Kongu Engineering College

About: Kongu Engineering College is a based out in . It is known for research contribution in the topics: Cluster analysis & Control theory. The organization has 2001 authors who have published 1978 publications receiving 16923 citations.

A proficient heuristic for selecting friends in social Internet of Things

Abstract: Internet of things (IOT) has a large number of smart objects which automatically interacts with each other through various communication protocols. They also cooperate with their neighbors to reach common goals. As the number of devices on the internet increases, the searching for right device which would provide the desired service becomes essential. Social networking concepts are incorporated into Internet of Things called Social Internet of Things (SIOT). Smart objects can find the desired services through its friends in a decentralized manner using only local information. In this work, a heuristic for efficient selection of friends is proposed to improve the overall network navigability. An analysis is also performed based on giant component, local clustering coefficient, average path length and average degree of connections.

Clothing Image Recognition Based on Multiple Features Using Deep Neural Networks

Abstract: For many online customers, clothing image recognition is used mainly in computer vision for fashion applications. Recognition of the clothing image and identification of their style and presentation make the problem difficult for the fashion item. Image recognition technologies allow consumers to scan a picture taken from a fashion magazine or print ad and automatically land on the product page where they can purchase the exact item. Retailers can propose similar looking items in different price ranges with visual search solutions running in the app or website, so the customer can buy a look-alike product at a lower price. The main focus is on classifying the MNIST fashion dataset using multilayer perceptron, convolutional neural network and extreme learning machine. Extracting the F-mnist dataset using these deep neural networks that are most common in computer vision for the implementation of image recognition and even more effective for cloth prediction evaluation. Fashion-MNIS T enhances cultural diversity by attracting more young women students, collectors, artists and designers. Selecting the right deep learning technique for extracting features and choosing the best model of classification remains a major challenge in achieving good quality accuracy. The experimental results, however, show that this Fashion-MNIST dataset has impressive results.

Proposed Design of 1 KB Memory Array Structure for Cache Memories

Abstract: Technology scaling facilitates to meet ever increasing demands for a portable and battery operated systems, at the same time causes diminution of length of the channel, gate oxide layer and threshold voltage which increases the leakage or static power at a standby mode. Static or leakage power is the dominating factor of total power dissipation in deep nanometer technologies below 90 nm. In memory design, parameters such as power, delay and stability of the memory are considered for which affects the performance of the memory. Static random access memory (SRAM) is a type of RAM, which does not need to be refreshed periodically and data is not written permanently in it. This manuscript dedicates in designing 256 × 4 memory array structure using imminent SRAM cell and sense amplifier for usage as cache memories in most modern computer systems. The other sustaining devices in executing this array structure are row decoder, column decoder and control unit. Design metrics such as static power, dynamic power, delay, power delay product, energy, energy delay product, rise time, fall time and slew rate are taken into account. All the circuits were designed using SYNOPSYS EDA tool and simulated in 30 nm technology. Simulation results shows that array structure designed using proposed SRAM cell and sense amplifier provides better performance than existing array structure.

Investigation effect of hydrogen addition on the performance and exhaust emissions of Pongamia pinnata biodiesel fueled compression ignition engine

Abstract: In the recent decades, the energy demand for transport and industrial sector has increased considerably. Fossil fuels which were the major fuel source for decades are no more sustainable. Biodiesel...