference on Information Engineering, Management and Security 2014, May 18, 2014

A neural network is an artificial representation of the human brain that tries to simulate its le... more A neural network is an artificial representation of the human brain that tries to simulate its learning process. An artificial neural network (ANN) is often called a "Neural Network " or simply Neural Net (NN). This paper summarizes the some of the most important developments in neural network and its learning techniques. Learning can be done in supervised or unsupervised training. Our purpose is to provide a synthesis of the published research in this area and stimulate further research interests and efforts in the identified topics.

A Study on Efficiency of Dynamic Allocation using QOS metrics in High Performance Computing Machines

high performance and Quality Of Service (QOS). Because of its complex runtime environment, with t... more high performance and Quality Of Service (QOS). Because of its complex runtime environment, with these requirements makes such applications extremely challenging. Performance evaluation and prediction of these applications in a computing environment is much difficult task. High performance clusters gains the relevance, as a common place for such computational intensive applications. Such applications typically run on a set of heterogeneous machines with dynamically varying loads. These heterogeneous machines are connected by heterogeneous networks possibly supporting a wide variety of communication protocols. The basic problem in parallel computing is how to execute a parallel program on a collection of heterogeneous processors that is processors with different and possibly changing speeds. Many scheduling algorithms are designed to execute a job efficiently in a parallel computing environment. The goal of this paper is to study on dynamic scheduling methods used for resource allocat...

Download

Hybridization of ACOT and PSO to Predict Software Reliability

IJPAM, 2018

The programs of device learning strategies have shown great upgrades on predicting of software r... more The programs of device learning strategies have shown great upgrades on predicting of
software reliability than conventional statistical strategies. Many authors are carried out some
famous device learning methods consisting of ANN, SVM, Decision Trees, cascade correlation
Neural Network and fuzzy inference system forsoftware product reliability prediction. The
proposed models are evaluated using simply absolute errors, Root Mean Squared
Errors(RMSE), and Normalized Root Mean Squared(NRMSE). To prove the proposed
techniques accuracy, we have taken here 3 software failure dataset for empirical studies. Those
datasets are extracted from Facts and Analysis Centre for Software Program(FACSP). We also
show the comparative analysis in between previous exiting systems with proposed techniques,
using simulator Minitab. Subsequently we conclude that the combination of both ACOT and PSO is giving more accuracy than the individual usage.

Download

Neural Networks And Its Learning Techniques

iciems, 2014

A neural network is an artificial representation of the human brain that tries to simulate its le... more A neural network is an artificial representation of the human brain that tries to simulate its learning process. An artificial neural network (ANN) is often called a "Neural Network " or simply Neural Net (NN). This paper summarizes the some of the most important developments in neural network and its learning techniques. Learning can be done in supervised or unsupervised training. Our purpose is to provide a synthesis of the published research in this area and stimulate further research interests and efforts in the identified topics.

Download

Uploads

Papers by D Shanthi

Log In